From 51a490fa571135ff991c51775c407030ba41e320 Mon Sep 17 00:00:00 2001 From: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com> Date: Tue, 22 Jul 2025 03:09:09 +0000 Subject: [PATCH] Update latest GitHub pages to v1.0.0rc4 --- latest/.buildinfo | 2 +- latest/_cpp_gen/executor.html | 8211 ++++---- latest/_cpp_gen/runtime.html | 17206 ++++++++-------- .../model_engine.py | 2191 ++ .../llm_args.py | 236 +- latest/_modules/index.html | 12 +- latest/_modules/tensorrt_llm/builder.html | 115 +- .../tensorrt_llm/disaggregated_params.html | 16 +- .../tensorrt_llm/executor/result.html | 12 +- .../_modules/tensorrt_llm/executor/utils.html | 12 +- latest/_modules/tensorrt_llm/functional.html | 57 +- .../tensorrt_llm/layers/activation.html | 12 +- .../tensorrt_llm/layers/attention.html | 12 +- latest/_modules/tensorrt_llm/layers/cast.html | 12 +- latest/_modules/tensorrt_llm/layers/conv.html | 12 +- .../tensorrt_llm/layers/embedding.html | 12 +- .../_modules/tensorrt_llm/layers/linear.html | 12 +- latest/_modules/tensorrt_llm/layers/mlp.html | 12 +- .../tensorrt_llm/layers/normalization.html | 12 +- .../_modules/tensorrt_llm/layers/pooling.html | 12 +- .../tensorrt_llm/llmapi/build_cache.html | 12 +- latest/_modules/tensorrt_llm/llmapi/llm.html | 40 +- .../tensorrt_llm/llmapi/llm_args.html | 272 +- .../tensorrt_llm/llmapi/mpi_session.html | 12 +- .../tensorrt_llm/models/baichuan/model.html | 12 +- .../tensorrt_llm/models/bert/model.html | 12 +- .../tensorrt_llm/models/bloom/model.html | 12 +- .../tensorrt_llm/models/chatglm/config.html | 12 +- .../tensorrt_llm/models/chatglm/model.html | 12 +- .../tensorrt_llm/models/clip/model.html | 12 +- .../tensorrt_llm/models/cogvlm/config.html | 12 +- .../tensorrt_llm/models/cogvlm/model.html | 12 +- .../tensorrt_llm/models/commandr/model.html | 12 +- .../tensorrt_llm/models/dbrx/config.html | 12 +- .../tensorrt_llm/models/dbrx/model.html | 12 +- .../models/deepseek_v1/model.html | 12 +- .../models/deepseek_v2/model.html | 12 +- .../tensorrt_llm/models/dit/model.html | 12 +- .../tensorrt_llm/models/eagle/model.html | 12 +- .../tensorrt_llm/models/enc_dec/model.html | 12 +- .../tensorrt_llm/models/falcon/config.html | 12 +- .../tensorrt_llm/models/falcon/model.html | 12 +- .../tensorrt_llm/models/gemma/config.html | 12 +- .../tensorrt_llm/models/gemma/model.html | 12 +- .../tensorrt_llm/models/gpt/config.html | 12 +- .../tensorrt_llm/models/gpt/model.html | 12 +- .../tensorrt_llm/models/gptj/config.html | 12 +- .../tensorrt_llm/models/gptj/model.html | 12 +- .../tensorrt_llm/models/gptneox/model.html | 12 +- .../tensorrt_llm/models/llama/config.html | 12 +- .../tensorrt_llm/models/llama/model.html | 12 +- .../tensorrt_llm/models/mamba/model.html | 12 +- .../tensorrt_llm/models/medusa/config.html | 12 +- .../tensorrt_llm/models/medusa/model.html | 12 +- .../tensorrt_llm/models/mllama/model.html | 12 +- .../tensorrt_llm/models/mmdit_sd3/model.html | 12 +- .../tensorrt_llm/models/modeling_utils.html | 12 +- .../tensorrt_llm/models/mpt/model.html | 12 +- .../models/multimodal_encoders/config.html | 12 +- .../models/multimodal_encoders/model.html | 12 +- .../tensorrt_llm/models/opt/model.html | 12 +- .../tensorrt_llm/models/phi/model.html | 12 +- .../tensorrt_llm/models/phi3/model.html | 12 +- .../models/recurrentgemma/model.html | 12 +- .../tensorrt_llm/models/redrafter/model.html | 12 +- .../_modules/tensorrt_llm/plugin/plugin.html | 12 +- .../tensorrt_llm/quantization/mode.html | 12 +- .../quantization/quantize_by_modelopt.html | 12 +- .../runtime/enc_dec_model_runner.html | 12 +- .../tensorrt_llm/runtime/generation.html | 12 +- .../runtime/kv_cache_manager.html | 12 +- .../tensorrt_llm/runtime/model_runner.html | 12 +- .../runtime/model_runner_cpp.html | 12 +- .../runtime/multimodal_model_runner.html | 16 +- .../tensorrt_llm/runtime/session.html | 12 +- .../tensorrt_llm/sampling_params.html | 12 +- latest/_sources/_cpp_gen/executor.rst.txt | 42 +- latest/_sources/_cpp_gen/runtime.rst.txt | 264 +- .../advanced/disaggregated-service.md.txt | 56 +- .../advanced/speculative-decoding.md.txt | 17 +- ...tice_on_DeepSeek-R1_in_TensorRT-LLM.md.txt | 7 +- ...MTP_Implementation_and_Optimization.md.txt | 6 +- ...Throughput_on_NVIDIA_Blackwell_GPUs.md.txt | 2 +- ..._Expert_Parallelism_in_TensorRT-LLM.md.txt | 3 +- latest/_sources/commands/trtllm-bench.rst.txt | 164 + .../examples/llm_api_examples.rst.txt | 2 + .../examples/llm_guided_decoding.rst.txt | 2 +- latest/_sources/examples/llm_runtime.rst.txt | 8 + latest/_sources/examples/llm_sampling.rst.txt | 8 + latest/_sources/index.rst.txt | 1 + latest/_sources/llm-api/reference.rst.txt | 6 + .../_sources/performance/perf-overview.md.txt | 2 +- latest/_sources/reference/ci-overview.md.txt | 23 +- .../_sources/reference/support-matrix.md.txt | 1 + latest/_sources/torch/arch_overview.md.txt | 2 +- .../feature_combination_matrix.md.txt | 2 +- latest/advanced/disaggregated-service.html | 62 +- latest/advanced/executor.html | 12 +- latest/advanced/expert-parallelism.html | 12 +- latest/advanced/gpt-attention.html | 12 +- latest/advanced/gpt-runtime.html | 12 +- latest/advanced/graph-rewriting.html | 12 +- latest/advanced/kv-cache-management.html | 12 +- latest/advanced/kv-cache-reuse.html | 12 +- latest/advanced/lora.html | 12 +- .../advanced/lowprecision-pcie-allreduce.html | 12 +- .../open-sourced-cutlass-kernels.html | 12 +- latest/advanced/speculative-decoding.html | 43 +- latest/advanced/weight-streaming.html | 12 +- latest/architecture/add-model.html | 12 +- latest/architecture/checkpoint.html | 12 +- latest/architecture/core-concepts.html | 12 +- latest/architecture/model-weights-loader.html | 12 +- latest/architecture/overview.html | 12 +- latest/architecture/workflow.html | 12 +- ...actice_on_DeepSeek-R1_in_TensorRT-LLM.html | 19 +- latest/blogs/Falcon180B-H200.html | 12 +- latest/blogs/H100vsA100.html | 12 +- latest/blogs/H200launch.html | 12 +- latest/blogs/XQA-kernel.html | 12 +- latest/blogs/quantization-in-TRT-LLM.html | 12 +- ...ek-R1_Performance_on_NVIDIA_B200_GPUs.html | 12 +- ...1_MTP_Implementation_and_Optimization.html | 18 +- ...1_Throughput_on_NVIDIA_Blackwell_GPUs.html | 14 +- ...ng_Expert_Parallelism_in_TensorRT-LLM.html | 15 +- ...Disaggregated_Serving_in_TensorRT-LLM.html | 12 +- .../blog6_Llama4_maverick_eagle_guide.html | 12 +- latest/commands/trtllm-bench.html | 1292 ++ latest/commands/trtllm-build.html | 18 +- latest/commands/trtllm-serve.html | 12 +- .../build-image-to-dockerhub.html | 12 +- latest/dev-on-cloud/dev-on-runpod.html | 12 +- latest/examples/curl_chat_client.html | 12 +- .../curl_chat_client_for_multimodal.html | 12 +- latest/examples/curl_completion_client.html | 12 +- latest/examples/customization.html | 12 +- .../deepseek_r1_reasoning_parser.html | 12 +- latest/examples/genai_perf_client.html | 12 +- .../genai_perf_client_for_multimodal.html | 12 +- latest/examples/index.html | 67 +- latest/examples/llm_api_examples.html | 14 +- latest/examples/llm_guided_decoding.html | 87 +- latest/examples/llm_inference.html | 12 +- latest/examples/llm_inference_async.html | 12 +- .../llm_inference_async_streaming.html | 12 +- .../examples/llm_inference_distributed.html | 12 +- latest/examples/llm_logits_processor.html | 12 +- latest/examples/llm_mgmn_llm_distributed.html | 18 +- latest/examples/llm_mgmn_trtllm_bench.html | 12 +- latest/examples/llm_mgmn_trtllm_serve.html | 12 +- latest/examples/llm_multilora.html | 12 +- latest/examples/llm_runtime.html | 744 + latest/examples/llm_sampling.html | 876 + latest/examples/llm_speculative_decoding.html | 18 +- latest/examples/openai_chat_client.html | 12 +- .../openai_chat_client_for_multimodal.html | 12 +- latest/examples/openai_completion_client.html | 12 +- .../openai_completion_client_for_lora.html | 12 +- latest/examples/trtllm_serve_examples.html | 12 +- latest/genindex.html | 564 +- latest/index.html | 14 +- .../installation/build-from-source-linux.html | 12 +- latest/installation/containers.html | 14 +- latest/installation/linux.html | 67 +- latest/key-features.html | 12 +- latest/llm-api/index.html | 12 +- latest/llm-api/reference.html | 477 +- latest/objects.inv | Bin 148460 -> 149941 bytes latest/overview.html | 12 +- latest/performance/perf-analysis.html | 12 +- latest/performance/perf-benchmarking.html | 12 +- latest/performance/perf-overview.html | 14 +- .../benchmarking-default-performance.html | 12 +- .../deciding-model-sharding-strategy.html | 12 +- .../fp8-quantization.html | 12 +- .../performance-tuning-guide/index.html | 12 +- ...ing-max-batch-size-and-max-num-tokens.html | 12 +- .../useful-build-time-flags.html | 12 +- .../useful-runtime-flags.html | 12 +- latest/py-modindex.html | 12 +- .../python-api/tensorrt_llm.functional.html | 18 +- latest/python-api/tensorrt_llm.layers.html | 12 +- latest/python-api/tensorrt_llm.models.html | 12 +- latest/python-api/tensorrt_llm.plugin.html | 12 +- .../python-api/tensorrt_llm.quantization.html | 12 +- latest/python-api/tensorrt_llm.runtime.html | 12 +- latest/quick-start-guide.html | 69 +- latest/reference/ci-overview.html | 35 +- latest/reference/dev-containers.html | 12 +- latest/reference/memory.html | 12 +- latest/reference/precision.html | 12 +- latest/reference/support-matrix.html | 13 +- latest/reference/troubleshooting.html | 12 +- latest/release-notes.html | 12 +- latest/scripts/disaggregated/README.html | 12 +- latest/search.html | 12 +- latest/searchindex.js | 2 +- latest/torch.html | 12 +- latest/torch/adding_new_model.html | 12 +- latest/torch/arch_overview.html | 14 +- latest/torch/attention.html | 12 +- .../features/feature_combination_matrix.html | 18 +- latest/torch/features/overlap_scheduler.html | 12 +- latest/torch/features/quantization.html | 12 +- latest/torch/features/sampling.html | 12 +- latest/torch/kv_cache_manager.html | 12 +- latest/torch/scheduler.html | 12 +- 207 files changed, 21222 insertions(+), 14146 deletions(-) create mode 100644 latest/_downloads/c68095123d889975e6e5e839a4241d22/model_engine.py create mode 100644 latest/_sources/commands/trtllm-bench.rst.txt create mode 100644 latest/_sources/examples/llm_runtime.rst.txt create mode 100644 latest/_sources/examples/llm_sampling.rst.txt create mode 100644 latest/commands/trtllm-bench.html create mode 100644 latest/examples/llm_runtime.html create mode 100644 latest/examples/llm_sampling.html diff --git a/latest/.buildinfo b/latest/.buildinfo index 4d83aad3b8..5278e8fcbc 100644 --- a/latest/.buildinfo +++ b/latest/.buildinfo @@ -1,4 +1,4 @@ # Sphinx build info version 1 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done. -config: ee79abf721be5d1b28815a3912832a13 +config: dab0402c124e392bd849f27a08ca7210 tags: 645f666f9bcd5a90fca523b33c5a78b7 diff --git a/latest/_cpp_gen/executor.html b/latest/_cpp_gen/executor.html index 07cfa3ce9e..a127a24f64 100644 --- a/latest/_cpp_gen/executor.html +++ b/latest/_cpp_gen/executor.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -497,8 +501,8 @@

    Executor#

    -
    -

    disaggServerUtil.h#

    +
    +

    cacheCommunicator.h#

    namespace tensorrt_llm#
    @@ -506,1275 +510,115 @@
    namespace executor#
    -
    -namespace disagg_executor#
    -
    -
    -class DisaggExecutorOrchestrator#
    -
    -

    Public Functions

    -
    -
    -DisaggExecutorOrchestrator( - -
    -
    std::vector<std::filesystem::path> const &ctxEnginePaths,
    -
    std::vector<std::filesystem::path> const &genEnginePaths,
    -
    std::vector<executor::ExecutorConfig> const &ctxExecutorConfigs,
    -
    std::vector<executor::ExecutorConfig> const &genExecutorConfigs,
    -
    bool hasContextAwaitThreads,
    -
    bool hasGenAwaitThreads,
    -
    - -)#
    -

    Constructs a DisaggExecutorOrchestrator object.

    -
    -
    Parameters:
    -
      -

    • ctxEnginePaths – A vector of file paths to context engine files.

      • -

    • genEnginePaths – A vector of file paths to generation engine files.

      • -

    • ctxExecutorConfigs – A vector of ExecutorConfig for context executors.

      • -

    • genExecutorConfigs – A vector of ExecutorConfig for generation executors.

      • -

    • hasContextAwaitThreads – Whether or not there are threads that receive response for each generation executor.

      • -

    • hasGenAwaitThreads – Whether or not there are threads that receive response for each generation executor.

      • -
    -
    -
    -
    - -
    -
    -std::vector<IdType> enqueueContext( - -
    -
    std::vector<texec::Request> const &requests,
    -
    std::optional<int> selectContextId = std::nullopt,
    -
    bool batch = false,
    -
    - -)#
    -

    Enqueue context-only requests to context executors.

    -
    -
    Parameters:
    -
      -

    • requests – A vector of context-only requests.

      • -

    • selectContextId – The index of the context executor to use. If std::nullopt, the executor that has the smallest number of inflight requests will be used.

      • -

    • batch – If true,enqueue requests in same context executor.If false, will try to use a different executor for each request.

      • -
    -
    -
    Returns:
    -

    A vector of global request ids, corresponding to the order of the requests in requests, the id returned may be different from the request id in each executor.

    -
    -
    -
    - -
    -
    -void enqueueGeneration( - -
    -
    std::vector<texec::Request> const &requests,
    -
    std::vector<IdType> const &globalRequestIds,
    -
    std::optional<int> selectGenIdx = std::nullopt,
    -
    bool batch = false,
    -
    - -)#
    -

    Enqueue generation-only requests to generation executors.

    -
    -
    Parameters:
    -
      -

    • requests – A vector of generation-only requests.

      • -

    • globalRequestIds – A vector of global request ids, corresponding to the order of the requests,and must be the ids returned by the enqueueContext function.

      • -

    • selectGenIdx – The index of the generation executor to use. If std::nullopt, the executor that has the smallest number of inflight requests will be used.

      • -

    • batch – If true,enqueue requests in same generation executor.If false, will try to use a different executor for each request.

      • -
    -
    -
    -
    - -
    -
    -std::vector<ResponseWithId> awaitContextResponses( - -
    -
    std::optional<std::chrono::milliseconds> const &timeout,
    -
    std::optional<int> contextIdx = std::nullopt,
    -
    - -)#
    -

    Await for context responses.

    -
    -
    Parameters:
    -
      -

    • timeout – The maximum time to wait for new responses

      • -

    • contextIdx – The index of the context executor to use. If std::nullopt, return ready responses in all context executors,if hasContextAwaitThreads is true, then this parameter must be std::nullopt.

      • -
    -
    -
    Returns:
    -

    A vector of responses with corresponding global request ids

    -
    -
    -
    - -
    -
    -std::vector<ResponseWithId> awaitGenerationResponses( - -
    -
    std::optional<std::chrono::milliseconds> const &timeout,
    -
    std::optional<int> genIdx = std::nullopt,
    -
    - -)#
    -

    Await for generation responses.

    -
    -
    Parameters:
    -
      -

    • timeout – The maximum time to wait for new responses.

      • -

    • genIdx – The index of the generation executor to use. If std::nullopt, return ready responses in all generation executors,if hasGenAwaitThreads is true, then this parameter must be std::nullopt.

      • -
    -
    -
    Returns:
    -

    A vector of responses with corresponding global request ids.

    -
    -
    -
    - -
    -
    -bool canEnqueue() const#
    -

    Indicates if the current process is allowed to enqueueRequests.

    -
    - -
    -
    -std::vector<std::unique_ptr<texec::Executor>> const &getContextExecutors( - -
    -
    - -) const#
    -

    Get context executors.

    -
    - -
    -
    -std::vector<std::unique_ptr<texec::Executor>> const &getGenExecutors( - -
    -
    - -) const#
    -

    Get generation executors.

    -
    - -
    -
    -~DisaggExecutorOrchestrator()#
    -
    - -
    -
    -

    Private Members

    -
    -
    -std::unique_ptr<Impl> mImpl#
    -
    - -
    -
    - -
    -
    -struct ResponseWithId#
    -
    -

    Public Functions

    -
    -
    -inline ResponseWithId( - -
    -
    tensorrt_llm::executor::Response &&response,
    -
    IdType gid,
    -
    - -)#
    -
    - -
    -
    -inline ResponseWithId( - -
    -
    tensorrt_llm::executor::Response const &response,
    -
    IdType gid,
    -
    - -)#
    -
    - -
    -
    -inline ResponseWithId(ResponseWithId &&other) noexcept#
    -
    - -
    -
    -ResponseWithId(ResponseWithId const &other) = default#
    -
    - -
    -
    -inline ResponseWithId &operator=(ResponseWithId &&other) noexcept#
    -
    - -
    -
    -inline ResponseWithId &operator=(ResponseWithId const &other)#
    -
    - -
    -
    -~ResponseWithId() = default#
    -
    - -
    -
    -

    Public Members

    -
    -
    -tensorrt_llm::executor::Response response#
    -
    - -
    -
    -IdType gid#
    -
    - -
    -
    - -
    - -
    - - - -
    -
    -

    tensor.h#

    -
    -
    -namespace tensorrt_llm
    -
    -
    -namespace executor
    -
    -
    -class Shape : public tensorrt_llm::common::ArrayView<detail::DimType64 const>#
    -
    -

    Public Types

    -
    -
    -using Base = tensorrt_llm::common::ArrayView<detail::DimType64 const>#
    -
    - -
    -
    -using DimType64 = typename std::remove_cv_t<Base::value_type>#
    -
    - -
    -
    -

    Public Functions

    -
    -
    -inline Shape()#
    -
    - -
    -
    -inline Shape(DimType64 const *data, Base::size_type size)#
    -
    - -
    -
    -inline Shape(std::initializer_list<DimType64> dims)#
    -
    - -
    -
    - -
    -
    -class Tensor#
    -
    -

    Public Types

    -
    -
    -using CudaStreamPtr = std::shared_ptr<runtime::CudaStream>#
    -
    - -
    -
    -

    Public Functions

    -
    -
    -Tensor copyToCpu(Tensor::CudaStreamPtr stream = nullptr) const#
    -
    - -
    -
    -Tensor copyToPinned(Tensor::CudaStreamPtr stream = nullptr) const#
    -
    - -
    -
    -Tensor copyToPooledPinned(Tensor::CudaStreamPtr stream = nullptr) const#
    -
    - -
    -
    -Tensor copyToManaged(Tensor::CudaStreamPtr stream = nullptr) const#
    -
    - -
    -
    -Tensor copyToGpu(Tensor::CudaStreamPtr stream) const#
    -
    - -
    -
    -Tensor() noexcept = default#
    -
    - -
    -
    -~Tensor() = default#
    -
    - -
    -
    -Tensor(Tensor const &other) noexcept = default#
    -
    - -
    -
    -Tensor(Tensor &&other) noexcept = default#
    -
    - -
    -
    -Tensor &operator=(Tensor const &other) noexcept = default#
    -
    - -
    -
    -Tensor &operator=(Tensor &&other) noexcept = default#
    -
    - -
    -
    -void *getData()#
    -

    Returns a pointer to underlying array.

    -
    - -
    -
    -void const *getData() const#
    -

    Returns a pointer to underlying array.

    -
    - -
    -
    -DataType getDataType() const#
    -

    Returns the data type of the buffer.

    -
    - -
    -
    -MemoryType getMemoryType() const#
    -

    Returns the memory type of the buffer.

    -
    - -
    -
    -Shape getShape() const#
    -

    Returns the tensor dimensions.

    -
    - -
    -
    -std::size_t getSize() const#
    -

    Returns the number of elements in the tensor.

    -
    - -
    -
    -std::size_t getSizeInBytes() const#
    -

    Returns the size of the tensor in bytes.

    -
    - -
    -
    -void setZero(CudaStreamPtr stream = nullptr)#
    -

    Set the entire memory to zero.

    -
    -
    Parameters:
    -

    stream – Must be a valid CUDA stream if the memory type is GPU.

    -
    -
    -
    - -
    -
    -void setFrom(Tensor const &other, CudaStreamPtr stream = nullptr)#
    -

    Copy the data and shape from another tensor.

    -
    -
    Parameters:
    -
      -

    • other – A tensor to copy from.

      • -

    • stream – Must be a valid CUDA stream if the memory type is GPU.

      • -
    -
    -
    -
    - -
    -
    -inline explicit operator bool() const#
    -
    - -
    -
    -inline bool operator==(Tensor const &rhs) const#
    -
    - -
    -
    -inline bool operator!=(Tensor const &rhs) const#
    -
    - -
    -
    -

    Public Static Functions

    -
    -
    -static Tensor cpu(DataType dataType, Shape shape = {})#
    -

    Allocate a cpu tensor with the given shape and data type.

    -
    -
    Parameters:
    -
      -

    • shape – The shape of the tensor.

      • -

    • dataType – The data type of the tensor.

      • -
    -
    -
    -
    - -
    -
    -template<typename T>
    static inline Tensor cpu(Shape shape = {})#
    -
    - -
    -
    -static Tensor pinned(DataType dataType, Shape shape = {})#
    -

    Allocate a cpu tensor in pinned memory with the given shape and data type.

    -
    -
    Parameters:
    -
      -

    • shape – The shape of the tensor.

      • -

    • dataType – The data type of the tensor.

      • -
    -
    -
    -
    - -
    -
    -template<typename T>
    static inline Tensor pinned(Shape shape = {})#
    -
    - -
    -
    -static Tensor pooledPinned(DataType dataType, Shape shape = {})#
    -

    Allocate a cpu tensor in pooled pinned memory with the given shape and data type.

    -
    -
    Parameters:
    -
      -

    • shape – The shape of the tensor.

      • -

    • dataType – The data type of the tensor.

      • -
    -
    -
    -
    - -
    -
    -template<typename T>
    static inline Tensor pooledPinned( - -
    -
    Shape shape = {},
    -
    - -)#
    -
    - -
    -
    -static Tensor managed(DataType dataType, Shape shape = {})#
    -

    Allocate a tensor in managed memory (UVM) with the given shape and data type.

    -
    -
    Parameters:
    -
      -

    • shape – The shape of the tensor.

      • -

    • dataType – The data type of the tensor.

      • -
    -
    -
    -
    - -
    -
    -template<typename T>
    static inline Tensor managed(Shape shape = {})#
    -
    - -
    -
    -static Tensor gpu( - -
    -
    DataType dataType,
    -
    CudaStreamPtr stream,
    -
    Shape shape = {},
    -
    - -)#
    -

    Allocate a gpu tensor with the given shape and data type on a particular cuda stream.

    -
    -
    Parameters:
    -
      -

    • shape – The shape of the tensor.

      • -

    • stream – Specifies the CUDA stream on which to allocate the tensor for GPU memory.

      • -

    • dataType – The data type of the tensor.

      • -
    -
    -
    -
    - -
    -
    -template<typename T>
    static inline Tensor gpu( - -
    -
    CudaStreamPtr stream,
    -
    Shape shape = {},
    -
    - -)#
    -
    - -
    -
    -static Tensor of(DataType dataType, void *data, Shape shape)#
    -

    Wrap a data pointer into a tensor without taking ownership.

    -
    -
    Parameters:
    -
      -

    • shape – The shape of the tensor.

      • -

    • dataType – The data type of the tensor.

      • -

    • stream – Specifies the CUDA stream on which to allocate the tensor for GPU memory.

      • -
    -
    -
    -
    - -
    -
    -template<typename T>
    static inline Tensor of(T *data, Shape shape)#
    -

    Wrap a data pointer into a tensor without taking ownership.

    -
    -
    Parameters:
    -
      -

    • shape – The shape of the tensor.

      • -

    • dataType – The data type of the tensor.

      • -

    • stream – Specifies the CUDA stream on which to allocate the tensor for GPU memory.

      • -
    -
    -
    -
    - -
    -
    -template<typename T>
    static inline Tensor of(T &data)#
    -

    Wrap any container into a tensor without taking ownership.

    -
    -
    Parameters:
    -
      -

    • shape – The shape of the tensor.

      • -

    • dataType – The data type of the tensor.

      • -

    • stream – Specifies the CUDA stream on which to allocate the tensor for GPU memory.

      • -
    -
    -
    -
    - -
    -
    -

    Private Types

    -
    -
    -using Impl = runtime::ITensor#
    -
    - -
    -
    -

    Private Functions

    -
    -
    -explicit Tensor(std::shared_ptr<runtime::ITensor> tensor)#
    -
    - -
    -
    -Tensor copyTo( - -
    -
    std::shared_ptr<Impl> tensor,
    -
    CudaStreamPtr stream,
    -
    - -) const#
    -
    - -
    -
    -

    Private Members

    -
    -
    -std::shared_ptr<Impl> mTensor#
    -
    - -
    -
    -

    Private Static Functions

    -
    -
    -template<typename T>
    static inline DataType getRuntimeType()#
    -
    - -
    -
    -

    Friends

    -
    -
    -friend class Serialization
    -
    - -
    -
    -friend std::shared_ptr<runtime::ITensor> const &toITensor( - -
    -
    Tensor const &tensor,
    -
    - -)#
    -
    - -
    -
    -friend Tensor ofITensor( - -
    -
    std::shared_ptr<runtime::ITensor> tensor,
    -
    - -)#
    -
    - -
    -
    - -
    -
    -namespace detail#
    -
    -

    Typedefs

    -
    -
    -using DimType64 = int64_t#
    -
    - -
    -
    -

    Functions

    -
    -
    -std::shared_ptr<runtime::ITensor> const &toITensor( - -
    -
    Tensor const &tensor,
    -
    - -)#
    -
    - -
    -
    -Tensor ofITensor(std::shared_ptr<runtime::ITensor> tensor)#
    -
    - -
    -
    - -
    - -
    -
    -namespace runtime#
    -
    - -
    - -
    -
    -

    transferAgent.h#

    -
    -
    -namespace tensorrt_llm
    -
    -
    -namespace executor
    -
    namespace kv_cache#
    -
    -

    Typedefs

    -
    -
    -using TransferDescs = MemoryDescs#
    -
    - -
    -
    -using RegisterDescs = MemoryDescs#
    -
    - -
    -
    -using SyncMessage = std::string#
    -
    - -
    -
    -using ConnectionInfoType = std::string#
    -
    - -
    -
    -

    Enums

    -
    -
    -enum class MemoryType : uint8_t#
    -

    Values:

    -
    -
    -enumerator kDRAM#
    -
    - -
    -
    -enumerator kVRAM#
    -
    - -
    -
    -enumerator kBLK#
    -
    - -
    -
    -enumerator kOBJ#
    -
    - -
    -
    -enumerator kFILE#
    -
    - -
    - -
    -
    -enum class TransferOp : uint8_t#
    -

    Values:

    -
    -
    -enumerator kREAD#
    -
    - -
    -
    -enumerator kWRITE#
    -
    - -
    - -
    -
    -

    Functions

    -
    -
    -template<typename ...Args>
    std::unique_ptr<BaseTransferAgent> makeTransferAgent( - -
    -
    std::string const &backend,
    -
    Args&&... args,
    -
    - -)#
    -
    - -
    -
    -
    -class AgentDesc#
    +
    +
    +class Connection#

    Public Functions

    -
    -inline AgentDesc(std::string backendAgentDesc)#
    +
    +virtual ~Connection() = default#
    -
    -inline std::string const &getBackendAgentDesc() const noexcept#
    +
    +virtual void send( + +
    +
    DataContext const &ctx,
    +
    void const *data,
    +
    size_t size,
    +
    + +) const = 0#
    +
    + +
    +
    +virtual void recv( + +
    +
    DataContext const &ctx,
    +
    void *data,
    +
    size_t size,
    +
    + +) const = 0#
    +
    + +
    +
    +inline virtual bool isThreadSafe() const noexcept#
    -
    -

    Private Members

    -
    -
    -std::string mBackendAgentDesc#
    +
    + +
    +
    +class ConnectionManager#
    +
    +

    Public Functions

    +
    +
    +virtual ~ConnectionManager() = default#
    +
    + +
    +
    +virtual Connection const *recvConnect( + +
    +
    DataContext const &ctx,
    +
    void *data,
    +
    size_t size,
    +
    + +) = 0#
    +
    + +
    +
    +virtual std::vector<Connection const*> getConnections( + +
    +
    CommState const &state,
    +
    + +) = 0#
    +
    + +
    +
    +virtual CommState const &getCommState() const = 0#
    -
    -struct BaseAgentConfig#
    -
    -

    Public Members

    -
    -
    -std::string mName#
    -
    - -
    -
    -bool useProgThread#
    -
    - -
    -
    - -
    -
    -class BaseTransferAgent#
    +
    +struct DataContext#

    Public Functions

    -
    -virtual ~BaseTransferAgent() = default#
    +
    +inline explicit DataContext(int tag)#
    -
    -virtual void registerMemory(RegisterDescs const &descs) = 0#
    -
    - -
    -
    -virtual void deregisterMemory(RegisterDescs const &descs) = 0#
    -
    - -
    -
    -virtual void loadRemoteAgent( - -
    -
    std::string const &name,
    -
    AgentDesc const &agentDesc,
    -
    - -) = 0#
    -
    - -
    -
    -virtual AgentDesc getLocalAgentDesc() = 0#
    -
    - -
    -
    -virtual void invalidateRemoteAgent(std::string const &name) = 0#
    -
    - -
    -
    -virtual std::unique_ptr<TransferStatus> submitTransferRequests( - -
    -
    TransferRequest const &request,
    -
    - -) = 0#
    -
    - -
    -
    -virtual void notifySyncMessage( - -
    -
    std::string const &name,
    -
    SyncMessage const &syncMessage,
    -
    - -) = 0#
    -
    - -
    -
    -virtual std::unordered_map<std::string, std::vector<SyncMessage>> getNotifiedSyncMessages( - -
    -
    - -) = 0#
    -
    - -
    -
    -virtual ConnectionInfoType getConnectionInfo() = 0#
    -
    - -
    -
    -virtual void connectRemoteAgent( - -
    -
    std::string const &name,
    -
    ConnectionInfoType const &connectionInfo,
    -
    - -) = 0#
    -
    - -
    -
    -virtual bool checkRemoteDescs( - -
    -
    std::string const &name,
    -
    MemoryDescs const &memoryDescs,
    -
    - -) = 0#
    -
    - -
    -
    - -
    -
    -class DynLibLoader#
    -
    -

    Public Functions

    -
    -
    -void *getHandle(std::string const &name)#
    -
    - -
    -
    -template<typename FunctionT>
    inline FunctionT getFunctionPointer( - -
    -
    std::string const &libName,
    -
    std::string const &funcName,
    -
    - -)#
    -
    - -
    -
    -~DynLibLoader()#
    -
    - -
    -
    -DynLibLoader() = default#
    -
    - -
    -
    -DynLibLoader(DynLibLoader const&) = delete#
    -
    - -
    -
    -DynLibLoader &operator=(DynLibLoader const&) = delete#
    -
    - -
    -
    -

    Public Static Functions

    -
    -
    -static DynLibLoader &getInstance()#
    +
    +inline int getTag() const noexcept#

    Private Members

    -
    -std::mutex mDllMutex#
    -
    - -
    -
    -std::unordered_map<std::string, void*> mHandlers#
    -
    - -
    -
    -

    Private Static Functions

    -
    -
    -static void *dlSym(void *handle, char const *symbol)#
    -
    - -
    -
    - -
    -
    -class MemoryDesc#
    -
    -

    Public Functions

    -
    -
    -inline MemoryDesc( - -
    -
    std::vector<char> const &vec,
    -
    uint32_t deviceId = 0,
    -
    - -)#
    -
    - -
    -
    -inline MemoryDesc(void *addr, size_t len, uint32_t deviceId)#
    -
    - -
    -
    -inline MemoryDesc(uintptr_t addr, size_t len, uint32_t deviceId)#
    -
    - -
    -
    -inline uintptr_t getAddr() const noexcept#
    -
    - -
    -
    -inline size_t getLen() const noexcept#
    -
    - -
    -
    -inline uint32_t getDeviceId() const noexcept#
    -
    - -
    -
    -

    Public Static Functions

    -
    -
    -static void serialize(MemoryDesc const &memoryDesc, std::ostream &os)#
    -
    - -
    -
    -static MemoryDesc deserialize(std::istream &is)#
    -
    - -
    -
    -static size_t serializedSize(MemoryDesc const &memoryDesc)#
    -
    - -
    -
    -

    Private Members

    -
    -
    -uintptr_t mAddr#
    -
    - -
    -
    -size_t mLen#
    -
    - -
    -
    -uint32_t mDeviceId#
    -
    - -
    -
    - -
    -
    -class MemoryDescs#
    -
    -

    Public Functions

    -
    -
    -inline MemoryDescs(MemoryType type, std::vector<MemoryDesc> descs)#
    -
    - -
    -
    -inline MemoryType getType() const noexcept#
    -
    - -
    -
    -inline std::vector<MemoryDesc> const &getDescs() const noexcept#
    -
    - -
    -
    -

    Private Members

    -
    -
    -MemoryType mType#
    -
    - -
    -
    -std::vector<MemoryDesc> mDescs#
    -
    - -
    -
    - -
    -
    -class TransferRequest#
    -
    -

    Public Functions

    -
    -
    -inline TransferRequest( - -
    -
    TransferOp op,
    -
    TransferDescs srcDescs,
    -
    TransferDescs dstDescs,
    -
    std::string const &remoteName,
    -
    std::optional<SyncMessage> syncMessage = std::nullopt,
    -
    - -)#
    -
    - -
    -
    -inline TransferOp getOp() const noexcept#
    -
    - -
    -
    -inline TransferDescs const &getSrcDescs() const noexcept#
    -
    - -
    -
    -inline TransferDescs const &getDstDescs() const noexcept#
    -
    - -
    -
    -inline std::string const &getRemoteName() const noexcept#
    -
    - -
    -
    -inline std::optional<SyncMessage> getSyncMessage() const noexcept#
    -
    - -
    -
    -

    Private Members

    -
    -
    -TransferOp mOp#
    -
    - -
    -
    -TransferDescs mSrcDescs#
    -
    - -
    -
    -TransferDescs mDstDescs#
    -
    - -
    -
    -std::string mRemoteName#
    -
    - -
    -
    -std::optional<SyncMessage> mSyncMessage#
    -
    - -
    -
    - -
    -
    -class TransferStatus#
    -
    -

    Public Functions

    -
    -
    -virtual ~TransferStatus() = default#
    -
    - -
    -
    -virtual bool isCompleted() const = 0#
    -
    - -
    -
    -virtual void wait() const = 0#
    +
    +int const mTag#
    @@ -3243,1741 +2087,1862 @@
    -
    -

    types.h#

    +
    +

    disaggServerUtil.h#

    namespace tensorrt_llm
    namespace executor
    +
    +
    +namespace disagg_executor#
    +
    +
    +class DisaggExecutorOrchestrator#
    +
    +

    Public Functions

    +
    +
    +DisaggExecutorOrchestrator( + +
    +
    std::vector<std::filesystem::path> const &ctxEnginePaths,
    +
    std::vector<std::filesystem::path> const &genEnginePaths,
    +
    std::vector<executor::ExecutorConfig> const &ctxExecutorConfigs,
    +
    std::vector<executor::ExecutorConfig> const &genExecutorConfigs,
    +
    bool hasContextAwaitThreads,
    +
    bool hasGenAwaitThreads,
    +
    + +)#
    +

    Constructs a DisaggExecutorOrchestrator object.

    +
    +
    Parameters:
    +
      +

    • ctxEnginePaths – A vector of file paths to context engine files.

      • +

    • genEnginePaths – A vector of file paths to generation engine files.

      • +

    • ctxExecutorConfigs – A vector of ExecutorConfig for context executors.

      • +

    • genExecutorConfigs – A vector of ExecutorConfig for generation executors.

      • +

    • hasContextAwaitThreads – Whether or not there are threads that receive response for each generation executor.

      • +

    • hasGenAwaitThreads – Whether or not there are threads that receive response for each generation executor.

      • +
    +
    +
    +
    + +
    +
    +std::vector<IdType> enqueueContext( + +
    +
    std::vector<texec::Request> const &requests,
    +
    std::optional<int> selectContextId = std::nullopt,
    +
    bool batch = false,
    +
    + +)#
    +

    Enqueue context-only requests to context executors.

    +
    +
    Parameters:
    +
      +

    • requests – A vector of context-only requests.

      • +

    • selectContextId – The index of the context executor to use. If std::nullopt, the executor that has the smallest number of inflight requests will be used.

      • +

    • batch – If true,enqueue requests in same context executor.If false, will try to use a different executor for each request.

      • +
    +
    +
    Returns:
    +

    A vector of global request ids, corresponding to the order of the requests in requests, the id returned may be different from the request id in each executor.

    +
    +
    +
    + +
    +
    +void enqueueGeneration( + +
    +
    std::vector<texec::Request> const &requests,
    +
    std::vector<IdType> const &globalRequestIds,
    +
    std::optional<int> selectGenIdx = std::nullopt,
    +
    bool batch = false,
    +
    + +)#
    +

    Enqueue generation-only requests to generation executors.

    +
    +
    Parameters:
    +
      +

    • requests – A vector of generation-only requests.

      • +

    • globalRequestIds – A vector of global request ids, corresponding to the order of the requests,and must be the ids returned by the enqueueContext function.

      • +

    • selectGenIdx – The index of the generation executor to use. If std::nullopt, the executor that has the smallest number of inflight requests will be used.

      • +

    • batch – If true,enqueue requests in same generation executor.If false, will try to use a different executor for each request.

      • +
    +
    +
    +
    + +
    +
    +std::vector<ResponseWithId> awaitContextResponses( + +
    +
    std::optional<std::chrono::milliseconds> const &timeout,
    +
    std::optional<int> contextIdx = std::nullopt,
    +
    + +)#
    +

    Await for context responses.

    +
    +
    Parameters:
    +
      +

    • timeout – The maximum time to wait for new responses

      • +

    • contextIdx – The index of the context executor to use. If std::nullopt, return ready responses in all context executors,if hasContextAwaitThreads is true, then this parameter must be std::nullopt.

      • +
    +
    +
    Returns:
    +

    A vector of responses with corresponding global request ids

    +
    +
    +
    + +
    +
    +std::vector<ResponseWithId> awaitGenerationResponses( + +
    +
    std::optional<std::chrono::milliseconds> const &timeout,
    +
    std::optional<int> genIdx = std::nullopt,
    +
    + +)#
    +

    Await for generation responses.

    +
    +
    Parameters:
    +
      +

    • timeout – The maximum time to wait for new responses.

      • +

    • genIdx – The index of the generation executor to use. If std::nullopt, return ready responses in all generation executors,if hasGenAwaitThreads is true, then this parameter must be std::nullopt.

      • +
    +
    +
    Returns:
    +

    A vector of responses with corresponding global request ids.

    +
    +
    +
    + +
    +
    +bool canEnqueue() const#
    +

    Indicates if the current process is allowed to enqueueRequests.

    +
    + +
    +
    +std::vector<std::unique_ptr<texec::Executor>> const &getContextExecutors( + +
    +
    + +) const#
    +

    Get context executors.

    +
    + +
    +
    +std::vector<std::unique_ptr<texec::Executor>> const &getGenExecutors( + +
    +
    + +) const#
    +

    Get generation executors.

    +
    + +
    +
    +~DisaggExecutorOrchestrator()#
    +
    + +
    +
    +

    Private Members

    +
    +
    +std::unique_ptr<Impl> mImpl#
    +
    + +
    +
    + +
    +
    +struct ResponseWithId#
    +
    +

    Public Functions

    +
    +
    +inline ResponseWithId( + +
    +
    tensorrt_llm::executor::Response &&response,
    +
    IdType gid,
    +
    + +)#
    +
    + +
    +
    +inline ResponseWithId( + +
    +
    tensorrt_llm::executor::Response const &response,
    +
    IdType gid,
    +
    + +)#
    +
    + +
    +
    +inline ResponseWithId(ResponseWithId &&other) noexcept#
    +
    + +
    +
    +ResponseWithId(ResponseWithId const &other) = default#
    +
    + +
    +
    +inline ResponseWithId &operator=(ResponseWithId &&other) noexcept#
    +
    + +
    +
    +inline ResponseWithId &operator=(ResponseWithId const &other)#
    +
    + +
    +
    +~ResponseWithId() = default#
    +
    + +
    +
    +

    Public Members

    +
    +
    +tensorrt_llm::executor::Response response#
    +
    + +
    +
    +IdType gid#
    +
    + +
    +
    + +
    + +
    + +
    + +
    +
    +

    dataTransceiverState.h#

    +
    +
    +namespace tensorrt_llm
    +
    +
    +namespace executor
    +
    +
    +class DataTransceiverState#
    +
    +

    Public Functions

    +
    +
    +DataTransceiverState() = default#
    +
    + +
    +
    +inline DataTransceiverState( + +
    +
    kv_cache::CacheState cacheState,
    +
    kv_cache::CommState commState,
    +
    + +)#
    +
    + +
    +
    +inline void setCacheState(kv_cache::CacheState state)#
    +
    + +
    +
    +inline std::optional<kv_cache::CacheState> const &getCacheState( + +
    +
    + +) const noexcept#
    +
    + +
    +
    +inline void setCommState(kv_cache::CommState state)#
    +
    + +
    +
    +inline std::optional<kv_cache::CommState> const &getCommState( + +
    +
    + +) const noexcept#
    +
    + +
    +
    +inline bool operator==( + +
    +
    DataTransceiverState const &other,
    +
    + +) const noexcept#
    +
    + +
    +
    +inline std::string toString() const#
    +
    + +
    +
    +

    Private Members

    +
    +
    +std::optional<kv_cache::CacheState> mCacheState#
    +
    + +
    +
    +std::optional<kv_cache::CommState> mCommState#
    +
    + +
    +
    +

    Friends

    +
    +
    +friend class Serialization
    +
    + +
    +
    + +
    +
    +namespace kv_cache
    +
    +
    +struct AgentState#
    +
    +

    Public Functions

    +
    +
    +inline AgentState(std::string agentName, std::string connectionInfo)#
    +
    + +
    +
    +AgentState() = default#
    +
    + +
    +
    +inline bool operator==(AgentState const &other) const noexcept#
    +
    + +
    +
    +inline std::string toString() const#
    +
    + +
    +
    +

    Public Members

    +
    +
    +std::string mAgentName#
    +
    + +
    +
    +std::string mConnectionInfo#
    +
    + +
    +
    + +
    +
    +class CacheState#
    +
    +

    Public Types

    +
    +
    +enum class AttentionType : std::uint8_t#
    +

    Values:

    +
    +
    +enumerator kDEFAULT#
    +
    + +
    +
    +enumerator kMLA#
    +
    + +
    + +
    +
    +

    Public Functions

    +
    +
    +inline CacheState( + +
    +
    ModelConfig modelConfig,
    +
    runtime::WorldConfig const &worldConfig,
    +
    nvinfer1::DataType dataType,
    +
    AttentionType attentionType = AttentionType::kDEFAULT,
    +
    int kvFactor = 2,
    +
    + +)#
    +
    + +
    +
    +inline CacheState( + +
    +
    std::vector<SizeType32> nbKvHeadPerLayer,
    +
    SizeType32 sizePerHead,
    +
    SizeType32 tokensPerBlock,
    +
    SizeType32 tensorParallelism,
    +
    SizeType32 pipelineParallelism,
    +
    nvinfer1::DataType dataType,
    +
    AttentionType attentionType = AttentionType::kDEFAULT,
    +
    int kvFactor = 2,
    +
    bool enableAttentionDP = false,
    +
    int DPrank = 0,
    +
    int DPsize = 0,
    +
    + +)#
    +
    + +
    +
    +inline CacheState( + +
    +
    SizeType32 nbAttentionLayers,
    +
    SizeType32 nbKvHeads,
    +
    SizeType32 sizePerHead,
    +
    SizeType32 tokensPerBlock,
    +
    SizeType32 tensorParallelism,
    +
    SizeType32 pipelineParallelism,
    +
    nvinfer1::DataType dataType,
    +
    AttentionType attentionType = AttentionType::kDEFAULT,
    +
    int kvFactor = 2,
    +
    bool enableAttentionDP = false,
    +
    int DPrank = 0,
    +
    int DPsize = 0,
    +
    + +)#
    +
    + +
    +
    +inline bool operator==( + +
    +
    kv_cache::CacheState const &other,
    +
    + +) const noexcept#
    +
    + +
    +
    +inline ModelConfig const &getModelConfig() const#
    +
    + +
    +
    +inline ParallelConfig const &getParallelConfig() const#
    +
    + +
    +
    +inline AttentionConfig const &getAttentionConfig() const#
    +
    + +
    +
    +inline nvinfer1::DataType const &getDataType() const#
    +
    + +
    +
    +inline std::string toString() const#
    +
    + +
    +
    +

    Private Members

    +
    +
    +ModelConfig mModelConfig#
    +
    + +
    +
    +ParallelConfig mParallelConfig#
    +
    + +
    +
    +nvinfer1::DataType mDataType#
    +
    + +
    +
    +AttentionConfig mAttentionConfig#
    +
    + +
    +
    +

    Friends

    +
    +
    +friend class tensorrt_llm::executor::Serialization
    +
    + +
    +
    +
    +struct AttentionConfig#
    +
    +

    Public Functions

    +
    +
    +inline AttentionConfig(AttentionType attentionType, int kvFactor)#
    +
    + +
    +
    +

    Public Members

    +
    +
    +AttentionType mAttentionType#
    +
    + +
    +
    +int mKvFactor#
    +
    + +
    +
    + +
    +
    +struct ModelConfig#
    +
    +

    Public Functions

    +
    +
    +inline bool operator==(ModelConfig const &other) const noexcept#
    +
    + +
    +
    +

    Public Members

    +
    +
    +std::vector<SizeType32> mNbKvHeadsPerLayer#
    +
    + +
    +
    +SizeType32 mSizePerHead#
    +
    + +
    +
    +SizeType32 mTokensPerBlock#
    +
    + +
    +
    + +
    +
    +struct ParallelConfig#
    +
    +

    Public Functions

    +
    +
    +inline bool operator==(ParallelConfig const &other) const noexcept#
    +
    + +
    +
    +

    Public Members

    +
    +
    +SizeType32 mTensorParallelism#
    +
    + +
    +
    +SizeType32 mPipelineParallelism#
    +
    + +
    +
    +bool mEnableAttentionDP#
    +
    + +
    +
    +SizeType32 mDPrank#
    +
    + +
    +
    +SizeType32 mDPsize#
    +
    + +
    +
    + +
    + +
    +
    +class CommState#
    +
    +

    Public Functions

    +
    +
    +CommState() = default#
    +
    + +
    +
    +inline explicit CommState( + +
    +
    std::vector<SizeType32> ranks,
    +
    int selfIdx = -1,
    +
    + +)#
    +
    + +
    +
    +inline explicit CommState( + +
    +
    std::vector<SocketState> socketState,
    +
    int selfIdx = -1,
    +
    + +)#
    +
    + +
    +
    +inline CommState(std::uint16_t port, std::string ip)#
    +
    + +
    +
    +inline explicit CommState( + +
    +
    std::vector<AgentState> agentState,
    +
    int selfIdx = -1,
    +
    + +)#
    +
    + +
    +
    +inline bool isMpiState() const noexcept#
    +
    + +
    +
    +inline bool isSocketState() const noexcept#
    +
    + +
    +
    +inline bool isAgentState() const noexcept#
    +
    + +
    +
    +inline MpiState const &getMpiState() const#
    +
    + +
    +
    +inline std::vector<SocketState> const &getSocketState() const#
    +
    + +
    +
    +inline std::vector<AgentState> const &getAgentState() const#
    +
    + +
    +
    +inline int getSelfIdx() const noexcept#
    +
    + +
    +
    +inline bool operator==(CommState const &other) const noexcept#
    +
    + +
    +
    +inline std::string toString() const#
    +
    + +
    +
    +

    Private Members

    +
    +
    +std::variant<std::monostate, MpiState, std::vector<SocketState>, std::vector<AgentState>> mState#
    +
    + +
    +
    +int mSelfIdx = {-1}#
    +
    + +
    +
    +

    Friends

    +
    +
    +friend class tensorrt_llm::executor::Serialization
    +
    + +
    +
    + +
    +
    +struct MpiState#
    +
    +

    Public Functions

    +
    +
    +inline bool operator==(MpiState const &other) const noexcept#
    +
    + +
    +
    +inline std::string toString() const#
    +
    + +
    +
    +

    Public Members

    +
    +
    +std::vector<SizeType32> mRanks#
    +
    + +
    +
    + +
    +
    +struct SocketState#
    +
    +

    Public Functions

    +
    +
    +inline bool operator==(SocketState const &other) const noexcept#
    +
    + +
    +
    +inline std::string toString() const#
    +
    + +
    +
    +

    Public Members

    +
    +
    +std::uint16_t mPort#
    +
    + +
    +
    +std::string mIp#
    +
    + +
    +
    + +
    + +
    + +
    + +
    +
    +

    tensor.h#

    +
    +
    +namespace tensorrt_llm
    +
    +
    +namespace executor
    +
    +
    +class Shape : public tensorrt_llm::common::ArrayView<detail::DimType64 const>#
    +
    +

    Public Types

    +
    +
    +using Base = tensorrt_llm::common::ArrayView<detail::DimType64 const>#
    +
    + +
    +
    +using DimType64 = typename std::remove_cv_t<Base::value_type>#
    +
    + +
    +
    +

    Public Functions

    +
    +
    +inline Shape()#
    +
    + +
    +
    +inline Shape(DimType64 const *data, Base::size_type size)#
    +
    + +
    +
    +inline Shape(std::initializer_list<DimType64> dims)#
    +
    + +
    +
    + +
    +
    +class Tensor#
    +
    +

    Public Types

    +
    +
    +using CudaStreamPtr = std::shared_ptr<runtime::CudaStream>#
    +
    + +
    +
    +

    Public Functions

    +
    +
    +Tensor copyToCpu(Tensor::CudaStreamPtr stream = nullptr) const#
    +
    + +
    +
    +Tensor copyToPinned(Tensor::CudaStreamPtr stream = nullptr) const#
    +
    + +
    +
    +Tensor copyToPooledPinned(Tensor::CudaStreamPtr stream = nullptr) const#
    +
    + +
    +
    +Tensor copyToManaged(Tensor::CudaStreamPtr stream = nullptr) const#
    +
    + +
    +
    +Tensor copyToGpu(Tensor::CudaStreamPtr stream) const#
    +
    + +
    +
    +Tensor() noexcept = default#
    +
    + +
    +
    +~Tensor() = default#
    +
    + +
    +
    +Tensor(Tensor const &other) noexcept = default#
    +
    + +
    +
    +Tensor(Tensor &&other) noexcept = default#
    +
    + +
    +
    +Tensor &operator=(Tensor const &other) noexcept = default#
    +
    + +
    +
    +Tensor &operator=(Tensor &&other) noexcept = default#
    +
    + +
    +
    +void *getData()#
    +

    Returns a pointer to underlying array.

    +
    + +
    +
    +void const *getData() const#
    +

    Returns a pointer to underlying array.

    +
    + +
    +
    +DataType getDataType() const#
    +

    Returns the data type of the buffer.

    +
    + +
    +
    +MemoryType getMemoryType() const#
    +

    Returns the memory type of the buffer.

    +
    + +
    +
    +Shape getShape() const#
    +

    Returns the tensor dimensions.

    +
    + +
    +
    +std::size_t getSize() const#
    +

    Returns the number of elements in the tensor.

    +
    + +
    +
    +std::size_t getSizeInBytes() const#
    +

    Returns the size of the tensor in bytes.

    +
    + +
    +
    +void setZero(CudaStreamPtr stream = nullptr)#
    +

    Set the entire memory to zero.

    +
    +
    Parameters:
    +

    stream – Must be a valid CUDA stream if the memory type is GPU.

    +
    +
    +
    + +
    +
    +void setFrom(Tensor const &other, CudaStreamPtr stream = nullptr)#
    +

    Copy the data and shape from another tensor.

    +
    +
    Parameters:
    +
      +

    • other – A tensor to copy from.

      • +

    • stream – Must be a valid CUDA stream if the memory type is GPU.

      • +
    +
    +
    +
    + +
    +
    +inline explicit operator bool() const#
    +
    + +
    +
    +inline bool operator==(Tensor const &rhs) const#
    +
    + +
    +
    +inline bool operator!=(Tensor const &rhs) const#
    +
    + +
    +
    +

    Public Static Functions

    +
    +
    +static Tensor cpu(DataType dataType, Shape shape = {})#
    +

    Allocate a cpu tensor with the given shape and data type.

    +
    +
    Parameters:
    +
      +

    • shape – The shape of the tensor.

      • +

    • dataType – The data type of the tensor.

      • +
    +
    +
    +
    + +
    +
    +template<typename T>
    static inline Tensor cpu(Shape shape = {})#
    +
    + +
    +
    +static Tensor pinned(DataType dataType, Shape shape = {})#
    +

    Allocate a cpu tensor in pinned memory with the given shape and data type.

    +
    +
    Parameters:
    +
      +

    • shape – The shape of the tensor.

      • +

    • dataType – The data type of the tensor.

      • +
    +
    +
    +
    + +
    +
    +template<typename T>
    static inline Tensor pinned(Shape shape = {})#
    +
    + +
    +
    +static Tensor pooledPinned(DataType dataType, Shape shape = {})#
    +

    Allocate a cpu tensor in pooled pinned memory with the given shape and data type.

    +
    +
    Parameters:
    +
      +

    • shape – The shape of the tensor.

      • +

    • dataType – The data type of the tensor.

      • +
    +
    +
    +
    + +
    +
    +template<typename T>
    static inline Tensor pooledPinned( + +
    +
    Shape shape = {},
    +
    + +)#
    +
    + +
    +
    +static Tensor managed(DataType dataType, Shape shape = {})#
    +

    Allocate a tensor in managed memory (UVM) with the given shape and data type.

    +
    +
    Parameters:
    +
      +

    • shape – The shape of the tensor.

      • +

    • dataType – The data type of the tensor.

      • +
    +
    +
    +
    + +
    +
    +template<typename T>
    static inline Tensor managed(Shape shape = {})#
    +
    + +
    +
    +static Tensor gpu( + +
    +
    DataType dataType,
    +
    CudaStreamPtr stream,
    +
    Shape shape = {},
    +
    + +)#
    +

    Allocate a gpu tensor with the given shape and data type on a particular cuda stream.

    +
    +
    Parameters:
    +
      +

    • shape – The shape of the tensor.

      • +

    • stream – Specifies the CUDA stream on which to allocate the tensor for GPU memory.

      • +

    • dataType – The data type of the tensor.

      • +
    +
    +
    +
    + +
    +
    +template<typename T>
    static inline Tensor gpu( + +
    +
    CudaStreamPtr stream,
    +
    Shape shape = {},
    +
    + +)#
    +
    + +
    +
    +static Tensor of(DataType dataType, void *data, Shape shape)#
    +

    Wrap a data pointer into a tensor without taking ownership.

    +
    +
    Parameters:
    +
      +

    • shape – The shape of the tensor.

      • +

    • dataType – The data type of the tensor.

      • +

    • stream – Specifies the CUDA stream on which to allocate the tensor for GPU memory.

      • +
    +
    +
    +
    + +
    +
    +template<typename T>
    static inline Tensor of(T *data, Shape shape)#
    +

    Wrap a data pointer into a tensor without taking ownership.

    +
    +
    Parameters:
    +
      +

    • shape – The shape of the tensor.

      • +

    • dataType – The data type of the tensor.

      • +

    • stream – Specifies the CUDA stream on which to allocate the tensor for GPU memory.

      • +
    +
    +
    +
    + +
    +
    +template<typename T>
    static inline Tensor of(T &data)#
    +

    Wrap any container into a tensor without taking ownership.

    +
    +
    Parameters:
    +
      +

    • shape – The shape of the tensor.

      • +

    • dataType – The data type of the tensor.

      • +

    • stream – Specifies the CUDA stream on which to allocate the tensor for GPU memory.

      • +
    +
    +
    +
    + +
    +
    +

    Private Types

    +
    +
    +using Impl = runtime::ITensor#
    +
    + +
    +
    +

    Private Functions

    +
    +
    +explicit Tensor(std::shared_ptr<runtime::ITensor> tensor)#
    +
    + +
    +
    +Tensor copyTo( + +
    +
    std::shared_ptr<Impl> tensor,
    +
    CudaStreamPtr stream,
    +
    + +) const#
    +
    + +
    +
    +

    Private Members

    +
    +
    +std::shared_ptr<Impl> mTensor#
    +
    + +
    +
    +

    Private Static Functions

    +
    +
    +template<typename T>
    static inline DataType getRuntimeType()#
    +
    + +
    +
    +

    Friends

    +
    +
    +friend class Serialization
    +
    + +
    +
    +friend std::shared_ptr<runtime::ITensor> const &toITensor( + +
    +
    Tensor const &tensor,
    +
    + +)#
    +
    + +
    +
    +friend Tensor ofITensor( + +
    +
    std::shared_ptr<runtime::ITensor> tensor,
    +
    + +)#
    +
    + +
    +
    + +
    +
    +namespace detail#

    Typedefs

    -
    -using TensorPtr = std::shared_ptr<Tensor>#
    +
    +using DimType64 = int64_t#
    +
    + +
    +
    +

    Functions

    +
    +
    +std::shared_ptr<runtime::ITensor> const &toITensor( + +
    +
    Tensor const &tensor,
    +
    + +)#
    +
    + +
    +
    +Tensor ofITensor(std::shared_ptr<runtime::ITensor> tensor)#
    +
    + +
    +
    + +
    + +
    +
    +namespace runtime#
    +
    + +
    + +
    +
    +

    transferAgent.h#

    +
    +
    +namespace tensorrt_llm
    +
    +
    +namespace executor
    +
    +
    +namespace kv_cache
    +
    +

    Typedefs

    +
    +
    +using TransferDescs = MemoryDescs#
    -
    -using SizeType32 = std::int32_t#
    +
    +using RegisterDescs = MemoryDescs#
    -
    -using SizeType64 = std::int64_t#
    +
    +using SyncMessage = std::string#
    -
    -using FloatType = float#
    -
    - -
    -
    -using TokenIdType = std::int32_t#
    -
    - -
    -
    -using VecTokens = std::vector<TokenIdType>#
    -
    - -
    -
    -using BeamTokens = std::vector<VecTokens>#
    -
    - -
    -
    -using IdType = std::uint64_t#
    -
    - -
    -
    -using VecTokenExtraIds = std::vector<IdType>#
    -
    - -
    -
    -using IterationType = std::uint64_t#
    -
    - -
    -
    -using RandomSeedType = std::uint64_t#
    -
    - -
    -
    -using VecLogProbs = std::vector<FloatType>#
    -
    - -
    -
    -using StreamPtr = std::shared_ptr<tensorrt_llm::runtime::CudaStream>#
    -
    - -
    -
    -using MillisecondsType = std::chrono::milliseconds#
    -
    - -
    -
    -using LogitsPostProcessor = std::function<void(IdType, Tensor&, BeamTokens const&, StreamPtr const&, std::optional<IdType>)>#
    -
    - -
    -
    -using LogitsPostProcessorMap = std::unordered_map<std::string, LogitsPostProcessor>#
    -
    - -
    -
    -using LogitsPostProcessorBatched = std::function<void(std::vector<IdType> const&, std::vector<Tensor>&, std::vector<std::reference_wrapper<BeamTokens const>> const&, StreamPtr const&, std::vector<std::optional<IdType>> const&)>#
    -
    - -
    -
    -using MedusaChoices = std::vector<std::vector<SizeType32>>#
    -
    - -
    -
    -using EagleChoices = std::vector<std::vector<SizeType32>>#
    -
    - -
    -
    -using PriorityType = float#
    -
    - -
    -
    -using BufferView = std::basic_string_view<uint8_t>#
    +
    +using ConnectionInfoType = std::string#

    Enums

    -
    -enum class DataType#
    +
    +enum class MemoryType : uint8_t#

    Values:

    -
    -enumerator kBOOL#
    +
    +enumerator kDRAM#
    -
    -enumerator kUINT8#
    +
    +enumerator kVRAM#
    -
    -enumerator kINT8#
    +
    +enumerator kBLK#
    -
    -enumerator kINT32#
    +
    +enumerator kOBJ#
    -
    -enumerator kINT64#
    -
    - -
    -
    -enumerator kBF16#
    -
    - -
    -
    -enumerator kFP8#
    -
    - -
    -
    -enumerator kFP16#
    -
    - -
    -
    -enumerator kFP32#
    -
    - -
    -
    -enumerator kUNKNOWN#
    +
    +enumerator kFILE#
    -
    -enum class RequestType#
    +
    +enum class TransferOp : uint8_t#

    Values:

    -
    -enumerator REQUEST_TYPE_CONTEXT_AND_GENERATION#
    +
    +enumerator kREAD#
    -
    -enumerator REQUEST_TYPE_CONTEXT_ONLY#
    +
    +enumerator kWRITE#
    -
    -
    -enumerator REQUEST_TYPE_GENERATION_ONLY#
    -
    - -
    - -
    -
    -enum class MemoryType#
    -

    Values:

    -
    -
    -enumerator kCPU#
    -
    - -
    -
    -enumerator kCPU_PINNED#
    -
    - -
    -
    -enumerator kCPU_PINNEDPOOL#
    -
    - -
    -
    -enumerator kGPU#
    -
    - -
    -
    -enumerator kUVM#
    -
    - -
    -
    -enumerator kUNKNOWN#
    -
    - -
    - -
    -
    -enum class ModelType#
    -

    Values:

    -
    -
    -enumerator kDECODER_ONLY#
    -
    - -
    -
    -enumerator kENCODER_ONLY#
    -
    - -
    -
    -enumerator kENCODER_DECODER#
    -
    - -
    - -
    -
    -enum class BatchingType#
    -

    The batching type.

    -

    Values:

    -
    -
    -enumerator kSTATIC#
    -

    STATIC refers to the traditional batching scheme with a batch of requests running in lockstep until the full generation for all of them is complete. Requests in a batch are all padded up to the maximum input and output sequence length of any member of the batch.

    -
    - -
    -
    -enumerator kINFLIGHT#
    -

    INFLIGHT refers to a scheme where newly arrived requests are dynamically incorporated into the batch under execution, and requests are returned as soon as the end condition is met without any padding.

    -
    - -
    - -
    -
    -enum class CapacitySchedulerPolicy#
    -

    The policy used to select the subset of available requests in each iteration of the executor generation loop.

    -

    Values:

    -
    -
    -enumerator kMAX_UTILIZATION#
    -

    MAX_UTILIZATION packs as many requests as the underlying TRT engine can support in any iteration of the InflightBatching generation loop. While this is expected to maximize GPU throughput, it might require that some requests be paused and restarted depending on peak KV cache memory availability.

    -
    - -
    -
    -enumerator kGUARANTEED_NO_EVICT#
    -

    GUARANTEED_NO_EVICT uses KV cache more conservatively guaranteeing that a request, once started, will run to completion without eviction.

    -
    - -
    -
    -enumerator kSTATIC_BATCH#
    -

    kSTATIC_BATCH does not schedule new requests until all requests in current batch are completed. Similar to kGUARANTEED_NO_EVICT, requests will run to completion without eviction.

    -
    - -
    - -
    -
    -enum class ContextChunkingPolicy#
    -

    Values:

    -
    -
    -enumerator kFIRST_COME_FIRST_SERVED#
    -

    Sequential chunking, complete the unfinished context phase first.

    -
    - -
    -
    -enumerator kEQUAL_PROGRESS#
    -

    Iterate through each context request in sequence and attempt to increase its chunk count until the constraint is exceeded.

    -
    - -
    - -
    -
    -enum class CommunicationType#
    -

    Values:

    -
    -
    -enumerator kMPI#
    -
    - -
    - -
    -
    -enum class CommunicationMode#
    -

    Values:

    -
    -
    -enumerator kLEADER#
    -
    - -
    -
    -enumerator kORCHESTRATOR#
    -
    - -
    - -
    -
    -enum class RequestStage#
    -

    Enum class that represents the state of a request.

    -

    Values:

    -
    -
    -enumerator kQUEUED#
    -

    Request that have been received but not yet included in the active requests (due to constraints such as maximum batch size for example).

    -
    - -
    -
    -enumerator kENCODER_IN_PROGRESS#
    -

    Active request in encoder phase.

    -
    - -
    -
    -enumerator kCONTEXT_IN_PROGRESS#
    -

    Active request in context phase.

    -
    - -
    -
    -enumerator kGENERATION_IN_PROGRESS#
    -

    Active request in generation phase.

    -
    - -
    -
    -enumerator kGENERATION_COMPLETE#
    -

    Active request for which generation has completed.

    -
    - -
    - -
    -
    -enum class FinishReason#
    -

    The reason why the model stopped generating tokens for a request.

    -

    Values:

    -
    -
    -enumerator kNOT_FINISHED#
    -

    The request is not finished.

    -
    - -
    -
    -enumerator kEND_ID#
    -

    The request finished because the end id was generated.

    -
    - -
    -
    -enumerator kSTOP_WORDS#
    -

    The request finished because a stop word was generated.

    -
    - -
    -
    -enumerator kLENGTH#
    -

    The request finished because the maximum number of tokens was reached.

    -
    - -
    -
    -enumerator kTIMED_OUT#
    -

    The request finished because it got timed out (via the mAllotedTime parameter)

    -
    - -
    -
    -enumerator kCANCELLED#
    -

    The request was cancelled by calling cancelRequest.

    -
    - -
    - -
    -
    -enum class KvCacheTransferMode#
    -

    Enum describing the transfer mode for KV cache.

    -

    Values:

    -
    -
    -enumerator DRAM#
    -

    Copy to/from CPU memory (original approach).

    -
    - -
    -
    -enumerator GDS#
    -

    Attempt GPUDirect Storage (cuFile).

    -
    - -
    -
    -enumerator POSIX_DEBUG_FALLBACK#
    -

    Force a POSIX read/write for debugging.

    -
    -

    Functions

    -
    -std::ostream &operator<<( +
    +template<typename ...Args>
    std::unique_ptr<BaseTransferAgent> makeTransferAgent(
    -
    std::ostream &os,
    -
    CapacitySchedulerPolicy policy,
    +
    std::string const &backend,
    +
    Args&&... args,
    -)#
    -
    - -
    -
    -std::ostream &operator<<( - -
    -
    std::ostream &os,
    -
    ContextChunkingPolicy policy,
    -
    - -)#
    +)#
    -
    -
    -struct DebugTensorsPerIteration#
    -
    -#include <types.h>
    -

    Struct that holds the debug tensors in an iteration.

    -
    -

    Public Members

    -
    -
    -IterationType iter#
    -

    The iteration id for these tensors.

    -
    - -
    -
    -std::map<std::string, Tensor> debugTensors#
    -

    The debug tensors for this iteration.

    -
    - -
    -
    -
    -
    -class DecodingMode#
    -
    -#include <types.h>
    -

    mode of the decoder

    -
    -

    Public Types

    -
    -
    -using UnderlyingType = uint32_t#
    -
    - -
    -
    +
    +class AgentDesc#
    +

    Public Functions

    -
    -inline auto constexpr useTemperature(bool useTemp)#
    +
    +inline AgentDesc(std::string backendAgentDesc)#
    -
    -inline auto constexpr useOccurrencePenalties(bool usePenalty)#
    -
    - -
    -
    -inline auto constexpr usePresencePenalty(bool usePenalty)#
    -
    - -
    -
    -inline auto constexpr useRepetitionPenalty(bool usePenalty)#
    -
    - -
    -
    -inline auto constexpr useFrequencyPenalty(bool usePenalty)#
    -
    - -
    -
    -inline auto constexpr useMinLength(bool useMinLen)#
    -
    - -
    -
    -inline auto constexpr useBanTokens(bool banTokens)#
    -
    - -
    -
    -inline auto constexpr useBanWords(bool banWords)#
    -
    - -
    -
    -inline auto constexpr useNoRepeatNgramSize(bool noRepeatNgramSize)#
    -
    - -
    -
    -inline auto constexpr useStopWords(bool stopWords)#
    -
    - -
    -
    -inline auto constexpr useMaxLengthStop(bool maxLengthStop)#
    -
    - -
    -
    -inline auto constexpr useExplicitEosStop(bool explicitEosStop)#
    -
    - -
    -
    -inline auto constexpr useMinP(bool useMinP)#
    -
    - -
    -
    -inline auto constexpr useVariableBeamWidthSearch( - -
    -
    bool useVariableBeamWidthSearch,
    -
    - -)#
    -
    - -
    -
    -inline bool constexpr isAuto() const#
    -
    - -
    -
    -inline bool constexpr isTopK() const#
    -
    - -
    -
    -inline bool constexpr isTopP() const#
    -
    - -
    -
    -inline bool constexpr isTopKorTopP() const#
    -
    - -
    -
    -inline bool constexpr isTopKandTopP() const#
    -
    - -
    -
    -inline bool constexpr isBeamSearch() const#
    -
    - -
    -
    -inline bool constexpr isMedusa() const#
    -
    - -
    -
    -inline bool constexpr isLookahead() const#
    -
    - -
    -
    -inline bool constexpr isExplicitDraftTokens() const#
    -
    - -
    -
    -inline bool constexpr isExternalDraftTokens() const#
    -
    - -
    -
    -inline bool constexpr isEagle() const#
    -
    - -
    -
    -inline bool constexpr isUseTemperature() const#
    -
    - -
    -
    -inline bool constexpr isUsePresencePenalty() const#
    -
    - -
    -
    -inline bool constexpr isUseFrequencyPenalty() const#
    -
    - -
    -
    -inline bool constexpr isUseRepetitionPenalty() const#
    -
    - -
    -
    -inline bool constexpr isUseMinLength() const#
    -
    - -
    -
    -inline bool constexpr isUseOccurrencePenalty() const#
    -
    - -
    -
    -inline bool constexpr isUsePenalty() const#
    -
    - -
    -
    -inline bool constexpr isUseBanWords() const#
    -
    - -
    -
    -inline bool constexpr isUseNoRepeatNgramSize() const#
    -
    - -
    -
    -inline bool constexpr isUseBanTokens() const#
    -
    - -
    -
    -inline bool constexpr isUseStopWords() const#
    -
    - -
    -
    -inline bool constexpr isUseMaxLengthStop() const#
    -
    - -
    -
    -inline bool constexpr isUseExplicitEosStop() const#
    -
    - -
    -
    -inline bool constexpr isUseStopCriteria() const#
    -
    - -
    -
    -inline bool constexpr isUseMinP() const#
    -
    - -
    -
    -inline bool constexpr isUseVariableBeamWidthSearch() const#
    -
    - -
    -
    -inline bool operator==(DecodingMode const &other) const#
    -
    - -
    -
    -inline explicit constexpr DecodingMode(UnderlyingType state)#
    -
    - -
    -
    -inline constexpr UnderlyingType getState() const#
    -
    - -
    -
    -inline constexpr char const *getName() const#
    -
    - -
    -
    -

    Public Static Functions

    -
    -
    -static inline auto constexpr Auto()#
    -

    No mode specified. Config will be determined from the beam width of the first request at runtime TopKTopP if beamWidth == 1, BeamSearch otherwise.

    -
    - -
    -
    -static inline auto constexpr TopK()#
    -
    - -
    -
    -static inline auto constexpr TopP()#
    -
    - -
    -
    -static inline auto constexpr TopKTopP()#
    -
    - -
    -
    -static inline auto constexpr BeamSearch()#
    -
    - -
    -
    -static inline auto constexpr Medusa()#
    -
    - -
    -
    -static inline auto constexpr Lookahead()#
    -
    - -
    -
    -static inline auto constexpr ExplicitDraftTokens()#
    -
    - -
    -
    -static inline auto constexpr ExternalDraftTokens()#
    -
    - -
    -
    -static inline auto constexpr Eagle()#
    -
    - -
    -
    -

    Private Functions

    -
    -
    -inline bool constexpr anyBitSet(UnderlyingType bits) const#
    -
    - -
    -
    -inline bool constexpr allBitSet(UnderlyingType bits) const#
    -
    - -
    -
    -inline UnderlyingType constexpr setBitTo( - -
    -
    UnderlyingType state,
    -
    bool x,
    -
    - -)#
    +
    +inline std::string const &getBackendAgentDesc() const noexcept#

    Private Members

    -
    -UnderlyingType mState = {}#
    +
    +std::string mBackendAgentDesc#
    +
    + +
    +
    + +
    +
    +struct BaseAgentConfig#
    +
    +

    Public Members

    +
    +
    +std::string mName#
    +
    + +
    +
    +bool useProgThread#
    +
    + +
    +
    + +
    +
    +class BaseTransferAgent#
    +
    +

    Public Functions

    +
    +
    +virtual ~BaseTransferAgent() = default#
    +
    + +
    +
    +virtual void registerMemory(RegisterDescs const &descs) = 0#
    +
    + +
    +
    +virtual void deregisterMemory(RegisterDescs const &descs) = 0#
    +
    + +
    +
    +virtual void loadRemoteAgent( + +
    +
    std::string const &name,
    +
    AgentDesc const &agentDesc,
    +
    + +) = 0#
    +
    + +
    +
    +virtual AgentDesc getLocalAgentDesc() = 0#
    +
    + +
    +
    +virtual void invalidateRemoteAgent(std::string const &name) = 0#
    +
    + +
    +
    +virtual std::unique_ptr<TransferStatus> submitTransferRequests( + +
    +
    TransferRequest const &request,
    +
    + +) = 0#
    +
    + +
    +
    +virtual void notifySyncMessage( + +
    +
    std::string const &name,
    +
    SyncMessage const &syncMessage,
    +
    + +) = 0#
    +
    + +
    +
    +virtual std::unordered_map<std::string, std::vector<SyncMessage>> getNotifiedSyncMessages( + +
    +
    + +) = 0#
    +
    + +
    +
    +virtual ConnectionInfoType getConnectionInfo() = 0#
    +
    + +
    +
    +virtual void connectRemoteAgent( + +
    +
    std::string const &name,
    +
    ConnectionInfoType const &connectionInfo,
    +
    + +) = 0#
    +
    + +
    +
    +virtual bool checkRemoteDescs( + +
    +
    std::string const &name,
    +
    MemoryDescs const &memoryDescs,
    +
    + +) = 0#
    +
    + +
    +
    + +
    +
    +class DynLibLoader#
    +
    +

    Public Functions

    +
    +
    +void *getHandle(std::string const &name)#
    +
    + +
    +
    +template<typename FunctionT>
    inline FunctionT getFunctionPointer( + +
    +
    std::string const &libName,
    +
    std::string const &funcName,
    +
    + +)#
    +
    + +
    +
    +~DynLibLoader()#
    +
    + +
    +
    +DynLibLoader() = default#
    +
    + +
    +
    +DynLibLoader(DynLibLoader const&) = delete#
    +
    + +
    +
    +DynLibLoader &operator=(DynLibLoader const&) = delete#
    -

    Private Static Attributes

    -
    -
    -static SizeType32 constexpr kNumFlags = {12}#
    -
    - -
    -
    -static UnderlyingType constexpr kUseRepetitionPenalties = {1u << 0}#
    -
    - -
    -
    -static UnderlyingType constexpr kUseFrequencyPenalties = {1u << 1}#
    -
    - -
    -
    -static UnderlyingType constexpr kUsePresencePenalties = {1u << 2}#
    -
    - -
    -
    -static UnderlyingType constexpr kUseTemperature = {1u << 3}#
    -
    - -
    -
    -static UnderlyingType constexpr kUseMinLength = {1u << 4}#
    -
    - -
    -
    -static UnderlyingType constexpr kUseBanWords = {1u << 5}#
    -
    - -
    -
    -static UnderlyingType constexpr kUseStopWords = {1u << 6}#
    -
    - -
    -
    -static UnderlyingType constexpr kUseMaxLengthStop = {1u << 7}#
    -
    - -
    -
    -static UnderlyingType constexpr kUseExplicitEosStop = {1u << 8}#
    -
    - -
    -
    -static UnderlyingType constexpr kUseNoRepeatNgramSize = {1u << 9}#
    -
    - -
    -
    -static UnderlyingType constexpr kUseMinP = {1u << 10}#
    -
    - -
    -
    -static UnderlyingType constexpr kUseVariableBeamWidthSearch = {1u << 11}#
    -
    - -
    -
    -static UnderlyingType constexpr kUseStandardStopCriteria = {kUseStopWords | kUseMaxLengthStop}#
    -
    - -
    -
    -static UnderlyingType constexpr kUseOccurrencePenalties{kUseRepetitionPenalties | kUseFrequencyPenalties | kUsePresencePenalties}#
    -
    - -
    -
    -static UnderlyingType constexpr kUsePenalties = {kUseOccurrencePenalties | kUseTemperature | kUseMinLength}#
    -
    - -
    -
    -static UnderlyingType constexpr kUseBanTokens = {kUseNoRepeatNgramSize | kUseBanWords}#
    -
    - -
    -
    -static UnderlyingType constexpr kAuto = {1u << (kNumFlags + 0)}#
    -
    - -
    -
    -static UnderlyingType constexpr kTopK = {1u << (kNumFlags + 1)}#
    -
    - -
    -
    -static UnderlyingType constexpr kTopP = {1u << (kNumFlags + 2)}#
    -
    - -
    -
    -static UnderlyingType constexpr kBeamSearch = {1u << (kNumFlags + 3)}#
    -
    - -
    -
    -static UnderlyingType constexpr kMedusa = {1u << (kNumFlags + 4)}#
    -
    - -
    -
    -static UnderlyingType constexpr kLookahead = {1u << (kNumFlags + 5)}#
    -
    - -
    -
    -static UnderlyingType constexpr kExplicitDraftTokens = {1u << (kNumFlags + 6)}#
    -
    - -
    -
    -static UnderlyingType constexpr kExternalDraftTokens = {1u << (kNumFlags + 7)}#
    -
    - -
    -
    -static UnderlyingType constexpr kEagle = {1u << (kNumFlags + 8)}#
    -
    - -
    -
    -static UnderlyingType constexpr kTopKTopP = {kTopK | kTopP}#
    -
    - -
    -
    - -
    -
    -struct DisServingRequestStats#
    -
    -#include <types.h>
    -

    Struct that holds the request stats in the case of disaggregated serving.

    -
    -

    Public Members

    -
    -
    -double kvCacheTransferMS#
    -

    The total time spent on transferring KV cache from context phase to generation phase (ms)

    -
    - -
    -
    -size_t kvCacheSize#
    -

    The total size of KV cache transferred from context phase to generation phase (bytes)

    -
    - -
    -
    - -
    -
    -struct InflightBatchingStats#
    -
    -#include <types.h>
    -

    Struct that holds the stats of inflight batching models for a single iteration.

    -
    -

    Public Members

    -
    -
    -SizeType32 numScheduledRequests#
    -

    Number of scheduled requests.

    -
    - -
    -
    -SizeType32 numContextRequests#
    -

    Number of requests in context stage.

    -
    - -
    -
    -SizeType32 numGenRequests#
    -

    Number of requests in generation stage.

    -
    - -
    -
    -SizeType32 numPausedRequests#
    -

    Number of paused requests.

    -
    - -
    -
    -SizeType32 numCtxTokens#
    -

    Total number of context tokens in the iteration.

    -
    - -
    -
    -SizeType32 microBatchId#
    -

    Index of mirco batch.

    -
    - -
    -
    -float avgNumDecodedTokensPerIter#
    -

    Average number of tokens decoded per request per iteration.

    -
    - -
    -
    - -
    -
    -struct IterationStats#
    -
    -#include <types.h>
    -

    Struct that holds the stats of a single iteration.

    -
    -

    Public Members

    -
    -
    -std::string timestamp#
    -

    Ending time of this iteration.

    -
    - -
    -
    -IterationType iter#
    -

    Iteration id.

    -
    - -
    -
    -double iterLatencyMS#
    -

    Iteration latency (ms)

    -
    - -
    -
    -double newActiveRequestsQueueLatencyMS#
    -

    The total time spent in queue by the requests that became active in this iteration (ms)

    -
    - -
    -
    -SizeType32 numNewActiveRequests#
    -

    Number of new fetched active requests.

    -
    - -
    -
    -SizeType32 numActiveRequests#
    -

    Number of active requests.

    -
    - -
    -
    -SizeType32 numQueuedRequests#
    -

    Number of queued requests.

    -
    - -
    -
    -SizeType32 numCompletedRequests#
    -

    Number of requests that were completed in this iteration.

    -
    - -
    -
    -SizeType32 maxNumActiveRequests#
    -

    Number of max active requests.

    -
    - -
    -
    -SizeType32 maxBatchSizeStatic#
    -

    Static max batch size passed to the executor.

    -
    - -
    -
    -SizeType32 maxBatchSizeTunerRecommended#
    -

    Batch size produced by dynamic tuner based on input stats.

    -
    - -
    -
    -SizeType32 maxBatchSizeRuntime#
    -

    @brife The min of maxBatchSizeStatic and maxBatchSizeRuntimeUpperbound

    -
    - -
    -
    -SizeType32 maxNumTokensStatic#
    -

    @brife Static max num tokens passed to the executor

    -
    - -
    -
    -SizeType32 maxNumTokensTunerRecommended#
    -

    @brife Max num tokens produced by dynamic tuner based on input stats

    -
    - -
    -
    -SizeType32 maxNumTokensRuntime#
    -

    @brife The runtime max num tokens

    -
    - -
    -
    -size_t gpuMemUsage#
    -

    GPU memory usage in bytes.

    -
    - -
    -
    -size_t cpuMemUsage#
    -

    CPU memory usage in bytes.

    -
    - -
    -
    -size_t pinnedMemUsage#
    -

    Pinned memory usage in bytes.

    -
    - -
    -
    -std::optional<KvCacheStats> kvCacheStats#
    -

    Stats specific to KV caches.

    -
    - -
    -
    -std::optional<KvCacheStats> crossKvCacheStats#
    -

    Stats specific to cross KV caches.

    -
    - -
    -
    -std::optional<StaticBatchingStats> staticBatchingStats#
    -

    Stats specific to static batching.

    -
    - -
    -
    -std::optional<InflightBatchingStats> inflightBatchingStats#
    -

    Stats specific to inflight batching.

    -
    - -
    -
    -std::optional<SpecDecodingStats> specDecodingStats#
    -

    Stats specific to speculative decoding.

    -
    - -
    -
    - -
    -
    -struct KvCacheStats#
    -
    -#include <types.h>
    -

    Struct that holds the stats of a KV cache manager.

    -
    -

    Public Members

    -
    -
    -SizeType32 maxNumBlocks#
    -

    Max number of blocks.

    -
    - -
    -
    -SizeType32 freeNumBlocks#
    -

    Number of free blocks.

    -
    - -
    -
    -SizeType32 usedNumBlocks#
    -

    Number of used blocks.

    -
    - -
    -
    -SizeType32 tokensPerBlock#
    -

    Number of tokens per block.

    -
    - -
    -
    -SizeType32 allocTotalBlocks#
    -

    Number of total allocated block.

    -
    - -
    -
    -SizeType32 allocNewBlocks#
    -

    Number of newly allocated block.

    -
    - -
    -
    -SizeType32 reusedBlocks#
    -

    Number of reused block.

    -
    - -
    -
    -SizeType32 missedBlocks#
    -

    Number of not reused block.

    -
    - -
    -
    -float cacheHitRate#
    -

    Measuring the KV Cache reuse rate. cacheHitRate = reusedBlocks / (reusedBlocks + missedBlocks).

    -
    - -
    -
    - -
    -
    -struct RequestPerfMetrics#
    -
    -#include <types.h>
    -

    Struct that holds the stats of a request.

    -
    -

    Public Types

    -
    -
    -using TimePoint = std::chrono::time_point<std::chrono::steady_clock>#
    +

    Public Static Functions

    +
    +
    +static DynLibLoader &getInstance()#
    -

    Public Members

    +

    Private Members

    -
    -TimingMetrics timingMetrics#
    +
    +std::mutex mDllMutex#
    -
    -KvCacheMetrics kvCacheMetrics#
    +
    +std::unordered_map<std::string, void*> mHandlers#
    -
    -
    -SpeculativeDecodingMetrics speculativeDecoding#
    -
    - -
    -
    -std::optional<IterationType> firstIter#
    -

    First iteration where the request was processed.

    -
    - -
    -
    -std::optional<IterationType> lastIter#
    -

    Last iteration where a token was generated.

    -
    - -
    -
    -std::optional<IterationType> iter#
    -

    Current iteration.

    -
    -
    -
    -
    -struct KvCacheMetrics#
    -
    -

    Public Members

    -
    -
    -SizeType32 numTotalAllocatedBlocks = {0}#
    -

    Number of total allocated blocks.

    -
    - -
    -
    -SizeType32 numNewAllocatedBlocks = {0}#
    -

    Number of newly allocated blocks.

    -
    - -
    -
    -SizeType32 numReusedBlocks = {0}#
    -

    Number of reused blocks.

    -
    - -
    -
    -SizeType32 numMissedBlocks = {0}#
    -

    Number of missed blocks.

    -
    - -
    -
    -FloatType kvCacheHitRate = {0.f}#
    -

    KV Cache Hit Rate, defined as reusedBlocks / (reusedBlocks + missedBlocks)

    -
    - -
    -
    - -
    -
    -struct SpeculativeDecodingMetrics#
    -
    -

    Public Members

    -
    -
    -FloatType acceptanceRate = {0.f}#
    -

    Token acceptance rate for speculative decoding requests.

    -
    - -
    -
    -SizeType32 totalAcceptedDraftTokens = {0}#
    -

    Total number of accepted draft tokens.

    -
    - -
    -
    -SizeType32 totalDraftTokens = {0}#
    -

    Total number of draft tokens used in the request.

    -
    - -
    -
    - -
    -
    -struct TimingMetrics#
    -
    -

    Public Members

    -
    -
    -TimePoint arrivalTime#
    -

    The time when the request arrived.

    -
    - -
    -
    -TimePoint firstScheduledTime#
    -

    The time when the request was first scheduled.

    -
    - -
    -
    -TimePoint firstTokenTime#
    -

    The time when the first token was generated.

    -
    - -
    -
    -TimePoint lastTokenTime#
    -

    The time when the request was finished.

    -
    - -
    -
    -TimePoint kvCacheTransferStart#
    -

    Start time of the KV cache transfer for disaggregated serving.

    -
    - -
    -
    -TimePoint kvCacheTransferEnd#
    -

    End time of the KV cache transfer for disaggregated serving.

    -
    - -
    -
    -mutable size_t kvCacheSize = 0#
    -

    KV Cache size transfer for disaggregated serving.

    -
    - -
    -
    - -
    - -
    -
    -struct RequestStats#
    -
    -#include <types.h>
    -

    Struct that holds the stats of a single request.

    -

    Public Members

    -
    -
    -IdType id#
    -

    The request id.

    -
    - -
    -
    -RequestStage stage#
    -

    The current stage the request is in.

    -
    - -
    -
    -SizeType32 contextPrefillPosition#
    -

    If using chunked context, the current context prefill position.

    -
    - -
    -
    -SizeType32 numGeneratedTokens#
    -

    The number of generated tokens so far.

    -
    - -
    -
    -float avgNumDecodedTokensPerIter#
    -

    The average number of decoded tokens per iteration. It is >= 1 for speculative decoding.

    -
    - -
    -
    -bool scheduled#
    -

    Whether the request is scheduled for the current iteration.

    -
    - -
    -
    -bool paused#
    -

    Whether the request is being paused at the current iteration due to lack of resources (KV cache blocks exhaustion for example)

    -
    - -
    -
    -std::optional<DisServingRequestStats> disServingStats#
    -

    Stats specific to disaggregated serving.

    -
    - -
    -
    -SizeType32 allocTotalBlocksPerRequest#
    -

    Number of total allocated blocks per request.

    -
    - -
    -
    -SizeType32 allocNewBlocksPerRequest#
    -

    Number of newly allocated blocks per request.

    -
    - -
    -
    -SizeType32 reusedBlocksPerRequest#
    -

    Number of reused blocks per request.

    -
    - -
    -
    -SizeType32 missedBlocksPerRequest#
    -

    Number of missed blocks per request.

    -
    - -
    -
    -FloatType kvCacheHitRatePerRequest#
    -

    KV Cache Hit Rate per request, defined as reusedBlocks / (reusedBlocks + missedBlocks)

    -
    +

    Private Static Functions

    +
    +
    +static void *dlSym(void *handle, char const *symbol)#
    +
    -
    -
    -struct RequestStatsPerIteration#
    -
    -#include <types.h>
    -

    Struct that holds the stats of all requests in an iteration.

    +
    +
    +class MemoryDesc#
    +
    +

    Public Functions

    +
    +
    +inline MemoryDesc( + +
    +
    std::vector<char> const &vec,
    +
    uint32_t deviceId = 0,
    +
    + +)#
    +
    + +
    +
    +inline MemoryDesc(void *addr, size_t len, uint32_t deviceId)#
    +
    + +
    +
    +inline MemoryDesc(uintptr_t addr, size_t len, uint32_t deviceId)#
    +
    + +
    +
    +inline uintptr_t getAddr() const noexcept#
    +
    + +
    +
    +inline size_t getLen() const noexcept#
    +
    + +
    +
    +inline uint32_t getDeviceId() const noexcept#
    +
    + +
    -

    Public Members

    -
    -
    -IterationType iter#
    -

    The iteration id for these stats.

    -
    +

    Public Static Functions

    +
    +
    +static void serialize(MemoryDesc const &memoryDesc, std::ostream &os)#
    +
    -
    -
    -std::vector<RequestStats> requestStats#
    -

    The stats of all active requests for this iteration.

    -
    +
    +
    +static MemoryDesc deserialize(std::istream &is)#
    +
    + +
    +
    +static size_t serializedSize(MemoryDesc const &memoryDesc)#
    +
    -
    - -
    -
    -struct SpecDecodingStats#
    -
    -#include <types.h>
    -

    Struct that holds speculative decoding stats.

    -

    Public Members

    +

    Private Members

    -
    -SizeType64 numDraftTokens#
    -

    Total number of proposed draft tokens for all requests.

    -
    +
    +uintptr_t mAddr#
    +
    -
    -SizeType64 numAcceptedTokens#
    -

    Total number of accepted draft tokens for all requests.

    -
    +
    +size_t mLen#
    +
    -
    -SizeType64 numRequestsWithDraftTokens#
    -

    Number of requests with at least one draft token in batch.

    -
    - -
    -
    -double acceptanceLength#
    -

    Acceptance length, defined as average number of tokens produced per step for all requests with at least one draft token.

    -
    - -
    -
    -double iterLatencyMS#
    -

    Iteration latency for draft token generation only (ms)

    -
    - -
    -
    -double draftOverhead#
    -

    Draft overhead, defined as iterLatencyMS (specdec) / iterLatencyMS (total)

    -
    +
    +uint32_t mDeviceId#
    +
    -
    -
    -struct StaticBatchingStats#
    -
    -#include <types.h>
    -

    Struct that holds the stats of static batching models for a single iteration.

    +
    +
    +class MemoryDescs#
    +
    +

    Public Functions

    +
    +
    +inline MemoryDescs(MemoryType type, std::vector<MemoryDesc> descs)#
    +
    + +
    +
    +inline MemoryType getType() const noexcept#
    +
    + +
    +
    +inline std::vector<MemoryDesc> const &getDescs() const noexcept#
    +
    + +
    -

    Public Members

    +

    Private Members

    -
    -SizeType32 numScheduledRequests#
    -

    Number of scheduled requests.

    -
    +
    +MemoryType mType#
    +
    -
    -SizeType32 numContextRequests#
    -

    Number of requests in context stage.

    -
    - -
    -
    -SizeType32 numCtxTokens#
    -

    Total number of context tokens in the iteration.

    -
    - -
    -
    -SizeType32 numGenTokens#
    -

    Total number of tokens to generate in the iteration.

    -
    - -
    -
    -SizeType32 emptyGenSlots#
    -

    Total number of unused generation token slots.

    -
    +
    +std::vector<MemoryDesc> mDescs#
    +
    -
    -
    -template<typename T, bool = false>
    struct TypeTraits#
    -
    -#include <types.h>
    -

    For converting a C++ data type to a TrtLmmDataType.

    -
    - -
    -
    -template<>
    struct TypeTraits<bool>#
    +
    +
    +class TransferRequest#
    -

    Public Static Attributes

    +

    Public Functions

    +
    +
    +inline TransferRequest( + +
    +
    TransferOp op,
    +
    TransferDescs srcDescs,
    +
    TransferDescs dstDescs,
    +
    std::string const &remoteName,
    +
    std::optional<SyncMessage> syncMessage = std::nullopt,
    +
    + +)#
    +
    + +
    +
    +inline TransferOp getOp() const noexcept#
    +
    + +
    +
    +inline TransferDescs const &getSrcDescs() const noexcept#
    +
    + +
    +
    +inline TransferDescs const &getDstDescs() const noexcept#
    +
    + +
    +
    +inline std::string const &getRemoteName() const noexcept#
    +
    + +
    +
    +inline std::optional<SyncMessage> getSyncMessage() const noexcept#
    +
    + +
    +
    +

    Private Members

    -
    -static constexpr auto value = DataType::kBOOL#
    +
    +TransferOp mOp#
    +
    + +
    +
    +TransferDescs mSrcDescs#
    +
    + +
    +
    +TransferDescs mDstDescs#
    +
    + +
    +
    +std::string mRemoteName#
    +
    + +
    +
    +std::optional<SyncMessage> mSyncMessage#
    -
    -
    -template<>
    struct TypeTraits<float>#
    +
    +
    +class TransferStatus#
    -

    Public Static Attributes

    -
    -
    -static constexpr auto value = DataType::kFP32#
    +

    Public Functions

    +
    +
    +virtual ~TransferStatus() = default#
    -
    -
    - -
    -
    -template<>
    struct TypeTraits<half>#
    -
    -

    Public Static Attributes

    -
    -
    -static constexpr auto value = DataType::kFP16#
    +
    +
    +virtual bool isCompleted() const = 0#
    -
    -
    - -
    -
    -template<>
    struct TypeTraits<std::int32_t>#
    -
    -

    Public Static Attributes

    -
    -
    -static constexpr auto value = DataType::kINT32#
    -
    - -
    -
    - -
    -
    -template<>
    struct TypeTraits<std::int64_t>#
    -
    -

    Public Static Attributes

    -
    -
    -static constexpr auto value = DataType::kINT64#
    -
    - -
    -
    - -
    -
    -template<>
    struct TypeTraits<std::int8_t>#
    -
    -

    Public Static Attributes

    -
    -
    -static constexpr auto value = DataType::kINT8#
    -
    - -
    -
    - -
    -
    -template<>
    struct TypeTraits<std::uint8_t>#
    -
    -

    Public Static Attributes

    -
    -
    -static constexpr auto value = DataType::kUINT8#
    -
    - -
    -
    - -
    -
    -template<typename T>
    struct TypeTraits<T*>#
    -
    -

    Public Static Attributes

    -
    -
    -static constexpr auto value = DataType::kINT64#
    +
    +
    +virtual void wait() const = 0#
    @@ -4985,10 +3950,7 @@
    -
    -
    -namespace runtime
    -
    +
    @@ -5136,16 +4098,46 @@
    class CacheTransceiverConfig#
    +

    Public Types

    +
    +
    +enum class BackendType : std::uint8_t#
    +

    Values:

    +
    +
    +enumerator DEFAULT#
    +
    + +
    +
    +enumerator MPI#
    +
    + +
    +
    +enumerator UCX#
    +
    + +
    +
    +enumerator NIXL#
    +
    + +
    + +
    +

    Public Functions

    -
    -explicit CacheTransceiverConfig( +
    +explicit CacheTransceiverConfig(
    +
    std::optional<BackendType> backendType = std::nullopt,
    std::optional<size_t> maxNumTokens = std::nullopt,
    -)#
    +)#
    @@ -5154,21 +4146,36 @@
    -
    -std::optional<size_t> getMaxNumTokens() const#
    +
    +void setBackendType(std::optional<BackendType> backendType)#
    -
    -void setMaxNumTokens(size_t maxNumTokens)#
    +
    +void setMaxTokensInBuffer(std::optional<size_t> maxTokensInBuffer)#
    +
    + +
    +
    +std::optional<size_t> getMaxTokensInBuffer() const#
    +
    + +
    +
    +std::optional<BackendType> getBackendType() const#

    Private Members

    -
    -std::optional<size_t> mMaxNumTokens#
    +
    +std::optional<BackendType> mBackendType#
    +
    + +
    +
    +std::optional<size_t> mMaxTokensInBuffer#

    The maximum number of tokens that the CacheTransceiver’s pre-allocated buffer can hold. If the number of kvCache tokens to be transferred for a single request is greater than this value, the performance of the cache transfer may be degraded.

    @@ -10539,572 +9546,1741 @@
    -
    -

    dataTransceiverState.h#

    +
    +

    types.h#

    namespace tensorrt_llm
    namespace executor
    -
    -
    -class DataTransceiverState#
    -

    Public Functions

    -
    -
    -DataTransceiverState() = default#
    +

    Typedefs

    +
    +
    +using TensorPtr = std::shared_ptr<Tensor>#
    -
    -
    -inline DataTransceiverState( - -
    -
    kv_cache::CacheState cacheState,
    -
    kv_cache::CommState commState,
    -
    - -)#
    -
    - -
    -
    -inline void setCacheState(kv_cache::CacheState state)#
    -
    - -
    -
    -inline std::optional<kv_cache::CacheState> const &getCacheState( - -
    -
    - -) const noexcept#
    -
    - -
    -
    -inline void setCommState(kv_cache::CommState state)#
    -
    - -
    -
    -inline std::optional<kv_cache::CommState> const &getCommState( - -
    -
    - -) const noexcept#
    -
    - -
    -
    -inline bool operator==( - -
    -
    DataTransceiverState const &other,
    -
    - -) const noexcept#
    -
    - -
    -
    -inline std::string toString() const#
    -
    - -
    -
    -

    Private Members

    -
    -
    -std::optional<kv_cache::CacheState> mCacheState#
    -
    - -
    -
    -std::optional<kv_cache::CommState> mCommState#
    -
    - -
    -
    -

    Friends

    -
    -
    -friend class Serialization
    -
    - -
    -
    -
    -
    -namespace kv_cache
    -
    -
    -struct AgentState#
    -
    -

    Public Functions

    -
    -
    -inline AgentState(std::string agentName, std::string connectionInfo)#
    +
    +using SizeType32 = std::int32_t#
    -
    -
    -AgentState() = default#
    +
    +
    +using SizeType64 = std::int64_t#
    -
    -
    -inline bool operator==(AgentState const &other) const noexcept#
    +
    +
    +using FloatType = float#
    -
    -
    -inline std::string toString() const#
    +
    +
    +using TokenIdType = std::int32_t#
    +
    + +
    +
    +using VecTokens = std::vector<TokenIdType>#
    +
    + +
    +
    +using BeamTokens = std::vector<VecTokens>#
    +
    + +
    +
    +using IdType = std::uint64_t#
    +
    + +
    +
    +using VecTokenExtraIds = std::vector<IdType>#
    +
    + +
    +
    +using IterationType = std::uint64_t#
    +
    + +
    +
    +using RandomSeedType = std::uint64_t#
    +
    + +
    +
    +using VecLogProbs = std::vector<FloatType>#
    +
    + +
    +
    +using StreamPtr = std::shared_ptr<tensorrt_llm::runtime::CudaStream>#
    +
    + +
    +
    +using MillisecondsType = std::chrono::milliseconds#
    +
    + +
    +
    +using LogitsPostProcessor = std::function<void(IdType, Tensor&, BeamTokens const&, StreamPtr const&, std::optional<IdType>)>#
    +
    + +
    +
    +using LogitsPostProcessorMap = std::unordered_map<std::string, LogitsPostProcessor>#
    +
    + +
    +
    +using LogitsPostProcessorBatched = std::function<void(std::vector<IdType> const&, std::vector<Tensor>&, std::vector<std::reference_wrapper<BeamTokens const>> const&, StreamPtr const&, std::vector<std::optional<IdType>> const&)>#
    +
    + +
    +
    +using MedusaChoices = std::vector<std::vector<SizeType32>>#
    +
    + +
    +
    +using EagleChoices = std::vector<std::vector<SizeType32>>#
    +
    + +
    +
    +using PriorityType = float#
    +
    + +
    +
    +using BufferView = std::basic_string_view<uint8_t>#
    -

    Public Members

    -
    -
    -std::string mAgentName#
    -
    - -
    -
    -std::string mConnectionInfo#
    -
    - -
    -
    - -
    -
    -class CacheState#
    -
    -

    Public Types

    +

    Enums

    -
    -enum class AttentionType : std::uint8_t#
    +
    +enum class DataType#

    Values:

    -
    -enumerator kDEFAULT#
    +
    +enumerator kBOOL#
    -
    -enumerator kMLA#
    +
    +enumerator kUINT8#
    +
    +
    +enumerator kINT8#
    +
    + +
    +
    +enumerator kINT32#
    +
    + +
    +
    +enumerator kINT64#
    +
    + +
    +
    +enumerator kBF16#
    +
    + +
    +
    +enumerator kFP8#
    +
    + +
    +
    +enumerator kFP16#
    +
    + +
    +
    +enumerator kFP32#
    +
    + +
    +
    +enumerator kUNKNOWN#
    +
    + +
    + +
    +
    +enum class RequestType#
    +

    Values:

    +
    +
    +enumerator REQUEST_TYPE_CONTEXT_AND_GENERATION#
    +
    + +
    +
    +enumerator REQUEST_TYPE_CONTEXT_ONLY#
    +
    + +
    +
    +enumerator REQUEST_TYPE_GENERATION_ONLY#
    +
    + +
    + +
    +
    +enum class MemoryType#
    +

    Values:

    +
    +
    +enumerator kCPU#
    +
    + +
    +
    +enumerator kCPU_PINNED#
    +
    + +
    +
    +enumerator kCPU_PINNEDPOOL#
    +
    + +
    +
    +enumerator kGPU#
    +
    + +
    +
    +enumerator kUVM#
    +
    + +
    +
    +enumerator kUNKNOWN#
    +
    + +
    + +
    +
    +enum class ModelType#
    +

    Values:

    +
    +
    +enumerator kDECODER_ONLY#
    +
    + +
    +
    +enumerator kENCODER_ONLY#
    +
    + +
    +
    +enumerator kENCODER_DECODER#
    +
    + +
    + +
    +
    +enum class BatchingType#
    +

    The batching type.

    +

    Values:

    +
    +
    +enumerator kSTATIC#
    +

    STATIC refers to the traditional batching scheme with a batch of requests running in lockstep until the full generation for all of them is complete. Requests in a batch are all padded up to the maximum input and output sequence length of any member of the batch.

    +
    + +
    +
    +enumerator kINFLIGHT#
    +

    INFLIGHT refers to a scheme where newly arrived requests are dynamically incorporated into the batch under execution, and requests are returned as soon as the end condition is met without any padding.

    +
    + +
    + +
    +
    +enum class CapacitySchedulerPolicy#
    +

    The policy used to select the subset of available requests in each iteration of the executor generation loop.

    +

    Values:

    +
    +
    +enumerator kMAX_UTILIZATION#
    +

    MAX_UTILIZATION packs as many requests as the underlying TRT engine can support in any iteration of the InflightBatching generation loop. While this is expected to maximize GPU throughput, it might require that some requests be paused and restarted depending on peak KV cache memory availability.

    +
    + +
    +
    +enumerator kGUARANTEED_NO_EVICT#
    +

    GUARANTEED_NO_EVICT uses KV cache more conservatively guaranteeing that a request, once started, will run to completion without eviction.

    +
    + +
    +
    +enumerator kSTATIC_BATCH#
    +

    kSTATIC_BATCH does not schedule new requests until all requests in current batch are completed. Similar to kGUARANTEED_NO_EVICT, requests will run to completion without eviction.

    +
    + +
    + +
    +
    +enum class ContextChunkingPolicy#
    +

    Values:

    +
    +
    +enumerator kFIRST_COME_FIRST_SERVED#
    +

    Sequential chunking, complete the unfinished context phase first.

    +
    + +
    +
    +enumerator kEQUAL_PROGRESS#
    +

    Iterate through each context request in sequence and attempt to increase its chunk count until the constraint is exceeded.

    +
    + +
    + +
    +
    +enum class CommunicationType#
    +

    Values:

    +
    +
    +enumerator kMPI#
    +
    + +
    + +
    +
    +enum class CommunicationMode#
    +

    Values:

    +
    +
    +enumerator kLEADER#
    +
    + +
    +
    +enumerator kORCHESTRATOR#
    +
    + +
    + +
    +
    +enum class RequestStage#
    +

    Enum class that represents the state of a request.

    +

    Values:

    +
    +
    +enumerator kQUEUED#
    +

    Request that have been received but not yet included in the active requests (due to constraints such as maximum batch size for example).

    +
    + +
    +
    +enumerator kENCODER_IN_PROGRESS#
    +

    Active request in encoder phase.

    +
    + +
    +
    +enumerator kCONTEXT_IN_PROGRESS#
    +

    Active request in context phase.

    +
    + +
    +
    +enumerator kGENERATION_IN_PROGRESS#
    +

    Active request in generation phase.

    +
    + +
    +
    +enumerator kGENERATION_COMPLETE#
    +

    Active request for which generation has completed.

    +
    + +
    + +
    +
    +enum class FinishReason#
    +

    The reason why the model stopped generating tokens for a request.

    +

    Values:

    +
    +
    +enumerator kNOT_FINISHED#
    +

    The request is not finished.

    +
    + +
    +
    +enumerator kEND_ID#
    +

    The request finished because the end id was generated.

    +
    + +
    +
    +enumerator kSTOP_WORDS#
    +

    The request finished because a stop word was generated.

    +
    + +
    +
    +enumerator kLENGTH#
    +

    The request finished because the maximum number of tokens was reached.

    +
    + +
    +
    +enumerator kTIMED_OUT#
    +

    The request finished because it got timed out (via the mAllotedTime parameter)

    +
    + +
    +
    +enumerator kCANCELLED#
    +

    The request was cancelled by calling cancelRequest.

    +
    + +
    + +
    +
    +enum class KvCacheTransferMode#
    +

    Enum describing the transfer mode for KV cache.

    +

    Values:

    +
    +
    +enumerator DRAM#
    +

    Copy to/from CPU memory (original approach).

    +
    + +
    +
    +enumerator GDS#
    +

    Attempt GPUDirect Storage (cuFile).

    +
    + +
    +
    +enumerator POSIX_DEBUG_FALLBACK#
    +

    Force a POSIX read/write for debugging.

    +
    +
    -

    Public Functions

    +

    Functions

    -
    -inline CacheState( +
    +std::ostream &operator<<(
    -
    ModelConfig modelConfig,
    -
    runtime::WorldConfig const &worldConfig,
    -
    nvinfer1::DataType dataType,
    -
    AttentionType attentionType = AttentionType::kDEFAULT,
    -
    int kvFactor = 2,
    +
    std::ostream &os,
    +
    CapacitySchedulerPolicy policy,
    -)#
    +)#
    -
    -inline CacheState( +
    +std::ostream &operator<<(
    -
    std::vector<SizeType32> nbKvHeadPerLayer,
    -
    SizeType32 sizePerHead,
    -
    SizeType32 tokensPerBlock,
    -
    SizeType32 tensorParallelism,
    -
    SizeType32 pipelineParallelism,
    -
    nvinfer1::DataType dataType,
    -
    AttentionType attentionType = AttentionType::kDEFAULT,
    -
    int kvFactor = 2,
    -
    bool enableAttentionDP = false,
    -
    int DPrank = 0,
    -
    int DPsize = 0,
    +
    std::ostream &os,
    +
    ContextChunkingPolicy policy,
    -)#
    +)#
    -
    -
    -inline CacheState( - -
    -
    SizeType32 nbAttentionLayers,
    -
    SizeType32 nbKvHeads,
    -
    SizeType32 sizePerHead,
    -
    SizeType32 tokensPerBlock,
    -
    SizeType32 tensorParallelism,
    -
    SizeType32 pipelineParallelism,
    -
    nvinfer1::DataType dataType,
    -
    AttentionType attentionType = AttentionType::kDEFAULT,
    -
    int kvFactor = 2,
    -
    bool enableAttentionDP = false,
    -
    int DPrank = 0,
    -
    int DPsize = 0,
    -
    - -)#
    -
    - -
    -
    -inline bool operator==( - -
    -
    kv_cache::CacheState const &other,
    -
    - -) const noexcept#
    -
    - -
    -
    -inline ModelConfig const &getModelConfig() const#
    -
    - -
    -
    -inline ParallelConfig const &getParallelConfig() const#
    -
    - -
    -
    -inline AttentionConfig const &getAttentionConfig() const#
    -
    - -
    -
    -inline nvinfer1::DataType const &getDataType() const#
    -
    - -
    -
    -inline std::string toString() const#
    -
    - -
    -
    -

    Private Members

    -
    -
    -ModelConfig mModelConfig#
    -
    - -
    -
    -ParallelConfig mParallelConfig#
    -
    - -
    -
    -nvinfer1::DataType mDataType#
    -
    - -
    -
    -AttentionConfig mAttentionConfig#
    -
    - -
    -
    -

    Friends

    -
    -
    -friend class tensorrt_llm::executor::Serialization
    -
    -
    -
    -struct AttentionConfig#
    -
    -

    Public Functions

    -
    -
    -inline AttentionConfig(AttentionType attentionType, int kvFactor)#
    -
    - -
    +
    +struct DebugTensorsPerIteration#
    +
    +#include <types.h>
    +

    Struct that holds the debug tensors in an iteration.

    Public Members

    -
    -AttentionType mAttentionType#
    -
    - -
    -
    -int mKvFactor#
    -
    - -
    +
    +IterationType iter#
    +

    The iteration id for these tensors.

    -
    -
    -struct ModelConfig#
    -
    -

    Public Functions

    -
    -
    -inline bool operator==(ModelConfig const &other) const noexcept#
    -
    - -
    -
    -

    Public Members

    -
    -std::vector<SizeType32> mNbKvHeadsPerLayer#
    -
    - -
    -
    -SizeType32 mSizePerHead#
    -
    - -
    -
    -SizeType32 mTokensPerBlock#
    -
    - -
    +
    +std::map<std::string, Tensor> debugTensors#
    +

    The debug tensors for this iteration.

    -
    -
    -struct ParallelConfig#
    -
    -

    Public Functions

    -
    -
    -inline bool operator==(ParallelConfig const &other) const noexcept#
    -
    -
    -
    -

    Public Members

    -
    -
    -SizeType32 mTensorParallelism#
    -
    - -
    -
    -SizeType32 mPipelineParallelism#
    -
    - -
    -
    -bool mEnableAttentionDP#
    -
    - -
    -
    -SizeType32 mDPrank#
    -
    - -
    -
    -SizeType32 mDPsize#
    -
    - -
    -
    -
    -
    -class CommState#
    -
    +
    +class DecodingMode#
    +
    +#include <types.h>
    +

    mode of the decoder

    +
    +

    Public Types

    +
    +
    +using UnderlyingType = uint32_t#
    +
    + +
    +

    Public Functions

    -
    -CommState() = default#
    +
    +inline auto constexpr useTemperature(bool useTemp)#
    -
    -inline explicit CommState( +
    +inline auto constexpr useOccurrencePenalties(bool usePenalty)#
    +
    + +
    +
    +inline auto constexpr usePresencePenalty(bool usePenalty)#
    +
    + +
    +
    +inline auto constexpr useRepetitionPenalty(bool usePenalty)#
    +
    + +
    +
    +inline auto constexpr useFrequencyPenalty(bool usePenalty)#
    +
    + +
    +
    +inline auto constexpr useMinLength(bool useMinLen)#
    +
    + +
    +
    +inline auto constexpr useBanTokens(bool banTokens)#
    +
    + +
    +
    +inline auto constexpr useBanWords(bool banWords)#
    +
    + +
    +
    +inline auto constexpr useNoRepeatNgramSize(bool noRepeatNgramSize)#
    +
    + +
    +
    +inline auto constexpr useStopWords(bool stopWords)#
    +
    + +
    +
    +inline auto constexpr useMaxLengthStop(bool maxLengthStop)#
    +
    + +
    +
    +inline auto constexpr useExplicitEosStop(bool explicitEosStop)#
    +
    + +
    +
    +inline auto constexpr useMinP(bool useMinP)#
    +
    + +
    +
    +inline auto constexpr useVariableBeamWidthSearch(
    -
    std::vector<SizeType32> ranks,
    -
    int selfIdx = -1,
    +
    bool useVariableBeamWidthSearch,
    -)#
    +)#
    -
    -inline explicit CommState( +
    +inline bool constexpr isAuto() const#
    +
    + +
    +
    +inline bool constexpr isTopK() const#
    +
    + +
    +
    +inline bool constexpr isTopP() const#
    +
    + +
    +
    +inline bool constexpr isTopKorTopP() const#
    +
    + +
    +
    +inline bool constexpr isTopKandTopP() const#
    +
    + +
    +
    +inline bool constexpr isBeamSearch() const#
    +
    + +
    +
    +inline bool constexpr isMedusa() const#
    +
    + +
    +
    +inline bool constexpr isLookahead() const#
    +
    + +
    +
    +inline bool constexpr isExplicitDraftTokens() const#
    +
    + +
    +
    +inline bool constexpr isExternalDraftTokens() const#
    +
    + +
    +
    +inline bool constexpr isEagle() const#
    +
    + +
    +
    +inline bool constexpr isUseTemperature() const#
    +
    + +
    +
    +inline bool constexpr isUsePresencePenalty() const#
    +
    + +
    +
    +inline bool constexpr isUseFrequencyPenalty() const#
    +
    + +
    +
    +inline bool constexpr isUseRepetitionPenalty() const#
    +
    + +
    +
    +inline bool constexpr isUseMinLength() const#
    +
    + +
    +
    +inline bool constexpr isUseOccurrencePenalty() const#
    +
    + +
    +
    +inline bool constexpr isUsePenalty() const#
    +
    + +
    +
    +inline bool constexpr isUseBanWords() const#
    +
    + +
    +
    +inline bool constexpr isUseNoRepeatNgramSize() const#
    +
    + +
    +
    +inline bool constexpr isUseBanTokens() const#
    +
    + +
    +
    +inline bool constexpr isUseStopWords() const#
    +
    + +
    +
    +inline bool constexpr isUseMaxLengthStop() const#
    +
    + +
    +
    +inline bool constexpr isUseExplicitEosStop() const#
    +
    + +
    +
    +inline bool constexpr isUseStopCriteria() const#
    +
    + +
    +
    +inline bool constexpr isUseMinP() const#
    +
    + +
    +
    +inline bool constexpr isUseVariableBeamWidthSearch() const#
    +
    + +
    +
    +inline bool operator==(DecodingMode const &other) const#
    +
    + +
    +
    +inline explicit constexpr DecodingMode(UnderlyingType state)#
    +
    + +
    +
    +inline constexpr UnderlyingType getState() const#
    +
    + +
    +
    +inline constexpr char const *getName() const#
    +
    + +
    +
    +

    Public Static Functions

    +
    +
    +static inline auto constexpr Auto()#
    +

    No mode specified. Config will be determined from the beam width of the first request at runtime TopKTopP if beamWidth == 1, BeamSearch otherwise.

    +
    + +
    +
    +static inline auto constexpr TopK()#
    +
    + +
    +
    +static inline auto constexpr TopP()#
    +
    + +
    +
    +static inline auto constexpr TopKTopP()#
    +
    + +
    +
    +static inline auto constexpr BeamSearch()#
    +
    + +
    +
    +static inline auto constexpr Medusa()#
    +
    + +
    +
    +static inline auto constexpr Lookahead()#
    +
    + +
    +
    +static inline auto constexpr ExplicitDraftTokens()#
    +
    + +
    +
    +static inline auto constexpr ExternalDraftTokens()#
    +
    + +
    +
    +static inline auto constexpr Eagle()#
    +
    + +
    +
    +

    Private Functions

    +
    +
    +inline bool constexpr anyBitSet(UnderlyingType bits) const#
    +
    + +
    +
    +inline bool constexpr allBitSet(UnderlyingType bits) const#
    +
    + +
    +
    +inline UnderlyingType constexpr setBitTo(
    -
    std::vector<SocketState> socketState,
    -
    int selfIdx = -1,
    +
    UnderlyingType state,
    +
    bool x,
    -)#
    -
    - -
    -
    -inline CommState(std::uint16_t port, std::string ip)#
    -
    - -
    -
    -inline explicit CommState( - -
    -
    std::vector<AgentState> agentState,
    -
    int selfIdx = -1,
    -
    - -)#
    -
    - -
    -
    -inline bool isMpiState() const noexcept#
    -
    - -
    -
    -inline bool isSocketState() const noexcept#
    -
    - -
    -
    -inline bool isAgentState() const noexcept#
    -
    - -
    -
    -inline MpiState const &getMpiState() const#
    -
    - -
    -
    -inline std::vector<SocketState> const &getSocketState() const#
    -
    - -
    -
    -inline std::vector<AgentState> const &getAgentState() const#
    -
    - -
    -
    -inline int getSelfIdx() const noexcept#
    -
    - -
    -
    -inline bool operator==(CommState const &other) const noexcept#
    -
    - -
    -
    -inline std::string toString() const#
    +)#

    Private Members

    -
    -std::variant<std::monostate, MpiState, std::vector<SocketState>, std::vector<AgentState>> mState#
    -
    - -
    -
    -int mSelfIdx = {-1}#
    +
    +UnderlyingType mState = {}#
    -

    Friends

    -
    -
    -friend class tensorrt_llm::executor::Serialization
    -
    - -
    -
    - -
    -
    -struct MpiState#
    -
    -

    Public Functions

    -
    -
    -inline bool operator==(MpiState const &other) const noexcept#
    -
    - -
    -
    -inline std::string toString() const#
    -
    - -
    -
    -

    Public Members

    +

    Private Static Attributes

    -
    -std::vector<SizeType32> mRanks#
    +
    +static SizeType32 constexpr kNumFlags = {12}#
    +
    + +
    +
    +static UnderlyingType constexpr kUseRepetitionPenalties = {1u << 0}#
    +
    + +
    +
    +static UnderlyingType constexpr kUseFrequencyPenalties = {1u << 1}#
    +
    + +
    +
    +static UnderlyingType constexpr kUsePresencePenalties = {1u << 2}#
    +
    + +
    +
    +static UnderlyingType constexpr kUseTemperature = {1u << 3}#
    +
    + +
    +
    +static UnderlyingType constexpr kUseMinLength = {1u << 4}#
    +
    + +
    +
    +static UnderlyingType constexpr kUseBanWords = {1u << 5}#
    +
    + +
    +
    +static UnderlyingType constexpr kUseStopWords = {1u << 6}#
    +
    + +
    +
    +static UnderlyingType constexpr kUseMaxLengthStop = {1u << 7}#
    +
    + +
    +
    +static UnderlyingType constexpr kUseExplicitEosStop = {1u << 8}#
    +
    + +
    +
    +static UnderlyingType constexpr kUseNoRepeatNgramSize = {1u << 9}#
    +
    + +
    +
    +static UnderlyingType constexpr kUseMinP = {1u << 10}#
    +
    + +
    +
    +static UnderlyingType constexpr kUseVariableBeamWidthSearch = {1u << 11}#
    +
    + +
    +
    +static UnderlyingType constexpr kUseStandardStopCriteria = {kUseStopWords | kUseMaxLengthStop}#
    +
    + +
    +
    +static UnderlyingType constexpr kUseOccurrencePenalties{kUseRepetitionPenalties | kUseFrequencyPenalties | kUsePresencePenalties}#
    +
    + +
    +
    +static UnderlyingType constexpr kUsePenalties = {kUseOccurrencePenalties | kUseTemperature | kUseMinLength}#
    +
    + +
    +
    +static UnderlyingType constexpr kUseBanTokens = {kUseNoRepeatNgramSize | kUseBanWords}#
    +
    + +
    +
    +static UnderlyingType constexpr kAuto = {1u << (kNumFlags + 0)}#
    +
    + +
    +
    +static UnderlyingType constexpr kTopK = {1u << (kNumFlags + 1)}#
    +
    + +
    +
    +static UnderlyingType constexpr kTopP = {1u << (kNumFlags + 2)}#
    +
    + +
    +
    +static UnderlyingType constexpr kBeamSearch = {1u << (kNumFlags + 3)}#
    +
    + +
    +
    +static UnderlyingType constexpr kMedusa = {1u << (kNumFlags + 4)}#
    +
    + +
    +
    +static UnderlyingType constexpr kLookahead = {1u << (kNumFlags + 5)}#
    +
    + +
    +
    +static UnderlyingType constexpr kExplicitDraftTokens = {1u << (kNumFlags + 6)}#
    +
    + +
    +
    +static UnderlyingType constexpr kExternalDraftTokens = {1u << (kNumFlags + 7)}#
    +
    + +
    +
    +static UnderlyingType constexpr kEagle = {1u << (kNumFlags + 8)}#
    +
    + +
    +
    +static UnderlyingType constexpr kTopKTopP = {kTopK | kTopP}#
    -
    -struct SocketState#
    -
    -

    Public Functions

    -
    -
    -inline bool operator==(SocketState const &other) const noexcept#
    -
    +
    +struct DisServingRequestStats#
    +
    +#include <types.h>
    +

    Struct that holds the request stats in the case of disaggregated serving.

    +
    +

    Public Members

    +
    +
    +double kvCacheTransferMS#
    +

    The total time spent on transferring KV cache from context phase to generation phase (ms)

    +
    -
    -
    -inline std::string toString() const#
    +
    +
    +size_t kvCacheSize#
    +

    The total size of KV cache transferred from context phase to generation phase (bytes)

    +
    + +
    +
    + +
    +
    +struct InflightBatchingStats#
    +
    +#include <types.h>
    +

    Struct that holds the stats of inflight batching models for a single iteration.

    +
    +

    Public Members

    +
    +
    +SizeType32 numScheduledRequests#
    +

    Number of scheduled requests.

    +
    + +
    +
    +SizeType32 numContextRequests#
    +

    Number of requests in context stage.

    +
    + +
    +
    +SizeType32 numGenRequests#
    +

    Number of requests in generation stage.

    +
    + +
    +
    +SizeType32 numPausedRequests#
    +

    Number of paused requests.

    +
    + +
    +
    +SizeType32 numCtxTokens#
    +

    Total number of context tokens in the iteration.

    +
    + +
    +
    +SizeType32 microBatchId#
    +

    Index of mirco batch.

    +
    + +
    +
    +float avgNumDecodedTokensPerIter#
    +

    Average number of tokens decoded per request per iteration.

    +
    + +
    +
    + +
    +
    +struct IterationStats#
    +
    +#include <types.h>
    +

    Struct that holds the stats of a single iteration.

    +
    +

    Public Members

    +
    +
    +std::string timestamp#
    +

    Ending time of this iteration.

    +
    + +
    +
    +IterationType iter#
    +

    Iteration id.

    +
    + +
    +
    +double iterLatencyMS#
    +

    Iteration latency (ms)

    +
    + +
    +
    +double newActiveRequestsQueueLatencyMS#
    +

    The total time spent in queue by the requests that became active in this iteration (ms)

    +
    + +
    +
    +SizeType32 numNewActiveRequests#
    +

    Number of new fetched active requests.

    +
    + +
    +
    +SizeType32 numActiveRequests#
    +

    Number of active requests.

    +
    + +
    +
    +SizeType32 numQueuedRequests#
    +

    Number of queued requests.

    +
    + +
    +
    +SizeType32 numCompletedRequests#
    +

    Number of requests that were completed in this iteration.

    +
    + +
    +
    +SizeType32 maxNumActiveRequests#
    +

    Number of max active requests.

    +
    + +
    +
    +SizeType32 maxBatchSizeStatic#
    +

    Static max batch size passed to the executor.

    +
    + +
    +
    +SizeType32 maxBatchSizeTunerRecommended#
    +

    Batch size produced by dynamic tuner based on input stats.

    +
    + +
    +
    +SizeType32 maxBatchSizeRuntime#
    +

    @brife The min of maxBatchSizeStatic and maxBatchSizeRuntimeUpperbound

    +
    + +
    +
    +SizeType32 maxNumTokensStatic#
    +

    @brife Static max num tokens passed to the executor

    +
    + +
    +
    +SizeType32 maxNumTokensTunerRecommended#
    +

    @brife Max num tokens produced by dynamic tuner based on input stats

    +
    + +
    +
    +SizeType32 maxNumTokensRuntime#
    +

    @brife The runtime max num tokens

    +
    + +
    +
    +size_t gpuMemUsage#
    +

    GPU memory usage in bytes.

    +
    + +
    +
    +size_t cpuMemUsage#
    +

    CPU memory usage in bytes.

    +
    + +
    +
    +size_t pinnedMemUsage#
    +

    Pinned memory usage in bytes.

    +
    + +
    +
    +std::optional<KvCacheStats> kvCacheStats#
    +

    Stats specific to KV caches.

    +
    + +
    +
    +std::optional<KvCacheStats> crossKvCacheStats#
    +

    Stats specific to cross KV caches.

    +
    + +
    +
    +std::optional<StaticBatchingStats> staticBatchingStats#
    +

    Stats specific to static batching.

    +
    + +
    +
    +std::optional<InflightBatchingStats> inflightBatchingStats#
    +

    Stats specific to inflight batching.

    +
    + +
    +
    +std::optional<SpecDecodingStats> specDecodingStats#
    +

    Stats specific to speculative decoding.

    +
    + +
    +
    + +
    +
    +struct KvCacheStats#
    +
    +#include <types.h>
    +

    Struct that holds the stats of a KV cache manager.

    +
    +

    Public Members

    +
    +
    +SizeType32 maxNumBlocks#
    +

    Max number of blocks.

    +
    + +
    +
    +SizeType32 freeNumBlocks#
    +

    Number of free blocks.

    +
    + +
    +
    +SizeType32 usedNumBlocks#
    +

    Number of used blocks.

    +
    + +
    +
    +SizeType32 tokensPerBlock#
    +

    Number of tokens per block.

    +
    + +
    +
    +SizeType32 allocTotalBlocks#
    +

    Number of total allocated block.

    +
    + +
    +
    +SizeType32 allocNewBlocks#
    +

    Number of newly allocated block.

    +
    + +
    +
    +SizeType32 reusedBlocks#
    +

    Number of reused block.

    +
    + +
    +
    +SizeType32 missedBlocks#
    +

    Number of not reused block.

    +
    + +
    +
    +float cacheHitRate#
    +

    Measuring the KV Cache reuse rate. cacheHitRate = reusedBlocks / (reusedBlocks + missedBlocks).

    +
    + +
    +
    + +
    +
    +struct RequestPerfMetrics#
    +
    +#include <types.h>
    +

    Struct that holds the stats of a request.

    +
    +

    Public Types

    +
    +
    +using TimePoint = std::chrono::time_point<std::chrono::steady_clock>#

    Public Members

    -
    -std::uint16_t mPort#
    +
    +TimingMetrics timingMetrics#
    -
    -std::string mIp#
    +
    +KvCacheMetrics kvCacheMetrics#
    +
    + +
    +
    +SpeculativeDecodingMetrics speculativeDecoding#
    +
    + +
    +
    +std::optional<IterationType> firstIter#
    +

    First iteration where the request was processed.

    +
    + +
    +
    +std::optional<IterationType> lastIter#
    +

    Last iteration where a token was generated.

    +
    + +
    +
    +std::optional<IterationType> iter#
    +

    Current iteration.

    +
    + +
    +
    +
    +struct KvCacheMetrics#
    +
    +

    Public Members

    +
    +
    +SizeType32 numTotalAllocatedBlocks = {0}#
    +

    Number of total allocated blocks.

    +
    + +
    +
    +SizeType32 numNewAllocatedBlocks = {0}#
    +

    Number of newly allocated blocks.

    +
    + +
    +
    +SizeType32 numReusedBlocks = {0}#
    +

    Number of reused blocks.

    +
    + +
    +
    +SizeType32 numMissedBlocks = {0}#
    +

    Number of missed blocks.

    +
    + +
    +
    +FloatType kvCacheHitRate = {0.f}#
    +

    KV Cache Hit Rate, defined as reusedBlocks / (reusedBlocks + missedBlocks)

    +
    + +
    +
    + +
    +
    +struct SpeculativeDecodingMetrics#
    +
    +

    Public Members

    +
    +
    +FloatType acceptanceRate = {0.f}#
    +

    Token acceptance rate for speculative decoding requests.

    +
    + +
    +
    +SizeType32 totalAcceptedDraftTokens = {0}#
    +

    Total number of accepted draft tokens.

    +
    + +
    +
    +SizeType32 totalDraftTokens = {0}#
    +

    Total number of draft tokens used in the request.

    +
    + +
    +
    + +
    +
    +struct TimingMetrics#
    +
    +

    Public Members

    +
    +
    +TimePoint arrivalTime#
    +

    The time when the request arrived.

    +
    + +
    +
    +TimePoint firstScheduledTime#
    +

    The time when the request was first scheduled.

    +
    + +
    +
    +TimePoint firstTokenTime#
    +

    The time when the first token was generated.

    +
    + +
    +
    +TimePoint lastTokenTime#
    +

    The time when the request was finished.

    +
    + +
    +
    +TimePoint kvCacheTransferStart#
    +

    Start time of the KV cache transfer for disaggregated serving.

    +
    + +
    +
    +TimePoint kvCacheTransferEnd#
    +

    End time of the KV cache transfer for disaggregated serving.

    +
    + +
    +
    +mutable size_t kvCacheSize = 0#
    +

    KV Cache size transfer for disaggregated serving.

    +
    + +
    +
    + +
    + +
    +
    +struct RequestStats#
    +
    +#include <types.h>
    +

    Struct that holds the stats of a single request.

    +
    +

    Public Members

    +
    +
    +IdType id#
    +

    The request id.

    +
    + +
    +
    +RequestStage stage#
    +

    The current stage the request is in.

    +
    + +
    +
    +SizeType32 contextPrefillPosition#
    +

    If using chunked context, the current context prefill position.

    +
    + +
    +
    +SizeType32 numGeneratedTokens#
    +

    The number of generated tokens so far.

    +
    + +
    +
    +float avgNumDecodedTokensPerIter#
    +

    The average number of decoded tokens per iteration. It is >= 1 for speculative decoding.

    +
    + +
    +
    +bool scheduled#
    +

    Whether the request is scheduled for the current iteration.

    +
    + +
    +
    +bool paused#
    +

    Whether the request is being paused at the current iteration due to lack of resources (KV cache blocks exhaustion for example)

    +
    + +
    +
    +std::optional<DisServingRequestStats> disServingStats#
    +

    Stats specific to disaggregated serving.

    +
    + +
    +
    +SizeType32 allocTotalBlocksPerRequest#
    +

    Number of total allocated blocks per request.

    +
    + +
    +
    +SizeType32 allocNewBlocksPerRequest#
    +

    Number of newly allocated blocks per request.

    +
    + +
    +
    +SizeType32 reusedBlocksPerRequest#
    +

    Number of reused blocks per request.

    +
    + +
    +
    +SizeType32 missedBlocksPerRequest#
    +

    Number of missed blocks per request.

    +
    + +
    +
    +FloatType kvCacheHitRatePerRequest#
    +

    KV Cache Hit Rate per request, defined as reusedBlocks / (reusedBlocks + missedBlocks)

    +
    + +
    +
    + +
    +
    +struct RequestStatsPerIteration#
    +
    +#include <types.h>
    +

    Struct that holds the stats of all requests in an iteration.

    +
    +

    Public Members

    +
    +
    +IterationType iter#
    +

    The iteration id for these stats.

    +
    + +
    +
    +std::vector<RequestStats> requestStats#
    +

    The stats of all active requests for this iteration.

    +
    + +
    +
    + +
    +
    +struct SpecDecodingStats#
    +
    +#include <types.h>
    +

    Struct that holds speculative decoding stats.

    +
    +

    Public Members

    +
    +
    +SizeType64 numDraftTokens#
    +

    Total number of proposed draft tokens for all requests.

    +
    + +
    +
    +SizeType64 numAcceptedTokens#
    +

    Total number of accepted draft tokens for all requests.

    +
    + +
    +
    +SizeType64 numRequestsWithDraftTokens#
    +

    Number of requests with at least one draft token in batch.

    +
    + +
    +
    +double acceptanceLength#
    +

    Acceptance length, defined as average number of tokens produced per step for all requests with at least one draft token.

    +
    + +
    +
    +double iterLatencyMS#
    +

    Iteration latency for draft token generation only (ms)

    +
    + +
    +
    +double draftOverhead#
    +

    Draft overhead, defined as iterLatencyMS (specdec) / iterLatencyMS (total)

    +
    + +
    +
    + +
    +
    +struct StaticBatchingStats#
    +
    +#include <types.h>
    +

    Struct that holds the stats of static batching models for a single iteration.

    +
    +

    Public Members

    +
    +
    +SizeType32 numScheduledRequests#
    +

    Number of scheduled requests.

    +
    + +
    +
    +SizeType32 numContextRequests#
    +

    Number of requests in context stage.

    +
    + +
    +
    +SizeType32 numCtxTokens#
    +

    Total number of context tokens in the iteration.

    +
    + +
    +
    +SizeType32 numGenTokens#
    +

    Total number of tokens to generate in the iteration.

    +
    + +
    +
    +SizeType32 emptyGenSlots#
    +

    Total number of unused generation token slots.

    +
    + +
    +
    + +
    +
    +template<typename T, bool = false>
    struct TypeTraits#
    +
    +#include <types.h>
    +

    For converting a C++ data type to a TrtLmmDataType.

    +
    + +
    +
    +template<>
    struct TypeTraits<bool>#
    +
    +

    Public Static Attributes

    +
    +
    +static constexpr auto value = DataType::kBOOL#
    +
    + +
    +
    + +
    +
    +template<>
    struct TypeTraits<float>#
    +
    +

    Public Static Attributes

    +
    +
    +static constexpr auto value = DataType::kFP32#
    +
    + +
    +
    + +
    +
    +template<>
    struct TypeTraits<half>#
    +
    +

    Public Static Attributes

    +
    +
    +static constexpr auto value = DataType::kFP16#
    +
    + +
    +
    + +
    +
    +template<>
    struct TypeTraits<std::int32_t>#
    +
    +

    Public Static Attributes

    +
    +
    +static constexpr auto value = DataType::kINT32#
    +
    + +
    +
    + +
    +
    +template<>
    struct TypeTraits<std::int64_t>#
    +
    +

    Public Static Attributes

    +
    +
    +static constexpr auto value = DataType::kINT64#
    +
    + +
    +
    + +
    +
    +template<>
    struct TypeTraits<std::int8_t>#
    +
    +

    Public Static Attributes

    +
    +
    +static constexpr auto value = DataType::kINT8#
    +
    + +
    +
    + +
    +
    +template<>
    struct TypeTraits<std::uint8_t>#
    +
    +

    Public Static Attributes

    +
    +
    +static constexpr auto value = DataType::kUINT8#
    +
    + +
    +
    + +
    +
    +template<typename T>
    struct TypeTraits<T*>#
    +
    +

    Public Static Attributes

    +
    +
    +static constexpr auto value = DataType::kINT64#
    @@ -11112,138 +11288,11 @@
    -
    - -
    - -
    -
    -

    cacheCommunicator.h#

    -namespace tensorrt_llm
    -
    -
    -namespace executor
    -
    -
    -namespace kv_cache
    -
    -
    -class Connection#
    -
    -

    Public Functions

    -
    -
    -virtual ~Connection() = default#
    +namespace runtime
    -
    -
    -virtual void send( - -
    -
    DataContext const &ctx,
    -
    void const *data,
    -
    size_t size,
    -
    - -) const = 0#
    -
    - -
    -
    -virtual void recv( - -
    -
    DataContext const &ctx,
    -
    void *data,
    -
    size_t size,
    -
    - -) const = 0#
    -
    - -
    -
    -inline virtual bool isThreadSafe() const noexcept#
    -
    - -
    -
    - -
    -
    -class ConnectionManager#
    -
    -

    Public Functions

    -
    -
    -virtual ~ConnectionManager() = default#
    -
    - -
    -
    -virtual Connection const *recvConnect( - -
    -
    DataContext const &ctx,
    -
    void *data,
    -
    size_t size,
    -
    - -) = 0#
    -
    - -
    -
    -virtual std::vector<Connection const*> getConnections( - -
    -
    CommState const &state,
    -
    - -) = 0#
    -
    - -
    -
    -virtual CommState const &getCommState() const = 0#
    -
    - -
    -
    - -
    -
    -struct DataContext#
    -
    -

    Public Functions

    -
    -
    -inline explicit DataContext(int tag)#
    -
    - -
    -
    -inline int getTag() const noexcept#
    -
    - -
    -
    -

    Private Members

    -
    -
    -int const mTag#
    -
    - -
    -
    - -
    - -
    -
    @@ -11298,33 +11347,28 @@
    @@ -737,9 +707,9 @@ export UCX_RNDV_PIPELINE_ERROR_HANDLING=y
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/advanced/executor.html b/latest/advanced/executor.html index 576e1fc49b..169e3bd856 100644 --- a/latest/advanced/executor.html +++ b/latest/advanced/executor.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -798,9 +802,9 @@ the TensorRT-LLM C++ Executor API.

    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/advanced/expert-parallelism.html b/latest/advanced/expert-parallelism.html index 5ae2f9035d..9694b1a6ce 100644 --- a/latest/advanced/expert-parallelism.html +++ b/latest/advanced/expert-parallelism.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -665,9 +669,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/advanced/gpt-attention.html b/latest/advanced/gpt-attention.html index 156291801d..8d873ea3a5 100644 --- a/latest/advanced/gpt-attention.html +++ b/latest/advanced/gpt-attention.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -983,9 +987,9 @@ is computed as:

    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/advanced/gpt-runtime.html b/latest/advanced/gpt-runtime.html index 5c2e8084e2..1e47fb9250 100644 --- a/latest/advanced/gpt-runtime.html +++ b/latest/advanced/gpt-runtime.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -1024,9 +1028,9 @@ The GptDecoder
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/advanced/graph-rewriting.html b/latest/advanced/graph-rewriting.html index d52266e9b5..4530a7c4fb 100644 --- a/latest/advanced/graph-rewriting.html +++ b/latest/advanced/graph-rewriting.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -844,9 +848,9 @@ techniques to optimize the underlying graph. It provides a wrapper similar to P
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/advanced/kv-cache-management.html b/latest/advanced/kv-cache-management.html index 8f14cc4655..046e3e9f96 100644 --- a/latest/advanced/kv-cache-management.html +++ b/latest/advanced/kv-cache-management.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -749,9 +753,9 @@ An “event” is any significant change in the lifecycle or state of a KV cache
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/advanced/kv-cache-reuse.html b/latest/advanced/kv-cache-reuse.html index d9c9b24349..4f40cd2001 100644 --- a/latest/advanced/kv-cache-reuse.html +++ b/latest/advanced/kv-cache-reuse.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -722,9 +726,9 @@ Assume vocabulary size is 100, which means normal text token ids are in range [0
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/advanced/lora.html b/latest/advanced/lora.html index a860c1d000..06c1fd5079 100644 --- a/latest/advanced/lora.html +++ b/latest/advanced/lora.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -836,9 +840,9 @@ The shape of LoraWe
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/advanced/lowprecision-pcie-allreduce.html b/latest/advanced/lowprecision-pcie-allreduce.html index c9cac0d684..71d4499586 100644 --- a/latest/advanced/lowprecision-pcie-allreduce.html +++ b/latest/advanced/lowprecision-pcie-allreduce.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -347,6 +347,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -382,6 +384,8 @@

    Command-Line Reference

    @@ -685,9 +689,9 @@ This feature is optimized for PCIe-based GPU topologies and may affect model acc
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/advanced/open-sourced-cutlass-kernels.html b/latest/advanced/open-sourced-cutlass-kernels.html index a35b266658..81223b55e2 100644 --- a/latest/advanced/open-sourced-cutlass-kernels.html +++ b/latest/advanced/open-sourced-cutlass-kernels.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -347,6 +347,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -382,6 +384,8 @@

    Command-Line Reference

    @@ -640,9 +644,9 @@ Note that support for these static libraries will be gradually deprioritized in
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/advanced/speculative-decoding.html b/latest/advanced/speculative-decoding.html index 48cc11f85c..1fa59bf9a8 100644 --- a/latest/advanced/speculative-decoding.html +++ b/latest/advanced/speculative-decoding.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -501,7 +505,7 @@

  • About Speculative Sampling

  • Performance Improvements

  • Draft-Target-Model

    • -

  • Prompt-Lookup-Decoding

    • +

  • NGram

  • Medusa

  • ReDrafter

    • -

  • EAGLE

    • +

  • EAGLE

    + +

  • Lookahead decoding

    • @@ -540,7 +548,7 @@ The combination of both these allows speculative decoding to result in reduced l

  • EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty.

    • -

  • Utilizing prompt tokens as draft tokens. For more information, refer to Prompt Lookup Decoding.

    • +

  • Utilizing prompt tokens as draft tokens. For more information, refer to NGram.

  • Utilizing Jacobi-like decoding to predict and verify draft tokens using the same model which does not need additional fine-tuning. Refer to Break the Sequential Dependency of LLM Inference Using Lookahead Decoding.

    • @@ -563,12 +571,12 @@ Upon verification, the Target model may return up to TensorRT-LLM Triton backend.

    -

    We provide two styles of running Draft-Target-Model now: using TensorRT-LLM-BLS in Triton Inference Server, or using TensorRT-LLM directly. Detailed steps of running can be found in examples/draft_target_model/README.md and the code can be found in examples/prompt_lookup/run_dtm_pld.py.

    +

    We provide two styles of running Draft-Target-Model now: using TensorRT-LLM-BLS in Triton Inference Server, or using TensorRT-LLM directly. Detailed steps of running can be found in examples/draft_target_model/README.md and the code can be found in examples/ngram/run_dtm_ngram.py.

    -
    -

    Prompt-Lookup-Decoding#

    -

    The Prompt-Lookup speculative decoding directly copies from the input prompt and previous generated output as draft tokens while generating the later output. It works like Draft-Target-Model but involves only one Target LLM model without further fine-tuning. The Prompt-Lookup profit from the scenarios which have high n-gram overlap between input prompt and output, such as summarization, document QA, multi-turn chat, code editing, etc.

    -

    See document in examples/prompt_lookup/README.md and the code can be found in examples/prompt_lookup/run_dtm_pld.py.

    +
    +

    NGram#

    +

    The NGram speculative decoding directly copies from the input prompt and previous generated output as draft tokens while generating the later output. It works like Draft-Target-Model but involves only one Target LLM model without further fine-tuning. The NGram profit from the scenarios which have high n-gram overlap between input prompt and output, such as summarization, document QA, multi-turn chat, code editing, etc.

    +

    See document in examples/ngram/README.md and the code can be found in examples/ngram/run_dtm_ngram.py.

    Medusa#

    @@ -659,6 +667,10 @@ However, similar to any new model, you can follow the same approach to define yo

    EAGLE#

    The EAGLE approach enhances the single-model Medusa method by predicting and verifying tokens using the same model. Similarly to ReDrafter, it predicts draft tokens using a recurrent predictor where each draft token depends on the previous one. However, unlike ReDrafter, it uses a single-layer transformer model to predict draft tokens from previous hidden states and decoded tokens. In the EAGLE-1 decoding tree needs to be known during the decoding. In the EAGLE-2 this tree is asssembled during the execution by searching for the most probable hypothesis along the beam.

    Similarly to ReDrafter, TensorRT-LLM implements the EAGLE model such that logits prediction, draft tokens acceptance and draft token generation are performed inside of the TensorRT engine. EAGLE-1 and EAGLE-2 are both supported, while EAGLE-2 is currently in the experimental stage. Please, visit the EAGLE README for information about building and running the model.

    +
    +

    Disaggregated Serving#

    +

    Disaggregated Serving with EAGLE3 using the two model approach is supported in the Pytorch backend. Please refer to the following Dynamo example on how to run EAGLE3 with Disaggregated Serving for Llama 4 Maverick.

    +

    Lookahead Decoding#

    @@ -718,7 +730,7 @@ However, similar to any new model, you can follow the same approach to define yo
  • About Speculative Sampling
  • Performance Improvements
  • Draft-Target-Model
    • -
  • Prompt-Lookup-Decoding
    • +
  • NGram
  • Medusa @@ -824,9 +839,9 @@ However, similar to any new model, you can follow the same approach to define yo
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/advanced/weight-streaming.html b/latest/advanced/weight-streaming.html index f1e877d015..df3f34f996 100644 --- a/latest/advanced/weight-streaming.html +++ b/latest/advanced/weight-streaming.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -347,6 +347,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -382,6 +384,8 @@

    Command-Line Reference

    @@ -673,9 +677,9 @@ python3 examples/summarize.py
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/architecture/add-model.html b/latest/architecture/add-model.html index 6ab2d034bd..931cc7c743 100644 --- a/latest/architecture/add-model.html +++ b/latest/architecture/add-model.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -735,9 +739,9 @@ python ../summarize.py --engine_di
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/architecture/checkpoint.html b/latest/architecture/checkpoint.html index 059b5ae264..0e4f536f88 100644 --- a/latest/architecture/checkpoint.html +++ b/latest/architecture/checkpoint.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -1002,9 +1006,9 @@ trtllm-build --checkpoint_dir ./op
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/architecture/core-concepts.html b/latest/architecture/core-concepts.html index 61004ee758..dcc28ba03a 100644 --- a/latest/architecture/core-concepts.html +++ b/latest/architecture/core-concepts.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -1006,9 +1010,9 @@ srun \
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/architecture/model-weights-loader.html b/latest/architecture/model-weights-loader.html index ba4bee3621..9e86d7083a 100644 --- a/latest/architecture/model-weights-loader.html +++ b/latest/architecture/model-weights-loader.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -347,6 +347,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -382,6 +384,8 @@

    Command-Line Reference

    @@ -924,9 +928,9 @@ The support for Qwen-1 is in
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/architecture/overview.html b/latest/architecture/overview.html index f415136d18..6a6d37e728 100644 --- a/latest/architecture/overview.html +++ b/latest/architecture/overview.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -653,9 +657,9 @@ Server to easily create web-based services for LLMs. TensorRT-LLM supports m
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/architecture/workflow.html b/latest/architecture/workflow.html index dc4ef1317e..e030161d5f 100644 --- a/latest/architecture/workflow.html +++ b/latest/architecture/workflow.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -832,9 +836,9 @@ The usage of this API looks like this:

    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/blogs/Best_perf_practice_on_DeepSeek-R1_in_TensorRT-LLM.html b/latest/blogs/Best_perf_practice_on_DeepSeek-R1_in_TensorRT-LLM.html index a6d91affdc..0c194e4020 100644 --- a/latest/blogs/Best_perf_practice_on_DeepSeek-R1_in_TensorRT-LLM.html +++ b/latest/blogs/Best_perf_practice_on_DeepSeek-R1_in_TensorRT-LLM.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -347,6 +347,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -382,6 +384,8 @@

    Command-Line Reference

    @@ -647,7 +651,8 @@ The command to generate synthetic dataset will be attached to the max throughput cat >./extra-llm-api-config.yml<<EOF cuda_graph_config: {} -moe_backend: TRTLLM +moe_config: + backend: TRTLLM speculative_config: decoding_type: MTP num_nextn_predict_layers: 3 @@ -705,7 +710,7 @@ trtllm-bench --model nvidia/DeepSe

    Benchmark#

    cat >./extra-llm-api-config.yml <<EOF
 cuda_graph_config:
-  padding_enabled: true
+  enable_padding: true
   batch_sizes:
   - 896
   - 512
@@ -773,7 +778,7 @@ python ${YOUR_WO
 
 cat >./extra-llm-api-config.yml <<EOF
 cuda_graph_config:
-  padding_enabled: true
+  enable_padding: true
   batch_sizes:
   - 1
   - 2
@@ -1108,9 +1113,9 @@ For more details on 
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    diff --git a/latest/blogs/Falcon180B-H200.html b/latest/blogs/Falcon180B-H200.html index 0aff19a5eb..2c06db2bfd 100644 --- a/latest/blogs/Falcon180B-H200.html +++ b/latest/blogs/Falcon180B-H200.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -791,9 +795,9 @@ ISL = Input Sequence Length
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/blogs/H100vsA100.html b/latest/blogs/H100vsA100.html index b6f5510bdf..b31752d1f2 100644 --- a/latest/blogs/H100vsA100.html +++ b/latest/blogs/H100vsA100.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -743,9 +747,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/blogs/H200launch.html b/latest/blogs/H200launch.html index 57b4f3b8cf..445ccab898 100644 --- a/latest/blogs/H200launch.html +++ b/latest/blogs/H200launch.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -735,9 +739,9 @@ TensorRT-LLM v0.5.0, TensorRT v9.1.0.4 | H200, H100 FP8.

    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/blogs/XQA-kernel.html b/latest/blogs/XQA-kernel.html index e65a63d113..b4fc219ecd 100644 --- a/latest/blogs/XQA-kernel.html +++ b/latest/blogs/XQA-kernel.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -702,9 +706,9 @@ ISL = Input Sequence Length
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/blogs/quantization-in-TRT-LLM.html b/latest/blogs/quantization-in-TRT-LLM.html index 5aaadc0558..3fdeb27d16 100644 --- a/latest/blogs/quantization-in-TRT-LLM.html +++ b/latest/blogs/quantization-in-TRT-LLM.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -857,9 +861,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html b/latest/blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html index ecbb793f35..fdc7bb11ea 100644 --- a/latest/blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html +++ b/latest/blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -1178,9 +1182,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html b/latest/blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html index 68a8a6dd08..422783dfe5 100644 --- a/latest/blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html +++ b/latest/blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html @@ -58,7 +58,7 @@ @@ -69,7 +69,7 @@ - + @@ -348,6 +348,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -383,6 +385,8 @@

    Command-Line Reference

    @@ -625,7 +629,8 @@ python quickstart_advanced.py --mo cat >./extra-llm-api-config.yml<<EOF cuda_graph_config: {} -moe_backend: TRTLLM +moe_config: + backend: TRTLLM speculative_config: decoding_type: MTP num_nextn_predict_layers: 3 @@ -674,7 +679,8 @@ python quickstart_advanced.py --mo cat >./extra-llm-api-config.yml<<EOF cuda_graph_config: {} -moe_backend: TRTLLM +moe_config: + backend: TRTLLM speculative_config: decoding_type: MTP num_nextn_predict_layers: 3 @@ -909,9 +915,9 @@ trtllm-bench --model nvidia/DeepSe
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html b/latest/blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html index 7c012d3f6d..ab0c7d923f 100644 --- a/latest/blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html +++ b/latest/blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -347,6 +347,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -382,6 +384,8 @@

    Command-Line Reference

    @@ -712,7 +716,7 @@ Running the shared and routed experts in 2 streams combined with other multi-str

    This had a significant 22% E2E performance impact for throughput scenarios.

    CUDA Graphs allow capturing a sequence of CUDA operations and launching them as a single unit, drastically reducing kernel launch overheads. This is particularly beneficial for models with many small kernels, and particularly on the PyTorch flow, because the python host code normally executes slower than C++. Since the CUDA Graph freezes the kernel launch parameters, which is normally associated with the tensor shapes, it can only be safely used with static shape, meaning that different CUDA graphs need to be captured for different batch sizes. Each graph will have some cost of memory usage, and capturing time, thus we cannot capture every possible CUDA graph for all possible batches. For the non-captured batch sizes, PyTorch eager mode code will be executed.

    There is a feature called CUDA Graph padding in TensorRT-LLM, which is a good trade-off between the number of CUDA Graphs and the CUDA Graph hit ratio; it tries to pad a batch to the nearest one with a captured CUDA Graph. Normally you should enable the CUDA Graph padding feature to increase the CUDA Graph hit rate, but the padding itself has some overhead due to wasted tokens computation.

    -

    Users can opt-out the CUDA Graph padding feature to see the perf benefits, by setting the cuda_graph_config:\n  padding_enabled: False, see API here Pytorch backend config

    +

    Users can opt-out the CUDA Graph padding feature to see the perf benefits, by setting the cuda_graph_config:\n  enable_padding: False, see API here Pytorch backend config

  • Overlap Scheduler:

    Showed a 4% E2E performance impact and should generally always be used. This scheduler manages the execution of different operations (like computation and communication) to overlap them effectively on the GPU and network. The intuition is to hide latency by performing computation while waiting for data transfers or vice versa, improving overall hardware utilization. The overlap schedule is already defaulted on in TensorRT-LLM by commit. In case there are corner cases where it does not work, users can still opt-out this feature by set disable_overlap_scheduler to true.

    @@ -880,9 +884,9 @@ Running the shared and routed experts in 2 streams combined with other multi-str
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html b/latest/blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html index 5f596cf09a..efbfc7a6e8 100644 --- a/latest/blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html +++ b/latest/blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -347,6 +347,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -382,6 +384,8 @@

    Command-Line Reference

    @@ -1134,7 +1138,8 @@ average 1024.0 491.651199 1.564272 
    cat > ./extra_llm_api_options_eplb.yaml <<EOF
 enable_attention_dp: true
 cuda_graph_config: {}
-moe_load_balancer: ./moe_load_balancer.yaml
+moe_config:
+  load_balancer: ./moe_load_balancer.yaml
 EOF
 
 trtllm-llmapi-launch \
@@ -1423,9 +1428,9 @@ Through this collaborative endeavor, we have developed valuable insights to allo
         
    
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    
   
 
    
       
diff --git a/latest/blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html b/latest/blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html
index c873e5ea17..8c111097f5 100644
--- a/latest/blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html
+++ b/latest/blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html
@@ -58,7 +58,7 @@
     
@@ -68,7 +68,7 @@
 
   
   
-  
+  
 
 
   
@@ -347,6 +347,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    • 
 
  • Run LLM-API with pytorch backend on Slurm
    • 
 
  • Run trtllm-bench with pytorch backend on Slurm
    • 
 
  • Run trtllm-serve with pytorch backend on Slurm
    • 
@@ -382,6 +384,8 @@
 
 
    Command-Line Reference
    
 
@@ -936,9 +940,9 @@ $\frac{\text{Total Output Tokens/sec}}{\left(\frac{\text{NumCtxGPUs} \times \tex
         
    
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    
   
 
    
       
diff --git a/latest/blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.html b/latest/blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.html
index 65ca216c7d..37fe5feeef 100644
--- a/latest/blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.html
+++ b/latest/blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.html
@@ -58,7 +58,7 @@
     
@@ -68,7 +68,7 @@
 
   
   
-  
+  
 
 
   
@@ -347,6 +347,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    • 
 
  • Run LLM-API with pytorch backend on Slurm
    • 
 
  • Run trtllm-bench with pytorch backend on Slurm
    • 
 
  • Run trtllm-serve with pytorch backend on Slurm
    • 
@@ -382,6 +384,8 @@
 
 
    Command-Line Reference
    
 
@@ -780,9 +784,9 @@
         
    
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    
   
 
    
       
diff --git a/latest/commands/trtllm-bench.html b/latest/commands/trtllm-bench.html
new file mode 100644
index 0000000000..8b37a2712c
--- /dev/null
+++ b/latest/commands/trtllm-bench.html
@@ -0,0 +1,1292 @@
+
+
+
+
+
+
+
+  
+    
+    
+
+    trtllm-bench — TensorRT-LLM
+  
+  
+  
+  
+  
+  
+  
+  
+  
+
+
+    
+    
+    
+    
+    
+  
+  
+  
+  
+  
+
+
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+
+  
+  
+  
+
+
+  
+  
+  
+  
+
+  
+  
+  
+  
+  
    
+  
+  
+
+  
+  
+    
+
    
+  
+  
+  Ctrl+K
+
    
+      
+
+  
    
+  
+
    
+
+  
+    
    
+
    
+  
+  
+  
+  
    
+    
+      
    
+
+  
+    
+  
+
+
    
+    
+  
    
+  
+  
    
+    
+    
    
+      
+        
    
+
+
+
    
+  
+  
    
+    
+  
    
+
    
+      
+    
    
+    
+    
+    
    
+      
+        
    
+          
+
+
+        
    
+      
+      
+        
    
+
+
    
+      
+    
    
+    
+  
    
+  
+  
+    
    
+
+
+    
    
+  
+
+  
+    
+  
+
    
+
+    
    
+  
+
+  
    
+    
    
+      
+      
+      
+      
+      
    
+        
+
+
+
+  
+    
+  
+
+
+
+
+  
+  
    
+    
+    
+      
    
+        
+          
+          
+            
    
+
+
+
    
+  
+  
    
+    
+  
    
+
    
+          
+        
+      
    
+    
+    
+    
+      
    
+        
+          
    
+
+
    
+        
+      
    
+    
+  
    
+  
+    
    
+        
    
+
+
+
+
    
+    
    
+  
+  
+  
    
+  
    
+
+
+
+      
    
+      
+      
    
+        
+        
+          
    
+            
    
+              
+              
    
+
    
+  
+    
    
+      
+        
    
+
+
+
    
+      
+    
    
+  
+  
+
    
+
    
+              
+              
+              
+                
+
+                
    
+                  
+  
    
+
    trtllm-bench#
    
+
    trtllm-bench is a comprehensive benchmarking tool for TensorRT-LLM engines. It provides three main subcommands for different benchmarking scenarios:
    
+
    Common Options for All Commands:
    
+
    Usage:
    
+
    
+
    trtllm-bench#
    
+
    trtllm-bench [OPTIONS] COMMAND [ARGS]...
+
    
+
    
+
    Options
    
+
    
+
    
+-m, --model <model>#
    
+
    Required The Huggingface name of the model to benchmark.
    
+
    
+
+
    
+
    
+--model_path <model_path>#
    
+
    Path to a Huggingface checkpoint directory for loading model components.
    
+
    
+
+
    
+
    
+-w, --workspace <workspace>#
    
+
    The directory to store benchmarking intermediate files.
    
+
    
+
+
    
+
    
+--log_level <log_level>#
    
+
    The logging level.
    
+
    
+
    Options:
    
+
    internal_error | error | warning | info | verbose | debug | trace
    
+
    
+
    
+
    
+
+
    
+
    throughput#
    
+
    Run a throughput test on a TRT-LLM engine.
    
+
    trtllm-bench throughput [OPTIONS]
+
    
+
    
+
    Options
    
+
    
+
    
+--engine_dir <engine_dir>#
    
+
    Path to a serialized TRT-LLM engine.
    
+
    
+
+
    
+
    
+--backend <backend>#
    
+
    The backend to use when running benchmarking.
    
+
    
+
    Options:
    
+
    pytorch | _autodeploy | tensorrt
    
+
    
+
    
+
    
+
+
    
+
    
+--extra_llm_api_options <extra_llm_api_options>#
    
+
    Path to a YAML file that overwrites the parameters specified by trtllm-bench.
    
+
    
+
+
    
+
    
+--max_batch_size <max_batch_size>#
    
+
    Maximum runtime batch size to run the engine with.
    
+
    
+
+
    
+
    
+--max_num_tokens <max_num_tokens>#
    
+
    Maximum runtime tokens that an engine can accept.
    
+
    
+
+
    
+
    
+--max_seq_len <max_seq_len>#
    
+
    Maximum sequence length.
    
+
    
+
+
    
+
    
+--beam_width <beam_width>#
    
+
    Number of search beams.
    
+
    
+
+
    
+
    
+--kv_cache_free_gpu_mem_fraction <kv_cache_free_gpu_mem_fraction>#
    
+
    The percentage of memory to use for KV Cache after model load.
    
+
    
+
+
    
+
    
+--dataset <dataset>#
    
+
    Pass in a dataset file for parsing instead of stdin.
    
+
    
+
+
    
+
    
+--eos_id <eos_id>#
    
+
    Set the end-of-sequence token for the benchmark. Set to -1 to disable EOS.
    
+
    
+
+
    
+
    
+--modality <modality>#
    
+
    Modality of the multimodal requests.
    
+
    
+
    Options:
    
+
    image | video
    
+
    
+
    
+
    
+
+
    
+
    
+--max_input_len <max_input_len>#
    
+
    Maximum input sequence length to use for multimodal models. This is used only when –modality is specified since the actual number of vision tokens is unknown before the model is run.
    
+
    
+
+
    
+
    
+--num_requests <num_requests>#
    
+
    Number of requests to cap benchmark run at. If not specified or set to 0, it will be the length of dataset.
    
+
    
+
+
    
+
    
+--warmup <warmup>#
    
+
    Number of requests warm up benchmark.
    
+
    
+
+
    
+
    
+--target_input_len <target_input_len>#
    
+
    Target (average) input length for tuning heuristics.
    
+
    
+
+
    
+
    
+--target_output_len <target_output_len>#
    
+
    Target (average) sequence length for tuning heuristics.
    
+
    
+
+
    
+
    
+--tp <tp>#
    
+
    tensor parallelism size
    
+
    
+
+
    
+
    
+--pp <pp>#
    
+
    pipeline parallelism size
    
+
    
+
+
    
+
    
+--ep <ep>#
    
+
    expert parallelism size
    
+
    
+
+
    
+
    
+--cluster_size <cluster_size>#
    
+
    expert cluster parallelism size
    
+
    
+
+
    
+
    
+--concurrency <concurrency>#
    
+
    Desired concurrency rate (number of requests processing at the same time), <=0 for no concurrency limit.
    
+
    
+
+
    
+
    
+--streaming#
    
+
    Enable streaming mode for requests.
    
+
    
+
+
    
+
    
+--report_json <report_json>#
    
+
    Path where report is written to.
    
+
    
+
+
    
+
    
+--iteration_log <iteration_log>#
    
+
    Path where iteration logging is written to.
    
+
    
+
+
    
+
    
+--output_json <output_json>#
    
+
    Path where output should be written to.
    
+
    
+
+
    
+
    
+--request_json <request_json>#
    
+
    Path where per request information is written to.
    
+
    
+
+
    
+
    
+--enable_chunked_context#
    
+
    Enable chunking in prefill stage for enhanced throughput benchmark.
    
+
    
+
+
    
+
    
+--scheduler_policy <scheduler_policy>#
    
+
    KV cache scheduler policy: guaranteed_no_evict prevents request eviction, max_utilization optimizes for throughput.
    
+
    
+
    Options:
    
+
    guaranteed_no_evict | max_utilization
    
+
    
+
    
+
    
+
+
    
+
    
+
    latency#
    
+
    Run a latency test on a TRT-LLM engine.
    
+
    trtllm-bench latency [OPTIONS]
+
    
+
    
+
    Options
    
+
    
+
    
+--engine_dir <engine_dir>#
    
+
    Path to a serialized TRT-LLM engine.
    
+
    
+
+
    
+
    
+--backend <backend>#
    
+
    The backend to use when running benchmarking.
    
+
    
+
    Options:
    
+
    pytorch | _autodeploy | tensorrt
    
+
    
+
    
+
    
+
+
    
+
    
+--kv_cache_free_gpu_mem_fraction <kv_cache_free_gpu_mem_fraction>#
    
+
    The percentage of memory to use for KV Cache after model load.
    
+
    
+
+
    
+
    
+--max_seq_len <max_seq_len>#
    
+
    Maximum sequence length.
    
+
    
+
+
    
+
    
+--dataset <dataset>#
    
+
    Pass in a dataset file for parsing instead of stdin.
    
+
    
+
+
    
+
    
+--modality <modality>#
    
+
    Modality of the multimodal requests.
    
+
    
+
    Options:
    
+
    image | video
    
+
    
+
    
+
    
+
+
    
+
    
+--max_input_len <max_input_len>#
    
+
    Maximum input sequence length to use for multimodal models. This is used only when –modality is specified since the actual number of vision tokens is unknown before the model is run.
    
+
    
+
+
    
+
    
+--num_requests <num_requests>#
    
+
    Number of requests to cap benchmark run at. Minimum between value andlength of dataset.
    
+
    
+
+
    
+
    
+--warmup <warmup>#
    
+
    Number of requests warm up benchmark.
    
+
    
+
+
    
+
    
+--tp <tp>#
    
+
    tensor parallelism size
    
+
    
+
+
    
+
    
+--pp <pp>#
    
+
    pipeline parallelism size
    
+
    
+
+
    
+
    
+--ep <ep>#
    
+
    expert parallelism size
    
+
    
+
+
    
+
    
+--beam_width <beam_width>#
    
+
    Number of search beams.
    
+
    
+
+
    
+
    
+--concurrency <concurrency>#
    
+
    Desired concurrency rate (number of requests processing at the same time), <=0 for no concurrency limit.
    
+
    
+
+
    
+
    
+--medusa_choices <medusa_choices>#
    
+
    Path to a YAML file that defines the Medusa tree.
    
+
    
+
+
    
+
    
+--report_json <report_json>#
    
+
    Path where report should be written to.
    
+
    
+
+
    
+
    
+--iteration_log <iteration_log>#
    
+
    Path where iteration logging is written to.
    
+
    
+
+
    
+
    
+
    build#
    
+
    Build engines for benchmarking.
    
+
    trtllm-bench build [OPTIONS]
+
    
+
    
+
    Options
    
+
    
+
    
+-tp, --tp_size <tp_size>#
    
+
    Number of tensor parallel shards to run the benchmark with.
    
+
    
+
+
    
+
    
+-pp, --pp_size <pp_size>#
    
+
    Number of pipeline parallel shards to run the benchmark with.
    
+
    
+
+
    
+
    
+-q, --quantization <quantization>#
    
+
    The quantization algorithm to be used when benchmarking. See the documentations for more information.
+- https://nvidia.github.io/TensorRT-LLM/precision.html  - NVIDIA/TensorRT-LLM
    
+
    
+
    Options:
    
+
    W8A16 | W4A16 | W4A16_AWQ | W4A8_AWQ | W4A16_GPTQ | FP8 | INT8 | NVFP4
    
+
    
+
    
+
    
+
+
    
+
    
+--max_seq_len <max_seq_len>#
    
+
    Maximum total length of one request, including prompt and outputs.
    
+
    
+
+
    
+
    
+--no_weights_loading <no_weights_loading>#
    
+
    Do not load the weights from the checkpoint. Use dummy weights instead.
    
+
    
+
+
    
+
    
+--trust_remote_code <trust_remote_code>#
    
+
    Trust remote code for the HF models that are not natively implemented in the transformers library. This is needed when using LLM API when loading the HF config to build the engine.
    
+
    
+
+
    
+
    
+--dataset <dataset>#
    
+
    Dataset file to extract the sequence statistics for engine build.
    
+
    
+
+
    
+
    
+--max_batch_size <max_batch_size>#
    
+
    Maximum number of requests that the engine can schedule.
    
+
    
+
+
    
+
    
+--max_num_tokens <max_num_tokens>#
    
+
    Maximum number of batched tokens the engine can schedule.
    
+
    
+
+
    
+
    
+--target_input_len <target_input_len>#
    
+
    Target (average) input length for tuning heuristics.
    
+
    
+
+
    
+
    
+--target_output_len <target_output_len>#
    
+
    Target (average) sequence length for tuning heuristics.
    
+
    
+
+
    
+
    
+
    
+
    
+
    prepare_dataset.py#
    
+
    trtllm-bench is designed to work with the prepare_dataset.py script, which generates benchmark datasets in the required format. The prepare_dataset script supports:
    
+
    Dataset Types:
    
+
      
+
    • Real datasets from various sources
      • 
+
    • Synthetic datasets with normal or uniform token distributions
      • 
+
    • LoRA task-specific datasets
      • 
+
    
+
    Key Features:
    
+
      
+
    • Tokenizer integration for proper text preprocessing
      • 
+
    • Configurable random seeds for reproducible results
      • 
+
    • Support for LoRA adapters and task IDs
      • 
+
    • Output in JSON format compatible with trtllm-bench
      • 
+
    
+
    
+
    Important
    
+
    The --stdout flag is required when using prepare_dataset.py with trtllm-bench to ensure proper data streaming format.
    
+
    
+
    Usage:
    
+
    
+
    prepare_dataset#
    
+
    python prepare_dataset.py [OPTIONS]
+
    
+
    
+
    Options
    
+
    
+
    
++++
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
    



    Option
    Description
    --tokenizer
    Tokenizer directory or HuggingFace model name (required)
    --output
    Output JSON filename (default: preprocessed_dataset.json)
    --stdout
    Print output to stdout with JSON dataset entry on each line (required for trtllm-bench)
    --random-seed
    Random seed for token generation (default: 420)
    --task-id
    LoRA task ID (default: -1)
    --rand-task-id
    Random LoRA task range (two integers)
    --lora-dir
    Directory containing LoRA adapters
    --log-level
    Logging level: info or debug (default: info)
    
+
    
+
    
+
    
+
    dataset#
    
+
    Process real datasets from various sources.
    
+
    python prepare_dataset.py dataset [OPTIONS]
+
    
+
    
+
    Options
    
+
    
+
    
++++
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
    



    Option
    Description
    --input
    Input dataset file or directory (required)
    --max-input-length
    Maximum input sequence length (default: 2048)
    --max-output-length
    Maximum output sequence length (default: 512)
    --num-samples
    Number of samples to process (default: all)
    --format
    Input format: json, jsonl, csv, or txt (default: auto-detect)
    
+
    
+
    
+
    
+
    token_norm_dist#
    
+
    Generate synthetic datasets with normal token distribution.
    
+
    python prepare_dataset.py token_norm_dist [OPTIONS]
+
    
+
    
+
    Options
    
+
    
+
    
++++
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
    



    Option
    Description
    --num-requests
    Number of requests to be generated (required)
    --input-mean
    Normal distribution mean for input tokens (required)
    --input-stdev
    Normal distribution standard deviation for input tokens (required)
    --output-mean
    Normal distribution mean for output tokens (required)
    --output-stdev
    Normal distribution standard deviation for output tokens (required)
    
+
    
+
    
+
    
+
    token_unif_dist#
    
+
    Generate synthetic datasets with uniform token distribution
    
+
    python prepare_dataset.py token_unif_dist [OPTIONS]
+
    
+
    
+
    Options
    
+
    
+
    
++++
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
    



    Option
    Description
    --num-requests
    Number of requests to be generated (required)
    --input-min
    Uniform distribution minimum for input tokens (required)
    --input-max
    Uniform distribution maximum for input tokens (required)
    --output-min
    Uniform distribution minimum for output tokens (required)
    --output-max
    Uniform distribution maximum for output tokens (required)
    
+
    
+
    
+
    
+
+
+                
    
+              
+              
+              
+              
+              
+                
+              
+            
    
+            
+            
+
+
+              
+                
+                
+              
+            
+
+          
    
+          
    
+            
+          
    
+        
+      
    
+    
    
+  
    
+  
+  
+  
+
+
+  
+  
+
\ No newline at end of file
diff --git a/latest/commands/trtllm-build.html b/latest/commands/trtllm-build.html
index ab6974cdc8..d44e0d2bcf 100644
--- a/latest/commands/trtllm-build.html
+++ b/latest/commands/trtllm-build.html
@@ -58,7 +58,7 @@
     
@@ -66,11 +66,11 @@
     
     
     
-    
+    
 
   
   
-  
+  
 
 
   
@@ -349,6 +349,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    • 
 
  • Run LLM-API with pytorch backend on Slurm
    • 
 
  • Run trtllm-bench with pytorch backend on Slurm
    • 
 
  • Run trtllm-serve with pytorch backend on Slurm
    • 
@@ -384,6 +386,8 @@
 
 
    Command-Line Reference
    
 
@@ -903,12 +907,12 @@
                   
 
    
     
       
       
    
         
    previous
    
-        
    Runtime
    
+        
    trtllm-bench
    
       
    
         
     
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    
   
 
    
       
diff --git a/latest/commands/trtllm-serve.html b/latest/commands/trtllm-serve.html
index b92828aa83..59cb9a1f8d 100644
--- a/latest/commands/trtllm-serve.html
+++ b/latest/commands/trtllm-serve.html
@@ -58,7 +58,7 @@
     
@@ -70,7 +70,7 @@
 
   
   
-  
+  
 
 
   
@@ -349,6 +349,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    • 
 
  • Run LLM-API with pytorch backend on Slurm
    • 
 
  • Run trtllm-bench with pytorch backend on Slurm
    • 
 
  • Run trtllm-serve with pytorch backend on Slurm
    • 
@@ -384,6 +386,8 @@
 
 
    Command-Line Reference
    
 
@@ -1205,9 +1209,9 @@ However, for the PyTorch backend, specified with the 
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    diff --git a/latest/dev-on-cloud/build-image-to-dockerhub.html b/latest/dev-on-cloud/build-image-to-dockerhub.html index a9c2a64e3f..9fbf0fc11a 100644 --- a/latest/dev-on-cloud/build-image-to-dockerhub.html +++ b/latest/dev-on-cloud/build-image-to-dockerhub.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -347,6 +347,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -382,6 +384,8 @@

    Command-Line Reference

    @@ -670,9 +674,9 @@ docker push <your_dockerhub_use
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/dev-on-cloud/dev-on-runpod.html b/latest/dev-on-cloud/dev-on-runpod.html index d4480c7942..bdad7d6ec9 100644 --- a/latest/dev-on-cloud/dev-on-runpod.html +++ b/latest/dev-on-cloud/dev-on-runpod.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -347,6 +347,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -382,6 +384,8 @@

    Command-Line Reference

    @@ -670,9 +674,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/curl_chat_client.html b/latest/examples/curl_chat_client.html index 0a346b8407..e28863aafb 100644 --- a/latest/examples/curl_chat_client.html +++ b/latest/examples/curl_chat_client.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -641,9 +645,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/curl_chat_client_for_multimodal.html b/latest/examples/curl_chat_client_for_multimodal.html index 0049464b83..020519f8d8 100644 --- a/latest/examples/curl_chat_client_for_multimodal.html +++ b/latest/examples/curl_chat_client_for_multimodal.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -718,9 +722,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/curl_completion_client.html b/latest/examples/curl_completion_client.html index 95fe1d0ab3..a8740acf2e 100644 --- a/latest/examples/curl_completion_client.html +++ b/latest/examples/curl_completion_client.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -640,9 +644,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/customization.html b/latest/examples/customization.html index 16c2244e57..4ec7311be5 100644 --- a/latest/examples/customization.html +++ b/latest/examples/customization.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -777,9 +781,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/deepseek_r1_reasoning_parser.html b/latest/examples/deepseek_r1_reasoning_parser.html index 813213d34b..fb91ff1e3b 100644 --- a/latest/examples/deepseek_r1_reasoning_parser.html +++ b/latest/examples/deepseek_r1_reasoning_parser.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -641,9 +645,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/genai_perf_client.html b/latest/examples/genai_perf_client.html index 8c7817956c..27956b860d 100644 --- a/latest/examples/genai_perf_client.html +++ b/latest/examples/genai_perf_client.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -646,9 +650,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/genai_perf_client_for_multimodal.html b/latest/examples/genai_perf_client_for_multimodal.html index a70ea3e24c..6a561c1d46 100644 --- a/latest/examples/genai_perf_client_for_multimodal.html +++ b/latest/examples/genai_perf_client_for_multimodal.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -649,9 +653,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/index.html b/latest/examples/index.html index 7e916369a9..f0778a2411 100644 --- a/latest/examples/index.html +++ b/latest/examples/index.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -494,34 +498,39 @@

    LLM Examples Introduction#

    Here is a simple example to show how to use the LLM with TinyLlama.

    -
     1from tensorrt_llm import SamplingParams
- 2from tensorrt_llm._tensorrt_engine import LLM
+
     1from tensorrt_llm import LLM, SamplingParams
+ 2
  3
- 4
- 5def main():
- 6
- 7    prompts = [
- 8        "Hello, my name is",
- 9        "The capital of France is",
-10        "The future of AI is",
-11    ]
-12    sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
-13
-14    # Alternatively, use "nvidia/Llama-3.1-8B-Instruct-FP8" to enable FP8 inference.
-15    llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+ 4def main():
+ 5
+ 6    # Model could accept HF model name, a path to local HF model,
+ 7    # or TensorRT Model Optimizer's quantized checkpoints like nvidia/Llama-3.1-8B-Instruct-FP8 on HF.
+ 8    llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+ 9
+10    # Sample prompts.
+11    prompts = [
+12        "Hello, my name is",
+13        "The capital of France is",
+14        "The future of AI is",
+15    ]
 16
-17    outputs = llm.generate(prompts, sampling_params)
-18
-19    # Print the outputs.
-20    for output in outputs:
-21        prompt = output.prompt
-22        generated_text = output.outputs[0].text
-23        print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+17    # Create a sampling params.
+18    sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
+19
+20    for output in llm.generate(prompts, sampling_params):
+21        print(
+22            f"Prompt: {output.prompt!r}, Generated text: {output.outputs[0].text!r}"
+23        )
 24
-25
-26# The entry point of the program need to be protected for spawning processes.
-27if __name__ == '__main__':
-28    main()
+25    # Got output like
+26    # Prompt: 'Hello, my name is', Generated text: '\n\nJane Smith. I am a student pursuing my degree in Computer Science at [university]. I enjoy learning new things, especially technology and programming'
+27    # Prompt: 'The president of the United States is', Generated text: 'likely to nominate a new Supreme Court justice to fill the seat vacated by the death of Antonin Scalia. The Senate should vote to confirm the'
+28    # Prompt: 'The capital of France is', Generated text: 'Paris.'
+29    # Prompt: 'The future of AI is', Generated text: 'an exciting time for us. We are constantly researching, developing, and improving our platform to create the most advanced and efficient model available. We are'
+30
+31
+32if __name__ == '__main__':
+33    main()
 
    
 
    
 
    The LLM API can be used for both offline or online usage. See more examples of the LLM API here:
    
@@ -662,9 +671,9 @@
         
    
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    
   
 
    
       
diff --git a/latest/examples/llm_api_examples.html b/latest/examples/llm_api_examples.html
index 98208f88d8..f947c43992 100644
--- a/latest/examples/llm_api_examples.html
+++ b/latest/examples/llm_api_examples.html
@@ -58,7 +58,7 @@
     
@@ -70,7 +70,7 @@
 
   
   
-  
+  
 
 
   
@@ -349,6 +349,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    • 
 
  • Run LLM-API with pytorch backend on Slurm
    • 
 
  • Run trtllm-bench with pytorch backend on Slurm
    • 
 
  • Run trtllm-serve with pytorch backend on Slurm
    • 
@@ -384,6 +386,8 @@
 
 
    Command-Line Reference
    
 
@@ -516,6 +520,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    •
    @@ -677,9 +683,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/llm_guided_decoding.html b/latest/examples/llm_guided_decoding.html index 0128ae1575..564fbc28e4 100644 --- a/latest/examples/llm_guided_decoding.html +++ b/latest/examples/llm_guided_decoding.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -503,47 +507,44 @@ 4 5def main(): 6 - 7 # Specify the guided decoding backend; xgrammar is supported currently. - 8 llm = LLM( - 9 model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", -10 guided_decoding_backend='xgrammar', -11 disable_overlap_scheduler=True # Not supported by xgrammar mode -12 ) + 7 # Specify the guided decoding backend; xgrammar and llguidance are supported currently. + 8 llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", + 9 guided_decoding_backend='xgrammar') +10 +11 # An example from json-mode-eval +12 schema = '{"title": "WirelessAccessPoint", "type": "object", "properties": {"ssid": {"title": "SSID", "type": "string"}, "securityProtocol": {"title": "SecurityProtocol", "type": "string"}, "bandwidth": {"title": "Bandwidth", "type": "string"}}, "required": ["ssid", "securityProtocol", "bandwidth"]}' 13 -14 # An example from json-mode-eval -15 schema = '{"title": "WirelessAccessPoint", "type": "object", "properties": {"ssid": {"title": "SSID", "type": "string"}, "securityProtocol": {"title": "SecurityProtocol", "type": "string"}, "bandwidth": {"title": "Bandwidth", "type": "string"}}, "required": ["ssid", "securityProtocol", "bandwidth"]}' -16 -17 prompt = [{ -18 'role': -19 'system', -20 'content': -21 "You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{'title': 'WirelessAccessPoint', 'type': 'object', 'properties': {'ssid': {'title': 'SSID', 'type': 'string'}, 'securityProtocol': {'title': 'SecurityProtocol', 'type': 'string'}, 'bandwidth': {'title': 'Bandwidth', 'type': 'string'}}, 'required': ['ssid', 'securityProtocol', 'bandwidth']}\n</schema>\n" -22 }, { -23 'role': -24 'user', -25 'content': -26 "I'm currently configuring a wireless access point for our office network and I need to generate a JSON object that accurately represents its settings. The access point's SSID should be 'OfficeNetSecure', it uses WPA2-Enterprise as its security protocol, and it's capable of a bandwidth of up to 1300 Mbps on the 5 GHz band. This JSON object will be used to document our network configurations and to automate the setup process for additional access points in the future. Please provide a JSON object that includes these details." -27 }] -28 prompt = llm.tokenizer.apply_chat_template(prompt, tokenize=False) -29 print(f"Prompt: {prompt!r}") +14 prompt = [{ +15 'role': +16 'system', +17 'content': +18 "You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{'title': 'WirelessAccessPoint', 'type': 'object', 'properties': {'ssid': {'title': 'SSID', 'type': 'string'}, 'securityProtocol': {'title': 'SecurityProtocol', 'type': 'string'}, 'bandwidth': {'title': 'Bandwidth', 'type': 'string'}}, 'required': ['ssid', 'securityProtocol', 'bandwidth']}\n</schema>\n" +19 }, { +20 'role': +21 'user', +22 'content': +23 "I'm currently configuring a wireless access point for our office network and I need to generate a JSON object that accurately represents its settings. The access point's SSID should be 'OfficeNetSecure', it uses WPA2-Enterprise as its security protocol, and it's capable of a bandwidth of up to 1300 Mbps on the 5 GHz band. This JSON object will be used to document our network configurations and to automate the setup process for additional access points in the future. Please provide a JSON object that includes these details." +24 }] +25 prompt = llm.tokenizer.apply_chat_template(prompt, tokenize=False) +26 print(f"Prompt: {prompt!r}") +27 +28 output = llm.generate(prompt, sampling_params=SamplingParams(max_tokens=50)) +29 print(f"Generated text (unguided): {output.outputs[0].text!r}") 30 -31 output = llm.generate(prompt, sampling_params=SamplingParams(max_tokens=50)) -32 print(f"Generated text (unguided): {output.outputs[0].text!r}") -33 -34 output = llm.generate( -35 prompt, -36 sampling_params=SamplingParams( -37 max_tokens=50, guided_decoding=GuidedDecodingParams(json=schema))) -38 print(f"Generated text (guided): {output.outputs[0].text!r}") -39 -40 # Got output like -41 # Prompt: "<|system|>\nYou are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{'title': 'WirelessAccessPoint', 'type': 'object', 'properties': {'ssid': {'title': 'SSID', 'type': 'string'}, 'securityProtocol': {'title': 'SecurityProtocol', 'type': 'string'}, 'bandwidth': {'title': 'Bandwidth', 'type': 'string'}}, 'required': ['ssid', 'securityProtocol', 'bandwidth']}\n</schema>\n</s>\n<|user|>\nI'm currently configuring a wireless access point for our office network and I need to generate a JSON object that accurately represents its settings. The access point's SSID should be 'OfficeNetSecure', it uses WPA2-Enterprise as its security protocol, and it's capable of a bandwidth of up to 1300 Mbps on the 5 GHz band. This JSON object will be used to document our network configurations and to automate the setup process for additional access points in the future. Please provide a JSON object that includes these details.</s>\n" -42 # Generated text (unguided): '<|assistant|>\nHere\'s a JSON object that accurately represents the settings of a wireless access point for our office network:\n\n```json\n{\n "title": "WirelessAccessPoint",\n "' -43 # Generated text (guided): '{"ssid": "OfficeNetSecure", "securityProtocol": "WPA2-Enterprise", "bandwidth": "1300 Mbps"}' -44 -45 -46if __name__ == '__main__': -47 main() +31 output = llm.generate( +32 prompt, +33 sampling_params=SamplingParams( +34 max_tokens=50, guided_decoding=GuidedDecodingParams(json=schema))) +35 print(f"Generated text (guided): {output.outputs[0].text!r}") +36 +37 # Got output like +38 # Prompt: "<|system|>\nYou are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{'title': 'WirelessAccessPoint', 'type': 'object', 'properties': {'ssid': {'title': 'SSID', 'type': 'string'}, 'securityProtocol': {'title': 'SecurityProtocol', 'type': 'string'}, 'bandwidth': {'title': 'Bandwidth', 'type': 'string'}}, 'required': ['ssid', 'securityProtocol', 'bandwidth']}\n</schema>\n</s>\n<|user|>\nI'm currently configuring a wireless access point for our office network and I need to generate a JSON object that accurately represents its settings. The access point's SSID should be 'OfficeNetSecure', it uses WPA2-Enterprise as its security protocol, and it's capable of a bandwidth of up to 1300 Mbps on the 5 GHz band. This JSON object will be used to document our network configurations and to automate the setup process for additional access points in the future. Please provide a JSON object that includes these details.</s>\n" +39 # Generated text (unguided): '<|assistant|>\nHere\'s a JSON object that accurately represents the settings of a wireless access point for our office network:\n\n```json\n{\n "title": "WirelessAccessPoint",\n "' +40 # Generated text (guided): '{"ssid": "OfficeNetSecure", "securityProtocol": "WPA2-Enterprise", "bandwidth": "1300 Mbps"}' +41 +42 +43if __name__ == '__main__': +44 main()
    @@ -676,9 +677,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/llm_inference.html b/latest/examples/llm_inference.html index 40091192fe..d52ba9db56 100644 --- a/latest/examples/llm_inference.html +++ b/latest/examples/llm_inference.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -661,9 +665,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/llm_inference_async.html b/latest/examples/llm_inference_async.html index f6f1b697d0..e069723627 100644 --- a/latest/examples/llm_inference_async.html +++ b/latest/examples/llm_inference_async.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -669,9 +673,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/llm_inference_async_streaming.html b/latest/examples/llm_inference_async_streaming.html index 2554ef2664..58e6bd23e8 100644 --- a/latest/examples/llm_inference_async_streaming.html +++ b/latest/examples/llm_inference_async_streaming.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -690,9 +694,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/llm_inference_distributed.html b/latest/examples/llm_inference_distributed.html index f5c8b7c7a9..f5739d440e 100644 --- a/latest/examples/llm_inference_distributed.html +++ b/latest/examples/llm_inference_distributed.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -670,9 +674,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/llm_logits_processor.html b/latest/examples/llm_logits_processor.html index 99f9f396f7..94dd0b7510 100644 --- a/latest/examples/llm_logits_processor.html +++ b/latest/examples/llm_logits_processor.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -754,9 +758,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/llm_mgmn_llm_distributed.html b/latest/examples/llm_mgmn_llm_distributed.html index e2b1dedf4d..0632c9fb8f 100644 --- a/latest/examples/llm_mgmn_llm_distributed.html +++ b/latest/examples/llm_mgmn_llm_distributed.html @@ -58,7 +58,7 @@ @@ -66,11 +66,11 @@ - + - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -564,12 +568,12 @@

    previous

    -

    Speculative Decoding

    +

    Sampling Techniques Showcase
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/llm_mgmn_trtllm_bench.html b/latest/examples/llm_mgmn_trtllm_bench.html index ac463b9fc8..b85330b0c1 100644 --- a/latest/examples/llm_mgmn_trtllm_bench.html +++ b/latest/examples/llm_mgmn_trtllm_bench.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -720,9 +724,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/llm_mgmn_trtllm_serve.html b/latest/examples/llm_mgmn_trtllm_serve.html index 3b0249ae54..b67b12f5d4 100644 --- a/latest/examples/llm_mgmn_trtllm_serve.html +++ b/latest/examples/llm_mgmn_trtllm_serve.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -683,9 +687,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/llm_multilora.html b/latest/examples/llm_multilora.html index 66ae212920..2c8462c8c1 100644 --- a/latest/examples/llm_multilora.html +++ b/latest/examples/llm_multilora.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -688,9 +692,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/llm_runtime.html b/latest/examples/llm_runtime.html new file mode 100644 index 0000000000..f449aefdaf --- /dev/null +++ b/latest/examples/llm_runtime.html @@ -0,0 +1,744 @@ + + + + + + + + + + + + Runtime Configuration Examples — TensorRT-LLM + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
    + + + + + + +
    + + + Ctrl+K +
    +     + +
    + +
    + + +
    +
    + + + +
    + +
    + + + + + +
    + +
    + +
    + +
    + +
    + + +
    + +
    + +
    +
    + +
    + + +
    + +
    + + + +
    + + +
    + +
    + +
    + +
    + + +
    + + +
    + + + +
    + +
    + + +
    +
    + + + + +
    + + + + + + + + + + + + +
    + + +
    + + + +
    + + +
    + +
    + +
    +
    + + +
    + + + +
    + +
    + +
    + +
    + +
    + +
    +
    + + + +
    +
    + + +
    +
    + + + +
    + +
    + + +
    +
    + +
    +
    + +
    + +
    + + +
    + +
    + + +
    +
    + + + + + +
    + +
    +

    Runtime Configuration Examples#

    +

    Source NVIDIA/TensorRT-LLM.

    +
     1
+ 2import argparse
+ 3
+ 4from tensorrt_llm import LLM, SamplingParams
+ 5from tensorrt_llm.llmapi import CudaGraphConfig, KvCacheConfig
+ 6
+ 7
+ 8def example_cuda_graph_config():
+ 9    """
+10    Example demonstrating CUDA graph configuration for performance optimization.
+11
+12    CUDA graphs help with:
+13    - Reduced kernel launch overhead
+14    - Better GPU utilization
+15    - Improved throughput for repeated operations
+16    """
+17    print("\n=== CUDA Graph Configuration Example ===")
+18
+19    cuda_graph_config = CudaGraphConfig(
+20        batch_sizes=[1, 2, 4],
+21        enable_padding=True,
+22    )
+23
+24    llm = LLM(
+25        model="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+26        cuda_graph_config=cuda_graph_config,  # Enable CUDA graphs
+27        max_batch_size=4,
+28        max_seq_len=512,
+29        kv_cache_config=KvCacheConfig(free_gpu_memory_fraction=0.8,
+30                                      enable_block_reuse=True))
+31
+32    prompts = [
+33        "Hello, my name is",
+34        "The capital of France is",
+35        "The future of AI is",
+36    ]
+37
+38    sampling_params = SamplingParams(max_tokens=50, temperature=0.8, top_p=0.95)
+39
+40    # This should benefit from CUDA graphs
+41    outputs = llm.generate(prompts, sampling_params)
+42    for output in outputs:
+43        print(f"Prompt: {output.prompt}")
+44        print(f"Generated: {output.outputs[0].text}")
+45        print()
+46
+47
+48def example_kv_cache_config():
+49    print("\n=== KV Cache Configuration Example ===")
+50    print("\n1. KV Cache Configuration:")
+51
+52    llm_advanced = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+53                       max_batch_size=8,
+54                       max_seq_len=1024,
+55                       kv_cache_config=KvCacheConfig(
+56                           free_gpu_memory_fraction=0.85,
+57                           enable_block_reuse=True))
+58
+59    prompts = [
+60        "Hello, my name is",
+61        "The capital of France is",
+62        "The future of AI is",
+63    ]
+64
+65    outputs = llm_advanced.generate(prompts)
+66    for i, output in enumerate(outputs):
+67        print(f"Query {i+1}: {output.prompt}")
+68        print(f"Answer: {output.outputs[0].text[:100]}...")
+69        print()
+70
+71
+72def main():
+73    """
+74    Main function to run all runtime configuration examples.
+75    """
+76    parser = argparse.ArgumentParser(
+77        description="Runtime Configuration Examples")
+78    parser.add_argument("--example",
+79                        type=str,
+80                        choices=["kv_cache", "cuda_graph", "all"],
+81                        default="all",
+82                        help="Which example to run")
+83
+84    args = parser.parse_args()
+85
+86    if args.example == "kv_cache" or args.example == "all":
+87        example_kv_cache_config()
+88
+89    if args.example == "cuda_graph" or args.example == "all":
+90        example_cuda_graph_config()
+91
+92
+93if __name__ == "__main__":
+94    main()
+
    +
    +
    + + +
    + + + + + + + +
    + + + +
    + + + + + +
    +
    + +
    + +
    +
    +
    + + + + + + + + \ No newline at end of file diff --git a/latest/examples/llm_sampling.html b/latest/examples/llm_sampling.html new file mode 100644 index 0000000000..ae4fc9bb57 --- /dev/null +++ b/latest/examples/llm_sampling.html @@ -0,0 +1,876 @@ + + + + + + + + + + + + Sampling Techniques Showcase — TensorRT-LLM + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
    + + + + + + +
    + + + Ctrl+K +
    +     + +
    + +
    + + +
    +
    + + + +
    + +
    + + + + + +
    + +
    + +
    + +
    + +
    + + +
    + +
    + +
    +
    + +
    + + +
    + +
    + + + +
    + + +
    + +
    + +
    + +
    + + +
    + + +
    + + + +
    + +
    + + +
    +
    + + + + +
    + + + + + + + + + + + + +
    + + +
    + + + +
    + + +
    + +
    + +
    +
    + + +
    + + + +
    + +
    + +
    + +
    + +
    + +
    +
    + + + +
    +
    + + +
    +
    + + + +
    + +
    + + +
    +
    + +
    +
    + +
    + +
    + + +
    + +
    + + +
    +
    + + + + + +
    + +
    +

    Sampling Techniques Showcase#

    +

    Source NVIDIA/TensorRT-LLM.

    +
      1"""
+  2This example demonstrates various sampling techniques available in TensorRT-LLM.
+  3It showcases different sampling parameters and their effects on text generation.
+  4"""
+  5
+  6from typing import Optional
+  7
+  8import click
+  9
+ 10from tensorrt_llm import LLM, SamplingParams
+ 11
+ 12# Example prompts to demonstrate different sampling techniques
+ 13prompts = [
+ 14    "What is the future of artificial intelligence?",
+ 15    "Describe a beautiful sunset over the ocean.",
+ 16    "Write a short story about a robot discovering emotions.",
+ 17]
+ 18
+ 19
+ 20def demonstrate_greedy_decoding(prompt: str):
+ 21    """Demonstrates greedy decoding with temperature=0."""
+ 22    print("\n🎯 === GREEDY DECODING ===")
+ 23    print("Using temperature=0 for deterministic, focused output")
+ 24
+ 25    llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+ 26
+ 27    sampling_params = SamplingParams(
+ 28        max_tokens=50,
+ 29        temperature=0.0,  # Greedy decoding
+ 30    )
+ 31
+ 32    response = llm.generate(prompt, sampling_params)
+ 33    print(f"Prompt: {prompt}")
+ 34    print(f"Response: {response.outputs[0].text}")
+ 35
+ 36
+ 37def demonstrate_temperature_sampling(prompt: str):
+ 38    """Demonstrates temperature sampling with different temperature values."""
+ 39    print("\n🌡️ === TEMPERATURE SAMPLING ===")
+ 40    print(
+ 41        "Higher temperature = more creative/random, Lower temperature = more focused"
+ 42    )
+ 43
+ 44    llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+ 45
+ 46    temperatures = [0.3, 0.7, 1.0, 1.5]
+ 47    for temp in temperatures:
+ 48
+ 49        sampling_params = SamplingParams(
+ 50            max_tokens=50,
+ 51            temperature=temp,
+ 52        )
+ 53
+ 54        response = llm.generate(prompt, sampling_params)
+ 55        print(f"Temperature {temp}: {response.outputs[0].text}")
+ 56
+ 57
+ 58def demonstrate_top_k_sampling(prompt: str):
+ 59    """Demonstrates top-k sampling with different k values."""
+ 60    print("\n🔝 === TOP-K SAMPLING ===")
+ 61    print("Only consider the top-k most likely tokens at each step")
+ 62
+ 63    llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+ 64
+ 65    top_k_values = [1, 5, 20, 50]
+ 66
+ 67    for k in top_k_values:
+ 68        sampling_params = SamplingParams(
+ 69            max_tokens=50,
+ 70            temperature=0.8,  # Use moderate temperature
+ 71            top_k=k,
+ 72        )
+ 73
+ 74        response = llm.generate(prompt, sampling_params)
+ 75        print(f"Top-k {k}: {response.outputs[0].text}")
+ 76
+ 77
+ 78def demonstrate_top_p_sampling(prompt: str):
+ 79    """Demonstrates top-p (nucleus) sampling with different p values."""
+ 80    print("\n🎯 === TOP-P (NUCLEUS) SAMPLING ===")
+ 81    print("Only consider tokens whose cumulative probability is within top-p")
+ 82
+ 83    llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+ 84
+ 85    top_p_values = [0.1, 0.5, 0.9, 0.95]
+ 86
+ 87    for p in top_p_values:
+ 88        sampling_params = SamplingParams(
+ 89            max_tokens=50,
+ 90            temperature=0.8,  # Use moderate temperature
+ 91            top_p=p,
+ 92        )
+ 93
+ 94        response = llm.generate(prompt, sampling_params)
+ 95        print(f"Top-p {p}: {response.outputs[0].text}")
+ 96
+ 97
+ 98def demonstrate_combined_sampling(prompt: str):
+ 99    """Demonstrates combined top-k and top-p sampling."""
+100    print("\n🔄 === COMBINED TOP-K + TOP-P SAMPLING ===")
+101    print("Using both top-k and top-p together for balanced control")
+102
+103    llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+104
+105    sampling_params = SamplingParams(
+106        max_tokens=50,
+107        temperature=0.8,
+108        top_k=40,  # Consider top 40 tokens
+109        top_p=0.9,  # Within 90% cumulative probability
+110    )
+111
+112    response = llm.generate(prompt, sampling_params)
+113    print(f"Combined (k=40, p=0.9): {response.outputs[0].text}")
+114
+115
+116def demonstrate_multiple_sequences(prompt: str):
+117    """Demonstrates generating multiple sequences with different sampling."""
+118    print("\n📚 === MULTIPLE SEQUENCES ===")
+119    print("Generate multiple different responses for the same prompt")
+120
+121    llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+122
+123    sampling_params = SamplingParams(
+124        max_tokens=40,
+125        temperature=0.8,
+126        top_k=50,
+127        top_p=0.95,
+128        n=3,  # Generate 3 different sequences
+129    )
+130
+131    response = llm.generate(prompt, sampling_params)
+132    print(f"Prompt: {prompt}")
+133    for i, output in enumerate(response.outputs):
+134        print(f"Sequence {i+1}: {output.text}")
+135
+136
+137def demonstrate_with_logprobs(prompt: str):
+138    """Demonstrates generation with log probabilities."""
+139    print("\n📊 === GENERATION WITH LOG PROBABILITIES ===")
+140    print("Get probability information for generated tokens")
+141
+142    llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+143
+144    sampling_params = SamplingParams(
+145        max_tokens=20,
+146        temperature=0.7,
+147        top_k=50,
+148        logprobs=True,  # Return log probabilities
+149    )
+150
+151    response = llm.generate(prompt, sampling_params)
+152    output = response.outputs[0]
+153
+154    print(f"Prompt: {prompt}")
+155    print(f"Generated: {output.text}")
+156    print(f"Logprobs: {output.logprobs}")
+157
+158
+159def run_all_demonstrations(model_path: Optional[str] = None):
+160    """Run all sampling demonstrations."""
+161    print("🚀 TensorRT-LLM Sampling Techniques Showcase")
+162    print("=" * 50)
+163
+164    # Use the first prompt for most demonstrations
+165    demo_prompt = prompts[0]
+166
+167    # Run all demonstrations
+168    demonstrate_greedy_decoding(demo_prompt)
+169    demonstrate_temperature_sampling(demo_prompt)
+170    demonstrate_top_k_sampling(demo_prompt)
+171    demonstrate_top_p_sampling(demo_prompt)
+172    demonstrate_combined_sampling(demo_prompt)
+173    # TODO[Superjomn]: enable them once pytorch backend supports
+174    # demonstrate_multiple_sequences(llm, demo_prompt)
+175    # demonstrate_beam_search(demo_prompt)
+176    demonstrate_with_logprobs(demo_prompt)
+177
+178    print("\n🎉 All sampling demonstrations completed!")
+179
+180
+181@click.command()
+182@click.option("--model",
+183              type=str,
+184              default=None,
+185              help="Path to the model or model name")
+186@click.option("--demo",
+187              type=click.Choice([
+188                  "greedy", "temperature", "top_k", "top_p", "combined",
+189                  "multiple", "beam", "logprobs", "creative", "all"
+190              ]),
+191              default="all",
+192              help="Which demonstration to run")
+193@click.option("--prompt", type=str, default=None, help="Custom prompt to use")
+194def main(model: Optional[str], demo: str, prompt: Optional[str]):
+195    """
+196    Showcase various sampling techniques in TensorRT-LLM.
+197
+198    Examples:
+199        python llm_sampling.py --demo all
+200        python llm_sampling.py --demo temperature --prompt "Tell me a joke"
+201        python llm_sampling.py --demo beam --model path/to/your/model
+202    """
+203
+204    demo_prompt = prompt or prompts[0]
+205
+206    # Run specific demonstration
+207    if demo == "greedy":
+208        demonstrate_greedy_decoding(demo_prompt)
+209    elif demo == "temperature":
+210        demonstrate_temperature_sampling(demo_prompt)
+211    elif demo == "top_k":
+212        demonstrate_top_k_sampling(demo_prompt)
+213    elif demo == "top_p":
+214        demonstrate_top_p_sampling(demo_prompt)
+215    elif demo == "combined":
+216        demonstrate_combined_sampling(demo_prompt)
+217    elif demo == "multiple":
+218        demonstrate_multiple_sequences(demo_prompt)
+219    elif demo == "logprobs":
+220        demonstrate_with_logprobs(demo_prompt)
+221    elif demo == "all":
+222        run_all_demonstrations(model)
+223
+224
+225if __name__ == "__main__":
+226    main()
+
    +
    +
    + + +
    + + + + + + + +
    + + + +
    + + + + + +
    +
    + +
    + +
    +
    +
    + + + + + + + + \ No newline at end of file diff --git a/latest/examples/llm_speculative_decoding.html b/latest/examples/llm_speculative_decoding.html index 7e431fe689..f2c03be0a2 100644 --- a/latest/examples/llm_speculative_decoding.html +++ b/latest/examples/llm_speculative_decoding.html @@ -58,19 +58,19 @@ - + - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -610,11 +614,11 @@

    next

    -

    Run LLM-API with pytorch backend on Slurm

    +

    Runtime Configuration Examples

     @@ -718,9 +722,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/openai_chat_client.html b/latest/examples/openai_chat_client.html index 1bb8c0dd50..5fc92533cd 100644 --- a/latest/examples/openai_chat_client.html +++ b/latest/examples/openai_chat_client.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -650,9 +654,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/openai_chat_client_for_multimodal.html b/latest/examples/openai_chat_client_for_multimodal.html index 96a9a9d331..04805df860 100644 --- a/latest/examples/openai_chat_client_for_multimodal.html +++ b/latest/examples/openai_chat_client_for_multimodal.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -743,9 +747,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/openai_completion_client.html b/latest/examples/openai_completion_client.html index e6714e4ef4..8f53230c2a 100644 --- a/latest/examples/openai_completion_client.html +++ b/latest/examples/openai_completion_client.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -644,9 +648,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/openai_completion_client_for_lora.html b/latest/examples/openai_completion_client_for_lora.html index 345f0b0385..0ec57c2d7c 100644 --- a/latest/examples/openai_completion_client_for_lora.html +++ b/latest/examples/openai_completion_client_for_lora.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -660,9 +664,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/examples/trtllm_serve_examples.html b/latest/examples/trtllm_serve_examples.html index 763b1734a4..a38024c3d0 100644 --- a/latest/examples/trtllm_serve_examples.html +++ b/latest/examples/trtllm_serve_examples.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -637,9 +641,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/genindex.html b/latest/genindex.html index 4b09aa665c..7f844796ad 100644 --- a/latest/genindex.html +++ b/latest/genindex.html @@ -57,7 +57,7 @@ @@ -67,7 +67,7 @@ - + @@ -342,6 +342,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -377,6 +379,8 @@

    Command-Line Reference

    @@ -503,14 +507,38 @@ --backend +
  • + --beam_width + +
  • --cluster_size
    • +
  • + --concurrency + +
  • @@ -520,6 +548,49 @@
  • trtllm-serve-disaggregated command line option
  • trtllm-serve-disaggregated_mpi_worker command line option +
    • + +
  • + --dataset + +
    • +
  • + --enable_chunked_context + +
    • +
  • + --engine_dir + +
    • +
  • + --eos_id + +
    • +
  • + --ep + +
  • @@ -533,6 +604,8 @@ --extra_llm_api_options
    • @@ -548,6 +621,24 @@ +
  • + --iteration_log + +
    • +
  • + --kv_cache_free_gpu_mem_fraction + +
  • @@ -561,6 +652,8 @@ --log_level
    • +
  • + --modality + +
    • +
  • + --model + +
    • @@ -856,6 +1150,12 @@

    B

    - + - + + + + - - - @@ -850,9 +854,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/torch/features/overlap_scheduler.html b/latest/torch/features/overlap_scheduler.html index ea15a671af..f350eba9b6 100644 --- a/latest/torch/features/overlap_scheduler.html +++ b/latest/torch/features/overlap_scheduler.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -347,6 +347,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -382,6 +384,8 @@

    Command-Line Reference

    @@ -650,9 +654,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/torch/features/quantization.html b/latest/torch/features/quantization.html index ee450dd5e9..2a60a68f5b 100644 --- a/latest/torch/features/quantization.html +++ b/latest/torch/features/quantization.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -343,6 +343,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -378,6 +380,8 @@

    Command-Line Reference

    @@ -616,9 +620,9 @@ scripts/huggingface_example.sh --model
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/torch/features/sampling.html b/latest/torch/features/sampling.html index 16a2a96e5b..fe91f9aee1 100644 --- a/latest/torch/features/sampling.html +++ b/latest/torch/features/sampling.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -343,6 +343,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -378,6 +380,8 @@

    Command-Line Reference

    @@ -618,9 +622,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/torch/kv_cache_manager.html b/latest/torch/kv_cache_manager.html index fbba15d257..fb59be796d 100644 --- a/latest/torch/kv_cache_manager.html +++ b/latest/torch/kv_cache_manager.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -347,6 +347,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -382,6 +384,8 @@

    Command-Line Reference

    @@ -692,9 +696,9 @@ Then, test it to ensure the
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/torch/scheduler.html b/latest/torch/scheduler.html index bb8ac405c5..824d94bd7c 100644 --- a/latest/torch/scheduler.html +++ b/latest/torch/scheduler.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -347,6 +347,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -382,6 +384,8 @@

    Command-Line Reference

    @@ -717,9 +721,9 @@ In the create_pytor
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    +
  • checkpoint_format (tensorrt_llm.llmapi.TorchLlmArgs attribute) +
    • +
  • checkpoint_loader (tensorrt_llm.llmapi.TorchLlmArgs attribute) +
  • choices() (tensorrt_llm.functional.PositionEmbeddingType static method)
  • chunk() (in module tensorrt_llm.functional) @@ -1143,6 +1447,8 @@
  • create_sinusoidal_positions_for_cogvlm_attention_plugin() (tensorrt_llm.functional.RopeEmbeddingUtils static method)
  • create_sinusoidal_positions_long_rope() (tensorrt_llm.functional.RopeEmbeddingUtils method) +
    • +
  • create_sinusoidal_positions_long_rope_for_attention_plugin() (tensorrt_llm.functional.RopeEmbeddingUtils static method)
  • create_sinusoidal_positions_yarn() (tensorrt_llm.functional.RopeEmbeddingUtils static method)
    • @@ -1293,6 +1599,8 @@
  • dtype (tensorrt_llm.functional.Tensor property)

    • Command-Line Reference

    @@ -851,9 +855,9 @@ pip install ./build/tensorrt_llm*.
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/installation/containers.html b/latest/installation/containers.html index d24db21141..2f77754db0 100644 --- a/latest/installation/containers.html +++ b/latest/installation/containers.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -499,7 +503,7 @@ on NGC. This is likely the simplest way to obtain TensorRT-LLM. Please refer to

    Container image tags

    In the example shell commands, x.y.z corresponds to the TensorRT-LLM container version to use. If omitted, IMAGE_TAG will default to tensorrt_llm.__version__ -(e.g., this documentation was generated from the 1.0.0rc3 source tree). +(e.g., this documentation was generated from the 1.0.0rc4 source tree). If this does not work, e.g., because a container for the version you are currently working with has not been released yet, you can try using a container published for a previous @@ -639,9 +643,9 @@ for all related options.

    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/installation/linux.html b/latest/installation/linux.html index e7a2309acf..422cc01498 100644 --- a/latest/installation/linux.html +++ b/latest/installation/linux.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -519,34 +523,39 @@ image hosted on NGC

  • Sanity check the installation by running the following in Python (tested on Python 3.12):

    -
     1from tensorrt_llm import SamplingParams
- 2from tensorrt_llm._tensorrt_engine import LLM
+
     1from tensorrt_llm import LLM, SamplingParams
+ 2
  3
- 4
- 5def main():
- 6
- 7    prompts = [
- 8        "Hello, my name is",
- 9        "The capital of France is",
-10        "The future of AI is",
-11    ]
-12    sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
-13
-14    # Alternatively, use "nvidia/Llama-3.1-8B-Instruct-FP8" to enable FP8 inference.
-15    llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+ 4def main():
+ 5
+ 6    # Model could accept HF model name, a path to local HF model,
+ 7    # or TensorRT Model Optimizer's quantized checkpoints like nvidia/Llama-3.1-8B-Instruct-FP8 on HF.
+ 8    llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+ 9
+10    # Sample prompts.
+11    prompts = [
+12        "Hello, my name is",
+13        "The capital of France is",
+14        "The future of AI is",
+15    ]
 16
-17    outputs = llm.generate(prompts, sampling_params)
-18
-19    # Print the outputs.
-20    for output in outputs:
-21        prompt = output.prompt
-22        generated_text = output.outputs[0].text
-23        print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+17    # Create a sampling params.
+18    sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
+19
+20    for output in llm.generate(prompts, sampling_params):
+21        print(
+22            f"Prompt: {output.prompt!r}, Generated text: {output.outputs[0].text!r}"
+23        )
 24
-25
-26# The entry point of the program need to be protected for spawning processes.
-27if __name__ == '__main__':
-28    main()
+25    # Got output like
+26    # Prompt: 'Hello, my name is', Generated text: '\n\nJane Smith. I am a student pursuing my degree in Computer Science at [university]. I enjoy learning new things, especially technology and programming'
+27    # Prompt: 'The president of the United States is', Generated text: 'likely to nominate a new Supreme Court justice to fill the seat vacated by the death of Antonin Scalia. The Senate should vote to confirm the'
+28    # Prompt: 'The capital of France is', Generated text: 'Paris.'
+29    # Prompt: 'The future of AI is', Generated text: 'an exciting time for us. We are constantly researching, developing, and improving our platform to create the most advanced and efficient model available. We are'
+30
+31
+32if __name__ == '__main__':
+33    main()
    • @@ -706,9 +715,9 @@ Please install CUDA toolkit when you see the following message when running Mode
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/key-features.html b/latest/key-features.html index f621aceb5a..ac9ac8d315 100644 --- a/latest/key-features.html +++ b/latest/key-features.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -632,9 +636,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/llm-api/index.html b/latest/llm-api/index.html index 4fd9cfa5db..a34d6bf052 100644 --- a/latest/llm-api/index.html +++ b/latest/llm-api/index.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -709,9 +713,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/llm-api/reference.html b/latest/llm-api/reference.html index ef46e2c1c7..d442a17f1d 100644 --- a/latest/llm-api/reference.html +++ b/latest/llm-api/reference.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -541,7 +545,6 @@

  • load_format (Union[str, tensorrt_llm.llmapi.llm_args.LoadFormat]) – How to load the model weights. By default, detect the weight type from the model checkpoint. Defaults to 0.

  • enable_lora (bool) – Enable LoRA. Defaults to False.

  • lora_config (Optional[tensorrt_llm.lora_manager.LoraConfig]) – LoRA configuration for the model. Defaults to None.

    • -

  • quant_config (Optional[tensorrt_llm.models.modeling_utils.QuantConfig]) – Quantization config. Defaults to None.

  • kv_cache_config (tensorrt_llm.llmapi.llm_args.KvCacheConfig) – KV cache config. Defaults to None.

  • enable_chunked_prefill (bool) – Enable chunked prefill. Defaults to False.

  • guided_decoding_backend (Optional[Literal['xgrammar', 'llguidance']]) – Guided decoding backend. llguidance is supported in PyTorch backend only. Defaults to None.

    • @@ -568,13 +571,10 @@

  • garbage_collection_gen0_threshold (int) – Threshold for Python garbage collection of generation 0 objects.Lower values trigger more frequent garbage collection. Defaults to 20000.

  • cuda_graph_config (Optional[tensorrt_llm.llmapi.llm_args.CudaGraphConfig]) – CUDA graph config.If true, use CUDA graphs for decoding. CUDA graphs are only created for the batch sizes in cuda_graph_config.batch_sizes, and are enabled for batches that consist of decoding requests only (the reason is that it’s hard to capture a single graph with prefill requests since the input shapes are a function of the sequence lengths). Note that each CUDA graph can use up to 200 MB of extra memory. Defaults to None.

  • disable_overlap_scheduler (bool) – Disable the overlap scheduler. Defaults to False.

    • -

  • moe_max_num_tokens (Optional[int]) – If set, at most moe_max_num_tokens tokens will be sent to torch.ops.trtllm.fused_moe at the same time. If the number of tokens exceeds moe_max_num_tokens, the input tensors will be split into chunks and a for loop will be used. Defaults to None.

    • -

  • moe_load_balancer (Union[tensorrt_llm._torch.model_config.MoeLoadBalancerConfig, str, None]) – Configuration for MoE load balancing. Defaults to None.

    • +

  • moe_config (tensorrt_llm.llmapi.llm_args.MoeConfig) – MoE config. Defaults to None.

  • attn_backend (str) – Attention backend to use. Defaults to TRTLLM.

    • -

  • moe_backend (str) – MoE backend to use. Defaults to CUTLASS.

  • enable_mixed_sampler (bool) – If true, will iterate over sampling_params of each request and use the corresponding sampling strategy, e.g. top-k, top-p, etc. Defaults to False.

  • enable_trtllm_sampler (bool) – If true, will use the TRTLLM sampler instead of the PyTorch sampler. The TRTLLM sampler has a wide coverage of sampling strategies. Defaults to False.

    • -

  • kv_cache_dtype (str) – Data type for KV cache. Defaults to auto.

  • enable_iter_perf_stats (bool) – Enable iteration performance statistics. Defaults to False.

  • enable_iter_req_stats (bool) – If true, enables per request stats per iteration. Must also set enable_iter_perf_stats to true to get request stats. Defaults to False.

  • print_iter_log (bool) – Print iteration logs. Defaults to False.

    • @@ -585,6 +585,8 @@

  • stream_interval (int) – The iteration interval to create responses under the streaming mode. Set this to a larger value when the batch size is large, which helps reduce the streaming overhead. Defaults to 1.

  • force_dynamic_quantization (bool) – If true, force dynamic quantization. Defaults to False. Defaults to False.

  • allreduce_strategy (Optional[Literal['AUTO', 'NCCL', 'UB', 'MINLATENCY', 'ONESHOT', 'TWOSHOT', 'LOWPRECISION', 'MNNVL']]) – Allreduce strategy to use. Defaults to AUTO.

    • +

  • checkpoint_loader (Optional[tensorrt_llm._torch.BaseCheckpointLoader]) – The checkpoint loader to use for this LLM instance. Defaults to None.

    • +

  • checkpoint_format (Optional[str]) – The format of the provided checkpoint. Defaults to None.

    • @@ -1617,11 +1619,11 @@ The BatchedLogitsProcessor class is recommended for callback creation. The callb )[source]#

    Bases: object

    -

    Disaggregated seving parameters.

    +

    Disaggregated serving parameters.

    Parameters:
      -

    • request_type (str) – The type of request (“context_only” or “generation_only”)

      • +

    • request_type (str) – The type of request (“context_only” | “generation_only” | “context_and_generation”)

    • first_gen_tokens (List[int]) – The first tokens of the generation request

    • ctx_request_id (int) – The context request id

    • opaque_state (bytes) – Any additional state needing to be exchanged between context and gen instances

      • @@ -1700,6 +1702,7 @@ The BatchedLogitsProcessor class is recommended for callback creation. The callb
      enable_partial_reuse: bool = True,
      copy_on_partial_reuse: bool = True,
      use_uvm: bool = False,
      +
      dtype: str = 'auto',
    )[source]# @@ -1717,6 +1720,12 @@ The BatchedLogitsProcessor class is recommended for callback creation. The callb

    The fraction of the KV Cache memory should be reserved for cross attention. If set to p, self attention will use 1-p of KV Cache memory and cross attention will use p of KV Cache memory. Default is 50%. Should only be set when using encoder-decoder model.

    +
    +
    +field dtype: str = 'auto'#
    +

    The data type to use for the KV cache.

    +
    +
    field enable_block_reuse: bool = True#
    @@ -1887,7 +1896,7 @@ The BatchedLogitsProcessor class is recommended for callback creation. The callb
    *,
    batch_sizes: List[int] | None = None,
    max_batch_size: int = 0,
    -
    padding_enabled: bool = False,
    +
    enable_padding: bool = False,
    )[source]# @@ -1899,6 +1908,12 @@ The BatchedLogitsProcessor class is recommended for callback creation. The callb

    List of batch sizes to create CUDA graphs for.

    +
    +
    +field enable_padding: bool = False#
    +

    If true, batches are rounded up to the nearest cuda_graph_batch_size. This is usually a net win for performance.

    +
    +
    field max_batch_size: int = 0#
    @@ -1918,12 +1933,6 @@ The BatchedLogitsProcessor class is recommended for callback creation. The callb

    Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

    -
    -
    -field padding_enabled: bool = False#
    -

    If true, batches are rounded up to the nearest cuda_graph_batch_size. This is usually a net win for performance.

    -
    -
    validator validate_cuda_graph_max_batch_size  »  max_batch_size[source]#
    @@ -1932,6 +1941,51 @@ The BatchedLogitsProcessor class is recommended for callback creation. The callb
    +
    +
    +class tensorrt_llm.llmapi.MoeConfig( + +
    +
    *,
    +
    backend: Literal['CUTLASS', 'CUTEDSL', 'WIDEEP', 'TRTLLM', 'VANILLA'] = 'CUTLASS',
    +
    max_num_tokens: int | None = None,
    +
    load_balancer: object | str | None = None,
    +
    + +)[source]#
    +

    Bases: BaseModel

    +

    Configuration for MoE.

    +
    +
    +field backend: Literal['CUTLASS', 'CUTEDSL', 'WIDEEP', 'TRTLLM', 'VANILLA'] = 'CUTLASS'#
    +

    MoE backend to use.

    +
    + +
    +
    +classmethod from_dict(data: dict)[source]#
    +
    + +
    +
    +field load_balancer: object | str | None = None#
    +

    Configuration for MoE load balancing.

    +
    + +
    +
    +field max_num_tokens: int | None = None#
    +

    If set, at most max_num_tokens tokens will be sent to torch.ops.trtllm.fused_moe at the same time. If the number of tokens exceeds max_num_tokens, the input tensors will be split into chunks and a for loop will be used.

    +
    + +
    +
    +model_config: ClassVar[ConfigDict] = {}#
    +

    Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

    +
    + +
    +
    class tensorrt_llm.llmapi.LookaheadDecodingConfig( @@ -2027,7 +2081,7 @@ a subset of the possible backends.

    -validator validate_positive_values  »  max_verification_set_size, max_window_size, max_ngram_size[source]#
    +validator validate_positive_values  »  max_ngram_size, max_verification_set_size, max_window_size[source]#
    @@ -2474,6 +2528,11 @@ a subset of the possible backends.

    gather_generation_logits: int = False#
    +
    +
    +classmethod get_build_config_defaults()[source]#
    +
    +
    input_timing_cache: str = None#
    @@ -3313,12 +3372,26 @@ changed, you should remove the caches manually.

    -class tensorrt_llm.llmapi.CacheTransceiverConfig(*, max_num_tokens: int | None = None)[source]#
    +class tensorrt_llm.llmapi.CacheTransceiverConfig( + +
    +
    *,
    +
    backend: Literal['default', 'ucx', 'nixl', 'mpi'] | None = None,
    +
    max_tokens_in_buffer: int | None = None,
    +
    + +)[source]#

    Bases: BaseModel, PybindMirror

    Configuration for the cache transceiver.

    -
    -field max_num_tokens: int | None = None#
    +
    +field backend: Literal['default', 'ucx', 'nixl', 'mpi'] | None = None#
    +

    The communication backend type to use for the cache transceiver.

    +
    + +
    +
    +field max_tokens_in_buffer: int | None = None#

    The max number of tokens the transfer buffer can fit.

    @@ -3419,6 +3492,7 @@ a subset of the possible backends.

    speculative_model_dir: str | Path | None = None,
    num_extra_kv_tokens: int = 0,
    drafter: object,
    +
    resource_manager: object = None,
    )[source]# @@ -3444,6 +3518,11 @@ a subset of the possible backends.

    Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

    +
    +
    +field resource_manager: object = None#
    +
    +
    @@ -3567,7 +3646,6 @@ a subset of the possible backends.

    max_loras: int = 4,
    max_cpu_loras: int = 4,
    lora_config: ~tensorrt_llm.lora_manager.LoraConfig | None = None,
    -
    quant_config: ~tensorrt_llm.models.modeling_utils.QuantConfig | None = None,
    kv_cache_config: ~tensorrt_llm.llmapi.llm_args.KvCacheConfig = <factory>,
    enable_chunked_prefill: bool = False,
    guided_decoding_backend: ~typing.Literal['xgrammar',
    @@ -3595,15 +3673,12 @@ a subset of the possible backends.

    backend: str | None = None,
    build_config: object | None = None,
    garbage_collection_gen0_threshold: int = 20000,
    -
    cuda_graph_config: ~tensorrt_llm.llmapi.llm_args.CudaGraphConfig | None = None,
    +
    cuda_graph_config: ~tensorrt_llm.llmapi.llm_args.CudaGraphConfig | None = <factory>,
    disable_overlap_scheduler: bool = False,
    -
    moe_max_num_tokens: int | None = None,
    -
    moe_load_balancer: object | str | None = None,
    +
    moe_config: ~tensorrt_llm.llmapi.llm_args.MoeConfig = <factory>,
    attn_backend: str = 'TRTLLM',
    -
    moe_backend: str = 'CUTLASS',
    enable_mixed_sampler: bool = False,
    enable_trtllm_sampler: bool = False,
    -
    kv_cache_dtype: str = 'auto',
    enable_iter_perf_stats: bool = False,
    enable_iter_req_stats: bool = False,
    print_iter_log: bool = False,
    @@ -3621,6 +3696,8 @@ a subset of the possible backends.

    'TWOSHOT',
    'LOWPRECISION',
    'MNNVL'] | None = 'AUTO',
    +
    checkpoint_loader: object | None = None,
    +
    checkpoint_format: str | None = None,
    )[source]# @@ -3635,14 +3712,17 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

  • validate_stream_interval

    • @@ -3660,14 +3740,17 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

  • validate_stream_interval

    • @@ -3685,14 +3768,73 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

    • +

  • validate_speculative_config

    • +

  • validate_stream_interval

    • + + + + + +
    +
    +field checkpoint_format: str | None = None#
    +

    The format of the provided checkpoint.

    +
    +
    Validated by:
    +
      +

    • init_build_config

      • +

    • set_default_max_input_len

      • +

    • set_runtime_knobs_from_build_config

      • +

    • sync_quant_config_with_kv_cache_config_dtype

      • +

    • validate_and_init_tokenizer

      • +

    • validate_build_config_remaining

      • +

    • validate_build_config_with_runtime_params

      • +

    • validate_checkpoint_format

      • +

    • validate_cuda_graph_config

      • +

    • validate_load_balancer

      • +

    • validate_lora_config_consistency

      • +

    • validate_model_format_misc

      • +

    • validate_parallel_config

      • +

    • validate_runtime_args

      • +

    • validate_speculative_config

      • +

    • validate_stream_interval

      • +
    +
    +
    +
    + +
    +
    +field checkpoint_loader: object | None = None#
    +

    The checkpoint loader to use for this LLM instance.

    +
    +
    Validated by:
    +
      +

    • init_build_config

      • +

    • set_default_max_input_len

      • +

    • set_runtime_knobs_from_build_config

      • +

    • sync_quant_config_with_kv_cache_config_dtype

      • +

    • validate_and_init_tokenizer

      • +

    • validate_build_config_remaining

      • +

    • validate_build_config_with_runtime_params

      • +

    • validate_checkpoint_format

      • +

    • validate_cuda_graph_config

      • +

    • validate_load_balancer

      • +

    • validate_lora_config_consistency

      • +

    • validate_model_format_misc

      • +

    • validate_parallel_config

      • +

    • validate_runtime_args

    • validate_speculative_config

    • validate_stream_interval

    @@ -3707,7 +3849,7 @@ a subset of the possible backends.

    -field cuda_graph_config: CudaGraphConfig | None = None#
    +field cuda_graph_config: CudaGraphConfig | None [Optional]#

    CUDA graph config.If true, use CUDA graphs for decoding. CUDA graphs are only created for the batch sizes in cuda_graph_config.batch_sizes, and are enabled for batches that consist of decoding requests only (the reason is that it’s hard to capture a single graph with prefill requests since the input shapes are a function of the sequence lengths). Note that each CUDA graph can use up to 200 MB of extra memory.

    Validated by:
    @@ -3715,14 +3857,17 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

  • validate_stream_interval

    • @@ -3764,14 +3909,17 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

  • validate_stream_interval

    • @@ -3789,14 +3937,17 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

  • validate_stream_interval

    • @@ -3814,14 +3965,17 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

  • validate_stream_interval

    • @@ -3839,14 +3993,17 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

  • validate_stream_interval

    • @@ -3864,14 +4021,17 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

  • validate_stream_interval

    • @@ -3889,14 +4049,17 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

  • validate_stream_interval

    • @@ -3914,14 +4077,17 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

  • validate_stream_interval

    • @@ -3939,14 +4105,17 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

  • validate_stream_interval

    • @@ -3969,14 +4138,17 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

  • validate_stream_interval

    • @@ -3994,14 +4166,17 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

  • validate_stream_interval

    • @@ -4019,31 +4194,6 @@ a subset of the possible backends.

    validator init_backend  »  backend[source]#
    -
    -
    -field kv_cache_dtype: str = 'auto'#
    -

    Data type for KV cache.

    -
    -
    Validated by:
    -
      -

    • init_build_config

      • -

    • set_default_max_input_len

      • -

    • set_runtime_knobs_from_build_config

      • -

    • validate_and_init_tokenizer

      • -

    • validate_build_config_remaining

      • -

    • validate_build_config_with_runtime_params

      • -

    • validate_cuda_graph_config

      • -

    • validate_lora_config_consistency

      • -

    • validate_model_format_misc

      • -

    • validate_moe_load_balancer

      • -

    • validate_parallel_config

      • -

    • validate_speculative_config

      • -

    • validate_stream_interval

      • -
    -
    -
    -
    -
    field load_format: str | LoadFormat = LoadFormat.AUTO#
    @@ -4055,14 +4205,17 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

  • validate_stream_interval

    • @@ -4164,73 +4317,26 @@ a subset of the possible backends.

    -
    -field moe_backend: str = 'CUTLASS'#
    -

    MoE backend to use.

    +
    +field moe_config: MoeConfig [Optional]#
    +

    MoE config.

    Validated by:

    • init_build_config

    • set_default_max_input_len

    • set_runtime_knobs_from_build_config

      • +

    • sync_quant_config_with_kv_cache_config_dtype

    • validate_and_init_tokenizer

    • validate_build_config_remaining

    • validate_build_config_with_runtime_params

      • +

    • validate_checkpoint_format

    • validate_cuda_graph_config

      • +

    • validate_load_balancer

    • validate_lora_config_consistency

    • validate_model_format_misc

      • -

    • validate_moe_load_balancer

      • -

    • validate_parallel_config

      • -

    • validate_speculative_config

      • -

    • validate_stream_interval

      • -
    -
    -
    -
    - -
    -
    -field moe_load_balancer: object | str | None = None#
    -

    Configuration for MoE load balancing.

    -
    -
    Validated by:
    -
      -

    • init_build_config

      • -

    • set_default_max_input_len

      • -

    • set_runtime_knobs_from_build_config

      • -

    • validate_and_init_tokenizer

      • -

    • validate_build_config_remaining

      • -

    • validate_build_config_with_runtime_params

      • -

    • validate_cuda_graph_config

      • -

    • validate_lora_config_consistency

      • -

    • validate_model_format_misc

      • -

    • validate_moe_load_balancer

      • -

    • validate_parallel_config

      • -

    • validate_speculative_config

      • -

    • validate_stream_interval

      • -
    -
    -
    -
    - -
    -
    -field moe_max_num_tokens: int | None = None#
    -

    If set, at most moe_max_num_tokens tokens will be sent to torch.ops.trtllm.fused_moe at the same time. If the number of tokens exceeds moe_max_num_tokens, the input tensors will be split into chunks and a for loop will be used.

    -
    -
    Validated by:
    -
      -

    • init_build_config

      • -

    • set_default_max_input_len

      • -

    • set_runtime_knobs_from_build_config

      • -

    • validate_and_init_tokenizer

      • -

    • validate_build_config_remaining

      • -

    • validate_build_config_with_runtime_params

      • -

    • validate_cuda_graph_config

      • -

    • validate_lora_config_consistency

      • -

    • validate_model_format_misc

      • -

    • validate_moe_load_balancer

    • validate_parallel_config

      • +

    • validate_runtime_args

    • validate_speculative_config

    • validate_stream_interval

    @@ -4248,14 +4354,17 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

  • validate_stream_interval

    • @@ -4263,6 +4372,11 @@ a subset of the possible backends.

    +
    +
    +property quant_config: QuantConfig#
    +
    +
    field stream_interval: int = 1#
    @@ -4273,14 +4387,17 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

  • validate_stream_interval

    • @@ -4288,6 +4405,11 @@ a subset of the possible backends.

    +
    +
    +validator sync_quant_config_with_kv_cache_config_dtype  »  all fields[source]#
    +
    +
    field torch_compile_config: TorchCompileConfig | None = None#
    @@ -4298,14 +4420,17 @@ a subset of the possible backends.

  • init_build_config

  • set_default_max_input_len

  • set_runtime_knobs_from_build_config

    • +

  • sync_quant_config_with_kv_cache_config_dtype

  • validate_and_init_tokenizer

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

    • +

  • validate_checkpoint_format

  • validate_cuda_graph_config

    • +

  • validate_load_balancer

  • validate_lora_config_consistency

  • validate_model_format_misc

    • -

  • validate_moe_load_balancer

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

  • validate_stream_interval

    • @@ -4313,6 +4438,11 @@ a subset of the possible backends.

    +
    +
    +validator validate_checkpoint_format  »  all fields[source]#
    +
    +
    validator validate_cuda_graph_config  »  all fields[source]#
    @@ -4324,8 +4454,8 @@ a subset of the possible backends.

    -
    -validator validate_moe_load_balancer  »  all fields[source]#
    +
    +validator validate_load_balancer  »  all fields[source]#
    @@ -4366,7 +4496,6 @@ a subset of the possible backends.

    max_loras: int = 4,
    max_cpu_loras: int = 4,
    lora_config: ~tensorrt_llm.lora_manager.LoraConfig | None = None,
    -
    quant_config: ~tensorrt_llm.models.modeling_utils.QuantConfig | None = None,
    kv_cache_config: ~tensorrt_llm.llmapi.llm_args.KvCacheConfig = <factory>,
    enable_chunked_prefill: bool = False,
    guided_decoding_backend: ~typing.Literal['xgrammar',
    @@ -4399,6 +4528,7 @@ a subset of the possible backends.

    enable_build_cache: object = False,
    extended_runtime_perf_knob_config: ~tensorrt_llm.llmapi.llm_args.ExtendedRuntimePerfKnobConfig | None = None,
    calib_config: ~tensorrt_llm.llmapi.llm_args.CalibConfig | None = None,
    +
    quant_config: ~tensorrt_llm.models.modeling_utils.QuantConfig | None = None,
    embedding_parallel_mode: str = 'SHARDING_ALONG_VOCAB',
    fast_build: bool = False,
    build_config: object | None = None,
    @@ -4477,9 +4607,11 @@ a subset of the possible backends.

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

  • validate_enable_build_cache

    • +

  • validate_kv_cache_dtype

  • validate_lora_config_consistency

  • validate_model_format_misc

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

    • @@ -4503,9 +4635,11 @@ a subset of the possible backends.

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

  • validate_enable_build_cache

    • +

  • validate_kv_cache_dtype

  • validate_lora_config_consistency

  • validate_model_format_misc

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

    • @@ -4552,9 +4686,11 @@ a subset of the possible backends.

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

  • validate_enable_build_cache

    • +

  • validate_kv_cache_dtype

  • validate_lora_config_consistency

  • validate_model_format_misc

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

    • @@ -4577,9 +4713,11 @@ a subset of the possible backends.

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

  • validate_enable_build_cache

    • +

  • validate_kv_cache_dtype

  • validate_lora_config_consistency

  • validate_model_format_misc

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

    • @@ -4602,9 +4740,11 @@ a subset of the possible backends.

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

  • validate_enable_build_cache

    • +

  • validate_kv_cache_dtype

  • validate_lora_config_consistency

  • validate_model_format_misc

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

    • @@ -4627,9 +4767,11 @@ a subset of the possible backends.

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

  • validate_enable_build_cache

    • +

  • validate_kv_cache_dtype

  • validate_lora_config_consistency

  • validate_model_format_misc

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

    • @@ -4652,9 +4794,11 @@ a subset of the possible backends.

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

  • validate_enable_build_cache

    • +

  • validate_kv_cache_dtype

  • validate_lora_config_consistency

  • validate_model_format_misc

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

    • @@ -4677,9 +4821,11 @@ a subset of the possible backends.

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

  • validate_enable_build_cache

    • +

  • validate_kv_cache_dtype

  • validate_lora_config_consistency

  • validate_model_format_misc

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

    • @@ -4779,9 +4925,11 @@ a subset of the possible backends.

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

  • validate_enable_build_cache

    • +

  • validate_kv_cache_dtype

  • validate_lora_config_consistency

  • validate_model_format_misc

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

    • @@ -4809,6 +4957,34 @@ a subset of the possible backends.

    +
    +
    +field quant_config: QuantConfig | None = None#
    +

    Quantization config.

    +
    +
    Validated by:
    +
      +

    • init_build_config

      • +

    • set_default_max_input_len

      • +

    • set_runtime_knobs_from_build_config

      • +

    • setup_embedding_parallel_mode

      • +

    • validate_and_init_tokenizer

      • +

    • validate_auto_parallel

      • +

    • validate_build_config_remaining

      • +

    • validate_build_config_with_runtime_params

      • +

    • validate_enable_build_cache

      • +

    • validate_kv_cache_dtype

      • +

    • validate_lora_config_consistency

      • +

    • validate_model_format_misc

      • +

    • validate_parallel_config

      • +

    • validate_quant_config

      • +

    • validate_runtime_args

      • +

    • validate_speculative_config

      • +
    +
    +
    +
    +
    validator setup_embedding_parallel_mode  »  all fields[source]#
    @@ -4824,6 +5000,16 @@ a subset of the possible backends.

    validator validate_enable_build_cache  »  all fields[source]#
    +
    +
    +validator validate_kv_cache_dtype  »  all fields[source]#
    +
    + +
    +
    +validator validate_quant_config  »  quant_config[source]#
    +
    +
    field workspace: str | None = None#
    @@ -4840,9 +5026,11 @@ a subset of the possible backends.

  • validate_build_config_remaining

  • validate_build_config_with_runtime_params

  • validate_enable_build_cache

    • +

  • validate_kv_cache_dtype

  • validate_lora_config_consistency

  • validate_model_format_misc

  • validate_parallel_config

    • +

  • validate_runtime_args

  • validate_speculative_config

    • @@ -5024,6 +5212,7 @@ a subset of the possible backends.

  • KvCacheConfig
  • TorchCompileConfig
      @@ -5316,6 +5516,8 @@ a subset of the possible backends.

    • allreduce_strategy
    • attn_backend
    • build_config
      • +
    • checkpoint_format
      • +
    • checkpoint_loader
    • convert_load_format
    • cuda_graph_config
    • decoding_config
      • @@ -5520,9 +5725,9 @@ a subset of the possible backends.

      -

      Last updated on July 14, 2025.

      +

      Last updated on July 19, 2025.

      -

      This page is generated by TensorRT-LLM commit cfcb97a.

      +

      This page is generated by TensorRT-LLM commit 69e9f6d.

      diff --git a/latest/objects.inv b/latest/objects.inv index 1468c2f94f45b21fbf09b95b22df13b06fc14de6..36ba4ca95c4a1d5d2acd3bec2aea7000cc21a8c7 100644 GIT binary patch delta 144938 zcmYg%b95z7)a}H!C$^p3Ol&(7+xEoC)#F3{3z)VFk|yGg~O4vZav`SPq*j(P=XZ zz+V&Gkl|8TCCtRFA|c`UqctRCi0JzM;rhhdD{hVhSp4XY!xg#pYm4zQ=xJ3juY2Zi z45!uGYw_61`EQo!ZcKEpD<46hI=he;@f#2WAomETyY#-TI_pJ)7HsBs{j2%o#AW&h zSG$AT7TzrL`4pmZeCBkMl=nssvf^ed`iy3kIyzMH!pJFDYi|s;n^2sEK3d- z%{VGK_!G4BLMaZONdCwQzeR%0EObyA<{$wCUadL!+~1|4#Jrh}SL6FqLlC|bB!>%~ zmjS-f>Dc@&lM4_9Ld4m6Rf#IIAl&;rrATq3T|K+L|NSYP4UsR}j1>|}a9!Y}s_a6- zzD+(_t`VLeLz}bMfjl@9yObtc&|xev3{wq1$c>rrp9XdMQ@msLV`Jghu{Qf1WSa;O zNN=57JsJ6kUBi4Wr;!jsv}YBN;@5(I9e;*3fEQ`)`flg-cyIo4@i>%062*ucEzOh_ zaJ+N9>*N*I$37a^Jc~N#dAFIjC8Kz1X~An$Nyo*^-2eHPOprwNuy0jWe-Km_({%!k zVBAT)w}xW_#Zo$-FMDVawr7myX%D9Y6ijR3sLT;ZS6Ql#tj5`L$T>yFxTTq+o$%#N zFWbMAd?`r%SM=GT496deCG!*5{Z_1^DET6mqN5Uc*I*CfZt@W7bz$O=38s2rSKrs8am3EN`g9EV(8$)>mG-jF&@I6VI{7q+08 zzhJGPO6{Xva;T^;rqLA2E3cE$u_&g)3NQh8tO&VOGlu8^9W5~ z-~wD*WZ5wa?85}TLyv&7w0%4PFJ1@Ub}wgGsXhjx-TOHXGU9GIFzxM1oG1nbAbv<(gh zXZKj+A_ZOgwfbzdI3%_E%k+L%W8#w9C)yM2GFa!EIDFhX9Q+HRN|$qMb%f6j5`y9Y9 zyBW2Z4eAC^z!pm@Hp~yHue>K-TOnq20=+PfmafhJxYvai$m1m96=488eC1!C<|9+` zadXdPw|wAoEqG$Ma|tR(QfLn?qtugKT;2z60u==#e=i)oecXiXtWR8R>j_)Cp&V7DgD zFDjI)jp%@4?Pkiy6Bw$C4XG$Js565sUO?JLYdX zJEm`0qVgKbl1()zmPdfrpOh9Ht4Wv=YZQ~@1QTlJcS$wClvX-%Te%r2} zJhelUb;qL_s+65|iOk4y zB->U}s>M+h_b~xd!1^Zmbry?D!pgR)+NuAP+q3wY2FX1JRX)xZO`!r$KAPcF1slLP zSTI<~eVM)){u;@VZX)gZ`M}(7Z9$&(YU3|xOapHHb{Q=R<*%w4`?96`W^^Qb%urI_@_~gUUPUe zM>>_jv6H9Q`LU6or}gS=0rm$bv>6tkm2 zlzj+>VI9UWdZI4g^g5>`Ap*NVv}c{zQXSW!+5VIwK-0yKH0irHWgF%=e|TBikHb+> zEa<}y=&=dUdk@G&P)i)CM_7EajP6*1tz&KCH;4_=LikRlsmL4RX!LDpK!*X ziL!F|KJLl=&4Nw;dczF+415FpGYZTgle4J(xx<&ATAM0^D1BSu($}ak`E?UWul42z ziz`lca>nZc;A<2(lVAx{#*k@7bg2*rGdcz)rYo9E)DpnEPdxBZ5BhWzi{O1MqDUEZ z&?d81m0BXf$R=BQ)B6BCG3-2pLaWHZ>_EK-lgLtbC5s;cb8mecamwVn49qt%_aeTt z@Id#4;_W|I5~;S)rwBgvD%|C)8>Om;wcsBDocI$gSQ7(etF>L`=cw46j(_0p!0<$A zKogSWYiK}IlQSz-wTzPZPGKU|RODPNST{I46GeKO?LPDqT(-lAN=GK5k4@5FUEAj* zMFuPzl)$CP+UXZctaZz*7>PxC>usp?okU{du}422R=tjf9Hdbm$nB52H#0vhT_~&$ z%e8)6k6zK^O6B-dJb4V}V+}!ld}kbDc67?4D+nO{`%l&Dyv;O0htPI-gId0_s57q? zQbw+KHshcXSJ<9hiezb~%;e+AbPy-&-*z<)hA{Wbynch2stBA1-`eFTU(8;}`ntR0 zHV-2-v_^ep2(A=Ga9iT68IEiJ!5MVzksQ3v7Mri9d%CVCL+$yD37aK=vQjkRew%6- zGazAyV@$s^_63)K4E$`c8e@kaFePp*+YTKi?z16D`798C{x52c!`ZL>1$%Q!siB)i^E>U!FE4)r{9IBoMQCza#o$| z4bwg$Ai*mcxqtXlsPoXoucrQNRwFj8=^(Hl&>1*8$czX%GbkjELJO%&+mo# zX{E~Vld^!uuP^+Q<2qL$u&ABm-OLUdEWvfUARMRZN5nVc#CAMLri#-yFq&mgaR_4V zwQ(>@xEO6v8DbTf1V{_X4a^8Mjl>5mv$7HYaFid?_F?@yK);ODz1OBH5G=v;Og(qz zU)nM?H4st#kEm~lS4#}MXeK70(dv0__g{n{elV$nEgw7XJ9*r94c(q|M>Zl&Y=QRs z-5=c^G1{?M&vVYnn=uA6lqVMj1~=2oEeq*NKw8OyMB#z|KW@M+$zrIvm9# zV0zly#Wk3OLsreNIZx1Ne##~(zW}x2m*nK@J6mc+h zP&Wz*@T?=xkFX+Fr3ah3P=E!(x4OBaCX1fl5IO+(tDQu^dphkxJ{+1MlB-!5Rp&)U z=-Ez5eI{$8E_+|HW3Q4XKv++_))t3usWTw-1%FlR%KF9hxdHk8#IxhW9zQC3XlmTH zyQ5nO#eOhuS3=Xm0Pw$HKVE-}MQSqv3qS?uxqebruhAAVBlr^CnuXoPF9-UCdJIG? z9>Z+XE)R~-*!sm^d8FB72W7g`I_B3XLkq}rOrx$JVo}&6V{p@ZocmQWM=8?DtrUtC z2|uq{$am<%-$1Zy*EgkVEhGPOE)H!y(&vK2Ri=U;PpAX4+T6l!sH@T2KuT$(gUb7g z?#OhR9Eh)#b7ewWtOX~ha>MQNQyrK@Bz|C79-7VgNGkLGha%__EkmO}xqb;dp_Wd= z^gv(SidJ|;gQDYuyp`&&2erLN`gr71Pgu!Pez}pH#7wfoI7{70IG=<1$uhVJxq!X zheB8n7u!+!stqoA69vZuVN;#Kq~jy19^>jXQd)3%=VUY?t+yh5lWzPo5HQ$u>*g z3f%@DRY`XtP4N+VgZN`eApylTeeX5V@WatB)c*?L)j!7S9q{S>E#HCpB2!JpdSA)) zizge5PdD6BI*Wb~&Dh07)o-2HP%`(m+uM3aj9Pq#BjFse1LsVOwMkkn?X;-2-kP!-58}&D@m{PfWXldi~YoPdp_K{S!@$1qX9MUO1=O%=1g> z=bBpk)lg3DzFs&7*({^94SG55e?CsYH{ipv&y6}bfrsr(?OC$_(|apCcV65BXD6Gf z@1p4DIIlC}K@sO7`k5VASB7xK)FWu-=a7AU3EqKlHHEv4|2+0v&(9s~0}tX&a2GVL zhg0~~{(T!|zxo8^h#3VO4d*#l9vZlvP-})<9e6$&dJYf7d1aQt?E2aAeWdeNB8XtA zh-%p&jj0nNU}2Kp+5?UG(Le|KY$Z5lyT8l2#UFmM_6sff_6&k-9V7G8$n@n*w)j~b zgSH%$sDsxX^I;nOU57B{G1-WU+-?dU)y~udoLpjYYYRUHoR=VM?XatMc}(_ zooFmuOWFP7jw^nhV(klt(j#SlaNSGgXqjiNIF0kq0O4eKPf=sacNB2R!Q^a%8?6_C za6Xz&_z-L#D@r6F4F#>ugxYOBwnAAvRz3t zt-wG#U3}M@KEZ|x+Fl7KaS#QKx;wq+NJUjddXp0#MAN7C>|ccE-&1lNy2B60t1W(8 zRl^ajwQCX_&Qn1PgU1#ZbVy)NNgoi{KB6ch-@5o`z<{@pkJbmQy;iAd!BGG1@m-vD z7K;juNE>~nA#k+ER5@Cx@y&BR9m{`C_e7t6!Ak#yqBy^mNqU}^tMA1be-O0ttHB$YkZp%Ea*|rDn(!!N6K%O!{gZY$!4W+CO zSwr>h2FTA?EZ~Z$dlyg#&(!h|rfKMooW9^ByhLT#%S&F^s-fR7+fNU#EpRj%rk>?E zAhb5o=$w~Gt<5^^_NyYp(i&Q-vx{7i&G{IkeA`a`w?ZOJJXiq4SP1mCB#z zU^Pk~zbK579@3Tk@?HNzg$#f9V4Gh>KB1?FXuv!PRCDk@0A+Zh!Ub*>rkgRQ1h{Z+R~A^!=NYoL{lVY)#fJqHyKMZ(%9WKC%EyjE_}WUXE8>f!fP9 zVG7pl5toOy@M)ipYG&!tj{_v-_aFF8QK&#_4UaO{zq2OSu*`vAr`gzlYZZ0_k#Bu0 z)#TTUnTeH?4b>m7uv!R(hCEZa2%1YHZM<(+yh+-TZvsI)?E{KGuE%#1u~!D@eU&5Y zhJyW`2PUnr`wrKj4Gk0deIUk|Jx(Jr+?vtAq19K&8EW4AkB)vAx$E$jH8&(wDWCz1 zH6BD@>x5@5pgh|=kk+(rye&wM7rJf#7^dx8No5J!{N9_arzoF=!7;Rr<(?j?|E9DO zfXVz#RaMrI-Us~KU+mPsW#g~&r{Ts|rxSWA`*hW%L$#70989-H>r}4mSSeIu&t|8N z55t5^hgxZ+7odn;$rhjnR?%I&1EdX5C|dp&@i5&ToGisDcCB<~Jb{OL669E}L$VjB zqsAm!b@Sbfz`H*t=~hlNNik^%q&I;tH}Jfm_Y`3bx|8-gB;0i|i({Oc?GLXm!fG~>wgRrrmm%;cKg z>wExF0x_#I@^<;U(@=@kJG1-0WV?wzRTVIS0Drp+JlAuF-D$ zv0YYW75xy)m-_)T5#{uFaqUi#ruucg@xC{=bh2@`<6gmbmJD=p%;D$ToXYy>$Tr~L z_OpUQBG8PP)7d*c`FJH)4?Tj{&TZOg3?z#LqRtx}KQ|uRbkGUe_iaZ$0_EpDlV`PJ6_(~oR{e7JAf0Y6Uhn88e+i)tnn|iMx_xt$c)wkH+kJR2_JsvewYq6} zlN@CoV^7nI1%T`ca8&2act|)5->|o4TFO&d0`?4MBKo5~vcY$RDlud{a6i`eU*%RQ`{jguxFS&86 zE>Vs4wfABFC=K;au?9i-dSn2*eclARTRgowo{C2Ij<7oY0n^U-E)mJ$_EKKFptPek zA-S>3&p{i6m{GZ9jcR0vQ@VCp!eZH2>n|S8(H+js=S{Kjn$@~9j|xo5;z(loBwe+a zCD8%a`QQ@x*Klr139I^t#H?%Ix+gHuwB>UHQjswwRIP$Qr(c@=my@@QJWlEonvi7Zq@ei|F= z_Qin*e2TXP$M4GJwRX%uY~=tNS<|J;vxxh{q#s)lC0wAf8_r6SY=p5#e-iI?(<4g5 z7G-$^lwJ6hU-Ya~T2Yl;42FvJE$O#(baD}Tl=zyjtETWnQF!n7yL%5{`3$d=NPLzK z!)m~sM=IR+0cxE(j73}@jBq05@h5VdKf>Hqn;7+l9_Tt(hAik^XpFOA_`X} zvOcw;4gyfNmNq>W9O7>|Ru)Ly+T~titWNojc@mf^Y7GFoeK7Zt7-vXIlqN%}k1wu^ z8mG%YE$Oa%pj?a1@7E##PMCM|-bd(XKOE3YgAtEmI*m+Wn!-3~IY@u8FQBDKH<^L8 zz3&SZ5Vf2eUzvs@IS?q%^#!Gv8lGRa0dkLbdL!5BqypjMIEU;xdo<;%3hA0?-z~ z9mT?W>cXIts^j14VGy-8_AisBKP2=Yn~#&UNEnjHjLW;^3v8ldp1{e?D5AXIKA=jL zvjsOkTG5$Z$5!%Y4gW^LHnb@OeCcdvfmI0q-T&C3Q!bIg4B~b`-a^JS6rnlhsnU56~H@ z8kjUlm<)?9#TwO!z7Ut7?OHtq)&SP6C2z!iXVV0$kQp3FT!J%K7gB2j5-(t0IT++e zCIyxc8X+SAI_l3rUT7}tRF4yh=b{)Z@<1Tp3j{1O!*OVG&IuKmw2iBXdslU6tGj4k zNZ0RTITv=9znhh(BuUN%3*R*sPnS4hb^l!CNCORDQ8YD`_7C^-32F>*Am7&4^Jwf3 ztS|3$EuPPIO2(XVd3 z3BD75m+@>Iqu@J>I;U5Zx?}je0)#s>54=u#v4x=H)~T$MV)`6C;Veht7c*r&zU*`pQt$tH1X+U@ZS6&pVO{utdM)_`OwjMqZ5?K0c3_xk8CroV9DTB7GTuX7gLC2Fb& z5;(7NINif?I;H+0UFZ6DLaN?xuPE@KsB|Jg>eU=X%AeTJ1DeknUzUfF4WQpdMY0F2 zbKu!92jzvbTb3DUv^wD-8c4_I-f5d@C0;T>vxzw8#fLO*LQJX0QiLVig9URy8SW;! z2G>ZZTM87w|LpX}*<=XwG+QJxQj1X9PoSV#GeP)^%)&Z}Msycvxc9xigA!QAHCk4q zVyfons+?2Oi^}b;6RcWSi3O`|tQ?R(m?U{WwHr7JNFP-RsO+y{>TftRU6z3`+cbJ0 zqI35fSHU`yQPYd@5U+++X-Pz#M~rLa8Z2zq<*`sx><;Y8jfr87aVUu(_2O?c4M;Cc zMB7F;D7%t)Gu_&5ikRh9^ar}wx0SCFe@`gr_4?fe7-xwj>qR>dcV=U2GJ_EE%m3p>8Z*mh%>?CEUEVklK3>a->A#RfC(e?iF z7B)IE(_-dw-g7-&&49A%71*0@W14tqOw}i7Y{>AB3#AgDjQUQT$PX+t*j%%5%`7$8 zT#`}U8b$zRRfSWgI6W3|cSJG*iVd_^+<*Wu^7U;R{h za=2xJNAOP21<$|dUN`tx0J7JHe(hlVO+8T?=U&}z!9=rhY!60?hZh`ePMxB|I-Lfx z+HAyXwoE2BY)V(*bsUKAlZ6Yg!3G5K?(^pQWIgfl=A?gjkUjrZD%o8*oaLg?k^%N~FMdp-+p$zA}9(!%Aoc%Z5r6+gQ+nKLE#+5FmiF+?_ratn^UD~g(x z%cXw3y4ifFhF2?dhUe;3S-XTwpt*#s4)pdeN^sht56ch=SOQh(%!Nv21NP7BGryA# z^WzbY%;aNt8k?)KbH}&8Qp%H+l$o>5qIv&U;9roJl3GQLf~(gl+}~_G!8*W;^m5&3 z$gf%+2@#V0)EPz^>h*)pg2sp9@MQa&RTDDGw)`4)JCD(vy5GL z`^}LhOd25~-;S&{VXq1NKB}}8&aJ!*Ln%(LRKzB>!R{EtSE_`exjMp%Lf`&n&6lV2 z7=8*AizBoyk(zXF6pA5;%@RTL!6);WevfBU-gdU!p2@o4fXjof!xN+Uqm(dM@4|?O zKHdW1s*Y^J?k<5PU4j)f;zHjk4#|4_jgXoW0N+GK7A38mZaI}tBkH;&H|cLTFNGA6 z{^CWXpi6_VSY5-pxRl zH}T@LfBnt+yBVl>uc%uuSLNK>lFrvN#f{!Zs}WIzg>NC8(!MpDBN>pJg9buTz2Bn< zn`v>%yX?@3xopz6sq%e+%ss*~Y%>*r5W-e^WYALdI<3sF4btDWWTei{XVeZfK)AXM z)_b-dDV0w^`fY?C|on`=^KNuoG?ZxQ!T`5ePN}zAyb0O#yd9m0Y-WZl67rsSt`5n z3?MX7+MtmVj5Mi9YbY;=511zd&OOlJunp5bw!|(s)@Ks2ju&NNqdWeKEK)}7oc-J9 zT&u1`0SWJmnghqVA&#=bCCrcDXBg}tBEMu~!D|H#noRROX}3UtrOeoI!E25>Xr3j; zKuf$}crISY?ngmeV2Eokd#E`KG`|Aq`F{W9i)wQZ|B}$=98Q=-p`$zf|?Zx0TAXOyb3Ka76((ebh40k^2?dH7zH{7j^8w z$Rkbu-(@5{B&Iz5Fpf|faARxB&@fZOg(d&DC|#`s0p-K{<;&&A6fb1-wK{-zjJTQR zBXqxs4YMk5th`!v7FS)osq8VSA6gn8q>Bma@=)(>>F8!VRD5*j`h?qmAq-sn`nk>6 zE@%IlZUqf}S691=H}Wi}=}sJp8O$_<;Qk*O!j}qxL8E|%+zi-hKFB>qHCpl${nO+S zN`2f@{M@n!;s=jXzhDfH=+02UfxefdBC%_p!_kER&c7-gQc$CGc-dkXFP7_NP|+va zGvI~=`WR0hjkjoSUvWghEj6xaU|Y1}84Xnlf629B*Y14Uxx0t%{@xJ3~L<4`^z@bo-F;6 zS+{Liz`8yxHUA9EEAI@l4k`>{C9qq~QBRcKo)twzZIRR%3OQE_5Uz`=6z?l38bl3b zfCl3@XsMFKtk-?&$#LoqSGi;?dHf)|@l1(i?v?P~YXkmIx$Z;(@kko!8h`hBCSQg+HI@&V(-wrL>UFFYH(iGRqt2Ise%=s4xINp81aZ|~~c zjyd(VkazBo^%cq#ki09-XUeB(WE}E$#{=$o^y-S$uK_HF8LOr!>rw5sTj=%ILu;5A z9d#;y;On%m)wa{vsF>sDI?hebbf<5CjJ-<;`arxMMjB{}-phj*3YpSNnT7t(ScG(# zHs-iY&y6uaf}YP-G2ePm9C`nSQA4EUWY?b18XeR9)=)0iiq*r4{+`Jbr=hVoiBr-^ zP&F=!t&*ymJCWdyLAJalAJN3$r+sSSoXc_?xH&WN(#E1rkcW?AxJ{+&AX4)jsjo~_ zt`8sN!jT|Er#Ut9Y3)F2Z=klwlq5_4&bNXb>$|iJGWdQm;|iiescRzw)$SklZ8Au+ zjXW$oX52Mr&ueA};tO^?3Q`FEy?e+~v@6{ioQi$w7E1LcXOhkidxi?-rG!>S$xHq+dsbf1wpJx9KExFzke?P{Ib6lBhi%jC$4$AyaT;h_k3X$L(Wp-o| z9&=j{of)I-(?RiX(O)iE_{fxxx*h+BsjlRfH7};~Axa>#S-7(k@II}rX)}k^z7BSJ zvR~mnK#)`T`9;6HmvHJ;+I+kk+Ej9q**d$#VmySeuKp3G!l63k@z}Yvtb_y-q^m3S zMo_g!#J47Jma*xtYyEQbzdb4`3PqS}Wr!xB2&uwql4e@prX00lfu8A_>*CCF{v9M9 zPP{W&PKTmenkCXsTb;`%hO~gOY=9Bs!0UztQepgqHbu|laRq)7oZL#AU&=!i474+>Yqt@*rlQ@-b5boc&>%tnAVC!LEr!4 zKd#s74;^sb;Db;Q4~I-*UU4hb7|o!jfl1O(n_mHEZ6U~F2RdnGcVD;h+CH_@s_OGZ z|B*i|o6<3f)Rf?=k2aE<8BGp^5Ei#4j5}bnDaob>$uc*d6d9quU;G4WzIN1v%)~mK zHWkVVq@e+Yb%!rxGn?s&JG_Knz|OHQGV{xcm$MuueQreh2F?->+^YtEHJW^MXr`UT zKItjtf92j)QmB-t%uUT6vXaD^Lkpg7k2FB{kHK4ajvz5r zo!G8hV|bHkwWyxXD-}5W)xW5EILC_BnzB&*+afatWLTc6@?D8eJEAf0_-N}iF`-8! zD6qZz4&{6f4?8ia&<%&_A*A0+d<AGeB!HzQfV1)Qg31ltY*n2GuT}~VR4-8v(Eyb6dnY4aq~At{`gS79{V>}9AVk@bM|qyEEPoqV_86%l z5R>^L&rK4B?H>S3#1avB&>~rFmr%W6;4!P1IRCX2Y!nN|# z>K;a*crF_{IfUXs+;MFp_O>CrCM)SVw8#Qqaz`ZS;@)Q15{&RFz%Bf|XMVeVET|7VW z{QFTFl6ZHrd{&X`m=j=Nh{CX$DE|L!X(*1MSZq`M-_iV&fOP9o7+5ER z?!>!_>*DSw^8d}{j2VJg6Y6ghtot}hC{1G&CeI+mMY9E_ayPBUv9bofT6-Ui*8e-L z;>k2kVSVRJP^ai($s}!%GYKReJ>h1q#rN$TGyi=SM`74_=6|dBKg%mThUQyG=VG+B z6)Nk)?#tB$Tq{~Uh-9*G;m&8ZfGpHrH4A6@>5`f^hB+^HZC=S-|ERz5-_Cl*gZL|lLUy+Z^z!8@U-@4%X{Dd~UE16WD32!Tu+RTh}ZoE|6(TCT+FFuGbuV7bLYhjny99-UnY zYofmD)}(T2K`FmkDShBKU^a+7)#%s3rz{AfzNt8UFX>>$o%Kf?K0i;hN z^gp>5_Oysvb77tHU3)yoliOBqXR3${Z6uSXH(uEB`fO*q>Ed-z?H~7?`$&V7V^`Pc zn`}P%@JeYA!B>$&U91{UDkcEf?2_1Zm1=ZVMV@{CF@iYiN#KrXzEWnPh78v$IdgB~&Ss zB@yQBAVSNf;1twj%rtrbjSOkdX|UPC{oyOaoNFTTr|>l2bEVKaBg_7{5b8p4)i4uwL`b zmFPpLWKx5ts!DDQ(kys>IQZ0d!SwiScZ@@$m@ozYaVw8*u~3R@>A)Oj>_4|VvA&6V z=}ST_u1cR+C+UI=!qHJ%1+Fgfzxo_|Mi&cgk(4@~SNATRV0guXTl0w${V?<2XAbq@v3RYC&!yX3au9>0p z>g9BE$6m|B4&|q(4XmKu9W~N13pYfFfzO4q(L-Q}Xj?Hg?z`bt1r4Q& z8Jv%v`Cu$eFpb7=>w-iMh46d*_F}Cs^2kW$7{iKeNY<|0 z8+;>8XJS`kxj@B@H6Xok)mi!PhaO57#C#IBrSr^H`+1BxE?bl2-KG2Hceh?l#3H9U zop8-yhXg`#aL*Pd@udqluNE|#Sh%{^d`%wMh708dBf@vh;1;ZFo8F6}UROV4BjQh@ z+D@JRG_1l!TgCZd;hzXa=16ioJ?Rv+5cdCya@zcVqyh*d(Sf4Tom;jLNPuf3P-@huMB*v1#3?yK0zYqA!@#7?;2k!9W6peDY5=e-~k$NZczmeItD+7c`s(_cp^j zjGwKn1BdY2j{sUS6Ab5u*&myYybio~SZTz1`D7DgJ+pZrdgR)TGT3}RFSgz|c`7iC zd)EuI9Js01BRk!5tL{FV~Wk?67_kKKc--UIeN(ZJpwrS@~*HNQt1_K%(V0|F) z!y(0!8%6L)+@g*D^#?Uv{dATU+0rhkZK#?ZpWI;f56!O0guoC zpeaw}>_gi4(X5UdYexE$zGk-r^p}_COIiBC%ZM4Q2CEOTXJW`c`Q406*oe<%oyCjjf`aZ#-N5y*}Z` z0x-gv^w(<^Ir~b6NG-N#MwQAr%401tX~t*i!%fui2R;wpH}bEihKf%%=4^dG?dZ#>!S=59x^?bvdV_P3O2Bn*{tb)K3!N%|JtiYo8YDon{1)uXF?iBrQd z0I5rTLxceOy>Gq-8+I85zgL(zC5>~^Ht8Jm+1$1-C~>bVRhv3D+96Ta^68CX^t5{+ zuD9}&fKD2JNZ=Z8!=c?cY~cPe+l*9occ}Vn7pAM${^bceK$V*((nI65oEMpXDDfLy zZ>b6-bhH~B!`W8)tIEV1VxTD@%&7cdmTAbl0yPO35&t#4zu_hof9u!zN@Smoz&`b? zq8I-q&~Ji8Syt-Ci*W5xG`cO%s^s_XeuzmF&Im@9;JjTu-92Tq z?^*F`wzsrYPPZ+LSD?mM}1ah z-wZca)=*|>hoSwFxDHoM;Y$$Pp2vPLY_R^pR#+lpJ%8i*eE#8aXv{aFsI1#_G4vA+ z=#QJM=qq5qoQCKHvojuR&L+e#m?jbAFb2)B z+8eis^EJQ0t{6osLi~0kGuuaR;qKi6aO+3sZ6}QI%^NA_=D4=JNj04w7rmmEs2qyf zX`{0I4+Q0=yLkO3NU1qyxI>as{Z`}v_9|Hm*ND3BomkMnLCck&6u=k{Q};gn>ceeVkm${+@eEph!+w zJ?p2tw6DnGPP`#iJg1g!+<*rAa9Vlk>uxXFJx7_pTirSM;w%=k%8`%+XR7WuoXZ<) zh$h@0_8{ib0U^e2`KFCyv4D1;cBE$hk59$yi0XKL8Z3?vkHB4tN zjL$@#5=5UCo!h@%f5s&?m6)>YL+$WDLJ7z(H_Ilrk#r+qU7e)@H`*)?d$R~PM{~RP7!m(<}2LLzU zY^f^gya&|@Z%E_1wA+7okA+wRDycxOpe90=uc61-F4(!sa$r7D;GjfBbjILEWz>1& zw6Mq0|EcU~)f7*UWwmRy+3<&76ug{CBwfpM38^H*UwhQ@$D4DQUbK&rb1$rtmF~Wi zVo+-ZK76B^(s9oN)96iO8xAg~>S&p;kJ|WDHrg@yYmQX|ZKtUgAXaS++(N42U(my; zd2iF?<6wGFN8`A`tID^SZdq>sel>h%v(mG1pbH1zng`{nD_a&(Yq;K-2M=kDWiwI& zP|`r_otEU}_r`uUl~ZbB2)9}Y4(!voL0 z^F@~6{4_4gNOk@?bA#{TNoe-20%9GmOOh<*FnSz((m*Y+)LIDx%!vPc~FMQ0}L$;vO`r@qq2 z3RRV6rQ(2NpMa`j)1Sj!O&;dBD@fE|cqpUVEnuxjVjj9latv1(Boj(u=44{v`L8h+1-}*{uW(cpxaj)&W!0^ixI3G|o7+b{SzzK?F zH!v>*0R+hUW=^1<=m<7DgtlF)Ni1?Dbhrm|>=Tbj=pj|M2W=>M9}fT2)3gU=3B;ik zg;I#e!ybuDH{}xerufmG3&uR}ru!{|V{`QIkQNEX?|q)xYFl_Ld*=hmB1Pnb?Qm%U zCFrSt3r=I;`!~iJsoj+7od+V)WC|bD0;Iei-FHWI_gGydy6=@}MqTw8U%b$Xz_J?G|O(DcFjcQoOr4 z)Gl-^ajH#QYs0cD5r#B@2y2MoMn$*bQUQ9rgp#YWYI!`y)j+GNi6AWB{q9uHrp6~4 zaUsQs556xJ^*Q?xIenlO;W9JKp`UDm)DAtCdqvM7{gD+JV$ zD0^3GE-Ut@SbPYG?=6x`10idus67>5I)P9GOdl>IEY^)YjdxW@ zDtpjB;|E!AB=repa@_liIh5f6XRE@Ck;-O@hxh-eHoZg%e@!w!*HnSVb#A+d$`KFQD*npz-N@LS>5(aDe9JOZNG{#0g z&^Ft$5=+@%XT?SS?wT-DttW|#d&V72z*jH)yFYF-9C510D}qCCXywHY-}$_iaNT}u zDa`4Q^#F$|#C<^;^;>a@_%;ViAL{!|1eY=NS`}b=Oq3HNdTc#&uFQqp%P!|kD4hc% zttHe`BMQ_@#vLH}tGgnmEUG^ZCHqC4!2n2K@x_rmwFrN7w*?dQ#vb#^)@3-X{~rM5 zKpMZ$a>$JMFW0X3j8`s$Ggj@`)}fY~ax;C`w6A>gB}`8?BF;+=Su|r>h1)AoW!|@q z6@>);h^90srYS|TMcqhWiBWjdnJu<}&HvHF9;$%AjGDSHf3~%H4U>LhBp7c9)Z3>O z%Nli?BGAkVL8WXflOl_-U7%HK%ZMyTO8`T-pJ+h2U(zm*0@b0LV-k5 z@k0#XsO$G+Wg2mOI%v`c5LzX9xK%`f8FLbSHU6cd%@%aEX!fX^kNmp!Wu=d;lrL&+-D2hM=FBOH` zb4G>_(APV1O`w6IV6zgc5gQw4j5w;PfeDsK5N@2KfLGoM#hyGYs{`j(H+cwe2*!1| zEi-P_TRXumP&avqV2ZbRBZ!w@_2{}_$<-~pe*&AZCW|Yw_-Y2>jkmJGVCuej=sVM? zTCuEAw=*5ttYmKw-WdipTSO{M^1&XBZt2daYQT8ajYGh|ACqsOJ33VZ#;eZJaNzM7YR_^*^l6P; ze-k9Nx^0}G`0?rIx#_Ny9LE^4XvVZkUBe7+UM?A@5_Q#b*}6L4yIC-?~fmsg*Te;@d~avtaeh$}nNPk^|x40im)!|JOw$B#U! zP1_$o^SFK~{s}6M(Lt@;CwL`lkHjhn`T@D2|@GcSe0M;$%oqz`?XD z7*7uSL>iW!Mt#8W1h}bp3?4sskN!y234qgYwLbxH`b|~G58iLMHR$-s2aU&me@=?_ z_#J)Tc&YRWus7}^I)3&^>n-d@&)@G;d|%!ZdGt06(>?#k&zWvjIeN}fmIaRx=zQwc`~J z(wtFbl|m~Z_jf8Lhun~;7#(!~oMLw1Z5@i~5!MmaT7WpYlo(Q3gI857@T>p2zTEeQ zJYFF|Ek_=o5dg)~@Vq)=O96N+Am(p8w2GK@Vdr9ZR@9#NMr`#U_vA+wf3!cljF_z8 zcl|_v)9_X?Vyyr?ezN-;wY36vXLS5GtZ(JwrCr=r3|(LCdzBQiMZwraQng5B#|3A9 ziLP6F-@Qbfc0k#~k=W#^F+ssXT4YX`_J~ww9n9Gn@@>D5~y(QJU8x7GEx#&-wt z3Ig_wR&GPvIdQ~^H=M0Qf4NmEYY6DUPhGbe9*M&%7_6;Py6#Y}g-7h*!|&UUOlWzh z3C|ShGflegwLfu$SSs-679wkcQ=Dg4Mh!c2q7EB$XsZqzbVWlMHt@WTccN{tI&Rq2 zBX!)6*DxH0`=sIoy3?-=9DK4{9Xa%bq<6AIb#>&h7bB=7hh9ooe@2cltWbsyd}o46 zbl}Sq6rv++{!+#cf1QFtc$A$L>gX|+TGi2?^o#|{Rw?hK=kS!#V_d?Z4j*ghkQbcx zI<X5PTHBe~DAuc#jXdcc@ z2Zu2L@XCXO7yx?r!67UFyaYkl*QKSjQ(eGYmsfaBc45g+)A^~j(SBi@$7yaY@e5gLK7K>F#&T35uZg zA>-3p`VQ0`VTazjrw|?Vw$>vdKdAyh8>Jn{2GD`pVQc^%s~yA$(BWFJ=T+`g+n^9A zJm!qHJ{Z;?i9Y_B;E?I<-_JJV7p_0Y)a>#B=~_i?P}Wg7$#(3h#p7#7&ssRMcJ!=; zgKEdlS~{I}fAp}$BWXtuTRew$^svPl!V`i${xB#XGdp(L%Gt7`$1NWyJ9=E{OKQ~O zmRFvR9=Cj6?AURuhs2Jax3YkD^t_d6^JC|&odG*`;QH+Mu@h5HdmTM;{fO7mBiGM$ z9X)dWFxSx|*QZR59ho*OdgRPtS5>QprXA2aG3b*>f6om^v5uaadj9IzsT&Sm9X&RE zCFSU`=_?M$j@@*o>e#s<_cJI3Z$3SB^yG~@l8&9c{hZX1(=!~7I&urL{e;I(nJ#`G zIpua=^^s%d+g*>GbKg?>vEz$ubU1dK=sV?3h`O*h?sTY2yWvg-yRiRFlv(wwocP0H zg>Q1Ae@@IRf00wcC>s5FKcqcY2jPa;7<3SDki9GiAqQF%J_tMDs>C7q5vB%|zQKvS zf~ffMO7z7IHBVP!?PFE;a3$idD@D&%qHQCM_~}#SO8ZB!)AdRp;zZs+pynA)tli(r z9^pjXsCcL+IMq!;D}I0zef3=N^PA`k>#85$f5czDMt*uz?FxvBM=TL{HmiF65pScu z^2Z+)tlcYm`VsBKkNSrnRqRZ_fA$f1+o8HgA2GMzD}C}2dAqH$8_p0hi@AX{$^Y68eM9F^BkVIQ|bzqbi~1M4AfZBntN@zq?X zwPInLK_Ci#p2*p&NY}rZS$8=6i1bQn8^p30R9;!mW29_20Ma|j1u`h#`B!$|U#dKF z^xZ?K4K3FS)9CP@Y%2(-1+v4T&8~MCe|Je4O@avVDR%tfsNNYhr`sstYBacO;#F

      Qzv~gWG5VwUTm7DNCeY4y!dO%SB%htiJ&A`p?2^jvl))4ifv%g21zCrt zyC65jU4^d+lS7S%m%w@c@?Eanj@w_?`W51+?6EI$myNUXd?&9P2e*p`y zq=XaD-8dIX8IWbVLk|gZR8zzcTG&U3L^&vH;YZ9y)4`us_==9(8#Zg)hfbe6lFmFW z6H`J&`(S1J94)+UraS}NqU$gD`afJFtk$@S1#;2e!l#|>GzrF(wAt`1<^G> zE%{4)x|YR&=;!d2hz!gRZcJs%e~WbPVc1t=$Pi}TjmW#9wXoKv8%`nm91PgnxULz( zl&tMgX2zhbRnmmed#q1N35Puc|9GpheRSF|?@zjy0hTb^vUvR9s1L|k)LjtA5F8rFb)gIvd*G_Vtx!1@66i8d)-*2f=)E& zCxTux#Hm{gZ~gJ;!E_?Ge}t*b8ey7{j7nN$W{lUA|t_OOA4L*OvLm+K8^AWU+x z#+`VZmPW3$k_`rl=TUItndQ3BUhNe{Lm?vi z6q?ubqG1$JoQe{u`O$9A^>8%6Yw zbd*S<_TCH$Q=#EGCA-YyV@<$&yD~lsYI}1I?k7Pc949SFXj*nObb6U0j4D&ka=bI$ZD3i%F5hA4j8XlmQbfueatst3| z}0SbYL#3b&)1MVmV#r30>-vBCQ~;RcZA5 zN8hw~4l_^Bo}P{7>ydUM*%S-5w4ea3iK-&Y$%XN@)@-rAtMYsa{8qQR~_u7vRi+lOh3uZRI$S5_tK4V%>gQSY@#HX6B% zYBhL%9rqgE$s+p4G^u$nmQ8|>AR5vS)@Jw`RW|;=*@0G`8|M1U=YMDX;?VU)_|tG# zmP=-lC6Mo8bY%ouMkUQ%IUQv=MZWLq(g~DNSC@{zoLJl2eD#UB?8@p` z%jz3(yK*{)ax&vm$gk2(A2baP(CgNyAgN2n-Z};`?PShw@#=f7r}Z4mwyl6HJa-vH zE-C$;Wf-Uqiti*!K7W}me;z7!Pt9ZToP-DZSokM$SCkL4=Q|Hs2?tFqN9?Agi*~?j zc$z*taAiDZr!CBARQA_~Y=AEE;PQ-iwo~7_cZtg+k_ya{pZdh24ax+Sp3Zp~3)#M6 zPbu1G97pK-b9}x0fhxh#I>j$ujX~Df)1+Ez|zpj4t2~28|HQxTEk)`v~w{`ycif?{^;)_})3v>K= zoI!hds}EDwz~^s|E9)MEd2>wj{OsSqV0AqT)78}3ZDs=QN>|P4M|z}saj^GH?d45w ze1fc92jHKh@T<>zcx7=ITR_XDl&X*`@p!9DswV$^h=1#_j%;{Shze}+^l1?Kmb((ij8}ISZ^T{F!KIQS z8vTldU)rdJXF4gw$%JiH8&ggxAv;uHxx7uI9n}80*xjNb3>XL+g>b`gXk!P*MBy zN)~T(;&>s6yIlcr<6kG$hEmWr$aimJMnKIoY80NJI-;gJhPXl9SdQWvRPbT|{! zmNiwgt4*k3I<70N*)}dW`Fkd}IZag2H#| z1FRn4Av?BcMg^N^#|pO}&S@u>P#WwWU2$yKdF4Y`)AD0kih3pr4E>uvuZUTGjC)aZ z{WAU!{9^1*tig$)>lb14_pxK(XW0u}+IdBfG$@@Ma80%azHW`y&p(MLKP+(TqJK_l zQ31*-=&@P+_Wspegphac9*?okMXfl&mR#FR85lcLN+x zeJB^lUyuIi%J_Qm{pK;J&E9TCWFBvI%ERB@Tqpz|#QON5EA28)D^hHxwX+B7UnC~( z_hf#)8@un88}&o9{IS1UvU;|x6Mt}scIz#PomTK@;I+LvUeo^ce0!PYVHR_b-`2wE z_+nWa#_^TDu3ycfp6(lV6MUL=;}G6CvET_JeO>Szi+4^cc$5x!PBn%O=cHq3un%be zNmV8I$GbmQEjoyQj-vt{!t|4>JH$1gZIa8pnst@v2px4&A*E_!^Hd}0Ab6V>-XP@xttL{aa32I_Bg7Gqy`7Atu?Wem(hIF zwxb^dr*qX&y6U9rT|D&{C8yuFNAtRHIu;k5R2Ze->~hm_JL)Z_%y% z9i5j>DwuxkMn}KMaP77-Kz~KpOj$I}kO7RZFxdA0OCu$WZCpiaZCqC@Yso{UyMS&( zuc%U%{;{4<&HYo;BP44Q~D!l+_rLm{If>_R(NO zeFb=w=>q}J_i!izkM#k78`RYr1vW&fzor|&o>{}(g93|sXEf~qHh(=*$1G~fsHR)q z9yRSl#gsIuRz3tYMO8zAV%Ca;Qm1J6Oc>YIai5z?n6GGi7N8sEf*vu-+lG}Y=)fqe z5@V(G8<22EHEjaK4lQai^5W2uKDXwSq7?yhl4}rvs|G2C6MK%-c-5fU?=W+{drFqH1ExLwv zGStP{)RUps9=ydHITdG*H&%Q#*;B}UrSgH8--Y3_i-hW+K$q_;s)V|3trg~A zJ^U?LJfpC-kRi2#79qq3N<4!Sp6!%~0XD=cDCD55h#%AnRD@)&s73@5KOoO`N<;va zly<+Qhab}^RvM^BigNkmt$2f zpW*C%7_WUlg+jEtz6gIJ&2Hjy$0u}85?t_hi$j73#9d;>bu7O|do6{lCa_V!l|(iQ zxsuQZCjYzA-a%e;l}l#73bp=X2-pL&wD(AO+u~c(HGfxGj|%Eds+x2`sOp*iqt z0Zgq|)W==GW$Nvx;MXeGu?J;^BE8o=Hbj{KX(~#UJ#qV)eT-iqT0t9BqfN6!v`sv2 zn*^K7<2DNG3N+P5{Y`H=Fsl=DTU)RbvOO#M&)@~AQ^C2a2v(-Fq%d_oG*ON*fdWU3 z#G?tmCx50$HB43TM_;_B*@WG}Rpc7P(itQ1!@aSdZ#;7e+sEq_1@og&z~HJyiLF8! zrNhz(r$hcOfV#9FJ{(NO^F)I&d!Jn|MEP|6)pVCOO6!OK8+G1-3bSb1ZJchAT^<8(dOlz$GdiL+i0D%{2u*i^>g;5v$5xS0bM0K&_U$I>;eqxX%Wlne zh(GA+vw4zapKHIzIAL;7_Iz&VgqYLZo^3l^7zPBouA9px&P|9aqei_MpaB#= zmHBQh$aMJ$O5zZve1g)zsogelKS4+-wgNbsqB1?rKw6T3_?Br`mt$brwSpRB9o=E2pIj2;n2w;<3g8_NHNUvU zm@CM$hgv}_TOdCArW?E<76WLJJCm6sy=bZ%T+ z!FRQGD$WxP0$_j6r;i3E*)UbXhc+jFZAbum(C54&TL_3w2saB>g{)H-U0bOfm4B9Y zR>qh5dFvR`w5R3j4dV!1Uw;OaIU1k|r&IQex9&Vr{=kn$h#|Q{+G%{so(cR#SBGeR zsq}JwUDw2u)B(<9c+Cr1K^bFrl*W6%#wI;av`8S%=@|*bsr`~V3FZe{uD}X|tuh(j zhB}OaJSgiErFKeH4Qi}krJdwz1apFOzeWY@JG^6_9a^PkVIgW-L4T7dYpF)zm3Cg2 zL@_HB3C*WHM|c__p3B&P?pzp@MT_9XTP!a7ia$2(*7{55E*k2 z>k!2In^M?tL*WW2^Fb%ad?VYhCb#wSosGU)GaM`()s)0NJ?(7cT2ak;T8I8r8+|c@ z%HNa^J6^5l^TCC`3V+1R()HxK{0E{>$U<{#A>Y~H6SDBxT)b7UYdl3Gw-fsR_HQ6* zzz&Skp2eP)-Hvkkx^dqksF`P5i;n{W^)Jn}xv;{Ihse*%jZJ(GB-p*6kj_FTll0m; z{o^C`96FtV_uh#gK;4x&%7jrGVmp5OoWAUnJzC$QV3>Zp-hZQW)|Ti>Qa}1`U0}u{ zDs+^6|40Py_iQJ(liSJd}C2+`t`Gn)w=#-zENFJ zn*jLaet5N(OMl`%?7a{Dle@v8+@AjH`QYalGhDoO!4Nrun9iTpGJO5j9q|w^ExQYH zL)_Ib?u{QiQNNHM9+N+ug}!7LsczUL7tPg!aq^GiXK12tH*NorDu!`g4IkxK+gu^R zO>*IUNYnKqJ?oiX>WbpGQB6w=WBR4|Ert9Tw@lA?P=A)kte6TS*(a{B)Y$IE?z`o_ z#MfNspFKZ|66^ZY#tp2MOO{}%Nwoz_n)gr1fHmc6|6}HlHw%kI{52!5R!~4$f^6ez zy|+k$X_Uzpz?r&VtS~@vRKKKxhs_H1y(b~THOZy(A$_N1A}C*-?d0=Ny*>J2W=zWk zCK8qNynmvBqw#S{wGfhO;s~^bPBEk)X~tX0JTRqTg7r-vN9;J;-6Q|lX5RFnDXbK_ zc&Fv~{c+#=j3|f8%EJhQQ7w%^vNu%*sd8!k%gxe!NH*O>z2avv&iGZ$SOQr4tp+;u zt*Bn@djsk4*zwn*aY2jA&HD&UTVHXuu`_YBVh4 z{|b$1+uow>`C*=HTLv0$WtZ>7%M{ zBY!$(e~E=za=8muy_Kv2irItOkjY*lS)t zm?hk1>?-4NGp4?lV$}6LZ`L1ueN<=xT7SJfgbld$Q*h?=_zLDAW?+|%#O&#@RetrR zAO_n3jXC0wJ5>9v9vY-U7a6M@Tdh`T17dYPgcaEJ7;z+wP=S@v%GBKT27b>_Kay&I zE|MW)LM?%{R)nX=A0Nf2Zv%!wp5(#}_I05ZXE%clrN4r1TQE6+ zT9lP|f9QZ-#oZAH?_kVIkK|x{WH<-MH@w4-J4TsgaOYy9sA%CE>dY)+~o1JHObPo{aJdw%)Q5f+6VvI7m93YRy!;F9^lUyLTf$-~X*m_EksYoWOtGjHR%TM0RoyOVjSIMsah3C2lJZBSOhF@Kk|`{JAg z#D536qocw%uB#DZj8pcbhj4wsu&Se2_`;y5Spl5+dw^5;gR%;af?r#%i_v}!Q^ByQ z2^|(F8>Qkji#u?lB zh*eXK^OYF@8mHu6JbBg+l@y{C{9P1m36J7WM>t>8G{O?yL*8uP!1 z?;#ZRC=+e)A7ISBiCxGNgnuJn@kV_;xB@db-4*+#!SO!g2Gv?Yp24Iw`iB|FJ{nTe zJBS4`E3eqke1h>QeoR&)uK8?}C+p=YoF=c!TEWx8bA#~deX4yojDKgtVDeSjal1Xr z>aF;v8`2CBwM2~}{9rTfagsJ~4Ew3;aJv3o;8fkQ#tf7-M-w~3>He6@2+*V>DyaCb zahn?;M#VEUc{`oj?{+ka& z*GY{=B2pner0XxXxqk{!(YU?k{cr>0$UJsMY!b@fIla?A$|M>*>dPEZk-bI9k)Dr` z>0O8kHJD`m=G>RqWHyA1>suNf7PCM>TQ6(N9zI7J4QK~6#aRlRov05QoWv!XZ!5U~1|31ut{2cyb6T(#UM z3(sFdm&Py^Yus^<2-R@SuXkWPJkWDD7(P?M$nQVkAxnO#gU3I}*YzK!1)c~8u~3Qf z!(-wvulQ@2kp$r@d_Fe6ZFey~`sVf_Vy1mhPqdwoPtQ-!jjO4HvMPg>N!Q;>uc2}+ z?kdHcmXm>PAWTjtImIN0_~(sg7zT(T7{Pr+wt>gl@z~~?4#d;i%-DliArO1Mfkzd4 ztPqGDV4;nNe9r=0g}nZNcYHa-{ryeB5}xG69`BUua-NgzZ7T@HBS$WfsV&2kAZ{Qg zar0GCsGldwq$52cR@w%n*bs4^u`5jX89P9fXY9%{dqxfr_09}tm@AtkKL^0h(X@hWLj*|I&BcPOL$bVyz6x*~elwre zE2@&Dotfe5bcqanUePAW{OG-*`*=`RCP=(^-MDXLdFi(3-eVruFxtpx#ha|^z9UeOI|PgJp22-T9wo=i80J$Y_DKmiS_%3&?S$wI9qB;HcB z+w+aM@yXC=NTWXPdK#4g%(j^qSh3uwpPgTMtEjvt6#XD}IcD&tvW(6Xg+S;(qq0s5 z8R~yzDSL^G>*_(Q$~y~(NOM)?uolgH?^&rmgR*K^YYvdK#XFMi_I$O?1DG=?s|K^? zuuTw^0K~Snxp<4;cE}q6m4!8`X$P?hYf#f-iqH@zB))6fDuy@>ngC#RJ-I5{bi>D2 zp9HU-y~J>PgLZ9H(+* zvP`b^in`=@aaQ!oxLQG#9PMM$xTy@1^G3yzmiUBVY#u3lzF$(tPW+hs)nz=M1GrqV zf;cEk=cNJ%n&fiXQJ&4^pPs)AP!@midqwF2Ojdx9f%+x!{8W*95j_=4=V1yLuMZ&G zGb^E#OXh_^S@=KO$>!i8rt_z@#Ap`IcCy)d7UtrW#LE>vNq160Qw^&c*x5*BTP5hO z4I;9yG6q=2|Ndf`2uYwMo`cF=A~bfxR4fNZ>rNKXK@ySQ%0gNvrGaUsXQh8%EY}KN z=fn&=geI|H63!O6wjor4*&&NTOIG zGpldE&_WD|ilf*n7N#^0=eJ)VHpWU}aSu{Ux7A5)^zU;A;BWvA$8imSpP7wwbaiTr z9!S~AD&iMef=`BpWDzpWr9XdYd)cyUf5&*ei0GfPrvBS%l!mQf$=hSZoO4L`Uo}_Z1-c#yb54wLyi+X5)BZkxDt!Y_$$b9R|>^w?jTNZt_L>~(E+_`X7vitN< znhoNf9Lt?}0S(1xOD`b(P(N#eDrn&LP5;=1;~qQgM?LkJ5}E>MFZub{?1%KA45z?4 zAU4Tw&*07jrx_GaA%t$W;j`iQ#5RG_wL`YjWe#vS==xe&q56L*R}U_~cLnp)q|d4# z+fB+hAU0bFpGVQKqFhfiViQ!s*M&CJ!;A05>IssL&<0Fy<}AjpNnYXJ{@Srhp_J>} zwK6SREYQf^enkP~r$;XBIo)4rrSq1Fe+< zuzu-zF353*fNp=3PfsC%y)+h^QQ08PFn_Kv>f#0L-9zJ}=S)H3q%2~l~vt15POe;wj;FP4Q zrTcscqy}a2BCMJ@SXdkfC*5EIjDeG=>V_1~qN?&DCPsgNq-iDT0-RRVyOV&xBo;O} zm81)BvJkioEg=do6S7LCj6T80i#wrL}#sRGC_14;C3%+O`=0<3%^ zAZ~==!OwpS(E@bB?b{o$0YfOazrpHIUD&p_Op=Z#Yny-TWqjCG27YkZCRmWi7Itbo zSncdOIIl%X&&BKMW7~1DG<;(TF?Y8UIxhgksXZI6X%i%3rf@`IKe<*R=qlp(9N;z`lIi|wc^1<}OkEpSqt zt9m0cK5c-B^9@KyBDAh>oQT&?*dfg#n#`gh{dR2Wx)e?NkKw+AP{*VFP!0i)=8+ly zyVsfh>Tp|c)$4mrDyL2Zoo{QY{AZ(4`USu~Y6bqh5X()ZVGG5h!U~_7ak`E+A8sa_ zyz+lauAg51m3HTu#J=?0Cu>#x#ou0Fo10&pkyjcRM_#ZAnX_NYSY~OPdf2&?xl+hBzjd@kJDrr(52yNCX}Cq3qKW{yjwq@jRW;ewtZ{7(H~vG){br? zHyE^|0g;{tgf1sZn71!D|KadmV0l&2Yg9PIwc{F$FwLGOgA;|99y^E!#E1y^_Dg?8 z^duFpS0m6`;7NZ_4ma7ir65yIA>{3VeNgXp56)gvCZVF`Of6DbbPSe~20p>Op84up93r25u|P>kCo2UC>3mEchoMUEuq ztem~NA~_M8Z?553OIGdp&Ul@B{tbVgEeC^kG-1+7Zu5jhm(gn$iez_z5V@ak1yxaD zYJ|}ZdHZG9F+ta3c=SH9iZTx@GzcT+=P_I3bPJ?3{cGa(- z4GuR5!sLSFrI{-uGG>P31LP#OQ#`5TC=jLY#4-(-J7w)Ld>fW9VV0VlA4MTNw%I<3 zYz2i?0dWo)z6-3R$~1YT^A6@s=hk)@cEG98&R!J-y9eAp^KF3?rq2?>S>wfc&Tml0 z5GKgp65A|6FsJ4wk__2dsd0a>_MmGp+%#`(CkvIJllrt_MK(91>?6O(GV-7qRb+EB zDit#UrBm8VR*(pICMeH+`YMsG(+mW^FgV)=#?LsZb%GsU42B&z z+&oEgEDTkdy_RrP7B0vL>}FccI}oXSpB0@M%(o;!rj8e(*J)=>2yTCNmK%~FO3a)N ztq`PUSB+p3MSs}%l=7Ed*!@^=wRajiSLDfv?P!X< z>oGX#h7w@wU00k8v=2LNAnE%poYESH)BCVW2z)Weu!5nlS=vlxAENPtYM;q7 zU}^7Z&q}RytK<)8-->ObZ@I34ZXY@0yl(K6j! z$=HfJ>u;;cSnYejHcXn_pC$qFs{2b>l;ya|+Vg9UYqF94Z80v3t%~fQ?>>fav2QQe zFsJP8k+0eLr0?2%cf5uvRkonM%~>~RP|6|wwx_y1L-Nne_P%FjY;%2gy@oB<-qLtv z4LvnXlbGK){z}Kj6^@5(7`)S~v#s6XI39K3aPypWIR-eAS}VvlhT9*dQV5j>C%ViVRNWtf zD|Eb#8eiGtEhP1Nf;N&3X-LhPt<6a`NlOF07sXFsJNEf6NO9{^-YZHgd-ti*SrcAK zE1-g!TQz^+FR#fP2pNobl$||DQX#*ZctH_HCdnfbL zumUZs&GrSN;)6R|wAs3T?4=k!w86kjn0`I;!9RBL6>SLp4$7CaA^fefuVzAo8o8g* zgfP|nw`tE)%YPd|^nK0~r43H-s^}b4+v_s#zAxd{Q~ykcL8-+4i44^5{P(ep)AP*s zF^qp>_O+>56tgqcH!`cm(9w4OJj^Zm28ohPF`uVT7a? z`o}d;MHRp+JahGak$TTUN&r@W=5a{EwV;1FlmV@Z%N17e*2v``4_$$@b8v)Z^yxNaedRUUQgrkzZ&)Ga!ImQLNC2u9RX z^I*%WZa+6909ju+MNPNz#;qJFq$^Uv(~qM*PBGMvqd&&Ay#3T3t}Nu%a|w*XeeZv3 z)%)h=&h$hoC%Lb>Vw9TPCtX?HMaTk_TYb-Q4Go4fOhL-65#?bUq%3=cGL_rIwAw9p zo?CvETi86utd$QGw2oUo*mA@D@G>@ySrib%>D#Cf7UdYK?bq9-4a<4>!g-PdY<}SC znBRT7wK!xw-xa6=#<#V>t^Ms{5ZZqQsh;O|o2ax2Qbo{jpHwR&+6DVtt>Fn>mUvH2kUDH}lsos7xk6nMuT_pzQ zza`ANbceN%JEhAodXKDPdQ&&qZF+2Sb=$sz)p9gqnHDBX1)m#_He6MWkDz)~Tmkwj z8W(fT=hGVQN1*Acpjaot7`^I1w6V_RDMsEQ@W*Dw7{ zcbOa$mGpTFpd9lE=9XkP*W-WaookWY-VBN0d4aNxq#s?Sc?ZQ?TZ zaa)Ghh84-2Y--j}d@iI+r)(J-n4XbWvW(elJ%jv08w+>!laMyoB5M7IyS%h`I2iV0<$;W;f(w>YA-JDamEa6JZPB6fOG{MuDzE_VJBE|M`D5M)q~sCG6Wm zxrHP*@jj_Jz}GgP$0CwDi=W9ZbHF8+M1Tghs47GAt)faKOea5|yaZ2a z3rZM=wJla_JN~Mf^5KRnHT!)PP!^>-*NO7YM1NSNo-8_@*SBUQ??bh4Kg;DOmx;{$ zs4V-VS=4;DsvZM9N~u%oZ(!HG_DVgo1o1gFRE@hogpNrVlD`1*S=38UH*sdI(@gpn zUFdJLVfKHkMdAjIlXFyEMhn%Ew#SOWp3d)HBe0a3mMOTF+|i>#y>-By>WJMJcca{u z75eN)NS*Sy2Gh4%{dLXVYl_}MdslHqqRMrDq!oa6QU~Ho8!GcGv~TPe0rRW?iSzvF z(jVAwG;Wf)1jo;HaM%VW$k%DMzEVO)i%E~F7-E0@(<$2!nAw>llEdGiRO*QECad;A zF@6u}FH!kbFvR$Q<=Zrg6=x`&_fWbju(X|y&?Qj0dJ6ltR5L|fXF5|xkof=~Pk)rF zupiS5;Fn)Npcx>qyM9ddf!`VXfL2f{$@TH9@P9(jEorNAygjUl(>Y<=SSZfJRU&m> zEJ=SLi~?4Or2R{tx^tDU%eJp(Kpbab$rX7rVmk_TNvmvLi=n;HwuxtagfQ#}S}W2!XF4^e*BxsyC<9j^#JJsctbYKxmFu0$ za=VM8Mlo!Vi7IK}CXg7>362Xs%|wflnZC0S0U8*Cb|^uvt&0GlzBecXi1B*Z5_W$B zu{&$Rh;f{64R?WB`LGR0jOVYGKoiJ@ha2%?oRaxx29;mk((eiY0bWkWjHYx}T;q1$ z0>VG*I`x?hlG>mwU4T=427~2Pp1k-u6%zs=nd3yN0Ew=N0Fcw*unk3oV`Tz>Y`VjZ zYym!PjvtcMNgY9eTf4)DWOvrY5a54TcJzR(&T_&0RD2@{5n{#TL~eTLRy%y63!3mP zjEHmO8`1M#u@hcTA#$^SdVqh9;_!a9L8z(q3Ut_ zX(s1=q|qo(6i~cOnnP|94>+*P>Z%Q{9KO(;JusF@-zkqZ2mCCl9$ge=g=v2X?WihN z=OzNj;k*#YgZ|UC{)q{=8LDFWi2$0R5XggW(g6h66OWj@^f)0Y&9O5IYYgC#gp@fMK~)FMY!*<5rSx!&>)lf#WzeR?Ctqh zO^gt-ZB8?hT)iV8q3BrIj((C#6r8uy4~<4H`3-rOMvYWxTT3C+j1PYoY%#BqkF5MhmD}G zsVcJ8d|Wq6+Wn;?!E7{|R~OzwZ%=*bk?{#tm$JfRa}Nx_J3|bcU2v14={-G#M7-w0 zhaW(nOYc5S(97uQpPPRa%}^#d{7ii)M2L>TTPgjsujk`Fm)>F~h&=G^j?+x09242G zf7i{zB*#e0EdF8qFnSgu4(rS#Le*`Ru35cVBhEKJ<_>{PPp&06HaSLYK`NT z`l2IdsNaF%i_J~%HYF3OZ*m%@+I+t$?Hjv?^1~%_9fK4Xqv?OTIGe;ZkpdfWVst{5 zn23An^t+(8uPh}8!DzH>O99zeOG=aNdB{ke+4eSScEYYVqWHeLe_}EmC6^OD^}(I6 z>y2n1eXwt0G8`j>lrRwE^-WBMTqlR&8DKGa@|C&BuwXm%-;tC z%A>C^Xgsqh#0Y zZwvBT5cav-&u*@@w=^EVCjl9YO%2nmy$k(qx2D}N-r0Yx1o&+ax7HqRuRgS>SIbk@ z76_7R<@_hfb7~Tt zq2Gz?pTC#L`iKh5F#3#E5{|+cwa4_p9<#sT&}SDzyB#P5@6!eZ=LRR>3u$FS#S=Jn zpIroCb$5T=@by*G>w4waZ2_NNpD)T=&Gn7Xt$)3VGY7+BHp=HFLU^J@i)T(AA zw9u*V1&gukFqvYLwb5*|+<1u2XJhBnK!ZPwPz`Eaw*LQM&jmE0a^MHy$ZKd@R)7M=W{o||Z4f0hHV`S#Sz zH+FxsKbl4CXs~<^&3u2gM?HT#wT8}V|A-bq$y5KRh5*k!|B!}&%qRb- z2C#wmp+BM>lwLdj40iZ;Z~LzA?3m9tMP!s-0Odd$zko{R=$_|s?eR)YR{zal*gI_e)entyup=9J5Ge@e5jBwPo-i-UY@EFf#bmU z@>Gt0p8k86RkZ;?F9hyxkKvjW#cPTU?4aLLB?!CS<$Z zbOJqIme!37ul?cE?#L^XyWp6BE)$P`I5uRd_BlrA0>-1i2Q8tCYEpT+{hHO3+dbTo zRi)YXYgGIB1KCuDY>(3r4UnT}na6E=n3DS9hA}+_``GMz_!N7VGXnK&=4Vs&3u*mT zI&!Y(mugy&t(;G91LQ8jr-bNRf4iWwXUs5Nmn@e}zuFI0yYT=RJjE^hA<~L}aAL4e zsQMSSf~ceWYD{LZdWh|J!A*hYekbmtOtzm) z@vq(ZkkjoKGD_c_279kyC*)+7xV_Tclfkhs+Y6HKLw}yA>BAd9Y0mou+9Nsk5Fw!t zJYMaEq>5|ri6D+|-1kdISZnEj&!zWQHGz1z_=%MMx{VGQ-+mE;^x0W@*=_5e+dk9m z%@Ot)SoKD65B$mQ<3Z|N2^@T*~JR>I|^YOm(SzI|X9 z1(r!d(EgQ*6w2gIKZ11MP=Zk8&FF{R736*RT&4^U9Lq>iid}f0bY2L56&?A=Y$Qij zAppfA0ay#0m%80hyrnwBwMBmKWnS?SV+OT9AgU!7w@tjZD+ZI(@sIfFiIl5u3R>ku z%D z_Re+8cI09S{+##j2+9~!F2L%iJMMtnKATY4r=tYZpd)8z3}xDX9rATT6l?B^po}rs z`#pgE4gc8GJFklQ%RAzD!JF#4V&{bUveGhAaug4)Y?kNd&+;b!yAo-lfl zWt8vaLzb`YxtUpiW$8rBhvo12#HHVUSpEo)aQ35vVcXu)hzQOA)lM7oMO2W}0Czy| zNF}rZz9W552TUJ2nIwz??+t0(oYcj0g^0;Z440nc&=3oxCUuFCRuaug#`&>1B8Lgy zPBW2wftyn?1q_4pLMSJP`_jw?L*Xo!$;n{uKN#){Xe*?DBKhzk-;mgFNM4Z;4EgYw zhz6hk#&H|(t|TXGJN(mdO`E8$CbeNjoX!b58d?5w5ib|d$+zkwv&KU^s>&DU}iT z&ufG9yhHs+p_~7C0U_m;C=Iqmpmx6{?kaj#kG#5nscNSUG%3!$v3w!soe{pEveimB zay-4zV!Dn^WS$!wC7$<5Wh+#!$2BY-zIUD(11#T;YXbS9+qtMs*$p~PeqD}f-+8a) z2_{oR-e;}?<0(q#38)ETCst3DV#-X7=$SgckEP9uMEWaP#*A#s_O;|bYm@s~6G*5l zIc+R|mDV8*iYIjp5g!t&*^%3fO&s=S)fq{C<^_Xc!#P9f!rs_}Jlg14v4`|0P%Fn_ zhhT9k+c_#O8@p(B^XCqh*#Q%6IAW)5P&;obx0`lUYcBS;b4oLVhBFyE!YU(yEjzxP z9f8kgzoG$Oe;Cp78S=#bYg&;Q&fk_9J%3w&QQC?dM&Cx1HDdPBZv)C25FtJ0(;6|| z^1I7!ODgOtcG=;)K+vV>0c?7{LyvRMvrg|ZnRsn43jg%N=+g7w)OWnPm}+NDG#Spz z*qOynx@n5Yc2LHV;b~eStJ%<4iJ`7mj=E5}_7CbRq*W*S)nM2GssaNl@=q^=% zjZjXVcB*URNac#G^H(oXoWx+*0jWc&H<# zpMoUNZkY<3fcnEG(kOq)o1HA68~Yjku5I^>YwUkGb-g(HQu-<_Aog0@%{er#chrum zNV+mt?BKeIrp6h4^3+ZnU{Z`XC;mNuFs_3sGDhyi$2BMbw#eQ1yai5$b(UL!9tdi! zfB?*qd&qeU91v^d0C3m=DZ@S>&5{$qd`~ls&h?Js+9wk~8o9A^8NI^iRPKXf*TnsV ziuJn^$5xAu#XkbiNuojIRn)M8wPnLPFSb$ssyj2Uwkf@Rdt22)*+D!Bia+mvZ<+Er z?5A{Q_eE`{JV|_AyQ$4VU({{^vsjo^rv5e>x6x$J(Z8s@Lh?^?xcF@_PJ{KkP541= z7Kdc!lV#=X6KS`m2DNo18yJ_y@>%&R$ax`&2dxgQSh}DPR$@V$`lR@7YOF|>WU^__ zZK);#*VLLSAzjGaKQ$4u-1bj@NxzQwc~!+Ir?ekR&W-S8Y|irvrV4c^3!&QKMySqB z;?{Vh%#+&}B}0Qa-htK%pulZ3GEBpdN=49=O8>maRMSduO0+GvAI2vskP=s${b+3B zlReFll-N4ScYV-3%b}F`(uMXWmdE9rLn-kss!RPRNaeNnNRxlqeJ@;pAF@%2ehs!h z*bmj>s2@jjnjtB%WsyuDBljc)QsNpe4Vx}qevxJNCRq>D&uIfxO$F)<#^!4eog+h1 zVk`ABuk6^|JdnFq;ryFetLG>jyZ!Z%lRBmjpul|`_1McBpb9G7TBRpD0fOqm*)|w{ zqQ49~2Hev)FJuZ*sIvio+vq67mZ;I`Zu25RsZuR_nqa$O=^r22^viK&QFCTR>CCM^ z(*N6M#UD1`>@m%?G`GAGK!~s`|3E!yG%`Jxe03XG?lkaL0SUi+Z?K}TZUNgf%<*@B zC|QG;U)>5`Uj~4fb@Nr}*X+CHSsf7<;2^Wr7i#ZmW(Gin>EKH|1-9eMm4mSYe z+#(cC11l1y(lQf(o9d_vBE^xIDBMm`*}{}StNFL^O6&Sd`^kbHvRhZAS@z-Jek>C% z+_eA3UfOMcD4~rMPav zuq&X=WJwT9g0ppu;N=Qsmlm8V*2o7YdT02}VWd2QPU_zjq)=Bw?Q zy;M1E7`tA7V3L5C3&-%s)w>-GDXYQX_WEkcIHgtTmK|SFYeCmz|5B!Nur5P<1>0fX zv-leJOEQV)UZTdg4JB-dc1-t0Z1-(B8Ovq4ir==Au^r}ZuFq*dlSCwNESF5$wyu=3 zp|#TnfcTE!4mfTsEXPnjaNZGJ*`1+&dcczv0XO=85fdqDH})CCmX+c}m+GKv+97*D zO}K&Rhwye6r70o#3#}xY^E^D;GRn`P;kX=bB$7bH}>Lg2&E1k4$1-eI6AIiz->P%_a&3=Y;B85yHZA${P zbM(a<+}vpSO~~d(-1_?z#34G0^P^Fy3?_YBJF1H2n>L)}-~0_ephWUQs1S!ZB9N6E zG_538gh;7679^e1hICF+>3al~wuP;&(~7`~u|YeIzV1h#(P*AtQYMaX8xi4Y zo{yoIoS*v`x=DJykD;8T5Bw;~NqNM7eNyg^*tYf8CGis%s95}QFld*nixSyNQ1Ow- z4vwAN)AYzNExih*2wiT5V5_9QRr+`Djl)?rq`vX1(v=U}r0QZMwop^FQ!Bd;&hNe) zA^bMPyDB2R=Cc24!)|}6rp#?Dt4AFe7EW{$t7rqcf|36x1^Hx zL2J(CjZL!g4^L`{m2mNZ+bBxzy)J;i{1RCF7hLklValSjE zg8gVXbLshSvnU{j6Mmaf(u{1n{@XI6=Wh#2T97^4$J`kmoe^@~neM;r#{*2ux{+w;+^`eu! zJ4){Oe^S#Yihb5`L$&+V1Lw1}*#@Dg@C~8IMyxK%V>EiXn9nDRD}6H4LCTJIQPZ>% zk~Gg7RF0<^h%~*w`k?ohJiVJ=s07ao7-@>X`mmrBO})#9``K*K*JwFy;3;y(9XZ;t zf~CmyuO7MnrOFj~Olik8G)2C@dbF(+*YV`n#qIbCmF8KFB17=*cDgwFb1}bP{E2JJ zK^aPx>GhMZog5Ay?tjkp2keM$gCxcCUX$6KN?nOzLY8^`B=&i>Oq00ZhG`haF20!< z4&1r#C$WxW`+t7-oOau=3Mpl;^WAqE_F>1uLG*2yhGA~j-(6>mgEl~dN&-FIBQ~56n>PmfSyqSe+iscWz3|m-xYL_?gz@!LRqJsq++?7s^iuk z$V#jvT!0ToTy^TTECGZV;m1yD91%~Uh86L=Eg5;6Y%u8b%0XGUUQS8fKW?IJS^hW; zcukb#4Oo&H*(}nuG}~pdw#aW?oMOwo4Q@#_wrj(V!9DYFe{gl|5jV6q>Yj5i<05hWi4S z?-BvZHqqfKe=we+52OItRh!#GHe+qLeYoo1akwQ(Qe1ftPrH?h?hbYbE)Dw5FEp5);E#=Y@1BN@z_utUyR{n|hv&%#A@v zb3?P;X#+-(gbuki!e_;{6K{1V{m86SvDtt5wr^G!=al*0HaScI)Tkex#2N-k5 zVkD3TSnh@S$wV@Hbet2zSuXtjSplSeJl7+KNRe}9xp$wF`G4~pji1nX(j4Eq63cRGpVAD#$2Cj&lVyC}lU=Ws?0Vg+U9SP`n!2SPOj~$k zU6pHJ2Hr3Ru`zS~J=nQA)#wnU`!aZqx}w$TMAwVQU=ymYf5fsskCAYF->#lX?DUaU z-=l#zaOk~zcj}CUjG#>42Lmbv=H;JAXa4M8_w?D>b zIT|QCiwf6NFn6X@gUjqsYt$5GyWENb^B z9y9!sHh_J$;3H}Ng&Y0B{kmO#?JbSRFXr-o8G&WE5ojnkC`*=M!*(&Ajp*8T5Tc<9 zyR#fflBVu1ugDUc#5==zG_VPtq%e{cAILHe0vfPf z6URa47pfiC0C`!{xdmaz_Ph`)%wsfKdhYs$li;L8f7j^NTUk*EzS(@(hN3_AMe#RQnelo_vOQ?_L~HZKhpSN zp1%o$OREI>INFU;y^W{6Q4eoiVXJ7S$8s}bI5r8xThDtjp6UAGiYz@7AzxxRcn^^~ zG9Yfh%(Zs_bqVvoBNDCj9J*rcPIMYV|8e){lkTNM0{uXfGp17%{b5AQXB>ZVTtg6L zMq|CdEi-z?lbWU+0k@O4rZ53Vljx=&0)JwY38zmIn>7-nL0P;mYp(3`*{RXkd_|LL zr!WK`UT|%bo~KAGgV^Z-9$_@8A5tksvkw^UYatO(LxUl~EfVch%C zH1M7*lM<*b0g979s2KrPlUb-f5eIN5#Bcg$o}Q%9@$kd;mM@d2s4M|Clhvp(e~azN zqCYcigkD${FTg2@Yd%(`nlx1`Csicp?)p&43i$FQ;*K^>^bJj%Q=GJj@0*>5y3j{YiG?QtLgsqZX(5bO} zfp`V1*1=1%x%t#@Zb0&psFCi}?nXeiR_R&2uSOcuS4+jsosTvf912e2Eogx z{SE}ASCTF_>@@B^z|k63gbOjM+f& z_`rOMBzyrr)eL;#UbIQR7hu$pc@Gy_4%$(KIBv_hhhuuS4NHV?J<}eposVnc`B^nG z>_PoSCAprPQzf$=j?dvnf3g^taz;Jq*pw*O>a=IlL(b66v}}HEn^b2oMrXNL0U8*V zIWOc25UD1gLe4bh3`cH0<@}OrBZK?QEm(4Vs~J`Zq=&~y5a zK<-twWXJHbtEa|5&H&}C7;Zid@^Ql zv9R3_3^!6m5aE_M$7Giq$$W!$6mE{ybUnyWZj-6U$t55mR1Pdx6^-q9+^HC$d{Ig+ zFISb%eOIjdvE;>#R*qoLEGZCGD^jsTz*iq#RhTze~w zuJCkLtH9C7Vn;w%XfH8k#{VX59=#0UQ1CNjb7I6d_f%u0BOl$j9go974g*@ zy``6>bs4gyvh7H303xuLtT4&j8_F3KYJ;sL3Ef?QQe-tS1RNhR5xoLSbT7fmI^uGBKn&(DRMzYc=*RE9!Kr)6Zi%6>Kw=)Lo z>wvVSO0|k`EK--$Ii{vIe`l6YF-61~V@pbE)dCyfaBTpG=uy zV%b)@ptBzcXQ|q>0t}0+IAw;3Ra@yoTUDL2TxDGWe}A>f?W0l8nddX{hFvQ!Bu6>1 zbGri2UKd^q#lpc{hlpKB^4+B=D`|vxlmQFlFf@WFip;f}yB!Z+gS2IM)B}4`2~9`Y z63|?UK@A8Ho{9Opc!T*TIP%h!thuABO0F#cOKRax(y(zM1aqls++2A!W$D@OLKp=C zXKZBwf7Gb0Ou-BaM^~nfIQN`i&U~)Eaxcd+vuhh?*kA>M_~bFkOOYuI&Fi$P5R!wc zDr7WrTWeW^I$I##Sf(9>ibbr$O37_xgMzSaWJHS>9py@N>&DtvIaOJa(dfCem?~Ic z-LG;u4WzZgVA1cTS&&tdE49fx6ICt&fGnHKe-f#0>QVr7K84ppsW>NBK6nd=NU}@) zv!ju}jWU?Im3b@F6y?gaYhozSqgLI*7tE-Nq~+?M^3MI6iyf1brRO-FdoFy}qbz1L zYUc|YumF*kD@Mmla&t}P;pTh;CC-liO)F7QlPa@St3t~=6}Mcok&9WIg6JP_*8w!9 ze*jZNwy-Ym8AtgBkupR2eFt68a~S~69e1E0`}3e3M`Uhj`8fUgJKVwgF@ypD<(GL^ zS6%nH2E#5Es%oS=PI&9Z-ZetVu^*gm&9F}vTH0awYy`wy_)#z(9C!b<4xk|YEtl?K zEx98DD3pli-Kncx`;&9URUxC%7T%!Se~cjH+ix&JCkZxhF+M6#9F5|wtU*%(RjF_8 zz(ICitt4EAP-4O+HL(7vz_0zT9%PRkb^xgoO^mvoK3LZT(xK(rA;Q?NT|HExnAms= zYv{4BM7`tUBy<8#`{hYhs)?oF(Ev1SM^O#M1rcA(`4$xZJC?EUdqEV^-ej{}fAS;) zTC`8_y$0U}#mzNV3JdsN=xAVwuXD^nPbWypYl4NZm-Vk}}mc zl5iJHrOnq~j|DWGZbRvh;*C7Vf3*Tf4(4!Czp{mem-{?cJPCXqT834YpweUrI&nzaPHD%B z+bcKsibO1#+}D`LE(SgAxP~CYOkoR)d!1U_1rlJVxCO)=@3-unY+;!^e-}+7R+~69 z!Y=OAC)FgjGa4W2U8CWwDODGtFdEHM7R2#wI)r#eCLEno?@NHw-J_*#grTH&IBUuj zBG5@n(c`!9YUO%9Pd+`3g0`bTUsX zy9AF)_85&G!3(B*F8ieQdxCH4v|7iF^EV(L*bUt<3cn52YAC;BgIE+s)i+g)fXJR832c{8C3D~U`3 z?wUuMXL{TKf3T3yw2~}7#L?*G@_sVc|7#8s4_6qR<)XQ%TcaZMmUbUPQtBi}lmCcjGMtj?WWU9Q5`eyF&XCz#X?_+?n{#8mLA-ETE)AYS?OWRx>f_Ne-%iCXIM!by63`!B1;$fWq9pr}uJ5_NCC^^}tu*z~ z=n?$Qf2TgWSn}2`{Wt85HCh9Zt{&N^YI`%5=(OEEwmz>B*eIM4BUnCPS!)u6R`m9e zUj^)?A&^*Y2ZDE@U*m&bOBB# z>!ugWCGjJ}U6T28K*DFwHsO2PQ5Tc|TiQ?Uf45oW`F?&g3DkzeihKcHPeJ-x&D)gF zp&udix|2GD2)j5WzYIGTtBTGa$7+Wg1U(CC$J+e8DU!L+oXhx+(&zHT0$tbUGFswB z?fa*#LB~{Bzv}SWm6nb7KC;ecy3vq)`{@;5DLk5c!>Q^zVt4qPT6 ze?(z;+JF(^XeZlHXp_>gB41!eaxAb-xO&J~h!&$W1!r=^qzaI5y$9kGBbuz}SOz(9 zZ+4~zh7iBNF>Lx7ycqVhfg!>#A0_$Afd~Z8njiuUJwH9A`_KQxa24bqc5R^cLm6`P z>*!e~J+~*Kfwi)z!?(s9HdhejJHM^yj;Wny0B=B(QgK2fAIpW z=z{F3wEDx^$vLUx=#LLKrKOz60sMeV!= zaO;%UMO-&lAP<#wQaw%(2$@5 z$@C|JMpR}(F>L#X70n39edbQ4=LHOebqism(W50(JZ{JI-M3y$p2L80?$6|q^q-9| znQL#ol@*1kcGr%oU{b!`3RMF=QQ8Bo6;qPEc(fa#+%xKFr8 zpSK`NGM5PcMCqR8D3TO~eMlKlW&q^)%jZ` z-q7h`{psKb#I%-C*jL=Bowp!L^%{2f!wSge?b$mcd_j(RTQQ~B$38pD2=fP>^1KSX zvDyTb;=MKki@o)dE(n`t9N_y)3!*sl*j7LGIPMg!OVD|bsp1Z3H`#4^bXDx;ypH^# zbftc@`?sG($u+DZe@RY3{-drbLuGUOqjcNU5X=CqY!~%PU(*7U*kSsA#rF4htTVj( zT6&HjMb$JcyV-tzG zc2Y-^=iJg^uvnip@f3OIz66W$po}EPwb;+Xo%D?vLhw>>?>F?kO-?f)ZCC-)bv2$icI;*=XWJ~zW=x&wE23!!WgKzKR#;*iw#HS+ zu5GW#AegoFbsb%WBbHIynF`r7jLgx(Fg%N;#$k*;5KF}5EQU1{&tj>u z7^4ry5-~Z8Aq~gVSY|xN*aLDyOUPPl&ocifxS6JFT?ij(Ilbnv1^xEcTdlGLX_Ysf z4mYy60F#5}Te2n)RVB*kXSv*MyNzWYwzmSNe=wvX^|Kiz5m?dN^k#DAt}XY81lsvU zxU{UxXM@*BRMKeVgm5p3AkqvoNqf#UMCy0B+zm}JKCA$CofeSw#JI6jAN@57jIjyv z)Y?g1p#Bav46Ig?wFU8~YtdCz^0&%9P%8=Jg9Im=kz)We|Q*sY3zG zf0`xPtm5THwl2a4n#yS=bqk4KWLX|tq4G$r3*3%fBC8C2T$8s2`EM_qFYZBx`F)>UYJy zoEeDA?t>L~@UEs`+Z-!D4yPoT)N5ybe>p?=mQS68OTPWZ=J9}+uWfVgt!___d`7+~0eq{0*>3K+BliSR_R;AtjUgh=tcBs7uaO-TVF^U9h9X*3Mlf#iAO zj0CL}N1i3hC^&3`;pS+CwKy7Ke}UG(5McL*6@>jPeNMW;MEUmPr%$(_i8AhEG#z(h z39w~RWk2RU=>`+vTmLxx@H%UP2=J>m20XiyIs`Yjm+alL`szvT@UhJ8yaj^yfXwOG z<^W{Z0>RDhs&ZBXN9u4RnVXB=x(5iy>8y#s%?+<}4IG(X)fG2`@fsYqe_?R*D_kuY zq2oj*H-Ywm3bHdbV<}#4z6E_&KBO`$>)Pu3VwFvKxnIF=`BTchot=MJ`{16Xe^|5h zbGH6r&4Yc`{$UN%*V+4rHBdh%(I3$~$-|y^z9o_D#&DQ1?-l`b~nUAoA?t@8e+d!T8 zq%Jox(9I+#bUu4F0%A_1ZPzn;=aw#H_K{n~g|`?{-&?8;o9+kIn@V@oj#7Sf#tEZ+ zY51E;uiRsbt(~*MSKnX89Tpa03_RJP_|M)rD)`Z!I70f<-B4EYf2;VE!Tf7~RF(Z~ zUsU1!?T(m(_}%m;^mCA*G?M@Ai!0#h%iHTmpJs-2&wZ01Rn z#}oD02#P^f)T^~6=F+9%UM!a+45y^FDI&ScI;==cu9TOr=<*R6jed7r>s8qRmZp}N z(X-r0X2WqyJJtoWfBj_bFihHR;YR`6HP(&-;&^MaNd9;cjalhhU4M8;{x(i7X(xZH z&9$p-14&H_93^h*f4jXdZyjnhx{?T=_O(Ieg2B(F&7O8MU&?{+Z`1g|6H8acRj+7K{`wwc4l`WCe_mnLzdxv z9Qkp?e)H#>&q^_c1eNbVYlW1g9}wzfeS$k;Pcsx<{C!al?#Xj6?AL!=X6-?3oFUqS zIx|*B+Fg>Ce@DXiSEsA=i=6{hP_-_`2 zTo`RvBe|2_iYeiMOQO3K8%QS*sd&Gwy@dhdKeB)Uj0P zvM0re-w)jkOOY;SG?k3R5|SL%YlD>{CuaR-AUxF)lCsm-4Qo{c_v@rV?M+-(yq=Q9 z9)V{~G&#GYc8!x1K-sRnkd!rFZ`~Ejn*WELe_U2}%n)Z~trbwt*cCbGasHqkQI2{K zv9eZzQSKvs^Hnlxe-j3u}PIDy_nnLrVBI&$Oh>xKtOFDN|(5}YoVkXcY!0<2GfA7dmq*9pmGXS zy)m{Yt)VIRlHIb0FnE9AJc|8&vW#sbveqQ`0(U?U3~cc^9jFrR;j|xPg5>DK5r_q-9P9#vr^Xm)J6AaFfz!BQn$f7)z;XFND;1CyZKSeqhPcUVD@Bw1OLqLD0? zqf#Wh*P;kL;J6b}jeH}HMc{ta1t>?oW$lULdz;Hnak|@93@DcF3a!PdZ=0r3sCUiK z!ql^TW`r9lwK=Z}r1*fHrZH{p^zv!#E~?BekZm@>zT5J7?Bp1)MN!wkE!XsZe}5Zm zo3YxrzQ4^>Hxt^Ol}}|R|Bp&+iPw!X?q1?vju~I#^89UG% z9&QKbvKg?l{YOT7YlWUdp8eIopIBz6`nRl2(MSF8U2Of~W-#nnHt)bMb`$M&z4^He zM+aECg)=2Vx}(E3*uO0(V8Om(f8)<(wvgkP?%RZ0P1su${ejFDs$BvQ+rw{yrS+xS zpI!mbCArJpsT}<3sRs=qlAgp)>qEW_A*Hx3L`jAESbDm#)6$k7S5d+DzD0C6PQ)v1 zPE5|+wdJzf!)I4UWUwFVJviIg?=|@T*oHEbDkt9t>NHT_n?4`jT0LzJe|>yA^|Oie z;qBDtiP#4>R$t5hk8P%2&%{2qsd`(^e`GVEXI%}-FnWicfSUB1E7iYtJ;c2IX;nWP z!rP_LTJdzwV`>atd+n%usej+AlYKQpPm7MdRllFL#2%`TJ^2pKw!!MSTJ`JSdeOAy zJO;1rj=CUukA`*@Q?_vHf44JyGSl@C@_jaw?II21)7h}E9huK&xSgb8d^RKYwtMrr z42PcPsJ(-%cbW`wA7Nio89$tHdI&8(o>6v_O1En>Es{JM#m7UmVMUt0*Qle>rf!A8 z14uRWW6lB<6%J)8sxSDqu*o=8Q_YUjCtWtrIPX2>t?YHNN;hq~e~d=9x3b_~b?Lh; zcE%sSVVtZa1@o4Gd7As6VO1KeD@;{sFqWf;#7^XCsT!~3yP54p>Lohb4R^Rf5GGd| zi{QjgQsKg!+J+Il)sAa0{4}$tt$?TG(@d-|kI^WNp}>27&gi_5FTt&BEYKM^XII#* z?m#N5-&u6#`3&2ze{1>cTYe?2?Px??b8I3_0Q;@EWrkl3cx#0b^i*G%a8O2(AZfBHx3?& zDh0QlB5(P(21UZ&I4f#f9!OhO!H+e|^5_fbD2JLtf#2XO{%Cu8P zks(RUI5ako2ctO55{NX#c|ge6M0A)H7zvtT(?5nXj~b;} z?E79o!yE|foYaMGd$Yhc9QH?J*NQB|rY%a_7sOe$e+ky7Yxe(H&k-Y)=TR&U;an6N zN9_Y}9PBg45OgY1;ph2m0pbP!@gD%g!VdKZ>M&2eFbas_uq27YTQ4x~JTuANFxUi6QFHaEhTTjPxc zX{UX6f04G~mb)IPfvwhOMx!Mj5!Dez7dw^{;_;K|T1i573>P!0J45<)xX*2f$qsBx zdd+8_cipJSjKsVIJ{$gN2A_?bV@UsGUu?AA(@__B3n~ca&fa+;OxjbS(Sb1%;QS0} zEWqxiXte*~zvVOXA^kdf_T2wv_}2eh{+ojeRh#s$|JVOh6Lj!sx$L|uJRq-R8Pid8 zaI;RBJdo^md}bbsm?lO2FYSNO4<>K{p{|sb7)miJg6V(sPr9T@vN%Y#+#d{gh0AXX zPMvvd*(M1Nez21q$XtI1V#Z7IM;tP({f!zLH;xd%!R^ItzL-ATU+S~j;*a}>#m^rM z)QG4DdW<8227Gs~Fa8)$E^f#FtuHQaZy)rlpO^aLL7$DUeqP)z9`0s~$^FA!KWrxV z6TKg#9Vys=UEKeiFaG*@F_|y^n4ayP#N^i>)1zI{*ts2cYlDC3gFd~degM5Y)~6yA z@dwXFxGPMRqz^qd-{C_&I3X6$-R%^kRWh*$bXiKwYqrBke}c&Wpbrcz@t%&nj&33x zSm9!A&`Ay4G3TyD&#%Q`bgx#B1FFxXh0#J=;Alh;J#QB9{U9%&jR+}f?E>_yB?!953WZvn;3yh%!Tn7dN%8v zz4cVvqpOfy(|#bGe&GU=RvhaQk?OZt`O(59-fRD`|LPC&jdoiMvKhizhEw82L`s!nfm<P@2GUXPg1hW&&9$Nb_forW;hybXW@^UXCJYl$++KX&qthXqXw4a z;o#WTk|Z@4Q7l%Geqg+&J5abv9GFIA^Z@f@**4pPjeBUAgXDf~4={ABM!nz!w1Z;+ zW%o{iJ8~-Zz<7jTGi0KdMi^nqPHXm4;XZ$xPJ-wSR{WElguqzrS0rM|^EAfBM2JK7 z2nG@W+q~U`dPoQn{pIg~uJK8Lg_2YfVRw$u`jYLfu*f?`@Pd`hP(Zw*i6#cx2%|j{ z(LK1P<)ASqbm1Ai;E|^yo$Po3gFmZAgeIH##E1~3+s2YC3>pMc-x(&ys90bjvB`fD zO_h*coW<)xdFX~h-M1|~yZjR%%8m)avr9w=R_J>n8bIu_+mCqCk?pg#$Zv4jS#(^w zm<%G7ez7j14rt+~i6PatS4Q-l#$oWXgCq?ILw1lSWP%G`WuXzY;E;yxSbbx?TKJx4 z4=}pOBc;7LIlur2Ji}y*%EdFWeUuiim@iqu#YSZ11=iBA7ooxK8DoGv$CClgI}}h0 zjgX$p7Lzn0QfwNFw9L&Sd~=gf%_M(@0g@l1W61soL+GoIBh_$CG{K9c1|X{Rg>AhM zJc#`AAF%Y&2?4ldlz8jO_PhYcO`)v}Q^5a%B6f@;7)dUY zSjSmluJ#jv@VA9!mGmK)^pZqUiGzgrIHB$NxHxoBx#eVKXdEARUtq=VS1w%gi=xoN zG1ifm$&3+UghiHXlGnxNbOBs^v_RSrprT3Od$ti_xCSd+q($pcH(!%0%UE48J4l9? zx(L0e2xm9bMqRD;z+d|lr?*vi~%k- zd|m~XiL#~Upg0vO70bq~D5r-Z7^Mrlo}0~?YZ8Pw6DGy@za;QbBu5JmBTn)B18#a$j)-$2d;kH!#dw%6o#A?ES`&8h99H_$RiOFAJm84^BVNzTB;#ztqAej( z!PYt%lP(GXjzRJqQE0i=%JD1|#ukca3Q?93A-f)gAs210hDrAA7-OrsNa}@_o8|L@ zi;WFB&n}Rr!crzIwB*QGVw`q{@gs^+YDxtrsyI`uc+IS-G-OUNrzji(L`ohlITR8X&6E z0@ANa$kR+4Vp^n-I!D9gtf?S~X+1q9btf>}t$~4m*=$X)e|anmDw(qJaBs-lFII>r zdn6XeW3+&za~Z3gmEUl(EzUA7>e#Gm$&(c%lPCS37xK2LM$`j5;{18XLIA90ocUyV zMV21B4S|KR^c+8?ON_h{a`6xy$MRGR$zjD*)5mN?lJ|K)ii$*lD?KLj;4%{oVe>*D zxL0F;X<*>$Q81=|{^Y=G<~f7!m*0cqDdF6Bf*Ka|7bpuz@@$uhBH{{?(_pO-w|E^>X)t)vFNQ z2Yr-q+y!|?% z5KT!z96y@JF8v0vYqY{3sx`YBPK{{!oM6GLQxSi#q&?3kX8z&=L01UTaQRGu*cTcQ zJ*X4nseu4}K!U$Hg|aOG&1BC2ENR~=`qv^U_0Db*04@issDmbIpIAL;7-j9Z5UriS z1GTA+e-9Zqr&4KDXUC3vD^!4=pY*{-FvNhV2&L;5o80L?o1A@MWzB>L)lWx8 zTH9ne58iJSr&Y*BA1)gt?55u!p|reX`_Qu8-fp>mdPDINNcnsh&&}F z2?XqQ83INFpb}1d`b8zt4~lqQHl_kT4Q5^~hnnhIzx|1zMHK*1m23SPLxDsrDs3Fr zsHA7VEfiy?a#4r_I~Od!l6!G83j={xjb+g`tY~(v&akcji<0kL5q@xC8n^7{lk6rR zPDEpNBY?MWH`Jx)MwT0Uafq+h2CGK}|2r!_fU6oq=~=0n<*sbfk7_9vvVzyF$`{@M zE5swKf$S&xauN?th^Is*99f0g)$q99lm82oF4G}02RlD%dHRr@MqJjSci8+ky|si#_!g&R8y+U!r3-FyXBML0VNG_BfBsH(t!g`T@$ zRH3A1C6j4ih{$VHD$NXJhD?4|rj}i-f`=f{;*ouy^=R5%o{ZRzLMR(q?0r~v@Jd~M z>X881zpOJSmp_IIBsVGA2|mP`yL@DSv)-cZzAg#-nqs7c3m&cxhn-Ai*BB z2+EjYf>D|>ooTT=UV4TE@0-#|oH1UL;L!`S+T1|WL!T_;?AnZ(-P2jnRTrdxWx^=% z+?D;7%mpT(U>f#8h9a?V){h&Nr7ge%rc7>Qf(4Nsl7*As2nT8;CX;^5ihyOZNA3NE zZyS)_a&3h%+Z&+LxNU0!`OIaXJ4^C?DQl=px zCbS6vVt}eR>MiK#2vGWiZ!D?jpV1M*wzY$)XIslRrSaV=@!>Eq>0&x8wi5n2+x#NGRzh^y0_G{PIs#2#>vS%eHLpi;Xu~>(@kq zY-~1!E@LMT&~0x;R|Aj07C11i&{(Ykk`~n8l*xj`c%qgGpJ^aygq{m69C{nB0g$|0 z1TD1WSU9%l2i#)QP6BR!gIq3kw@**JtcSePvn>`Z@&WlLCaiV`37!^oXa?3293zZ8 zAE|@0O>7LALT!1(EjhUXYMI~`E(8nlKJFBs91dKvx5-&`66MLbP2Pe2*UyXF#q{C+ z`az$~lr7Q*@yGaKHeX!c-|36=%bEW0OTSXZicRA>F#KorRY+BT(!pj80<%u2iO){g ze51HV293}>E&xXWjKgc9lQKeV2Pt{edc}UT*rHJO=UyO=d{vGsn#F(ArGW%oZE}|p zJ3ddR3`=##vJD_Tx&hhYZWEsts-j^L9t1m{%#T<7XSytJtFH=#lQ)IxR%e@h&o`*> zMHppUzrbdyQ&$mx&-%>V2&hH!idxF9xl`sraTtKf9A*QfTRfl}?FI>B-}izjT$J`R zrB!)z4aZt08CdF#+YokOra#J@z2mJ}3ma>a+ivp6i0$m*4Kp4J%4UDj#4Hv91WYP$zIE&@8 zXDwku*ESFkm)Itl&7^7Ek@nPd$qkM|8{B+bga%!^0gbgbm}FqH{T}wJR>;=%izMq7 z4G(p2A21)4_O3K{7)uRSih%@{7c8RZfP~MUZDK*O%mS8DP-GLlzg8C!&yIl0P6kVj ze7U4FPG0GMPfcPz#4f9IG9|&&jq9l&?`@TPP+H$*`NlwtRc_d#jNl7RGXkj}GY=wga(J1dB&juN};=*Re(My6f`-hyz)pw+g0x%yF7EcOXRnOMMTw zQ|`ih{8v^<0$My>dMY1Nvq_4b07Uda` zI0P9ZHJId0i6Z&xDKLuigRnqm9+<<5&6i<`8$q&Bu>p(P5@b!>D9ho)MVoxIiEtQh(~2 z2JJt8-qRB+yR>jD>Z@2Jo}~f;<5})Y+6sXAD^&;Kf(#smSV!ll|J4dY})tp?9#q*!^j9C6lBESlWYmnMKy9)$zTFf zyvv8#Lrg26!FG1@1zdXC+5zhbC56)Y3CDVW$dK^Smpiy^*q< zg%Q5FOLb|{CO}W3#1KIw99MSq7=j6c;YGj94!(IZY!0_b3ZLVM#+j}vqarbvmz35e z%yuq?WM&%`jnPH8$Mf_VHc*-OJtZhz4gN9i6|KteALmIMP4^4zHl1LOpM zrAv5n@W8g7z!quSkk%xyo~&g$A+r}*`v6T>hWJo$i@7cc$fNl#j3S@PXLmE%_(|S{ z3!$>8?&ec4AJdR^@I${IPZsk($CI1!3h3M>I%p)07V4 zXPROG$3;^(J7{#tYsA8C!ngw-IP#-^rMF`1io)Zw7Xe?1xu7_afeR6N{tFHQ;6ZAO za6k{)lwQ6AU2knb6n1Ml@~M+`E!#$F=kywL+SbN$N&Lv5Qj#aMqh~8g#|8l=W*i!D z4!=bltXFIUfN_j%lAYv-kSRFrFn}(&O+NFBnJO%zz*7Wtczfz+c7+Vc%ikM+p)eh< z5SMJ!KN>b0=>aU$X1y9f*?_&*w=O-$nUOH86>L`$1hS~Di8LO)AOe(^Cb&Beph$?l zkh;kD(Xk?MfeY15q{%g1B7;q1Ez&?|u{QZ2zNAgC6)s)~@fU^-lBn7N;m40Q70L>k zBBHRU$g@onMpz)sQ94;cQs9k$msU79-`OS}az6emrrKZFD^Foy6*3O~n4T%>TamT+ zaeIGxvzT38-0Cw>!BhQVarx)PWTM|DUl-d4APD2h9L^4R zxgT5}NNDn}AMSrn;iR8|cC0h_Zg57`pZ$en+NSK(|LK$2{lj8<`}2A{!AE1>785L2 zr%x;}1m!@tBn4!RRF+36Ic$^6hST(bye{q7Os-wU>V>Aul0m}nvcMI4MFXN%X<6vA z5ib5O2|OBSTW$m>n8wzBsZAG|iL*y||6zYqemDrgGDT)XBAl*E(vT8JlVry~6Rp03 zU6$+zIpuI^*pSVNVh9WqgpTJ$eCkquB+tt>9tqbHHUUL~-U*Xs}It$IBOyg>S<*K|@p=qIISfZQTsyxX*Cjv5m7f|(zs=~qQhs?68 zw941Bs)9iJX-%YInn@-RyY>N6d88@dVly8VpKjE^^t3vP&tCjZE18XyUVwQPpG4b zfV}nglNDQhjusDydZ+v1zwUa711mA#ntaKfJ9kLJMj62xMt~KGz+L4uB zBf=mbkSGpZ*muO*A@WC;Fx+Ye0bM4!9R;w&ZVezW9}g(;#qv=XETM1E*=F%bqThtw z3&ez?b2Gd|thGc$9G`W@H~@B#jPnb;NFPBY3j(26H>qGcU1Er3^F)Nu7lPPbCO0Tb z`!T>6Z2z%;w0>0;p1)6^eBe`)bg;}`Kv;zNFBX1Lm|8XAr2&>rYs;*jG$K^B@FZN$ ze;o%fe`oFmthS@$Tef=QYg1TWCgmx%?W9~5ggLrlEZ2IALifmlcXm@&my7oZ}I!xWWln z{0`=XN1`9FfG(LEZ4aJsny^)}28_Q=9{{G!MtNu1V4$?wrLaYr`{K71J#Q)_Wj}0| zE`@R{sZ(60%QLLrw0R(D>*4`Qr?&T)S~LTP>%QCy4z;acLV^9JhV$9;mHANOb_l0` zUE+fXV5wdRIbbV>#fOK?H41)s>^{LAW8F<2dGyj#xUKaoByv*Luu0C(R2lC`|(Bnb} zE$DF<3_XE13>motWsvKOcgP>mY~O*hyE!~Wr)?OF=P&8c2Va93AC-GZ=AN9x(DcWx zs@IQ0p|2hneB?6O;~=($90i+y1X}Vhmt|2tEZ567_1vb6d+@pr{y+uDQ=#i0PaCr% z((cs(tn;bBw<7LE>$7pzSth%W#6K4Ku(kt*y{%7x{)K|?$P3oI?#{9-xqWr@|`tF9|?X))_wR_PaN%A0rw!?S+(wQn1@8&gMKut z^l`|$V(vk`E6wq7zy~Bf1bc6j{TonMGVa4Wu%-VxC{pD$sShi=HP{mtLg|v3|28G7+Qr0_a8PDL>3vZ6@J;v_7C*dwx4%a?n9zm> za~tPS^`il#H<;x6lAC$315nM!V-xIpR<6TrSpZ_*5@~Qxxx^UM7;VZNel1^}{cZ52 zydiV=71jxFvA}kJ1-DyYdq}y|aC5$xT%X@yg&oQQ9u}|Ra^AxlevMsyMEKHV2J8rK zI0JT(+KtHTIQwnb^?fUG@YPMC8;tCZ*kIqqoyAknJNe#+(O;T?C&|Gde%(%)y-mX`K_!QMBiLqcZmb_ z>tJHL!^sAVb60M&b-4#L^n~08Xtw6}pc>7kHbRfeWcby zKB$4+5IMN@`{DhEVOQ2#V8cG%!MH3JR}Ewjy%qU6l?aUb_?sLHY@9=6D_TuPPVpxej3y>tp&F5OG9hgOwm7=tN&^< z|48!C-LRH9d{>l z-u&|N#fKl?wUXb^Zf&5P(VxZ8vB(~RY>Tj%e5@@Irt?YHjEUGOO))rtYy>bkNg&xR ztn`k5+~uWbeHthU8lkTW5PfZF8RX;2O`YJ*Y<0 ztEu_eLug|@28}FkB@P}}ygd(}!=KAe%cE+B|&TEK)ca+`Cpz<=x4=%0AN2Q|{dfJ;^>+qlxyey`_KG%ySq@WmTq^kepoKDDYIo4ZNdy4Aoaq3 zZwKIF*v{Dy+-^DSA+;NepPQKHpHE<(e;(L8|J=$vzyCOu4f=RTY_r+8i_>l{?jjA& zMF?QfIkOhnV$!skGtJlKE=Id)d9qpAdQuKOCmT)4Sy{}&^s?k(S;wy2=V?}`Fz2cm z^Kyf5-mD?iQz z4(Vfd6Dc4eJ@V#WtcpJ0R_i{w7Y_w$KwY&4f4FC)tG={IF~nU{=n5OPIHl z-|7_Lm-4!=lnu7qZ3_<ub4D!%Ms#)FU1g-ar2gGMCC6-Ie#PkL$IcYK=x)F#kjlg-Q9}{S&S8 z#*l*&pTiK1jQn9RigUJCd1Jtv%eJF-4NuiymtGaheYXrs2Qia}#Xo=j%Zu+nOg{Yl zr#FB8b@JxFKD_zm&oAB%YQc^Gzj^V)+czfx`mgtIe|+`hhskDBPXYXY_UE7f^x}_i zUc8>Xe)H<**FXOGhf|=wd-M9QzrHvH(w~3$<;A;`0R8;ulgyOA{`%&Z$@^b^{@ahQ z-@HBrVCQtg?Cj2->M>v!+=@Gloj!)e+4(AOe_mGu)7D z2|S{~`Sf}Pe|Jgnr|5A|@)3ou&OUEUl7n@DpQ6g9z&kZqcFOU8I=@fW;sNvH>f$0? z=Gj`Aqa|mbq|C0=!^-41`)xHYhpM?gL4^%*cVPFOaI`k-6Y(F=0n18=lh1sm%U!iG zpQ6tJx%cTLc62&YdU61*wk03YYr1l@TlE~Df(|){u?kg>TcRB=>-PlcJ)uYRxJ;8= z(s~>Y)tY-!_iqS)e24~ztKB`NA1)uM!LexO2|DbEJgi0SN=B`W)!_#vL|bC|Fk@y%5YO+Q{G|t?wpwlH z+c%XMwBvuer{^!r)o-`hM=Jz9O^IExkI-h&&bSqLScCKPaBBe%RxWq~{-(UU;QQtu zziRnZ749F1Jw1jSgbi_ru`lRa)DrvneYGcOuqX709^KuV)m%7yiRvj@Yzn+ngJoA7 zzpeCSEjFcp9#Lg;M!ah>HQzmOZeCmTGE++|>E`?x}PAak@l3cE{~0CTv^e12h=We6EBYMU}U(vO&w`gPOjn#Gs9r zceQ?yC#ZB>`Y{!ApQXIk?v8}$C+W2>_wgF-=1~u%&{FJATP~AunJ4A9>#JFJQKa5ncA1w?>+|J*#oPzY!R2S~o_?zjEsx88D3@i{De!BV z&mZ_A`xekqgg2K7tiE$pzua72J}klO8$~}~5>L9w{2;^gtvFpKT)BkdC{1zB`f+Is zvdl>CGsp%++MHB{PFAxw;F3QEaeGj-y^8~ohlTT%K+0*)#NV6-f(sfp8 zYqXmjCTEDJKdx_^Hyt&Cn=fW1Tujbx9-689t!TN#o3oR&t4HcTJfDCb(`C~3plR8( zhCN6Sy}>;N(5#%@oQK&dp!!+Z80qtWG_{`wk0^QZ%@{Wq*OPvd_lADnwBt&cog=nf zTwPDnY>EJS8rtG@91qlJeqGX{zqHk`H|z8qZJP84R+ICqv+1I3f7a<`IH#zkpZl}c zV0jYDe6ecaby$3Cj5q^YS2v^a$ep1n7`YYsxE;Fom}l!>oCvmDTo9d`VGvV)ncVJF zHN{*^E_+tj&78&6r*heLX>^b`7n6@A&=cZsE!(~24Ut&1ti*nrySgjTW;2wC(yk3?+QJnvYrNbEr}Gh~09uaNDcW^^9nRp1R_^vB zVDrWDAfqMH^@Q#Z-ds*Qm)k|RldGG>DVD$v_GS5U3Ln2Zyy+u9toC$%(|N>hHMWMP zl9#RN)1xb%ek;(dTwHx#7E*w(JwEWrWj~2R{xiOsQ-U8WA+Gqo`cG_*kA3fh{3U}~ms}bTc=h+DE zh|g?=b~E`>re_})9TQ5WuVUT??D+XoJG^5@ON|gWqnJhz+rdj4kiFxUHZbSm^6UnV zZ4z?0Ui4OEY1LbQ0n$Sm)To9AV}}zq1X+X`k&ix?yJ3rt@Xl6XzfD>tq3+?(j>?y5 z?z2tW;p`qw z-2;*~NISxN|Wyz2vKZ8NSLUjW?{-|C2T6JsL_v61}K z1t4Sv!$u|X?ZxfiPPwS?l43* zIQ>Q47D%tIuba3^$ZhK_381aRB!rWCv<<+MIkgV6sb3?66Sy{l`4@Sg74(T55WzL~ zK`W59ZirA$>4^xhz4hKkX=1?F<^9@(Jcqx&#dbRZ6E34bKMbFdq^`wY$A|#50 zuP)EOo&c_e$vpzJnDhfzOLvoFeiBIPJuK;5eme===jr?=oS&|V)640qTg&CpceU?; zoLif3b=Me2~^r<<*b$bM=)D^yeo&e`!=*uz(QOF1_hA$ztgVh%?Xcp6SSuSLFX^Fz`NwcQ=uXf^m6$eC zSG8vbA6K$9!*|CrAb+({zk8six+8hmdITT3AO3h*uUg1#aese9`tW!5Hih4RT$CZV zr8h)(v#*)rbA%}6|CBbWf1Z{v14>?29Np%b4|rYbVbT%V5L24;H#}$kF76#qH;o?% z_`oNjj%an8lK6m!s-C3MQStX{)=H&s(dB5RmnUhmEA`QOY#ZVsb?GGEug}3+GEdTD zQ{w&j4?nSZl2Z4=+^^}e(}yR2>9r&D0a_g82v5^vSM1|88E`5e6n#Xab)}ArWr?V} z9#?{R8RHtL*zMiDdj?g2zZ27I>J=Oz!)uslMbbWpF#=}sGkkDhg+&;y<-7$CP z@IFnmgR+k(I9~=B!`}yOAbppnJS9RPA7=2g?eAE3M5MRJGM~G(5&ghy$xa^_+_v4{R(0Cpv(cek_hYk51^8Y5}?r^p1^rg-IZu2kSpuwKN@#bGffA4r$?Ne=X(H_!mBzUQYU@ z_{)d!+qds}6<6}dTk-+?dIh}s9n$D#PU!++)S1o^?LLhbAIs?D&Dk0KqJ~6&iQ77^ zmQR;}-XnK%#$nva8Iznb}U6hNf+1KTN5cQuQcb~`i|Gx44XX5#Yy7F`X!u3N%-hQQ*3MntPrI6s;fkjI) zhG~vr8qIj$uk$8DjP6|_jc0tkL=qc=P0FkUj(%AwL;9|Uot|qs-yZFLCOmY!I|19n z+zSx51O2uG*&5$&?4QZ!qj)nt&sev4L_3CC)0Q@h!;~C<>u|l-!NGduG2pgV$@mry zYQ5Z2Yg5jxTBQE;yQ`(r^M_2P>G*2A`Z&J*<99!=z71h~wA$Vz+|?U(tA_^5Z}g(h z=+oy>UkAAV-a|l_QoB|!rH+?U$Gz0?+U6~#k}|*CugstRwxtZ(AihPxeRQ!WT0KX{ zUtCYmdxfTdm-9t9KW}A6mrz}oEupqeD%5$kq0Wy>b+)Xlem=UoCMyxn|1etIT$a(< z_01^twP1$Rb%ik|h%q3>O9b=>k|K&fz1kw&{gX0^8J_gY&bjBOCN7a z2k7g4&}aYO4AW~y)ql<|`_taVRX63jthv>;Ux0CcqqMN;tTR>J#mOnr(8F%Ld(C$| zD_;#v4Ef^?be3^ZN}we_8AK{agAv(dB0pDAC2^ z@5*l_-7J=CBVQ%bd+(Q>!lO6KzukU$Wg`xKcay!Z*6*`_US?qrNR8KVPopZx=BOumMT^XJ!J z9}R-#w5?InVxqc1a~=`}BPN@zIjW*sleQ=O0JA5}*A83mC-z%hl`? zB}_jaqWk{1|2`q?$OFJlyqGS&Np$zkPUuR1#*e=SfgJzP*y?IQi0=E`|2~4 zo|Z407+at2WpCNpkkSn-)7L}BtE)UW{Xac_n_iATY?>(a%JQq5GH&t|F-*nsoR#x` z@LK^5=pM794mkv|DCr}WkvgOB;!Lb9;{=xR-G}#+AJOzKis;J?&?{?Q#_2xR8{7Uof^6an=qY1Jl ze*^DfaB|frgt6I!A3n~mZq7bZ@*q0z&wu;z^^Y$mFV7+WOF2KEz*Eonby%u!8+~lT zAKTLDD-86)`pRSDL%;vsMp*MKDXj96yNm`OBYbjuWn|DuV6@T zep{*Eiy1G)yx11IhS_#5ooASTrY#O}_a}Qsv9)r>zb=LR&o{q;9Zow-aQ?q;ArG;f zy5jmr6d)t5qnB1Y?_h7Goe*b&W_YZ4U zcZ}yAmUe&(Lqq%!zGL;pcb#o`cGo`GLE*>t%P55FPBTXD*1z~exAQpv&wdwl-gnh< zuW(=BtlZ4Y-I(1+)^L5q*!}EQ99673D1?5orphDgaS=zqAHBW$<;8M;WIZpx8-Zf4 z!t+hhUl7NnDebh6uhSHN0psdTg(HYZKi@0z_Ug;{{rVFx&d-18etC;{bq$W(+krfW zZnU92?w|FTAB4Q?3q9ulb9psdOc&?n|9y5R?K>#`C_g+x|5o4YH|oH4W+hx46TbVQ z^X-AIi|c*~o}XQRVa9*FIKp`E8zZvf zD-jSjjniWR=$^%(ufCnWoIVSemsf}uyCt!=Z**P|AdfGv7G>$Qr&){9i_Nb*gOfjk zx@A}ikSr=boj!(3y7Tz}FhyS)z3RWveR;iYb9h^D=M)7$8sC0{Wc{-G+p|r_f0v)! z_}KP$5FmV^T%$vO9-gk;?F0}TUmdT$x+#40bN|CC^SqbjL6s{zxxwOU+m7U+&1gLLa27ONu7u$3<^`YUvTXmc1^O zDu8s0ZSxB~y;^P2(*|{!9hH9Q!v~tsBd)gj-*z8+c5tA7jv{T1pZ)-8Woe{V^R=MNCD{_A-CrM1Krd7f{GrjWJ^R9nTQYkerlCZrcz z*bua#&GOBEtb3K=llM3Cj}&6O1wE##t1n@&bC@AYKNJMg#_9Vq1KECD-7kQ*{9`<(a4aHZuVH$Qf6W*F05_#1fFtKBX*%9WXNbK%;_~oDDtm(WqUA43Ex&&cEmxt;9c>yjE!?VM?!@gP>{a93L)x~X?f389Zu_Q}SRdUA99;bk z(Jyzfo{={?o6(YQ=4yV|`L`Yfc=Kr*O}D;(*9^G>8}ER<>@?W^ey`U22-~3AYT)ye z)eml)MPGVG_u9tG*SjAP1-+!N{n~vEA}~eDXnh#7w;O$ZYjVG%KaV#*x@>GGW9t{d z=;XfK_}L2U>(veL&Zd`t*glC^#xr-rFaJF5i%pHsC^7B3O=QHuHQbyp#v7mBQWNlh z;|_j1|6ql_RQ&&kk}rEDx7Z{88BI^u@*6LOzued4U9ZVoXtMOoqc`1$x7A+u^QJ}(hwkoAZ8zifQnL-V zu&sJ$3IDNTO7xq5oJRG|Xm8?fE8gjUwfXA>GXfW?cOg8Zi1J<_eTOD~nNo-^Cll z4K+8uzjr#&<9;8`)72$+?B)26#31$*+xb8b+y8J(KP8wjqW$FaGU`Oo&SW=bfBf?Y zMZ~t>2RF~{ZzE#YWj1(et^>rF%a?su9T=Ja`pb*)Ms&UfeEYi|m=5kX zK7T#CqB3!mEvbGRU68-M?ePuvO3>&fn&Wf2RJwAE@g`$NJ-c(g?JISE*TSUz@{&h4 z*Q4%YcDHrfHT>6~KfKspTEq`8r~kYuot68r)hEp(-2GOaCa4}Q#jY8_t=K<|Zsl$* z==a-ey_eg^0VMa?Aawh_4*53zzLmC1+XUNR>g>hlm!1usd~jd0o}AclXway!x8L6! zv(@*zf&0VgMfa7_YuZGAp$PLe?8!OR12{aWYO>rcnDmFjlZ`{+`#sOM%UZ7NJeT`g`Nbp-bmmu0E&|-$G<}+s0Czd*NY;Hi-udM%7O-?v{l`b|mLDH~{eJX@z96^9qKlkn z&mvgP0)JW1A^H6A+?KvRUVr`Nmb7PmKK1HK;Z6*FFs<`{Y<*??aha0+ZYAPbpHP4I z)@)fh<h; zw?7?|yxRzR6-{=3sIPWVSL3=4BYWMt3%WOtJ#ASkvi0R9?B>swAjeZ3AD-pY|8h%G z54gRqdc1YY{PL4nI3PWvt^)720=ax1gNUT_tDC%3p!-yp6y1I6<4xSs;A7d|vgkk6 ze`~1{;cqRY*FFA^^qB|gNH*{0y1&12HCiijhwjV2V3}NhU*!iY+$Hz-KwB+-NJBa$ z|GHMP{}tU?Ix>#mI`Y5kmFc$B>7LZD-6t^7a>r=i(kBmKE~eKAMmv`{K5~oZF*=No zK&;XS287t3fZsf4fA{bi*>64F?x=n1zSmOLIBX=FZyKf^XT2A&Wsa7)lIu;l@l!Y9 zZk4%X^X(RY`F7K7yu0ak`=JL~mPeYlUdwwdORvB~29oykLq|ROR?bJCr(u-N8*c2b zTLF{OV=sGnJ_h!fuwQQK_iL};n+^S5z5VfE8)*7IWC{$dKAFzFNph<>X|+2&It$eg z@hB}V)RU~=TCdIDlVmahz2t|Q$Cb`~lJqD}FLTF#$0&H9pQqpdezcj7`4nxb>z2vb zE1d4&jDDWhS)VUA)q3Bn^>SA&%KBVoe3FXmoLV|4Sdx?nC4!~#>hDC<#;dQA{LSQB z{H6QF5{#DQgAS=49Tas6t;E0D1nZ#Bt`~=g<7k2`1a9Wk?xxEg9p5AOG&Ao+tTI0P z^Ud>r@U^?WG7FdUZUsH;1n*H-4*Im#9%;OT)MwMa?X~!@^}Aj}BKlbVDRkq0B%0Wn z7`xv?NYVZ5)s`&CzYb}-_&S>7ca$hR8(m+WPj`=OA7qto=B3`8uf~dQ*qzN++Vm*n zHOhF2@@j?u>l*)k_Zw(7UkrQ`;uSA&| zjjo*LgO5m;UmUN#_-ZNWRsZ*AX*#-|USoM(midD-LGXjyFTMKlR>HHcF2f8d^H*A&y?!eU!d%=`hM<8Yd>fb6My_h`4b+0 zL^dKB`fD;($Z(^PN0G;T-c(EsL93{n2}0mEhMWdC&u#$R0tuaU|o=2 z2E(~9s>UKrvXZCbgFS%?NpPoa&P;J9gOb9t>Z@^_>!@=Yav(ZW+L_Q)=#h?Pv98tt zXe1XwDHoV5#xO6q_elvS(Zh<#Eb}RUbdb_GuahvCc9m;qolI7x8Y3%4#*^rvB3A)Z zn+xZ?$(VZhtE`@J#V`f!DReLl^WDngOf^;3T2zue)L@McHmUgUphJ+63snW@Mmb}h zl`>)K1RkZ~m6`N!p`?z|Cl|Gr$q8O;$~j?Bjfy&EQOduClCZE^vyw2)wTU%<2wk({ z684_+;>5qjlneN+)eI((NiA*S%&BN3Y+$Y4Mtho`Ow|_4ROYI(=qzJCa3772C6tiO zDRjs&_);~CL9vY4?;OjqL?(HOmYt>_at?uKlMBm5R;_Z?Qd@2X79{-9NhVBj=m}M| zwJg`*H0%M4CD*Xi+=g@#TU}v)kTc7=Vl}HMUG`blz!a8HR@&4db?6!H`;TE>mL=C( z3P1zJ ztcJfW!3ZuH%iMF3d2{@KK+|6&XG%tsg+kP&tK%Yqg|iY{<2wdZmkQI`*Brco>4hm^ zG9c`e+BdgWWi78pq!xEiC z_+Gi>5fBQUv+~)psHDa4CvGDmvgZEJn~E8)Y!xvZTU9DB$uU}gUY)49Ht+ucbK_N{ zhJ$%$gD@+=9$0RI7n(Pp{~_Dzof8=K!WmEKbr3v}1yjX2-Q54gC=h%o^fsakX*pJc zbnpV;nK@R~eEp>;jQ5Cxl1))ck-V~rAspk{M=ni!d>H(YD;R(`pnb)7G#*|+!W($q zzWt?(=+IvWmVP>PNV~`@aIOzWJ zF%95LnR23JtZ&5}{JkpNm6{oNe@g8&K!a`NO7dia1KCP{w3iT57ShAw%cBVs2tZZ2ratds8wnmWp)nC z8>HKxKm)9QL61grgOyOYhu3Ek48#~H1wPbXgJPYp3C71D*ssi~ti7#C6{1~I4Ha9;A5xCquKt#vbCbZccQ z@ZuEsVWkKeL24{n7>zmHuEo9@bSZ86mShkQ!;2JN6wIfih3uLEQ|y&ttzfIbj*SQ+ zfk@P3RkleCdO)@V%ymw5D1udlUREA`EkVYWNdhdf-K-AIVR8vDK=8icM7DGik4OL^ znhdRf%o17T5|kEIC&74u9Yz=gcOblB+{o(Mjd8{zlF}f~kfDeG@*fne7nA64CsJ(& zTqI)LD68i}Czvsw7`$(;0jyst*$^0!uIl1UQ8eN#sUo;X6`1EP%c7bA*TBKMT+I%# z7XHVw(#|=AS(sv;wQ~~W6BKbTTE7uYPuHS2 zWlAoNac#Mmu5zqj!*p(n&3zJ>HMB-Sp_$b-YcN_HgO7o^me^dz=q(cpZa+!^lA%rH zh8e3wu_d*{Rw_yf%PbA$Oc>Y-xPQ*c9otfkZi%f~0mrJqwbtuYO;9nzBL|fd1AlIR ziEXT?tT-4Z+M|GR&RD+H(pU>^m1&DzKss196*CSjJ!VAHB0CebikJ*7vB55ahBt)o zx57pjB6{1woFH^hQkSOK0->5z9Fbb8p%$)%<}y`yD3;`~n=-rDj+=^bBnOFQ#^9O+ zh^17eFoF4In__#RM5viE&p@oD;F=eI;S*LlVhi*@OKgm;4_tAF;RVeipI9nTLGfW` zc++_vVARO8M3{9@AuM+VVp2<_nUBTS5*zEP@G69Lib#Q}IcKG8%0*y+GBe{_Vpo$T#y6;%q6va?gyGJ12Vq7Q-_)MhOy_IhoCXYkKP2b0 zVu;^7%S9D1;Re{0>)A+bM+(3M5Q<7KlaWpqDMWEz$SAyXoHax?pdMUFFG4E5WEBuL z30M+eJyX&&M6Nt4&rCv8oP*8aK1O2>XRnoEF}6eI+{P@mcV0;)lFTs6m_~@kxk#=w z>}>>sE*XoKuMc78^P>;qfcv5FKJf zR(%Rd&~af*7L*8V48$xooMD(>%EBpObs4WR{;OP-oWVv_nYnL>OnVI$hKWTJtu{uh z5Hbb<@nbATwM4Ep1A&f(g+XkZ-~CqhWeX>N2`+7u;Z8AhxK>gtOPj0>kp<6S&=wpw(A}08!SIcC4Ezqp zrL;sYxnMFU#8GsoA&@~s&kMK`UAb+DEDicvY3HL=+&Grt8@V*RfZ+$$(1uB+D0(S~ zl53L8X<>xMLWUhxv~k@K8OGVu@e8~&yhL$yg9t9eX9VoUH1v{xGDtY+XuM<<6RaY7 zw5$pp5jr#7l6%TrO|jV(jI^a^!V;oLgvpljd7wo*WX!5UZPOyVjG3javI6l7(}*o9 zZ@8Y}CTv1%%49YX?vYZrS=6;!m5r*oA#zHwO6RrHo>CcL#<0>n3!(%t!-l>}Wvp9Q zt@H>LITT2VIsz1b5KGL)hIU&sT?{NWwa*laIkb-1+rm9d(%F{Ck<041_n|0JW46wD zIs;6R_8uFqDsZplOqDUfa%v;sC@TvXbVg@WEm^OYh%I9AmhR`3LevOTnt?7@7K&-e z0BPIBs_1=!6^kKYqQja%2hEJKjyFWc%%=T4n3AfJ7qP~F#0+SOvN<{4a&9L?b0J8t zrO1-2$i1x+R9~XeDYTs1HEA?dW{o%pK?cVxGfdJAi0Vzt09HV$zkL$SW;!%4Sry9g zWS%507O(i=x%7)g{xTrMw!vHY4-DW(9pF+Dc zd}PZ#1CtS=bFh0vf31d*B9XFGO!i!bT5L;XUty+cH^x}n&7>2$R27%mm*^X^Aqxsv zrACmE!NaVJiO4@JX>itL-Ef?(E((#HOBNx#F%0v}DmZ5i>YtQv$a*cDat$z6AoyVU zfpQ%gA`D`qh-e$KA&cNuT5m1g<4VlKqQEaJ1%u{1EO$fXf9y2fkti-Hgja^caGMG* z#bwH-WkhF-f?q~JsjI^5jsOMm51ASbwHo>=r$9fzb0flZ+MzI5+lVSzb%t{H8_sQF zd7?|*wWd%$P^6%aDpXhrE6&>@YfNRGjO3P~lQSqjVk|_lGUtYt#3dg+=UjN3GhNO= zn2|Es(7}I;*Yorwok(I2$cqcsF_p=<~jguya5QG%PHnd^h7mI(u z0)>SY(F$?9(@`75Tf_nzB7&It{*XCrX9Pci6^S)PSQ%GaA{TgPr)tqLvH)*E8D}BEnuUZAuOV_O0W8G1 zY-n7ge=jW5NMWVWnD!0#00V4SRsoTt<)#{tP`Hj1=xR4(xh2!5gEGTh?XHZ`EgP*( zm!DlhgsW>9(Sa9m<_$cAEFxQrAr9GRVkDV+(X!3jGEmJxdyw#3z@pp@;VFwiv)XV~ zA%MaE^TO!zOsNPUOMs8Y%Ysr)sspYBy!S=BhLHE-Y&razC&R@JYwv><>`YNzpxJ0gbv>}_yh~OvC z-k7|1V1f;igUc3k2_c3Gh_W1AkR@VNMWSn|Es?#<1(poHSt%^(1oK&nbuv_rxThg9 ze~3s`*@EnP77$lv!E@mla$oSXhI2cWY7*>o4N?eQHF&?Inherb%{*^tJ#)}bv1*BD zCrL*co{MM_yq04oHf%HE3MxS*5iwU7FYb)PG*8h5RT8TWcbN-q_+c4mkUz(j<&hER zELCGYLyv~Y92QJSr6YsI#td_aI+&^zeWJGVyTLEHJJ!5EprowljhL*@)GZTDCkwv=mfKUTY8|&P_rl*E&uEGYx41#wj zGp`|rh>%Vp&?6?A8@8DajG~E%D$qy_G!gHv#tNknfgmO z8^Mw^7{!c$wO|G7l4KY*z48#gP?6JVXL8I@VXPvBk-{4-b%v+V&G9uxFd$lYN>POj ztXrQHr8~l11)E#rOQ)pbUZBs?zpbKUH#@6^A z{azxSsAy@V$6q8ElPO79IM87eJr3bVhG-}8R6~}SiH6P=tnzeSGFdH~H{++$oyo&@ z)5RNvxruJ>SDRx*$Y*S8{KBP_g^r1>5Sb@ajkB`LdloVdx@oq431E1UgZqkYmp&E& zF9O@gmv0sU76Cq&h86*B0Rflv76C$kypPRwEmGxb5UNM4twJSXi;wWfX4o3c``8A4 zo^{1JU2q6&g2Om-*qB%`{X7pS9CYq>58?qSqY8N#{V^)=ZXpGYX!M=41p_xT5hs`CH`ZR zz_f3QO~p=Y3MEP&bIG|D3;POsZ&g-<9s?i1cEs-k0=z2097IwYoo_(6!Lf7G@m4VB zT&AL9azenWSjD3?)?ywQJ7_JeeQZkkWLkJcG?-@D6d6*c0ul^Ut~TW@2p>QbgtAFi zp3wIi#+~6$*-2M(Q$MD_T5Mu}Fx_-TlPbWm4AY`uQeE*pw#D{J7`i$MTT0hN;ZZ@O zSP~IrwYHsWDT*3du$rp91#eTK5;PQB$EXH9EZoPgE@>DQPaGoHT$Oi`d!r0UD(qZa z?1Hr{wL~c3oKCVtMaM`kn_!D;YFo6{2ou3crGW2{ffYnZUKLgloPffAHpTYUz>8W7 zE-tx`nDppvsYQ;;vfPxfX?jT}2ap#pgZGFFsGd7d_+v3OH}&6$1(Ky~IrwaFmr|qF zR8`qw@Ld*7=bB-H_A5PN5S_iKQbz3=f)Zanf`+!(uq+uKQ&H?23v)FT$#PC0Z3w@c zatC8%);fB)uObU9jI2%*P^d(kR6;bJYnV}mZcj3L1xII>Lm2@+0)SPwgBbyp0RoT9 zw;CG(GXa03M@mJ=4wNFfSen}NgjEJwUO`OZSKv5vXW>{vzZWfy$CFsShnd$O@*KMM6YIh1-nw@TWx~Iw-km3|w+$ z;0#4rC8!cIRX}1&1j%4@YH7N6Uj?iRg8ZtOD>inO5F=xO?!c!YLtAX81p+@t4~u6f zw8%PD6@p{Hj!oBC)u1fQ(*vg!@qkSUygYwVLNlzZ^ljU1GJF=I6YwKV=M<7zohI&O%h70vs4^o`z5nm}rOp8r23>T8$VJ(RP0U zSRi$(g!$b)Y=GW#ziEkNn+L%V`7122vMC+^9l#(F=J?nqM7`^T8 zL~68h;8LqgFh|@VFaK`E^8=pHd+Xf%f-%u;3rgjr^gNN`45={?1q!*PfvW&1tKR!D^zP> z_UZN<77t<&D+RN{Nq7NPV>GQ$eG!p1&|sZ36OoEWO9{3J!X{axl~aE`h*`-6u^rXC zvYF~0WSA&}ITrG;91*|HCI51BxtLy*_hnZ9ba@pU-2J-)r@Inoz?NLK)l)qSWf5l@ z?&xv(Ob1aXR7GNNz0*WrnW0*dQYlpx;!wKCr2Pq1Q4EU>0WUZ@n1@1i=5>w12^Ki# zDW6ak;}CLd>!OW<%0WE9#?pmB#k8X`*X4w&c%>qzQlf&cwg(Us(0pZ?%9K|*aO&ti zs+gp*qz7L@(lXNXU`8Y=5Xk-DnF)87{~!Stf2UL>#Ka?)&Vd31#9~lOO3GHLa2zF^ zP?dNsF_NP=uWF;kx ztj3&$6utfc@xsJ*u zLuaQ!h!d$np^=wZ6tQNhj5n2oid0^t0}m1TL~0lXPcN!PFUSCT?_fA7)6O{Sq%878 zYFO_b1&Wdin^i%yt_Fv46@az?;qB1R+ye=0RRxH+SHB-V=J zr3&a8m`BS?P}SH|sgYq1U9hY&U%5`*t3J{PYpjeIrUBLX;bsb3-R!0ILzkf<0T~&N zXdqfWz-teiuXjY3Ga~^mf8RhwA~Z5tO?-wvN|&q|rWGAh zWjW|wv?D6|Y-$obfLK$}1h`S3DJN3FgoERpU_A$Bd`?kQ&FfeUs6`ejMM-ZzCj_gf z&>$Di8493S*#@rVXh7)nD;2|8L!O0UW33~QYkokkQHp+aBJy)S+q=n`pAa-;^8VuhL_xQk7R{vye;bA ze_^1(uq(9m#xlC|mU)(5YR6)MX;$8~SJ9-P>7iJ}^kCY$f~zIN5#om`g&DM@{}Bxw zOG#jcqZ_0^2O-9<)(0v^4sYSg2{fQ0_tI0j`=E-|niYxo&t}-o7_Dlr0cMHL3L&s` zSXGR{JQXG*0>ErIBJuVbBvGx3B6Frae>^f3Or%|U9TPo@sfYB9Kh3W$e=W0VIG_HX zu$W$5wv^o^ki}@|)FH=^3gd_fFtCaqQBbfDsxiE?QaNRk;sy~3f+e4=NC@T)43o62 z;W2>|z4lIt&4zW4qX=fZggSVcG^9uV)8Af&^s&78TrL;y!euxsv$oRvqkI_@e-)na zlw&KTP)t(Fen#Wepbyy}RzL}(6+#;LX8I3fl*sG~6-9J*SjKZ$fs`}2g5n?sg;(wq z_@1G6j-tvT4O(OOPoFyl2H%t1l1qbXBBlO|Sb3yVRRk|dXwwz%Eqc%^0K3p!AV4&T z(V&Ganq`cxp&ac%$%%s=;qF2Uf3BsnRJcZJgh-AT=ef(4HgpOb^b-6Yw0F96Sw_xT z8$_mO?+WOM0TCGXxvV|ts5qmd`IxpL)6GF&6UQp17mchG4WXsvRYaX6l<>k3tJT~~ zlelzLez7HVNlH_W7d-;Zqjo$>syt9AK#8FxG`)-K5P=t6a}hRVMTHMwe>ULmUDhoZ zmo~w8@_Q9jBY|r=21tpZ0e|wMDYSJ;Wq1Z#b*#B6L)ApA!SJIq2Cdk;2ki}I#gKhw zAyD}oD=5#~TRK%7w5aADbPceg+#u|6$s4cH`?6%(d7&)+me$NLt$C<)SZ9^Q(vp=f zEpi)R+N^5|U8>FW;B%n@e>PP+#G@Vr8?DyWsg}?dbiH_3Pr4HSFa+;w}>8Zc&rSZg>VVK^CyA2&wBvw>QXsamy z&AAXMa}mqRWqRAwNUFjoVoPY+y#3VpMLQ7j0ZYJTF^1f6XpNrsO|?aG4`= zPBtT6b|z3RVB#&Iqs>NS#z3zlRfJB;sz5m-SYy((^w$A2j7x9eBulLH+>We{ismXE z>0Wk2=*WtuH5@E>64ix5U=CUcx+pB;gFZ5}2hEF*fbvj6XV}j~_v@6Qq9Rq5mNPsG zI17+58L6;Ch4)Yhe`C2VRPPV}Z3*q@4zgwyRG7-mF@#oLQI4GVAc`%iLJUQ_An0_; zgBk?z1}gDasYnmPgO)ZtB2%DhW(4)6j!8sU@_Ll*^ZrGEp+h4;Njv7R5b6k-h;MLsT6CaMeGt|-e?0}OiUbvyd`uM^y)Q_L{ti6 z2=G7?3S~E2C%9_4xN4<4fYr!YixhOH6|O^*-wK$1f3*QE{H5Siw8`CSJ8}nr_9cCc zMZ+Zpy5+Abrvv0@O~tIT*@;u=Kv~<#Nv5j|^t^l)bd3#moRW5! zf+5`VjLIP!hF{22=s?%xVoa=NWvi*tYe$biaw{muBbk%vP(esNyfzD1?=E3f1RQFn zB)n=|e>jB>bTiI?yTGUmD^j*z7Gi9$_y!cFoG83W1gJ9=m}D9p5@xpQ=u^%4 zBsyRbYUf1qhW5-6iK^g4tya0{b8x57A?TPHVk4%cLNqL#swHWU&|G7AL~|M)KA$Ag5O_iL2^&xrA1pG4QV~lXfaLXY@DNmz=r8mc&r~RSIKte$|O*CLc zV1)W4V^NAvDpG!Ofyp$QX`@S_tHu#-%-fUbP%GW^@>Hz>4Ad5S6h>;s1ZQ5gI9=P< ze*vq2F3D!J9$ZOhLn#R|mdfBT%%JPy?bX?IF@JwGU%a1Pr81v4cw+Y`22mv&q);VT z8?;4GuZ<=5SW8XaA5NqO)m!$#*@zfZ34{d#{1il7VI`DdFOuJ-hVUlQIX1#<%r+SU zRrGOI3nr|~gJxOXrG}(Z4|LL-EJ74+f3%Is7nfz!0&eS6gQB=V7q}>>z@}ODqcd4OWr6NFJ4fHrPl{2Lhe8EQ9El+kLHNagXT{on>WUIaB#zh%}&56!O zoj;KpRNN$F&5AH|;U^g-r88K)5?0C&TAKVWHNYVY{I!&vaZpKBmDEJBf1YZJ z77Cns1%pxw(H`tb)P?c_;lpVIYfv?2p@C^$3GFUDgL}f;O6`JT5}hlk1Y)B70?P+| zX>SWx(EHmdYETX7a^~HO9yVEe=TQZ%Tj5%!H6kD9$-h!^19yl}i_L+m?8np!*BM!B zpyxA;quoty1sp#3u9Y@x*{r>pe`iO}0VjAl25wh*v@#X&9F2I0=T^AIc*Q-qHO!Qj zTuJUst}vaP!Ke9V?WNZWOjlside^;B%L1!LyOLARX2`|)ZgzD&e7@U;)V>U=(IQ#d z-M5u=`&H(c>1vEsM(Jk22vSvzNo5mE0v$qp2KzwayQi$T*bEpP*hj@ne@L7PiP3u) zHD?doq^Y!{X$DMBF<{P8NERZ!Qtl-^6)5QCGMfi|V|E*u9*H(O^I9-lz4RW2(MqF& zs8m99$P9^hH|LA##Z?aHKVDwnEZRvXmd_YhHN)hwwdT8Whc1D_4tdo6GQ^v)q14dR($llb<*=~ZOQU@WTEf{xF!u2{X< zg+k8{=CI$|F+T0pniog_l-f9F}n(N9v)pZuM zwQu5}LHR*^<&t3Ne|}jl;y+EV1!a!_P#IyAtIg-1mQGQ<8-(Ce8_iu1F$L*dfXU;T zHOKEtl5xv8myt?v6z37F3y5xs=8s{L)bxf2?Rya(KqJ%ND4jj~42$LI&46Kxx$j{sCz7TdZ+g=#=ES+7vc49y z8>YiFZ8tqJ#9)*;0=n9DH)b%}pU?%oxVG(13?rSZkD%I-UiQKtjm88B47|%X#m?L# zW(Kohf6-z!b+wT)%MKx=%iOiZ)|8xNYcVn_R#@>qGZQmY23Jw#=z=Lj;|Vw>Pi1qBFFSrx0XN@KdSYE*EsZMzY}(hVUi zDwuA@L@x$Gz3+DT>!8nl?PKf6z`-=LlviNrG)8DDqC#&a4qHTe4;!XTQso>IxwBN@ ze>)39Pi+eXP%aGmMASYuC!|b;N-2B{F(6v^^mbmhrm;N-<)$77qT))^rdFz+Jb8aYGM%CSTF*^n01s!i@=Jm!410ibO>Ct zh~6&TB6??$ajL#-wK7s>$5K;pgK?EWbcsry7(uD?98IS;m-4XJu?~P6dhZDTe*+IJ z+<_R;?m^%V&Qr)iFUubQ_Z&-F+DJuFt2Tyi>}bRz4m}}d+X;urj;db3CCjc%5xu-h zcTTIX_(!w_w*`z4Ogve7<)t#F7i1iZ-#f zw%utVtblV4h=4R@{$bI99BXMDeJ!$P6h&2Be^Kd6m+7h+ zgQ;XrnhY+_?JkK1c{F`<5bO7O?Ijhe|M1}=%_}PG*Zj8*g)vBkO zr3`Fd{Vf1XRU761->Ym>8bH@3`r zY3~2eMsvc~1r?fb6xR$NxvvF?mFP2Gnp*J-qar8jGEmnY)%lR2RCGC>dd~CCM#_a~ zX2A_H8HVj>wQpSoMB-pw^Bto-@ew}(Is5JuM-31}{N0p##!Hp_el`jpw>MSjbL!w^ zs%ws5?_2Pue>2XVFU4%a4;a{x^`0ovU7KPP&uTz0?b4Upl-cyese^|kiXLAqO2m$S zZ3Bp37-jz~K6SGn{i(Avw$-dhGx*6hqwo&V^GZP-po*zYRb^7~=#-aUIsC%tSsmO% za&BNEyBV)`;1myJei2fF&Sq+%dv0Z%ZF4%ZnN_mvf7yN_^i|kGvmx(f-8Uu zbApU&^PQYsx7c?V|7)zZJ9m&n>kR=+F_RNBn+634Y!^BRxF)}IWZGiKbGGjY&|!;4 zWxt$dWRQsZ(zm3ajVj?iT;EuA!p>1?D;6+>e{9QX+*wnVe3F9h&r>t=Yd0miqH2+3 z;K_H4&XGk6(C=a6uzpNU0!v&%P1~L61>^7GX1zH3%^na#{GJ6*bE=&?p{?r_XLV); z23-mMH^B*VEJ`8VOJCXpL0pq~jxG(PLML4Vu%NC}>lLG;4GjY>tE$F~tXc5E)p9@V ze;Rqm_YNEn&#Z7dH6m39MBCuQ>G1X4@9>p{`HV^A;trR{b zclLXChKbsR80=gt*jjP}blr72w0Tv!+u7 zD0j%2u4%ck`5ch;Y13eSol8bbmc+`SnV16vvdHd=);9qDwmZmSF}^(6{kAi!(i;=| z52(2ThMzmmVOd9D)3Me8t_M6@#DT`^-XtoQzBII&S2jr)!vpiXj);q8{6(pEe+bk% zOoX27G^5gMR z$>_>Go!$VlsdC#kzIX#Sl{k{lf4t+7+-2%u?u@X_2h5$$R0``3k2Ejs-bh86jcCg# zqR8GJOFMjqgUhr#z>KY$XWc9L$p#pz&W1(Vftb8SzvBjX%BRCbTG&W)kA*Mn!5Z+w zcG-745?Eo$Y)DjE8f;dId6rU>;K@w;fTT|HeiXp!DA3zvCMMGXilm+Tv}xW*X6wyIqqp#E^*1I zcMzI755;tPb1efq8e_mQe@*q$^qvGaAERi6XByQ3lssj2kPu+STSjXJbu!JoO;5Zm z1W<|tWSH&N3seXnEZ9@3=Hzwmxz4fvy|-7Xn*%NfkL46ulUc$2KP#8k~9tKFGi zHVS}i--3N}rmbC~Ojcg1J5}877}YUNSWH_xsPMsu0v=V7hHsT~f5|9$+F(9jdy2pg zg$>-4*{^^}ddVnNw(ws8{sia5F2hmr*;v*b_0BD5Og(A0)@$Fw+}DK|p80H?wokvb zk(T%Xb<&8lm~uG=;BT9e&a<5_8QmRBeDsqd2S^()ez&dXxk4^oy#^dl)!Yl)O`KD$ z92+N{jsF1p--$9#V6ju6PIXCq&cs%oo!cGHz=~eM8X2#~k<^|Rj5UnPbCMb*px4d?GfB5d(Z+?gi zKk~`^!66skFV@925X|&vlc6HA;O)vCt67Y9P~e(asLb~5fAF-G7xdUa5%rGM8dOk( zgPT#)S#&`ojsa}u)ADF{tf~ZGC?)4Yc`CzZ1ASCQq-Fp6e;>@?0zzwN#DX`#=Hz>w00pHb z=cM-1bhXcIgH9`a?GYKt%Pj4%G8#~*Ok%K`wlm#A-jkXsXV4KHCYU}+bj(h^Y8$~N z3gg+#JyL3&ElC%3rhE36O3Z$48yuw{){`umtck_W9rb{tvQ+b>Dd3;m?xnV4+sp-E zv$9!4f5m_(`zotm-D`OWTcc?4W{-q;Tix4Av)2u7<5z7jaB-%&@3bw9{Rpxs8}Pzm zA{^bcEeS*%;Vx4+rD|xS{=hzkkLRnLtG1;Vwnr&o#b8v+Hb^YIXHD$e<5%~&3&5_2d`7>wadNx9*Xbwa7A=d(w8U zeCufIgx0Hjt)|NCzTBCpfT>@FJwmBAv9|V?)}McFyOOChyJzB)JAme7S16*8%-p!E zw%I5=#3<_;+I8*9oV@CzQHp+EwQcZgR7-IjtYo9WaKaX^*!?xeRi8?gaPXBSdxiVn zf2o)U6~t$@tZ_Ad<1|e@!)g>S?7iE%S1_u&sM2_MueHiIkFn;cvH>Eb!K=WpZt#ko zEHl2d~nf39-fI)cd+^K_3kuKE^jJprLo5-Cw2vnS)7 zK}jpu@mdYt&un*WZI)sw+$iE_%LjxDgffkUsn}Q7yQ?lsz)gu|7b9WeZD+P-iKh8n z#piv1(1AwlNNnJ}yBD1IlxiYOm8)m0Z%uo_E{wvlrKZd)v_WkT6T3R+L!ukLK=t$@ zmMrzgx?}Q#F~@9Ied-vXe?1leawRK6Bm-!Gr=e%heO)!)8Z-^`q&A#2 z5W;!awkJ$_?w9aC0V995QOlto#g`JMO`I~gHntPov!%PZ#hgjX>0ph^0QKGAXDmVl zXmR4?tG0m+sln9{!`P6mdG83LirqHSyvsuoC@t}dTQi%cZZfjmrcj#K#<@G^h}N}5 z+xYSM?zhC|C%Ji>sl%~q>PPnOS7Yd;a%E}c0;TV0HQ1dpCk6TETjy2VJ z!esV&mHQ)-L|%VDtGiC#@yu1tTi)4#q>fxYV@t$YV-xtVxhrc?+A!S)sBSY|^{Mzw zIF`0v1k}1# zUFs>{#pi!8+S22?_lVf6IM^D4N2~!mU-fGqkpzA@l{kiS2lnE-~u4NtT z8gQr4_<}*j=9{+h^Yg^90s+lf^ujiqjV*C%S$rqEYFiMusN*;@3xOuc2>_Ents!y# zuFik?DF6-0G8-{xWBqsV#u19OtS}J(SyH>#Uh8?_37u%zTL>q_RiRRokw4@BvWwG`6w8+;2-( ze74-z-8tV%g(M&*?6kC!ol!;xYywU`quzhr=Tr`5uK@=@E{NueD9X2Rw%PS@6|bE$ z*!c(lt+gu%c*%YM7; zdNzv;2UUMk*Y(;n{JC*NN>9{9?ZBUM4x7;Q#rI#pmOZW-#|{U}%x+qfuF|E~1G0_K z#RuQlzPQHsU(K(-`hVxAufF}}*3W-sk|&N#T~iA~(b{Zh39Of+w%*e@^QP%MLYyj) zDv{a&pB&C-CPW8tx_;Ai=exOD6acLpy(&xb;LTQOnJ;a<`zxk-HBmgZS`u8OvD*&? zRH*XnS0{WpKK9gPPjj?|NQ{j;n?}bkFBMAo%rqu9O=Ho9utsKxm*RV`m~Ma3uC6s! znGFYPA+Amc6RhAGV@t8N@2>SK2h@RguDMq*C@k={+GcAt>uYbu{?fG9KAM4`W4#qv z7p~da=L!IuJyEWj){^%~`%n-Lhx(zD*xfaJ9lyEOnHBaFtM-h~^@c4bSmOkw2lwLp zrfD{U>+{JBfXT%|i^1D5go%H!QE!^Y?pjP#&{+@o6Ba$$SaOyPY9HP-U3Ul4Qmdlt z%#qnkzJa*uuCv{p@TWstYN-SBSk^j$znUHL8up;PYC49>(a9V$DFvV>=bojPD&Q1x z)AVR5pMz!ItEA1x%b?s@-dYT9?xtzm*j1nw1l^eG#*U&9Ou)jyt~Y-p7ra)(;l?CC z@*VUhXDWNBZQuvJ=}4KJo~bsDfDMdfZCI^U)~4dyd1+gjzcekmAz(>td^&ra12dS& zs9F&+BdwdJ>r(=)0$iI{P0x}%0hu~Aoy=xu3*p`>kOENuP1A@R zi|J*DX&dp-8TS%s1AY zQ7vMg)7I6mR=z9jRsjrWaprV7FWIe@k<+>9!=*a!E4*hH&yOOs+EqsyY=oBmfMFeQ%rwdY-*1)Iyi%`jvomrPXR0hSP{6j& zT5Q!kh#IbXvyy*fgeHV-_6}l3*-yzI-Q=9rZ=UM{Oj06sgYWJsu-<2f#-ZG#xZT`l z1)(uhbX*gh>0&j;*cI%rvC7HPRnvV-x6)bgVa+L8&_F!8=GErDd9I62P(0SwaIqVh z786f$?`|b5pR1;KTI^i1rw>;rIEh20LNJhZ6)Ke827-TA#*zzmx7*6KVzXmbt>Y3Se_Ll^Zv}M!-wh_def!U#Jg?)ls!`E zJr2&7NYW8$oFO+auPVVebrTV#YGL+dG79X^m<^EOX85RG64up$Q3jSaKN(i3H--83 zTGji{Ob>r*&+pakY@M^aH=MI^s$<)4zsawwrNvg7@Y+5L;aTaGl@OTligS0<^a3K> z&5k^2UEn&Ca&6kEv*r1w4{xby!JH4>u?IfDqHIoM9!4-z63C>sT=H(UD zL1UBv0w0vEFRhJ}%S2o$pj}rde6_+pZZd#Lshup;uXWv@-C0++ zS-^jru}ZHbUCLUnM`s-|ToJdE-89Vy>FxMWWg-(WQHE6zuCw_9agzdQicE>1T48Rm zlV}2R$+D>km*VDHYt6X^d#0*&og4HoN@YXYfHReH)$|hUe9Y4vWj8NWYy&ikY3AkX zS9iG5W}6*|QfCH614=<8o2Ph0zG|8=%SL}=o29<_iXE8r(%@58+b5E3Vcbg$hup0;t5-a4GuDSb~eZtYfxt*(~4|@f9DF=Tn z^DtnRE`~^2sq1i)edq}lwv;&VD@$q)-R8PvvblWRJX}3d>=O8YFK<&3zRQANtEtHx zx!iQ59mFyc?{I24%G>A#jJW1uhMk^z)%02ZH1;usFKY8Bcvk?B=2qqE(|OkwJlrG6 z5kOMrB(Z=?5IX$DIsSiXx{nkTHCBJ~#GaN8U_Rzja1lOx-82nSZ@KIQhK>DZU9jp- zbv?e`>&+Xaj)*MnPhbKTj@y)!YSX6lm9&1MVi_1XZ4Rt(hWf2;Fl6i!vbEafQv=1 z?(mSl4mR_{>uVjr3=dK;5U{rNs%bWVmZAPQwpXI2F*8Zem~Dr<-GqfWSED#S5O}Cb z9}8#=2*rUD*x%yjT3bSFMC@SRFs5LD?wn%+z?7MQb~ADr{1};SWx9ZyP%g59ZLT<_ zG`qRh_`p;^_8L|CjSVz~&Bj+fBl}5Lzq$Z~N5F}|sj!D~UWIM4tao73tJkxCRhz`bieCTy5Tc7 z%U;>wURTl6>exUi660!Wx>>D%k*U2eOwX=0(>MY(=0ZYmUQ~kalrx>3w2rYEWoI^N zNhyugLB6hcn1zNw#=BG4c}UWHRd-D7geSZx2&-#-U1?wTmhCQg$tMNn}=)e zvb04AAFC@S0dqg<+RWCVp20=aOB%dKTXss@&7b%4(1N{w>N!`5539FU?n_+xqL_jJ z32t53GcUEPrrAOSj9y58El+{bHjgNfVy!3I%^l88k5q}@ory4VPOiRMUhE9p^VQ6& z1)f2v-PU`IeGEtmXml=H0sghGPWbRT2K&5~R1vo(?~llG?JUHun~rqNnJZh63yame zGeMyneCsIc<>~{(g5SW=9?rMKT>u><2X-&(=cNVa(QysxIP`Y|Ad-thT2#yzNcI#{U5oW{F(q&oqDXYCD6lh0h(RTtJg;#38g_5tDW?hXd1zy;Hhz%oDF9nP zfZvSe=SXgVDKk>SpLTI=?W$?ulgPVKw=8)z_)|L8Hd)PQS1TZZPlAuOnZ!8>rH-5 zUTr;UFuhQJWM&aLY_;qZ9=-aKyQ7rRo-E;du+k|TQ-~W=L(bhNwte8J1%6xykXYJh zfeL_+2d!ol7R4zzF6?H%NUK}98XfW(_Y6Y*kaFB$$rG8?5k^P!5fGF#Wx ztoV4gmiK~B#4nwFK8CO$Tu+a%tEMT)rZ`6k9uowAAEyg{=xi#!rCy!zl3JSZEa})1 zW$Ua~nic+{_~)u=%7pNaZ1tX!_FZ|K70g`Lc9r-9qgD&HyIz8DdA#N^@{+T&tgB!+ zfWy^9=QbZ5o}~L8;9LuTT=3*KO@r|5;i}R=tr;s>!sd$!ojBcBO*>*ntqvfLeJ*>~ zp+_-)<)Z>CT-C;b3#l`@je#JYj>460ZILy>&8%{DhXaqTRdK*Pu_Cv`sKCJZ2XmgU z^6S7yc7^|l);dBb;9xfo05<$7UBzYr9H>l985vYB$T|i11pG&Kq^mysD!Z21&3@3iobXY0}oHiQ)sZJ@(*gjH!t*v#_rJMqy$rPj+%ZjZj+7f(_x&?~$>k5ZW!oix zA)e-!hL3-m-^Htc-c$LgOP0<`q;Y($;d3X@h{n8=*NP$NoHKNyA=0j4X!>0nIBtXs|Pudy0#X63ukLDGBPCUTo z$9_0>eyRHVzu7EO4h3ul-!(NG#b{Qh=2M0n)_TQeE7Z7GrG(pD2D(#YSi=`ft}pcr zKidR}nWsPco2;&&ZpDZ}^$hINvaZ-X0Z@$(%CXk~?hF2BAgBNV$x9zM{>^5UbUHSx zf;A@rxbEyf%gXx0%Rswg(`;{-l2ZW{f3Lo9HgP(m0$2m%Wze`(&r7>v{%jNUfiPAp z*dmAwyY#`)jR4%t_R?2`f3vC0XJVfh1(aU|2v(UeHRebNGIGVHPJCprze}qF&gf)( zGAN>lX3W7Ao3O&i5z$&g;fTs~lgetDt~M{(JaBWf51Sk82#dR^_8{22S^K_ne?B`_ zFW1Eikje^y))BRFUfOD)Ec=ST?Omc%NbwQ79zdNUY|zYJLf{N{zO$FSu~GMo-6XXd z?#yQ>J4TLt<$U(hngLV;f{fKv231&@ArfHyskAFL*VLYzZWi94W9#Cp#aVSSB>SE3 z+?y9;eJNcK;u=h~umZY`Db82?f9;@FUO(8TR5q6Jv=n4!_K3D#tBCotP1)F}^GLQ; z{1l5cF~u`w5Zd}u)$E^bh7BF5=A^;+&7#D!BG?&4n_clk2AU4eezFK0dsI=|t&cN+ zK|S61PGb&HDI35GAUEmgWmQ-!R0JvY3LctNCtK=%+$F8r52$|1wI%GMf7Y+~A%GuM zW(~1h9a9DS*{iiGoflyH%G@r10c;y!KX$(WgFt-0tTlT97nC#rR9e6DovVi8aI~ql zCKkN$>IA4)l8q?y%6cwMaIga8B~R}pW0o)LHx_x!9SpW8HsJ=Y)N_KTjaq;f27O@# zR=V?@z3w^vuwij+^XWD?n0LArUVpz_;bm}pfYS>xB?Aksk=kbe@jT>M#V=QEE*$-n z2Ev!lqvi;wnSFJlByOi0Ha%yx(pEHt6jdyyI7qg6U%l6PC1wNX!3_{^0m>tq@^ul8 zNZ5RvoaKhiourQE*}CxlYk}_$D^e3XwCYQ1*nVNt58vhSy^Lq3mWX zX$3I8?3P`&%ems?qXPd7(7=-sS2AcWvGvwoSHi}@KGf>Q`8+LfQhRGU zhhO>5(?%O-%JVkc*8t@lbANI(V+V`B^6qVa^~3z*AOG-&U;f?ip1=FMfBBpL`Mv*B z{P5}f`RSz>jla$CPmOcL>T*_RdP#8#A+V-th=1v&Iyk?1Y?*gkJPNA}L$CmHod+8< zPr!lo(kj{CJT`rVwg;SS8vrZd5kS0|zh9Dcua6xYz-S$YrELmV8GitXX{XH0uDMM< zbZi^(V)cz(7Fa?iz%xzxSQpUwwLfxfKtrpZ4tNWvdukd@=@QRRNuMvxpZ?8bbAWHe zzr9ZaR*h4=TC3m!Mh)`$p=W`asH@uPQJI9$*C`oPxATO2UbBrM|t5l4wLgVtk63(_(p7+dWb7#Smx8 zE=8G~S>8Do2Dcteg5E(D*&U$CZ8{(_;Gv{3ac0t%?!WcaCLk>vbT& zgCQJM-vM{Nf}OWH=c+Gpz`6G8rSJ6LyPSnDP0J&m_>9wPK;Y7MH3K*n~US z5KFSz80Rg6pk6ae_t{kAST2p4Q*Fbur(MpGw+upKBxPU6!CT5CEB9^8htH=Ymb_;s zx~3w@1b?o9Dh^Fb-JAr(xyYyGw+w>MxRl&wM|=D-Kx+$oKCpqET(Y>2)C~BmO(5~dX;vnfD04^Q9yC9eH>aa*lzxwL2S$g1*se`g6XS(SOx7`B6VTL<$FTl5qMXT zy`M%(o9=gXYe`PQ0(yGWAU3v$F3keeQPdyjUs=t`OrG~_?PIXC^P_+51^`64LBVn~ zc7Ng7_XhFppZ;_g^8Bj-lKZ7#NZQvFGxmY7D`lXcu@MSaH@io)KbG=CWyoQpDs5}da^*K0dAet8T#A{#d1nx&i+ zHGsw&LIrrTjEku67h~vrVrfmsa(2KCtJRLhY`~+w{Vn^U2eoZut5b51{}r=atLp^V&?38ngc`hypri_i+`lP zIEIB#99V%>bys$6-Afyyb4%D7udO@z;uw6h*ZcwrQZSM(L)e9I+unow^euaGpImaT z&WgHs2H4&2T%@0xZNc%CxfIhJ8t`GB3amMv@N+S#A7q>-)1kavy+*w8^M1>U%% zS_iOdc~W@2g3RT9e=JW^>zRh+YE^A}!6b+!W*N*BeZ_jqAXe&oEd=E=a(`#LW6gkVQ(B_RzVSKP)8ip;AKL*ArM_txfM1kvXeTN&E13*z z+TbpMQoG)J8UBl5^b;o&g@27KI0D>)%ng*1mcW~@Hw|NeGXe*BvtFe5!U2fFKEXBTZ3I`-Z3hdyJ0-1k89!L@8eIG#$5p(f5v>zAY{iQ z(hQ!sL78}?AT?%f>g^&(`S*jcUUQC(;5?Y4;t0w@D!oNV*ZP)0WNU0OF?1J}nHnpw z1S_FaY8sZ_G6v#%@);TBfl_DF)KV#ZpgrO} zgTSXFF!1qZot_XeLEno^e`O(4YvV10sCh5eWQb(f)7eM1wVuMyp}_Zh_C)PnDPg&a ziL`|E_=(o@#TP)fyk`)zR}cx7()Pi|bZ7RRa_WiQ(C=k!{rf?LrdVYN_Q1(fPG*PM z1!T2~+nZ)$+X_~lVsGS<+t4LvP1z#w1tie+}PPH*+hO?9&jb zRtJ!L&nRkC*;bb&?7>D6(_sirK+Zy9x!yAhY&k^3UA69!vnT0n&~6A_h!Vc_J)?-e z!53yOXYr9dHSYpOo0VOldKvE-#fjePDD5CBQi^`FbGjFtL+{q|wNdw?z>~n}`7;xuv{XMqIj=Q~dcz z%F#WF9N_acHIFnw@hjNez%~$-_l*QBI#!RN2nIL?lY)r}0G5vr`C>A_=OfXnv7QXs zTEbUur6rji@D}6+@!@?V8JqofR`2*{t_9!(x7{!r99Nd|f4*-d%R{YZjXqNA+Z8mY zodDlylt*6g8wq2^QqK;ikKY?SIIwja_*>E3#v4b{XFI+|1Vzx{K@R8UupzEmDQ{dI zA6j!ia?Vea^*jlf&f9?YAH+J{cZML@!q!8G&F+*`ib9EMIjwI1DMa%R12GT}vo`$E)I-&;l z&sU4Jdj{&#zqv!$_dkB~>8n5eRI&B-*Z&avN00ydXS>|prlpHQQWE=2(aB(Vity87L#70|-!`xsx^0m>;hIAineskGO9 z_fIB&H$Tna|MPdZe(WC}e&g^;VBJ)o%bg{CKFmfO1kx`GG`_%c>1@U`+DJoIl{svV zv-Sqqe`{lWv75pxECZMHXn<@>dq3K-aX|WZL70?u^PBORb4J?1YlarB^5K?(cud*I zUu-P)3d>dxWxSZx8>h0Q!TDwsBWyYy|*BoZ*Wp4(~oSy6L_++uGrVO9r-Cf3l9B+DuJzIdtv+qi%$N2NGkOrY*!>+m%R zAnc3RhW~#p|HnB=f8$Sm^ra~uL>qgJzmklRM##o#?(jT4J4yb&aLo_Er4_^dPwX?02Yn&Fa$Hp)|vnnCAl%Vw$T zX+Rfs+r4vK;4{JXA_FnQHrs!`j4nm%piJWz#aCWoxExu#u*qIfcgUCq3y3wQOFH*< zby=}$VsbsJ5J6QcwZ~7cBxl<7o?$;;OIK&c#OT_FMvl~35m=Jm`{D}RQ4Vmj!gDlC zfUgEd2ydxCmi32uM_c5P8%$!4$w42ji(;(o?(1#LC|kU#n^f%LsQ$@UGyo~u(k)2%;|qRS~~!GUAm zT;@1IEibT_E)i_`gg{XaAU%k)^?SP-C`a;&G_3)_FE*re#pbRFe_vmIclQg!G4|BX zP1bv9x#;2xiiCMox|p{vdX<6 zK`AHDa=7OecG!y4R$T(59nn@x7Yzeg4l7S&fX^5#%kXnjo(UfO-WQ*Most(b?^BAk z_8K)c)^x+2yc`Jp!~EutapPw`fEj<CZ<{;*v#3(gD2(?=;;PuUrWxfb!% zTX73}-G2FRKkoT=fBv$f>EG}ZpTd*)IzGMds{Yr0IBDxXT@e!zikX^rDyWPjW(sha zWjnX+_mO|PvrR=!4p5X&Vy;int%>Z^Zrcawg2~bnKh|Sm02H^z#sO9XiN0;0E$TaK zO##pxD1U5qWfqtN9O92R?6W;)-k~5;nCa1afY6#vtGgN1F|HV`;4(tJPNCjZJg`6-p5@L&zkqf4I73HOgUNL{#`QpWwda0w{H*oL=iE|MAoJG5>VoN8So7pZ)Zw zwMTykRD(C2ym_7N2z9SF6HB%97joS%4WMV3pP72+)^Yqcs6uQko~63&#V6v|1~5}$ zJe5#GgsY|Ooe^Dg^~ho_*9Wj?jO4y?NPU7AHI^j-Y%cg>UL0Q;0O)lagJ})Hqk+iA z5?MZOX$Q!7v7`UlswCq>+GgoE>k`veeJ+0uLx;LuvdWT|$sFyDz~cHOiB7G6`5@va z?pQ5sIC{)IMFOT}1VwxsQiNrx{nEEqY~)znL*3XkvQai;P-%FSdGyk{R&Y!UD$Kd! z(?YhD#on*Ej-Bn&3f!QQo!^BIRSZg;F&SC^S+0UUoG3#&|4Ua8+Ga2t25vIA*r zjrtZ+G;dF1%Qyl;Jad#we%JxSdOKO*2RD`JS!`1}K>r>q*VhH$--Um>zxw8n|JOI) z{rKt5Pvu|y-T(95*I)TppMLlKJfD95?f=66@AL0|_yChna}mZjhkv3lz}kTObjXsa zF_>Stm41KQs6eHeJ$n44FZ)Y7z*nQ9$f!1xt_d%Ji7uG%Cv= zwdriq$=Ee_zQr;D0IW!Qs~`?ibQLR#98A9-Cdf1=9iej(z)Zxgq zeb5T7v$e>neNsvteybKB6{a+;9CLioTzNh_9~RFlQ@M^EvF0}SaA)ev2aU=(1b`_A ztJZ&(lk7pAsHIdf>mL*ccTPjvT1k(j4aPl=_K6{pGu8MYf3*cXIJ0Op?4&f6gR+)} zt}=F9jX0m;`)}sgZv{_ZFv-iI-FB%O;22E&oN$cC=W45a8|8&*dcSE@S(vFX_8QF$ zdzi@*$#pAs3{G19m{B#VtpUkb@Ii#S4uF5+J!~CWC%LT;8dZR=*3LRoxJU(xlF-UN zPlzn1o{t$--$GW&Hannrm6h~$j$~8^>fPqYj0)i`4HkNO9WHUw>~+-6ixg?DA2cd9 z0URpTOq4y{l=^yX++HzvMLuY^J9GV`sIs$~B9>4qJU2EDnmC&MV@9>rnzST?@`r!5 z$x*m$7vS^;u-8854DNjt;WzCJC=M2?^T}lAkSOl^L8FS?FqAqgyj3D#5*<&mXc~yV zDejHx?_>Y?!@M2Were@l+&I(6y$ol6D=)6H;By!{j;8arfnc`#>LVdofa_-mrOkEw zXxOtrKk01)!EtS}w^P{#5Z>{NiA{fDn^8$GERX)H18MBA>%DeOQ6?PkNhPyx8UcM& zd)q*E^U&SaT&pgulxuQM1yBVags(ZZnOZ(lfrR%Gwj09~U^5ujBuCgx_Y7nAX<^>9 zjvNgx95fxjE&-I0xaI^VuPT_17|S=9H>eRp?P_pKx~<=fAAHzrtE{MvO)h`NDFIwR z*F5838~VL3mXY9B7Y_SV@^W%Lc{kpnhvF};k=03ILu{^Gu($_cPFS%(huGuy*u!jf^0@*V>)0&CcZ2O?`xJnbD&?AC#hijPo}DJb zjrZlHmL#dJ8o=P=p5Yi)$eVwGU(@Igys>eT6X5`cdeXBJ4f zBVaZx|2@Nvs({g&O+?0EU4nra_FdM%HaqtWv*#;LZz-!v9_B-5q+HrgRa(gx4ZHD9 z$BO_aXD_Sh>8FZLgv*P*dRDff>^gxubIM}mAOQq2;X2nnTn-=AL9GuQHO>|Mb>TaH z8<|N9*8N_PSWk;deBys;)TEaTtj#?0bxx;B?LET*keM*c-g_eI)4GirDij9C-&`~7 zeMV_UzJVq68C@3}pCeQNRkwSd3xNIzn+ex21E;`pr^6nIOr8F6ccT{=W(E6Bgn9c! z9#nfiz3rM(XETC(hKJP+_eFJ=V^tT^o=nTB@LUK_*9-@5iEV$J-Yc+WN@ukgp2s@8 z5xRHL$lSRs13^N@V4Ikgn)Kn+FKB%5zh?NPXdC!vEik9;?Zl??hAUHiVg8=ssgA|P z(Mg5Hw+ohc$Js6{QQ7y__#D7@@mkDdXI93*`c7#&u)fvTleYi)w1Ev1k6jo^qha_CxP$#mu0H2j761KX10}$ zl`Vi}Fs{VV^HeI0w~hry=falRwXhkM19k8+(?S2)I`f@l=^Jr>@bwQED5e2s)lsM> zi@z-P)-}S;C~$QKXbpOU^PNUn8$1dl!yofI$3k()98uYbrSDLj=^hdld*)Hke&<-= z(Lk~Wo2Gx^7#C-~a*Wn)t)P*0Y9nz^J-GLg&aw1)OBI1}1uOEdTgj_>W)D zPhb5x{{6rF;X{lvAQrH)y%)|e=>AA9CFRXNh(*ONq#XVy$CXdf5o}@v%DN5vSh11I zU}(e^@{bx<6T#N40|4UGk_sz|F@cn$D^$?}^mYLU#1VR(=z> zHv@mpT%7G(Phar(X$?<(QG8W;&UJu3yX=0^@@m5RLSSn)iD(Od!@j0@QEsQ5iS@zhy0u)Ah&X$Ua5fVkYV zT!ocb2Hcc1_qAu?y9FZjVjG2Y@l@5hc)Q5PtEHM`S&!@-rK#b?%RO8$6`?D5Prqde z_0VR5Zy9Hlz9jW|({kuOUKiEpfKns(z|I;wQ%_MZo~q6Y20%eXit6Vq0SE58GBS$miLzVrf_$mk{+fut|`GEL@H(MJZp-E>`gI-etYU_30LyuJYox}Ud2$yAoyz@qx z4<<73XTA8%u_U)S!Hao`Ua7RVcE*3{0zl%;!3!<_`74kA^7Yr>I>6|+-~8Wy{`!Zj zKl}li&ASaOXq>XCua`==fNgj9lbvtd&n*5{O8UZM@`Xlrjj`A}$y!_Ww*3mX z%%1EKB}wP{{IgnoRi(1Evr8EZ1x{^#76{gBlcs;wJ_{xhG*ghYezUQWtt z6oSQh8mlJ(8hBxSsqFz6I^Z_ZM|an@OH8wkGL-Qh`QKF{6$s3CB0 z&8qW^zil9k?})5#SODe6%Cb5^2Wl|82IG6%K)mzokA1fKL6)6!UEZ ziQfIRwZ}*UWM!tFPgb^1Nbq;V-!_o5C^B^5?PB8pD5N$jvDcd1b*_7Ri0(=V@itM^~t4Y zFXM>OCBrL~I#0hpf&zb@lo!v! zSr|uVqr~$xV&7OLH1eR==M?Zi+rJN9#wJmuxkWsfc#09HmmfnF!n@8;tv3Ug` z?8no~dV^P<0W?^691?;fVgZpm0`&-&T6F;+e>H5#F1-8+#j+qWq%+0 zrtEo@4;A%1ms8H}`=mFV1#j@cgF1GnvF+s?gQ-zo5Fke>Z}0~WYye+y*oN{EyKg3J z7%V#jI=|yI?qr~0Mu#wGx1=Xa12zJ9?(BZ{h7lYCLPUT*3QXjwp1|@4Pz!v8=5>Dr zf4s)%RK8sxW>4)HZw?&H74dTUJ4R3fxbSS1(nmWvonGtHzN6 zSgrD={L%;ydTxo3Ctk+O8AU4Vlc zU%bNR0TZJj&^5c0D$-gLTm0l6_-AHNFwbXzmgQ@9Bh6GDnC>JXTmkRgx+&uTf4o_* z#S}n^JrGF(_61=2Kk!$lj#4Q?^lbw|iA!jM00K;xT zw(~+Ufxoaz@$StsFT;7NEf^)5f0y*MrA_;qf1Z(RM&MaF_l4!%)Nkn0gjLb!+D+Q!qpD9!s zzP7&G6TDMzWp^p77Ph6WD~hvAnqRvCf?eZfXSA-^*a-Aq&!Y&!-fR)q?1EPWj%h^{ z(lWAwZ7#sO45|@<8MtQG`W6F=!#CHK_5^zMmSxYUljAi%c~+W^4Rtcr8YcV(C`D&e zNA^j5^?m!_f4hJDI&S>Te7kg$BILl> zH413nbk|E};rFOg-RtRmu}zDbP^{7zK3jcZC*8j=8G{M2f}tb!8RXn0$3>rU!B6mDu!i_28GM+kDZ)&ky{s zeqH}ho8)Wr9+V_X2DAu_cG%S{<>b>@*I4t%jB2<6oc9I~daxU;q*+yER=|zZUa0u- zpBdH5bEE$AHlKt9J{hI8g&>#&r@nwl>>g_Z(c5@oviNTsR<7MLP|&F@=e6mYN)um! z_+8|M`P{#4SWqme$ec7Cxn^oni^7K2;#? z&^huhA2qC1Ln)ova;cO7oU(vLfrn4g)ck{n)kp0BbO{{9v@p?q1vvj*l!;XAdymUW2X*}SlTEeVwbFX0UUqNFaaHF386LfkWV&=#39%1 z-Ot;C>@UUxvc`^A-FAX2+{c3*QbcXRExvvKSabG8+JI|VDcPQ*7qCi%FHN@JJ|3)0 z>iYoZV_qnGw$h_qk6l#MdU^MF){rA0M0=#t^C~rA*QDXv;r!D2|A_nAo=uP2y1z6p zoVTw@)4+d40vL&bek_I@QWk1Uf-JY`zwbHsw)JWyZ5rU3`>~akcI7;rYhK86X2?T* z_jt}&;5tj|NdRaE;Bm!jfI|sKEmwQ{c+|aZnyDm!-|n^7gNmV?%32d==slwtKrjU$(=)3J z4Do+*^xP-T(w-^5=^P_k$EyQy5mNL~#oFB2tTbUV&6{>77K0BUvW!h{@?p_|0C^7f zl-M8KFg%?01> z%S;Prb-{5c<(>i&xG!nEmwV4B6ueo$5;uP(hJbTHL?X$kGY0wD+eYCB;dZmTOr6Ts zRh<_gyowya0`D0Gj$}`Kcd{96CY^Hxlfmkav1iDeMsb2|w0mPBeDw~@Dix#yh@TAk zJs0Pj!izYPR7Rs1007Wheek-oBi4@hT*Gea;zkl3+{>yy}F9NPW-+9;EHb~1pyLUVP&fCK*s6amrLx>uqba)-YSZg@&mc@kEeMp83Rw<71$G$O z7e>_9laX(WWQ=W!&3*qwFPzzqW7GvF?Gamu#oYf1k``88t)?7 z-H)=SKC>>(F)MhNCSd%H8R&CY$qs-&9z?ajYTS8|^pfgnn(Hh* z#VG8RvVGPEt2lqnI97VWAr=bflqwFcS2LW((WCjv1{%L+yk^!1P{(_~Av8g>it4(@ zX(!s{4F|r`WNGQUm#QETs?>kgi$2&Qaj&b!`z$`&Mnux$1=OX0QzAgNKKN9g?ixQp z#EK}uyQsdC=OUoD(|{ASJ(xuEYsN;sd4h)c2s&P#p>OoHuB0W5|>(B z)~fj=!F-D#T%Xdvt;M@_QAAC~(RpZfk)DVC3TTQZ99T{+O z2V5y>op+7v!t&}|E%NFhKrb)f&(c~_w+HhNf6cgAp71e6yLAC0%+ej`_(&QFo8WF> zIcW@K0anTga06BeN`b{}usr(imjnGT#j*0~RHH!{2L%>Z<`zC-+;y)p9n60&%zI@+ z8AKL?V_W+;Twc8q)rfze@B>vT`Y(Vi#bXs}Xf7p+>b@>nJ#(E2gBx2cW4Grc0^)y4 z0o^sfW0l$mDv5b72;3kV*jesk@NxxfeCbj3{FEJWdlXzWz1R}vmPfFJP+$#M2=nB)CJOSirsxw8) zI&CD8J65AE83$hCgrqLZT+)%X8w{JAbIB^^5wH;mUYHMHy|Q-+HkY(zy*;{z|I1&# z|L*U<|1Q4$=FU%L2p#Q^d2y*`Qmct=!D^a&S(y*Yw|swTxHN)7ZR~ZG97wq3fz<>- zFhxv@i-!576o&!#6G22xV^cgI|7JXV=kPPb_0|8ag8Jecce4=PS-=VmAiec*&oFRG z!GRdss0mvs4phUB!8wVae9f>VxcEgSkO|+{DHNc>BFPPGEHhm*+{ys8^$e;3=kL_v zJ*^xzn5%!uLhl(~DS>6zKG#@MlCxXdtKmrp4BqvgVdHaf6iXe@q2eod&Yr7Oi@El_ zUES#Xm$wOIHkX2RBuR71EV*hXlFe4|>E@X3skx{En>K%Drrk4ap5|hqdRjPEZML;LhtU{* z+q`CY^OA;dNuaONTg1`&5}KNT8#3-WkPWMRxM4elT62f%=uJt%X3Xt=&9EvAFKs}` zwz0hjkqzs*TN421ea*1-4yu<~n#zK%QKQRgnDDtG-#kt>eXzYSpQns3mGG1lPIDsJ zq4$3_mqp43kF}{mktYT75HU*kzyX(MUp{_j7_6>IsfX7wlT849)UD>Lc0O9)0|MvO z@fBnsS0-x!6ttXL!C#cl*NcX6fTT|^EotgIvmP3At?-xvwtX)w9#$?%iizL=u+B}s zy|G@ODSqwV8hbWNiAB0_kd5z&4UA~k3ip4ZS?-0!7~bR70*WWQK8R)hW-7+9Pj;D-CwbB{eESj%aH%uaU*S>#% z4F|gk46T!@-ONsjJlYMDY>)})4cMC$K8ER7*|&?PQpPFyipi2KmDQ+90z@V)^?}Gz z4)%^ecwzaO$!anYFN?c4yiIO6D;cxe_5i2rH%zjeM+$3q)-lTlzs`Hhv;n`@y0MnL zW?z^?%qjeM(O4%9UO#(85j|H-MgxETfdjR*^3Rx0$|ij<-}f_BgT;j`e zZo`$yBr6^D%%-FINs};c#LJEovcsB;5;EMHVc$BN#$aZr+;9a`0_UE>&hE|z8x*|4 zzJ*zx?ZMQI&rEJsnBzo9?17-HaPmHv(BCVd>kX6cf#qaF<-tHUjpZOj&IU$UZ%pjU zX#$>S<_lKlk80YReUpLK4gP=UhDk7a9L(DIEFKgV>8~Dcls*6@x$%|z_&UAj#b{M{ zk16hT5HEqC zUTv~9l^cL<%eJV1QE$XcE2mi>dnD}8*3#)4R+-U~rhq8iFu8&$fOe(;8O)fuB^(t% zJgYOc8*7QLIyjO#2LSERE&)d31k+#*n1dT8y@ho+@}0(}U~w661RX9(HA%m*eQ@+= zP9U(%)!6y;tP}n&k2HTe?`5u-3|-!24Zsj4*$TYwk^#<_Q=d1WbCii=nAkGcdhZm^ zDCV&+!=*R9fn(!rvb)^b{sEZ1_Ec>HT$a)hG#}it7joQxcQ48PcfXo+49>rW$BMz8 zawf-*%V`>36@LbzIq;Gg(;DiILdUAym?8i5I|ktxJCn<`LxupEC3Su~M6M z%&2Fc@?hHWuUkKRuF8(-p%n)oV0N=bh2US!sh7XKr-9(Vdja`^)5|{WSg&&zYWj_G z**eR0cR~1c(4vJ2C}(x}+ST~*EqAR?wgoNuY){PB*j1&xWb3?~w4S^t`8De+d9QLN zLG3OjodEhPl&^oy2(J$c5d6CJ<%@|be)z_*TZ@7v2-jT)b!zTf*Wq5&@?_({VZEH$ zT_cq!*5kq2ykE6`+Dms7du**qvXA+%0OOfy2>C&2p5Of}J*c!H29jDFBd8!W9b}ac z0n!?#V%{?AqjGvj!sLPlV0oGCUYAwTRNE!9P4w)-u+M+$<0<5CYEurC#p{EW*k70h zYRf8z^`ESH_SVh2I^4=K5a(-VBURmJ@mgS0*p0=$8V-C6NM)DIj>;YY>X_X)Ir_q~ zQtEq7oT;_rl3Aet0eDKq>xS5IUep6bU1!a_CcI>JdvTKl;A(ctoSPkNW~8OU8l`;6 ztOF9y49kBwM63^THqt%;xa=j%gW7n%`@`#BKK=9fY=)3hCc8q`;59&Yr|x|#Y?N9a z)V=@AB<~q*Qiu%}a+aF=9>AB0vUxk-FnQo#6KFnBW6?yVPLm`^NUEYAMS+lqOo`1VBebie7!!3W{~X zq|D5SI}Dd$i2)OT^O%(tW0gIe*Sf)^(kEpA|7Nl+EG8cw67xT>XDRVl_)K7R4Y{$F zEzWUp1hd9I5S}o_!kSKV=*1AIA(&wve3$VcE4)Yssy&IO%a(J#(Fnx89IwgTwGx7Vuu8w~*2?j8k zuc(p~o2T*d-YJPEqjy_3A_>LC@P9amX)Z}UG+PX*Z2sPB+*r%m5S zrs*eHIrXf68z%j*?4$rC1Gk@+JN6G7>j1;|=;ew@xYL-gTmhrJqGS>5*oEzsYP;d^ zRw^q+PT58nsd;8g-Zq(@)#2%Hm?Xw&R{CK(7MX;x03aD@h~z1VVID!t8?t`r^&Y zsW*1)E<~=0$zJ1V7ziHDWU6eK2WoyJcp;Rm(G%OJvK1m$u(PTJB%0a{^NLA8WFPFB z7Itb_iN=~>IcWldjT?~!zEo`0#LA97U$JX9sRC*_z2qBk3lM8aJI*fQ3v(l=s2X~ib-d{?B2{qQK25etiXId3tiw1lT)VP zGui)T)ZCbLUfG`(|KLwb34LZ#OPabCPUMy(8*DnW8|)G0LhKtm)@%u)S8IM2U(+|k zNS>vfQCq1uLNqg4VlgqiodD4*iyanDjtXLbeR{uPvH~RMrUA~*9*PBlb95OtrtUkp zTYQE?u}+!E1--euE$cZiUi{>2ow46(r!2Q2|%fy%FvK<+|4{)Eirk46oO8$LJU-)^XcY;m=kxb%|8^>|M%} z37?-C?K#((SF1Shyw764f?2aSUaD)}cZ}l1i3iRexa+QEfdTmPap2o9fPBS&=vawr z`z(@-T^gUAFu{}QGQ0FAUzZ>=cjva*$`U(D2P{$DND8<(>h^`WrP~{uG-9Ho4|oO@ zyJ8evvb6#m)Ycr!o$1+H&XJK#&GsFSbikCsKIW0AR34Kl@_}Z zB$lFK6y+Ejqm7{tD!G1c)GO7s=cw?6aQqqYN)t%f2@t?1`wsup_uv2b{g*k80U>{; zh1W2m#AX4R>rmEe~OuslU`UTr9+?01ZT4+>`pyd&0D+uRM13{IK_iS}eJ+gHW_ zC^#nQ^&Dl{N&>16?$i=7XtY({F^1)5bZ|6G$MWq9$1TP>>hNpDBHl3u(2S|oM&*6n zaMnzNH(QS6h+m~WKZb{U(|_@EKW%?;%;Lsz%lL?wfXytM3A&@jm1+HdriZ*_=~q3w zQveH=8z2rf6VhD$=2!DhBM^(=P_(s~uz{9n&xMlYG3G_nfOam2G6NJvKxD37^28@6 zQD3?)nuZHy25<_%p6-fW+|sNCIO}Bg*?ZpfzkK?$YhmN(KmV19X4(YPItqWE@A=9! z5+Bt!epep6IQz;FhK;DTC)tBdAXfgguQ2_}lF@ezVeP!kJS>5PR%_M^H`q2#%Y%39 zUl{^|RiBpj7|l~JOEqd3UlvB#ddEWKR!tX0KPRR@stcd43#&kmf}_7-2&JXe#^R$q zQ~z@Zp|U;|*s$jo>kUJwDWrduoHW7e5uHVfuqq0e!lu1r7AU&D03j${Y^+OgomN8D z@ZxjMcMJh1(6dw=!BX(+k&`J&E(@E(_giM+U@IWVOg8remNJSAn+;$p*5!^j4578? z9&%=C;3h0;pR7m#HC!>Jr1uPA6SofFX*FKo_VwvmL&3yrykiL3!6ScW#9D?;Nby)n zWjlBjyW9C2h5+wlL)x&MS%n6GKbSta0S%ZZ^$zbi*i=ze96V+O8y5k=?q$P)h1Pk; zUeMKbIxxw8$)3Hm99iug6>fTTdCL&^`E$cDF3pRbSkyrFvSdx~!3)$hcemD7Z+SNJ zjXxNzV0l)+YrSI#YJ+JnF!b!hr>Xxb9J~#b}f0s5a1E3 zj-^d=+Yama@_LkQ9vAcd9vs4t`|r2?(Vzc`|M{yfuGYBe2SHRe*_+2(=ga-dsWwViuq#{7>TC&=w;de8Nu)OH~!E2JN)|N z)gS(_2>EZDc#+41gMN%D;b*U0#m7jwbq9MxM0nRII%|upU@6^mn?r;-(<`;5Gp#p` zV$VjbR={PGGOK@wcLYcJnl;ta-!uv~Gd%6U{lX=dy;Jjsd1-sAcGowJB37QG@}2dS zyfsSh-E&PP5Tee0&nR-sgJ~;lkM1zc27PlL%meeGJ-urbdkgSVu9bQMA~lz~DWgwO z>QUb`3b;Bdtt(q$3jz}k3w&TEnAeluG>VcA+yj_&0=IvR0f!s5BX!oiPn~Z%BV|aQ zDVf;RPPHC{@VP{C+7@naIwKW8;k2Gs&he>Ick}TvD?mhlvOo7%MweT2jLXEGdG-hCg{AhR6kSE`KnjDqDBr&l{6 zdRP)((n}L}B-V|~n__Ax@JwkFR4%*r1P_)isF!8cOWZ{{uXclg{yQqdxU5`QMuizE zY$1QTMr-@FeYV6td2R;{=tZb6FTi}*j??AICZfM#pQ)&uZRE8##|AjvT3sxj(}RFw zx9#_war)RUp_>TyKgNJxyxXp1V%P0=WrBQwhP6_QZ}>>7mG}1SlW~3hXRQNYKC%Agy8S~j7HqZAWjkQ4?d*R5b2V~`ZvDD_Z$JmH_NEH}l4>JVI_iko zhqvap?QgbA?zu`C=D^fAihAIose$5_@@@N?2e!Wk!t`h(}VR+*X^(5D``zz2HY=OfqIr1Yj*FoUf=&=s|@zDoqf+z(+Gb{ zm32wxl<&Ln{hwNJi0z_hc%2jMe)Qg|Bw^Q3~ zQ!9 z-l-BSq$_NLa>+T!RB+FRn4ixi+*$$HS#f|S9LK(8)b>mT%oDV?y`C46W|h<}yTqN1 zBnT`O7|x=k4x()UZ$Oa0R87F%1+^IhmvqG_&|Cn|&31NMEj7@n)><8{9-O6-?iiIF zV{I1IDW$5+W;zBMF`VKJcXn?Z5fT)Cj7*aWwlf773}D;I>;`tn_clP~k@2mycbrzQ z?7>#29T;z8?kh$IXxTEUEHkM&$7B|>Wvwjqkv%`eD7M!MIK))orBVfZPc;tvF&O?o z(#an)D){NVY{Z%D0pGIh1!#XNz-;!p$_I@KyA*_a;IC#qSk60ony)md^`y#w+0RA= zWO*zD)hh;bR_|w02M{#RQ%JgGbb_^>NMLh99dht0O0AwX*&g81{BLRz6BU%S=FkEX z?~F3=f^@dGj0&q#BaPZDv0qnPpp8+1(4Ley`rPP5Bw>Ahlawi2TViIj6CG<^UGIRC z*|<$#4TB^=CbS<|LvX>=BEH>aVJ=hmURcclTwq=~LQ6$x!=FU~%D;1D7QSvTF$%h! zb20{U*IDqQ!92rm-0I=3KB?bySs`R$`JGj(PxwDbjBox#aE-L~dx=9_!q;~~z z(Vp5Bqt=JBPL#b!QlqeSQkSon0UUqV%#WPISK7?rsFkRmT|@XrYIhLPN$g96fV089 zBRo31{FyT|^>xb~=Wu#}Y403qE7(39FO|wqfK@E8;X6m>*x_pKd3t+E-U8ciFR>>P z{<^cKK3Q6_aw?8s)6*U*i1fXUgDAYs)S|m2DZM(C=XuxWa0b+So0qKCJlV5d zPG?25pUKRxjXxYzFRquYD*VgHHfG_?S6|@QK5z_A&#UMqtEI4Ov`_jsx;Nk6NGJ!D zGwPN*R$qyyU`h*EZvsTGOc8)p!$QI=U$Tmraqz{jf^%kiGIC=O2DpE_%C&DDeGG7- zETI(pKRA`jCeAEfJoVDLf_g8eA^{{!cFOT&qLgS{EQns?j#W_{R?ywr$+Cx8lD%4! z)(U{hzVxkP@N>0<_Z<`|Oafn*E0z@AZr`%nmTus^?(M)Cb!}y;@m-y{S7pW>tE>TN zy!&qjo(SFv)N~IYDeZr<_2KO8zgeAA9Ml&s>a}yriYj{|w#|`b-LiTrUm`@ZtXgf2 zQ-J|HD~%l(_tFdxScLm$Gp`0nU0E{)fFu%QC5>BFC%91#-rI;2W=8~{ej3|m$kO>S zRuPm&xQ`43(`J9gUDj+V7*!*r`JiFtvf$#txn!^>Rie10CU}221Mid%o2}eUv0(## zs8yZdD7My;v;ZCebU$oZC$nKs!pZSQ2*qwwQ)@KIHAVTLVU>(kLuiQ8;HKF}ly|0U zdz?9%$p;OqGG_E6>%i~u#v;SJ2RmiCtQGa6h7~Jgs$_D$;QBGT>A{j~@X`5UCsEi( z#3Y!C-{zVV2xEU8Ru=XdPiOM|{|^g08$hxGW3q#^SO&b*R-?<>eW#Dw@|Yn6u?er5 zvQC??I^b3Yl?q1R{eyQ!2n`bP~5^tSXG(^hR^#o0;~I69QAt>;HAA~jSxrT#Jk zV7D?v@xQ_HVZVcxr;i#IE1a?eFw9<8W%5P>20LXOaXlZkw^kqX%uZ2rN+JmW`ZlZJ z^m|da`h$OlmK{lYPhcp$`eEk&!NRP0ygps&^f#-`%UA`o3=Yh^ z7dZafC`&3;>%6qxfQ46At8)6P+klf{@&I!Qd$)hdEvrjFeN!ANp0#~+j?MNV00q=u z-FK|6s#$ig1@UXKaaua;6Sqz}t|6E3(VDRV`O5|-OA*6zjns9iV0Wi<30iMnoRD9) z*aoN38&1s8($1Mcg}1EEGlbQW{iWAy*vJ{s56&x2Pvg>g)meJ8T_~4c`x!|qepl1N zX6k=->;A}qv~%u>caLzz9mh8pcH%0zWzW~F#%3z#-V6e-FRvhyBhIG!{Uz#Qv$J%j z7DOU8+sXLe#a6w2wwe4Agg4D~ln@&UjuAjgr?&;m%m)j<1n$nT0PU310+_O;GvN&_ zCx7KZjZ5EpWF3hVe<+_quuapf4TOfB`M77=0_Va>HF%?a%WhlNmZyJZ zyER^*QBGMBNLFf@eTr|{WtI(4AZ0r6!{-YzSUJlhzg~fE*#%F-mdqtPEGA$- zjn%6>c9SDR1mg=-`%r} z<0&ima{65G>(=Y(C(39iS8Hcpw0y>-60l{Sm%?=QB08;ZcA-9c&vMP0*`N6B z-?J=$`2fMCDSK^ZX75mOwdyi!RqdkXHVFLNN!imBQGlh>M(5(!{a_O4FD-jdW_^^J zBdx;Lb8I1I9xBJv#q-=Yd$NCZ5V^4$cG(8#U_bKMBwP=w4*kM1e6_G^TBO5I6*s2i zD{LP8k&Jtmfx|)B(^jx7MTjasc5-;I$;rQYo=2=f1=}io!tN>C2C^Ebi~;f`7iSw# zZis>d7`;em-%K{k1iHm|{J{sjUs@h=a$~iH%@~4t@4D-VU?oq!8J~ZrAuJ|VmM9!FwzxVsh=?w%pMG$7tgb{9XLmGfg8D%amHfB{^H#=@E<$p@G>dae$O)Xx1);V!;^y12hQ-q ze};C|;TLfj;VmL_SXxY_4{A=8*(88@&lneH`%E!KP!jMNHf+mDEB4$O!M%6WvUeJ7 zQI!vb!&l>s4%Vf*Cq>XN_MVzN*gkF14S?vq6b1SHBG8~*$*$8KC zfaO}t_Tdkvz<+5Lw0laoO#!i#V)Ro@ZBsmQPoLpSU!9rwiM4bn_ z^?hMBz%zB~tgW!st6^!q&muAL+jMJ^vq(rZoqYK^{Yc4e;V27mGXS()Gs^=1LZLLt zfD>5KN&%HKN9z7yX2%z1C%j;$qzd9UiGeSlUiYqSCR}cv+pH}z;z4&mJx=RbX+-t# zS+UFNEiZqCm=~_V4|A8Y!Mb8I=ONVgVcVW-W--ev0Kx%`Heylt1&F?vP01_W3VbZgEE#5;11zf9_*Q=CZ=9M>8?EQJm zY#rTCrA$QuQlyZpASCe(5>csNo8;zIebqQrR>r16l&voCRep9K*UZl7@JG~QqdG|L zHFxz4q@x29p|{LhDqEUkL$A{{rGo=odmZeGP_8-0@=B2B-6}A8-*n0)u&)v7BlmSH z0+oLQj*MBBRc1Z0XUd=j)_OjGbtCSXjhYdGl8tR{yp@?YTTN9;)LY20!U1B_!h*s> zQeUQGx`of8fIH=ubF9*9_~K3Ll2k%K{NSL*05#ZN+cmQ~o951&`~^y~v8}P0YE@u$ zy9VKS{bcaRyBAUBWq}L9OQ)^EDuP?ivG#w?ghn8?2*5W5?UdO-@O^3wy|t66xOGyU z6c=mntEb4I9y2dScQ74^3O1c_&U!$}&Y})GSRU4SDnZ@MFcCF?3-hk%ml~_QD zTWajyGP^{rOps`w@D8iA4c>Vu-wY6!u6^waU7c`EwPkh^*V?x6?mUX8e#@*TKqh|* z%Ncdz!E6mw$Pk$N+2EVk%=!{|#uLpNrIDHXAB$aHPlW@yW!B~*NFVHAG7EfiShub$ zYhOLiJ+tTN@yb?dE-ax}IoRBXnY;Ja*5P`KG>hGO;>%+3#g-xMbRX^7*G6~CQz*h} z410Xn?Y0mTVt{^LGAqg088=}q7e0R#NKzcGD$fOg;n%J@dC^&4ow7l3R}6l$PMjZ{ z=(ev>FNC-4UDpnmq|~N91$1mTvjH!4Yi$MocOcw=edGxs11|}Ny$aPCT8(_otWwg1 z6AD*I9m>P*$6J7wOLC; zwV%R-NNLTlneEPuk1l|aAO|(WNh!iD_%{3aT{DZ5Qj@aZcmgKx0PK^!)_H+%Ha^Jg zW)Fd!q%zq^x|WW0P&!pMl#$auY+L~sLsB8RZAyEkITsVNPHkt*k6I>pB)Fiqz}@?t zl&4+M$D(9I;$+5$jjI`m0p))$wXv?hw*+UhZO*Y5Jjq9m>+H}Dx`LsBD)ly9*v-AL zhl<4cuzgRpZLv=`5(!8DjG?hyLCArqo1-(z%hKTA->xf%a-_z!Gdf%kZ2*rzkDAp{cCSo(VKUD{ml{-!p$}1(;fF_R{xG!`XY1aw3P1-@~q%UA7focL04JZBxy8ZJ4$t z8R^>Ef^}CGGo3w!jm$uvW>gz&Yq+k3qgI&0CabC__ArpX83H20&nde6Tr-QWU9WD` zh&jwsWWy$EaZ_(tZrwk$TK3{AT?0d0)qEo4k2CsUImK?*%+7yqFe%u`2Uf?LJ+-~q z?tbC?-ZCpK!CiIWXyE7Va8VgpqqMpY6((+(otRQ!30WYC0rXdD2h75jPJF?;wxyPi zqq`-;aalkR;KdUk-us0AzIOl66hWfu$_hB)MaK|3$tng=O1gGA+te#K2V&x@HY3-O z+rr;_>n>Zbt*w6xyMOsA!?B+RIFItBJ@TBP_tw^T?(FFY5U`GkQ#WZVl}J+R*AmO9 zpQD)NijTvt4t1@q;W$;-wy#mW769J>rBk*6?&OseYkKl@)hhEAIPIKgM4DP<;0OWf zP{EdJ*qp7 zWwuZ^N0&@zzBXM%E;1=MBf8?+Bo}~Lb^t2?j2&^Ww>o<7)REQFubHjH5Y}p@n2es$ zM5G_08-(9;EAVxIsm&Yzkv%zJtJI@IQ*C~l-p+4nuOl5T2Tt`Zv%tthZ7nyDKcLj?9quZL`vh0KXO`u?19Kg{9`GM#;qsvc%zWi> zE8c=)WtLqY87_QzX7!eMPImh7dd(+e`{)9OGD&}9vGv!W_gJ|bIQhEeE=E!lgV%?% z2!f2+2jcu3yNs5`E$2ugJEa3j!23^eHcnpPo@Hf9s>ni-AltEx@C5F8);I@cX|iJIZX5d zs!GgaJh$NaoXl2tOVo!SHHTN;U2C0EqLgbpdBQ2!+QWLZa%?rnLW7FnRLw{0rGIXA zjUugvY|s&QtHdX>&FQEF>DMmk=kh)T0bPH0QNcEDVDdGma{zY`3U8T(M?Tgk{-d)2 zIxeXW_~!Z&D!ewypzR=Alm`StPYXB$lxx&wg;HndnpyCl1c=xgusM+O?1!oQ#S2hf zy2a*afO-u4(xvvbySG%s!(x>KGSse_-JL}(mav~^%{J=6hT0zO;B?*lT10lCo@sw| zu)ONvyNzvdR?hf?TRR!-eR&`TfdiQC1%qY4JLd%m+w|5>W_s6*LDAUhQ=3j*9V9o` z*7In$u+(aU>NnEaa*IT)dtVA)B>;E*+QS+%Q@}T=VMooKVhlw>@?VRJcwiFv` z)YVF5QxbeP=twOfC?~9ra&AGmT|9cDs$Q+wTZlq4;GhwO&KkMgg6CU+8y9~FSb|p` zOP0&X*vz>xvrKOtpbcaUBq5D0VPBg`m^eR9X`XYtXZGOdPdEth=`{_g!m-Mk`W)Hk zwMkx8`Hq;pP-zB)1i`koV+D}vTtkl7IWU;Cz(vYVOOLJ*8&j|===QBJ&mxEh9F=xs zi-*)4^kfyGj-%ykPm7wt9%?I9I0brnCgR;ifP!6M7KQcHVo(Q8E0>cY}`#blGzgJ5d6 zy)3eU7s#y$Wa2m~=~Sv2oH7Acx4|N|l$Cw$g2-B%g_=vX14Dn#Ix6D+nPC)M^?O@t zmbQg;v=M%?Bit$i?P;W9y8AV=&Ys;f5{r6pnglSpf!UUJu(59WWJLA?9-?Ws3C|?4 z6SJUOREl-vTl^L~C`}*=2UcVyQ|^H^2IDZ)xJSS`@{y`p49;Su@P zB%d^L{-jz&$y9aMks2tKY*BFhLRYS#NI{)YMqsBFhdJp!ykOG8_HHra5 zWa^n!!TwR>vTUZ4`RHAl2{v_tQTkx}+@5RssBvNI>e+uY*wefvN}a-43$PAOv(+Bg z#swTx`py_bWt=Z#vcsaXM9|N*ZOxQ-aDvI!H=o)VWv?KEytz4EubBmSC5S|rpQmbp z2RkdVv1_G{(k-)1I#?Lh8z`}m*>8|Fa4QK#CT;;MD%6T$$7|En#_A*G!@NAiD1fVL zo^pfFC+vT#jy-)8Wd5aYwEC*Or+UpJX;c`9Laocj^Z;yTjoqTKZSO5+axC@MI=jmn zV2$f}X}qn>X0xUj%|;m~Q=KYa51N!F!R`WH?{Foz%$_*G8bHCPO{?>GZ@tw7?7YUj z=GB3tu&gX#Bf|v;?A@F-cZm%nZh0vHR%eGfKy-g&=6%z^Hy_K*)6#3{yDqNyQjp#W z+N+q{jA)vx2#b@h@i1=yQ^2s=c-u(|WM-q{B#o?(YCeBqRwPwDn((20*sGYcH84W9 zD5%%Wf_N3+q-+xhNdet^O<+SW*?hlNlnnMk(eP@adFO0p&dHYS_;AXy=ryyi3g?D} z9S48Zpmz`jz>4IocaU4C2S2^N(!aYGx2-^3OF;m8Wf|DDDjmn-j?zL)EN3@ZOm9ZK zp90=ld;K7@duWm~2V2@uU>gxK19_$c>NeYxz3Bdf<2oeid5$z1Yq!AOl+Z#{A*{hVo)|}`X6$J6rubCwl8Pq~3 zG8)?zGegO64vk4?x6D>*5sB{%5(aA64qJiexmzhfWcSP-tgcB=e7DU8D$xWJKs`da zSCsJz98@xsvsq=jJ3APZbO^uawM)IALYpQyHV|)jZxz%s@nr|=tNq%R>W6vkWtD%O zTIOY*!O54B$LyzHlZpc#0JUI4HxLXU-tY#P;HRI$4)fQ(b}{R>QrUPlW51DZ2EN?c zGHYCW4i1B_K-|h}gT)=@1LGhKV4~Eqwc?st1^u_Q>{PfVxapSQCotodKw0NCvj?_( z*F0;mO;bCvmj)$*bnjdEBqHUgF=v0BE4QKSQo!bC2o3mCyXG$NT>!fW80f4Dlw^ir zz?U8^fZxyUwH;Xr%_RVC!mX}x+nt#bbkQw?^<6AYdMND%4VwhBj6@pwB-aW^I(5}k6*QJ z!J8I*w9Kh1aAZ??X^F1H9JJ@G|I7ZL|M1;6-+t%M|3vCwgPWW~QD}-{^i}d&h^YL{ z-uc1j<5g!m|_u;?|6mu8zz)to7r}Q8o{M;y5AAr!9IROrzd=wG2TiZYo86a`r zF=}O530oNs9-rLypf=V9SfhXZ>!mNH3+|TC=>QXlV*AjK~%N3R5d+ zXuq?O7QPLzc~hG%Ww1M?=%pu2uTUH9!4k=z8J(%%ps-mn(+;q$a8%B#8cBwZJArI1 z-qi43Bc*JeCAhsPK6mFnW#5@zt<#syvjG=>s=1u9=bluwa2#2inVmTA9GT<1kZyd) zJ8WzUBxe0A!)cu<%N>v8X-^ea7lm{%2AMOy{__ui0%Cu-N!`zX?5l;E`It!~`_gQf#8v$zkPRlX^xU(IpKc8XvjbUw zWvpLL>~GDd9V#;3w0ydhS-S6F>-vt*Zul*=I1#)bl==OoW%qWD6*dO+p==;unPI`q zy3rp5DZj9cxVcwnGDibML}V4y77GNlvkle7*)A~#qMK1v=m4S26!7+*U!%z9;%rx@ zl+Q)9-pp7Vk=x!$t;QL7mW!6*=rj9&ZW++>r|zsw28$d9sCMk4Wj;nu(*Pdy#@=H( z5e9n7Ok{kpSo{~3TTw(9in25XI`dr0ID4=Oq+!X^Ma#U;#v0EvUhnK|B;HDD!q=$v00 z_3GD{vC^@Dpf6hPlwQbdoapl;9c{5E8RZFNJ;^YCX?fP1aikHKWLX}kNdQUKsO)RI zF77aVU0MeOy0GS|wuYVElu77+rde9PXBid``@QLAI@YRyc$3etwJdGme-|xN2+zFW zU^QN0_EKwFtTT%`_k$e|eqkB=>7`}@__cP+tBA8fWCusl9(pl8!*d+CjJ2ubk|>Q3 z0A_IDtuTSB-m|<@sp6&C-k~!F{!tS4cB|Or*nk%;19@ec;d^fYuL9U1nP9rasc!6=zWh}Fuw@P)Vc1{GXTHGJy9NdHi3zlIc788w?u$Fj{iqakY;l$i zjj(EnS!|yp1wrhdWjK=Pr4@FuToq?I9k{at4|8m$bkTc8fKg?Cf^9jYti0GBd$xu@ z6wulSPt^}@fBn<`>D&L||HkUIFBYeRzxT?rVow>Mw6m@eqps6Q0%5M&Vd|@XX zMbEnB*uc>^Sd~%`g4cP+UZ?}uHO&RKlD!(UC@GNa*vJ?|KT>v2p3u-3*uHUUGg zGPa3Q)~LQ=2n~#>G-_=FT2k)2r=?4ZFl|3P-ZBKn#&F*2Zkg^t_fn34Q;hXwq0es* zVK52fuoKXKIv^RqfFRNx#=9Y4JSf}s+e4T`S7upe@Twr4Sr9BdRmADkWxc~eFDCx0 z;P3Nz+px}YDEe)^JMoutn42MIb4u8Hq|TfvqR1#ZDIG1SaV1fr&dr*}XW zJC*f?APChf90PVCa9qLxVZEuoV>@Es#mXJ5B!hpisML_6`WwPH=+iq8^s%Z{603Ql zbYra?pj=ukFm7Ydw+unB9f8tHoXMRaeNqr_~fc5S;l6VWyYY2C)_3GW2O3zS%@(M z7@-|@drV<_Mmrh+a+-Ud??BMuo+o=-vj1b5s-;V_EPJxo&$xXk|N1AtZ-Jzd7@*fu zQ^D>JkOk1lSqqa4n&kAJL6q_m&ly!!d!iVBC0qKkCM5$T>w5+<$WasD&6F(3`mFm* z12AKIi}{v81$eP+)2GQ0S2uhokO6es0LV>tsJ+Ic}I%5Ac2$CnPnRex7?>c*&O++gJAvRE?Q07c~gn+Cz|v$ZX&KERwX9WAjx z^HOTGzh@B4)ETB$O9(}^*DkY*b+{|z9(l_krnnH3_&AMC%HSul6shb!meNoI1d|z^w#+%WAj&9y}2f@rxvq+rW)o?R#6h_WbI_{2aW0`vd;y zpT7U*8~^dbk9?ss+r!m)bBh^`shxWbbGssy2aCIYZnYH~qxnnJEuA45C;OCXO<8c6 z?^yM&*t*+jw^-PzsZkFJTZjbgxkdZ0-~afh^Khd0XFv0W>@nc+2~x5{r>V3PKvS4j znGaSUera~ILN<82DFfk1b4iGQ+9`R_^I#&_mu62|XRLW}^7+6%&Z%A4g>U5bAZh)= zY@WVhQ*2X`W{nJ3(3kL{)zX6~^$W9(pkIzT7-}?p?PjwwDW$>5jeTovb7l&<0QFIs zlN}bZs&jT`&h%~NlG#%Cz#iu1koJ?jr&=2LBG|ZTc~C^=3$xv~+mTs+YZ9L)B#qQ5 zTYOe74{GauVU`L3HDXF0h~h(8wYD^HSiJSzRZCT?cb}91d$J&@UUtYtQ*Tq-X|p`oUNN1c6U1K;QY>OW`${qGN|RQ8^83*R45OD%Sg8-+4}POy7*|# z!AEp-aOS!Y_hn|g6>m=hIYz+CWpp^@4Lk!hvp`|tFXNhjmpZR% z_?NdBc~u?vog6f)betXFayIosBm!nPOS!#k96Ao7LPH3|zMj$s^YNmx_0wwU!8(wC zXBg9u{MV&n>t0i?Hv1X~&Yjmhqk*TU z4hs2(A>_&~GdZSFICmXspv|QYanRR(;vGW}@A<5D;OP0%znABykiImFH5X%>Sc{(l5$dt3zq;HDDsXWoZWjxyjyLW3B|~A z0A5ig!DruZ7(#iyl1*$paBGUif&FC(&>{q6?2LB|A$E6v^zX6n$*?N(YIMtzV z7(z8T+GZ|B{o|5X^}28x*+iy3DKY((Ap|^sL(^bbEK>)dUTl?BS=Qg%c*77R%_@cI zU|@))q)61J0D*dF~|kLp+`{wBpdUPWS;qs6Csj+ z7N}P`0|05Te@IcbPuALnm8@?WLhI$6I)KkIopL!t*>13vG}3rSj6jIQG*I*xzB&WD zTT38fzOgy_%H_L&ixs(~IKcBTqr>$7(ZLH&O- z_pZxre?CRcS&j*J^s07UQ9wt`4_lTmXIZw|a(C~Ei5V?iB_2~Go22aa`L$nT zB4%E0KgnbQs47&kNRcv0&)%_nTgAecA5getCK3s}hs)p%ba{pzOvWmT8DtrMC-fwJ zfe=(!RR&sYj(0*6%*(CuI0wv3X?_X~8h2WhC^Lgcm`YWG^#Bc^3-r+&sZP=g+<@gQ z^Bfcu(4#d5qv2XvQIWte@)Q&>Cm<|Q@Jh+>Iy`881)l`4Do-&YD0KUxVghdwNG!(gZ~p5jW0A?yP5Hc3xHp^{+GYg1&<90t}YM#`!( zx#7g5r9Q==J(Crh zbbT^nm^ldrO(bUwriP+K_p1QSiD>vB6s&$lPBAZNbU9{!Ocn&DD3}tMPEm&`bX9<< zcalM=VU=PU<90F7MCdfZ$V-g2Ea1C{Q`iw&g4MzlCMpM83MK-X0)vFYw_!$|#G2Az z(B~4CM@+&maDS*M6inGX&ER9Cr&uX9W+%r~+Mp(+)PPvfWs?+`lx3m$X($LuC1xim zOI?;F=B?3xG^d*wTikTrxZXOklMjxMO#Uz5qI6nJQQo(5S^j z3n@l^Wt2*c_*SPFltz?=5X2&$KF8k{*74Z|Yj`mAu6#Z>RJ7)v@t0N~B1Q z$(?Qf>tCGs-j#~i2*Z3aVq!;C}0js~Kc$CrSkPH`CUOu~FFs3)q7(}XIrUDBkBPvxSI|+##)EzL93s3|F zHKf9ng&D&;MJjlf(36lT(}KaOpTm-;Y+6;RrOZ_&%cKA^JwFWzOs2~c=nU|`QWhCl zXoQ0ntaP3dcA7o`3zA6*dQ)@5(XkEcC$I1#Qz`H|j+2nUYdq6j6VQldB{XLgBl%K) zk>{WiLO(qX35woaQyE^e4D`SREYs_u?&o5+z7W@Je5>Pttx&R5=tc)DPr*4OiIC4t+=doNnt8YBvU6LVNxn3%u0zM zX`bWQ#C0^o}|*))O&(ei#i zpDlWN{d!Z)rm-#V-#&8y@7`TRSMHI={N;9+e(Vu%u{+y;UejBf=7dRqE{!%gL@Ldg z$uMDfRi-Jy3@AGfkq}d9mSR$}+~hFMQo|%z@t`UgNnlQ_9)p<+C5ogw@XS|?V%n5=KXXm`DzSPkXxyS)-hNNZ?Ey6&+tF#_2vEY7FMzA zcN~^*`R)3}?0%~FVyu_fALbxp{6F#6ms-!SwEi4_gc9u%at*b3|Hs>xZ=YYk$dcsx z_2uu&b}nn^_=VGd&W|m}f7ypfd_JDIN1NAfIa}yh&OqjTwQN@4wy1~E(dt%5cc5-e zqVaS!i+EIPCXu!`aCc?=bw8G$DkR`JdKShX`Tg2ez9Td)|xVjkCEu?IT~q+Wzl zKiL;Qeu~_^-ax!--;S_<87BA3wFc|2?f&2K3fg>n zXB7nu>R^< z{c|54KW|fiw3YD*5YPQ%6f{MB3%)8!0+M@I2Fru0X~kjrvo7T240V|4ibFqHMB_Vt z1MQ|!$y@uv3$UaY8ow_}Y6>-D&i@@-khldo+XQa~>%UhK>Uc1(=!F}I^IN{u%MHzW zGhfAg1w#Q}ZAAl2jJjhB6MLAmK*;M>$ffGwSGUcJv*jw@zF-F9OXczHpgZy_+{w2PB8M6J-8z|paxA3K4 zjd|ACkOiWTN+u z$(3jF&b~fCe9hc{T0g0qB$`bp-+ubeN~}2o>Ib!y7^MtUXU#$Iw0_d%H$v44)&&@U zb9XT1aHnU?j9r^<=J&Se%ZF9T;`&N*?6%kEe?!ey*Oz?3ClfsxFYm6$)9YFziorat zD+_CIPjEalcAW&lu@ii@g&ydej^5Tv+`^doF||O+J5-}3=;~or&fcK2AN?6unAG`t zs=r>_mjVjDkd^&T3%Lgg|k2Pg`*gAmUPjX|j5xK=&}NK^l=CJK!L6wgd&eUVQghps`^45CkC5 z^ZM_RyjMJeWpaKS{jWGA;h&)Mub^WnJ=aqOuMJLmr#0GuWNb;sA;q|%*i4>(zrTDQ zz4o=a3~TeUsZBj`0;c|=(MH(G2Ufox-$wZFb63>DELZT=?smsktyRMZnR1~H@eEg|>eB}^FN{jm&?>0f^da;=GbG^0Z zAs8h00!HQSY=-)!7l;sX0}*?OmlpZFK|Z&Sy+D+d4eK{MNkcJNqw2h@G0(H}TIFfv z+=JEvTFP?uNI6(OcI6v6za!=+eCFibpt5cFUz;2yYP{q(Hw%4#V{KIQ>W!rioz84FzrMo8gxPq|YO0ZAK(43j z=wsTEc(_K1F5`p2zM&hOY zan!8Lb`xIcTmEI-cWvPiEhozh$);ui(}3)UPj*-Njk#wBO`#oWsZA#0^gD zab5%`ZyQ-x_MIM|UNpphB!a>(H=vF-me@tylWn+xRqy(e+tFCfVl@NZadCSu z!U&I@3b=?5*9Xz-5>86dOZyfKTPQW!>{Zw(blvv=)%&6+vw2qzd^P8C7_H;(?A3U( z1GfFS*{;Nx7Wnxw!aP&Ohwxi_bou zKYw{~-qxYjB-^>60gh|n&Kexd5HA`ESMJSzo!x4^L6cp!H_OGfmN3MuM(MKfn!pB$ z<7u~lpB`4xzzy_4HYhiIeKe@8@2}ZE>57Z5JkV3?P##;IVDi%jX-{?d(j&}@p`YRq z^bzc?@8;uc+%)Kqx?P7xmldGJ9<3fRZixefak8tm+bf33t9|4a!rv_tg2QSm?(wT* z&k8oUH@l&l!F3%JZ=}`_>?|1Iy$nR*4A^debB|!TxNkMVo-sNBO-#qr*{b$=ja5c* zHEN3hz=Ch+3KRIL>2|Y^&*9y#)5(mh2v*y%;j%x~42>sp{cghVcyWElq3vL?zSjI^ zqOU{Uz{AEZ?8{ox^ZL<9Ew}-rnJ;eiD)y%9p3@0b!-9NrAl8x_sc%z$H#_je0Fo?! z>`1c^o*KgnTB@Yp7eEbW257rmDTIb#|v|+R~9(`M) zL#_Lhb?-J{=MT!ODc#}bYNwU(t=1R#h&DsWPAge%E#!G1Ic%k_M(`np+g#Lxp6JmnX9$j zxRHClBf+*N)^qW5wEQ~0ncPR_u@RYOPUFAsIm~9A3Ag5Ly%A1E>}51mtw-YL=<4hE z^}FArS1xX|%WpophYoVIR<-PZyo@fbOZ%_@TtK70WrG1H6X&k^PG%1@7{fJbOw0ax#=GLx?<>_rbD#y0CzieqSUySx~&?PoUIkw$N+NhQ0NQ)e_*taA@@jA2sHn|c*FQ447QH`{rQWXitG~~Qu6PI z6jk@$T@zX3;81ZMK#R^BVgLHWPHpx<9isxTF2JVouC3WrM{3M5GV2F!sI;80PQWRy zIh}XdegL*F-7h2WjoItq$+;`jltsUY_bM(Qbe;G@F+PdwLLL#i*T?5Ie^LWKGk&LR zc`ustwszC>*S+`5YUwlM7n2s#hl@8{K&;!oxN60^z1m-EYWvx3O~W-+TMtDGw>-8- z$E^p$?Hb>I5xCdk29*Ae#B6u+LZBvZf@czRF^!^Tobr|}y!<~S);Hzxg{2dhY z;BN8u4dDjo2K0gPHTIote@(XbmJ{(BA4fP-tTohHiCwzHLxna--PkF{Q>FhNlw^Nt zzfL_&@U+Wf2AYnW{5OR!4nhvbICjvxfL2LU*R|VkBWCZtrVZ?27kAdhYGUraCdgwn z?DgI#rg>vPzy_>qzWg?o4{PJ!0@Jt;l z3Nzo;aGU9aVt*#2fKx09#hk;2zfN^E~~O}Hz+k8qr;0wpOp3X!QkYz#D8xai}ec*`l^2Y6X>PWF=mH} zu5M>vC7zt@mTPxJ9-bP9UiJdpUtE}9XOz$8cA5E`Y+tS8iv|&C%pl}v@`V|E;U7FlA_dx zW3Cxf$wa3G$yLRQyx=MkbSL~LYp|8VB-ts|c#}Yxc)Nm!;I39C5GbtQPg zWIN9P07E@tP^)AP%p`n=)eZx3z?f5vu4AQT)V0?*Nn(gE~@F1s>2 zflccud(wEaqm;>5j#oAa#Kzh!_lpSFSRQxu{f{;{#D?uHgJ=Qxakg;BCGe2#a`J4p zv?tw!JrRv3Z4cUgoiw*~3({hc7I&nbcNx9CdiU(Z)w>R(k>L|Lo5m?k1S)~B1j75E zt=(oxe`3#FTP1EhT@?}k`qw{g2s!zs`a3dw35r}a!I+)6!qONX%+n+ps^u#y2Bf@* z-vF|!Lm(S>fqCp?$0*w#y|#{ilpTX?8|_Zw>hIWzjvLW7Aw+CNziJ>~bgF|w?Ky2* zowx5l718rQe_OB4JCFIoRp&WiZf~Ma^Bkt;f1O%yuTiHqK=iLor;P42bb;oG%B$z_ zvgYW;40}TaQ|@B?_t3!<|Ms%}$8}Kb+7tSX0C^2rvo+kuZ+Nf-W?C zPi-~Q+wsk9Ji!3!PMD1oZSJSmdBr!y=DG9V3;lI5ZjZ&a!ff?gVR0+06Z+#CArSWJ z9U{D~>3(eKzCna{mhRg%y0039k(uY&e?KELPl=s8gh|P!uQXq1IbJq9Hdr#of_5ge z1z%kv*sDtq_Tp7aKtSP-CjPot(o85p%aW7yh^Z`p^G23ifL(wWqhUITZP6=QgCVD`CN(zHy~3R2?Z{f9`Ji z?kN)xv5tALB@wrdad>s{=DEdw+y|lU2cex0a+E-c{!=Tp6CSZH+Sv;c2F|YUQEl7o z>I;iKR9r*#g-6~tfd$RJV9D%|;1mVbuOVig(sZr1hib+r1MPM{nS6_ymm`=!3-*Ea6y$L+=<3z(HH zi&x0#`8CEr0Xw@|V^IEqgRC904fh9$R?467?@;3M6c$~;V;K@zdM2=Rf5VvAhYkn~ z94`t1!V>{bN_=I31JC|o)F2pB{&2)(ez5Vh9yy5CV=HGUdJvhswr^a#f4dwVF@i9R z%nRcM?G~TK-=3djc*pS{_OV?G>#QW}dywlQcFNJR)8^wkfqs^j2X`l3ADTQev4Ah_ z(h9uxP&TQ+O=pW>hXXJn;7Z#Zd%bPHn=PAlI~}oUH~zYE;vUx4UBR1;`*yo?=UAB5}w(JgB_j|oNw1r-G!)b_E6H{#i zX&T7gx27I5{XXf=t=$Z!yDOvpq@`)v=8LuCr0v`P z@bAU-d#`=DEBE)PLv#14JaLmr{6=&2Pyg@V?)BoEbGp2SC3Ef`e*}@lh!buG4om7~ zoj&{d=jiq2r+Q-$L43*#pJ`oanroRA3NJU8oT;iXB-d4y5yJG&mpcHi&!DlJE3th) zhOy9)`sFr2vUgG7{`7u;zE}tMMGb}U|6@6ux(vfRL$^g7?0<*9&pZS|{$;-#x}=_d zEqF?HHQBJJwRq8oe`ibL*ZR$(J^%B!=;@!ub3hxRvr$fF@^jRNBkmo>hF(Jp62vrG zzu%cfzGxnfTo$~>!7!9ybgM6-_s}I8b;;;HHlQ}!XkU`g&-5L#JVIZZJ8L%Ty}gg1 zCz~;0xM~&sVAH|VaJIv1&&e7Ox9I(a88Rwh=D;|#N==5jShVw{T-9IArPlY z3EYvAp6#DWPRDLj9x}l%@?5Vq*+}Opr0+Z zjO@K6{ElaFf0_%QGUI_m^XR8``5JvQp^Lkg6gx?An$=AJXrM{T*xqSUOY*rrLP>9S zCj733dEv8`gxf{7-go@(c-7c&2i&Bwb?u?QS(oTpKo6-;CLNkW0R5&X%L)IojBYn< z-3)%fFU#1z|Hc=_?m5CtS6}%;Z(10<8z&C;3!X%8e|)JCe9Hy;Qoj8f&1bX8KT*E? z?9_$1%@@C46nldgBV26J>_TM0-n7y#t+W@dG(6}u3jEhfFUL1%l(tcq$JmVzoY+oc z+>!WZE1}Wt>}xb$4LLJ{} zStuYpi=FUZA;-C4b^*++4i;U(j{~#;+fPkDfOh-F0PXj{%x!1awCjVsdu`BrslKci z;|}HaaC?WGcRxqn5z#wNT}vF4Q4;`b2l_Fre|w>J0D~*c1h+#fn8(h>jy~p;KoT7V z0am;)b6P*b;>~vcf#|iE2w!!dHQ6q!MO0_mh<=WI@`i4m2hxT;GHZvgv=i@E^&+lc zk9|sqj&9_Izv=LHa-hF9ynXtIPR=J+w65|(&+P=MPvPD5^=xIn>5*ty-M9U%&O+)O ze-f+t(aww2?CyhZ=45-f3CMoa@@p~)hWtQSSO=W1!*Szst=Kmgdctv+7|-F)SL?ft z$Eg@DEuEB!ZZig}=Ly9Dp*P){gd-@Z$wyz4=S{)72{5g$>$aU(E32-I=XS?4+8FJ0 zz?7rD0f3GlMV&}3tMGU_o#3lCZ7tjgf9k|lSv9DxMesvic|0@sIpSglDs4AC?619p znqU^M-Mw`9+FL%c<;5 zmW(KoD)?`%WLD6!$W!?!(30p>=u)dZxG)r-U5^lxI@sX_9A^DXM}S$qcEg!f>9MvSLYo9I1K5HC|+2k&;&0@Twx* z7$r-oOvYt;9I2J6lum@I5}jrhf62-+VN_&glEOnR$Z@1fk{VTMEmNX3sg&Wu7)}I{ zl~R=R<4D!;NvV*W=g`1JaIFo4kt9=1QVH)rPAbjvl!92E5$OIPJIfPnR!MlGn0XW^ zDPf=|L=nw}ObU@m4$T5RK~hRhp&kb+Dym@MXIer#(In-}=(11(r0~Q%e{L|LYb(`7 z!pfwo5>}BaCluxuol63=A2;lEfn86-0Mr`rb&^*_X7aLRT4pfEJ`S`jDHn_;CMir- zC|+O>X9YDCND|r3pl*S5pb1Q%1tT;kQe^@LYYEeGYJj86(~K350xdHEGqI9}r7Sgh zmcw5#Iq(#w?m{Q*QJ_^ye=5O9mgST~H()}lDy5alCAMoR9tFx$0vw^U=PH*b&7omw zLP;jGs)SX5JPK4Xp3o#IU`7&nf+FQvQo$;!jYvzf$4U}{8d+7a6jxQIjOH-?7?l%K z8lDhc<-70uj9mcuZW}57<@h%8J@J>@(fE=3J>#JbpYiK~9iJu%e@680W*g2Q?fds& zp84)xT~j>nmu@qNx4U%yB8@?zcY4L~vWG`Xt&0zdz3{&Ua(Oh>UxUm@HR-)%$AA%B zvaw!q9=!)C?fn{S^>+%Q?3_pZaeE}a9PwRRy@c?cGn81N*#bo|f6UHy;w?K;1ITsRxGDR#fqUT}4N0hd#%fdEtZtCux}3&Qtb)yN zko~GFyKxt*U>AFUkJ~B%D|4s(>>Ezo4X|_@BVhJ!%GbW$TrHPP`P5d^UXf9eU? zQ`*{2f#2o7{`3D{cJsylF9u`HSJPh_tv%o9B?xj0zVV$nK1lpG=@*5~SvX^f}e|`Q^dmr`~ zPI$uxl=O~*$llu#{r0avJQQFrS77Q7%wZez=f4e#bjv^DI-jt7eV0!tpuWf_e9tG2 zG>aL0@!90Vn+HEja-PdyEfDXl-S?Cf6_fdOWYx;DW;-d(KtYKaVGXB z3+T>BAwK+r!X#$j{9t9<@DuynpVS7TSbEDl=$5xOnic4Q{=5e#8V9A30Ci%o?9<;I zCJ3WW7RJpsyA{iQMl(plnA>_AWNF1b!|?Sw>mZJl6=)4y4xV`0a68=-d!4c?wNXU((G=8e^D_l-X3rokD{<@+y_<%K=z<|DrdVI8w)YqXI(_jV?LseR3oXET?(}HJ=vMNg}QGExrOtdmUwj`NI z(xS?Xij-i$Y6)fw=X zY03--6P9XGWKx?%B-JBPWyTU{16q|P9p6t`YQ)q_z1msSJS6BpX zuCOK1+?wOHa+BrGX!dOf^t&rK8ZReNkuVa)5grpxldOoI-eE+`6tzS?UHTQz-{AMt zf1z)rSWaS;Z;uV5^wiS`z$jR#m z@?HI0AkG8zb8Kz>EZYa`M^l#l$nS^pcmIB#?H=DRs9#o+=;`v?6zm3jUGNDi1tQ}{ z;-;EdURMpTmcCPHcO0R9-wX!mCtqyze?Ro}^Vo)JV6@Pb-|6Mfr*VB*e-hV~{qO5| zBbUQ;FlYBkT?URvo!9$cA*-6Bi#rOh9b5i*!Y)>-OUko&TQB^WF0&UaUMWe0ssH`e_G$x zKGL_&MTC}b+-X*Cl9sv7*}66$mRWYoL$8vC1z*j)OM&83T? z^ht^LjM^Od!NzYcT>z)^5qap|e+Ai&$)#iRB4FY&7LOi(UH950-D_8KuVFuA)9faw z8v)vv+BJY03fNp54^iy#1#H-CfYXS_CJxV1G?EW=xV&Mo^@MptXX`QZM~52rf(t=f z7*06Qdi%EXll}W|htcj;d9u#l{3|HZf5B_B#iF2Yl+h03P#J+(piQ+a;#mLqnn17xKt&UR*@Z>>IiFn>;Fqi;rx8 zUG^3S{BA(n$fiHB_b>Pa1AC0Arfi*@AhM}Y>`e*IAGUP(%Y$4{<*1fd=Oc`G*Z@iOTvkW$Sf*&@udEtNYgm{zmyPX;dWr*n@7*o!R_R zQ;fItZR=8f<#8I@vhPBu7ky+*ptDb&mM(aV#k&G9pU%1v`h7y^f4UGF2*HeMk8C0= z`Yr%^(Sv`{up^{`0y#c2k$x?S77% zoY^nM-_YSDCa57q|bw^Y>uVH&;uEdxequ1IxpI{Px`6aT1cNTp~Do zw(5S40j*hF{2e!fe}mIvZft|#*a?nNaC6m^7aZiVo4P|kBZK=-2MzR_7_DcP? zsn#~XpGDeK11rns<-;j+Em7@;ZAyFM65hqx4b#)sWjAZ-zC@6MzXs{*nsqkx^SEkxXd*nCd|iXFazV|)64E37HlxeK5Jf4RA}25v0qfUdXM@LdKd z&Yw8g;}9WA@}&^kW!f5bzF_E6SpT#ezoLDw5k3Uc{OEuXu@e%vLf-YH0*%>c zeyjPWJR>{Ye<#~Ow24LDHKSAJlf~t*IuCzxw!y#vfKU1 zn6DpQL79ktc8N*c4GB$l?Pn2CsP#mLdh8F6c~pYWj>%Gjj}8QULV~f1?)ZGZ`NOvr zwV=MW#(0R)6|>+MeY8<AR(2A3-JP@TZwe0!T}c_(?n zdG+SZjT1M7X{A}q8Y9WPb?rj)e8_QTgi3TpIjwYAv7*8Q9fc?pQ>I0_a}@hSazsfI zDbl1;T9|^!tSD$fG$ovHvq!XiBgda;Daul3L>5(1(lQ}jm4!^xBH=QrDk2{Vt8s5Q zD-)Ire+5WJFv>G+(wy^@(^T&R>$;q8?UWe>stKosW`dGZNFpjxQYCVuh}j3%IbF7d zhHmIV&V|!0_pYvf7q6AG>s(dC-$qS~`uWK|$EZi|8QLd>%;xf;ptYXoCGR)e*6(}d zV2*8XcWpcY`+E$6t6N)?@V?gOl=|q{_sMR$e@1rg_E?{|F67g3F6ikE?)74hId2cG z+n9T{O~<$3@NJs8+TOB;Xuz}MV>oa5yleQpK>l$PQ5D1V=x-g}G-$rIFVE#zwwJO+!djtJN{Wmo9=1c>Pf?raZvICk%G$@ZEvYB@Z(E=CErdFzF4%r`!D9p zfBNRV3q<_n5uY#pZF?h3DiBz3kMHo^bR5&EaCG`Le;^&}LiWKu4INw6rbaHL zyYbIsjha7RVU5t`>>R`Jw}Ze&8Q@`?jK-XXDDGVcV$U&o3{X$THbuxITC`KvL4OP$c?tJ(h0y`K+?JAfl;2$u5Ag6P z9%{B`6kCjD9OGa6*y%w5e_TZIuf`G|a=mYwyWG2*0|2}i-a|g^-8lNwKK^~5r^rJz zM|3Yd^yRlt7TO=o{i%^z^Z6d3jZ)K>TCd@2V(q*a-1C5;m;>>{J9_`a98E1K=CJXB z#TO4q-9*a?!&P;*W}SW)HGdAv17GYQ9VrfEwVr>A>mS_aigygVfBe>{FZ?i-V5T>y z1hexED!~j4j~$PO?`3F#ZqPu7QmmtgFF-TLxH%o^`7zYiR-p6zv;y&(!i&vx&M!l< zs7=m$d86DW`O=oW5!vwO@&WmyDmw2ai}D<7-5iID4(apDEu>$g<}teap(^|no3jl$ z*s!ysC1C>zE|VY1e{+fXtW<1=?xpU>l8&FKm4qxhvMrll#)cj8JRXc*FDpYoyCd>l zXV-BhnU2BCJ}TQ< z2D19Y{d;6@n`pF%!Fbp2_qv5Lnkd+)J%)k?NQo$Kk?) zdv!4%g&)J;e{pVg$mQgIaksl?FX)I4#i^?f<)W2w70S56Up)hNtcb!7j@*w7AqqNZFz5H zK5t@Mto=0SQcu6w>15}Gj7`CY4br(zuTz^==K6Z@f8@oM+u(Nv#3!G>T>GO%2NcuX zau5G@K{AI1wX59qb^YuB@I%KL9`nua`mVFBY;c3gZ~QHHIo9Gz_zk>evtGV;K!19m zdLeOd1NNLRN)=C@*mj)jx{zDpT*a<))*w+xSL zb~~5p&%WWJGnP9=c3|1qrQ@@d>ay>LF-KEaf)-=Ru}Avgl^qihH6`0P8oc1aqcx#0 zqv;ns3Gr0a?yX%D9NBVlQ!IM_2VOV*v~iRDG@1!iF1(Wj53}7Y@95_`XT&kwIDtfa zfA%A`5}TY6ANqt|UtQ3D)r3O6OZWS1iU)Z&=JGgl6_&0JKw@i7j}QCOhKgdAF`Kq< zA;$0q==eUwsE$|Kr7t%yaRcM~a~-<`+-gbB8%Zu|sg7eB&5W_h<@G$mB`Feog2EQZ zXxy<%qYqx*`K1k@k6w6rmWYq2U(H~8e_E~vPmXRqVcTNhDHg=250ZY^gg%;0Pgwsf z`Y_#4efPY!2Oc;-;uP*{Yg6ypn4RwZU6(p|@$Wi`{>{JZoGgLh>ff5;3?;kVw!5@P^ZH<` zG{5%Srj^obp*8V#4`J;T#e+O-JGJ4}n+UlL421vS2&^%)S0rN;_Gs3a^X)}0U>yef zAru0mQH^=ju9P?P`{l0@w?!g_f7(6PNMWWLAhkHj&Q;62b5ly7FGGVk=It7f-mzuO zZHX9(+qMdbx2)QWV?L%~=qM^7mQ~cS!Wc?ukLR{X^s;V`mkq3KW+<5c5@EiBuYd|; zxXzh5y^)cc$2Vsm!mD zbw+fz9>A2C*(i$sHr?(=zZ>e_=Mn~IgZ+crgoXdm@UW>)yHVM|;{(ps@M1vN+{4#$ ztld8D&p+GYIUY(B`v}H}?`gZuEEWX7D z=xJHp2(@rt3r z9tzwpT?wmfyy$RS>#M6v4R%%nyh+)v#INrTMwPJwmq!jaW6gfKU&Co((;hK zkj4+KXg@`r4T&Drf9}rk^mNAsYLW1-?yC*mrCf~XtK~BleyL|4&!4}%IIn$P4a6M! z5N;gU3jicKbhewe0~=}%!ruUZ5RF-T*@9m>@Yu*iNCj)6-e(H3n?lhYpiuPN;D=t9yI12~;@S36(?U+Qgpkgae|xsZvFV)w2GMK$p~J&k_x3pb&(ZSh_-1lHxDtHFx%%*R z>vOP&>z%A-vFJ0h2kn23uD*_6zxzF0Hr9DRIt{>f^>2{1mo-e+=LJ|}dF;dmYg9L7 zGFYR%f0o){zM%?7k5gK!!+PM-<%6WwdHcrNsF)wJ)f-uXGT-O(Tf?W-@cZxhGz>QR z=%a_?evR!!#x`f^rV;6qIoNoFjpK2E`p@W4M(>Nw`tRvmM#IoD42R`kGHe9S1>o9y5)!$ZZLq~D|6wUfOW1jo;I zQC&6z`9CmKiH+H`xjJ05JUp7--}wwCdo$b>*bhuc9MhfHOA2jL5Er%%kKW(k`79`- z@0ro}u7AU}l>w(e_|f^b<4>5r_!a&*dUO(%$I@HR#8Pwf*^>QEfTadA>dKx!xSKts zOb>aVS^zsxvGa8hNAvMq+rWy(8&{`FlGe$w#Swmh#o7yRGCR~OofqD9kzdwS8;_k| z=B_-|j_-U>5#126=-%CY2)WjN9i;P1A33Pp$$#>`@*ueUa+rhXw%qr~iGzdUv)N?b zwe-CKo|g_4(3dMvWTjp%!;GVki#G0p#Vy$71}UTYPB&#@B*5mazW(+`gV}8Cx7(Nw z(}q9*=I-}&?i-`|WH2H#L^+{fz43On?%_2e$PGGrZyv+lBO5<6yI0TrA23JGXR7I? zu76lld@z9Wa5~pNyqqRR(#x;!1#5V$=iYD9rtFbhrIxmyXun0f3?z1w>^JY!tgZ)J zXUl~e{o2NTq+jOW9t##j(HhS>%6I#AJy&y69;1gk-^5`C-({iyx`$4;(h**!G|}qj zdtFcgX53<4hNAveKkhJC?sExgh_~#*{C`@{MBToI%9fgao!YR^q0R8`+LP}vh&_RB z_e9;WCQ$FFUv`Q6n;g1bc7Qlk*yhXLuoJO)p*U$_^0(k_not-{X#P~%lrM5sY}VfUS!s+GcPK znr9$-5tw$&y&!xMn+KVWg7hR0jN0fi|Jy};V=!=pw48piqyjUGK!Gie0B z-z<2vNjUmpZsTc{7d?Y$z+-^b#8Q9Hcv1a#d_8;XUOI6WXCob8)CmwLIfHePJmPl(k^gf&{L?xp~=bx-z_ zZcRH#Rt?adM^FEHrvBRX1X<@+KdXy$z~aAR^;h>&Ka}{gC-JvuFMs=~M{GXcW|@AS zEk2vc?CTHvq_VzBV zQNi0DeP^bIuw=&!GO8s!HLHbKxhkAAb*qXnOSengU1 zEY{?A{D>HJddCI->e6NIW-m0agP8#TKKDgO=*e;i{**hjZoQUG3f~{6=?BEz5q(Rn zP6`}-+{zoOr54<*Hh%^vZaXFaQNMI$M*|zgUi)ZnOYqk2uZQ-d59|+n|8aYff>*Bw zc7`uomhVEALp8Fy%i*r~TICKlfe%#5Zia_D-#gXMat=4YgQ|MUZhv5eT?|-4D&IJ9^o{kAB_$)Y- zyapH8EZZ}$4=82Bh+Um+&|keN(bF*CKr*O0W;(jC&jP^JVsJ3YsFBga9K68n46m-WO_r3Z3qc2w<*4XJ& zf5$%Fli&k?!959V?M-K_?Cs$GsmZiKDPDQaA?cj zM(&@U`G0bw#cajx#VyOaFX%g=?Vc1Y5VN`7XN9m>af=lXegXu)>b_cemgNE7U2TiM}$-owqX z6P=(f!u`ENun%%{2JGDizQ8ruEs{h#|K%} z&VR>0eUYXj_~WiO-}O`v&l4H72pZex1mH)93AKr4U zGtRVTf>5POuFE{hxS@)cx!{7Too~6WvG=)rsapm7UEEQaO`yL4`E-t3 zBI&P@(#!FUvm1JsNX$&{5}2Qk5r3B9Imhd_{q^@b@wZi+#*VRF!Fo4i%uN3l8PCSw z2-wM8(Ay}Do?iMEdD*te+qD*X*SUx0r>4mbmoRdkF88pc>YBTv@vfLU`l zwwYbpa^vaB1=(%b#_xeNf5x4H4Kli~o5!PV$yGw1(t}A@qK;Rkyg)qlNT>sB_0C7)u7;xE`9&2d(nn_!Ow1}$j3vY9LSH1?oz z_xWePHVyz!JGydpK5y%c&aemSeD?dNch9e`U~y_U$fJ6L ze4ARQ24b1$(jc zGGCXBdF)GGwOCj7$;hVHOn-?m6_@wZdc$tpfhMl}`HxzVo`Z63G2$A-s_b^B3-SN7 z_!l)k>f2uSuaTT!4%?Mof9>AFS`PI`CbIFoEWY(B1^8E9_}PH)h8g;7+t23qi+m<< zGz*q1yzKoLhJTSGjxOD{*ST#WpQ*eRUsvSg4qRQuvR_(ruXdDyVfh753U5uCHuTxE z))1>bVFA{am)96mwY%%AdB=1571rD-9*uDyL(eB-TPn%}wsRKOlHCagklf2ydF2_t z4jG9xSYP=R0|*>wju(JZf0e4KoS5O6I@#`?BFN zUhFfl!Si6x$>SO##w&Up#FaVu`*zx|bC$=;vF%j{))@4!PIEieG&c_S)zj zT7JK$7ZrZ{b8WOXtF@zZ)zImT&SkKIm%jqlrF+Sjwr$Iu=BaBp$l=JBF$#3Cw^pG0 z{M>1&y7rT}N&vl2yU=r$A)PUPH=B;_X*X96DSscX7Ni}>UQS&bE9a`F(~j1Qbvll9 z)nUC{&E{cs55~A^8KaEg130!-hwW9D#;B83eISf~+mYq4tUm$}W?J{r{mnMmny$Ug z9rC2z|8hF-;$E({-uu@EH+>k0nc8yG-XpNDQ=Sl-3saCRsY)%4GzCkwC|OEKW_Xev zS$}*^jL3y9DP<`)iAq>1sZ3a9(mX9ha%Ayko@uUmS*El!f*Po|OqonfNhr-zc5Lyc zRC&fI<1}TwVDL{_(uDC`u{0IOZhRt1n&ef^c~S{pXsCNx6{(TX5z^G8M;2cdRhkxM zL8T^!F{wFKSs_VbWGNU`#};3ysw5dvRezpVJShwKrzxt0QdN>FJ9gvKtSkyHRW7nb zmAYV5GgD;@`hsCuB@Ze7r55)$J~R8JUc9Z3>YqXeR5h#e1O~ZOl_7=VvXr^ViA-po zq-Co0iD*dZ<2*}AB02Q85eRy5(2IVg?s(udLdy%NxMR?Fi{fNG{1W`7bG z#5sX}Ot@Amp&2WSBol?H*`IOI<+U%0;PFR%Mh>M%3{nlhRb!yG)r% zm1Z=B#%4vz72^V?MtMBRpyhB_{Hq*v5KuVNidI#XD?w;gN=lFTouy1^RevNRAu5q2 z6QGUI6xIi-%YvEwh<#gSM1!Km^Bk1jlxA63RlMQ_=-~-ZRdqzkoa9X9iV(p-;SnXL zG$~}xSVClOjyRJTo|Rde8>lJ{?1B?ec#=vfQ1enSKaMC_FvD}26$y0fQYd&(agwGg zuSCW2gX*|%r)Gjq;1~Wfjemo$`GW#*aVj%KvNA6cmPsiYR5#Bv=uEIU@to6BaL6)Z zsFs8#Ndih1tQZ=WtE5O^I#s+?PS{~5*i9Tj2`&f>bfuI?GAYs|H96(b5-`)32|p-@+R`}usP7=-aHoo< znF3A7Bn7M;Ri)EZ!|Ew$2Fe3Hs_--iJ1(nIQA!3Hp@#8piZasz)G|==tK$mS2~=Bv zYJ|&mRb(pDN`u9mW`8=%a&uJS8B2*aQtA{)lnRz^P|PbBR9s{P{yMI3_`W)=(u%;h z2BoY3i>d;Xj)T%tBt?2u;W_Pk*inhw%)i59Ly6#-Q(u zTJ%n9hqM$!T-6Ow`2P!?6D zH7s7o6%Gq!%75}4D$Y_V41v~%MH6g)Sj}}Rjw)PcpuZL+FO5mmiq!Dw>iW@l9iHI$hy!1g6oQh%npkQD>XO>>qUx3}w*Ndxmt zpr0s49uw9Ta3(S>;iMn^aXA){r7kMJ~9`g(gfTQs!tMB?s;8|N6s*h@UMqp25K6 z+Q&t=tAB@Pnt@)FF_IMmbQM_5L?Q}NWlA2_$>Ir|+hG4A;o|9zV`8I{rMc8)m7tp& zEW?B-&~#vQ6cvN{=&(B$1LC=X4}&wmPSOf@PEu_Oo>L7LY_1hOmUvXMn1P{~mN^5} zju=%4P_-*UDy4;1haHGL(K0WMkqO9Sf)}!=V1Lnt#a@zv+xg&_qJ;((GE<}gyDhDh zGN9lUreX;JJF-lVC|c80f!zvytRw|X@(dOol_ngGnUb*N2%chU+q+Af2Q|lCY#Y2??sRgyl(2s}$x=QgMS(1-UGB zp2GUWPC^1|E;ZQ0rbKr{R_2;PUqh!zRRD+6^a<<_iOP~J2X!Lhi9#ct=}J@tCf8h@ zgoGhdGK}6(f|XgGQpF1eb6O_BeiC_lG=CCD9eTcUNoHul35+?SV9kJ)xl#hGW9aiR z8jm=+)Q!u)AYqE*h9yRdDVl@M4t5Ie#WGSCfNp)8Cg;$?@IP5q!r)0L z%;g2xg4DI7#PH0{Yse1H7s+WrhpdA6-;On zxUl1QLRA?Ms!Pgpk!ooY1D1K7i86!kkdniW@h@J3@e#B2p6zvNZ(RJyr#Jl{f3SF* z1XJACBQPjofuT&$1RAE2I3wCXhJPQ=FeRYdR!nkP$o?%Hb z%%y<;U*=iDi!uRag=eY2X@+LSk7rnASyq&J#j^sYfFyxgh!_mR$!MMvMt(d)p+r(9 zMka=nVd=q^MxN7DmxZrzAU~=nV8p3F@>g;Un{e5uO;9;Ib@P$(cB!=ptu1 z=vbf=2woPs$kGy4O+dv=xXCFoA~6Z5oUlksdPLDQ!3oNM zzN_*i71m3^vJ7>BTxFy@rhn+NVhom-N|aQ<5+hiW!PgdrW);Z|Ii_f83TSFr*`&xR z`Yv;r2qhN@2c1M6v%#5EFtSvIhaY&s;M;4Mhm8>U(N%KHZl(p(7?MUo-zrE2<646X zNMR*qFvlL&vUoR}edf2Ct2zO|;We8LBCPfTivvwD#*(3<-{e&S)qjP*LDA)TaT*q> zOeDyKNrhzu8k<5dgLNxO8JIf7VV!WBS!CQ8Rb~av!Q#PCYDy>)~8+xh%|SSQIG} zIhO?H*EA<-iM$e+ZNLEJpi|~2Vo~X`qA&zfn0ZpEp^NYo<{D|h427Rg!veIyGOef) zsmXKTRF)Z+S!xQf^M66P<|kqyKqswWIApxkl}Tt;GLxVZm_t)geHs>3lH(VU1ZtkJ zQY0)BDNKb-VIbRK*ZVCjDnpIQ40H=)PjMtvmpLhO_$5<^Jsr521+74C%Cb@j4B0k$ zVW`Y`f`RKrN>4OjP!7GKssu)cfFf%OAsHzWF2OG6x;W7o5r5h+T`-a9Op`p#q$y-Z zle8dsb}l*57*SkhpokI%|I8~=2;4WOpsDbT(o&x2i@<6@5?v{hlohYiA|ryKZ4Ro6 zqQzmueK)hf*j^%t%rlnf43$Kg6e5?5k%Y+XME$~40<1uoH&ZDTO;ws|DPfRi6(^!P z)fWNdC|3p8_J0D_P_Ro#R%D6J(JHO-k{nch^e4_Rq1c69E!HyD92z~)8-I{I8(mNe z&>3>DKZT@P!*oP2=AUMu&k?PD1SMT6Tqxn&n?mzU8G`;&sf8gNdf^YD1hNxMVvFZ# z;qS82Buk~@S;dkn`2mzYf zNlhX&2BcHmZBAh1gAxKdiL6R0%@3xh0bwzo&ULC3D6A$S6ij(haYh-;5^0q(u=2(6 z>3tgCow6@=#9@E;;j~OMt-zwoN}6*6s$!WMPS7h_DRX*81m+$F%5zRLnSog)atvyg zWoaZgFgu-|5v9!VlCqMJOoHZ0IVf|q(3DV3d6u7^k-#JBRaTaTq)7(sGE^~@VyciV zG06{Lq%-(P&}lN0B??xvJS8v}aY;;4l!x^}?#2jOM&*Br6eNY^i{o^YP*G?>be7~< z@&kIdQmHCnY!wxgECU;zz}gSWxFDq{RYH%=i04d!o}K5i(2RjvR^UlqlWB}zr2MdP zK!XITB+E$wBMJH|PZ9-67}bgt9JIu|IBe|tFaZXuVoEs-FaQ)Rc(g34f@{iDmcjCuANt71AOVbd zGI%OZ7e!Km!dpm;pf@=$Wl55wD=ggP0#Ar=juuIZt4moW2HFA)!IbJ_D3b@@?F(^_ zl_qDC4125-)*P7RX#w+@5xGhXo?T4}l4lGIh!cO&fI%Y+jA@*JJ6G@@@wI+$F4AohtGQrp} zMQg1G zq%2LK$I&cf=w+`8+?zY1Xj)dFn6LuOegjG+SY(NjRg&jbQe=!CRkSuKG_*3A0yPP2 zRt@#lnBJz4N^5dN(Sl`^L$@~4R6Mii%rJj+3#|GK?9}9#-&(;q0xbx$Poyjd9Ziv} zU^zy0vPvc85k+I*pustmRAq|WRx;O^$q9xvZhIbcTO3jSBuQbR2eYljG%2ab zV8v(VIL%vDHhl#L4H=`-WM&EskxVmeW|}2O5n83JVqC%6YRU{u)Dq8fYeFk9>GO)G zM-fUZYSJ{&*YFq(}EsFC{HWO3c*TFVeOWT>NJ6F3mQd2l7v;q5n6yD zz~Pg!OoL5V(n=d+xBVpM$T*Tvr7JK<3=C6Ez!XU_nNPto0jo(O&2f6KWYB-O6-kp4 zENaOJL2a0T8Bj?uiSpz0UX>&nXe6wHX^>@E24+vGSe7sbAG9FsC_+tYFuX$&4)d-| zsK8`s5+(-;9h)3l6ZH|gmy7XiFHkd z$MR_DK?mS%P5_J&D8Z!ENhQF*DkxE!GEpU2ArG55ZkRz~{l~PZNCpN-QetJ@9ItNQs?$odSGlC6;Gm3=lBdFeZIt0zFWmT7 zDOIN@WSxJisgebJ4N_{(P015HI>98K#Y;|3C@V^I#pP8Ym_6JBeWt>&QHt?xKY$R% z*p);ORq~2JV}ZgY%A_m_nm4kdCnr>b6$8r$Gn!B(K_AjNm{kn3l9z?f`N;{96bvb9 zG;k570xd=}yd@}?R8+bwPv1hM5=KfU%EDBs!0dmjGG~~i-c(9U{R0Rw1!D`(LTSZd z!jpL0Uh@An_if8<9NCud{0dA=N6f@nC5$ZIRONXUdMS3=m4|<$7qh&ANoa0SA`7u zxas5fv(QxPGBD4eV!0|TaPOoacxDZ~puEh8F-49Eqf^mBuoLypLP=MH z5+Vv&gGxp+nyN_>s+2q5Ut4?^=A~hB{0tC>aGGQ?(qv(`k0&B1EtQWkJGs&L0u zh4)aAoDyKe2NDI=3ho!p59%m$GTyu6I^!Eu)(Jq`9oh}Gh1@>;=V7N7z}nrKUU z@+BIV;;D!=h1O5nc{+$Rq`8ktm0(k(6xI%diaxVOX_@dC5Zdmw% zE^wA*N=dTgrZapnsmKha_~G0^^%#HKtalE^Rb{gGSD^G&lH05$&sju-$~q`0L8!&(Dt|6saO4D4GdEOx(OZ8RQ&rj0 z(i$bTIPS{Q$MB-^48bX$9GqVUa~mkX5bb{#CiLn3-ovX>sUh%4x-dr@VKY-XRIVvh zaj`#Nh?2j8#iIPVI0Z(d?w7&N_d5@;0%*3Eb07joe-EYS zd7lnOv+#}bHzHQBZ~%=dh%r4JE=EP^U1Z@zG`!{pQ52#o`bb}zY+cfn3Kukc!}y74 zWLJz3jCz2{mRY#!!qO%P=y}I`G&`F#ij;<-|Fde7^%l`wsqn@b8i-M)f-j{pyFq|< zwbpX?E(KX$|8%*{r>+mHV1G6e_scJ@?ojW$3qG0+z2#DENjwQEvyfPnf1VNuKoz(o zq}aPB_4x=JmWnMVJ82Zc2y0Xp3NE~gmSOPdua0mDjPg(v1@FfS8+oyrQ}q(Y4P$%r z0rgDy$5+36d;W}F@)p0zxR2l!_L%BFGG4Mo>sV#rlLx8G-sA_Tq*&oHFj_^<;62zT z>sB*ylo7KjujAK15$Z31e^KE%37XlW6}G&}3g27Sn4gE@Pv5@!@frKs8omueyb`oi zkQsR3u28YYTq2d<O=R_U4A@a50vQk>G;dlZu<(|2H1#)P*kA}uTR+N&C=f7Ep1%H^+%ENxEK zAz3O-TZ%ATn`8@Dl9Eb!`E`-iIxw(xE;uT+T7{>z^-zaND=FBsl6~%Oxb*R8wj&xH z4DAG$B^v1}RmLN4dH)u)Q&RM?_gDjHvG<@u{3TQyeLDs6@Ef@TJ@vyOY|f4+uROf+9r(PX@4nGx|& z*>=WrH8#+0vS*{{p0}U5^`;UY5lnD}rim(wU{caW+d!!(F)HQrGt7eO(nncA%Ob3H zAchztsHy~90rwR!RJzt6l**Q+S`818a(+0kq$#fF>BhYbe{Cs#EfaZr=`ckN=Ah8E^72rqnUF?(F@Z; z8p%&a1eQc83Fnz>U4*Ax`dK(haU2{p)2BjP7jWv`m~0`@{I-Iwij;VZQcQ|Mx#W^d z6u64yk2zWQa+-ercsc(mT<6QulUVwsP|%?qe>?(Rl(4Xsid!LLMKE4W5IrJG57qBz z3qMr8wVHz3m~A$NL;1$kBXUtLknxM9mf|b0bJkL`5R|LV_lK-m%}SZbBFwG{Kn@`o zuLXi-D?*R09Vkmg)P}y?dP)z(1^O-RWQ)G=V*5jmg0lB0t~>)YjI68(H=|ZmiawPd zf1epXxphfpj=rpPu9i{FkC=pU27a&U4>`$bIXV{iOcfEh5!q$UV96v^Ve0XjQ^`hq zFK8*XvaI0oB`rO7(t5?K>kqj^fp<$uo8e{4m>4`ws&y@xlxX@Rnxse+kWX&c?t*TT6wRpe2edbPDt@gCb;+msqrxlzEyL z4_zHG?B$8+RHKS>Ra9L#Z9=tFe-zsb0WVm=?>_ZFuavU|?my*tSCxsBeKx{dUn+fA z>a%rz3zs*gZ~0B~(4stCJ@2iqMOQ6LDArQp5XlVZC!ipe%}^7L))ob6QenPOArHZ6 zHCOhhpkUzv6d`JHoN{x>%sgW$2IeJm!kvNwEjld1J5gPhB5GG@vHyQ z;yWvZ#+z3P0lRPv!2u32kxNadpaA1u;bllKrEGT3II6D35v8Cp*eOPYwuR}eX!n|h z&qEocSyr@z&B};CBeNy?HVB=|tXb77I#P z!MfADFVm-J1zO>dd^7=ye~B^JB<7=pV^gIwRKWKH6yQU_bJ0-;nc$%ZM6Axnh@e?2 z=&Vz8$3(B(TVuSf9u5@Ehg4TJq6Fz(IO4SG>vA=jeWp)j?-sN1_51!LH{a%N4>n)q zUcCAB$lqKagWA?N6wVi!sG=msJv^c!bbvopsQM{CEwO(*OLP3=f3`W`0dPv;07oom zEwbf4g_?6r$)w1|X^Fjg`SZ^|eE+7|fN}Cx*#d7CNXtSC%Y#yiIme{*R4T^WK#D5) z=iv8j4YOXGP+T*g!xH5v$yWA>45f1;5Qe|vp>>>0j&2+hou;zmPBy6A(1`%ddU3|zGeO9@kT5)v9w zeXbGh?2DtxV|Xor)}jWBwl=3B;dPZtX@6mn#s`t5N<6A!6!ZuJG@8Omy<%r?6=RwF z@93CN5&tHIa8OZZ59j*CEFE`e46JL;+z45;D+0M2cik38-kJ(W#h?%&Sdk1%x=D0PDaV61WMmMc z!t(q6Xxvv(;g}H3mk}!h7=I|U>vB1#Q$LQc$McJl+bkdbKKwygGVrV*R+hqG_y(FM z58fKm(KKTR=k_Gb{`0qH!sO+3E`Oe`J?@~=WEuLsgTLcwmyQWZHD7H#t=VK+@g4_4 z*Lt>9n%jIDy|%^yP_j4okJlrLkAL)pMu}gTVzl$u zPzo4?BUJ2>CC8*Hp8Vod5W2VYNKa^_84&IIkm>sv6s9my23wsHB6%)Zji(^wPWklR zvK!u0&M%J+;8mcd+JzfMA1=6vG-KO4pPSS6{hRI1?@dJb59>fXCZGaT&c+MtLaHGi zHTpcj=!CuhX1n`S(tm9)y{nOSjl^0hr$kq^l>uIr--gLap;j{mX2|rX`55TgG=wT(pF0wX`8_DsQh|8hOs@L zd??qw2qohs4B762AVxThUKyC9!iE};rou750B_Zu)vF69l>D>MG1WZz502tWIWEg#HcvJ&ff#UEsP8 zxMlTF@7g=p5`QLjked0uRYCE|wE52rP*+#wIyXn>e>)7d{Cl{#xdvAIRNvgpOTD=q z#+&hF9#X>&>t%R9U$#e!Kb+Lz2L7 zKR4;mN-eWOxK-SV!LG<3T3AOA6+jUZ(7BH5og;o-e}XWz*{4w6D6(CRc#JnV~~mj<0Vv zn-#r14O@A`R^Gcc)C)lU)I$A8r#dYDxCt1X|8C#;)g*88ctGdBCD0W%Y=zyD_-7Z1 zX2U__^MCasY`tshZs9u5zgf%{&_~00nSETVj(5!sxNp8FSA)y)5%*BXzFNxNA|Ed& z?;)t9ixK_#4gJGMZ*JyP26prc5&CudJo;{OgYG>Wm-*^Qa%jd;*Q%! z7)`E6KmYdf`j%{M%r0Q3n5NUKEM? z*PziI`#SR!>S8Gv`_uhRm0U)E+%=thsyg|m|o!8PqXo2JsLJ83|A6b?BUy`;MeWpCEi~z9+YEtDf$8ywEc7B zE}9txM|J3E<6h3z3uc^PszjZt6ZR4HOMkmULvSuJuB`J~8%k7Poo5CA@f`8#(}bod zyy7Mou9#s}X=SQ2T88R{V2>z)wsKiWTTG$RW?OFvgJz7*N(TR%G?^6|BB@Ll^KL_; zYpic?U(effjGXq!8e#|~v?1^S)Z`lbP1LTceSfr8 z-ay}ww1NIz=gby58J)qW$?QYDoP0X))T>K&;WmbAEn^e8k^lSh+$MIqDCxs=f^g~3 zi(Ox|1Gyt%1NFuF_$FebR|lWU`27VG>E)y`miw`r%ZJO$hwbG%SnRrNlTY(mc<}oY z_f>PnCNpS~66R&V{>s^3*|w%`&VLQBCyO%QfxkM>hMW!ACi2@2xqC7B7hv)OnEU{y z_ySCE08<>mlwW`;4`9jznCc5K)d5U(08@VfrapkF4`7-vz%&Oi%>hjN1(@~#rage^ zz5vr5z;p*O`4?dF1DN~(ruYI(aR5{7#q?j$w*Eld`u%NdpWd`~f6Lna4S)Lu{pUdU zInaB)pivLBY1^dp1!9gmz8>!g%x)u$G#+kyP4mUDd*k_*q%(?OO0BTO6zY^|W32}< zT#`F9yFUU{qj!i-D4=S+|IwScMwQ)RxrJPaUMo zFrPnY`icUm)sbO)8v*^Wl7IAq4mHAO?We;>%3j{p5xx8bxgoi&!~1B_?QI*fmy$Mw z-&{VPHQlr+n53-4&L%hSFK80);LJhe^e%;VjtrXs;#S6&dD&|@TR!%!{7n!0_V^V> z3tY*oyFvdQ+^rFEi@71AgZa91{A@9v?j3#$+!8O#{9-a$bY?TpaeqsD9~yM9b?arg0fUx6VqwNo5Vx2pet)J6}P(?HoO8*fv0UlGgMaIfFN!&zrN~ zg@jhfXS=7$?%ce4GHvi}b94{}KbKF-plp1-52M?9I{@x9?tey%KltTi`GhkoVXFeJ zI|QvxErqOpF7K=*ki7Zoj}ba$9A7tGVAPpL-;nu$n_9FV+w(LbvO2$-U*D2Mk9rxV zqd8)3+7CQCfO_ZJ7VMYy@ZjC*@HWQAH1&S*-OF0Z-C5^tp>rB>D}}aO;OdfA*t_Mg zrJxTVmnEg33V*`;UC+IJMJwh%e;YK5qR^hr(WSTp?YGrjoo1SaTqfH~B_7o1q~@1* zlbGu{Y(i6tx}B>Ng4Uk$YAh9lXUZ|JqK<}ht9YspuZp!xc8tzM#|3Ru<+>!#iWWs> zA2?O4`4ZVOIZ=FxDMYEG3sGh13pX@#$>bwS>^?zuV1FtUs@GVn&Dk)iRTkW4%MAC9 zbI~g}*IL%Vy%E6~II1#KmQ3bVq$pKoy@D&jxssl0E=!iU7rI%zO#fP=yy_Rc>LOXp z+-WW=bIJ>4IAbMO6@{_Ag8RT+#E>ZH)#w4vx+d;Du$_6(TE~dzy%gvnpNn9sIAb;64p!{d8HAlVQ7_|(0JynpU4KXSb3_hq1<^(oWljWJpZfUHu6 zG0aOI%%>nhpTR$t&ccx8_x^iBeX;(GJ9^7Uug~9%UXqhd&SmTIz=vOb^zHiFYy4pc zf4!PyxWYew7*9OUn8Fh}l*R}+5fw~lAuYzKJYr&GEo6vuBxHCioKzOq{ z*?)zfPUaLf&fb>+O|(1-{Z_`XmC*rzvn8Lf7jW5{ywW6j(0tE-z$}d(eLtRu_wQ%r zJ$*49y(2d8+jmaTv?#+h%5aHt-lD%;qrYp8pDhE^!S0aupSrF$JUi zooS8-&xEw5rZe-_d=CEWaG1jaO0(79=_)Um#vPQkzHE3`;#%GwxU2BzD24@^aX$Wc zIU4Gg*aP6#H&>%(4rhK;@Q&C6;Pdjw=yJIR_E^X(nR{TbC!?jp9Ff9YslH>N?-0F* z1iYA|zV7LCAJU!4iDSV1u@7w#V1Hc~u!EFQ`j{{Fj^M)t+I6&jFz86$N8!ltcCq)} zE@n6L#b{QpCJUM?%SXh#BY8Ik^t;}>@E^T*+r_lUmvz~iLcFf79sM$_rOdU&{g5SG zjXsU@;^LU7w?g*<)0(!M8M%<3kBHorx)=I*27Cp($AsTPmh1Q9>oUsY*?$pHJ3{vZ zPmc+Bpzk8&XxHAuvb{ed=BC`e@awtiil}zSu+fh<`@^cYf3{)|I*!dU4EWJY z=&teD?F?)JAJZS$SYNWwCD?#ZmvAe~>{$MBhrov9gA|VHm~xjP729mygg8X%*gj>4%t5zugGBG1Wrx+{oXZWGN1rC_F4Q|XS9piU zG2PrP7JEJ2J0y-eYq`Z@|J3Cj8prdww>a!^yEh3O&++Y|@9}*%ppWeScHj?rz#9~n z6LClKO*;&_f)5dx9)DSdPY2X{yM zK`M(GeBR@HJ?L^+i#-J1!!&z`!+mq@yQmy>!u>9n{j=_yWR5%}7l()B(L%=#|3r+*5m+|D9Ll^u7K?jWq?32R)Azfp zlXtG!$$QhOdwCJpJMe|%gWW~!vDQrsJ z1AQ@>FOG)T2-^d+bEa@I`~2{U$%nGIA88N8W2&9@-+#S2W(E1kNzjMl?wkMI0sipM zXO9Bk@%8L3_#>t~9|OK?w(~CdLnk^PgM4R>a|^atA9_jS0LC6#)Lyj9U^<(mGM_IE z((&HOKKXm-toNE61G^En59r7SXL{J+%u1L~XdOI){Mo$Bj)r?j@E!uo9xnCzkL70tD}L2+52HD5n#>EjX|PR zGxNnw{``auAIl$5ki*6(4XG`gy&QB1+M#`+^Hug2F*t8gUl8g$LS6B|4TDC;VEumk zH`#BoMbm(U=ZZclXyN~uf&#{~I z9fl8h=Dtb)?|bK4SCh ztxO@5*DUj>tzm^FtA$ZscpaUBU(t)qz;g7KnaH?EJTdRR4N8>iYqZ9C-V3M*QP93} zpMRv#L2+S>*B+;+4V_^9fEK9{oJ1d^$W$G#q!e-y!g{6?E4_faoQ10*Rpz;rIrFM3 zpe=VwE5%hWpjla#Yfat-=9A&tQH>qvgw2Js*b}Iyn%KI;;AAZ+3cOpzv=tVO>+I8d zZ%N$CfH!8G#Q&)2q^^+#$GCiAKdFJ$kbiT;lV~F%OVKgrv{#|pB7Gk+aRCq76`7n2 zx=>zWTe+5&RWzb3q8CuhBUKo+oVn_J5(cPQB}Ij~5(~T+Q16Q>Q6?=EWl!;5YL=)& zCS{~n_9>u}p|?4nqvafr6QngI2~`W{7+&dVGPx4kR3@dVUO4AHeukVR6olnUKYvN4 z2+}E2qRpBS#j1?=m1$A6$~inqrqV$c&x904sFbLv9u-mYCItbr(}zsT7f~qnLiVO+ zUMdrTX|zzJ`hBjjUO)|}1Q{?$Nhzr2R4o^ZN7z>3M2Y=8Db!Wr)=^RuXH`X0)Pc=4}dn$PA284bb3Rg@31&V8-Bn zDUZJ9y|N~&en7K?rWCy3a6pHbIl0J9#DIXlWBoiSxeL}x6QuWK#-pg{q&a(rzs%m+ z-(LnAmBh%yUlN>x#pnFt-8pk_!QK^)fK=dGC zw5noHGKkh^XfcG4Qd38vG*Jv17^;}c%DN|M1F{Q@TkoBhR!a}F$$#+dh(iQoIvt-P z6EDtK?WodraGJvxNCg%-;ssRb`6u-p2fZMaivismt|Xo~GY84s7A-K6`;Zx+^rB+X z;}N8>5`H(84dL)EUFOM@UO>@FC1;XUgQY@gz8Y&)g@&vefv4;RRN8>Q6e4(pex(L$ zp>u0aI^~Mj$9n;_8Gqp=i`lZmg*5_$(z_@$L&%xo5%mHZxF|VFiEtnpFC$`8?YVIr z=9Ti0^#WRXQA}p?9D}zq3m6;i5;uh>a+jY13ho$79{x>CB0-jCc!I`pg-Hvn51Bzh z^;EQ#qAEBhT3eh=46dt^a52S`h9NqeHI)N`royN!wi3d@*+EH3x>%p2^J!kFT11xB z!HH1}QK%E9$dCY`gzG~l+%#6bhP&n|l;c$w7QDla2`UwRx))Hy&DL222?1{|7VS8f zKRp5;e@TildTk`7FZ3|gPD`UPQXe>Kt?e{;HG->G+*~#(CXp*`(P53F4Mruw(6YWzQ?K(dr~x=a=@Fy%dZsmR+_1T z&xkCieS4BnL*$bG>=kfjEW|NZ-7|7XdEyq zU02%+sB4QF+ZvGvhr}IHHMMX450u#cmy3T+F;?^JhVS%VL+fJ_1(~H;S>a zY@$EWv|I1J#D%pYeCaC z2E8Pi9LaqvTon(=`2W-9ZL(orU?8`%o+{=VJmO(Vj!88BNq$sz+$B*|QxmiVs3?}< z&lrZt*D?1bbx~nO;PZR*TE)D{HEZtBi>#|5i~J;QfX9R*1vR5MS|A61INK5mooB;2 zeDH@`qMPenX7dHDXt>QYOnYDk@259|cCGE;W**+}E!x~((@MOR*2yQ_l-Y)~VSDAU zmG?=apd_qDzdk2YRB zGMhBrvP>TR>-z4qn`u*j$%~-!Bz*vf@f9`mVzT^wakDiba``x%To2Rb#1 ze7FvmpXcM{dtQrd^y^aOa3ylM68YN(@~XJjHuBlW$>j}y#=_O)=6dm{?$+KoT;BLw zE9Q0c>+Dk)e_ZwTha0NpT}xZ_dsoI;n}>Q3$Bl)YKduCMd-HI8b6Wv=@ZIwFN_aPY z_I3@oU3JV>a#!~)#lC8PE~RcI*0?*awl7=tA!w;)De3PtVwR%ct!2STzHREfHQvwb z*89N_pWj@6HCpX#Rb4wo47J#hRsbO(^I!Oh_MEuF?e z{5)9Jp4j#9RMLg^PS(+?=nHlEZk30fg;4;vOc*#MwBZVE7(cHnT?~GI`Q~qf9}ZJG zBWqMIC!aRC&C_fQm9|-I zLdS^%v&2it@&2KxJkOvaGfC0H$y8FyzQVu~388GPtp!p@|Bdjt4v8a33(ScAO!#+@ ziCaxd%K3X^V8A%`#q<5e*~2A%ffZ15bvl{jeFb~l1P}ofh7wrMy*$ffG_1ZG zAOomK?RH*$Urg5FA0rPaG;M^Y8GMz`UG#Y$Ym`6=-p!sTuQE3|I_zDyFS)ppmW(Y3!N1+#IW)UOO?J2Qd>U;95ixS(lyvg=?uWpoMZyD~^N0);vl_ zfKiKI8KZU!((3t*X`^gMeF1h_wqMRp*$D7o$J6vVKI9;Nzj4u{`LC$j0;x1FiK(VT zgnmH~uRiF678szPy`C_|I}-2QpTC8c2Jk_Oh1$`;BXR9X?w1vu2$=PXC#lzp+z}Sih;AiE|f;N7k_qC9M3eF9Y8w=e*x4M==F23uIUW) z_tL8=5qO8^A(((2IQGbvX(CuK7th|-7dMwPE9`stkH9Q#`u@l`-QtQM#2&}0V^H$! z%ed3PF=dNi)4f$a6venUqb!v>-ros*@YCLb3YpSZ${vdH{Czvgw5ugt@?!4xsZ#?= zl;UkS@l8<^JM}1rm;i`76HiF`}{@*oRp_4{-7Mw-el2n$z~9gI1C5^n{~ zR!oiJuuZiTmq~f)s2_$OpV)sqTJ|H|TssosbW5pbn{ag}G#ubbyWO2TJ$;Q2w|{qf z^)>pke+E*{y$H3&U1*6m(8K$EJpVjWky-KmJGRB&sL;BwT#V_Wk>>f~@Z)yR&H2bz zQkSOom=kANE6qVR!aVZu{b@f#hTiX=I>+#9F;nQ7^0LQpI)q;JyT`#q=*a8qJ}wbYg9AX8978}y&|IB!D*O<^==M@%bZ&X*eAp*)SW$sWqj2mHB7DR6W90ch zvvl?2YkkAr-A@YKneV47C_p|Qt-fwvoE-qxJjMKcnD_iq(mHord6Eo)&<*M=gpw_U zKpJBi3&nR#td5fMdkQmUt@HfdKG+$ zZtYQPB&bJMpR} zZ!d}B=6zFap?agR8!vc_uxiEnR^!C#G3U59U5KZA+k^XxB^KJ9fp^Iaad<0D z&b*PSf*@f5a1W1#ScFundfYzy)`S~J%=4~58 zqzRl83<_Z_>TmM)a~mW@n2KYj*l(Zs6PeK*H!}`8IZZD%R@fOZUd|yVrksE zpy#D|30t`SvJ!Q1?KIj-oLW;KKNRlVL*N1+IS0kBIB^i#IO6%W<~nJ5z61$&z0 zB5D*-M?KA1MK3>fu+5yhK=&5PGF}8TsWE<)uos^o1>5}P7m&*aG*X$2xSqsQw>fIv zoflOP>DtsXIpoohsSgqWIFjNQx5< z3bYRyTK}=|)UvPLl>S@&4kOAit5e^Uq9U4*1=F!&00G7EY@?Z5Kwj?Kag_sB-QEY3 zfX2Lu(Yz&{$tPR{c;6;h_?&^5>6Ph?dT9gln zH4=b3h`qLozQtUgXMmy?STEwbse*pmuGjZ>H(4&!qU+K=@mzPT=iHb(LngmMIv-r!&H1U!nxC;gH4IYir&08-N5TBhjrT^=z{**QQ8q@n2 zwaFR3&^@a4s6iG#>~w_`%8Hh9wWsECw%xqB+(wZ3axpG&D0Fub8DDMTh8P=86Cvi0 z!csr1`#_vouYp&gS@hh_X;;K5mK^SvFQCRqkHrp08BHfFs@$`cFk6c)F^i#c?@=1t zy*^F3O0U-h&{Y6JU)yX24!erON|gv&txlnF)!i&kf#KVQ4IJ8^R~Y~a@BO=@KSd5h zoey&&1UO8mVpmH#$!!VE9oS^~ffc5`E}s zB=VgLAj*?zu7CYwCZV_6S4PTo`k8R3r8*jaLDyipu3vfMFEF{6M598l%M*D_?EJY3 z1N!e4nWy62|8%0t8A!m{e5|2b!d=}56dlSwYxJnByO)C|xdD4VTgnulX6IVDVKz!> zR)@9#@7#JA-cS(~BTaxHjwy(F)tj{*PmsMCkRzr#6i&U0b0C;}im2spkQ&GI)EEFl zPa7XYWZb<1bG)~EjmLZpI|Xm_20pKQ=QfE6Tcxkm7k%_gC}SUo9u7SEbDE6@8fX4#N0MQrk&dm7#6U+93AHG?T+1E!n~@}yf1MPc_}h}M za0%L$bStyb@&E`hZq7jZ9FwGOhFo`%m}{Tx0V{znOCxbCur{e7Fc+oN#)AvzgchgL z#gc(dFY!hT&S~Nk5`b6F!w-yYY|i~N{=wd!+pOJzwVe!dOA#*%?q`u_x>UCF^GSHok@nLV2DiiN;{# zfDX(@?ZyJ7qp|o3s!(ev3QC~0J^^e29jl#44Ob03oVW_-3apr@0M7%cwzL-g`Xf7{ z<;^rOM6-g{li04p7a~UgN-=*P@V9k(dML8y8oz&*TT=w2x_|)Edj75^qKDzj1~a6y z?smf9Ay&jn#{sxuVAS0}^W|bGa{uFl*Gf?BKz>};liyb~wWuZ0cU0JTU(H_VvlusC zZ#cCY_5-_HBmPF($p{gkUsQy}T}@@Z{a0?J>!55X@8h%2_mUU_%j=x54692pQO@Co z_Yoomuu+h*9@HXzXJluiMHaWQE+Bk8yNDGqL#qnB74em%$X}xwlOQw`5|j0u4cgXq zEb!jJb#E}pr<+aaEIcf@gU@bdBP@SSOt&FUWTs;5eH+FTNY>b+lG;n5;mil| zTsbeV(rgZ#5crJf=%aP>N+sSSo&ch%Q>bj3)S}UAx{p1zrt56hVgB_yr2<p?-~ggf+3Bu z#t6D)o7LHtjpFnQj2C9kN(NXA;k|B$G9G7>g=89lA#R<~(y*R~%jYKkOmH4{|5KgS z1Xp|hdjyjld37V+-Ylew=m_-Lk%D+sCl1WTP@`A0@0?u6lV4|t&Rx4M>h_IeO0IXD zh5XYXw3J5K3ZlV|I`RRy3q}sE#<_IjhUmnN2M@{Dc+)v=={5sEUHVN}dsI|0G5Rp1uuoZI*H=Rv+(i5{ z(M<`Q=KFB9B^phz@e81sZ@xZ1l`2j1$&(KHKfo5VMkwj<$#uD#PC_KU1;X}>J+3C_C_9K2ey2HexXC*+d02`gR3C&n!cOg&>MrR1Mynu zV?Nm3bM*Q@)Iu_TG7$Iit3%)#ZB6WjxUagfXKZ#`>C)EnbAmwr#( z%o}fkW6x|IeeUj5s0;RS8sqF-*0qxMZaJV;m%l6WP9F0Rb&Y4he@fdADVz~^M*hUM>#FSGJi8_OUK;5-@{!K3xd`r#v6IW(+cNF$2D}CS zV*cv}=i{)OzPAJDI|}%V;8yaeI&$vkKHLrD-ST4M4Qe!CF5>rz;>ghbq-qP;+R*Fi z$ZJH<@jHVQYPWJL_Gp)3p-_yqGRg&mZ0eSOpVdGFw%%am=WWK{jT7MGbt+Lb4(j`^Uj`eWTYO!eV&3b3 z1$=hl88k0ZdD+Z$Rlw$i$n+(E_XF{a@_Ky@6(d;6^nw$2%*>Z63< z)F|v!*RgU0x!xR338=y!e@4ssQCPsba}Id3mzoMmfCO(mP;9FziJ!!_GJH&01(HC~ zH4KFK#3B^o)%r4YrrarvN8Pp7^GRQGJ)3T4ZNm|uO0CxCZY&9u!ED?Wi*rg+7lq?w zix=S!Fr&rX2rRF?c6SIKpNi^jVLh!-KYMlbZ;xF9t)(P`!qx&wWYmg|tDO{P^pp47wFnp$QE3!KnX8Je`!c8vI2m-O1iv%c3GEX!i&L zlpzJB3*^Zr1&CX^#3aGiS`rY&sAsm&-3f5W3WDtC%%a}_Gq^o~nKNi0mJzw1h zG0J`pESF!RZ@-LgFse0T9%j$)wT|UjK{Npw;n2v_vP}?7)nu~s3a1r*#T%kE!`L61 z;;W@5i|iCnKJ+(^;r9n0Vr(1#+lZ_HoQ9{<&u20fKA+kreF@e-hgY$#}*cp=OcqQVH&vyc7pkg z)^_VX?P&Q!A2=qC3B2{rL^*vuxdjV#rr&B6w+nDv4 z!$mxQ^td->izJ>KcnP$kZ~E^nUdPZ#j}$Yj_k)5Lq^oV!V5+VIoIY$oobfzQ;OkMg zACwvHfvXiOOYv0rJ?X|7`ajNHwdC=*icT@C5&YZ2Lmrfr!^Fc|6ZLxtWd~mujIV+< zQlEqzk5EosO_T8k*1Ek4%V68p7NwrrNkYWpjfNGwu!K6laj|jyC!Z4D)a!TAdX;62 z%;MKcj^!Fj0&LfS;{_c6qP^bNVdb=IQSp0!_tuy1m&?+1HUoN37D-k#o|e9i{p}Oi zK4G_bYgaw2K2yWANOZZ^bTG@r@InOac+5dUZi1F1%CD66P&Mj(bP&k_yUcTBt=%YV zPt&MB*k=(Nnq@xhGE`P@P$YLoy@v!zY-4#XOK>VQo&#cs%n*uzGcY^DUo_NYJ6$e3 z*1NAgpCv`~i9MulYs}avpSaifXcp(ObF~89!5FqXf6L+0VqjHWU8|)p{Y2B#KdMSB zVoS;w-9s976ohI1R2aNj7Hl@61Ce&b7^;L>G|OD8G&*T1!&(jWiPaE?yjEN4za2@Z zUDbhP(&DniaEOEfp8BLhWmxPpss3ZgKJywmtRB)%%6J#qKCQgW(z4KMzRp(to+7I= zBf&L8OF9T+Yxtn`c)g%8BXehs8O#uca+BVYV(PgmF5Q%%I)$H{vr+jaS}3r>WAC&& z=L%`IxG@%OhSfbodh?dw$b67zBK%6*sG-&VxoJGrGIs%n=Kh_riZ&jIC`ohX&N{=W zNtPmyS}bI!DUiWbfH+_LV+zo>%Ma&UWf4i;ve3UZp+z;xTj2Z$F)2LGII^7Hw0wRd>F z;8je#kpb{!eS3X?{o4sNQm`Gq*dU>62?uhwnKNsEk;c zbMscA5Jbm`DUbP+ElBzoXQ;?%45&mPO_VD!p6l{&)7#azsL&k;CUaW67X zCKBM|0PxAj4jgjv>3uourd2&U)K#d(`8m3=zEuW!rJ6>8`FW;#^m%-9bGLbTa{$VR zw}zrMd2o#z5Sx3&1vm*?Q$)C`{e{dZPm2`;neAg&N+YMpMOx(AWE;8x zcm&_dmflf6ypJT%!fG3m>l?W$qtqczfKJ;xfN`afMZ7>bkhdo3EPrakq)jsm6QCy< z!iQHaX|IE2I?&B7dliYtA7AH_&(H?)E04cM5!@;9r2VzKeVsG>_#gA;0SAe%w=kAS zRi5z=qooBd^JfpoB5}Gp#eL?dPH`ZXvwYLimHP7?5Rny0-AqEq7Zkfd%S7`?&p}2& z50bjSI;5$rQ5lO9N?b9>nuBaQ=FO8M5BS6n@a<+?e!0Ln|4oPJpZQ zv1Jb4ACCI+ymff@Q%w0xfWU9$IG_g1c%ejn?IqH!LR%H2a8e>dnhqSPT>5 zv(wp|E|e?TCoNrOvbrjgC8BU&Amh^?16=ty1MJNNb(dQY3-- zORa^2cIVe|AkGz#0IAK00?=PCOoY`Jl$Czl-dm)_>gBS|49dg1_T+5-c0Riykv zw~$4mus~*#z7S%t-WAl*u9i+o)7=%+1V_+uWpZa83gL(;v)mPuVPm{5A1-r<)u>bkv$r)x|^z&um zqa*z}+F{*Uv4TWtC9(uKjW*AM*pR$2B=Z*O+C=sFxa~>bLb7nW;2!9=4qYM#5k6oF ztRYba1_fD+dmY*wd~6--FTOXOLfWD>1H%Q^``LtnNZ8;V;fbdwo|HsZ6JC?3j4EvW zFd6?B<0YI#*n+|j&F?Lf({CIk>_D&^AOCidV;Y{HtCNAFX6^1Nu zWA$e8+6ezy5g}3ajVsT|!<8O2yAF6)b_DkP8a;@_ij%ohD+AsQ_r8rf!fI2yIM_hh zX2&E;Bb4ETM+`L4P*m-KFt|PQs>ZOFt+%y)hiYk*JOxW`fv$_xO!rSZNuB_xctM!* z{z`M&bHCm(9tu$5gU|)Uh}-pK_R&BSLWY6kWvI>c`C;@3Nu-R1ArH%T;bZDD^Gnkd zKIDf$Oo)9{PV2{WJk2*L+rA`P6RQGSCiW4dQ72g;8qySF;_d@9nsg=w4HUi_+8l^HLzEF^qeQ?^)Wjo7BL#-5fm zaYxo(S1~d%%E_%T!VZ01)y)2n?zs4~Z6zz6FIwf-^3@s(%G)U8CC3hI0(T;%>|%)y zkb?p|PKtKFchF2H(oR44oR}2kS7hcE(00hYOG>e9CEb|*C*5h^Q`|JqSF@s}9!1Lk zYdHXco&G+-o|SzlI7Dc?dlU$qV>`F8leLl$JPuga>VSwf*#8~2gMp1|3w?qB|& zG919KUsuj#?m}cQMyt)cl>@Og=yj=m>f267bh6|Ml24HDkHc4{O_+0fE`$!a)k_>el(p|EKD~e5;nq0)qnlmeC^dcvTT-xc@?U4|0C&Un<03;t z>vm4Vo~vv}@O?bizxyIzT@Fe}v?k)JY*}F~UZvv#T~eweu`=n1AomtEWdSIc-3}R` zjlI%VoJa(i;ywz!pAD|XoiB8SIE)1HXAzuCJ~3B0Q!F=^r)5GY~{rG3RcU|OR4)A$i4y(dnFGk?u4hhWPkp7 zGK7QHw?%^KjGSh;E1c_+XsE-FVY|;{bcoF86+MT%DD>%plzZOTP-H{?-2xAwUvaz+ z1+~>*hHQ4HuzhQ-rP9UM$c-ug?S2EJi>FZTK%O2*7MB}hXq)o491vwLsaCvR;U5*3 zBW08=X{BIxQ4(0(hh`rJ(IRP=5!I9`q&SGhx>!@O(fTW-hICZHv#P#Q$_*V9i-=2c zbU^Fc-<(DwVNj|CNH_z8@pkOD@Jf*^D}hq*->oiK`;@^>X6xA6a#2c0DdeQfx?n@d zG|Xctgg1#=hiKg`WWXYhsj3E5J#}w8rNV+iSXKv}F!kyZ3>aNqS)Zcuc;TD5gOF*a ztm)rAH6slSqcs<1n__?FYep}GWNrbozY#9Q<<;Vy1?pf_8&XhKA^+BJ_UE+evm44w z^@X-)Mn+OcI2MKwyYO}E`zGhcp#Fq2sJfH**4zJC7d?ebBm`tg86+ zvRuY?pF-TmO=>5sr3TKlY@p4@3>Lbca%1*XGwi2Aj~;swyTOY) zwH{KGxX_C^IcT&{1hz<|O5JSeDXe&CE{#WTxM#Psn+s~yPIER^OE>t~mSBj}(UlsI z7D&cB6%LD=#sbb#pP#gJ&3_Iqb4NH=_4iH0`uss91g={Ucdlei(%XvD=hBxp;y^YT zEit*yPaoU9fvemM26(SDzSixp&l(Wo{Gl~M(=XYTx3vg@H)~_ATr54R#Y>`Hs@jj3 zYL|B}zzI_^0)vfc&|cseTiT(a zC2PPDzcXVBpw;Fs*;P zb@>d09!Xv|WE$Q>D*$}D*!tZ7uQyL$r~AW?J#3VEH?jGZ5TE_3O2#w~LC*UwaOeVl zfE3Wc%SSdNwkS2lAO=g6jkZ+7gVQAaGxeSxR8O(qR%9mzpv;0P1RfNW=lHI_$#=@F^8)UkgzHq087;^V#z=2yPK6%A}RkN_@v2 zqsQgH>;l$hyg3XSWMYaI-@A|m0O2}bQ%=7yxsyQ~v*8B+(*jvgNujtpjZJ^t_2%ty?-bG(%!p0pc2E5F0+DqaQRo>_8W?q`ZPHS9YS3L6!y^4Tb5L0k*M@M1fh3 zv9RH~-0P=E12$)tM8MBe7T7~GG`zI57}nsTLU}uoz!?hjx({(aC<_fhP-ZXW3(j4x z&534=r2yLsF29Tv z0UA|d7+ycZ1x6H1GCmoeMzqdihml;n%@()Cqz!r^Qhi#>WI0jlQtvwTpou0%zgjY< zJf1Jzp&4bkgc+MiXQEp;o1C(YV9?P6GsjHb&25+rB%%cE0G4nPaCL3ZSQ~pLgqh8-)W{tbv$sdy6x79siJk7XlzlB*_+-KI#8?#$kBuu zFKCI!;g6$HjY((%YSJC18p4^+k_NxiJp9p|^pLr+Z-8RpQE#UUrxadp4caiaX6MDT zPu4v;riVJtMgN)DCKQx6UCW7Pd*z=3M7pDSqJTZclm}x@SzndwV|C4nESX*qt$o43 z7RX)js@!q78*%Ni;CeS7$-(}m4Ma%5UpnKSUTBh)lc3uHZtcD0W-NRy6%L^LeM-dp z5&$=*~vaV<-#+go7;)Ecor{mm7JSe6sl?)8AA$XaTdy% zp>;gNfI*&5&R*j1tQaMl>zX7mmlrSt;)V$QO0pIn!;Dg32{2i&)D_3Nz#q5tMfeaB zZ^>3H?3GdhV~h7-`VwbP zHoK!J+$#4rA8Wup6-?WOwUPSLK436%YGm?nT!7(PFg$3$eeJ&54{{`2r%$t|r{~2k z;|H!Pa(gZ6I1Fh!XV~s%)Gs}C0zY@Rt@Z7vB!}++_*m7k-8br)kv90BgLx>OYqs+e za5nQr>P(h{jt&e(5$sEQ^F!kX1NQ9jqoA4TAQ)_mx5%yon%P(Ck0`G~sp}O>77y4;69RKgEz#VP3}xc%pW8A% zA);3S-0hnB7{d|5&ilZ>HhzqKQ0%$0G-Jk#()n>QAwS6IoabxJ=z)3K*4F)B zI<}1$EaYzt%6a=ivQrkO9)UVBai?8B;>ee9q z+8lLnz#Lj#AiJrvgw)TDwLelreh4#+jIJ|m0T)Jl!&$U5ulNJzy}t@`AMjw53x3&BeDPTX zND#Yg5}V-V1!RdWGq2lGjF&8eP8Z#{DyKY%IjRSA;&NMGN__}gJnq^l=N$*4O3@OM zCVfN5TN`uRgHom)Hu&r|UofC)8rBOF4y)8od+eYP>lR}$c%ys4qvNix0;7naS8sNU ztNqRY^7Uwff`L@0Q%}qH*osG;`v+(hx50;RgR`}lnjb}gDHePgc}2E3Kg@dQWRC!1 z@7#{v;tqpNWjS*5BULRMD+j|Lgt|20=k^0|>;OJVc`}!}=<{<< zMYs5>vGoSom0-5^LgV-tOSf#>U-rlA9N48oq;~2R7Sd0@7n+*viSvNIw>UF_M#`hh zBU+j4wTAcn@)Fyr?H1OL>Szg1TT3LtoVOJa8TCS=v5WhxNvH)bd;|IHPCAYZq5o(k zv4#6JKcD$`NzYS&YyvjeARexh3Z%iBtL&jSBo>;&fjFF}{cyq)i0vlcpQhky_0QK{ z{95E?mDXTa-#IH@x3G5u(LN-oQ*kT9I;Pm5QdoNVR!meAM zz=GcYAS`0O8BYSt3;~Ts{yJONJ)nvS! z0(`MOto}!`9UTKG>atc`_i^RGNOXr68_tf| z=l{ASG669E*(6qt^$(R(3;F-;&3chk-?BVRx?>b|YR+;Lly^qy(*dIF5raA#Z(eMg z_B#BfjQC@_X4AGU=%vEBo2bm9t;g0VFiu+4FN=XAvL?b8&>W4qQ3=Mkz+@e6Y70U+ zFtZ@GiSy*B+SmRZmvlU2K?R&}qH<++OuXR&rKF}Sd^A!i5IMZG%`r&Pzq_Fm@V2kIvJrulc z0IqNllCQWo^Wvdh<^k3&LR<7`wR-C;Yj)I6J@!}XD(zvXHtSMLP2Az{vKOw7J-a6> z2vSQ8Py)I)(B=D!Sf=DW9 zJE@>7vPb2iyoU4twMEpcUBakJ8ts4IX7Lx$zsac>Z|D6?^fjpKoVxXYooo&}%b})7 zpsD0X_Oz3r{?9;H?Xun~Rkfp1Y8>T!m?OSJWR@&~UeP(+D3fyHN-2+C&>6Zw8c`Oy zAGT6M%}uN4zhU?ZOF84;#_E6L>daLzj?{>|OHm@o_w%-A;wbGqBaTH5s z!FCc;C@dL#C_Ui|!TX00~@N&2g4RRMJsYbWU?7deqL`CMPoS^zK0M27s;*jIZsP)W`AiRi*;f?Mt1D(g@AWpN)y_Hsn|lO@gPZa%@J={)^9rR=!Go~v z(o5sKv+Y15)Ej0Lb#zDwZ|!DJx0OW>AjtzgfdCxm!Z?T|1G- zo-uTUfbV%(yWMgSQuP*@z=9dF7Y8f={=w`U02!RJU3XP@!fE~Tm^rb3-W@1{2E!Rl zq4E&C9~ygotS%)H)PCYzgusmj#U$<~FuWc_)0MPT&gHbex)%dA(1EuaLT&}{tV*E` zhi`^CK4#)#PmsrTc?qnkh`N-Uw$xP;-C}6i1VI~l3mNcRO6*sL>4$30?cXm0s4!*rO1#sV6Ah=UPf-*GG$4ObQtX%yl0@qgU5;_>+>!O~zTV9loW2UTa)6O^Ro zBL+hXXgu&xHhwQ+^Ih*UG;`5s`8L2p7wUlCJn*M6<_WT5ZBuXvpizujfF5U@Fv{l4 zc*1k!yT^Pr;o}P*KlPpI4d#u|dXnbS*L{`K;r?BgPTI3spuyN>r5V&?5Zf>HMr5mk>s_9!yu z%x6t@aJ8qaLamAjMeWscyxjd^Jlo zqFG9Xv|@GCk#hEk@5uKK@%`Lbd387WhS$%Qw%ePyfg(4RUcw&}K|uuQLTg8B59<-N z0984sKo6GN@W%(>_U!BGbnna6)tCocBM(*8DDOn>lEY%Z_cQi-*liyf+&&B1ybzjb zSoMdcRO>obrHJIdBgrO+K$ds#)ML(0j{BMZRkLbGJJI>B$~3VcZ{E-B_DL_tUH@_+ zgDyU(`Qs$lf!Z_lh1nO^UtVsJxv${sB5|M0!Qh8|<2M1KI$*#g%iw6RS7s~8I(sU~ zI==3dpskYal!oBXQB#B&6}_BAFY**&1=kBfu$>ZrX6)W3ECzi);b^6{3tV4AEbu0g z(})$pz)KSh&UIFdNx?+7bt1_SV6SK14R#E(ocrQ-(jWV*4HABBzAp>-O4s-Y)#u9qIi^6llan za&>L@g#y~eVWUC;p@T`9&m_Ob+H4GIJq;J;U7l_uT31#z1Qg#rjhjZ^RwaM;L3_@2M#0B|bh;_+UH zje4W8*| zCRi~hpzf?7!fE`uekiRdOoeOU10Y%ikOOGc2kI|eqPCYD1_$DV32@1qH4Lop9VLgi zGk|^8*6UUvp~qJow!K+ZNu7Ffb!KvDB~eKz^W$18c~&r`wx=Y6Hb~KFDwtE8N{vov zU;08Z3zKcuKfm;AUg3TV@H$%5aT{rv8KqtHLiMEae#Q25bY?ZF08I%!+GQBMs1j1W3&br%xO>|1?Dtet$m0@vR)BFHUsjD zpz4W!Of)TI_^ajXXDJqxHay+* znVZ-h--Z4CBO#O225>);14OvqBA^>b$E&=9-r(J(&fP-iqKeq!fJH}qI?tibjcq4> zdAZ)dW4sL+)ln4ot~Esk!?>^2OB4-ifqE%H(KfG|I3PdP+VhF_ZZs{=MiX_u91U7f z?O(N~m%~q@O%;M1s~;>alrD>UPyxIlr@srTS-*oU5<|(L3>V8`S$QbN9l(11k?T*E zas;)WO8BZRJs_pjpNr_V)KhbHINceTIG#(fy1X+}>>wyHi_%0c+MHE)qjvpoG$#XC zm`7=)1g7#I=GfK0*s53zSCxl4v{~8|F0!3@2@SG3by~R*yFor>IX0k^!gbDi#JkXh zN6h$1O@BZgr^9brY11`!CKQwUQuoj(f>P>kC@1`*ggzAvC>eUFnq(9~FNgY=Ma1HFWPchF9& zs}O7+g$D-+#*L!t5QKWZZlGy`%*U<3aDa+YT9%v%8iSS4{iQLiqK!bE(xZvCot5CY@;6BYcEF#c-TnP|9s zf0CHJkPyTkBdA4M`q50wxST;_qTLCtbmjw{i0ezlc0CA#*{M0dSjx+R*Uxo+zPGCr zgmPI&>(&WSmI(4z5$)v42SW^nEOgwT_hc?YA7`i z65ev%2s!`kSrsC!{D%S;oAZ|z5`e>lUIJNg7l!yPsPQ&J%utN)f}MgI2nIPMr&*{u z>=IJPPtEl%$_~Bo;a(x92Ur$7c?4Ah`C>e3%QWQzd1_8Y@Ut+D`_AUv;5&oVF?0F1 z`}l=8YK^^k92HP%u0inA1(TkZAtFZ$;7-@6CFMS_mwU-S_V?Qcmt9P2z<;}h3D(Lm z)|IAthoUZ(A2$5y4dZA{M`Ks~EAzj6+*l>BhsKj>;X9U2_sv%O_~rQ?rYOfO8G3%5 z`8ss{i9fd)RB;Xg)eI+p{E~McbVZccxh$Uh>d9{~o~9y#Fn+m6c_YXzejUg-1xn?7 zWEEUTy9nF}CJNbIj6VUOz)Y6Peu$;)W}x_u6E!!-MD{?0HYUbAe=lcU?^ZZq;E8fs zs)$yBJ~tFKq8=mcI&yUn!JW05@e zYVK9OHR8+Q(lMEnjItW;4|mS}c00?8iR>}sgUFC-ard1)o6qv$RqK4fCMvgXYzAnf1bC|+eC zAS`ENK6QYqMeDQ&Sdu<>;k+%rDvhPGbyR;dHO%YBa6VC*Y$eFQmGCCm{}1Ir8o%@K z7C@E&`rNYG;!xN1MlP2>$O0v_CT$uK3M7(>A7c1MUB4$Q(}?5KL6bIs&??Epts)A{ zn3L$M@h=r^wxFv;vq#+|C$?dD4P?JT88ExLwa80@QqZU6BVB#)(O*r9GI7{{RGzzJfJ^c$1`v#aaA z0vi!?+BUHje=P@>)q(S?o0Eb!guH~<6Ca~yeef2jYcCK?@jYi9K5ksx9govil_++o zYcEg?%C?B1oN$}e^}rG1o^wM*k2g)+lF+vn_-9J$DpBlER|_x=dI-%G{vP0>GGKOf zy(Tmx6wJB;Z;Ms7%U6{VQQgW{qEMz?hYX5AmcEYDe=3}k!ar$s@M6QAF+XtmA+4JC zCv3V=3r@vKx?)3vwdV#Xods=5Q3MirsVLl@GctUDzTS~*0u2-eo0U+F*w{E@#Bogx zOt3_PaN`^Wyz*8k_T*t%9XP+b$wPQUFs{RGnQ^P$+6iufy2(QXQ@q6+LA?B`N7n^Q zu5Q^Cf7paISzMCES2GB2yptT zI0Ov*G5H3%qf<3tyy_ec2OgiH_AECqVNu;V8lRbQ<+e&lg&+Wz>NC-qD5PXM}pZRrU>*ALj80CfG7 z#|c2!H{~Bc^pvtjarD%^GwOp8CqsGy4yIkfcyib$(y;V2>H~%+z)ihl@c6lV^hc^r z0GxiS{Rx26Z>lMw+8GpsDlJ8}8X@a@1B$ z-rk=Uu~phx^`+`l;jX?zd?MUh?P$blfKMwA+a5Lb?zmxf?a?@P;O4&g(WB?hf07WX zuA8)Z7_?o3Dkg!7HmNiRej!cQ7yF-T$15JBIitubg;qfB?^H|1ne2D+=jMu;)oM(I9rEuf2&m15YU64 zx^6Q(5{FkXSX-lX-Jx6ykJ!P7-?tr^(DF_bo+;30nsnW3f8q$SRN&7oMAihSIM1$( z8g}MH9X9CDRvk9ziiR?5;CUVIMB83<+_0-h>bN1VVK@x;NyQ0tr(YR3_++;_a_9+3 z?_`JS>d0X)Mo>u(y_Bwue;i?0p$r}P&IFa{z?UZ|L`T^CrHmc^It7LBC_5|E(PJ#N zs-r*Y84HxHQr=0=;VGlXxP(C+KGx15FF5UWYVX8XrIqnx?R@u6eGOfi0ce}s)meaZ zGlEJBu+}-1S%9}7sLTYkYX}tDfVpK{oe^jk6DTwSdvBjALzL{We^O-((47SefnhE$ zPzMZki-9^~uj4r2h|l?Mkg0QByILs$TK34*S#OG{~| zx`4MXukf7g!jhk+^HXc1{lYen)7)C(7sh;t*l7-Y;YMsw+M7AK&XZ4l-(E!-$le^{ z*B^&J{t-;j^1k;ef30f=>58q=-S3za6hZ4l#;3LP9jH6P4!w0xAv)-7tw%zBQU!oE zN;{AZpaZqT*Z@3MJBSgW!?j?~tK6ryK_O6h%o%NcFswfkef%@QA=BHxpKZo3Tz`(K z+2sS$wTjxHtfO+0?buO^$JdUYwQy$b=vfN~)sCIDbUN+me_@M9(vBXscnp3vt>t*TRu>B^tjTO)TqTRuRI++Zuz{}vEx<`i5)#}WdZN#c`MWA z$Ie?j19t4d_1W)ZC#IbCI(p>#5wD|1uAl2VdgS_HuA@h;PnjG$GHq7$$eF>es#Xh4 zJD_!9&?k|ee;bZs9X&Pm{ME5jHypY;dTjbi%F$!fR~(KVyXj2Tv2#Q2XHW{>e0u8W z$s2bh9XomZIjJM3XE+>nyyT6q^!il(1@la22s+)vX`~WBV>bc_QH_;c? zRX@Iof4_W<{Pd>U6%ZAVSR(FhR`vWN-bQ`pk3T9{yI1t|Bie}{^$$O)*qMO;>?88F zLv@cnVs5`z`s5?>c3WjPoFSezQFp%?<{=6E+szQx;uYO(hIW2Y!9`#gTMN)H(}Ldu zqwXp#%#%T?F49u7c}?XtTDZrFue{lGXrw1?sc#F+}EdbbVb65*Nw%#1n z1dwewDzBfyK5m76Zxj3m)a#2`8Ytan6%6Aj@=z9unlZridT3u#XUl za!}U7kC=_7gFmhC6&<%XYSy?9oj!LYoq1X&ri6(0!OHeIT6o(`c?Pyc*I)AWf4D|i zt#K6#6DA#x#%#VTMomsnhuN$jW(23^!M9^!7ICX2`tv?<;m`>!De=wCpPey*ER`RA_ik$u9HwSQGHxu8fa@ z+TNUl`$-T9$4N^PnwA|6onEdGMwO}bX)YXUz*3{e8);#i5PFD?&xLahr)y~F-WB6q zk?^v*^Gy+?}0SbYL#3b&)1MVtKX96S~wTMOr~xtJ3KAkG^T~9A>^cdwMpSuSeR6WK%5I(tV~M7`G{*=Xc4s@356b=+%sCyVGGS4qu#v1}521ksRw zur|ZjsIu|@%?`Bk+%VT)K7T*s7l*Dd!k>n_vRpEYEP;F%qbnoOGAe2A%IPS}De`?+ zmrkIJy1I1y<@9O>*@d9zKceyK~kLVlHQ`k-lWfL^yo z1xZ~p@zybjX(w}bi&x)sJ+0?hwrvGu;knBoa!Kj$EWyq_tZQV z&q;WokA;6CcSZRyd%p9Km2l9+a>Q;*x@ZTihNtPX16RglcG|*>MrD6($Oh;l4=&GW zXFK(+dzZLOBB{VE`KeDV+MrBO>FEr^SjhGjdrHwh<2XXspX2N04^#<`)+v7R8vo8O zxnBZeM+_I+j$h}V1b<_f#1D{H#x;n2?kN3wlx?3>=%fSZoKtkz%J!a3JAZsA=zPcS zyF=&lQ}kJy=f53tRB`-%Taj%`xcz-_i0<-~!U5NBj)Z^P&Ho?7z+r^}&NwH3u}5;3 z7>_+eXW!F4TsHiDOgjhmoHnT$wjK1w55Q*KN!Yy`+Muk$5Pzqm(t>-p3S2W_eqH_O z6PVN_YqI@IBTMI}Z|nT?72o^-#TT_q7UuZ#ID_`^Rv)IUfzRI_SJpiS^X8c5`PsjJ z!RmSxrmLy5+sp*qm9Co8kMv0O;$ZKY+RK~V_yk$I4!}Q0;a8vc@XF#awt$vPDODj? z;>lK-R89W-5P#j@Jwx2L_osy!4Tz-=NKCepj82C+(eEq5i38L#dv-iW)TgG(hvH2M_@zqC;c&va6VlL_0ZHm00XLUyRY za(SCZJFY3>@NWEOJprso+SyJlFGdXstS%L)N`!@o6n_fNLvg=LAnLjq|9odU1fk-q zb9J)6)g=l0mHXnIpfS#QsU(1MLz#M~LxAt1?qLkbVMP%?DfGR!RLJ%Btk}6NSkY&#-i_TT|6Tv1VM; z$C@ zvgzt+RK4ZA25OSZl#Obg?U_rZy^LW+W3}tuF#WS*En)4rgT0P?jfetLo0}0ILUh$c`p4gVM(*%f{F8X{!veQ1>VK3L6`-tw9-GB)?_bSD2zlr3@fhoz*NPKt z$+gY2L0K_CHFU0v#iYWBX|7TNKX*HEH^A}KhjMZJ_2`c-jj!k5Zys~n?CoYm=E+v4 zJpAp=xkB(ktdAeM(k|n)BE@D}JA1JHMPlN9Pv+;liTiH3Q9ne>AN#8%t7pqP0e^>R zx89Q2X$6l4UfZkVHSJH&x0hKSW-<5pZ7rORFP5cY9AD|{`sFO@>Aqn%!KYa_4&j{> z3!Wg-*9Fh9c;}>oN9lm)RAcCHPCAAL`+)YJR8@k1y!&(2qJ#M7I4aN~Oh2i*LtOLO zCb`VZSyzdU&`~E9QmQ64Pc@Pb;(wpxNXLgT{iN!Svn!=vFg)DnT-c5ILHwXgAx)0D ze*c}A%Ng+#M|JgSkE6OsYH-lnS`#~Y8O=9sJNhwjI#(T~t4^xk#Z!M#a{7IHG_MP% zV{y?*g;Dy=E;k*wqfRTNlGom&iuc9#7TwC<(Rt~lg6YR@bo7f1*KR8VRDXoclttqV z8Nm1ogKhu6G*ZIY##N-&CUwQKmONCt3+OiViYjI4AM5!9-GE_5tE3Hxx3e@@kluSz z`~=DZ)Qem2tl9Q&aP!Zgtj3VUjH17=j|L;^E5PGS9|(B9heHu~tPcR(psv;^upvtQ zHQfOA%o^q%6j;3@+rW>Hf{HQn;|sA(T6rld)=@*$upsu~IuvsNUOIz_{0 z!lbT_``lE*d`a800NpSb^oUX3Hmp=Z2S!*mI=Ds}3bNQH~iovfWxG4P27>?|@E!DsRU?>3`8Kt=uW$y|nVe za~$XczSCT&!N*X=fxERlms?;f%}W+;(KW1-p)Ss*o(#42;4R+BsW^MGvEr-AonJKy-cW`QZuU$MaOdL81pH877Yyzkt49e1IBo zNE<#uIY2d0kr6vVCx2*2JOLv3h{QEJyVfu1;cvm>8HKfl45<~g2q8XD;u)0iY^OvF zupw4KAqQne{Ge8#A|!i7H6oDs0eQAlA_AzSwEHDJ{FqL$(m*{@l*^xN#T)!wx!=I4 zMuKB!wAq{;S~455`=>Y|;_M9=Ez)dFA^f=KYPPpY!!DHPVt)-zj5v*?FK9fNF9@p} zxuQ57?-X&nE50>w@s7whh~+1nA>yg+=<|^L3}^47cT zy+^{^7T=n#xqr%fR8VhH)uanTW$$kY&4FJFU~0XhKJEf8Q*S>7zgD@9Jt!*_>Ami; zA<6_uQ&FnyiQCWYWBdZq3fiC=ZJH&bZQ^m;B-mUYw^3MEps6#S)G{M+Jc>s z?OD-(1}{jR3eHtUurj43g{kYIiE@ky6gX-m9!>B)F@Hs>QL2JJ`r-1#23IXgY!%Wd9hN>g9rAYp)TRCK;b1Zj6Ai}feRjPN z<Gp%i${Rzxdq(yd zr|Y?5cg1dv8UavsQh_Ha^^$M9DG0Gd_A_9(54FYIRUbbL|)OX^CiFE#ub4q2305;7v z2*7QN5`k+F3+G2tkPD}UbaGw%MUq@R(d1G{iVl6y0-qf5P4R*gH(~jJ+prGGnkq&} zaw`laSVIEP?G6RGypa&psQ|Y-6hxOPw|}mSH$axoloq;>a;7Bxumwu(JgiwE(wkVy ztx7st+(CEEWyoZ!guB0#0%Ba|Rpc9IIz;fCo%g`@tP~WC9MOd0fL|(A z3;Ck@PAV@&^y!zIYxrl!cNzw<0s*Yc`S~p-*D%o_0QU9j#=r%OH3)#+fBARZf`5z@ z2w?qzUXXvV7i95hG)!k_lAna;B8ZaGJio65C@bYCqf|C85!x}{94t8(oBvA~5Ah5y z3@XwA-W-Sb{O+8rtRN)*u7QR*J=8A=W{bD#>3^s(NAa{jFGy4yuhy^~go5;bBwPe( zw!M!D18SIv7r?^1y0M6t-SA!v7Jms+%qttAsj;qVEK>32kB1L;aZ7^0TtS{a)CywR z0`bu|-QWcwkCg=TvD~jAyYf4!ycE%=bL0FHzN@uUF-$ZFfc-hYdNeS}MyU!uv^n`} zLjur)KEsM^As{*-+$>lXvQAxeZKZNl{#n{t8DHw>tz$^jzA9I57)R*(GJl}V(Ev?2 zow8rNb?1@t2Yxg{49OkRPUBPdOyDoNIz;nJrI+*Tx+b2a4sa&JYhKU_${4$&G~W9) zHt8_YB7r!kXCw@#_Dkv{m>+1l0xJx*%4B#O>M#cKpsY`n+9_2vsIh*PcABdZ%n8o@ z8Wphb@Q!(QXqB3Ug{Wx-O@E@Sr5c4-+Id|P#jI2$G@tey;c0+)E@K0_b74>xErJto zvApn{wM{|-zA>=Er)dRUocU)<`@^(CWXwUVLlEz8N@2qdg)5-U2b~=AjcmV~+}6u? zHu`eSaIkb-Qxf;|w6l$CMK$MX9r{<=_=_1-{-%7`@p3(%56=BnAb)0-t|#B+KM;LF z7MfcN`OXHPkcH3Y;;njJ<0%@sozVZce*;Mac3_nDEcUeQc9e_Pjr$fs%{<#$d>jy{ ze_^i8g%y50M1EdwY~phu!R`fxbQUt1q}SHzA0Mgb(CGxc_fGr(>aNUjCXCV$+wt4y z^ktvy(fSqzqx9SL9)F#)wnSHw`q6jm0y7p-q2uiPMhGi5`Xt$?|tZ>+zk%p_Vi!R z2S2}<;o`LmhR6}bbpEuK;p?yNh=+J-*_&Nv!3att|)#R*R-@SreBKR zQpk^S%k+!~Wq*0him4!yec}pBjqPsYzFY1~e9d+K+4Hj~v93RD+`wA7WC@m6$U7d>X%gTuvx*r z_ar2^rnz)Jr0=v$1m&xc>*3> zT24UibRRMO!}gkV81QJ67CC`G)f`<3Y%doT8*p~!AVydqwES>fHiVxgtiqEGsD-!w zK*+O$SgtX#h}mxfb!Xr&j<#AWWjkgcN>pp5Y^UKviEzZP)*vDI)%P5pu0;HnGGiBe zE8Zwh{*>PD(jE=t*va#WqM7zs9q614d(GU1dCO#?;qRjJm$(&HAISj|we7 ztACe=umQJz3eKD!U%?#24D7Ozm_0qV%CFuO#9%w1F-IJ7hibpoLxVKvB4d?ftJMl^ zK&;M(umZatBaVa-DzGwInVP%a!0#FAM^X*YMKVN8s3oxVMs&gca6T1X06vg=L&zQL zO5BT14CLNu=ofxuGk@?C2bxxp->{M{2Y;=ix1_>~@I?9376>nNQu!#*3PT6gitzOK z}If`^jFYr3nnK}i?R~$4;|2}xI5zD9gJD&ksOSV4CmnZ zhIjaJ$2gM=?p$nKSjVCcmr#9-I&8voH{xIf+1*OWf!uAa7kBS=fKU%J$uVg^Ab;VN zWx%>SlaE_3l^NmZ&s3kX6_}BaZN%G`|9mu_9{+P@$R8-Jo@d(0X6M-*-2+4!CQ>;d z3L_psjBzHH1LU!Im=O?VnoH(@Nq$%&B+X1RY-B6I1!|2ldAKbX52zbu~haams%55UvjxRdo~# zUl9P*%ZF@N3I;G1{+DDi}63p~C`Yqf{JfQ;Xv1+PuzA^)VoF9H2ehXAIz~6&&ZgX>Z6;WBwQMJ%pkjXQB=M1B}@>u?ty(@NeWR-l(q! zS77F*yJEjIINnFxpjs=)GnlkS|1bmDM?*?_2eCkA3hW*ra zI9>lPaH{TDV+P8aqlq2ibbric1ZdI`6;ymzIaq%dvA%;2dSE%l4*1Ho;PHi=#yfFC z*_&~vxg-{CRmF1c!%laBVw_z*|9l)c|ILS?>!d~_5vh_qXx!fNez<{g zWFEUDHVNhLoZjglXA%t_^<@sI$ljvlNY6*e^e)7N8cec&bM8xQG8;nbP}R$ADi~z!(F`ko(uH0Od$xgg6Mq(QP^uI^EAWR zPL{!^U`9IpGVGm7aJs%U>e_OmX(HNAxTMM|+9hTdGJJ6smjJrM$ zu#bM=xpD1Vo^OR8N9oDn5MDeHOxD5%8bK9F7{^c*0>}Xijemx9IB+PecQGvNd?M|> zWV{2l*PjBWX$1|uAqP9AqTxjY7Loix9bAbf5`0{+*Nh5CQ-rDV0#Ag4Sg1t#;W6=-SNt{1NP_ScJ|COkw!0V~eRKN| zG1I=MC)!TPr{|~V#?{n8S(U-cr0Z{`*HF0@ca>sZmEKK0X3o<4w?_*4Z+Wr*kAJ*v zf&a%pLVrX4mvo%6(q2t-ifIn<&l}A!3=l&wg8PVU12~Vf=MB|OQCJ>DtRWtfw0ZYv1+BS$WfsV$?E zp>7~1e)CmPs1Flm(vhAJD{TW(Y=}6|*cGPxj2$4#Gj?T}JtGH*@vD>PZb1goKz$o9 z8j~(>H7G>cST|M%5$O}PW8D-RD9$Hp$GRCiOq5Slj&(C~fEfQCi#o)T#we4EZ!LeW z-1SEK#sjTi6342RMj?AqR7ql$>zx_QFjqE7ehz@0qiF@%h6s?Zn~Mcmhh%vZeHGv~ z{ANC_S5zfQJ2S)At0gkJzs6}0OkzJ zs==%|Y!gH!0I_XtF5cp|9r8v%WnqnL+Cgl>8q~CyA~eJaiSL@WiXl#eCIDDnPp*nK z-SF|%C&8;{FEQNSpj{i+w1e2ROeQb9m4y>TP1b*C1-)=~ptX=qW}GdBTE})Pl8=z` zQL|W&^H+~D62-W=65d$Ra!Kus|T?v2+3NZ9fMdO2zY4vE26%>YX!X^ zc5DK2d6*15D62-WMtLQvtB0~`Zn{g)IZsyJOm{&J(F5pB+CbPXz45#^^OcxOoCWJ) zMZSM9SX9Xq>u1D&KuA+HP_19m$Ig9AmYcxD@n)|mTns6GsyF`E#m0X`b!dsT*Q0Bd zvjHbfmdUkVQI{Mq&Wc_cS1YKJqkT*oH}J`z2-U#E;2eUBu%# zfXfvth=a0pUMg^)X)c!?<=I^R>G{h5WdVP`SClTmWCaKrs9zG#PZhZr(NnQ>9;R^d z`T(*$vl2?VWL_AQh5xgiYz`h`I)7SAjAr3%C!3vTVJ==tyj)_)1vg zOT&r+4zlVL4QMyn5t^fMy*XJEGrWIW`R4!6-kUWyk|XJ&f8{*fr(-s{3Q{X=`j{!D z$SfX76iZ}g_3am0hyhX2imhT{O7qaa{Q|KuRtk%IkXmM}Ikj$eB*42SY@0;JzxYs2&@?pwn( zR@+_% zcAp+fvq9XGW4RMAprQC|=>?=8>Ss+*1r6N3=^wjr++&CRsHYxNLQ~-EB|jgV{g57% z;S^X0#3uRe8Qgi`G=t(PgwV}4d@}r=*d|cAcF0z`%mEGuU0*9JR6l>^>cQpru3&ze z^idULyGi*5#AXZO<0u+dl~;W7~+VHL3mzd<$l9(v77<5Ux}mN*qD#%wh-J0c}%c zptW)U)-OHJ1v%~z&`p0kZQujx1%5$OL@S9ani4wo-dJZ%0zjJiEbH^`@i8P(&rLNb zLqlm3ko8X6sYyUUGq4288fBpj%ACwYa|<6f@OzNm!-vl}t8n%9-H^grR8?NY#0Yxh8M-W9 zfR%3q#EmdK_<4UJT7XWteR~5oU*H&`923)}XVNz(CTZS!xvj1RlYzz+`F1Pk)m z!cJ`mtDRj3=d~#5xp+N&Y&$NNhHoq(=I(Yv=LLW`wI{oFh%t*0F^ z>Ea!0MWV}cJ1U+Kv~#18>IO!NGGw(@JSp0@u^pAAAe#8R z1x|`{Rc}PbrwuT1z5xkIgw_>~6Y=^9JEU1elUX#R-;OO^m!e7kG2G`6>Ugvt$|2y< zJTl||^g6R&9d7HbdVQ}+<AajG^MR)ot@ zf_~v^8$<3VzPR`TmB-pjcvt~bWel|)zLhfn6JLK@Ipe+YwT->hBVSwf0DjMDdvD== z(20+6A03?kNhdzey>xMbM6W9AahePRx->k^gz}Sc;irO=H|qzqaiE^bwr`AA`lBn@ z+R<&~27`7qAkx!-(B&iv^Y#VjKODXZEU!v>jS7djc3guIrrFbEaH8xI-1= zfaNjhFTUZLU@u0sdc?yvEMaeGBE`WO%X3pW^sPR?fe`PWRNvYVigBCdV2aYW59d4z)_5_V z^Ba^ggbA{@#5PM1%&EDFBtv#qY8-#8J?I(?H_aQ{$wDRQq&{s}k6G@;xVfaKVYh}4n}At}6(jQJ@iR_ponVI- zgJA~_H&2or3qw_AuO%Fng$ptQyO~z=4n!*7XGLcQ^EC;OspCcHb=p}If}4Mx<%T4P z5;LbmD+H<8RU_C$(eF1trTk@AHkiCV*;2hN7hI|A)n2KX7O4E#Ix3xI?VX0s6?rsb zJDOtedJImwp#<1^KPpZJ+J~Js5cs(nFZDSLn%#K|1~PlP$OL**e*1 zv`jZwGPdH*`parER{I*T4U;DKr%8ak>i$#~WjSuL_WYdVnrx(hS&YkKt0Md7tB>JZ z?90nF%qe?&AN;x9j{?Zl`W_*bJoonlyXSF?5S?gko-Nfy{}mr+gx8=uVKrz zw=^DDLr)FUB<5ESX6kgcztXXBh2vox2JiIhY-@Kojz?WM+&m{;jscFO)(WzX;r2(V6hfuJi7xX7 zRriPB3LS5w##i=u3rW46pp9fh8d7s+YjcuK($YZhMe)F-%rhczYp_PDPG%1Qa?qaN*)X{-;f_dCdM5CiBHn2WGm4}1|zd#jGF^#_4 z#x4{(s$#?G1AmcEK&^q+N&!y0X`g{wt;xdtK(;_a)qV>L1B4D3#bhkb(N0|K68z zdY;+dhjD+*zBVlU6+g;}>IjB%A|eUl_|RvT9d*DWNm%A;=Gw38{8xm4)1TE`d?F z?`?mrdf(jKnVv}HB==QUj8c>Pq${ht2w8w~tM56kp}}y5DM-0BqC9Malx2@lrgD3j zR=dT{bIY%C3!CSdweo?2)^W=RTW+`?UdE;|ivnUeeH#_Rq8vlD{d&8!VL1<9I8Snb z%@151^Q&*S7Kg0oy8>0f__8**wZB{pLc4z;)${yn6O}eWstEe!lWJu|yI{YJj%Re} z(uQB2Mx`+jiX(nCh(d#??h1W5qTWpX)&FrCMQNw-tN-_A>aYHf&?qS7b-!9fp+ztX z^nSS_kX2mYg)@G)!UEev1@<1 ztHi+kw}e@j?y&Z8r*s)cZ;@3@Z|WwyO^;2kZrfL|T8>66)52t_;B(`_hO4Ua9#oHt zD?pz`<6^G)cv{0-3(dK`bfaV?VDn;{WAFHp9T^rNdZj{zXY(GEA_xG+bf zOK^rgIcdYJ+9;FJ=--XfkZGbIGjYbcs(birmDR*Z1 zezXiL7#~N|M=$to1m;Ef>MnnwN8z9>T))?ja)+5-?`PgN|4DLkAkH|u>yFYKeXvij zs=q(_Glbrvm1JY^#q2Bi+!1>U3i%a@X5B6mfc0quVcRo;mBnqYPVyq%UtaJW`Ub#* zTxEKLVF!vX$niE`i9<2dh85Y|d|q9{vC?Wy1n9lMGOP0z1YT~prF(xAP=wB$w;#u@ zk*IC10XA4!HZPx+(FexpxF(&K(=V`X^6JWOBUqS8X+a9c=cF#4lT}Ef*a!BL$B9t( zaC$9x+$?!(abqLstj-6zUitOp%w1dVBh~th)zf34sIJ!oSNhG#I(eRbTu0Nl{`F=R zKNuEaan2_Xf^}WQzQ}*8vM+mg*c)qs_+{{h!CNkKUNPQZ=I_P)b}s0`UU{jIub$tt z>C@BmFRS-rb-cCdm$4hh#@~qiGJ0-_WYLwa4iw%L(oP#9Mc{#xYMNwZa%&21?bcFU zz_f5|v0;t38g1}X>^^ls>J}9Mv2Jl=JNM}YP9$y>05NXa=YD@B4g-T*1wf1&*zs(W zm*6RFK?&oqw#8~~$6qy5-d}U2X1}ch%A$1VI#Irv=y$8sqeZ9l`qqr(eW(`hXSw|3 zGLe}dm1Tc4i<<9N)nlLsDRoNy4eYwtUa4o6AU>vss&V(b&@l-^@)tlpihAkkCeEyN znn~ZH3;m5Y%zl5hNZi12a*nFYXrVgN_E<64)A`+N1eQ|MG6mO?J9<>8w+^^d9kKi3 zZj`&SLZAHzsZ$=;VER_8zplA^P0>4O?<%fHRJrbtv;xph>Og#HLuH#_vA;B`UuPh8RDve48e*;tZwp9!ggQmbTLox&$g$PhsDdYNm+mOlQgnG9Tdm z>5p<1_I;WG{POENGy~*y*Y~MD@H=Dg&1O`qAvWqWs}ByC%b=5T(iqj6+)L=s_X&NB=b0LJxSVG z_yw0`u?rP2N?7;PYxaV>TqCSVbh&*&2*ZA$wIaQ7rc-13qhl=wW#B4=7`NMw^$#Go za=mj|ZntsND25F(Q6&xB1QH`U!EwQ-nP@RG(>E3(Km%jY4kgI7brAs6_XcGEF<$pu z!ft;cc4ti(F^==C;Vw`sAGQIB@%+^iXad>ra3fxfQ!@X|pz^C*`dtAaz{}~F(Ui`L zYuwITK=@}}r#_QGQX7<|3vjB>V6dFZlNUdyVnP5UbDT&OAkj4u0CE}}wxNh{tV{rq zO?SAFEx@PE@k6pYsUrw*Yj^mN?9Q4P0{nl zK@+})5pj-uBYN5^cEal^WKNXQsTFdhCN(&XM*j}ccB#}&)(brq>#?rcgY`s)!#K@8 zR6TA#&E&j|G#cfJ0*aSObI48N0S9(jUA4iL!xx&f2gWk#JLR$FfS)DRql==fFb#j9 z9aY8Z+(h6woEHLl(0{tt-!TC2jRAbU z2g+YVYR~R%nB)a&UQ#uLG#!M7VcX4yZ!E3o6|#Latt6PMo!GUD@~jC-q?kShi3snr zzQN_VCR;Bic4S`HqQoQ&mG*7OdUtzmN8~x z>xzKb#0VkV<}?$@)jI+bijI}-=qIT}!FfCV&}ih6-;j4{)JTQ4wG=YV_;7#07V{cO zUZ`AHkBexWtnRIFv1E&j#d@rrO+Cwv=(5iy4sj#aUB~D1QdK&O{`ZDH#|bsPzHqs} z-w67gsv>L6$91!$-CsHq%toVmb>S`a_SCx`86Qw}DJwiQ_rL(WGsLjj1ve?0-s59P z#A`0R`vLT^^zPFHy^Nmzxk-P~3}u4DkJN`kgy%0+MEns(1X+#K&>^?=b2_IJo*ZQ#xsjTjDUa1aJ^Mlp|K1|z3M*zkCRmFwtAgybvd)))%s6TF27QUy#D@T zcC#oO+fq zwLE2Qfgq_?{uV0MP}(y!L7y1jOFdOzM%`asp-q#$6owam3zK&VQ0T zrzXJ}`klD``Fn}1_o%=Oqt9q1;V6tzdrS}PG5ZS+eReUl+kryxK5am7Zg2v=kX9yC zJb_d9*+l?Wch`RnUtcx7u2+8D7Vzoy`J%klT;KTI`q!H{b1*DsqnuAZ_vqX~U-tMA zZb3!VC2uo$}zlPNY?8_hOLuEogS*v>uqJ0>8RCatEdAPAZ=`{1u+P@%A^APBMp zONwb>CYl>lkis}%XtP|~W^K)!_tzUO)RaJ3$?btwlyN5e9jof^Mqglj`2FvFF&5+?iPN7n-gL^<~zZ5h}7#~$f)nN6VXqiMSRL%!eFx`$v zn#E2t@msV>G6k|AN0WW3)L%E;t(NFL zvTyak&gxopDRx{sv#h$_t8Lp$VJ~5p-k0Kj)U$t6Yv`Qz_hJoWc#2=LtVcWDU7 zeDe2d02_E8`aRk~>9ymJV2A(ow(t7Jj`@63L`LZas8o*rCemnhWjV~8Cr8T9-J}xF z3xPc7WrbC5XQrYG-C3>nO!`iFtU2IkPX@pnT&c9Dpus>sVWgT4ty_9 z<>-IuzqeUc8vyh|AP+k5yH|N5@V|Qi1ws10RV4!02wd-8<>*GVXEhX4Vgn=ETDR=} zIvsBBTf<3bzp3iV2%K216R(7%~L+9sD-EeU)|hu+E2_HtcyR@vJI6L3pG zQp6bv02EirOh>=5YOmbCbkxgaD_BajE06BV+dEB;#DXA}R7}Ha*kIlY^PqAk?BT&y~el%4- zk=CE3BjdMnQS7}Wztl({Y{j@nkzn*-hG;&huD4>+!Sc;cj7L} zWc$Gs|J;oaIo*CDqx9Wru=fgfLQZCh+bhjI865kvy&(BM^v8*s-n{{o=DZJ}J(6P& z5fb{qswU+*WSbBd}6Nrb4A4uuX+vt$-?I$rvpPi+b-M0R@ z?K92Z9ATe#z(UFhL zMsidY0#G~>fVHrBsoM?3TdFf$Tjcj%<`o|?W>EVBqFQos+r(?TVlX)!e~TXynhyFrgfz-BS``otQcMKA&a!1mbptt5mN!CCFfI8V=x9nfkSsYIb( zkbDBCn@ZD}cs(zs1JkQdF`v|6o&;X&gdIUD|$sJ8UbuhX{I|G zIVKg-uT}S$T5ksI&w1~Tpo}r)0<3Bw-YIuSnzOq%NK-L`+^{xbz%{hFBmqsY{Hsl4wpc&bQ4G zIZW_&nu+8K+?KYiLOD6ym1Z^=3TL@YP6l)T-f*8mTOk#H$%ha5hQx+L@`{9D z$cM*7H2C}vj@x*1B{^B!;U9);+C+6VsSPXQbWYgO$nuwqc)55=zEvNYH6GegRlYDU zAHrSKNoghF!i?4iJfXvlY<@mYZdGVH=Y?b;GJX_5GdW4c3ei{_&@7G%wfhZmSJ9JtvBx{ z&U-CSFqsv<_)dJgH-d_>fS|j@)K!;;=WX&PehzFBl9P&KW`%_QoFM(MHdT-KRf+ zS~(6o1dCJI&QWpM*hRCOKXC1|L(pKCs`ZA)d5wnke8Bo@M2; z$#7oA&MbD)O;bd+gEEc`Ptyun&4$KG40W|~)P>5me^6H;tvb=K2Ez_emHit|y?T#D zcd2TBgmUV%Q(YTJDpzEkzj}${BnHC{NF9PbbCQVMwN^kd=D3r|;J6c1Mgz+YNf3=) zKaSG*6eNLm%T(9|)bBTuM)^zL>|_Dm*w5&9ZM$b&WB=W$>&4Nh(pPB#vDeye&Y^L= zqjpq9(v`Vl2iHwBHO}ahr*_%^lVZF%@$Z3uaUD#NF>)t9u0a8?MefGuEpRHVv)l^w zKu~K11YnNbL(W^^fLJ33fWr<*8TJ8bmYe|QdzxW%u6GpIKAHH@$c>%L=mkEfavv1? zLEI0hSidWAY_;fE{2q8t5)C4+qJ|Z$EgRN(v5oRq-I;l{P3i61+o~4I4&q5r{CR(W z%ao5{KczFfPiiyeN#gU`O>GYPq;?CK#loaA^_S7OjV61J{z>f>lE0I~#V><#8m!-K z!gp%3I3zQlEGuW9NV_#PsI4p6z_>J)Ps&$8&I?IAXmw!4(glUE5)0bYC&hPDV@0wg zlTCAOOEnR=rq)ym=|blIsfm!~wtq^0`gOdIt13o0rTtKHZiLTcbDmc)Rj5N*2-OZZ zLUnEuH^wVvp4`4D85+d#4zyMP1#Y8}VH$o^DuSj|`sXdCnpT2SqHVeTFg{6vl(^dL zM`IJ8>}iIi#MVi^>x1rD4yDAGF0?nXJTBiHN{Me#UFshomDk=PP5x&0y>NYh$VMgl zHQ4%KKU9mOejLqdhNQ%nMKXPi+>;bYiEFqtY`S#$MV8r{WIaqjrwvdw6{s^9n=d_d zjtohOt<=lBvSV}eK<-+F^KW9Uo}zH<_SZ*F>XeQf!HPb+1#HhS z$6x)SWDR0|b}M*&831C|%~z$Lv+tH?b(pAsqv~lUTsUGa=2&P(M@+JRFrC_T2Te*l z+yIDki%>WXtVozj%S-@ns-r516h~sBa63t53sVBE=HJ3At?MuCCkuMWZe5XP*@uJs zu}rvd)BXp0X}A5Mgf>!;TP50{ESA$cKvg8l*5E1|Q7}mO&LSg<)80bdSh*W(T1l!f zjnU}&*Tv0GeKDI~%zw^*7B_bnSNc^!E**cM6bFZGh|0uo$FtdZ@&lE*)(WXieR_X) zspGRh>O$pH;30N=P*-xqB1%5l!P@n_1wrS%y0eXDa`vA52*I{MtUdpgwFjtwMbC1nmBzl`{K10| zH+HXwT>)(-OM+MuoULO7&sQkBwBS^+Mm{jnTf=V-BjpivQWvk6;{W^W^4FyulVZDs z{>3JRS4NxBDD>iBN!o*S7%#DV9U~)PFCOBI-M!IoinWEeHyVDpUg{yZ6s;s#-z*F_ zUv1CqrOIi;*!2Q`lLW+EIEFv2-tAyWSq=WS*H=r%DXmJk?D&dW3%VZrr!t*`bs6F_ z*beia#pkeJl1V)G5;eYTC}BgiW4cdbyD!VhST4&|{IZ>l?J#e1eN6kABqD)hxn$C| zb)}pQt(`Ui#CHUDz;R7;Ed&^@AhUrt6>XG+6v_A{&#DP-zs zTN0R^qc7gz=0?kJLN+(z*58L94$)DZZ;e7_FzMUcQB^eGwBaQG=5O!;C6X6Hg*e0! zfvnu1X(hQLL`v1MAnBYoq;rx=-y^8BEo^O_Rs>#uax~Isg94I~cDNDCNn?}m2~Osu zE}WCnZS4dZh|Zuan4ik#FqVD=+pX);IY~`hi~IqxI%|p-pcNwcqK#ZmB7fD+lEC^; zNiZiBBY3{BZQ(r(4y$Y=bM9lZPq0x4Pi9aSExsBre;P3YRAlMLz?=0{;G6N>11~ka zfFGKFCyNUApC#IP2ry5y@Ewq7=-XB_4-7Z-y^vh`F|7AFZOGT}o5i$c-g@cQAbU#^ z!AtE%oAjy352H@x-y81p2T}*}W#%2LGj?4fbdowg)Zbo-4cc+^bwB!yM)UNNGI4y{ zhzL*fybrzP{M`G{P15VV59K6%;CoR{$|LT7lXBl<+ty!}#7|tHV)4hppk1ymN@OcR z#YZALICgSR(<8&Q^eU7hbh#OVt&;jy=|8LQT<5t?W8D zzxi^6@Y@h?s)+QO%l@kkyZy0G`a+e#X=g815~teJY;XAtlor`e?ktB8t(MTrGy5uk zuW}CZ?iV8MP0#4(kNK>WtJs@NXR3EOxj)O9YIKy$szGot^2x=t^aenN(Z_NLNc>FdP;{4*sc(92~ zM!yirqbiVIy56NmInVijK_2da3eXvU;bLuAb}lZ&ix{-i2AJpqCN(f>TyyHH8`W3t z4!u(jh)s-;AjdR=GK|_C%TD&dx1@X31m-2bZA%_0LT{2)>?~XOZq;RyOVAE)iQ@&Y zNhR&cnY*@J8vkf#S4LzcKkM2Itssm(q;hkA#_kh;%(nA- z(MjGNC3pNksOb~MKI*uk+I{GO^HJJtgHTlXhR|apRu|iKAGttWyiay zX<7+Mn&&kt$I}c%n%h-sSz>Y_{lYw465Z6glIL z9Bo*^Qsnw)k6iy$<%&F}wBs6@BHv#<+E$9|c=GGwW_*Q8^DIY^A$WT;T^#+fnBOh_ zz_sO|3?<9-$CELh91idAe$MrK?1*lIB*pVilUtrjU5H^qmU;ak_Ia{Qlek}oX&A;X zzL^*f+_~=uv5sT=e|+_vcH6KDDP^zo)pr{9VaLKj^ktZaVXoI-U1y7hU@Nu1N25I2 zNkl`;v3nOsGtsho*Bq8OYhqLsevq>QpHTsS08XniW>VMh3OY#l17&HUtkX_XvD{77 zacd7`B~}tHzy~9)I`vwX078uLV<$C^h^J7)ig@0ZjJ!=Y7<78&pe$T3r=;#5H_^5% zf1C!qCQ9-KEXk-BjQtMD)3@|@n8gj1@c_8cG{529xzJ^O+eiEnD|j_X>6 zR8nB{V#(?u5p(W6)6awT`o0XC=x`N(7?06AQUL6#PK6fNWt}RKH_%#9wpx&tSiSV<_aq3FJ@Zjj9yjo4bY(q0f=t|1!DqQ# z0V*vvQFL}SQVlb$`N@^WC#^eYud!b@ooA&kN@AXWihHp_haf%X1iwR)(#28Ge7fHa{xQ}oG(da$K6wr2m#|$ihElyYDmwpVg)~^vgNkxmS&eBgXM~Fd4JKV?@ zWc35jL_dU0^aI&MKcq}FcEiYUmnfcHE6Eq6HMLxqm>9M?FQiLRLTkcd1wxA3)bng) zZVW=28=CD-8!&<#fBw3~auigwI2lw&k;xZf<>Zr%(yncd%n_5Si;*aQ3hW`f13pqNI}O47wS6+Rk;Q{tYbIN{jpxP~CYE%(W= z1B|(2F%n1vEce3vWFnb8I?jpVEEoRvtN>C!p6ijr@&k>}m(!m>^%^%~kC;?m0zXg) z{NN`r9Zx3u6*z~}Ot2V#jp^Op4LB7|D@o_&lluwScH!|8>@Q10lIIASbED&=4j{k< zaoPW^Z(&D8b6`&q&dEIC6?vXKBXCek876lC(HOpPj>yGWY-_P+Vuy3T~oKz zgJ}zItgCYE%fK7PAU0;MzXv;4ry3oCbYBLqQCGA&o#=Y;7;Hj+)sZmm4xv@jz-tNk{4eg;_))Prj-OsaAEW2-DEzV{Ji@)gNe*K>CvIE!II;8 zHJ)93yMcR3j z8D{tT<FC(xFHv$di24%@IY}hWwlM(%} z9fWA8!tN{wlBB7-%PX?PW_g<7NRsTqjz`b(HvHj7J<#)Id*ZF(JQ&ynPf{33iuYt0 z2LTOOeh|kQLFcL+*8q80)42s<$M(DsE6igwT6*sKnv-CqM1Pm)##>oY2)@~T*oLA% z^hNPnp5t19BL{P^J#i2V{~#`#SlHSarymSEfO;i*t;BS##*|M5uxWTG2a{;09|FH)lZmHK66-Y*qd{4`E^Dsr^VzA< z*nB~g>ZdRScQ5#1lOCu@EP>eR0Uls9>TBfefug-lN&BfQ-mKM^zBg1>Y^(^AKkZ$^mGf`=R70(|Cy;f9Z1;LvFYhu2vX zM1bF4Pgdw7tftNj(cEO7uk`O1KX2xX$6N6*4Lgmy4{)@G72!gRDt8{B85P$Z1Q^va^Wi8RRi%q?s$}Ft_VIEu zz5t&}CO$BqA_-rBPc;J{xEF1b?*$ljWZuJtmVx0_oxKO+XRm)l3^mzfnoD z;bqjCv;xQKv;iQ-Y{p7sg0B!aqWRghq|U%mI;qR&=2cCZft(dL*)qIbs(&YakX(do z3OgMsGLU;!E!i==?CPm8kTXCzD~6lTv*qW0%}vhsq2v0)HVl4#TT*r)x3#;nb<}v~ z=gNSG8QnR1scQKSR=zGYuKXHV{O(RraT+cD%BH2@ZxGFhVT-sL&3D zSJV z44;hITP$q%1H+9}5k$Bp&N12LMl#=^9fg}?HC+!fl-p$LadHVr2$ciNRYhYv9(O86 zC|{J4%ga^ebKe!Kek^%$qm?7rGfN6Y)k;-zMWt;hGI@?|a#+RHZGQ^Dy(0jqg<^F? zF4x`)qbod})hci_ve*&O721oDIEu)YSmYgx<-_{Qi`P;VN2BL;J6})-0zg`_7$eu# zTSa{JMsMk5XHW%4uKq>0q-sBeCy z%MqrXx`REiv4K@kD}M#bJC!$6VXj-=j8l5m{_)zF6itB!da>|tpLL!D^8hVV%1i<&{kFFELT}qz<*zDa{Fl1bLRO>ykXbM z3&~MV?A)#ZwAY2#La}f#*CApTl6-e*%1RpH4Q0T>I1G&-iXwCE=5EJ>*C1^f9`(SU zR6^5Hwgfa+Vo(DDglA&@F5Y1N368vUC2Q{Js*-C9z>-?HlQe8x2*F&c8aG#-O<8)j zyAVc!z!_Uv0Dm=VD^oCo!qJtfBhEeNmouNMuiVSA%qstOs6+}2vwpw1SEH1RZdk_WHfr} zET#$;SofX>Wa&AM=bj7S z^(c!OjoSHw1}s3N<%-eqlH6QVxxYT&K#8-Xf7417)TGL6)vD0)PQ@+PY~*6rrXc#q z+jRhqDSyBeku9vtd&W_|L8Q!(e&0bC^jrpjbH^Ph$o@QN#}SzuT0TyH{swojehi@i zK>20f)m7JhuEDU2g{m6qjuYN`v3HFSa_k3ZTQlsFg_d?0J{bWq7k(6s2gluitpg}X zf6JviSWE860173dd3Wk+*Z$;OaaG7@w1qe5Hh&`s`Su%(&`E;LTZ|716i1_YD{Ih{ zKvn9SJ8+PlS1SpZA(WV~Ne!%jD)4K+s|VR5haEtwL=&TKrw`UOfploOc8DD=(|&nUm1<(?H#7jv+EG+PaY4jabG`+I|Bhws`(6-*v^Uu- zmw!CTfEMi&e6PWGL2+}9mBIqP7djdkBJ8?K8-T8V+i|$NBmm886`pG5+tsB95#UdOR18=tH3>a;l*&!wle(5*wU%L(C8#tRf=(Qg zwo}^i;`YkTy&@4yCigYwv5P@ZJFX#!FjLsV;$ElLc7X)gDQ*FA$NMciCtFx1&woYJ zh}9+zjj)S5^+`2}?Tp5Ude>+;Yf9BcD2zt)lm&5on+_qKkqJkq)cX?PboXd!8(}Ev z9nP9Eg$Q(#QuO#Oyjr=Q&y!D2qoD08RZT`CQn~yE=9KqEy~qdw^BVR=t99$kxbID~ z(n%?&-xFb9PWlz&wNVG2*2Y$Xq<v zBc06C$}Yi!l08PF2k?R^AIm;z{hr{B@vLkaFr~9xI3E?(CvS=41+OUfIo!zS z<5TS|YH{&~OsVT6*|l_>knlB(h;!s~n+l!U^m7N`}rag zvwzumf%1W9BvaRhOcSQ9bAQT(JHa9hFm7_LkZU`rK2U7hG7kvi`}lG9d8$hJ?a_pl z656+EYek~Wyb$LR8#>zIM)I~3h$@wub>P?xE5i8+rBR}p75%+6{5wB_r8XFL!0?l7 zxKL$MrpNeo*GA?r@o`;)*aG7l`4vBZ>cFVgSJ~Id=FXo3OPhc;s8B)8tpFoYlFLtIJi`+7A`i@&uDw!NrY; zzbx1Ee*Yp%u$Mh4Ppzs znc?_0jVMZWs8qb?QB@u{@M!ei_6(tvN=^#rgH41QTk`Dn z-%3*-jUK??e1GbrizRRE(tpF=Sfe!n>FSYvs)jKd7|~=! z$1=!?d$Th&FogI8j$zZ!;Ki_~4Ga-}`6$U>4n!b$)&vn?==td>-9P?;;VQ`A?Ak!> zhce{o*U^(qdTvid18ZebhcllFVr)Sdhv+bz#vMqu&h5 z;(rBL(FNI6Y4wM-lXFtX(I4)wOG`PC1zcSe^0o{v^}d$gxLT|wGH`Z8eofZ_CQ#A1 z8qc#_w#ZUC|4coJ3C?<22||A;C7sr6Sk2p+iySMJ5RgY>-^w_~3ue#mT^)&vp?j>3 zEA#gH9_xebM={g^DKE-L?{lOr&^lYgUacv~JmQ%J1qeECb9%4k$d3CObq0A{yN zirRS#;MOUxi@0vAKpraVqn2BWGzvC0%ii+5#v={KoU14ff)8{$o_yrwuqM z(&>s9lj%tcA;oUuxv1Urhyh43!+V#plWe!^(vE(*CJF3UR?Lz)W-xt5qY$!U@qcb~ zs|iq>zPd+bji}6oV%YXKE1D6I`^=q8&kGm`>lVUBqX$c-c-)TZyRW^NJcj}0+@HxI z=|34^GS}XCD=P|7?XDeF!K8e>6{-e$qO=EEE2boS@n}z!?`Z}iOHeW7lQAz;)Mtfi zai4IHK5s#kWG)f>iPAmGQ6wn}M}L5#1W!^7DSFRcenI7gp}W@}w&BTy8P6M!fWq`7 z1(2iG;R~=#+U5sjc(;226xP~V6HSV9Y5b!QJP)rh#XBs~FdL4i4KOrF>~3==#^Cv3w%;yrI*>`qRM=h-odOu&=mLJ8wah>NV`{hZT^`+q1Vu_>3I$wqi=Lk9~HQ5#|p% z<#`o&W3>q=#d~c87JKU@T@W_QIKcOp7DRF8v8{gWaoj0dm!R_&Q^g(7ZnE3-=&IPw zc^&y(=}P@*_isOnl51E+l7F0n{6}3=hRWvld+D~RA(#PJ*)HmpKBomHvBUKLjP393 zSZ8?mwe%c6j!4p`?3tF^#_MPB3TmyOl5Q)#xb~KNl8sQdHB%=th$j6gao7f`#=pxy z!n4=TnvhD|TRj^B@1rW566c;wJ*=R~Ggfdk60A=fh?2~mEj~tRH-Br(*c^6%>hc=Y z$0ibW?WB$-&$*?;V6i@H;wkdZeF+xhK^aMoYq6h&JLwxUgy5y%-cMwPqC==QYfAL; zCZet!GdE@KVzGp-8(doDwn?i2h@iu!d3sySBPu2pxJkrqRWxY!eXp+J_4&_^cEhd? zx5jnJoq=f-uNl4?AXm#&bC>a&6qmV7evzz$~fYdt+2#4 zY>lgsUE5xfK`?9U>pHp$M=YbZGZnIF7@4DyH%%amwHn#yQgpdqZrX^*q zlOsH9G17|)X{v&hxTRvmVR#lxjl&pyAeM;9Sqy6^ zp2bpQF-9MZC1P?GLmG~!vCMdku?OUamXNj9o@M@Ta5GKUx)46na(c~S3;OMiw_0Th z(kgE{9d2ZC0VW5{H)Ks9s!Ej6&vLojb{oq)Y;OfjVSh+P>Sr@bBCw*@>GkByU0d!W z3AFQzaA{eWPX@1%sHD-z3E^H6L8KXGlJ=Zyh}7?Lxf_~dd{_bOIxQgUiE(46KKe@( z7-JLSskM{3K>ZDD7+9?&YYXB}*P^ScJ}2e$g(`PLgkTK7q}g}L{=I4xF&B4@?TzHn?Ns7 zY9(QOkWGBWDWpuH%7-U;y6fxun_t}zt3HUUoxEofk(Y?M0^26G6*^$k*1NQaN!Heq z)bEOYIx`TL-3Ke~;9X5Ww>egR98O6vsn^c>bbp5MEuT6Gmwfq)&Eo;jpW6cI2R?I$ z*zPQ)1MIT)rwxp4n<7=;MWV~yAuVjrC2VAz4A!1TU8x2uNzCd#)TKYh9dO_XsT zqv^O4OMoqlD*G|-NjI1P-}=Ylhu2vXM1WtlG2q#q)FHUJJ!kKh)mKkyhmU1$=PeMt z2V_piHU}WP76@*3SCz9GI8uij$=qD@);&NtPG?O7Zf4S$21 zU*T%O2puOfxe2rfRFIvi8B6hU^DXGJ@*$O3S=UzI7prW_%l!&|%b!y2?d<&B+6VV6 z{oR_SpR@IMYaZ;g_IGQTzRup?t%3SEiGGjfNgnpR^(~2HH@@?kD!{ho&qMt9NPb0_$b5t?bQerw z+Xm{yCv~}rfvzVxq4U|35fF14ZM&Y)JGXQpvya>=F1*Ev`rcA)*mOUrURS!Kc9im? zGfo)oOT%ARdgUHdZ0(#4zWV+$?y#^3W8ldS#eeq3QNfS)#1Yb;?uN3GUw_4?4CY_^ zqpIv@`=Sc(Z+FBT#P6m*p`U{crIGw^Ut9r4U*2Bd`ZP1Fd+u8WyiuA9%uZZ((in;p zPv0uwIi9G`MoLt+OaN}?SCh0hhfro3qK0juCaC$5XW1SMe@gsXv|92>iYeC^0#qv zNjv#lZLVEy8%Sze;3#oj|J&_#dFxQ4(UnB_w66^!7Yu$ZZT7UA`BDyif1Ab!o{)NM z95a0YTCu{#X(ncmfJUQl#BgTB2$oN2&>E^1)X2fL(}rj%K3x>mLVt!WEZd0FX?vJ{ zeQUVJYTF@;kS2NfmP-YSI(DO-a~ZQ@Q`5kE2eF9_M1OmeO8JoB&d7`S}UX^{eVy>>l54&dzzu>;_r)ca8I6lVZZ*%GHVZN z;|$Rr)S0n5((aP9Jbx0tzdBu|UnG^8&AYA@kaMa9V!XPs*R`0o?W+eGm#;Q9JEA0Y+n$i$a4%hV^qb=vlpI;L)uNb{ z58LqMXy=cmSOH0hCUYoq?{39}p`T8yi2RQ`K_wN~EGH4W_)!%}SBQXj$XeCFqtSyA zEuY5b3s~uso`3AE8!MZj`<28KmZ9ViORmpv&){C?=Ag@M3b{SYS%bP0hI093rSh?_10aXtoeW0$$w>K#|&{+)>;AOj9rm~9_J6* z5#^}&5G!jX809|FH(w>A_BUYw+c?{$!Vl}uTj1nuervpZW5$N6i??MRQihTz+j@M4 zLpFz!CYyVj?04AvUW3yuu*yp4?#glrx(+AZsM0EIIi!T&#%tio(Vmc(^0F5>_N<|S zP|mixk$<=D+Ce21h@Bnu_6}6#`Dnkifozc80tD3dp>&ChyB12SaThppZ7>bUy7y7t z4l1WW)f;1b(i)m_FWD`72!r<*&ZF4hC(GD2B5O@@FK`R=z`z!t(}60{9!~o)CP>a- z&H9d1o^Fk9bI%)r>QNO&f@a623j){k7A#f5rGL#9c*cXnHZTdwjkPI)b%zxcNs^T{ zDH_RQIVwf6do7C41CBcp)yOyESOo4zU4U}bTh^W^zPGvT6sNmw#eibzuFzVX`nG8r zg?iTvElfSjXGXY@Qk(OtK#C98X&TekPA{L-)=0bu*#eS@}?ALcR<0fo!$G`m$1|l|svXPU4}j{`7{W5Xx+ka%Vw^ryW9aCCsBTR2k^q&qrngZ;~b0v7BmHh=zDW(zrv>Ap<3)r7r8(eKD?q1q(?u|51I zSXy7I{pl3|U6Q-poyx(lo_f#_BI!x&v_9m^5K@ZkLX=df_ob&BJ1uSbeiapb?^{HN z<3zmD=EUU8U0W`zJ$!a$L6^-S!2o2s|v{ChSNde+sT45N4G38+cGxl;XW*F((P zpH}s=A-r7*trbt_Jf_Cbwbzcim-_d;I@wnv^t9;MTlM={OYEWg*pu(zY#XeOt5v`L ztrtyO&SUV}?x+ir_h@KmF=Y$4et$c|2Qys{A>T(c*)GyBKAa8v+L8HahTBOh#z!+^ zZ@V`i%W&vvj@lc@dZ)<{_Yw9bmGRvfr-#tu{TXF9sdT$G(;~^EQG7f^8&;(0dyP68 zZR%DiJb+X~Kjth@QQ=UgqWXew3!98nHP!4WebQy~jPu@8-pXDVt8~+*%YSHOdn*g> zRhPcoVrTsE8^*~>QZR1`n5Vf98djyjy24bI24gvjNbE$Oma6eezMI)zq+X(<-EfB+ z1YvTeu?SA=Bo!{qscjg+TkW_8!%s7N+6s6|KF!1m^B9fN7z(`S=Zww^`4Zg9#sZyz zb9RN@>JFr``kh5*p3kriyMLCyzU5ca+KxuVHOD5>1hC(lTW0t<^=4k>hPaqZ&=T2|^+`D!4ru=3ic5hBsCiK~MFC2?u2q36dtOa(jakD-|5I z5{N8Cpi*$#De{(oYfvQYjkD5rISR!Rhzv!_$V@i0ECbJu!wQTH&3_`iK%jS=NS9!h z-BToH*Rdu7*}>U1R0$>W_yvLMkjj=}RE{hVXr1K%65Qqv(;e~B`OF9ie>@*zLWa=j&WwMCq z+F=-yXl&{HeCTfs_ZeRZ4 zdDJM)V&C@y8sSbz97!3O@FXHU9zVO3 zH-SuIaKcC=x$9G7MY4pAEZpA}sncDJfI2uyMY$1_%|N#7lj^P+zYw7C&J z-x#kXNIUJDi+{8Yx7_tW4Q#bOGa4=Nh^USzy4bOt5Racs*GdwyW4M?}-5Jua!+mZ; zOm<*n(rZ5Zyz53qW+dh%@Y(QBGx%)e97Fmi`(mT@o{qZ6TTnqTclOQ;VbY!ojSh^F z0Ow~&V*z$AMWg*M|23bH59!y@ljr`I;amT2`EL#?Y*f;}{;&V1Cg|Y7a@l!RctBpr zGNz;G;Ch`fxhL7}_{=;MF-?m4FYSNP4<>K{p{|sb7)miJg6V(sPr9T@vN%Y#-0ux{ zh0AXXPMvvd*(M1NzOj>?$XtJWV#Z7IJr0@H{zeUr8%GG>;O1gBUrg`sF7?@L@%`?8 z@$(x4H6rSP9^#0g0pH%~i|^yf#m)F%`r_i|=3c-0d8se%_1XC9=f%z9{&u#Q+}+>y z!)9_f(fdK#k%A4_#of>O;?JKKllkKN^lbMeCcnN?vs0Wre)CW+wG;Dm8V&9}wJqtnUKdVsC@oaoI=?C$4JXzda%=O9T|JM`XWb*5#AE?RYWluPwRI1uwzqr^=}Imn z{QxeFIPA-$%Q%cYXW`KA`vLTgBxu+X*`*y49mHgJJw*h|kft<6w?9C;AWnl8HT_%Ti+gU^|TTCy4wH`oO>v@9D_v z=qAE}6)x5Woz%b`bM9L7{8|h~_i6<>p!z&m7%j8~jz$F0(`EtR5AyQKh>)VzEf-+rZkXE??%nSn99cPDP(MMm(tpo_KzaUOqmg}W$)0=vQYR_lJ?mjPkN z7mvm>S^Or}>M80GHMHC~^eoe`ndZsJ3U>^@c=UpWk?&M3d^=uQ?mlozyTsm6tIV9c zB$7K}Yz}OsQVwKI=y;8Odp%-48TKOr9P>Q0)X`(CDjNU?=BsNs))HsRtb<`LLYipw z3mU}sqgj7CNB4w9hdEZj+C+2ugK|B$CnT&Wab}t9_>vgT_zGkE*5xNDln*!?GYu@q z!@;qwB}u9rqFAgV{lIuh_jquXI53UK=mF-@vTe4>8TZgI2gwcA9$@HLje5ZeXa~mt z%5HW5cjQ#+f$;zzm1m-tMi^nqPOIWm;Xa#Ag6Mx0R{W!##Nt@&S0rNT=``5KM2JK7 z%mfku+aBG7dPoQn{pIg~uA)hRg_6|jV7GeE`jYLfu*f?`@Qjr%P(Zw(i6#cx2%|j{ z(LK1P<)ASqbm191pMc-x($cl~`aQvB?rm zm5_g3O~va%dFX~h-M1|~yZjv>%8m)avr9w=R_J>n8bIu_`-OPYk?pg#$Zv4jS#(^w z`U@hJez7j14rt+~i6PatS4Q-d#$oWXgCx-gLw1m-Jc0{eWuXzY;E;yxSbbx?TKJx4 z4=}pO1Esw=!oUCsJi}y*%Ec40eUz@4FIf`7#YSZ11=iBA7oov!@?wBI#gm53I}~CJ zjgX$p7Lzn0QfwNFw2;gqe07u6%_KvL0g@l1W61s+L+Fc-Bh_$CG{K9c${wopg>5|( zJc#^y9kBG$2?4ldlz8jW_PhYcO`)v}Q^5_d}0&K!TKmGl}yQtN_* z_&A~M`M5ZAP`TxFU}zj4cVA$|ZZIzLtC-NjG1ifm$&3+UghiHXl9$EibOBs^v_RSr zprT3Od$ti_xCSd+q-EhyH(!%W!B|}}J4l9?x(L0;2xm9bMqRzXyl_SpLj0A}6*{1i#=&wH%Z+d!CE|E;f8x z1(u1jrRJbG6)F|W#;ok6haniH3%j11&6#Twgg6r>#rPi*cqo#ig@+NRc>V%s$At>^ z0vx$7ID%swr|%mW<}KwtK}+_2V@M4=3^V*4Tg&GK(h5Jo85w^8F#@cE{D3UiC}NTJ zII>e1ypStE>KaAv9*W>avV63Ou|_faYGDT`R&heC`*w`6)m$X?Ld(tadBMfT z2AyXYNK;`c6Bd73a%3zqPCLW+0Yxgtyoa_y7a8sohFH(XXtGMaII!#(DW_wTf(|Yi zZ_MS1=fGlrKal{8ZgMUW))LR(e6}U~)Yd0k8j=rgt?-HGvT9j6r`Ur>FZgW)e3uls z+h<@c8d&OXuykbD%&_>9mxB7K+i)gPJ0HVdN2=PNgo_`Gx)oB6g zS0&_WrVW2FEdxlMqhWH^R1n0p9v_ps6PWGRz`$&_CfL6{mIake*?73uWyQ0Du(2+a;52WF(QA-`#c~;MIykJ9+P=+nF)rlc_9$o ztFbgNaP_H7_JU28Uj|};jYt#|B(ewabO(rZhwyZVh;--GtCXO;OR~Wgs9Y+8943We z_LB31PtJ7qYra^eWgH_Z)6SYsQ9yE-y_FIV7PT+ysRL6&m zn^UPYsCCmD&(RMmkknj({GSaTHdjJ=vj}7Y`y~w(aH_M2an6-jvu5o+7U$Fw2}k@ z_PPuKqXAF}r#=0mlIRCTye=D40iOmlFP1}1^+Uh;iJ(Ol08y16`VR~R60xYXaag00 zp8d8^jGf9wAr94By#my`X1X?wgMcc4{qS>`N!?ykhCEvLs{NTbgZrIN!*-bu( z#_UD_Z{KdHOV5ogH}>KXU#$&Rj|%=PD?Wg$8bj$>shQ=jY|@WvDHgJVKUkG7ya85- zM^*#bPxR#^?wt@%iA*@M3bU)>alI%16Gx#|C~);yWq*X!g-q@Q8#_O0dHRr@MqJjAQg8+ky|si#_!g&R8y+U$>(-FyXBML0VNG_BfB zsH(t!hn~A&RH3A1C6j4ih{#J+D$NXJhD?4|rj}i-0*A2J^R4V$lzQUSVE_t$US~ci zf2$NoZc zd@Q-lBPGdUA+TUSNoU$*4y3nLG5ShK{)RS;N2fwBSUAM-(z*pef<0;xlrh5uqcmkY z5n_3~^oR%EH>GndW4tE8gBNC{vw@_CK3T@utrj!8Mzf%cB1p@GQQ)~N`!$&hOhCaj zDuaxF6k^}3p9U&RTY$$incT(%3nDut3n#y@4b(_XCjFQd0n21>&if1BHXyy_+6rT~ zbwR`1%~Qlcva_6skllrb9mKih6ZoK^x&jqEoB;#bXtZq0l?f`6-Rvp9UTEmfAEbZ^~f_iLfCF_F!gL} z`KmO&TO}U+_<3=EF`4W7)nanD(0`3D=gO_wj&ytR&&ALA_-6dCi~0C&f`pRp-7da= zUCb~4P=)Z=)39u(J2(Phlw1?-8|lt(da`C>uusbGu&tfsE$9`0`^{pD z&9XoD0&(Q4a$wOcnxifaB;sn5yNuYeb2?{Os#}R|0O^?u$kub4__V+ijf?Og*zKtN zSkix@>+-g`q(C@%Q>gAiw#oN=g9=}SQMM-wY^FMO74fXk%#DCrB(FrJ?3+7f9u&Lu zn9N~zFuKJ9dg^YFF!p^fh(hXrL6^_jI}*~Wyt;;CEtAY8^~P-oJ22B9WzOF5)~tn% zHA(V!e$#bM`plB*oYR7w<%(=(nMIV;ZNP=A?)~CI0(LgtSlI+@khe$!9p0_-vyK)8 zBy9z{I=Y51d>a^HKN~JsLB*sIP;nN^C(l~K#I9{1ATF^@Fq=u!xFhX@}*8E$kObwkjGP>fkdf?`Mh?5w{y=6`#!E+U?t&6b@EmKynTNokzC(4U&bypLU0A7n~`$7|P9Ki}Ib z_n@@C%kp%A*2CPeMa!dq0%lWvz8HCQo{Yt#KO8KKy6D9ZN10_E$aWV|CO zlVKp6jI4$NX3wXdbG%8#=YRK%uvqCph!lv)K~M%p}e0=F!0qQK=u z)nvoXidDg$``{UYnT`tt;vsc>u4&Nz<2^pIxy{(X;Ot? zk#f9t00rNZtZzbp`S6;+gE=$EJ$sFMcTgaKi!i7eXPFF6sJ3PjMy~Yn{$SI-pKY7= zjvGcs5TPI=_MT+#j;?-@yGjNVkmBJv%pPJ|0gZ~YyCdMz)7DPjw=XG_&QCbjOWp=e zA|B=KkDHrY1;0l>oo7fXZDN$=ER68gU8+lqHj#7^C58xpBH_5QGr|x|5DYK+Wp+Z% zlM8dWMN;?_M>NiKRT&j2w7jIWE@8HF5v)|tu5Uc=*?1y`33i;)ArZvmcgbEFc5;7; zt~g3JsR9yuaj+y9h>!Zd$i`3d@L33z?sPk!g87(+tb=d*kMU$N|6@G49#4KOrhi<_ z^u_${TAx5PeG^ZgT=j?s>1~?QLHtZpEa13k3TG#RE_sPq*i9IBz>`6KwDewST~T;^ z_T=3QF&7jkGH@Xx&ws{206g(*5f11fo6^g-i0iF?4T!?-{YE}@vaV&@NbQ_n1Ww!9 zST2bl8B|L0Ms)OKC5h7@z{HG01J2>Mh=cWtZ2&Niu}!j*{17r%rX2>*1-Hp(elb&p zMHG07fDUipy7U}pM#8XGomxo{$O5M((s=NK2vA;{mFzfxA|ckrb&>IdV@2Qs7pfZy zlOJ?{xdi6YTBLz`v^M!54y{eF6)v6$@fU^-l3myV;l~d)70RkMBBHPv(z8txMpz(h zaq48%7l9Yyt#EL&K%00--~4AxwZE`ep2EN?WE^~-o+;{Ek+t}Cb9Z^Ym|b4n=rd5k zQ~iE%`Nzd%qTeK67fVSHgz;n!XNTMIKlQ7B#q?gk9M9CRv~T22?iPRkyqL`41pfLy zJpz;V*U^P`0xNBC@z1UuF>kPgdoKf{>f8v<7DLeIl`eb%@znI?q{4t*3qcLxb36`tVCl(lja-dt10TF2830lFu`Kk-2p9iD0*}VomKy;I zrm=Nu(?w?D?8VW)+2533Ndd4-amt+tr|Xh5qy*9=+5OE#tM6u(CHp~6Ib0exWV50e z0>cEM<9X3jDj9ZU160E*i%a%vNo25p66}`pdi_4V3atl$7btk!OpJ2*rivU8zg?9G zTC=+Os>)1NI9Sn#S$6+X`A$t$5J*3*i8M?z z$tq!206@w`H04`t=A+`%jT)GqR!8yK^QLM2Ni!RCi|n;#FM!2*FidcPU>&-DE}E5v z4~Y>hpXl7MCP`7)MW9~oq75f0Kff@7z<7n0P6ws;2rJYid9E6)Txx9E6i;OczG%p#>Cw+o$(da14*@$AQWXHl$|xXD}xcHR;t`TYz%eH79tH z7*t(gaUNaY_{4~6Csl9=z5(x8={h=OAHo@Tu=O}=!kM)rE4@;JK|UZ+9JsKLCbdK4 zPuO6%)eHi#qe+qO3f>WuS3B5H@~Ek7!{1Cj;7Vj;mc33K#V#IyfEBTMlPyGwi`Hl` z0r?vjB{@J(e5$*SSTbzzjAuEv(ZVhVyUSNR2zH+)sp^TRM-)WtK06x93-z_drD@tG zuCdBzAnAks3PQqiL4zjV^^s+2XIz4lx3Kegte#H-YNeGCJg{oeOV74RQbCLDK^(#s z46P#4^@;x)u^;7s6BfYrvkF9VXxcUzLd_*bI*ys&YydS;*Hj20o9!qs{dmFNybd9! zC?+_0NINjxXAHrxY;hvSOfDVXyF}`opiYe!)CW90~7@KhdHYd;fmi2 zpYTZZ1Ivxl0K)d*qs8=LRoY7^K$aHee0gxf-J4Il#0L?;Lbeccz}5uGyDv0UP|aiP5?k&)@=;os@ZVlQBQ}5| zzY+rY;&>xEeXABlH1Jw=BY2atQdk|TesviotCySFo`qsK0NHl8VH$n}G%q$VqQ6ZC zT5?ufd=aF7#l_Qw_Ot6D^`=K7jMBz{7A(HR8V=tUn=BAIN0*96-(Y|S+EuY&VRln2 zFw^SzNn=0YE&>_J*QLV5@g=DOLF!O@TV6<_*kACtT$nyx1VoKc01N01M-PKW!-D4| z4FI@nN{4jAt_OgBh9sB<-nv}1U-{sxTPSD+hix!_?4cr<`E?5l$bGdf@&P?jslOk5 zV_&yEqVQjxa@%A!vkoj}xw4Em z@Dc;hSvlY(VF~zZZPp>}O%61&Q3c+JcoQwnhbYeZ>yImoBDafsi^cW_o&`Cy3VVw| z*Bi=zg4i`NZ=iC#6Do$^E$}TSTVAsiq|lV~2KLq`6ve>XM7@R1_u`izkF7%AVAS#I zju?ZgkT($Dth_8ZjdX~6gT>(-X`n+XYO6Q+e(gX!SDJNSZn;@ z-gZNk?}yi{xuaLvRhC?GmD=w41m}}Piv($Z0F+Ao>u1L~0Ej0=6;Hz5?y8bVAa>*{ zVn=3VVm1uyNe5o z4r|yeOFuN)DhFaf5X9pE_$vhxm<}&yi_c}gy6iW|@SKoOxgDRwJP+NFU-}!7{u-kdL4fEB- z_(e;k!9C>)V^CwXEpzy_d~@-)!I$!u%;8s9C%nZ1+ZWt!eH|d>Qp4TVa&mirb%zyp zEW>kHyoSs90BiU)c5{jFrO6D~6WnkH>?5@sk=Jql>#*zlUgF@Zn?yGl**&q%#mVQ2@lBOIQcaxBr&-8&@ROH=o+Ij_t1G{J4bD0VRDMlL0V z3@E+aE=u{>Vm%y+Zn!26u^L)`yA|5sM8j^|5#GGxcF`Jk-Sop?9X0*X$W%e_;1=p$ z=H&Bqc{xe-qM7iUyXD~WTUj@VzMI{4$NBZkU}C!?!v>3UUv9H?c>px@gggXjw&o9@ z8qK9Qv*C%+w#+uxW(Q&LQJ(#4h|xZ7>){@r7#&Do*IBuntqvsyf%!gvT&4A!%O( z-!zat^m>Kl28(r9YO^J@2h((H4}gXq;HKN6d-4bOx{&|l;7j($bFA4P+bygg+pMe~ z&$P6DJlop(aZt~+5!k|iFAc3}Ge!SWZvL~){3FRjcf&^J@Lf@^ufxEm>0adXKfZbQ z?uD4Vc>Vg#>&f>&ym|ZjmqC}|K9oEk)LD@J_U7l8FFyS6u9f_Tc54geg8nRqjzta- zWLt#gSpZ^7G>~C*>`iE2}-@pCo?}M+m zZ8S81>JWBUO84GbYtn7)SkOLDV{_6r2G~a!JPLUGHoSW=tgqb?*|75uP`cOK(#P9n z6NsVBNGH328QGWHY@Hndwas}tfNMOn4xk!MucqeX0HKZf7&NlDmpFJ_@%Acw3V$iT zF8h?~fvw&#;Vox>=`P;iyJ`#bMy**%Z#^O#m^1fUt7EehXp8WvOuD0x&8xhFz`bkb zRNkG}k=(UTlvHJWJe+FSZ}O->!&?VUQbI3IjB@D|{^R$GAY!gXvBTJFnj zw|e)1TK7=PwYv}1YUy^@-G}8O+cH~r(KgJ`0a7pgegLk2hwYp#!R?mA0aClM_^F9` z{^<k6?i>R+!?FZQ_k7pt$aiQ8v4I=bGwzCQ zM1S@`+8h0CoVIPD$3vP4Z?sRc4>R~-**?I$T$QkYXeYnbDZtO=bze{#Y`5DM9xm+I z7X8=1m)Ve#)7^YtX3JLTH75ZEr`M;E8m)}41J2i<7##X0f+&Pjwd9715$|D6S9%*5 zYvZtnlKabRxmCkUydKme9u?j{iwiQB$^ze53`p&cz`kI|6%gsr$4{>%P*5R|M}s~&wqLGc2Em; z0{G2~KfZl)7NGxp|MrJhKYW;MH}xFAZ-4rK>CZ3z^ybCu$?G?-etP}GU;cOw)OT-Q z|Hm&c&VlroKmPpU-C2Ns`pa2n%76Uw=I6=#pMUz>53k?6J_lgubi(}N?ivJjI8*ZX z%jp7CXH{EZC=0SHb#S-5C;p68Bo2{Vc(J&uZr%U=;R@m7$3Z=|^7sjbK!(@Ke6=Wl z_ER)ECH%2!eXYdx({($6@F)fMf|(~O(@Q%6OqHD1$S3PhKShCkp^wyKz%IBKcN{xi zhULZ8I&bAv`Q|5Ruq*LlCHgLSs7~_J75Vyb9MxvHA=wdlLW8U6?Hc~!lHgC#jFPTm2H6!YOv~*({+A-pRC0r=Eu$Tb(rP(Mwyc(XP>0ZzSQH&AWjQD1$8dwNCGI%( zHC>BZVV}OQ_5=+Mgr3l&yIZrK3&$@}Jw=Ocfe&i1>Wb61m7c7{w$u}Us%+1QcTJ|| zyGPE=>uUrolSP&*ZN8HB@C1#HOFp3${fBN8+%2aMX23r|p97)asLF6XvoG^eiu{%G z>7Mq^>9&YRVSe?v_bJokgzOWFZJ5=&;kn(r$8ftH4ThTw?;hrM*LPRTDgGR;CZ!Jq z7aRZjaJ7u5IGLl8AFtql%JY4t0LE|%u02)ag+cnzHqaH}1mDoLf`r2HNdg#0V=)(_xeXlC0qMmdnRxTRsNn!4`}kC;O{ivIo7oxv)9F|LRa|f8pT)+4*Eg$6l;% zj(u%R4ly1f{IR)t-zuEu^D*_u-vaTNj(MCCkLIM`ti&-!y7Q^^Etg4{N`jE z^WALrxCF1?DEj$|c+y4YM;V^qiqmDnl^G02X^L~vk4sySRYr23K{g=L_N3|)mWCVp zL)qQE_J=IC!mx~mmSGF)BVBuwSp z8V^D75&_}lx?FGC_lV0hPk{S0`B>(&p4PWSn%`iRZn8>Squu2&xj;O9xw&oLbkqoL zv7DE1J-N7hY^LsSMaw1LU7V#|JyQSS#RT-2E|azgO{=Cg>_LL)4emLB=H=qYI1dRFsehlbCx$B%dG9v z=pgT|CzmDU#pL6sreK$0maov47|zAA+&0EqOm1%$({9F;>sWGLZPYa!KmzRsZ9-1z ze6Se2b3_4`)11+^GayYD>oxEVMWCJlw%HLs2j0g|lN8crnVf;SAh14b`UqUF3R#;u*-6NOTW3BmvbTB+*fWqL~ahZ&6K)b-8E>l z8A?QH-v%^o;hLB=Uhag``G|7>tw!t|?Ya$r7w|-DcY7AF#d39!(Gux)LiY#nX4B5) zcG2zR=5Be8C9sD*E1%Edn3VZg?-%MUJ!wz9?bdcxQD!>)w9*G|AJmoRkpWx#F=7>ufRE*71CQ zOQ#1OcGq@mptI4FbL<=UNM{(E-UfF&D-n^{$Hs7Xx0xDt?{g;c%Zfuc9XYD?^{?2N z>u_(ETg7h9274y!aA&1*#Z$(yCy%ivTJ(NL> zYG^R_IAKGOWtbEB=ySOnw&(=!Yz6k~q*W5?0S@h`e4ge$+oT=NL2^PnsIQ!WH3FtT zPiEn|A;!+meme-5zB8h9+YcKmIJ-Y~J`?mA@a|7Z+F|S;khDSCJFaL0vb(F@2ID?; zqd%Iv0-@;k!B*+5tx;*n2y4-Q672Y%eIvAEJLc`6&OkGd?31?vT6~<|Zd<@^CuMOK zygqfW5zOv}c}tMC<8y4Ayb;oTiC?YREM1AXtnIn&?hfa`7(-ud+`gSR{9(+&MaDcG zGVi}3T%7d@1Zrc_;Pq(*|BFdSNC=$MzU41zNTnm$X0%$qu2dAG9XZ0Nh%4?s?@>E!mTkoeenfWGZ5)+fVt zdu%Yz?cvC*oYiX5bG?%#UG49tX!{0k@N!s&=5Xsr7B^`vl-Nsux%&OXS!coT=W2VX z<=u=p?9j>Pk3gH$yDxWVhPBGXqmy*mFZpe_hVQReRJ<=9yU3u%-TvW2|Op z_*ho4-r`>XIr-=3G83P!{uR)lrdQ!ixZm)O?UTT6uX+MNk$e2o)13CO8w#-ERo&m4 zqkfv^ax*!j6Iqde<3<#ODkg6gmu^@$@oPvef~sG_^)0=;Fm&qsuH5Gl1nTq696aV~ zm9{_Jq3Ax;{e?!%g->M;67^*=A3VQi5B9!R*zi>__Mv7Ol&~p8o%dUPUnaL@7Os|G znxggFiD!YLZOr>j_|J&oZ$39Ts6T?bdquk))O5DBJ=+w2=C&!q>}CQNQo?dFyO@XT z_JhOWQ`#a$fd38fR%%zsmA7wIv*j>Fnd`O3)b$Z&!`9S_Jpy2Y$?a(b5It1J+D?ex;dzO;* zyQPeqh;EbSxg&j(&z0K&O=t8_!QwL94!RSxRVAj4)OGEd!N-+s&G6l^3dmn=)$bl? zsqRT0wjRNU?uS3j>P-uoE$;7cNgw{s-nQ_&>oVkjw)B?hZuT`(e1Q<9{C8=i`lo66 zJfP%N#nD}!`H0u09w!}<4Kbxjf5UU$@8Ul2bkq2efRB6<>V#JJDT$AGsOm{7ofQ9d z&04ASTXZ>D>E%h9>`VP-J$4Q8kh*k|zpl^GS~5@4V_V|a@gIL;@g$|b3iEYMPn|wI zNv}PBp^wnwBu99f9{XayU6TQ)@=?(zG}=_^xL%crdgyVr!OYG|@MCp4RqpFa`s@ik zq05fn8s1|)!dGo;FiE$!CvQ9qr3eWpYZ#|w+rh8jBo0H zxEC<`uon2H`#T^$gKLfu&0Jj2HHR?kq5jXeLy@5ITF^MmddSh=N&bf|`5p5AA>{6G zwd?ei&HirtFTX*91A*i1zl{Fg{k|LDl>z^5`!CP<^AUbOqioL6dZvvj{dY$Xh`d;Q z_mZ+bZ_B(+Zs!3}Pb!m}+2nO8x4)Es@^Sn#pG;?yekuO^Vf^;(yI#e${PB)_0KZ-X zZ-0k0x?51XKp1tVb40sOqvd58UEW<>&@XC8^q07+<9hjY3Ftj?CubbSot!br8AHx^ zC1*@>#v})j|FMF6w+s2F73B8>`KP-`+O5jCjkR-5itjPPX^im<^#jX?*d_S;gNyacOFifL4@B4MpWQftdYozg< zk5@=yYp_X~wZPHOYh_5^^{~@(Emymv-Oq%_j&~aA(@mMsb*uV;!!4_c}OOk30t4&MFz-!$GZ=J8EsqxmSzSpMH02 z$uu3`jMpE>w}1HVr}eiXjE~man}oZ5qi+4sVEL6^)ERyJH0tXB_uqRA=t^qW>Xp>- zO6s_mI^Nj4l~hvZ=dUaC=fCYJgEolYqTnIAI1sI#qvNk{r&ql~)7fHw8LqBc+0hkL z*JUfHU6TrRUTvxK!%CeU>#CoRZf?m+gsVS{mUpu>qi$2p1Rg3B;t!=ZmYm`Sm|`J8hAF=F{8d;=9!+%LP4M z{oT)RUc7$yW;L4qZ^oUBaVKMRMDDYHK#j?laDDas_RBYe;Jah`?)di0XiLtsf1q8H z2(xi{9p)dOFD}1XG8y}gfbrsTv@h}5Kd^v7{6F8!KT^Wc z6RT+JqrLCgETvA=c>DJoQ61Lkmo1ca5Vca^wAH@(1f{3t^ESrLr+e8ub~dDR2g~&3 znDOc=&rSck=Wo;5_`|k|La(g8x-H`_PZ7gZEYEql3cnVA(17kSJL-^Q5X+J-sf^SG zg%=lMV;Lu~jPE|YpZtKPcTq%NZh&4Nb3V*zX|KgaQKdcc>TkR$;&Iq|6H!FCh*jYLmgHs+(#eV@TazP`U(TRu)gxx_}K4%w-wer z3ptOE!~vAlK1Bn`_kFkd%tp_?w7@E`dluGz{YF85{rA?P%SGy(&?ut+ z3i#L#Sof>%`Y(2A(8s{=^HuB$E3pzcUW?o4@E3r-TZ6v;@}UEL*?;QU+Gy^gZ^ca1 zMg2$aKfAoSouYO|Le`KV29Jr5?uZ7d&pxf=irySENArM{SVs$D8XY)H1X=H zTum3(Cq(UkY%P?2K6=0P_33QSb8N^WVxaqH3yz`ee4+>FHi5@~Dk1;->d$|@EAub^ z-bDm|#PYuFe=vHn{@yO&5hi!+_dVFF-~S$e^!>wz)t%zG$E6+N!q5;ugzs2?@m*&d zo;|b=c2xMO{W1#Sy3>r&yUj2D(Cs`f{=MG?UG!bG+ABO1I4^gL@-SxikqulQF?K(@ z7e^JVjtZe)Y^d^xdR)ZO??-QMetxmqAKA>y??#~5>+pPA^k>8|X-YfoS$s@jyIK#{YD+w&b)-{Q^NN@v>7bA<~#a35rck%Z}iJX4kEI? z&$?juUAN1CP<^(zyT0w0;MK(qX8h%U^$EuNwJ{Og9fF4*3`s&;1%jvT) zo82HgHYp#%D}{ZSaZ^zrs)x@VY= zf20?;qvos4FZbl$pbyf`jG~FfY0=xCT6x5-Wv@%63LxEL+x|jNuhv`iv_W0wC#4_z z@R26;i0f_sx828{9UZ8XNIN5c`Pgx!xW2+voRqr$z!9na-tym9A9xlPUuJ1~1G2dQ zal6mP*qwakSF)jH@m;!GEN}LLtZfP7EeS7Hzj)b+zE5^|w##+)*U^E|y5}#O@2#lu z;t>Kie;seWw2`YIdZJN{@n9Euz}b`nQUZ^32VdU$M;w- zj_c6rhKOWN=?-8TG@7e_l6wEb5!=zJ+w55B^kP?A+ScgyhtZBtH`C72Qz{9i`vvfp ze~iZzjzxs*HB7JYuf_5o;HH!WaN=AgO~-pKa3y%WCHPS4xEK23m=;Hr=yiA&KL2yH zy~8$Iq;R!5NL(Hqi9I|IKmT*Qvst$iHC~H)@%O)u{<@9z%L?m%`~CyZA_ie}9ey1z zH(M+HE*|gqkm@Zr_oq_>9w`EMyo=lK-tm5~i*PpwY@?SawETIc<@fKQ6U)Oxw1!{rpt?EC^4o!pmOKU-scxw!-0#dP+E-IIt_ zJo7O8>d)i8*wpxf64SohMn)W5!`;<#y!GiFH32{F;CJ(X57y`_#s5Dj`Lb7Xhdtt- zF$HxS$Zt3V+H}UVovsR_84Pa!-q46h?Rv?qE}wn-aBTHP7~cyAkN>=0e&dz!mxr3X z>os``O;(0urPGiw#%ql29r+E$q1xTP-HR=~*8B78?>zhJ zAhsHU-#un}P^$gP!7XSTD_!2)EJ~NdHSadLc9>Rw(Q5I{XP$&J-r!LFLyyy?lXW<| zG;EFY^0(>t>^J)G?YR0WG+^{6%oQkmQI?~=i?@b<8)|NS|KN0>$NfHBrJEUd?B)1R z#2^k7+xtKd+y8J(KP8wjqW$EnGU`Oo&SW=bfB4G>MZ~t>2RF~{uOnjDWj=a)6|TeB z(zn6pM=v;ID}DZiKYm)!4-Qqi|J|zb^r_3R7^&yx*G|axoZD|OwAh@!a`x{GpI+X4 z{BALS3QPQ*U3a5ir*rgTS8igh5Snxq?q(|ru&dDKcPoXc`8^6I(X1<4HR5881!cZl zltew&b$}Ri`Lge-BO~*le|<6Diq3a{?|;_=)4|===WpjXR3?tHCDpH^Yx1}EJ-)?W z2^zgbb9_OUO4p7t-et_FXAiEoL!};Cn6zJiUh?SfcGO+W?zT?5hX3-@hZnm`i}>Me z`p>)4S-B58ebPL_J#5u^g6h#q?1mBCi~YmsUhd97k&w2`v)|Lk_`LY(%q52 zsaOK@i_&e7l+l~_|NGe!@?5^w+HXmh+073atv-6ft?t5@NoRi5K_ zj%0mJ#|OW>!va=rs{i=t-Rk3`-;dsZ&==(HSagxo{8i8CIwW6wJGZ5;k2ha` zxg+gapHIEMQn(jGA5H80zjnSdzFehbzgvrVwo0hKoj$btwsShMPKu|m^k)-@FBdC8 zTW3u8=VlWyAB_zk+~Mm{?teNadG{gkIvng!U+tl;2WAro_PTX9Z12AHxMZb&$j+Bn zu-iXdft=1&e0-Wt|H~aoJ>c%b=3?`ATZtn6*f$mdX zR&)2Q%e%Ov!DZRqbLc&XAESEkz&r;AR%bf3UP%N-?oOP@S~ zxt!i2n(Tbq_{24sZ_#0V0%CpsKOn^61pLi&_IHn;k^SD${g&8o-MCuG8i%cH@omG@ z<7|TY9doowcHHcuji0)UcCX9>yJz>v_q%4}{av&B4?WVde4}aWwfu^IW$6`o%s|qH zeCW7C-^#`4(=?3IRl}XxO)FqhdhAsXFUG(g6ZXq({eJ27d$XnAtG7QKZ39i;$4r5N z)hE+=FiGw;C$09UM`xk>As(fbg?f_p+vv6Zdy-5hpqKnu^SIWz&vG8c=`44Iir7E> zJpKOnqwR#sr)W!Ex5}n}UgLBpU-a{|N!xt6t=9Wqt(W_1QQGD@Ws_9gB*oHB|B9qM zDw8XX*MBFXHeP>~O^p5TAtva4_G(8KWky`7hkOez3Tt|EKNtZ(_1XBSy?h|N;?yp3ca$isXeND8T0177i{L4TqBD~PN=OC&dj=g`iA5_Btx}Q8!nF4i|L20r zQj2nyu_!iKFKSGwCa#qcJPTD6%Mo2vyc|-8-g~^iM9{vfN7Pa{8pm`LRT~)8;$q}h zm1qM~GR6{ORJl2RW|kRU6|1$z9K9>aWf6kZELiD(+vA%8&!Q6yT8%b~R0`SIYD;1v z$=3Li8|jQp-WlaFyP^tJOP*N@A?s?I<71U4n@uVv2hBy2u2vh1Wt#EY9v=%SL>s+z zCT3?N@Ug@lGtLBSIBSisl@g}9EPY}acxi>RRYu7r_a4)rHNG+0q+AR`AHbbEw4bw- z3Y?IC%EpKG_|?P;?;R6-jw;Mz1!`5Sk;Tf|y#1DA`4{PZt<37mV0K_&C1aU;E{1h7 zNAUwqf03Li8BG=nj7C?-MU=s^5?kXt22+>d*tD-XcmvZ5Q@~^ZrIOk=w|}lUsf(}N z)T~VADU@0rtIi5mL2}#U2cKo)idP?Fir!#av$0jB0+Sr0<<*IrYxDjOFgIRBYB)G%Hb%JsdtkWE`|?Mq!Os=;j0eqs zPRXVyrAS`c#GJ5PdoW(p9v=oj%uq zKmr}5RoEIotL&LUXrU|Cn=K+%g!J0z0zTrEZjPTkVjE*iPKfaEU*>F9tVo536Lxt( ze5%Z~72o`_q@q@B#navmqZqn6Usy?hFz^gB8(kfP6v4$o_ij#U0AI?KL$rwXt(b$q zSB1M$GXw8Wsl5hhu&rE4o=k8cTgmuXV#)~X4H1p@8d#7@klG-vbvbja_>2zF_^*hb z4;tp2(xAY~R7`Vg;N_f?+)7z0#aM=kWZP@ttcrpos$>YUs`Me4EYSgIKYXx%7wt6& zaP`SYA#_ki3Xu_Z2b;7*q+`H#+iMV&<2nYRMK>I^O0A>J&VhM@bo(=CfHmmRXl}3) z3it5(OoD+J1Es)++G|j(^EJWv7zF#3IhD1yHK{_hOR6D5&etX0T@1c+xh0h%XvK5& z8pfq^;*1>p6_z%#>;+lecEHwuM$KvaM#_*(#(YxVXigT6#X+gVF0k`aD(@2fbaXme zRxMANm*O#(O5p8)vxmL3Ia}j&MWo=o-nlm|Ox35WFuqku9BaAre4{CPOQ;L>9ROrA5_A zFkWDX5eC5>2yYlSvbuI-oUw?cG>9`~C?bIT2LbcMfW{f8W z@0)7?>z7J41V*H*x;RsR6pc7bstE2;1?IWSvZ!XjHE{4QSF=N`h5xavv~vz&7N(eI z?VJSp1V!A7)^7yU)3xYilnq{H8-@k$%TqP*x7&j0(17toJLE>0l8a+pTkfT+9P8IG zott8Fp9E$Ntx-^DX0^>4jMm2BV_>c&HkUDa%Y=g4k5YhSXcM`AVa6&^Y)LJ#m5Nfr zGD{F;2Y+Y-+&|~!j%}$%x5U=0fMZqQTI+SHCa9R8z3SKMKEL9@swmI_o*e3%*Dbe;zoH8L#`W*t-r z%Uyw()DmgtWAU}b#=0uJ3SpfhQebM%St*-x5iu0qwB6Z%gL-*KlviNDi}x66Zylzd z%*^U^BRXkI|UJ*=uE3jO~y)w=qlYomWzcBs0u1rV*lXE|Mz^dmDkEOUC3BV5mJB zS)Hvu@|;D5*U$}-eM#1moiYv)lY@QEsYC&b4V{|s_%(8f4lyFDK7}OcxG*LQN(43r zVwM`tFw8Gy;gqntj8_@|Rjx|TV56$c+&4s~y#@<^!^EPARvV*L2pNNb_%RlvS|Zn) zfk4N?!XP$HaDoEPI45mu6AG|Ku0}-=A8rv@NoAxrDS>BVK{@YAXo>8Va8=s`t4UL< zI@$}D$-%NI*>G;dKqqcIoUT_0&r4+1bE7iL(uc?z+Av`v0+$qgazS%Y+~g>yIXkBe z2B9{8M5b&rItGK^hz1@C=FGy9L{JWJ?3TUlm~g!0fR^jX6!T8QTY}{aSTNbpdP>f* zY~duqrEN0YDTWT$N@`_kleHnT;28|sg5w6t8;=nT-)P6c?_gX?OXQLZCUZg@g~b#o zkJh2*1zd@)+%`m(27Rrx^U*49982(xTpC_~!0-cWXv3sZ6ulHg$u&vlv@k+rA;XR; z+PH3r4CCzS_yyh>UZOb4&WFqJ83B7S4ZWlc5)L{VFImL|tB4*gt3pSF&P=!Do-$Wc zY<2}BZRri2geVeWvZZ_;XweQCv#LWfqVvEWfu4lLjn-H5anN5U$ zd!*ED7Im#wWut0th@4Wa(s}K)r&I=*F|0Jtf+zvZu%WL~8SB)~h9Ai&(sWrTaIf5H-S-W}pj}g<={qK-zY(Dtez_#bOAU z=&&ZxK{KPQ;|-B9vuS@1rlhLmMXWI~16rbNPL8*n+X>NJ2-0gQvg9gqZ>t2=muPef zE$4Pk8V!|MBhEpP!7N%@AX*TN~+0AmG$50)P&*O4K@AU2AKwjmp`2wtW2 z*3vz$#5^nt{IXIoXwJiOH$=`((;bQ8l0tZ8I1IO`@KRi+Y+6QiwkY^z1eCfe%CYC3<)Lm-|g zh_H;bq9L-9H5l)Nr~7_?mLt4z(&P|=kfPXzHq85C@ef#_u&^RpA#Qg7SU{)0I%

      zi&$VoWbkYO5~!_C34x`A1%jH>OyjTeqTN{0s_+ zxRp?2LO_#+cdAGuf-EKTmUBB8#Sm205@_Fmml%?#6xOPR$kjKro&j;Af66}L51GSu zM(`6@kyulNm2tHta)Ebtsumq13-A_{aTXG+Sx5-+8X~6>z(SnMhQ>Ae!a|J{Rtk-2 z-*68wz;qvpFb~Bb+GJQHIGtAZQ${5|U(b{zR*%d^%x`q)QcmZeL zz(dF)vb7lEkbNdblDQWxf7`4r1Jw+)2MNCgEXv&wp0Wrus|{Bb0vP;1FN`kFl!^ed z1o&voye5-dt*xpsiCg|+l5QynnxS5sf-9d6(Nbqe|rZe*bq6mY%!M* zVyJ*9%h3f{B1Tmtx|Z4!*~?sD$>5un!jeufpQTtQL*iAwKGz_H&{c!?ORC8rZPm>4hSoC&?G&q)cy^L>l;OFECc$etW@5uO zBd(}$h!PQVh4JFfe>hC@6kSjyvD$E#xzL6mmT?C8b6i;-8F9{1HP$oqXo$>V!Gu&g zGFWWPFo&pvsaj#eD=RJAjIaXi&sdebjf}`2jEjf$rs^}M;W(E>@k~ba=DZakM%6Qh z_GjU|4>hzz_L`aCONuPgod<*(aN1bs1~xr4Y;zSh7-kT>e><6Z4KYN7bP9nUG11(x z&2(TCO+-|IMq;3ecy~2cD1`_Fu^}=z38J}bz1BG~7%+4IsDX@Hhhgi8>?4E!MCO9G z;67Dmn<=0z2qiVl+prPcmsz-;rk7!vE{DHmav;1*eq*p2ST=$sX)uZz0c*hu)+Na> zY|pJ}F9fgu4nhx5k%F zNyWhoY|J1665Vcu(;`I-37CFse8n_ENpBFcijcSwSy{UFVhi2939L1~4$>l)Q!y!t zNG>QTb#SUgS86PZx5kIxAl{8Gmz=HxNZO`~!a*0xX#S0@@jd#zL^@H?(nycLNH8W- zlCW@~!zOwh!;cKnPU5MCEHM)eoh?}9>AGaHS~kZ|r8|>{@1~142y+wN+^;srh>*|N z*7$`>DGMDFTOl$}rW$8um-j4W9CXucQ)PR2k%Rk+U6&6S0WShO#Fs!A0Tuxvmsc18 zZ2=LN#TWrX7kr4#buCimY7nYNtgS*NVT+IO$A;OqmmnDd7JuwWJ3-zCG#OJqWeTn; zx?V=XyEITZi<~*bhN=Mx|{8E#ah~|gvMy&|C-Ko z#f0>=g4{ZWz!gC)H`x;Zu}NUsH^ru6r!|EVC6Bq}T#JQ$1--W_t3i)}k6=6E_W=Q3 zm0%7cDUHrIAb;H8*tzL=E0}XGQ_(RwAz)Rk;?WvwF%OI#v=-JOHl=(rEj%I`OtWl? z3@K9q35F?GoAMTf51nQT4iRjw%Dc$DQ3fOxcCIaU!CIDDA{1~=Ct0GRVN z3L+%03M&XsKw+C=`)c4ttpyjC+(%4$^tRL@M`c-V%GWTZB}f9uiz~%904-{e+-2ltjrFSB00?err20zpyd_B6n+JcGj|q_ zCG>mIqA7PsF><;H0rzEXf*nO%Xo}Vtc*ea6ZLw1d1rrOT+?!$rRR@-$xD*r>>~D%) zV$7w2ys*+4Hcl@yf-k8EUsBr6wVIQw5%b+(YB{2;Rq>R)toVU%YS$3uhg_|-f3i|a zFX#A+7f zcPYD+jEbD{)-k({gcHYTsHXG0f6!xxqHqDWiWv@T4trJ%EUZ(;$fiED1R*P!Y8D9* z85M3b+QXj~h3KHfE}Bzv8q8?n5PF$E8+p05_ox{e}raOSLxff z+hq7GL?_@!n$9UCvpk0kvZ!PcZLw{jdMr_A&ZW|p9*|%zL?fy}mp6?|ss}f$RK7U* zkS*l_2+5L(FgD;YEwCv=(?~8oJ(r=ql(B?dIE{f&h8_yBZBPZ`>zswCLIpT5+B^-R zA~4Yo|23)&sEf3l*f4mVS(bX73D@-;R>b?}whz*KU}Q*s%;gC23E7n8J5 zjZjsz2r08fIE}Rot4TRyLShkn#U0~~P!aG{7o-6Tvy2sPHSC6rD=l->*%;d zVCA{u3|z!ZkO4aHE0x|OX@iP59-i3h;8n4VUOodR!@@19z@G9s{STRv~99vDIVn7mM;03f6l!#uaWj&bk>v*AZ(*? zEi`&oX|HwFwgzDw9by#a6BR0Gv|i~&YIr$WEO=8&3_5@#SM4I&ZA>GMSalHemPX`4 zA=1?zZl0d_q6K;AXW-yg_H0Ctj1_sq52{sZJ@zAX(l2Sjg}H@ z5rj>$Mk}X!e-N{h3t~H}d1W)zJ;*Ro26HUrVL2jxolE}tZnm6Wm-l5}|2(^i4etIu zfYV)xGhj=u+UlvEg|dh<4R`doe5Qk_GpZsnxZY`^ugp-bNU4;n3UMf1WYYeOswjrV zhJY6w9n3=^I`g{5-~!RlHJ>Qz=nF zSK9-K3245uOl8We95{9KE2@~JvZM!JLeetQ^I%3KDiFy1;F$>zt3oICToh1b+8l9Q zP-Qc!9+H!$;xy+}CB(!dm(GC#1jJ%cOG?UCsc;-6oKcqnBLNf{&)F-K^NV0qGaq5q zb5it(3}SJZ8cVzO=a()c0TzFFSe0x+TPlcyww~@aIVL65W=r&#Wm4xHplYg7B06y7 zuGVCrdKHrTrfQ+xIR~iLOjpCTH^qYlu!6~on@KN!qw|}sLKyGAMx2H z-v1~DZ8=&`Mw4Z3Sfc*dTu0@Sp|jH<#F^Bf(8x~F2lxb(2by602CN-@0jsitVh0Q9W8gA+7E7*uss*>zXYB-*lrB`Yg zJ?|h2mIUmB%Dh-3jMQgRBhs@mo@<1#y1Oi-V`a`ORx;(Hsxzs95Iz*Hb>UQd7-6m{ zIV0dQ5hIdYpYS|jG;P%T@Q&4Sy+h~lrl#tqNL}4l;EuRc#hQ+ z5$w@~q~w)~ps#;|Rt1a&y(TNbHrs0ezF_GFQ>lSRQ>~Hon7bp}?o%GL7S#z2a#D`6 z9SoLfs`Q42aKh5F9l1C@=*i*<4XQAdhME$B98rX!T<9nRq7GllP@F*n3`4Q-DMBhb z2ZUeI)ywF#L-gO!9=s3paJ^_OzI$~&pdE-`n8>xOTta^~*@iA#F=^jk1N5(V-h`^M zw{%;p6uQq6ihwd+nSZ?ofw`noaP%N6*u3G^(*3e%nF95Z4f)06RkRqxDpV{CQHO}C zWLK)7OK31)N{IgfD!MG_TvZm>a1GKP!4_>URPs)GBhvo>73qm~oxov*r`I>U^j1ZFt8K?-ybV*F}-pkn0k7OtE@11fSaJ(ar;s#vXAk%<3nhTV+Os`eUS zmguYy0!xQg#Td*}VKO2B%!VTpZ?8cT)v72mXWDmElD%ytQN@G@ygkNoGqy$b2Fy!ljS%XeWGF3P;E^!_Mc z21S2`Cp_iY3Mmwml(L`EI5p@)_Qw@a!f1t%2ELj8!x$wpyFx_~ogJ3(99JOa46dL! zh(Y0%`vksc=$)gea!7;L*!}aTPJzMqBzNS}pqfaj{~}f%=~NZLOA^|2#e0h$^a{W} zG#3aE4PrECA&X`iqiZNfJ5X}sphvj-(1L$!sVo()ks2YAB zE?t(9bJhlt>DjviI$}TshJ7yU06HqpsAxW>ZOC+U(AUJVis?loD@8+SDR~u9CkZ9I zFvMy#_tGRT9hF~f30;!Xl;cH@0Q0CFkCG}66bevcXbDa4;yOg&Mb}(}4Ovm)1DJme zxOuF6m~5o<8~=!`)t_8vfc zLs>CopIHc0KF12m^Y)fb6$dSrAltSC1KdtCCyYxKS>nRZ?%i@&8cGfZn9Djn8Y zC9$+*rAv$42ADSMnnIUqGd=iRsDOV>)eiBf2f;?Gb#M_4_fr@02*`41bPF-qX&4RLW7RpC9Yt9fw!Dy=u>*?uX|}cab_5%H{xzX2Nj7G z)e_n&%71e%M9N&mvT~W;_B4{J@QK(Gns#qNqr%$ld>vM&Is0+G%fvg01e~P8#u`lD?PU( ztD~a1N=Lev-4HsmqG=5W3!X%Ep%9pZ7J@Dc%lM#=3>`r8;v=9ul+YRWGtvDzWvHk~ zRi)(&j{?pDWK2dX>`>u76vBU4ZVT1>!+%>sJGz6cSp^lQa&ru!l~=C>$B<{OI&MmZ7Mr%34oGyShk1X6G2UBN5qo$| zcWGqGEe&Z3!Dyb7ck~)F)eNCK$cRaFOeM7K@G6Rlo{9k@?no5>`QqvNgCwTdvcog) zj$OQ@tbxR%w}naq)5|pUU`=WXZ6xLLrKC)hjPk=pSFJ^Hk5HtvwBZ?6yJD;(Gm0Ld zmMTbtVdjo&CEIp*vZa3r5ize2b}+-c=EGBi|0nBPwi?DHB@fC?HK(ihLQy6-*0`bj zfW9R`DhRCu=ZLYAhIQ$R;%WsAC~T?M^* z%_9+&!WaTP(1b$S&DII7S}v|y=?-8uGS(sm-D!pE(B!uQreA+;Kns5^_!Mn&x7v=} z1E76LA7jyQNr7(ptIFvBIa*UOt88}S96C_ec5;&GDg!+)p9NiGgB_=2qr})*bcn^! zt!)KNCaquy_dKI=$cEt;@*FzQHMtlQt6AAT>cWbYt(S!u8!Wy7g{kMz!9;p|tRw;IOa&&H28V>1 ztvdQtb3Tg>ScKX+k-VWjb3~#lI8m!rF8UnYIdlj*W`@{^DX9<*3#V#H+9NdASRT=w zM+cBPE$MQ&lXQ9lGc1MUQgBQMb(T3vJ5iEz#OWI260(1wXRa|dGfx?T)LCp)q60z2 zl1D5>mMK&9QA-!jDs70J#a2@#r(k_Zo-+ZzjQJQN95UQ;NKwl3=wRv1ap!4&s4|dH zP)-vK7!equKFe5?;**M$pIl%vjb_^DQs}C2gd6krEIQOmH@!SnYXAeag&u{GnlZtd zS1nH04t0OPDxgcU8LbCb(%Dc-f{djyI1DrBx_EnYF56sX_IYeQ-7+##91ffdD@R5m#6VW!Q`452+!%Npy~l zFdMT?hCmg4oYjH}>++ykRu8Emsni3V^d^fCg&TiuWAepi8MT1hI@h2mF3<%o3Mw!k z=<$$Dw{WwkU9UW7R{TS1XjiES5Lg2}4o&4usRUoJQFhCdokMH+Q1rAjd^Hbn%6?ROV8k*@U~LBpqNDG3Mzq^ zXurVnL0{V2!4>rWc8VHQL%N)K_o9bQmfm?(LF-nymT8U1$9eLvl-$4_BGh7Ypep+@ zwZe5q)*9&f4C82bQ(FOt558-q&002VZ{~m5(R08FUXFp=RUWNO1w2P19^$zbZZTeQ z4{i-Jr6pIAJCiF+Cui_!zFB+ewF1)>n6%z?FVwQYs?o0Gl(QLfalV`1+zy}bwk5SM zgKD%$R(AJoCEb3NIcB;VW0g_588CuWRbx`w1d~9A5TC(5Q26dC>n%0|1_$<0@e+R$ zr$S=%9!AaC!!~Iu?P!_-(^CwXvlNnrNUxN8Nlyg|db!NzLEo6&1*S)$jn2Fl%vLYG zhhenRs30np5FIi@;@#cVa(aD}!_^P7+q-2u$;9#*!8i8@udh%q35keu%)@K z+*4g=L0kJK4jPmn#aAu~hVFlt)gu1W^jc8%2mqB4M!DL2{%PqH)w@9mF169z1rbw_ z&IOn}o>_DJt|S?^jB^>O1Xm6rD)fJJFm<_k{~IPltZ=IEs)!#7ZCP6fqL%Pqtwd{l zM+MxOFc$x&tRKhe@@sTVaqclUTI16*&Gc3^Jvr#Ir1w4@e2bvs3Gjcf&GB=Ius_Cy zT0Hnvtp-6&DF|vb-P^CN@vB1QMlb2)Oo;=Tg``vjDb7?kdeCgvpYE1$sKdLpEwSBY zc&0qn;^$Q4Az8XrBVpLI^d*@=-{RUwCUS&G%JBrS%3XzVt#qlEit7!UHo1>ng$&-S zXtWW&dupw)7^C&oQh0faB~*Yr9dz$w4;d8L=ORr?qIzHH zc0XO5LUUOjc*k%L+0rXSmG)?52$G&jP2l1zXr`(g_C16>WS2lt6dkS8Q!%uGFS2yp zrj(T^reT|-bi&IdDd)mO!-_1J;`Ck%qL4UfIvL$fzPc(`gByQ}UBTTYQaHMjD?NK) zbP99v(K90!?!++Cx%vpI9qDB+{LyGkfWW}J zd{gYqJz{1s3l@JZR#R6SDYNVlLb}XdOKeTaNwyXvvtor6?=v$oGlhWOhqmpeCs#40 zz%T`T1QiV96k#ChWHRMJpEEnaHjy4d>aI!`Y2hDD*4~5fsS2iBn$9&VC>zStojYf1 zve8s5Z&;OBd5yX>#V)cM^mC~UY#@UGFip-G+(^(Zik5%a9_JF7+o7u&WQ zF)ZB>vZ8|NW=!;A5Y+o_hrbT`+}9ztjtm@3GfQ~|hE8LIrXnizR^qTlqz|xR$|P0J zF_Ak<1-^f?F!a>6Kmg^!pie{{Vsk>uRH&4~#}EUebx&{SWosJSb5L&TaUd$rWTjIu zxDf6Hm}$y!P%>8PvQ6=aJ;_AJ3TGM9wuI_bpa<--W*!W|>PlOLO~FM5i;hKS55t+6 zNT9qTz?N!lljgiBxGchzT(o7No~6z``Af5$zrX?%+Iy9Q3mM5pd73q@|5i6t!w&=*EslJmSz3QnsCNi0r891zfW1 z$`sMdt90kI`ig%r6~Udg!xULiBWZ_gt9niPJ}3PVT04Wd3_ok>wt#T9>* zzI2(csxg=v*Otl9O?FJJEQ+9FbI$2XZxlMNk_6Le-0~DEFW?O-drY_r(;ldH0JMla zn%ovVbM$+~v;!CiiDi+BNhM_p++1lq+i4R?&=Z`F%c>*YH7?pQ);%+)+7ifwpbx|B z7)-h3RkKtxB9n||pt;Fyms&>jBWr)<(L32)#e;(vT$>;*f(hAn!W9|1CsGo^{3=Dw zRMwjw=H!yuAlfpSk`n?4os_E#p^6mn?nRay0;Q1awiB+}5M8FnDGH`{g=1lqy8#{% z5v#GbE)`S>^F4O#mFI$)mWALfSi?ByX3%b*-(24=Kith)yvcGXynoL;TWNnxNrF4> zEBqxLahgFlO|oPuhNU!9hSMwL*8Zukn{-MR*Ow?^wU zXvv|U%RleRVmZ7-+RRaiY*l{=aJ*H(EeOGKO~vEq2F}T}0qt*)XnMgeQ*IkLhw+IU zkYHFQ+Xl3BRa}(N6jL!%;CCpDjbH$LSSPRzTB%TUh{7ld!hyDGQ6smWp3E9F_x~Q0 zGqkQyg(fV;7)o;7#t4eV$Yu;Kdi9n*W*?4QM_ZuX-;bsA$^&3ZJ0pIkEv?+}((3hDq=Ol_(vlZr>D zy!6W97e>!Aa1Y73fr;!kc(ntkn6RyR%X!6U$?ViDML~BPJEwmcCK=X%4yocVmyCAi z8lCl%WN=M8JcY0w7XkRKFJEle6m<`|jdDgSB?&4svML5Wo~OIWe=TQ-EOXLI(lY~*H@jeb5wuYiUkZId*sybtf@*qNkRAL zshRn;o042nwMZJ^$#;y-o<$4L?_uLGJ41&AmbiotZFi;@jNih?u;T1Ddq52F&n$SF zQ^&az+DxZ7t1~Mw=t}Uv2~Ln>Q3~N+`cex7aZTbmOd3dqPPztQL0zZTD@J?k8Uwhj zst#sk&4Paqt|QxF*T_4*x8rztW`)zK5ve*L+6Es^hp+E`ho1t(?}C`!hl7?LaU7G@ za@x}I(GpjT4!&(m_q9XT0R{KcOKam~P>d9pjDqZwSm2PPoy(}qLTm1P`2k?M!^DR# z>>p{`HV^A;trR{b8+%0OTSoUn^gadO2B@G|QU-r@cnrA4+U<_fnTS+UYJm6|Aucr> zl+}4l1^CeKtmza1%I$KdYg#_od=5zav^ijYol8bbmc+`SnV16vvdHd=!!`i^9(Rz# zVtjeB`^V0#N^eZ;KcMCVF#Ozc4r>?!oA$L1a6RDJA`Tq9?oFa{=}SZF@X96$y?bDO z*Aahl85w_2>Ky{L4ilj#JI$zAZG0M5VFfvZ&bk9v;NYi%kg_}+G%+i-tS%BZYOCiv zT*k|pODp^WOapU!&XwIIaee`P?GAFFyc(!lg{!Rx+(Plq+s<>%lChER7#(mw2dA>< zju0notcckC*nlPW29H5>#WKq!qdBQ+cWIRo zT$fuda@LWupMN_AS^qXO6W?l*!6Vb*GBk9i!Uk5Ej!`0~J2_P{4nqD$?++ zaxNJqPwULbYfll_p|F7uW%eszl3p@Ol`Z@&z@Olp*kw2>J{!xLqu#j%jj1Q?)~wnV z=Dse(@XTl9w0-)ejkLr&sFOyV#gxn50e{e$>=sP@opzY4v;op{O+-y=L)%W z^%`(IRkIbgn>eSAaz;PtZ2W&0(Em=9!GanbLQuOcM+0%2@cOQNZ_J2rcZ`~>rK5S^ z*d(doYjWq$EjcH(m!_+IZX0x3;cJgbPhMtehn3NQLS+(z-L#$Q7V@6dOgWv7 z=rFSaiE>RfIX0}MF8C#Mr>P%bqmrBfjZW|oM4(mylOxDC==k|KQQCX__ z(iHH|ZCk1Bj6Hvb3&3V&vxtfTQTA0)3ziKafG`};gqVOjrs%o6h5A>a<1AID{PNaz>2}B*4QAi z@SZiXZ;xNy=h7WiCndlfC%ZBoj~KY)x1;FQ^_KCZ41s@90a*41C?K11@}?)h_+9ri z+q`v;yhe*Gles5t=gPN^woYihy4Px|%xS8cOVc*vlvYpChkl{tCUd!rQnylQ*EuTd?{T{Egfw^+_|*+wv6I~W?y=Yr6*~>Vx~EtJOfCWQ4o4)ban&~8m%tROBzV>(b!MTU z?Merm{iXF3f5!H~LLc57t#QsKXenLUd2Ga7S7Uz({K;XHoEq$KmFw0XOs<&6JX*i% zTeMjMLZu{9qClpl!8?PJR<8ZE8oHm^Hf(K{Vkz7x;%CbTgbRc+^@OR|SJ&HA*GRxk ziDef(Vd2NlY|Ro)^SO%8t%J~kMr%)O;JwWY&U;EV5vI!3GiF=UUa$+JaBQh5^9o0& zw#P`2adpnSgbjS_u_7alWQ}#lmYfA*l3Lp_QwB}|(*WpHh5C%9)zcX7*b zCMlB-2&0PK*3-PpLlG!P;uW`MHcj1R zWVubDH1Fu=?wli9*A{K#$LEvloRUlON0)c|*mrF&m;mYaNEFX87eunbYgzo$U98B< ze;)5ZD1DvOJ@E}iH=>zY_t+*8@s=RApiY$7LDV<J`;|`n9Ve!YinbxRHHybYpY$|Ypbm>OXQZ|-&#=~GXog~j7ie- zRh-Hi4Hhr-GvVJhkqfZI^3oFiI#==9>cgHipTv%oQ5q}#TLfTJ9iR+XZAa&Ae>E@k z7W-@m;Q3+3I|zBgsk>?06I&_Cm|-fcK&qe%K&++jiOqg>y*-QcGSg5{pwtZu4$MZC z!)fQW6&#=2E-@rE0R<##gO9`U(tTOS`d z(BObBon1&XTp9vuU8^qjl<(qme;94)aoxK|Y*rj>jm{(1fSs@UHIGOFznZEvN^lhl zko#y%&p>FodcL>xNFV`9fs!_w1k*+5oQ^;~+ts_hJr($TQp;j4AedprVjcuC!2tHv z^SyUI&FZYGCjlw;F-keXti!TB-~H}m(|ox|tU^tV+8oro%o7VF@oM~zf2yXu*aYA2 zW0k@ln3_P%0Go95yS7I=eh@?#;KNbyFbPdDt56W^>RW7R%|%66U^7*D-pG$Mv;#7| zR2lno+kGh$RKi`$I>R*JPNVS!gNn^JZR6+XiDLxCcsB(3t%e8x$097<@VS*Yv#&3mrgk|U*ZU<>``>p zwrlQu0MtDP+gM=k_ei7oY}wY`Ip0c!Bp@d2w6xMVz4Q#&1e|<&S-rc@sT|5)0}g;( z5X}`)lyBi|v+MmTUOT6=^AG;6)f5E0v(-9-CzA=rWAMs z0*C@+1O(nC#{jWS3p8x+oz7L`6?RjXC}WqfMFAOqH@@URJI|7=tV!AMPy>tYVO@rrU;c6vV9}jyQ{7t6W|3j1 z>Q6FVuRX(`8%Lz{L|s$^{*-grgvJ)%e*s%|ziJ#i94s^Y(3*4=6RQVg8=;F2zOQ|8 zjqksInqPnQ|IJTdef!O=pUWgq9GSYN7KWm=+0GJJFGp==>704fbnYQe6-bpx?SM~q z=Q9(c12~=CG;Mr0*AWFkD~DBODIUDp3N7=ct#|*7X-w1r5FjXRr$;g^>RC46QYlbhy$V9|!KMy89G;(M={KB8S+YpgOG4%R|k zoe(Bi!PWbgGTOeo)~g&)2j016t6)%A;5}-at<|iry&3zpX|LAX071ukE3htHv$M|? z05*G~Ts5sF@1FLdARG?$LnpDjYxp{TbFDKg>?v058K3J7TTHOV2}lp_#rI9qYy@Y2 z^T`Z=$;Cp8&f77Bi5R`!G>zT0n5dw$9`GkDdK!JnS))_?@TTdy4M9okY$2Fx?E)(QO8#v!j^56Y{iqpKX9%rTQv0D5w^ELN(3Q^ZZvy`_8( zmU*v|HXkp8a%XvK8E|tqO^=OT1!_Tm(2c2X>?j(+1S}lvdNXptYc(8hO!6b&L2q)V zvWMCRe$bnal*#FtYU2plz(}L@QEQd8srYtY+E(V*rX@E7EQyUzXODAWh9T0cR)ow* z>!#`Ylz{XJjvgI2zks+8%9t_%uFb2aXGxxbOr4reV@zWUVQUpg0jU3`X+(~H#q_f7 zzK_+8GiImr5xGg)<*I3Tl*v+~lLu(r>B%wWD=&&ncfD&m_L@^DlItMzjWuUfiD=_;Vo~}8SeUb|odJ*Ve}`bL_Mvh!XoBVp0Vedd z#967RM%1w7Yy(QUdahU6**CaV=XTje#c)T`U<^jyW6D$5Li6tL~H7F#uU zqK2#9tmNpS31OSPgP2kFQ}TxmIcM3;b6tQ*N+cWb-IfCDeRgOZ%1w%oo7=1)G-is9 zYl1Uftj6fOg8emCIgNDHv~96bj0GQ~IYkQ^h=*xjZSI@ry66POV{Hu=yMbvj@g$r1 zC^7Q6YI>)|&Lw+#cXfh)lQ>i=1Or)Dp+d3N5xg>%T(G-+tXvHzZDQTsuQJUt07zS~ zt76vP!EwhZnDRD(P3yTj;RsSjMH~>zv!Z9-pLuooP(595x|EuD*A0NOdn#seaK1#6 z_DKD7xp{e23BIYDh$vMHvnSJ_!2XQc02ywEk7|;zt`3aSv9$Sr$*@Y+6z1D&RqsDD z-KjmlmyNS^PIGTKXZ=*iw%>k}U)PZqTWP{;`z(ZK#VRWyFyR&F?xyJlM7Y~H@}zZv z>rBeEX`{}T=bJvfrKSaQ-gU?B`0!%_!p91H2O7S)!&_cB)7mK~R$JsnE3qxKcp7u1@%Bg?-$l1CvraS*Tz2yb3VA?5gQq@U?YG-Y~flyNDZvy#dW$ zs|NeIY48m`O{Z$7u7-$3>C}>#8PMz1uMY6}R>~OFcLxKPKT81}f77^Wnh(<3@!!fs zCSalrs~}uw^9AB21<(|k5<#`XTxTcI1mu!sQxPu3&9&B=a}D-P)nPg}=wFn|hOz-? zD&?x_CByibr#Z@QUZ~gxXcTh{FIT_X;7Z%r>_C)^85j*H1(9r?;t~0(X~wM48`~_| z<|}q!(o2I+S&?tLe-!OG(b(!;HnUBPdU)Xb01Vr%zG>=csRQ>8?OqFrUa;Zy(8{{t zan+^JiZ-zNI>)IK$jo*&gfkht+P;ZM)hFdzav7^Et0#)`E`yzWqLjPa3}J%ZKyZ*) zA;)yhZEMypXl z@^SNUS)$k_@c&-krXqZo1;18Pli72*=|~O4G7|4_YB|c==mm_p=3$1No_f{vS^hNk z831x1Z@cw$dW2Qcq* zDYyuqy>6NYf2kk2>;#65{WeUn>P~e%zTWH28ze)-mIAgH2KF?0$zj>~W z&D@QNAvIH%d~P;lNC?&JwRDwp^#qDtil2r})*Db7NJlsbNk3-i=DislX0qAkeXx;N?3&dp32y3Ou+xDH=^Zmsw2#7JqkB?I(6uttBC5=+DW!{WjY^y4kj44Nm){k6yorPMv2x@lqaP1=I z1%$q`yqgzyaAdPeY5?R`ubKutT4Do0;oz4NOv3_Rs(_0{ukP>=TL+u@;q|q4V1@@N z3=puk^r~q#mVcrCIJQ@!rZF=~PoHgv`?v`UajtrCd?4^p6YC3T4G6`76WHJ4=30-0 z*ofG{ykSg12i-Ym2mn)N0@}^UHQ>j{Y%9|Rd-0axBTb>F>N@kDtVp0=B&4g2iuIM~|=S4R>e$q?nO#+m8rgqr{ZVu^tm zC<1eudD7{*m%+Y3S523BKx(r;!b|XNiR3mXww1QKF2x2ubF=J~4eoUnJ+1Z)gd)+e zrlyZkYky>F?+eqjYt1x{K#jSO(3=;PpgZMEXD6*Q*o@McOjRQh(b(RdOEKLd*F5Nc|*W6`kix56mS4;xtzSp&x ztwBA5i>8+}c#pQmDQ!1@-p@k|_WG&kTqQoN-dfp~xbj6Y1pyM=y0B+nYFACOg$NkE zkbhd90;6pnQ6R-yPqdpmoSh!262Fa!Fmg_=zFJ=F3~Tvn=G6kvpww# z;AnT}TjDN&4w3`Atq#gH?5kgWaEcvMtbbNoFVc?f05+TSD{bGrBlQ%pF;@ddi3L!^ zy`2*i)=M$JYPw-B0UqV90?G&EjR{a{JR^eY)x+gY5`KBoox*`em#)(awd{;(P&ZA3 zRKlZ_pznT%W&xc$kiSg)ngEFeR42Jpmy@0OdfX(rzHxfDbT~7xJ7&=yN|9`F^SrO7 zu=*K53fA!XIK~##JnbyhWKQGVJkp(jz_VI|)8sQ3cKJ-DsSUss&o^DleqLVkYT|8o zw))mdY2lR`aG~U@rde0xN`V(PqJQqC;xro=V3D=QO$xx)58yX_`8kpsV9Jb?@Vi}H zTf1r+_$2af)GbS12mC1=Yn!a*8&@kJfKP&t=Vul$FKIRBT-nbG@W|w0sKN9?k$;&*%mH=JeWeP2KKC$fsM=kK<+JVHd)&yrh;UJWD!biL!N8D{U11qWJ5oY08A~ zj%=Bwq_!(>vx1q++O86xVAN{CcGpV~E|1sTdtP#OmUR^j2XMF!(Yc3rgC{ZH9h__7 zw+o*9rfCqq-Cb20s5N6HOW1rdp%bV3s%b~esMP_)vCn1i+Vv==ynk0RG`uc}XeQYBv!n9G6gOKif{)l-*;Psyuc{h<~T~rQzcr=XdeypZ8Qg z>XN0i5@{S?tNYvuG@>!@yY_UU;iEc`G0GigFnUZ!oS^DdXs<2#-q64}7!> zLHYJ!BBgf_-fm2{Q$3}F_P$h^``>IzU!@GgG4C++=0P!7Fsm*6%pBDv`UjzuFGGVIEo)Bc@icOvP$Y6h$Ry&;0$@pYYL=VlFgDW;+g^wem zwS>YEmFYt&t7S~bykzsh%}wiLZm=UP?xxy?H)waOXR%rbU!vAL#Na=KY~1H;zESBtaiq)YZY-?=w0#%w8F5aJq4wHO6- z8&jOG_}hO@tvox}rc^eT{wk-H*GZRqcT4r(9dYK5Bn<#Sa1es4{Da-RhVsXlJk1su(Z8 z_LaF^00Y=Iz<%t0S!?zJE-0x3s5HCtovVi8aI~qlCKkN$>IA4)(&$mIh#tj}AvT&FrfaC2>35u<1GL zC~ZYUNKwUNii2biw`Er6m6#2j2RA^x1t^bb%GX6WB4P7wa+Vu5caqwlXY0cIuLZu_ zN0FM?p;cd6!}bfCe)ukr?*%J^11e(xr~rS0vM|A}V9m`N=b;2AgwU8y$;S%f&4{pd z1)FTXn~9R;CV0V#D7H-wc2cbp^U8V#4kS}13uQNBNh^TyWw-3IUCtFB9~Jngg9e_A zxROD0iLJLWBGwEvl_~Fy{^V3T&8h@MNpBm@LsLNTM z=_SP}gut5SK>SND)xr7AW6QkT;!#+o4+IM!*Lko(^8_4NFRhaO&12I?XuHG7whpiY z9s$Ig`Oiy|?)9-_0~oD+U}>AeRR(_mV%jM)vuo}lA3C;;0E0k$zj(21W0wV%kO}Zi zQ$E84bbjrR92?Nks>c9t;dD<;y(wMd`6=o1rTNppd29~wjrh0sNx-Ucs@KsfxWJ$W z`TWqcz)aLt$FZnPLa=p82GuRTSknH|Vy)jiw!n1RBsM!^lmzIkpVV%GEFZd~+eiuLZbpuZ?qXYJ@tJ$P@ z_!>vkm^s+*&(llmlD{~H+PCjhJBWbwvl4UUr7UU+HtdJ_jxj{xC9v_i+!FW!b?zop znL(-nOwO$_{MY$I{KNP2n;%Ym|BUBudgoaB>J>xa*-YJmNPA1{b})jnPcJQY{)=N7Kyr0pZKT_OE~9nN z-K7Z_en@F=U8C8sO1=@k(ijbJDfeP~0Yt5e5!QE(W$j_LBfx_p997=|cfNw1w{gH; znuqZh$Ks{hDfQ_Y(cxd%BQJGeO2sxx+21>s&IZ_(na-i3jj1wth1m_f>ZMv;e{n3a z0H_}&)nrFBFDBaOVH>V4K&jq;IhF&$U61CnS9JEnb;&KXo+6fuUJJhejsNiXpXR5y zZ{caWbr!E2$C+d@gOE-ZBX4HM4Y| zO*PKQrBQRLZFu&y%Q^CvL1^@(?CaQhOPOS4+k^S=`50o!duGBk6-h&X;2Nmn(4^GO zNkE*7d|H0XAoz?+$z67|$1feUwy@_T%Z|LsduC$xV6LVkV$_V7RU^k@8h3zj>*{YA z!~&&PX{QRfKtT`%6bIYKp#_7r;qMv5##~U4$^j#oz6ywSKnM`McGB^lJ+bl4fSzT0 zc8fTC=s(c}k$nU7)&DDh1~DZT9Vr%ywa%lTLdoP)rpv;=^#40X$poJy;F4@y9}aqn z=zDr8l~C!WX)s?NC9}L+6R%BMhWjnM&O%)z6J}h#Cj=gWcNN+DX{5C2e!Gp9@gO57A(-yiE}~uqIZk|m|ul$d$&6%km>0@5GPK0 z)NLwtY#HbaCXedH*| z_Gm1xYN?p^ImalxS6}CyW1&XS#KAHEkt_#pXAL(^I}1EdneQA+A6xl=owk-OYv*e0 zPgzpW!=lSO#{z8Vpp^n|TvDwaShYMUyk0@(vfUrc)6{yVF1e1XV|&3Q$VkjGm?><< zddnbIvb`39^6A;w?pS|wVwudu)YR4AGZT>$J3CWGxpYj!N;4mz6_96O*yQgS1R^47 z^W0SQ0$|HUqOBQWiR!zz2JyRp{^oytwf@JqbKmn*zqIl6K7L9|RM|H^r}6Z7$lLpN zfJ3Qo8V2AOQ8oQQ_Hw|NG4;Ma&M_G-zk+O4n>XWINblx-!&?Gnk8)c@s zw=wbW^jTJ&Ol-S%vGD6*U|Y0u&IV}hE2U8p$VY}p@C9D+uDyX{x!ZDfpc&Q9lrk&T ztJcMR+?k`|2+Be#y+yleeaj&7Xlyajbr+VI4pv|Z zRzj!L)JJ;DAcU%$#>cA4Rv$43yH!~osm|!8Zy7`>+Gg?0?ln&XC1canQYn3)7V(}z z;L{Np`1rDpB}7cn_aakS$kbYY%OGmri!~V{+4UIv$hKxF{2U5=zkg>>R5PW7% z%v{dmBYA3W0!EvaU7)P=_l)9%wc1NNh>Db=-|U?31?SLhw0vz8|C)66ck%!J7(aY^ zlbPqnua*sl)X3IWj1rxC?C`>y{&>7^BrH3s*l&v>jAJ4O^nc_d<<&Cc(!HGG&qq>@ z?q1{opRcL8rwNK*!R9))fvCK1Bw*38EV?2X;22B_CMEz_K0f4&$pD{^M5o4jGGuEB zU%8c*WE$Wt$P41b`$p0?`|T_<{597CaDv-z7!8gqOL^ZnlI5YJW)179*>(lZX(zyU z8s(AK`$oc;v47OFgX!a+2Rt~ib?f+3(cJnQM`E)bUp;~%=$q2&XJJj#27GNHjhj)hFZ87z<xf zX>oY;>yHN`_|l^P%m3o9_`!q@Dn2@23-LGj zW%llD)^gHfVQM#RQ_U_V;P=C>ISW9ot)HAPi>tq=nEevl#t!xatRbJ-ODb}Tx_ zu-AJ3VmF0XSOzY!Xn<@>&5jy24oKfF2$Pa-et$DQbIwRRc+JqFRX*HO5RWMv`HPLk zUSWCELm4k-^~R|zX>h*T$;r9K3lGibmJfDTfio?544I8>I&bAudaLK?nOLo+~Q#AtRi9yZYFMe~c`)L9?*x7cCHLVV? zg?~6eVCBml5?^4M_sLzEp@DQ-FKOhId|y0Ofo)vCm7`J|FD6iT8SC&h2_Wo? z*M|S6mjC0Nq`&f~KKjy>526ldfbGIHSw0A_Ama%2HJ5vaeT(u6YHPw)S?~?R6~Eil z=lWua{R<4ULl~VAB0Jn-9!YVA04+9FG9I~KG;EZ>Lj<2sA8J+wr-8Weq}tAU&2UZt zEuy7^mtbT8Ab&N^y{XQv=AqynF>3LCDzDfaF^G50Q7#&`qOP+7nzJ!+N|*yfR5<4B zao_G4p4+oHz;VYSgZImXUz!D6tnM%0qrSlK+VkM#oQX|!o@zzOr-gxUl`o6Cy}F)xZeh zEfvVJ-t%0I`Kkvb3~M_)VQVR<*)A--jM?r%A2%hkrs;Fz*E)E%RcKXbVUH4!XsVuC_Xi z=e9-xwr#21J5G$e&OjmT;4U+;=+!|F(>T^BuR9$kTuW*1f6L zNuACPHzMXNliJKumxIv67LxbA7$=8NmZD(2uGuNUsyPGhQb+OP=CTQLRy?z8bxU;i zkbjZJL>dFS-uKS21(RdoB*((nrVQYR2w7NTU**ec(0{$*o|s6s_E|d}mTZG>S4-^2 z=9DuBu&=$Y6^U3!hu?zzlpT@(JizWna)7lxznsm4uaR+?^5 zR?i4eV}do$dz))fT%-VO72xabbBi#Mf6SEx-s~Qe@G2!WU;y~A;T2&45UlkztYLeX zxMw(Y8DIxatz`u@&l8++TWvjZmV1~BJJ(>UO?-I;C3j}HtaI3WR#v$eBq-$sT7M4r zykZ=-A|0zP0n(0WtEG#E0WA9{Ph^14=q$_db5foO9{k=HpMaf`7c=iuinaFYH8s|B z!=1bw2>jjr<_~e>XFh-#zuVFyobrYSw2HZOU@G5pYQAN5t-cXi+3p;Hm0h4))n0@W z(&^;{;a|-n&cPd$V28FT>qr$~*MDKDwgZ3IE|~@Ah2ybaO4d_$24b#7JXtF~V!Up@ z{I?(X{F^_0S<&>b_=!*9NqiljUU*gi=YBY8>prH4i3r6^O*<7-#t}0GIBeu`Zrit> z%-N=*CI=|WCo$J2=+;DbYPanJbirh4i685+FaU~MW8(m;fkfZ7&ldH@T7OdjGzZG> zTV0t2<^YHI?G5{EkC}HUh!keJHwzHjG3Kbd4XR^YFNeq{6G0 zdc|lf$$>&n3^o#Ci;|uTrg;_RrHNiKYJBnHOTE-y>n`jyIDoS2WY{`)*0ckLIgoXG zIt*e~yNYMNSEo|^i^}$Yoqy3G87m436>|WLjI*jOsNj4}eHoY=$hXKh&*~g&R1%)=&QZr|)C_@xqV16<9v|=}&7915|@I zoxFLS?Fe*bBMtmj+-N=4Ynf`7j*64XO|ui#Jl;Aj*|1~hca$=tPWGG>1l1{jJ*U-{0NfejDJAO_KugVF5XcE!T_Q} z?hC6-R$i&!C~zBhtg-`XYmNFAQZ#Q*eM>(ALOgSnOMch^!>pYw@PnJm^enb12GGCz z%Jp>t_;=yo?ytW2!~gTmcRzl*^Hcc;fAhb;`}!;Y>eKJOpXbv*eEU!M-#-8DhYv9M zG#6ofbND9;1AnXyxKD>HnHq!ngb;c(a101!861}x03S1|MxE)% zKq7$5k(m$B+!bUfKp9>LM1Iq#Y;LQE-A}Z!Zv!a{Xj>k$HgLuDF{A2*Yy;SF>X1NS zjRIm0y6@Q51X4lEIN_`=AwEXKRsDZBj}deybKB6{a+;9J7DWTzNh_9~RFlQ@PGK zGMbOMyMH@VUp{D5&LIFyIasx}oMdHVfrWnrd5->bJVu!or}kzBW8$Ka&pkAE3equLsfd<7pws51Z*w;1clI?2cS zpiu?*YBko8!bK`jl!R9Hc|v44^?b~zYztW>+w6eiRaVm1+0&ppklC0YGb)6))LH21 zwY$Vg(`v8Aixg?DA2cd90qiPu3{m!UQ|jxnaeKww75Sju?#%U%qRP%{idaIe@Z8uq zXn*2p+Q*D)>uA!FbjlyrCP(42U4YXYz+U^HGr0Frgx|C?pg35l&L@+dL!!9v2aPIn z!%*t1@K%X{Nwh!3qNyYLrnon%zm5Il5A$|h`=ynKapO!M_tKsHt-QF(g3n>-IGWDe z27=kPWj!HSfa_-mrOkDFZ`iXyKk01)!GCdWvbR&&1rXlx%aAdJZAK-%usr%N4y3We zu3I%tQ6?PkNhPyx8Uel6@wS2N=ApZ-xmI0RDc9tj3ZM!;2w!t*GqrrA0txRWY&V7} zz-Aa&lN>Q-x@Q=>PYd&=wdZJX;h^dGbqS!1#5E@{c~!x5#8|$;yg`i+YFC3>(tkbd zUi{$0URz~FZESMUPYK}qx#sBy+tBZQvGfGLx^UQ^l9!X~$-D6mJrsX%jjT=z8)9?i zg2g=mgStyD+xpxr0O{Al&#VAaV`y4I&FH6}pDx>!KExis#~x;@lg|~{SZB;qd^gxW zW1j+$Ql(rote8`f#Z$<@-tQTXJ_>m=@N4Skz#AJUIRWmkGi$wQ zco`KmahgFaQcAgRnbZU7pdBk+H0-|i)Nwi=k8|w#sLU>@&Q_w=4BG;rqs(qy3%-*b ztPABbH7pEG#35;p`L7+yE7I5>iMhJKT*qpbEhPRmY7z$&19!@$a5r1~qoCwj^ zfWqu0u}#^t#m;ohcV>ZvI|63I^4~Mus0tXZjfuz@tV}H9mPwO7cP@yn5{^Xirw;81k@(nDh&oEtVe2!27RNd}*E&%!?Y$jY|3~&l8cRK8W z$kgdCcQ<;0VOFs3M3}cve)`AwA%1w9p{HYo<_zbsRIWh|<^G8$`yB0RXa-a@gW;*CUTW7v= zEVdE%J752RfnpB8tlA6JWbub(ymgJRGYVYY0JH|Z!TCR)bonxUmWR9q8 z#9})XXWBxdVt>y(>e=rc3p^S~R%g>R9OL4wSB~B+M-PCtx9;7uYdxzE1B|L0By{$C zRKQ7QYha=m$MW~zh5z{V{PfkI;@|(vA3nq=17ZOy+k4^sg6{X^Qc~XRgIH9?g_Ohp z(3(G(KuvI$FY< zvH1+>F3a&7_V`XYy!Ns5qsB$>O#G*Pk5PvO1qvoWPiK$W(?4uny#UOMQP2;#6wHkY zw_}b25R}@zapA<-0FPpSRRmG$jYshI$-ChU=5^8X=F?j{hR_ZCJ;IXqnvPLzyZSv~ zHFK7NgMaL;QzAlkSYs={3EZ0jXD-fmuE!QUep=m=EsC#-|o3??>Y%zei>!|K8;)VSxDr>rF|?tfsB4KNgJQp@bXq#;1WH&0bb6%JlN z6;GX21G{TlOI?7$1;pi^Ip2#oI+TUM+PS$miU6uW(_$mk{+fut|`GEL@x3M-rLK9=l9vdH2@D}S{jciNjlf(pVi{4DwVCBUCLM}aBB0jK(Jn$H2r7ovtSZI zGX=R#1!311F;Y7?-K^5PZof4)vFcIWHZX#yT7cterwU0cx9uOq=#FU33;o@gb;**t zJ^1D@%1i5d{=EGGufE#WdTS<4ZN^E@-Gg=lud@VgUmGt3_69~o3m7KoORaQ z27+&QcX*PS&vUomYX}@%8`XKn-!_oNcSP1VEP(Pe${KZo4%A?F4aWDjfq!_h0yLaz zW0hFq8|xfw0iEp36!UEZ2{S)!?cP%dS((Z5$;$Q#3I4A8+XiwLMTQQ%T}=Exh15nR z_F9v>&UJ5(ytvBa&;NKrJF#NYnb0KyJl8uJ=vIKe1OhSNF@hP1O#(Y$yJ6EyXIGMy z^PYTFzdr)$Q&McxCzqbRjDI7#NrqP{bsoDvf&!X0cOJO~TVurnMFrjsUUlo~{S6}+ z?Dk3#e0ZP4*Ku#NR9;9d{N@e&pv(gYl^3|BYJao$qAu#JSldr0 z&GL>BbUA?g3ji-tUOWqDVH}x_63+|u)xJ0aWkJ37ri#Fv9ln1rtcwJX$k=c22WD)p zVv3zeIXj)K%81RI{@(I_!%n2`I6FhHGF-HZA^7gS*$-u%VPR_oK` zeNz6vy8gNLwsaW{_beO8JTIEgor4h_D8t4(`oPB6yTN)%SiHa@5ml8!^UXwWo&A}Q015F8RZ`liz~zb-u=Q0dUxIGgEl*=XVDDzV9FZi<1po{i zC*XO{J-eHal*O2K0S-F&;uT{aFfj@OU9&r>BCR#C#ZR`tUo(S(c|IMqEMK!5X{PGH zbSDAf3V7$%O&JG&;LUn1rT|Lpjz~gqc}4->D1}J3z>_WWdCe~NE`p|pMPk=oJ-R)# z_o>VCI@k8Ivg#K;O4u~KNrjsPuaTK?oReR>x_Q-ns`?ly!ArUnxi-&T zd_?1Nva=E*;%mBv|EBkP0QcD*!}safR%3K<(UbMl;36Mxgh4 z9z_uLW{bFH7rY{HOe><0mYx-Ca{=CEP>l%8z%{$WwhXX1d~$vQO%(@7w?O+x_F$apPxyKKVg#bebI`qys1RROcoiS`2sU zx6ERz^jOQpLNSd+$bqqI6wtisu9wWh?@^`N>M_39rbSICR%vvft-i36?yt;7rM?$1 zlh`^n_sF{8k3fZG_tGz!rP_1?HpT41@#WH69DM2WIHl%fm&`g2X1D z02k?h_$!5*e`OY~?j-QJ1Ynv*-;u?;3?S10&pVgQvi(P-SbSesR;Gw!d~M#Hl0<0$Edrw*b~Q^m`E=Gb*8DM}>OKI@t-*sH z?1oX&tg13A;Kpe$RQ&kQjOyjNQU7_HPeOt|^wQcw5KMwoUqB?b#hO6$qrWg&{I?A& zR~s29=+u_;+H_5&iLXHXF7m>B?%y^nslYB9bbdxDb5RVbN*R}bdjT7Nzwyc!lixHf zt-Z}Hd`i=C%1A)(v105;(|E zV^&x~B$fk=?Ciq*VZ$2BJ!>u&g44Gf&S4EWad4KAK5EN@3qx_)~=R%3SH6zXsWt2unvcPVZlJQebj92*zlt@wdeYNY-wxcZXKQjfcll!V!vrv z=U`YZuzo^O-veCMjzwx+mrZ;D7#91X+ODkFZyygJky3ACCxb^Utrrm)mwS8x9Dh$A z0y@?bLTlzBpKKC|L$2G+&)b6RFUAA1#*SAuc7iM1$AcYGM8|?#eEa?x&Dj@e1Fm7E zWP1)PV3i18n#O+nc(5|b_5sYtyioRRrAN6QyQt`}^6v4hE=NF!c2C9fDm7u(r0!~P zerc_Dk7wHe*BPtq1c0^y9>*CCaDOP_sO92sAJ2+t)B8>i>^hGo)frK=Y-}Wd`*`4U zSWM|XFHj-zr(!tcKTJ+KX73+Q44kdiR<*`%ro&FHk9vyLWN-IBSQN{B274xAszxa# z@e#Ss1>72M-_J1@Z+DkbW4cGr#smeXa)GY7zlYSb8B*X(oh});ukD(d!+%ue$s8*E zJ-cRBkqnx;2!;i`erM49#tKf*oF(r$OS9<#eORf;>NW2)sFmE7mO4hq8G6qs3)@29Ai2J)qi}v72&JBwbuNV$&vn|HOT5&!#tS-CxoRB~f3Krok2out*l@$3m1yuhCuG z@Os zq-CAeyQKD_o3lUI?)htjkeDpU6##}@;H3L;2ip}KznyD-&me#+WACXHlL3tDeVf1f z>}|He%JQB;L;{!gR$r2}?1Hw-ROW<_n*G5P)UOSKy1A#sGJk6+mFb%`nzBlvHocAa z3}V};1%XnjkmUeWV26=?Vnl5|StfeBcJeLV{fiuB?3O6Yhp2m2p?_~|8h z<3C>bk$<;-+JAiTZtoXAnSLaVTvky5l40u#Ianz`ti7EJ*{>SU@YDfty#qT2(OZ=@ zrjGax7BU``fPeZ`<6XqM`!UwkXSSu)ZU7b?!#LXR8efQv*}%Ij0pl;sK-X0zI{^N8 z5Y_&wapy(SORA??u3CDEQP?YGxz-1(IDgGJR(irA77FK-Dh{q!Gn~e;WBJJj8oy?| zX4VH#$9upbG(ohA>bAydC)(u=2for|TIs8oY9J71)PL2BKG-60&8x<{7T2~Ak*s(D zbt&MK2#~E0K9#4t#t#s&Aqwy=s;}g^2M_3lv{d1e-gOD!&Q)_js+zF{4RW$9htuD#4Aa&l+A{&H~nZYc_!I|B5BPwKyF zJQ|N0Vt;DIf4WfaaC`S2s1R{___8CKcRo?rm@3B|t4*>}N25?pW7h@_cbc=?mIu|I zZhu*YF{~@LRO$4W$s!?alo3(SgO4*mv#Qp1B5jtj_h{B&Fn3P!oP-N^tj^YY&lP?l z18*m=fC&_I5Q^a^ve!#iI~?FjMW;8x1t;*m zE0|r)mu7g+k_WGYGFX&ZZ6kp9l^t8y)qnMpA9jH+JhQ*VXxz5M>+&NI2}XKSvhL?r z;qON`n6~5zAjeYG6fK+XkworTjXGr}L*Tq;erYhqilnsm)w^g;QSFMkb} zMo?&ty{?i23Aa43nji?<5YytKVSXvaVZi-F5K+@u6wk-M84uq%{LFBD^?$3NzWBz~ zc8IMkUz4dX=FmOu2ff&}P30o-+RKw4Pa}q!Knqf(B@smm*3g6c$6kx(4$pvgI znywjcWq{gx2GxM`ck1w-Rt_7?)qk|Z?irpbfo0dOb4)48*)8qW@T3Cepdp7+5cj5fBEpokwH18&c1*WgE@r@{jenVG_Y7}O zI$5ZmCXQ9pHdp5`8pChXYlasuY50}|`YOFe9IG#(DFxh+anFG)SmnbF+ac7NJ6uO^ zMhd2(%l(>RGZ>!MfROjX_8vqwtm|$~0G!t~!@GA-z0A^77IcjoT~5P<>x_K!IBoU8 z_QHIg+I*>mr=)P26Uh#{w|}{Iq`cv=7BwicQZNq@qjV1(aC!FS<7bA!>Y9{#cpal` z0_dYI+dgaOqxC%?a9$l>K?ZVVvIamw%c&LoMd^IIXcz}bx_W8JQeT<%(3oq3#}u&b zdtvdga!FDsf&;)hH~I3$dVQw&wR>yqdGC~1qzebx_@3Cnh_qI?4}Z&YFD%9oXHVOy z0N6Rw0sUNSff+5)c<^@Wcb}3?p8k2S$Jl--aIm{os(BZ}#nK8Wo~-&Hmie2>90+BA zYaJ(psbpoPhQFr?0M)Q{E|@HPWI4S9i-SL|ome1|*wG6?HSa4X9Y;Q$bVk7Ol%Z5B z)mVE+^BMDoNd)iOCx5WvU^jtbRjJy|?3Bo(-7v`pnSkDay~*HXn2wcwxmYS?oRY7Y zEP1Cg8&yew$fTt{5LwE>-th-7EI%_@wEV^-T5;B@_lNtW|SVeQU5 zd*=FYHRI6j;jzWcxzjS&w@+J9#9 z)mRRAepj0bjM!$GUcL1sS%=&(skYhFgq84p$8^vq&nI|1Bk7|g87 z4OgHNIQJBGc6T<|px_nuEzFv>2U9mbGr3q{juRoV27d9eb8y3?x7Zzye5J7{ zSX>4iL5E8+OVV#_9~^zn2?Un88Y`ckP2unINPnaAUgnC)u<1?a01RQ0t-$L}8Q^?5 zb-e+dqbQDHV$0m!d#89t*&Y)!Tzaz`I5y5AyUU&JAAs3wPjxSV%TgMG=7T%-LXP|I z?j^bZ?pKqJ!TFc)STWdB&gA%UIV~d?>VrL;e)sEH$Cb@F(~g}?F_Nt|gi2a1@dEg+ zb$`jhJfb||Q-&QNR%+7@je7Ky2h)y!-TGNND?6r#RUCYP*~JzWf`6rIm%qKIf#AP- z0r`T{%Rctmz3M8|^c&@}b(ZU{g7E2}MH3TH&g}5Dv+?0u?pjy21ugk3Pt4a?)ug;+ z>%5#apS&meHS05ZuX2>2c9oJ&0R0up*MDY&*9Qd%e%<=?$wU=DeB)THMZpq;+p2>) zHFvGsa4)vAvT@+py&UaskxG=^GA^}$N)FU$h9Ws}4DPu4tp>)X3I+{)Y_&ezOFsQodx?0f{xkGJg&c>w}z)v`+vod&%;kHs0_4@cNfe|2#gMA*2*# zSI8Q?2FUKzy>Eq$QpMJ>ymivB5&lQgdGe_%cy8Z{-^%5BzHa%_nLsmgsrr zgi)`ji|;EY0aI6JE<^!-j52KjJL^yj5i2)LdNzDdnQde#x+_jW&i0a|@IU`JKUt zYC4#0-8yb;9~_Lu($WJ*%4+l$?F?*QJtMUzMM^(2xgugQ!2w~iPAwKK2U~tH58(I> zlP4`pc^1&CJ`t`Cm<6`aUN%P(=J|rjm!v?J6pKATyD!A&*(2(JCrInY_Nlg07Cn?E zn&kvQM?{KVebowzb-|=)X2cyEmobY06MuU4E;Gg~YdEiUgGr@N$^ib&WSdw_K0GAm ze_+p2;;-D5^pH}-`8V=-z@SX=i!%N4f{qHm@EZ!lbB2RmX)X0P5-M{76YWq;4` zKZm~OAVf#2B2=)mA`+CWx?vKSk+sxTX9!%nzRI=$3%0J74SnSb zY|1N27Qv34*iNao8xC)#GE?M~_lQkup4pPODbuq$JpB!m#5ir2e%OvhlrR>61P5jV zE$EHyGwVLmcdlu)-quhs*0O+NrNJ{?p+R#^ww#yBul1yWk{gHwzx8NOHh*XO%;Z6A zOwN2Z)AVZGm;F?qym>kG#*STu$Tcz9YaELWf`>DiDjVj3n%@Xs2qkm$#P+Fdg@_gG ztSSMCrgno~F$sw5gI&{NpBlSFV@Wk=Un>{?B#fLf}Td;@L) zVhw4>*(H2pjs?UB+a|MlYk&2)aXn#Wtg+H^1?*{k&Qq+|?(hN~hjd&q=?s|N+uoy? zP>(<>FkjC?7kI;@iV8lH{a;4SjalcF{b}(J{-l)9XC|#AwK;Jjmn2zW)0y31k1!Wv z-Po~vPeJr*&Cld(`eGQ#TFM!;Y9?8psJ8EeYqqeOT|n9NBONWJ7l#<#BE z*f6$n2a|O0yvT#CuY);J;CeQnq(MLIfA&9r|KtC9{wMM#JAZ&_3Zic;hp%}lDIyXt zKId%2$}2`|C9P4aFWalG?--LlN3&5u0xlU9a79}S;T}+~d+kEKvDwJ*dQEqXj*(&> z-%AbtY_@GKkxJLzr97GN`I*t4bJaXs#d+s_7W)-w&E9yaZh74?iW4UuID6o(tCk4{ z;M2!}Z^Hoc6@Q~+CaUeTNHSJwe0IVFE7N6G=}*2keQwln>}#XA6jO7!#6|Fp7{%Q6 z$qJOujDmb95h}tVNcsUHx2-j8*3+*u@9f@{+hQwA>?j+sM0G0z)#|Xh_r5c|mW@T- zJ`uNUd1I4COmy@C&tS5z7zLMXt-uDgHOF*kdbX8wWKQJ0*By^^z?8v0^hi`H4^myU zGug=4Gj{DuMi=#!Cc6SE_64sPKev{2B1d5=hty5Wpw< z4*%2l-~adZmk5vnA%EKt@5VdEP_>`7t5ZoU!7mkHd5Y$|+EA*jcZ`7#3TFtsBi7cM zt_Da3C(VMy{bVlNSH=J+I280+N11yj0o4b0YKa&$+AQxF!}K#cI2xv7`tph67GoZB z__eYl-Z2Ky47IvP<$c_6)=Yyp?;Obyze;<43=j9F|KjI<+JEAh#f9UR@ewZp8!d|o zx}(LFY5jkuhrDFzXFaP^01K8IAPzMXlFokft9hpph(&NH)|w`4pefdKp(J?>y=WTH z&gD>MfT9S9%+*U)d~y==Y4f6KxKL&QrvU8fZrH^wX)VB6C$rDq^QQmh)1O@n8$bW~ zuS~RUO)#ya@PGN9uS_HHQGMZe<-v=yuMA=A5w-RtYp@B#%%AoZrr%gH`i>#YmFM0b zJAs7O-F7eBU~6+)9=v1!$`BB&y6&{bXr6kRW>I7FWnsjg?^uZ3>b6PIPsJ2Sb>Y)> zVHLVNJaRJ*GI8}{5{zF`P8g@3e?lOh_nb;h@-ZBdZTLD2v+1w9U zYExu*?*UB3y4>-GA+#3VLyo2fZo;B=Wkmw0;S80M-ZO+n+&X}#ZS(rJ&ri=91}0wP z9Ye4V9)F<`b8c)xipNSS%fX}A-Ok@I1bCl4q>Y_3tIz=O2h#@^paJuw-r*ewn<|Ql zgU5_u<02r~HTQ5}p?Ti17i@M@2PRoB*|V3HBdeXG!cC7ZZy5qVUl$zXv^?2~#Wu)Z zmTc)gc!8Sc?z^?wTh_LH;SWYDSe_a1TJIPFn}41Hf*y(}V>!Cj`4TTHetLTF?eDjT z;DjelN=AtG)#8=HyCuplQq!*Q7(xcOXPr%54TL1v$B%t``IL{C{gxrfz%V9rGZC;e z4#x()&eh=}*|p>iLx4xDHl{VpZ8@yt%j+?=d7RAmdvFLpuD@UVkN*5m{Lg>=)1Us~ z-+#9M@YA>7e|P!E)0NVbCBQ){ZHziAX~W_a3x`-Mv^Yo+E5 z^U~Hb>uzrvMa-&8~tg205s0w0(O=Ix|6jiRIj_W&lHz<(`c zz~RPTkvePM)$~ngqzuWL(w42(sn&xKu2UqZwZr$D&PWANIIX9db9}1QU3`4Z1`yGo z?9ctxQOHZs0}wJ;JyeRZ_X_(5^(@Dwy=fHKkg+XhTEK1-+)i8A5eh3sDQ}t!W+{Q> zQjJCin;3~~nOC~CcFE)X+TM5k)dc=ZO?%5)NM*5{}e?-|92DM{;~5GKC<_%5e|=Ya*k6gb~A zid8Z7c`nxA8jkG&%?fYS;HvVZqU%>jfem?bW7#nRh>hLBIuXX$!mq9^Z-0vHo8?Tk z9E4Ns&fIWbvJm00xc$j4DPJGO&|P^WROUuBH*lFY#WiCLyTy6eDBz)TG&XPIQ-2p_ zg3NTFU#T+QGYXbloL=_{vBQ$^l3tp)Be8B=-V{^AfM-fmP`T{Z6FgYnLA|V9y~JIV z^J+H;=)a;OjLXc0WmK4v!haT`bF{W@+h(6bc2t)qn~45~eWs!= zwvo5q92?;D-RflVoE-#|ecOJ|8K;l!68aXw{>K>bi}$@Mnb>vv-IyRBpkb}l;tM`< z*UEc)_Q|-u{#q-=Ljkaz`JTd};d2BetSi>PT(^HH#)7Rjx-18*-G3`Pz+8=-qVIm) zzBizQS9{Y507 zQceIU%W75t&W%-uY)k?=7$?3s*r|b4-@|morB?Io4tw24C#?eE+8w9I{ujGrX#T-H+Z|l_cyaqJ7*knp=H| zA?)bq96%n705d$gVXM`7$7ty?C|6ARX?IUj4tV?=oxQfA-!aN=ZBkyPBT|Zjkov@) z>V@?z#qJo5mH{b4)|mL-L0;Z!)wuyClHXZV*5qK5g6h-_j(>%f1PeZ8V=wD$9#@P4 zB&A$4AM)001&{?klpSZyMP<8{9-O6-?iiI7V=fle8KtWB)^s*##Bho?+}XWtLzsVp<8IfpWfd1tFE^pT|>VienJ1{`84@KULQy{8(7{TMd>f25N?W>oOg zdF~NM*#o|1SrgFyRDjv+I?D%*3cD19df>0Nd$62$^rWvesQIMI+0RA=WO;T5sy7Vg z%-)Yu2M{#RQ%JgGRKZ$LB(OPup$<8C6{S|sRJI4WH2;fQ#6$%pO&wN1;+;_jUXafA zmQi6ss1t6`7? z$b|I+YX~lwTEw?I%tdXjiPa3i1?H6_v{ZyP{8<#B{5wZx;_KFwO+mLtGo5LYyMa)E zDGs3eJ4Xi81put|MTvm|k1D+_{thlROzvzXHVFmwh0BUSh;CBH+0wg#xL8l^iqYMN zvrd$~NK&J)buyQHnE@PscW*y(4qs_AgQHcVdUg%r8|l7-h)!Z(A_SZT?j7OL;pLBN zX6oybJI>+s0MlMM(lW4pI9@81p8%_vV8eHg%-M&lx%Bk*lDq}BUtVG<5&pchrmie4 znK>0lu<2n27$oY#li*-QJhORe+(f&QNgzF zbMo!fa_JLf7@&nZ1?7@aoRwGGPszTA!6RT{LBFGdJ^3BF#Ma4_U}WdU=9{ljh6qbi z`0|5~8vTcV`@#25e(t1={^F;9DsawoB-Q~`&r>>(3eYjOkybkopOar30L~-a035Da zZw0h8W$g;@&;TZ^Ka0#Be=lVHzd!O*-e%Ndt0XDCI+f>n*XD2r)O*uQR%=%FY?sqn z5$#8r`L*zegX+cgl2wC$8F>#ay!q-A{MrYO;pur6yJWQ#c8zwWf1`Wz<&A`LP&uP6 zxnuQ}cnYR8f%Oz1dS;3M%o;l+_Rg2AB4!+X@vGpRnVyW?7{mtLf1Typw~jsrI8l}` ziv1s)N@EjemM)%pX?0bjXPFZ1JHQ) z-wHetyc4MD8a`55e`VRj+1r1!swxiZ3m5g;xn)L`rHE}hlFVCHPvuL5NS0aap5s(t zz|Klz2gbcL!vhxK{@Ki{0a91iOaUN?#F)wAmQ@8e%E5aZk;3eV;L}fI+YFheA7d3k zX@vX8Krl`FEAFyp%fP4_A`6E|-Uy-CZAz_1lU!4j4;og)A5_HDH{J}0T2(^6$m zz>hkK!@$j&c+Io2>8V@Ei5HyCoATa1Xjoce*fG96e;asBC@<|-cH=vgKAh?F9~c&v zZSf>7u&m=RQ7!z>b3?G)>K`>M(A&~$=$^I3F3wh}z|moBZLJ@*h}2N&l={mEfPI%C zhW`f3hy4y(o<3?=tZ>Q>z@WX(%H)j%40g&m;&wi2Z_PgRXs4(-C6NRGeeGSr>DQ!g z^#={he@~JE#ycp(IonQsW^n#9&Wj3P;@-ooY>=f|!9Z)B8NPrUM`xR*$t|nVPFc0E zeASZ)P;N=Q_N*!Q+%G|1Ei01rp1@Fg^~22lgN2!Tygps&^f#-`%a{eT3=Yh^7dZaf zC`&5Us$SY|z{0cJu5$XUYXc|4YyN00q=uU3aX` zYFSpV1@UXLaaua;6E{yfZXuWO(bQOg{AB@?rHHX}jnr+LV0Wi<30f~+oRD9)SQ}2G zH=LMbrJbWdg}1Eg8NzDG{?hB+*vJ{s56&x2Pvg>gH7&jERVbHU`x(h9epl1PX6pOa zfBn%0($2Xj-aWz|Q*RTNnGY6z3EZ8r1GH043t-BYj=~%6ocxss zH7f3rB=cZ=Fs-tD4*9+|R-X~)9EuS>hhhY`OJ zLa=X40V>t)1^9*yDsEk5xfg(lF=vC10+Q(2CpHuKdLMcBeamXiomyo^-HT1-I`)>_ z9n5Z}2eHII`}yl%o_;R<{D<->1lu%eZ6Gx4%*Q>`CO8*P>V`L3x9qmL+w?T|e`<{v zXp~cy1d^3nW}o6)c9~@Z6iAs4{BV6ChF#9|$gfwRTXwA z|NHOpCr|1M|NO_kgmkHsAUf&-e_?8K^jQXp?uu<=#zo6}7zmnoX9`uY5;*(9J{q%E zdGOl%7nbu#iMc&zgHM$HBByNZ*n2x5_4T4<>H~u{D?(>gAyA0S5>ybjgx}q>jN>UY z_j0;U`1RfE=_kr)C)eGMUbK9MQVDoxo|nRO^&+ObE_R_lcF%Inmf5AFe=2yt!8$g% zrj}}9{l;n+Ezh|C1bg7qX98^%%JqQhSfyw7iDq;Xjr;X0Vuj|1i&|g~ip7!pe)EsFR zww_}PvF%}UJY77`ZLud?e+Q8pvtgGlfDZN}k43`upz6>sEW=j|yQW1t{8aJHbbN!& zgFljS&oXd0D0^B4mSqT0#m7nx52l>_o9B7N98|Ea!YAyW@?JnzWVhn(D4ZLu|mVBWi}IwDxflW)dnf87X+iIpYB$2b6X zuxed_31H4_zGoTOBWF7l^8$DGBa3;X@Zyf>3Ey(ja%9IomI<~M*w<&4UGhG|5h$O$ zkNSn>W#tGq)5O7Q<2ZHu2~D&IgXhKbY;6V3kxpIul>GkqpB~mt{_JPIG+IhJO=VBT)PDQn3OwygNVEZe56#3mKTUw137TL7xlv`BjG zYbDhRu$qStf97%~pu2oPATSs><7;axjX7%+uU%lka0-K&1a5mXcP!sB+kDA1-=-rL z5nOBZMw6ZGpKKcWh1p)avN`u`AV{n%;47k@nh|>UgUV`OnAK&Vx@qI!%*sYMa{(;Z zT9yxgFa`cgv!LB7eJ=`#r4-XA8wuvl+`pY}nWf$Ze@l|nK)}hxg&ZtIbRp_I*sbpi zvjLuIYFb-itJjUC^{z!i@!NE3lCwxiG*iBOoqnX`HgS{%xETOiu9;UFKkX2Rvxxy{xhBOY}3)8n*`l}1z#*NRPKs6S7zEXBDCj~HFt2|g1{)JgS57l5=*f`ixqpYU8 zmn>`VwbC`SE3!=L*T=MTPAzqURWlNwKE^Gxf5m&)pnz-j@_LmL%)If2ioHK?nXRMy zsg$WGK#CM{6@(c!M67?2xtZ;zXw6I|Ckkpr{ zm~P>-DBw=H_N9zOO+z zUO#R4nfp&^E5PVmQVYhZN6}L{RN^!w< zFo=c8&SDN{ZFAgm7ggyLQnJ~=`x>RKVRO%(UbTVgnpsS)EVo*YuLWqHUWo;ixTVJK zEwfW>7X^uSg?E^xE%44m`DTE)bnRbJ~V0%W4Ff83@{ zJechU71{_){Ved!Yi4~4JmZPB8>Nw%`X7^BUQdMsxn*|iBuF3ZV4?*+IdNb~t*yiL7HKxnOm#V1>aw9|dGYhN4PcUGYY>t@*F zyKdhTF(C%%=Owd}Hap`ctmVX~e*#I0!&POS02qGls*@L;_0=gG6nDnpH=E-8;6%4| zjd~%xE$=p0xFn-C^(mlZtL;7DrEaaQ!2b?}8?cY805b5BVA!)zouSpp*UTCvO*o-& zh18)u?0&oiXt|UJg@3*<+g8$I`z&izg9yT!JSKZ^ueEPQAn9er#=_R)e*kfj3PtTz zm=Gzg`8BiMneovD5EA5|W;iKBxCP&4AHQp6aZ+kB_8U*Yhyfh1Uhx_WRc5fQ)|1+5(Q@I*0gbW6V9R_llLewoHhY-hjwJ z=%!j`YK~^=%uS3%ubpy*p9KbMdF~?xAUJlGGjLYM%=KD8Q&3i6e-U0$UnQ|gNMX`) z_|cZf2bo>)tfvA*z^7#_cOQEc9dL8ADS~kRsBvNA;{XIubm__AbceTmdW}}=*|~qz zxK4?6&Klhd3;qLJSKvKf8TRRnYY2e^Rm+({G%uwrK*59ANlb~k_N*@;PtTB;`a7AHT=GW_Ipn@VW!&^H@{c&TGT8c9M~< ztu0u0WiiuPDr{s1@}yDsU|Yj^EgZGN6gHXF#IT2f^!G+UMEE(yrk`tO@wM~SjT$kB zS&D4fL@jRW4a=?jhgQp)e5Gq(h_h~2g#2+vA1tR>?V4Hbe;XzR8~MQMnA%fYlkM&& z&hIU=(h}TN2aX1QUJe(Pfi+62>ri3hmRZG=0!zpQNerOBQafN4wshhP-nA_?Z5&%I zZ5)>g1OZ;G`0(Bp{`=bfLo)=4YBL+)gcln__DQ>90HvgBm$S{hf^#4yzG^da9l1^X zy|?bN?AqG8f3W+P&oUhQX@K(>U)m$9hTU6RU%9iVA3(r7Tb#N{%cw+>Qooj1M*SSa zELVISc6FFrZ4Jk%y0vwU>a_s)1}Ifo8*nGjWLVRa)y=BtEpXa7&xka&%D@o<(xHMa z)v~*R>XvI}tpVWy<*{39-mi+Ao>FDQ*tmAz-}45He`M_-BEYcO=q8NalzXso?Jcu~ zx;ZvQo%z~y5xIy`ZbodzwMi}jv+Mv?02n*sUT<~u-l-#NrC&2!i6M5YnPM__MiY^K zh;9&m&#l1M0j3sj{73fWfUQ!G4NJB8X*=JdGrc3|u-6(`bA81iLb^nSfeNH??cDO+ z)oa_Ee8OPC#4 zyJVLA68EV#qIey5BD#y7IB%*GxA1)JSV!y&q5c6b{}spYHQ0dWo!y@09` zvl!1Uc&^H9b>E5l@T2DN%DZc;DkVy}wv!c3Vb3*ok5e4MX zuL0^Y@JpB4=jz^44UZkO9FU=Q&FtzdYS{_>-9&D)P(GE`6y{|=N7wVZ-e+SE} z4!+yi2507sKe)A%!QQ6_Vh}jMwl!g}40z`}0b!fn+R04s(ijwtRaa}KHakdeuC3?M zZegj}2Gwt*v*i|vSob~+zDfY@`n88OW~P9ROq|>?C$(@^n+3RWbJnl%TX3Dj7sM3N z+8mP?3T$h%8XR-ER>3scHYtxde}xY-c}3aAVsp(JOq0B27AJHMHZ+P7*})HdkKwsz zX)CTF$9a42){MMFYLybCH zsccGu?*<*I1q9{9uA`h=5N;KZ-l(cqEA|$mkOmwyqR^Qmms{|B32@^Ce*sJI%45oO z85x^7H)fXEtpl`xjDaMiu_f$lGYJ#t$0^NoZuiU{{CtIj0H2<^fhruUoT<-|U9U~@ ztj2f5soP*jW+6*gyrnDe@2*4lqX50SYp^fSF|8WZa@&wnpoo$IdXyH?R{q1$I^)I%Hg1TPrrH6%jL7 zsRb@1^Xf+Yzf$D_Rh8}fA%W5>{|ON)}GY*|G8PV5Ls+wuy}!Q2)MgYFcFTq?$Pd;?hCq87shF*P&8)L$w?<-74^EQ+CO0tK(hfG(EuW0YUcf^vX;XM6iItcI z-J(*gBj4h;*g;8wC>&Ukl}xz@))ZP3ulH4!r(17f3jgw6_mOdiw)U$9{v&hq-LO-YhPPN7rw}EguKC4 zhdOO2`@b#S*L?E7XLb$VqEI=cTdpx0FRO-$hdTdr{itziG4H{C7gB(*u|_d~h_-oV zRj_~5xOU##l=uLn&^lVEoNuXnhTTV_w3U=5()({xuo-dk@q0Xxs3*StD# z6qc0*Y-G6LfW2>L&0S){h+AF?fYsSy4iJ4afAhXs;G56R&C|4N>ANm&_)?Hw1?@FV zZbmfCRfNS!*LavWfGJ>DYrO3w1=@R$ijy?5J*xTqg;|kQ?O4Kx_OV~ZoUMTovPD6? zW){S&04L?GI7kNQ-fIFIddcSdwW4IO4~mA@9hO(lyQnH#vg5-k%VO8ezABs>7Iqv^ ze}mpZ6aXudv)(~&p&tD7_DcWmUVJYD>Y4@u*elDxu2tzc7I%~uR$@B4!D4zd;=KxZ zXYKWa%&uWcjt;i8p};mGWCrp~2h>g5lfCHvgX20R=~+h_jkQ}~Z^m|YXSGVKa?8C2 z>+LsB!&$SG!q!557WODRSH&&&8ik#ef8ge<;R|sf4D4jc<|_!|sb4coEHbEtP-HZ= zD`tk$#yQ+fI=f}IQj17@WsopX!*mDROaS!=FVrYP|_j%)@zq~L4`I;aBLvn?%pb>W#Y>Y*4O&AE!7Y6*vl*{f3?iZ zybUK`N*>xzza|w2JOFCJhHfAjK)m4%Fu_khg&pRveeGn{Z>6&FY@7W?`rhEnoh`G* zwddg2@D+$#c`mTH!+c;IqybEnI<{6^Gi#v#JI#G6+!EY$OYjqz@tr_f^_tlOTfS=6 z8f??lj;v`xi6C3+7CwncIclg@f1SAvW0wLpKSOB1pYCh!0^bF&dw_w?tUyV7BN*_d z#|q&0b36I>KYst`AAb77U%&hIyKjEKeq4Y4%f%o4s++1T&%!1x?ZxsP;=E(xcn zT(-`a^?4c<^;ZJAsAiKgKtT5g0ROJ_IkA?bIHPQ)nm+<=;ze6dz%mc^fA{!R>pOVU zf{zwen}H*n%1cXhCgz|$XZ>H+|NMvVzWMe$fBq*@2OHev9Ew6y6r<0Q=R`#1Z`R5W zJ}-Z6l#Td+IJ*xAZlIXEY!B>YA8<+!0>aOYg7pCi4b2H~_~c`VsC~Bu1d#y}*Bzs~ z%w1y73&k1RM>nmRbFke5W=} zo%6v*g3m`KFNyTp*g6rrRb=))vu+0(X{Fj7qZ;htS6HvI*#L}zf13R{frSFV{*KWZ zF+m|LS9d+z)QTjl6MsrAhC4lx?}VJ_|$5-oU(K&6)hY` zc57xQ&O1luI4`6dAMy?xn*xdLe&)t$)s*FqNAk4Pgw;hMe;tfLbQt_XPqXzUa_$%% z6t(CL{C2j?j!*`)+*&_uG5TOLtbbj9{^3tR><>4o`}vQ3wNTqWG+AVymNzDGR(}a( zgNaN#_blV5?*@a}fvhstFDLf5=F<)p8E;xXU5b|OE7-cem*uld$Tqox3!Y(8fRoJ7cIllXZGFNK+B)HvoaYha%@1g zvoBiaW29~i;6ZQfJ!Xn9&{Jk2eraD(y@S`FIw)DUdVHt=z5ZkHrbPm@&q!UWSGCStTksG zX~ZR&JCD;OfFx^F_O+cCcNo4d%>x2mSaVfd!_IETB=l`rTE1r)77zQq*m9ve~t&gu#ElmQZoVknyckm#MvOSgQHjv zyBMG0ISyRLT-0$%ltu^uGdS>8n7~!z>AiFys~Kc zS_{BS0X^Zq{Uk55YQDI)*FtcBFTsXd;;hy2usIW;$xNV57cB=cPmkW$SOxQouuPrn zf3BVZ_&x4f1|fvsV(EUw)X5%|SOCz|LnXJkc%E(Kys52{gAea@4e*WblDWxGzUV#S zMB;4o3cnp4Ajl|n-vcCLE_qNR;un@#&5roY=K?CYwS&K_!jm9);mBP)&!<|{xh3%F z;xjEQdDU(u*hnTW;;;kmkH5gF$~<$te_CSf1{}6dXQjhE%RYLZo#ogyD4_6lgp_pDaMs09LF>D3a@zC0+l`IR9oUIfJ)(Pwpb14uw( zgUvko*4*DQ1lPtwB*Q`OI;V>5w4DhqQR{>PW+ayL9R$&#EDZrF&Q#k-?^uYeB_XUKim%+t zp0P`!9s@Az9P7y&!`~i4P>!gTg$S1@p;HSbtDBC-%-s2gA(Rn5;TYUZWTehqT#CB6 zZ=k6sIm&MifqY>l97WHzHc?fA7?_*)jFJ zV+d}?F%iI83;);z486)&Ta2&<9X`TcLZxVrFz(+Y4RcvpfuRuR(GT_M^5ip z2-|%q8#84$$2O#VDJ6sR-4I}YV0+k$g!#=b&vitSxt8{oL;mUp-&zHbFvN))(- zor$3|GZBcI5}w`xS@x-{F9boTUf~$93xVSj4hZW_?H$_@`z~hge_$mU{Ch^Fh7{G` z5XM2D-hrUcu2vzvk9R%wiSFv*HumQB#8I2LPf78(t`!i3YM*DjP!Aza8ZPyY)QSG^kcG(^7YIBdgWe_SZ#3VjWW0NxY zNi0Pws}E)Z$9o3BY+Ox1C2Nk|oH~M=f)Xb1SNT1Im<3GIn0b9hTBI?3>OP$^G|Vx1 z%OI9TZGq*;z9x1ka7!I(98s;9qPGl!-C1|7t+OE%e-)<;QQeXuoH)xH-ZF@jJ6oIq zyz;VxCA^&vJww%+JlTQdYlDap%0^!W!ON)wY!lo{;J0?|yT1odgd%>CL~@>( z=BhovdNDr-@BV;4`ls)|`Nn^|@FQR7Y_H+wyt&1UhFa%d!`#kD<-y{vpIdEZkJ0=k z>Xy!se~goTitc7CxXgE~dN*v{wQ0BP*r%pOJtS-)60qkM?Z1Bi{q@4ho!nBG$Sbg}V*~JRk;O(Xigd@u(A!?`O#m<9?U|*U&X`V6l;NY2b@sDDB(%E3r~g>knb$4Xi{(a zWabCXXneda3XlObx?+y$$2u>@NQFD>A-Hg%5m)=r)U4smHpr4#y}u~(v$Ap&1bAXT@_%CLzrlnmzuxTbVrGH5!T zji&q-a$HQDn=BQlPX3l^h7edZ@;TqokbXx_Kt?MWcV2za@S4yU|;XMkoVC@lPCT=P=r zRgMg%iK7$AqQhqt;5q9ZmeVz}tPYJDxv-~Hq0o742^*Z7y2dSd?l?Y$f0b;yz&E=~ z=gUl?n%UUXZ^hd{fM-2bPt*xsjK1R-C^e8po8uOiiqb4~Il#+xNsb0cL1lM77EVOP zTV}_A--j_Ap=@icsUf6#l>66u%Uy(>7SbgGfX&(asIgX^ie~Xb<)p1|RL9?dye98;XlyzV9vq6H;xmOf225v7-4N5 zS_;e3SI2MTUE_!Y3h9KVaneD*Q^QC`H z&uKOXCf3~6TV`Puz8K1QDd51{vXr>+&SEiV_`G8X2rpB1U)0MQb4$v}C@x$AWT419 zhHzHz74dF1-CHO|f0hIAiYf`NeZ64_<@HLY*m&U96pI7<%MzeP2*}tO?-)X??jDP3 zVc>oPC@Zt|A|r9C!`?82y5VTscG=WFE_qh36Q_|)Wa^U=(_a}vz%w)phQ*>b0QF*- z%*wL<-o_h-AW5qfrh|bYmXab-n+nLkE&vWa ziUA<)p@$^%=sQk?NSdHt=?nm*!Tuq|*gn~67gn;qWeBa8bLs#-%XG@+3}d^&R?|UHIp019xlGZ~Gsa;PQzoBfUIn|}j)h>p-Ar1r0OduPy^M9pWqq#mV5j@9451f7g-8ucKfEkN=^-ko zxPV-}f5SmD0|sn;Av9`hyAQ|N5JA)|&FX#!WYMMp#6FpY=zy-hv5TJJM7Gw~e#b(n zQqj%gRnmho(DMONRZ*?h-|0C?SS(!JscQasmq68x||BDfH# z$_A-Oyy{e0~sB_30xnxyRZ zfB7}Hu@SpBH&?Qm0P2%Pij+xuXJUG+V&TaLD12ll5{V47_(Fpohnax2HF%Z92`J#L zU_PHT7d(XyP+z(vp=5KLaL&$b?)DMo};1)6DQrqUgTPklQ{j1Dk-A{(-hVz zqnT9{?;sR-_7IDmf`aC@BxOMqf1{G6+NKyWimp$=oNyP&H3eD($%s7(1+eTvGLwEh6a?%lyab$D zQ;3utesAhZ$(6prC+}u=_p4*$W0XivoTKRC6(+|B37Z!%8!B}FtKta32?G>B9WpS> z2#^UX8eG5g6eGEkC!l~ibTMuY^iz@IMNK)w4dIez8PId&6ci*S7V~Q2wQf#h60JgM zo#IXd#>!qHx#6fsO>`s>Q5PX__B%(0{al-P`5r_!4l`83_YkXqe9x zSGmNrOqLh$#W6Rxe@#z90xxOFRgvY~Qo}*V05hmSf3m~aXI-9z1Xx}LnCM`Kl`zMH zL1c2_O0ZBUGsG}@5)v7xJ76N`pa?4NScxeMslYo$N_dv?laMG#E@0KqV97H+t*W+K zXQtFenuD31orVM^(-kRn2KZmCa|#w3lb{6~n-L~X(VkFCOY~ngfF}b8Ff0-4hA%Tf^iPE4+)56&j#)TCW zcVCR=dqwh1#;f^!+B>g;X9y-Mt5^36`|Rs{@!3u1UqdM^gD-gWar?;{&=LgLZ9x8o4v>H1 zf#$O@JQy$U@9yS{o;to>!}%=n#pBy&0pR`nfAjHWcoZ>zx!I-rMZ_EIh5nyc{KjV| z5n5_z9ro+xo5XAjTHoQiDfQ>;X$0xV0^<0?=*v{tb7b+ri{wd zl2Ejvbeah;WkG?Jpg(Cw_BeIY!pt*~Go6=2aq6tfm}FUz0(osL-RGLUHYQXMkU*8t ze>N8w$3%-%5}-=)_S51qm<35;zQN2Qq)>zlo0pV<{%n{JoFb3GWd8heR#1V7JT!Vm zm;$@p;A(63*u-sN3L-4Auz+)x8t3o^4Oe80!CE1xmgzAtC0WgT}(wrDYsj@03+GaXuIi8YB3tsM_)dA-HY@+3A0#i^}V1||-Si^3v@So4{KjiA- zet83n&((VgE3f``^HyHXQ%yA0qL)$uvCLyyWWn!X|nSGVfN)df{w}Mi@I@ z-PrLhXbIEtWVV`*<+xHP#@1h)-Iejz{X~CGmMghfCD->8)6B#OmH=4d!4d>ZWKw}8 z5$vob^}H?hlYjB!r*XKh+tZs`e`LBG%ezUJ#pVU-9}`2okgDwSi+3YzhUxust-<f2h;qmjRrM-?VJ*>hvy-82j)b|P}Y2mcBfB9O@yOx}maz9%w z=F_T6Su^%6aqo>HSa&91fPlfF?Q+>4wf1kk@6Iltq5T(Ly{cbr*a3P{qbI)AJ$e#~ zBn|r6K3pp1c;Vi7e!s%4xUZAdP5t70xk@%L-#p(`h)F<95V0oOMLgRe|9y~ufp1^5 z*?#E_ly9pW_)@UOe>|&AX=uq`rt(`oQQZ1muF25veh&ZQap6z=rhv4EEnJsNe7Um* z2Uac|>+^+~%%HbG^?bc%UnXWE$Ft?+`UdQ+Z_AavU5=;nex`5sGPgikwGyZ1d`KdegTSC?91x4nAxH`Hu(bs-mWIhuD!LqXl;(Yv>!8lQv~Dt+1XW>SF@1&fIuMMF zyXjgsiwBh<4*_~KJV|PZvkDkAAyAyd(?(nX7)!0eG+8}TV0f5RAhpPk9dHmjUxI>O zExvm!&{(i}2m%o3dG+^5-y1oGW%BN3{J-Lmgnxq0f4_o`VeFlq8F+1Q(mSou1|$Ipe~p~(DD4VLT{WeKg(vV*(t_@D8NUY6=k@QAT5U}3QvdqpfmW!0>$XLMU$@9| zHHR)aVB&XlJx~~~st2_}*)Cfn*+zqg9xc~0#D}@^^Or0C&Q*M;;vO+-MLMZ4&T9Bd zpB|rwpIVZ?&F>fE`B$h2{ElkWpzQj`zECWle?al1Dc*?v-x2!*U|&{0g5VYIij0-i zpJ8B)pBn2VeA4Q{Pd{|J@Z6F}C5hCkzhRd6^#1wf<@m)W?js{tu$;sd){m5C1`SH; z_^C8^J5(|os>v19uE>i#;qK#+x9Eav@m zYmKP~#>KsY5q2}5qplbQB1BR{BoX4JM}Ac!zw(cxK$Jv>b(Ni@p%_}LEiWs~SM*h- zzSMHS#$SQPv0Ob;4wg?s`C85&i1`Vhe+4<$s5m?M*CwZjnJne?^}=3zdlNl$6Kz{^ zuzcdnzpUY2KmQ%k^#ql+=#^aF$b|`8gJ_IiKgQ2dK}O$X1({Tk6|L=W0nx}TsCt(b zv&;Cx=s|>IQGc=%H{1&zRFdI8S6zRG2gLWQa@&VvN0n%oz){!=6!xPp+>bKBe;C3& z0IMPuBK-X>K-7@I{NE2VIv5(z4-o`V?cEY4#qokXJe?L-FWde7>Jl3hX4XLqs6tKv zxte;%A4x~z?dq;){djNSJWSdHs=*K|+L_tUKV4kC>p)%sWVH^+MmKNqOMpkuSo1#1 z4v$tH#vo+;Zk=~qNT;5lWG?43fA7VVi>2M<+p3COEyz_}t<&Y-z{W z_V#wqZ+bNC#4}2eQUB{A(>Jfq&pS+^26xl>x8OTjEhZ~?bux?V%h>P8e=K&|I|?|# zc@uDw8YhW3FI%!c1zGQES(pBu9-m%h!+s=Mg#*OdcbEw~Rx z>$p36D4y(q?SHPf9x*-ze|~<9u!xnkv0B7;V**XJwjDV z;il;vtN^fk78^~_mhl&%L(!xu`Z9ujs-BEGn%d4At?efXZm4%*nyH|kDZv6f9YJ zmyO)^>!U&4d4E0oNmpEQ8G)X9SM9{F(9@qbNPBAAFFiuZANnb2gFb@Y)$QHn3f=Mj zF|cb#?Xm*2B%)RQH!L_{zD;+vJ$uDamGqCovh;^XLU35y)IEN6>{+d?6DM_l;17)_cJ+QLZ)JXUE1~UR>AbS?dTOuQD|LiT8rYYW zr03P6ky%IwCahds+f@<`$wAu7=H|wvG6Cvpc#uy4#M@OPfAei7Z|4V|7(kMT9ie}~ zev#Ar9d*I|H($_$(2{`8gXYhXZ|p}j)T`%j-oFZ^v*A$C16n6ROdUh|sv|X!P$7Bw zZkAxX1PosP=Zgv;-~~U`9&pkB717RP@sYh%)|j<8=kMNvepTU)?94Cj*K(mSZY2ga zX*siMUCFn_TMzQIiVw)n*27&VCyI_ODO>UNNZI zPB0A2i}x?Wa`@duCm4cOL&CoYS-yGqzAt%*VC_9$*n6;r(202$-836UOYJN7B|6l) zKY7P#4fg6mc@?Ew+_vnr628@V<{r^z2-#^R&#i%cf7O!QZl$i|iXcX^NsVC_Roqq+ zv$a_V-)g^9L@~-OKvz*>4fLxAr3ZpoAup`n|Mwe1F#l8m0Lw!M3s!QIN^US7E4fK6 z_tlOBo0@n(!q4O7*U9zte(W9_>*(%y^4GnD*{n0+R=mA$Ajn9fjGC(V5Bxm7{5pB_ z{*UqNe-IJb<##u|hYoVIR`u+nj4rJU|FB_$p&ZlTJo!#$4>TA?n?ymw^xgxL=*9_D z?|M}4U?7-r9dtOn&wjv0^zxEAIq4$gjfSe;#>w1c?bsjDvTrH+~GHenV1W1g{O9 z0p5OYx<@ao8oIdX5Uo7G-A|n;HL0X-tA^+J2Xc&>9n|Q{WHFzivN`@D7ZY4H9fS1s^=RZmCuZaj48V0jch|1KFiQ2^8~hDmH@*V~0SA=%!>!$$5sidYqI4k|gt ze-F4g5@&CP)-r(HdldR2J{av|$UV{&0?of=ykX=IhB1%-jM)dkoz(X}<7*|C{OjCuNj+ZzohtP^lbDo(FD zY(D_om*JOD^v3KQ1rFaMl&DLhS0wrrf0qwBPGX@1pCnbGhzOnQZ+}Wc(u15wnv?< z2bt{}H@1_Ep;)sAW62(f6WbzqFr;i#?AY*Lzy|dGZh?0f#xuE{K(f|X*|rfoe<^s|370m!gK)AnLRZhQ+n7#MvHt>f?!Wj~;hlTg* zfQ!+v&wHbo`i%hr8?dhA^4m;5j2PYwltW5nQ)6~>I<52o#je05Fs@a z)IJi{NS@hJ$z151i&9dejpAj>w7?u6WDnRoFjH{Nxxx7M)p6V|QAkn?d4JUxi$tu( zTk1T-v#NLfx4NyCuzZyS%b@5Z5H+=lgcGowS$KCPxqYt$30cp$D&O7`# zUxb4IcocLweKueE^H|EC+r{&s2kpK=TG$2!X$eS6I?`Ts8NIuF|Lnu%`wpX#lT$sP zC4{F6RVr8l;eF73ZfKhN)4^UPn#@-DSbqKM-+XX1`=$JQ?Bo*EqJQxe<6n{zOJm@x zBxyQS%hz5ENO_UG1>{hNmTcTnl}V7Dplp9Y*gMTpb^@|}95+kKzmp(3sYQFQR^mm! zt|4D^s)IuPX<}cUcfWng$It)#eZ4yGBj$@xo#%kLy@@)_bC{ZUYQ4Qio!S7=zc#u4 zZY^|y`tZf;=kT(Xcz-sy-5bU*tW^h`!EK@pOf?Fp?3D4SxZ4}K`@w!htl|fJNyM$<1zw-OeeSUz_kTfn^Fes$gB&I3p#RiM?SvYv ziw^d}7=uvPcYLet+D~CbEE8*|T_!jGkX%ED^Btt2G9=A2?t+Ap6jHkm#lS3IA?OT%N+BYw=jN zi7X=%Sh~MqeCb2M_5%lJ+5qk7`XD8_^uR4Y`CtSd7*p|}!SwE6<7qt#53R>W&QK&C zGI`_QIDdaJI$|_lJIbvcd*?UIJpT498pHc{|9|k0{Zd%v&RE~kTNklYCXt=C^41CT zbBR2-*BAQG^pQvAW9e{U{!N7P$K|g(4)+}nle7U>)@Oq2ZK7Ro+4|b)xJt8))|Hd= zu(s~8U2oh4+nqyiXRXHuhE0RHWz+5Y!9C0^jD~hadpx{>8s4jqR_wBIdc9?@#k=3D zy?>T1^t#(OL&WO%WFMANL+-xO^O))PNq27T=Goj`8SSUmT+613*v;m9jafYnTLbU# zpYY~t6+X3GtR0kW-u_2?FR9*p6U$wOzegRKyI18&m`swlR+@i{|Ni~nF1`h)%NtlS z@4|ytR4(E~cia|9z1+xWKmR;_bMXoH4S(@5g2ZGHF(0_HJhPhS25-*RQkXJ#EVE@v z854Hrn*#th=7!kKmDs$Wz*wkB{c_Vn@)sT8Zts48u~-N9MFoZM|6@6yg*>=BLpMbN z?0<*9&msgu{^h?Lx}=_d%_U*Gnrv9qTfFGQ^Cj_X{qE78|M~m)>7V&?KpUa6QGZY8 z`t!I6?b|yj484XPq!l0N{eEX2`MiEO3c1>92g6Vr%&oqN-oua%Go(!WScCeUn0-kx zi_mw-iU@sa;oR1!_x3)5o@~a1;cCtJ2b&I&Mz9^;L{8p#xIynP%#h>!7xs5>L$^H< zy$ukUgTQ7Bjvtc#TMBQl=AWNoW`98VJH7R%aNK0ET!lmILsfnYFMe5~hd6LU1_>}o z@`U~Ez0qx7NPov9sR<+`O@II%c~3CIVB!hjNg+=l9EBgh?bHvYwp}UxZIFHIH}byh zP{uCDGba>P(U$afXTt9*m=`f0M|-=-*ZWrfovdmb?tq&#zOFs=x9buk3+N%$ zDW5}AXhFa2$qK^1EXOw+wr&PL;Fo3M-+vnmWA_|k4yUhju`&KQx^a^Be!-LR+gNG@ z-*SPzlyAR|@8b2<4N>Dmo|L z0@%A%bWR{L?j6+2tz8U>*6G5Z)^kIM>Y1ftlCA#+UHp0ByjIQ_~Ni-MleC z`!`?~wzDhR)uGtEHt3_&ST>3Y2V8r&y#vF$pGoeB=p9Y2Bo4}`2!OQ%{TSB0wsru6 ztDWO)hqNk>os9#1%zw{-BsvNLta$C5VEqV-x7+!*M6bm}#Hz>KzJ6KF$5qCP@z3L! z2%%f&frMC(%zzOq9mI!KJx{9Flb9Z%qZ>uxZ#%q$9O$n#@0d!Vlg%g;t*X4RcYcDj zr||B^dNwlO_DIyM?wkHr<<|@jiPhcF&R$jQ?pxg~$c}CkkbnKQ;aBI#Yx4tP?K#P#ljn88 zstJ~M6~{~`*2=3ZlRLlTIo=rUbiibqu>pWi97UZ-EwAuII-TIFw@od=2XIjFSV#HYXZ4n2Zdymmv-;cM^tB%V+I{q9-K$Y z(qDVGSwS`MUZP0|_=>meQBxMSOiN8UHJMb#Fd?!m&3Mj*+1azy1+_A>#*)l%E~y}? zUf*C~&{5Lb2=Df%=qJJL+S};qLEv(6ibTqTJEVW2e z;zWk`_m+)o6oCgo0YCXNCsskRwOGg`X5%%#)9v9ipal++ca zNVDTe%}QzUmh_SpytGc1C6mq>U1;N|)Z{o)OH&$~DpRJG(2~)jNCj84NC`Z&iXBI) zX2hA&T7ONLwX8HwD(56qOqa%RDUT!7!YAcQOPN6fGbOEc0!ET1mJto_KTayA8Q~yS zQU={0WYa9gX4OolMz}|TvH}Kr$_%qo=`>fVme4HF6Ex@C<>qmqs^kU+KD8R!iKj#g zXN%k@kRns}xWR<3En@Rj6lqzeqGV;pILs|J(|-(TKW^CD9J`){0cb7Y+cYb4>awB` zR#TW`9|u|#Tq?m+m*$S(Qi7BDRn2OM=q zsK_4$T2KWuvC&QtL0m>N_zNZnNnq;EZ7LoGS`t<&!6?nRgl-^|HYMSu%QUuYp&kV) z2!8{P(AhJSX-6_>Se|l5H7yHR1=yoNjgTo%(;Q|bg(oP8q-hDOsC9}IY>$u5dDCw#;_l_nCwM@ZC02;>*d+IQGO}Zbp+w?)OZFHhd;;26lYv zgc9TbsJG$bLAn1J%%I-gtE-DA{nAZt?0;sLE?)OADD>8@Bwl0iNU2rvA+hK2x0YNv zp4qRhEJGFPy<{hV(Ygv^z2b8G8%Swxfmo}5P!OwYCx3Ka>|XZsF0Edw^RxDkSfTj> zOq|siLwaEN9P+^o2VSa-@N0V9NrvAz`--);ENDUxYWs|z>yBh9Ad^9AX@_!kd zO*yE#L5AycYDckYZGMC7*In7QyV$gLu?P5strD;@cgj4z;k4ZV%djy5X78p<39E4JWII|X~ndfTbxclodX{J)po+^hc!!c4SX`X*WpBKxbvSL|ovynC+7|@* z4U`@EYbC~ieg0B;ANCkdcy|PpjE;h_zma16`#=8`p#Xci0#kor4%?U+{#~m`xBMe6 zs%e+6ZmDStsII7KzZa7*y2Tv6`22nW-*`Hi-S>L%!|%6p&ij~X_dTLN*8?w6)^Bglx{|h6s#S&9VE%^D$a(x_BGD^V zA;#aP^>6~;5a?xkKs26`nqjW>6(5HX>2SGa2q^KtedT+E zmV`r6Gfc9+;z_-Iz3 z2m13KoOseIjRbfQd+DG49xy=|53(?Bw%)B+?lYP}62{zC+aOCX<{5^sR~h_pq^v+| zkb3aM(}p|Lp7=|DL#Y6OXJ_yP{CsBDX5G!PSyj=bRrFm2cUC_eZGYZa-F7SHlWtO( z$({b~%XE3}PrAj(FD67GjN?*h%5pAgA-rqH37R>%yP>`gErbO#kU4HhNhQ-+S&&>( z!9__)smkww)~PiP$QF#Ml;mZWm#hE-CM#6Vax1FiW=?^srGLO%6C#`h6P8<*Q*B+U((;k0nu-+KfEO%J0k6mjON~syddqb# z(|uZa2F*~NfZWOOY8OG9tKE`lZr$O9Y18G-X#VX0^hYQ-nk=W|JQZx5jPaN-NohWQ zdW#V)Gt?60Y#CQPw0V|x_0yqmcUVpnl<$uXqx2*SPg=s0D1RK!4p(gP2ytM09@&0s zv3(iYhWh1cTGbB&MNVEnkRR$70&yOwUtsI&=h;43KTZVwk>3yH@BaNF+daNttA4a# z_P?*=jY2-q!Ti@Jbr}R6RgUa`wpmpiL)=mOLapVGCmdp>x}+le z_v?H|xbL?~iD?}Ghu7K)%RlY6wyuI8!)M5`T=h$XRKJTj^~v%M3hJJAc7s*EU1v6I z9f}T~hj`V3@B;q-^R>RMeWY)lEA~9!q|>a?##w9BUVl5z@T%US)9dXIiZ3PcrGNSo z@$`BqJ_R1Dp;p@2YK$V#!4W9Z^-|*HeE`7oIn}ZLh7K+GkU!0GF)iw(6 z*J)4=7v5L{hvX{(`2B#ikdF$5__FWYP%rw(nEz&31dDeCU^<+2A^iJ<@O2@) zB?J?qJ+g_g==&DXiyrLbsbi|NE^|zD)_*0=zefP?xJOBU$^V89uQ8LmPik48!}3Gt@4uw~2OggXi@d&NN!=R^v>#X={{8po z@w$&TxiaK&^GBoZ?=T*fCi&k|T$cH>v{@72PGKVNuydvScfI2z$voTPp^u&OA><^D=P+FfIbDgw4IuMBY z1SV#DEAQ?$fB2@N9yGSr1kWIbVjldwk2Y%EDpaM9Hg+W^)8%f0qI*6RO{$`;8-{wQ zL1626dXp)6CwZ;o=Jk=8Ab)NM(@XP)F$RJ~<2Xdt#fV|*lu2#LB`eBj<`RLeJt8Thcb?qY6n0Kztr{i3( zvuoU{#T0ST9$L3C_kV1gj&C90`z&#lz2yzj7SE24;Z?)uea+_u@=xl3s060Rcme08 zLG!hF`A$!4Q=)b$0pLab&hzOs+?F}Im7h1?J-^kHh9%o~%AX@r>s~_NTdLdaX;^5D~!{?Q_1=An8wcl{KwX2)CnS*No?ZEqhEh$M`%6UurdGj1t znfs;O+g^AAAXu;}zrt^`FGwhx__6_R{0aUYG51-S+9hCZ3V+tC)6jmzrVRVBZ~d{v zV2`=$=3|IJew%IwwAj`C>*r0;3g*6&u{meOR$N~mZ-3G3l;5EOdVY_woXcI?wq3@z zE&5NnCN94+`n^de=Jx>_G8cVNL5(>=ytNy7S^?yo!=kjA|3eRZ4n?4a|YO5 z@;MwW?80+Mki)rW^Xk(D^73a1;ERSVF3a)L+qwN|&rB~72766}!JBDNPKExeLO-9s z`e}4Km4D;7JGEy}%J-+`0NF{9-3vlFfB!sgbM<0T*0Udf@BR^HF-Fw=_x+$$z2gTc z^$R*W9AZw2M;Y4+zsQ28G>bemu3h)u~Z4HUu`;gwD&GJWfYVT+3kO_Gk zp0^%F%3JKVZE@v6M7MB|(LF8~gc$24v&my5w0}wl_?PvAb?jX|<$Y-HHt)lGA9@fG z?TXzZ00MX{5RVJhym)!#Ao<;M2mLH2I!BiM^VE4ox$jU zT`oIGBg!A4NCbFz6c069J&HX>J&y6OeeCpB0bE4!ui6qHa=mYwyTZGh0|25IK0-e2 zU4Os%(?0(Fm}V$K)F*7uBlN|$PaZm+tNp2#S@HQEp|w)ems+jiYhwMp*Se+wBPj>M ze|Pl$w^J-NpqPRt#s!~0AaxV1APiU4`I>e5UDV<+stA0(gLI@gkd*rFTT=ZHHdmr! zIHadWec^|x1arGVC78e3pc2f%@YwNW_kUi77U%{wbX$sd^vDHh<{0*7$M)_RYHK4f zczzmzc+24VW;(Af+GJ6iyz8ZX3Y+9hU-DYf;mzd(@<&zlu9xd6a`1Hv9L_tWUtMe= z{RTCU(d`da;h*@FYskTeogFQQ8b}C<_)uQRtLLR+J9KY2KbCa-M2#e5(UI-h^nVgA z?2xAMVDx%P75d2;k?%UYuFVV;2gUn z;XvX&tOr=86EL%n%C?e$to{}LJ@S`D)LO(~yzBRS-P$thDB1Il>A!?GHT!O6j|@p9HH&2qRov>RU3@zYi;fpbG(3bdFV^C>Kk@y0q2#- zi}+-Owu?D(WQ&*43T^q#%Y0tPws`yLPHH>*;-{0H^C{K^Yc@#did+$&73S({@ZiLj z%iMPb#3!G>T*Z??2NY9ZQhyKs4nZ=92KB4l)m8QE0PsV{86NY^Zu_pYt!!|EDQ^5N zcRAJ)O2iGkWxZbh7J&YYK-EGL-o|Um!UO29Lr$9=E%*v8snM!A`L|7SMwl@TqmSdc zUKqk(V8Aa!XtBR1ya^NT#TQRPqU1+LN@JR}MsQLI4w2IS67wdixPKQeJqf9uha#mh zHCrQTs5(s~^3K(PM)G&l*}LUVPFH+A39tW#B`@)xBRs7G=Ir40q~E)t@LL-jB(0hc z{p%QaTlCHS>@$4z>QdaQU*d*AxIg!BS?xi5y9Z8X5~bG{>sFcs?l}bMzjZ0&Ud$HC z;hNu(PcIiz?fExCe1FAqr`QZEn}mFLo>Eozw_(iD3>J~aL`&>bG5lo53_x|sCK3j3 zScqtKFw1E61n`368-6o#7nG`Hhkz4dUJWs|5*`g^IeAD=QBJ>yD^!@k$O zjFp_Cu*ESNcVfu+LzMUG!iT_*UqpGHNQ{YJ&0%_4t_IJ3Zaw1KVBk3v#Hfyfe%ORQ zn$J#He>(m!+ka5~@VwIKA2uz|Cx8AI(Yj;1uqv!9&XNVc^-5n6K)5W{%QU`C|U4JLhzj}9_lPA!+d$*!EN68_% z>@Mw5zdqP1^{@T5X{7X8XidD|1z0-=@gNW1PECOHCPHBg0^vUd0&C3t9mN<&J(|}B zd2^Er*mo@r4+??VXC`votd!Sx_sd_$(ia&U)X%X-22;fVsl`e5o*L$zt4dlLFEmJC z-mLNH-+x*r(w9h(xNoZ#@rG4%bIV844*oi3%*6IEB z=Bz`nuFS7v?@s7$9)K}0_i+&YjketnZ`ahL*MFoPUJVuuY7-v*L(RkI8tuka1CI|l zSHp`f!tNfvR$v`=Vt@YG56{U^rq)L=M*K)SYzHT8^oHq`IHO5=*-NL86+ zdw;uBFoe~&YjMV&tMM)ZWp11S2kXBxUKb7F#co3y>Ddy)D#{e@(KtaJZ6xKu5g$^aq4xI zK0B1C>bp#DY>K(7qTwU_hXI+R_@{n zZjeP0o$bW&hbXtbmsgXiFS&fom6(;d2Bea8Sv~QB7XF^9YJ&5*#7 zKlDEu$ZFDxkiDS94~^(JMV$?a9#sy@_W9?I6VoH%U)@)0x=X#7+^v?+O#4ec`+xZA z`OEWHmG88MxPv}~u796_U!y~3yJ#Gw=Z zJ-7w5{Sx*%4pM`EnB<~JXLiXr6cH3ZGYS*Q3Gsj z_C}PCF@mK?qxWaF1loh{rQHvOc8T~fA`hSR;4gYKo>w%^I`4Jp;%OGW+RAUp``D(` zfwF0JTNGYyHsca`$GkOGMgUYFe99C815{GCW&j^6eO| z*FKqV9V-4whe#M;2Qf$2$A4`{_9y>nNVvy%#C*^?WwGg<0S4nY_(O+>x9&`*vW~Kb z>Bf`&Yb=kQdSH#}rd$MTwAYdo+-<1B(Ibu4>aZSqbnzgmb>6YDHdZR;hivs)R!f=h z^ZC8z(`fkpcVZ$1pFZ@_Lvg>x4k8nub#&8+4CxqrJi^BDI6(bpbSR_u#piAM^?1#{ zUI+9nqu0hu-lal7_K&4^>jbi+jfzs+myi7c9)C7FJew$Ch$el_cZ1+Z0miGm+O798 zytPRue*87$dz0VkUUSTr7F;{sYsp*I;$ue1-ed=d86FGnWZfR^uAS`7pml(37u97m zQ2YavjrgcbpKT+=yThZ|{cX%avNywBf#bjo#4%xsza`M8^$3CI@aVVu+nC2>^gT2B z-hXx2wld)K2R{bCcJc`m5WmJBM~_Z}@>qK7xl}4{G2e0A3GmclMqT+61h?~tl<6Vw zQv=`!Dt5jO;^=O2XMJEr?TxFF9cl06*y0F3z+xSR*SQ(0l`abJy2vjos

      1E_0WW zYR7jzsEBTeSPbuOK1N(=zX3A%rH>pI9)Dy-UwJD${9>3x?+ z0iG8D70{O}P-L}TF55Xn9~Up&1xp&Riw#mncRO8GiID)CxBB|q8#QLVvEOWC2239U z0hqgAl(}z==99sQ%r?pi{pz*1t8ovn5kYRy(R=e4?jHI0nfbkW7XN@b@@{VGUVj>j z)x`$`C=aJ|{Uge$VSC^%$9nesI`PRK*-#6b^w2PL+Zkqi1oyf|&qjzhe zo~IYd~oH^mh*S*e1CTsB#}V36QBlG5vca9FS^9zjR)P1F+dzD?DI-* z@b_1LjxLWLRcy-QvVUpneJoJ^Yq4-Oj8Zb#(BP?kP!)YU)-g-P+ ztnTd{H2!@4`Tj0>bQ)>wZ64@-0ID-b2mCM+Q1Q9lG5Oefx#VUX9tL&%B7cI7?!qQu zb0DPN1pIY85OkOSj6f#=#oNv>0An>DD~mq7%}IIMsRpCK%6!8ELoGCn*jE<)a;9QZ z3;u1h;L#=}yHa0cD0gLNKKOR@ZPb4+N88o-UC>(!e|4wQ_KZxsfPc1fH&ww`+wHSm zKwFkvZMAK9b)!dVhxdbkuJdR^vG!$34@hXw_VwLIy_{7W?}zLsrs^f68m(1#QyAI0 zKl(|xrX3`&X4uZ7r++;&f9-k>taCY@*L6Bz$zO^2t9v&dN_^Rq`1`Y$zyH)Db~o8( zUw)l0KD+7s>ktbp*?$oUQ`)kNzC+rU4knoLpW2gG|Hls4?>$MK6fA2r@UFzzN3cSB z`-s-4;H8PNGkL(@2P9U#>ovSEYVSlPhuw)9*m!F1GbLf4$)9K)`xC7j$4BebD?s4; zm-z2a*?0)#!Q_AK6SP&C7G`xgse?VR8@}Nn?%LxHcJLLizkk!3UxsmaMtO+elU|wXYp<9TjwziBdn6L?)z1aMvpM?rFRO0`n@hZ`s=Hmjk5!Xj38)|jeqypqlKJ( zenhfVELP`P{D>G;n#G0u8q!woW-rvQgP8#Teie(3&>t0!?U`_P-1{EuRJuP-({B+A zN98@SDmm}?<9}A(P%X2NZnZJYaGRy}(Y_32M+4iuQTwQGEr{0iuZQ-A5A5_IEEDmhamvhic^ah}(PDYn40L1U^tHzop&Yzuu{So^yK(yH(YwK6dZOYWZ>N ziTg?GUaUqX(UZa5#XnNC2-^ z*1e>|%jer`W!oG7tM%*Xg!uvo(gP0U0<2G=&UeY>+;fN^yHR}G>86th02TN|h zAGu#TIF)f=)+!fN62{T}^ue2wyI!ppR?@;sDu1kxEm<#GvOb32J6s0x-h8)u*X9@S z+l)fK9Q4cMrQNs#5#2X?+`SV^Cr#<<`kjvv_j!XGZ{Ue#cGL-@fSYjw1;e4meJ@b| z7|T^hE_V9V-?1C_r1gQn;GPGz_NJ3k{+90e)aT-P@W90PN5lN1;gxJSS`}{nj!$b| zAAg(rY&d!qZUv7|&tkdJV!o380+nUe7woOFe$NXQi20q}XNB-sNrRQtSP4RnKL%kJ zjj&gZu#fYLSFlze@ljlo{+ z?s*AudnBMEZJ6j1ygPOikC2iQ8Ke0Xt`XQt=eZAFrBLEyEbo=}fY#cM`@Tkqd1X9O zOLlv|@Zo0IiB796+WUuxVBgA>*~v!5??Mfv%@|M4rf~LHO9hZSI|Gq}6#zaF$-X^YM5qV#Bu1 zw}R`-+I^ABx(1)RT-WZ9T-LP;m%|?N+lPy2w|(kb=Eg7U--!1$gdDUn6;||av@Z9< z19bPdcU$ro$IBsVoB_K1S8#VPx_>fS7x%SARdx9jnFfy?hB-G(qfeuCY2R5>d^ETc z?Xpoc7_j)USzSD8=l1s9?|-khI=jWIDAmrz@3p9t--A(+>#CPMs+A;2; zR|vhS;mOMyX0*gcTvIiBeue6#N?*B*e>bIlSchHNt$7AIjVYupvXn~44KFe!6*oIywOnEEa|2Mf476#NAU0`;2Z;XNar;1gfA{U_ z9qtE^U&qESC)Yt~?%iZCcfFfPemX`>LgbvRUpd#`Cuzz}W~&gvwqXyu2U7o;bPCqU=)0{SkGACpX**ON%p)@HxD=W!|IKO(6gaLp>mzQ)(S(oJ8JUUm@ObsEyoG0Gb+cRk&3}lORCrMt@1rB%i|CxZUEYfkx&j_ju-3p2+2D}3WA zO#iF>(;@*t;sKHfaM?o~fjN917n_w&!zgE%W%moVM|~pGAFtoz41NQetbFoCIZGmF z(tUq?xwHJyavDxy#eb`S>!JH^WBpA}CmNjwQ$Je6j?7Pw$n_FsRF?oZo{u0Ri4x+T zPqUqW8M(#lfuA?r&LX#uk=u*Ntv+7*kWmGCQ!lyblW6%YZ*h7IZi^r2vhXyLNaNCT z3OfbPgZ-49z3@dvT?ZW>J#^Y2j zmp}c;2I=hh;_c&}cgUUQX(vboD;tL|p<&^9x0YtZXB;6ahcJykSBu64NRax0?_;bDb$ht2l(FEvP8aHADB z4=V`t1MH|@4u2O$MYH*(`V{9Lc7wp3FW%l*e525CB{%#AYQp_p>!P7>%glTw$DMF5 z9EGz9F2P;}eq`*KmzUh%HP;ix`)EL3X9quN~zJWaKkMl3&J{O)5Gmqh+=2On;6v@o+^Y$lif+?lF=I!>jCm zn+Ng#^!Vo$KI+?1_OD|-#Wbudzy5m1`dS+BN9JOQyga^lskHDfqwuo<;WaaKST>(6 zY?j1i)@T+iS9s(2F$|+X9Q~P1uM2x3G1+z_zN*N_9k_;y(O(*KuksRsVfh6QyKc?< zHT2nOV}FQMZlD&{Wt3MNQXCrc`b1n-Fn5SJ1CV}*{Fy?=zgk0AJ0&`|Ee&e~7ol?=(`@X(8= z-)Y#@eEe;Gzo@R4KH!{^B^8GRD1@wgK*6_rC+F~Lo*;#!rf^wR;zM1DPyI@~+*XOY z8M<>*?GrxXz{z?ORPDLmG=#GLELF4KG??;VLLkkzNB6QkM7(_K_c1{JS3vIdu>98; zf`7a=dWV+Z@99N(-1}P_t@Uah=v>xxI-_&hTEUB7f$B266ifTIl|l2gl^f)68O z`8u7zy6muCuI6{`>K=@7*)T>Ktq%~`mVX_#mt7j8PGazZ81`-Ff!k$c{ChiDcnoc? z_kh-P?QQOmC(Y(h(0Ld4dbRcPxhAsb!$82$mh0Xgfqg|}%6O(+&S+W|Ry*x-L98kS zVT?MN(j$w{m{Xau1?PfDmzq=%&2=hDM>3MD^vL3ij9O`BQ4n4@#U0dJ6QNUAFn`W7 zB91NI6(*yC3(1L)xqyG_f~P`eMi8Qo-S|v1l4fNlWm+nkTc~?c=EP~}2!uFtWbtKQ z5|S4=*OoaUw3Xb@T(jKiLJ4k;Ext5m!6-9jMoO6$IsDV*Wy-lJSV@oF_?#AbF15)N zO-*5Q!L4v570?%)prt;f_?K4QUw_Bs;um)Dt~v*Q3K>vUT4pH>a&1b-awB!2GnFx& z@+>6t<&ZGI9Gh07d)d0kQAR9e6sOB`25lnTaqYS|%4ynjM{BJ39* z2^QB$WtC+qOb@A}mKpeiL*H?vD2&ckc09>MDU~ys8ZC@w*5+Bk6;nBU&XU2BaYV`1 z!t^9amMdp7M_EQ-ya=LLUb>Xn<4Mk-ahWR8G-r&JD%Y~el_E5iQW7Ef5hV*{Q|>s0 zVWWzSmr7?=!Ae1t$WopkPk(Yz!h{5>2aI2-Z4P}aQ-w9Oq?~cV%<&|%!j;&&TtT!U zloM!dkrQczR4_H_<4FcBN5bM?W}t(B!bwVAmStuX<7J^aKjL@Rn(#7DRmx1N3!y+8 z;RMzPZi`&F?1+8aP-a2Vl351IF5#3GWhqOUgC3qrV#*^*mMjw{Gk=UJ0Sb>QB)-!tb~&pr+Et9x=;oll#&r*vQm{I zJE)HPZsw-w1bz|kgE;t_KPUhfr-B+ri!4tC)mjUvZkAE#Ot3h~O!8B3pp-doHREZT zf|3O*hK1!S%~P08jeji7DL9Cn>LLXi62>!3;Hj}jIFeczV-BX#({L!1g|V$A=)J}k zl7N8)?P5xpXjPh>f`is*-LL{|N$zX`W85299MlJ)^Wr4!U>xH)C=IxVrUF_6I%7_; zXON7E!%nc9IDitIGZ^T`7?o13NJ?DBCA0+0^hGKU%Av9}4u3!DJIFZPx#5Hw(1cu? z!`e}nmJkc8r{WZp2YyuHBm+B+mP8d=fJSIxyt}-hR)JauN`84<;WmY8D^QJaxh`{R zs5KTWW-g8Ie^X8CcO9TXD|no4F%C9_n*fY#6l!6b0b z@zU9&3I{D*F;Ig!4!WWcDKRW1Buh(INOM^K7F10Exl}3X_QZlDFIc|p&!cifNNPkV1p$~&NCUP!PXLtb%Y;jcK zO2V>DxN}C!Oyvd?3a~j%2J?*(B|oxoB?V~a40L6uc@CBdqo6hvc}cB>#p}4jVWA`< z%b?{|_uuZlLBc=$TDL&Qe+&cZLJ45KL|5Xz934t<_*J zmD1(}EC*-Vk(*tV1=LVen}hAk%CsOh*QEf>%}S9Tx3^m&w1asjH?XvWdR~C>1Vca< zxw6pT^5Y7pIjH0XC~%f%x+Ga4g*1khpdN!}b${HUW=ol78hV*d)6C?;=4Gj|yMuxZ zE2}=La7RpOVGYSMqB13IrYsXC)jC7_C_QLz|L4Dai1^vU;u#FgTzy=0zj|0<1?WXo zFq$jSRbVw!smfJJjXtcCB@%e$gZ+<$i>Et|iH%B@mD(0%if(SO3{z%6(}B^EmjdRa z!+-8r42YKwJ`B$MHYFwQoDl1BnQ;piY-SBVmUvXMgoB|-icElN$DGL(sM;lCrLoGI z!w$rrXq^?#=@jG%C3BsZu;{{KuURhrd~i(B%7O|>4a>o9Bc(A86ujJ(B4uDl7UYPc zEhh%-R_J2|%SD<|Sab|YB^omY6X_8|e}A;M^Djr6d|K#eD`l$8Ey+tpGON)nhDBWK zJO|?ecejr~;1d3{=EZcbKOd=zJqcLNf@$b9ipnyD=~fvIBgYmx<1l#BJU4s+!)f{i_J`EalxCn#q%t*VqzhZBlELJfnUj!kOlyJB8%BwOW`rA= z8<^9m2Kz~6a84t5Ie#tV`iLH-|i=7@@83xD1FHeDv6h2ei_S-{{)In3ob*yN6bqRx&^pa7kK z79bSNGR`ty6r5(V6dbn+vr-?QfYC6KQ&bRy<0TlQKm!Ibr!cNcrjAa4QD;F#FxD_= z@Klk~6<`i(l><3$)1wm*U=V}#t6?g)u*`v)0$Q*%FrjJSB97k)P3b_WEq}Pk6tUW+ z4lMJGs)9myAndSX{7ckeV#I8p%I zn#~3gUVDMXffJ0e6zJ%8S(!q0;crlMWtN|Y1<|PnxiF~+%Am11^fFktQX;_A$q(y< z+suMW=S)F!o`J=Kq12pdCZ&N1$4Z^M)3C^iP?^*W=2wz2Qhy+?6lNPR043;@*@;+` zwkSCa0Rl4*(H6RhBrw-#2WBYzbQ%_*4Hl&2P7#-7z^N#x)Red!?0itJ<%w7*&`C=e z4pbJlbSbBWa49N*88ijAr(sd18GZrHpysJ4R4S+VHrNYP%P-I=M zv|xEEHQ43S<|i5>$~s|lp{S*nWrS*%YsyoSGdw$&o@k61X(%Y7Ou#?0lI05bjX7v4 zl5$??6MYd_Em&$x!_uOZCCMpM0&R0pRSeG$8}7TA1%Jl&GR1U8MV1Lv5_OuZObfwM zrs;|Lg)0?UfiQ0ptqdoI5UVu|Qd&x;%2Rz2Fpe^lgKe*14F$V|(VV6>L#wpR3U*NS zF`hWXgktA*wOGqob7=II-uQ#$`RIZ|fzFVD{i!s!7N#SHG5?%`KF6&25tM9UaG`{6 z?{X`taeoZ`rP?aTB=o``LJ4H2n8X&()570HX&EKjNLq@tOn(3+U1nMnSSB*Cm<18K zP`uQ5zRPK?>5ph7lY#Eb3Zrrgc6>p&NMSKmIRjP4vcn$l8>VzQkPhusLu<2av{29@ zqC6)G3|}xxLElMj%AlciW#u-(tkPbHm5N1K?wn!M3)8E?g!JemKXyH zt4kRNQ(l!)Z~?OfDTx3pUmc&`r^)Rp`%*_7b|1+LLahOdjut$V4pha0ILXi}S{iqH zMhxa20m^g6sit67sSJafbx}Ai9n4OrXT-U1vf!d%jB3zaxddg7=aw^Wxun_Y87VxX zUVqY}$Td$Xu%oDA8Y4`uMe5QYz{pbgNYH7hqp5+_EF%o&BB_~6^Wv~R$lVx0%a|}q;GnT_hf`9%h)6{?x#;sww1T8Vk4;#BaOhCY@NVtTd zTx6njDu-?Xx~a~yTw6_#Pe4ly)dVfnNTOk8Gewwpg#)YD9={J5r5J+&U|_-HMPBC8 za$zWi7W*BC+XGFj+?rAJp-q{|eZ5Rnos5`wEsQGccm z+5!wg!tF7X$%F6qwQ-M?CTEijf22Z(_D}gdK{-zpqIVOac}O3qIpq*Vj^-d`yD8iV3DOxmw#!Nm1#}| zKdNZ!2sE^D)PR}u`n25rarG{DEq{0;k?q+{@A?)E1{ZeEx^;3rXe;PXr&y3Q9N>Hi6bk#=@ zn(3029IRmN;A0W6u2hCDRh_4KW`sJ5P(1sm!BBD;o}Cav;*Ju{q)sjFspLlyT9B06 zEG>#OC9u$g*;Zhh6rw1s_`)5hd5hAguaKZ2V^o@^F2@i_La~`SO^+h9B%*&5(!kp4 z3JNA_foHib<0Y8%St-d;gz}O*LNe#W! zEoc-eOH)xEM`#X)fP_yfs0DwUuHdD0&Tso^%#m>$|PDn+7T2i0^g87Ealu-@_rz-JZxM`?PNW~D5GSo~dOSJ)G zRKOBZ6dCjl2cz$xepTGNsWxp6?n7Av$4EORxi%`#1W^Sh^aSMs7I~#D82tLMNpyzf z=LIKP5e}koSJ(+*3MPL+y`y;U{P^+<0xAZ=&#xz|<-3`ipHvvmw;6wR(t!O-jC7zVWU16( z`@=KP1aqFBnvb>|rUNi_!1jml!C@fk+&g2ebXi%Rnvc!F0LqxKKnW8L*&LQ5n1Aye z3=?Gz>V3lwInhT;4>|zva{^$LKmjJDO-ls^R?eBRT&Oaoxjt;>xM2pl_aF1TWE2dL zG^bz+BR1_>*m=0iElFVc&wV9%p!vM+I zF?rm`sXKOEYZ*8bsZ?tYc8|l86__oVTTG#vDK5(cTh~1rfQ(NkvsFf~u8#hNhs2>e zj$2Hn)7F1-l2Rp7m(i3Kr6tsYDpH(;5z9~70F5}G_|B3tmqiAHTq;-Sj98QB1uYEb zX*VZf#7|m(-l{&XgpB0S`vs^Zu=qMbP&)$ah(RaFj!)?RwDrI5H9*EJ%fSM0)MbSe zRv1yjss`qOEpvBRlfX=t^7{Jfs^|W?o6nZ^&&hx4=AAjMG=G%~DU<|dj1`h72euK# zvtGFIZwNQ1C*+-~#ONHp1}m(Tu8=7noe&z&;-x1iMDqe&aaoxw;ScvfpD8hHlw*9` z4tTqJsRe=TvqgB$UX32bB`j3z<@+hC5ffj2DiihuvHG{N?IO5jc7|Ax1(6zymm}AYl8${8E2p+|f*$!={hl%%Z@nE@diGm|{t8Q%MBR zGO%t8rtmMtX;`q5=A|SAcnDb!xO$IY73@8+k+7RIw0DvOkha4bj+BX zmiDkGCpWVYnHCJ{T)@1Li_CzHNsZDlI&%yJJ5lenm~>U zi{rJ$3%RtO$>B3VY?I@Y$z;sX60aDOu!b607MyECLEUhaA9gByfJ#O%0XFDB)WT{7 z>KFP43zZqogy4r&#yeE%1R$YDtd5pvYPb{{TOq@f*!~vNlm7;&eFrC zGu)Y!N*Sj3A%w%!!%83TEE#usX(-EO`eR6yrFFa@JhP4nJTqY=rUe%c^n!naor=_j zT*&G4#2xwnYwk;y+eor4_xuX9b(!_zSycKw)TT@+Wmd|bl&O-a%)wno_}M3KD;@sAJkzQfm8aqrD1DXWHfzaq77?Mc4hl*TYB9RX zpNbb8IYHIT4HaMXR>o9SwzRZHNi80CW$Ar*QF(^o6i*J$FN3)alwXMUzY7!k^nUN) zRjJevcqCnzqm8hcsT?ZT6sow`pD#qoU%_Ht{+yozqt$nmsa;t36rn~WbX-SanU;d; z^=T$gL?ee-1Kz%=8FUbPXn`0+Q-wProf0RaQL-(<1z!*cxnhlQDF{Y8a=0==_UHAz zz8>{E53mAgx0m`N0!M$3rRRB{4UBf-8|80AtYF~)8dDHsdN^E+iqgBt!ii{j%?+X` zL{;>WzO>o8q$w3HX!eHj6Vb@77$F$-0Fy1VaMgvSO%TxYj`wJGwrLb84MYED)h6pL zqPbGxjWaY5qe=x2r7>L~K)YINxjUDFEU!OaZu_b0DV@S468nlcDDO1x%Kjnz_WM(bZ(V6mvm_S&UW z(^OzXyQU2Sx>`Bq6i=jLV?y*<_Qng3Lv#FTG_GaJH&3@C@Wkf4VcambHy=>XgnxeZ+q3g0?2;MC0fTS1D`xd zUG^qFI3>jjmx0kLat80gwpq8@iKC2|O?e%^2Z~UC0gQhN&q>hC7Ok-5RaW@kvc~*0 z6n}a4>gOlyXKVN_2=PkLPC;hifxAM*8gq$Mev>=PpPr#HJV&RBuu@xR6)i$nGV^Mj z@L})tmK9R_nmP*16!Q)M^!;*49HE zCat7kPfGTwyW!HuquGvVbTG6NT$X60t5g|}yyg8{&`wFwyQ(}DA~3-VS{R^X=BZ6h zq7wXr?|@=vBJxzF3MG51l{dE77_A9fS9H85qiBEB_oDf}VnQp<>3eLAhGAS*L>k40 z5PYIl2pF#Z`yyK?;fD_BdX#p9vQOO&yCxFOMb1r%mGVmoS|8~cqA+HJwN9DufTBlO=x8C7iBV}Qgcme3n4NXp zOZR_0v|^(9s){D#HOq{Mhsw4yo~yBec9T6BMfbG*%&j+-@Q7f7D>O}1Q3R8cF4_i4 zMTt=(wdD_3griL+S;u-ZB2-b_#uR@Y zqGKJR&5BWKG0N^IWQg)~L@I`PdFY(2R1|sq8iBk06p2P%z3t&G<*1M81QFOop){WfTc+IeDPcT8>ar z&^DoTIwA&vDc+9|wrWcWaI(NC)|P+P*IAiQMNs8m(pqV}u+PZ*K@5W>Y ziRQNzbXBCpTa;o_6v`!+T%y2LB>$L`buX{eub(bwzl3qVEIo;(PYMMc%E5ml&_xLg zTdBAeGFAlR#RSnKvh+~>j<)baU@95n$@h7i7dkGngHYwg7I1)Shgbc*xG@zL_}@q%dMyMKwO~T(oVMM3oo`mG6M=;gegJROaZ*O6O`B)%=J_7-!)3n*NZJjFzKganDo{ zfg6!s)(nK$2m{ZeuPE3D?*m#5i*4qeIix(p!jjo7zC})3aIzc;lEKCUKSA&qmqU(5Q z^b9+mBUdM;L*@Orv7F~ZpO2G~wMe*d(s=rk>`zQ5MZ{z!Xa&bHE1F?f5dGXNI5yM`dm`*jSI9Em0h0`WfOGSUNy%6w%75wf~5A;eo zTj2gvj(1g=NZDs2y!EBhhowGS=l5{AD1FOslZO`N;p%yBbuGGTSwgXv3WrE$I6nae zsceRtaJ054NRtZlg$j8HPOG`HKLrH~512WkIt2w7_X;mVdMRbQd&W_9 zHI66+jloVaBD5_`XGOc$EPNiyAkDI(9c)%c1S%(>U^OBy+90cotLT%;=L8#1+hkdi zPM&~*GZ_()0*7h@kFZ!!!V1=%=6#tyMJvz>hvcIPP)vV}!6q>uB^;Y7ouLB0C!hcy z3Z9FOI>-bMJs@IrHbw-^QbA{(qB|yf<=z_OZS`=VXg;L6su3kf@4_QatG+H*lj#@w zMD}hz9gRQqC%OGLcXP1)BKQ2w`$zufdLPuTzM*iw$V3$-G4A0J6`=$Cp+eP9`Duy$ z<4Kz1A2)x^0S|yv3I{l1Ict$E_bJqzV@f7PE>27A&C6eZ{prP%Za(Y|NZq7 zw8#pTjJT45b^~!ZE*u^W3>gbmwMFAX4UgGJHWPo14Efvf__1gB_93)0SBe`ACF!CM z67D;#_b_nPDl8>T)k#QbMD@8ww6iacCXeB@1X_z4EZW+fhJ@EuDv^UVGWn8HrMYCd z&LSI1fly9DA}B{CPDN1KhC~&IIMtU`B|6SBXD1<1W#L6tZELovSnYK5RN%>Qp_9pv z=(B&k?f!gGYFJ!8=6B8=!L&T3#*BEVq*`d%n#{&3JY8FS!Rajf#HRg)MH(MOmMZb6 zic!!b2+(K>C-sV*y;Y25^1q{FLPh+W6v9D8nLV8A6T9$~BBiHSP%^NtIddaq(T>CJ zR`rOz`TXtqYJpfULcg(|!Q+C^Ty-%_N5Ox+fD+Ok!L(Gc)Y&uR4K%{3c)(K%h@`y3 zV6mo1k%X=}L{mMbsqT@-T~!qx6M{?;{2#?&kpktStp@EZ6)QP0o1H2>vbeLR!lPnP zh!Ctuh9%u5x}}uk!5cC%2vK4AeSb9Ws;Kao5bgITI22ks<13;=%bjEi+TUoncgcU| z9$9=W({Z_+(W#$DAh?S)<7`}n#$%D6sbTrM_!MQyNv;X|P zoiKSh&gIY3wZ~VeG+Bmz@8It^+NEPcQtek;Pir=rR=mf7uxUNJD$QL!jb2;h04P}; z2Vak8?~3%461-~oz;Kl~C7aNS_s2r(9>qs`LZielOflN|YbXT_!VxO=$dY4H6;FQg zDG1$JdZZ^b(hP`peaQ5E3<^`2D1)s|36VUPtj1Fia;JRy&6jO10vUhBY5V?SxAS`w z5&pwE(2fbH0F|@x!n%-Zh>se59$<9B-oM!G{*-jvOYdr=T_dqp%J^szIdTNxEV`30 zawmQM%>e-KkE((vL!T@$>~$$p)AFIpC}1}I5&AS4U zm{qd+l6;I@Q#-Y4iGruh@Ror|TEe6bQaiu5Dkwg=ZvQg{)YVlP=l1CAZ-=3l ze>d~R7+Bp?{jivoy0~oOVsx1sYS^Y;h7Yr4dvy5Cq&8dlO^4s?;IDWS-{)I=f9v?Z z-QkM|yuO}H=YxN%FrSY8+@?P*wM+|3-V?Y~0%5+dimt|)%b~K*N!{ue$>OXX^ zx=trofL~0}AudPb#dfozx2L9)*L3pUt)ZR+>X#1cXF7ki!Qx+wfWi6i?wwyv@-B~W z==?VXHib2vup1Kp+(e?;aM1WNo`;=xP2DYw^X!NDbPj#g%*yoBT6Mf@Z@_)CdAS-~ zmQT2cI`-94?hg5QIr#uVC0z{Z&mZU?K76y7Q5o3bD@5qy^kw+tWP$EI9hKSew@wzF zeNoEwyHbBXHg9pqO(P5^NC3##O>^90ay>EefwNjnY4<@1nQ^|AwOZ(R=b?$+~_u;` z{M%rDQ3n6jz9ah%OOV(wcuxS_5ItT2`lq2Ip(Y7fZ-#ci%FjCq4HrGt}k%y=jmv^9u3T zH|2krU5dVd1?~PEx{G!O!BHJL+PIgq^@15Em?}}H>V&;V{nAaLAvl*9SJrv04JE3t z&a;C5c#in=IH4&DueiyDD`r?#TAAvMmZ5qf*gZ<1ty~t;7T3^d)15bjK{G;UC4>J% znoJ7~kyNhdv(1J?*I3`)y`Hz{7&+aMHAH^{CA1~*0Mz6Yl+~zw-a#QXwk2VO*1UT4 zdhl%H%r@$#s=c>X-a_A!w1xiT#+e;-GCG6Llj+BLIr)6xsaKcWhT9shwTx}#R{kH$ zbKBVIqNI=46NF2LUhMj!TaY&-Y@t41AKyl7_3Ger8GX2bBE6in#&SP)dwH|Gyy<@~ zzlFtZmu>TDKMN23SmM5Fuh?b=O;WYRtl_L-+sJRX zM508<>mln=m^2QcLUO!WXvbpTTxz|;@G)CVy20Zj7%OmhI! z9Kf^>z_bT2?Ey^p08DoP(;dX*55Rxq2Qc{oOz{9raR5{7#q+urfb@hkLnxPez+ z2kc+r?)2^(%q zVm6 zbk8{?bkjP|-n=Av6Fl0NcCe0a?H}u2kC@Sp&7gnk`}HD~Pun zN6%WeEl{4MHT_o3;LVrw_Uw-#p%wDk?Ndr$-F*9`)8JWqbPxu=me0%JWi;N0vDtdJ z0DRTBTe0xqw@>9W&a8igtqPsqB4~ALDP;9?d1ozw zXuqB2+GwUJ0_(}{l7eq)bW*9yyGhJ=2L0QXZ0_c?grGH=yc$bI)0uM2tEi*l+$x^x zw^xt4O?HgVM8^ef=j6I1&x#gBWgj?Ic6o?wnVcxT#1x{`(S@k8^o1Lm;bZb1rD%_k z9heG*>KfK+b2fiWYLx}I*)qeu<6QI#&b5{`aBoC#1`eGJl_isT6)8$pS+C$qaIU1M z+QgD2?uBj_`O?4ED6jejuewMUGk2QH%AE2-8O~VARYhTJui!o~7cnFXdNq20v#wHw zd2d;WjK_yHdodVpl>IR?qjIieZ1MRWzbV6>xz?mu3}uq3W!Z z?-krf$s}i*bLL87L3tT?(k27VjB(yPM0Rcy%P1csb5uW+sw`@qs}o+-81CO20?Gc?k2IV2kcYd; zkDOfkeHni!xI1Qgxiv;h0gzQn6A^Uh!R#6&=yUO>vax_-`Ca_ZkXWogcMjk3;p_7^ z!WUM9T48EPHw_qPi7RMO+SB>0Zm98g?=NW>11qxzuA#b*mJmS zZT@AFJZQgrf5U8s9=;gO!iNvj@`1iA4&M|l_3cfh+FknTvMptXj7?TN$kX6v=>F?Dok%PA{FVUyb_&GrdNi*H zFlX?22Z2`Q9kK9ebC!gr=xEznvvKu)vTf6?C^Yj)(@{9zH^=a1#rAwMct)3=b*n)J zu?sMtaGA$)S;~sY`P=jMW9BOGU7l^fZ61GI*V10HX=-j(yWC?z%=V4VR%iZevs?l; zr1e0p&~%lT>(CC$U0>Ghm)@ki!0{G_-R#O^LtowneO2Zmhj|!w`fb=}J6zpGW;q8t zq$#k;V*cm^rgsroHo|Nkrv0&)-@ziCyaS%T-(8)&b4^d)n@-(xhF904A*~>RJJElu zLfZhkqibzb>P^jU61oBTW@7224b;hMnoR@!FzoK%mApN0>2fiflWrURyF41^me4)G z<@#|kSMv73{fW4-U7sKD5;`%n#{<7r`W`ADt{1Z*yuRU>R&zcUg>9*Opf3uQdni7p+Ufq?t7BG>SK-fL40E{IkJ|Nj z#2x}K;cEDKl;;<&G=D~S2Fj(_Uc0~X&k`V zLyOvrW>&7JlT>E2r9pbUcd}3Z9y;s!wa372h3x}+WP@{k*x*b{m`y15A6|cl>8wm2 z4fiX-dk8Fh#B}nA-EC9m9@v{T2#*DNBXJ+(Bfr`C;Ws;X4naF~FLbtA z872nj9qMyJeMhJ(9=Ku9${2sF-*2B>ZoPWN?lrjl*m8M?qk9eFCFvyKPGJSNBnl z1sip(*#<3ylU9~ooX^_EYMhYw_~3UVQwZfX%RFjpSYgR(VU!nMN2h<_SM(w?upGT* zCNeG(Pt1F7gA%3sN_7xD?*&wZDCk?dPg3ZhxG=_Rk5kl!POyGJi_{2CqK{Ez%A8kH z3b_bjJ=2MmUO-*W!c~zf^IXcDdDRurmOG`D;;I+WtSrm5Chr3C$#Cr`|BiFQ=E7O* z3Di@*Y+Yh-vX&GD-mQOP+6s%tb@sU4TN3v&;Efq4@jq%hscU4xF)oknCpEAda*lWs zZA4@#I>wy#DpXsf??Wao;6b}0laoOg+H+_t*V3{|wF!&p1=R9L*+(sBRI`nWdMTS# zQk1kSvA}x)^}eVQWuofSiYM=-W{EmvQbuZJj{&9nT*C1jEvJ8C96?%Bl2Em9D&m!n zlgX9PrZOo_^};#t@iXKkp&%?*`Y4$qNT*DRHfu%{t1^_hUyG_$&fzGTN(Wgy6Ow8S zr9=t$D8Z69DF~RIK4j7wnL^7=vNtvJQke*hYNkcX?dJ;X1=Mg_6a<5ml!9tb)pDVD zgl!d0l-SRcLS26qZXGS;GQJosb9K^Xmjnx`xO^0-EzuYZy;x{WSSB)Mg)^2@J~Snd zl37hL!DuQ9!L5Q=20K{f-E%GR(q#V;SB`bms z#zGHppFp@qZ)8d3s3D-Lr8*cc6$TBHRdhx8SUkp>hj9WqYL{w20vmsR(BP=F1xqkv zaKDsCU-MpBlT|;USwd3^UT`>|!^@mp%4y9UoDUIHtbND~@HwO>?doAR z;CPnGP2f~|O*3*y`T^CM76C(LNOT1_j8#XKm4o7-%(O>2c&0%2r~);PckH54DKmlS zLBeQN#f~zF)@Nujgpg8GN1>&$3>p}!m{QKVqqG6p1;(xS&P#u*rH9#Mcy`1g0x_MA z$H>HsGgdpw!X2FEjA|mmB1gP{3O#>R&!G~#Lb({wz2QpYi8FJM%x%#EBe@Tm0ZK0_ z7Cjz88Y|&$#V?e$}C`Pv`d@{bCbJ#3@Er`EP41hF^L3Op5X~v#}y_mus&o4 z1=Um0R#e(6m}qTrRKG)HCE;RCdKf~LYKWwu2U!ok@|NxE2%()lzmR4pRQ z>fppEhA7ktQ)EbhP{Q>g6K)!-Uc+7U6w2|c3k%-i#srm$KHUo_;%4hCf`ouK7pc|( zm&ZZ^AAcyt7`--uTcIiMbV8kP?K&+CfSe-L4Pc)3kBMk_LuDMB)((e+@AdjXBU zqK|pu4P0Fd#piKaQ*nAkEAF`Y=M+3c&{3!e6o1EKNQSOx;SKWWgetNRnL#k_yn?}Z zIO$t<~U#XPSEP%{QF=MlrGc2%C_p9;l9VJ5<4oIPC2-?I(Vh1x6(`% zd|tdc>r-XN1p;v1yfKmURM1AHMx&(j@IRpkDuV4kWCnp#&^$_^F)Er6z5!zSqH(~e zTs&Ye|l8wW#!>aYYZc&8A1Vg@CZ6ww86r+JI;r^ zOJ?92529dxD8rW_L;@2H6I3AHbp~NjjEr{FVV6Nf0#_2Zim|Y4qe9O@z{+?ppq8qp za+j(^0w#aRZ>e{J#>}jQM-sVau-8JPO$!w(*JP27o9@V3(6o&~FG(gxa^DJ9#X~aw zf84xHHp~kQ`M`;5*Ce_0%N^!J64sd_AB@{Z(hI9Df-)@N(<6Ne*Ijv~8 z*;`3_UBQJnOm+L zyuV@aqGRxK#i0BB%OalL(v!Y5$;kVzFSN8=y%amI7`qvsuY(aLaZ&xZi)* zxW8`VZl#9%6s9A}y?(!BaDRd9<$Y(LMzaNg{#{xHbN!{u=yg4v)HXkLml5wS@nIY; zzsyF<_q-O_Dz>G_W+k#&iTr&Fd6mg)7y0bd_DGS0dL1cQG#YE9GZetE&Wo168`U0UYBkIUaH;baHC>TQQI z^)KbF?pum|)%{#bZD#Xn30M2;p6p(>>O)Wu?HbNMXv8cw6yXYx<$W1E4%}w-|A$|N@E-yEB(yxDVMRdrW zQv&2az9#hgpU=SaGEJ^pbGxZE{@0A`|6-k~!e}gv^>wLeon4;})^NDr0JH*up_uQ(>^KsqpvvlwKe? z^m-wu*|`9~9R_Ub;2$l<+cn17=h5}w24&n<&%gkI&$aZ{2Jy>andpDwwuh(uF|=v1 z4p$jwsLOArl(;nu3*ed#ts%5#h1SF`tF#(}KVH81+u*0el+JEX&Ob}j5mefCW|JS@ z{`Bm{>z`IiW1V)NM6`bGQsF;gW{nkb%7 diff --git a/latest/overview.html b/latest/overview.html index 90fa00856d..988469d196 100644 --- a/latest/overview.html +++ b/latest/overview.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@

    • Control generated text using logits processor
    • Generate text with multiple LoRA adapters
    • Speculative Decoding
      • +
    • Runtime Configuration Examples
      • +
    • Sampling Techniques Showcase
    • Run LLM-API with pytorch backend on Slurm
    • Run trtllm-bench with pytorch backend on Slurm
    • Run trtllm-serve with pytorch backend on Slurm
      • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -690,9 +694,9 @@ Certain limitations might apply. Refer to the
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/performance/perf-analysis.html b/latest/performance/perf-analysis.html index 997b3d55b2..5925934ede 100644 --- a/latest/performance/perf-analysis.html +++ b/latest/performance/perf-analysis.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -749,9 +753,9 @@ python3 benchmarks/cpp/prepare_dataset.py
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/performance/perf-benchmarking.html b/latest/performance/perf-benchmarking.html index 0cb2dfb1cd..3632beae18 100644 --- a/latest/performance/perf-benchmarking.html +++ b/latest/performance/perf-benchmarking.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -1599,9 +1603,9 @@ The choices are specified with a YAML file like the following example (
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/performance/perf-overview.html b/latest/performance/perf-overview.html index 6549ac8400..b3bfc2d727 100644 --- a/latest/performance/perf-overview.html +++ b/latest/performance/perf-overview.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -1213,7 +1217,7 @@ a model name (HuggingFace reference or path to a local model), a llm_options.yml

    cuda_graph_config:
-  padding_enabled: true
+  enable_padding: true
   batch_sizes:
     - 1
     - 2
@@ -1452,9 +1456,9 @@ using the --kv_cach
         
    
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    
   
 
    
       
diff --git a/latest/performance/performance-tuning-guide/benchmarking-default-performance.html b/latest/performance/performance-tuning-guide/benchmarking-default-performance.html
index 0aaf303efc..5aebcf385c 100644
--- a/latest/performance/performance-tuning-guide/benchmarking-default-performance.html
+++ b/latest/performance/performance-tuning-guide/benchmarking-default-performance.html
@@ -58,7 +58,7 @@
     
@@ -70,7 +70,7 @@
 
   
   
-  
+  
 
 
   
@@ -349,6 +349,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    • 
 
  • Run LLM-API with pytorch backend on Slurm
    • 
 
  • Run trtllm-bench with pytorch backend on Slurm
    • 
 
  • Run trtllm-serve with pytorch backend on Slurm
    • 
@@ -384,6 +386,8 @@
 
 
    Command-Line Reference
    
 
@@ -900,9 +904,9 @@ P99: 1.00
         
    
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    
   
 
    
       
diff --git a/latest/performance/performance-tuning-guide/deciding-model-sharding-strategy.html b/latest/performance/performance-tuning-guide/deciding-model-sharding-strategy.html
index 4ee3e0f1ca..a77a1e1ceb 100644
--- a/latest/performance/performance-tuning-guide/deciding-model-sharding-strategy.html
+++ b/latest/performance/performance-tuning-guide/deciding-model-sharding-strategy.html
@@ -58,7 +58,7 @@
     
@@ -70,7 +70,7 @@
 
   
   
-  
+  
 
 
   
@@ -349,6 +349,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    • 
 
  • Run LLM-API with pytorch backend on Slurm
    • 
 
  • Run trtllm-bench with pytorch backend on Slurm
    • 
 
  • Run trtllm-serve with pytorch backend on Slurm
    • 
@@ -384,6 +386,8 @@
 
 
    Command-Line Reference
    
 
@@ -679,9 +683,9 @@
         
    
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    
   
 
    
       
diff --git a/latest/performance/performance-tuning-guide/fp8-quantization.html b/latest/performance/performance-tuning-guide/fp8-quantization.html
index c6c6043c88..3192353bd8 100644
--- a/latest/performance/performance-tuning-guide/fp8-quantization.html
+++ b/latest/performance/performance-tuning-guide/fp8-quantization.html
@@ -58,7 +58,7 @@
     
@@ -70,7 +70,7 @@
 
   
   
-  
+  
 
 
   
@@ -349,6 +349,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    • 
 
  • Run LLM-API with pytorch backend on Slurm
    • 
 
  • Run trtllm-bench with pytorch backend on Slurm
    • 
 
  • Run trtllm-serve with pytorch backend on Slurm
    • 
@@ -384,6 +386,8 @@
 
 
    Command-Line Reference
    
 
@@ -1011,9 +1015,9 @@ accuracy loss is unacceptable.
    
         
    
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    
   
 
    
       
diff --git a/latest/performance/performance-tuning-guide/index.html b/latest/performance/performance-tuning-guide/index.html
index 728ac4026a..d78bd64381 100644
--- a/latest/performance/performance-tuning-guide/index.html
+++ b/latest/performance/performance-tuning-guide/index.html
@@ -58,7 +58,7 @@
     
@@ -70,7 +70,7 @@
 
   
   
-  
+  
 
 
   
@@ -349,6 +349,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    • 
 
  • Run LLM-API with pytorch backend on Slurm
    • 
 
  • Run trtllm-bench with pytorch backend on Slurm
    • 
 
  • Run trtllm-serve with pytorch backend on Slurm
    • 
@@ -384,6 +386,8 @@
 
 
    Command-Line Reference
    
 
@@ -670,9 +674,9 @@
         
    
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    
   
 
    
       
diff --git a/latest/performance/performance-tuning-guide/tuning-max-batch-size-and-max-num-tokens.html b/latest/performance/performance-tuning-guide/tuning-max-batch-size-and-max-num-tokens.html
index 7933088a20..94ef25f28a 100644
--- a/latest/performance/performance-tuning-guide/tuning-max-batch-size-and-max-num-tokens.html
+++ b/latest/performance/performance-tuning-guide/tuning-max-batch-size-and-max-num-tokens.html
@@ -58,7 +58,7 @@
     
@@ -70,7 +70,7 @@
 
   
   
-  
+  
 
 
   
@@ -349,6 +349,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    • 
 
  • Run LLM-API with pytorch backend on Slurm
    • 
 
  • Run trtllm-bench with pytorch backend on Slurm
    • 
 
  • Run trtllm-serve with pytorch backend on Slurm
    • 
@@ -384,6 +386,8 @@
 
 
    Command-Line Reference
    
 
@@ -861,9 +865,9 @@
         
    
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    
   
 
    
       
diff --git a/latest/performance/performance-tuning-guide/useful-build-time-flags.html b/latest/performance/performance-tuning-guide/useful-build-time-flags.html
index 1847597ba0..ffb0f47bd8 100644
--- a/latest/performance/performance-tuning-guide/useful-build-time-flags.html
+++ b/latest/performance/performance-tuning-guide/useful-build-time-flags.html
@@ -58,7 +58,7 @@
     
@@ -70,7 +70,7 @@
 
   
   
-  
+  
 
 
   
@@ -349,6 +349,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    • 
 
  • Run LLM-API with pytorch backend on Slurm
    • 
 
  • Run trtllm-bench with pytorch backend on Slurm
    • 
 
  • Run trtllm-serve with pytorch backend on Slurm
    • 
@@ -384,6 +386,8 @@
 
 
    Command-Line Reference
    
 
@@ -924,9 +928,9 @@ This can be enabled via the LLM-API as such
    
         
    
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    
   
 
    
       
diff --git a/latest/performance/performance-tuning-guide/useful-runtime-flags.html b/latest/performance/performance-tuning-guide/useful-runtime-flags.html
index f3c11c4ca7..fe2eb42645 100644
--- a/latest/performance/performance-tuning-guide/useful-runtime-flags.html
+++ b/latest/performance/performance-tuning-guide/useful-runtime-flags.html
@@ -58,7 +58,7 @@
     
@@ -70,7 +70,7 @@
 
   
   
-  
+  
 
 
   
@@ -349,6 +349,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    • 
 
  • Run LLM-API with pytorch backend on Slurm
    • 
 
  • Run trtllm-bench with pytorch backend on Slurm
    • 
 
  • Run trtllm-serve with pytorch backend on Slurm
    • 
@@ -384,6 +386,8 @@
 
 
    Command-Line Reference
    
 
@@ -847,9 +851,9 @@ via KVCacheConfig
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    diff --git a/latest/py-modindex.html b/latest/py-modindex.html index 0d79496445..a1dc82d818 100644 --- a/latest/py-modindex.html +++ b/latest/py-modindex.html @@ -57,7 +57,7 @@ @@ -68,7 +68,7 @@ - + @@ -345,6 +345,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -380,6 +382,8 @@

    Command-Line Reference

    @@ -666,9 +670,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/python-api/tensorrt_llm.functional.html b/latest/python-api/tensorrt_llm.functional.html index 7d1e51a8d2..6f44a6c99a 100644 --- a/latest/python-api/tensorrt_llm.functional.html +++ b/latest/python-api/tensorrt_llm.functional.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -1148,6 +1152,11 @@ self.max = [dim 0 max, dim 1 max]

    )[source]#
    +
    +
    +static create_sinusoidal_positions_long_rope_for_attention_plugin(num_pos: int, dim: int, theta: float, original_max_pos: int, short_factor: ~typing.List[float], long_factor: ~typing.List[float], dtype=<class 'numpy.float32'>)[source]#
    +
    +
    static create_sinusoidal_positions_yarn( @@ -6742,6 +6751,7 @@ function creates a constant tensor.

  • create_sinusoidal_positions_for_attention_plugin()
  • create_sinusoidal_positions_for_cogvlm_attention_plugin()
  • create_sinusoidal_positions_long_rope()
    • +
  • create_sinusoidal_positions_long_rope_for_attention_plugin()
  • create_sinusoidal_positions_yarn()
  • rotate_every_two()
  • rotate_half()
    • @@ -7030,9 +7040,9 @@ function creates a constant tensor.

    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/python-api/tensorrt_llm.layers.html b/latest/python-api/tensorrt_llm.layers.html index a3a0e89dee..8cc8bcebe2 100644 --- a/latest/python-api/tensorrt_llm.layers.html +++ b/latest/python-api/tensorrt_llm.layers.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -2593,9 +2597,9 @@ the number of tokens used for each task, should be equal to prompt_embedding_tab
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/python-api/tensorrt_llm.models.html b/latest/python-api/tensorrt_llm.models.html index 0555e00c26..c4b792f327 100644 --- a/latest/python-api/tensorrt_llm.models.html +++ b/latest/python-api/tensorrt_llm.models.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -3636,9 +3640,9 @@ ranges of the dimensions of when using TRT dynamic shapes.

    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/python-api/tensorrt_llm.plugin.html b/latest/python-api/tensorrt_llm.plugin.html index 22e4aff957..4fbcde6c64 100644 --- a/latest/python-api/tensorrt_llm.plugin.html +++ b/latest/python-api/tensorrt_llm.plugin.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -683,9 +687,9 @@ migrated to the centralized building script tensorrt_llm/commands/build.py
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/python-api/tensorrt_llm.quantization.html b/latest/python-api/tensorrt_llm.quantization.html index b9c8e15c87..d860ac0a42 100644 --- a/latest/python-api/tensorrt_llm.quantization.html +++ b/latest/python-api/tensorrt_llm.quantization.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -721,9 +725,9 @@ the quantized model as TRT-LLM checkpoint

    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/python-api/tensorrt_llm.runtime.html b/latest/python-api/tensorrt_llm.runtime.html index 05a8a5e0f1..a37b58ca7c 100644 --- a/latest/python-api/tensorrt_llm.runtime.html +++ b/latest/python-api/tensorrt_llm.runtime.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -3263,9 +3267,9 @@ For example, word_dict[2] = [” I am happy”, “ I am sad”].

    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/quick-start-guide.html b/latest/quick-start-guide.html index 6af430db02..eb7e9b1b25 100644 --- a/latest/quick-start-guide.html +++ b/latest/quick-start-guide.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -512,34 +516,39 @@

    LLM API#

    The LLM API is a Python API designed to facilitate setup and inference with TensorRT-LLM directly within Python. It enables model optimization by simply specifying a HuggingFace repository name or a model checkpoint. The LLM API streamlines the process by managing checkpoint conversion, engine building, engine loading, and model inference, all through a single Python object.

    Here is a simple example to show how to use the LLM API with TinyLlama.

    -
     1from tensorrt_llm import SamplingParams
- 2from tensorrt_llm._tensorrt_engine import LLM
+
     1from tensorrt_llm import LLM, SamplingParams
+ 2
  3
- 4
- 5def main():
- 6
- 7    prompts = [
- 8        "Hello, my name is",
- 9        "The capital of France is",
-10        "The future of AI is",
-11    ]
-12    sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
-13
-14    # Alternatively, use "nvidia/Llama-3.1-8B-Instruct-FP8" to enable FP8 inference.
-15    llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+ 4def main():
+ 5
+ 6    # Model could accept HF model name, a path to local HF model,
+ 7    # or TensorRT Model Optimizer's quantized checkpoints like nvidia/Llama-3.1-8B-Instruct-FP8 on HF.
+ 8    llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+ 9
+10    # Sample prompts.
+11    prompts = [
+12        "Hello, my name is",
+13        "The capital of France is",
+14        "The future of AI is",
+15    ]
 16
-17    outputs = llm.generate(prompts, sampling_params)
-18
-19    # Print the outputs.
-20    for output in outputs:
-21        prompt = output.prompt
-22        generated_text = output.outputs[0].text
-23        print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+17    # Create a sampling params.
+18    sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
+19
+20    for output in llm.generate(prompts, sampling_params):
+21        print(
+22            f"Prompt: {output.prompt!r}, Generated text: {output.outputs[0].text!r}"
+23        )
 24
-25
-26# The entry point of the program need to be protected for spawning processes.
-27if __name__ == '__main__':
-28    main()
+25    # Got output like
+26    # Prompt: 'Hello, my name is', Generated text: '\n\nJane Smith. I am a student pursuing my degree in Computer Science at [university]. I enjoy learning new things, especially technology and programming'
+27    # Prompt: 'The president of the United States is', Generated text: 'likely to nominate a new Supreme Court justice to fill the seat vacated by the death of Antonin Scalia. The Senate should vote to confirm the'
+28    # Prompt: 'The capital of France is', Generated text: 'Paris.'
+29    # Prompt: 'The future of AI is', Generated text: 'an exciting time for us. We are constantly researching, developing, and improving our platform to create the most advanced and efficient model available. We are'
+30
+31
+32if __name__ == '__main__':
+33    main()
 
    
 
    
 
    You can also directly load TensorRT Model Optimizer’s quantized checkpoints on Hugging Face in the LLM constructor.
@@ -643,7 +652,7 @@ The model definition is a minimal example that shows some of the optimizations a
 
    Container image tags
    
 
    In the example shell commands, x.y.z corresponds to the TensorRT-LLM container
 version to use. If omitted, IMAGE_TAG will default to tensorrt_llm.__version__
-(e.g., this documentation was generated from the 1.0.0rc3 source tree).
+(e.g., this documentation was generated from the 1.0.0rc4 source tree).
 If this does not work, e.g., because a container for the version you are
 currently working with has not been released yet, you can try using a
 container published for a previous
@@ -853,9 +862,9 @@ container published for a previous
         
    
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    
   
 
    
       
diff --git a/latest/reference/ci-overview.html b/latest/reference/ci-overview.html
index 8ec327815c..01cac31b11 100644
--- a/latest/reference/ci-overview.html
+++ b/latest/reference/ci-overview.html
@@ -58,7 +58,7 @@
     
@@ -70,7 +70,7 @@
 
   
   
-  
+  
 
 
   
@@ -349,6 +349,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    • 
 
  • Run LLM-API with pytorch backend on Slurm
    • 
 
  • Run trtllm-bench with pytorch backend on Slurm
    • 
 
  • Run trtllm-serve with pytorch backend on Slurm
    • 
@@ -384,6 +386,8 @@
 
 
    Command-Line Reference
    
 
@@ -551,9 +555,24 @@
 
  • Search jenkins/L0_Test.groovy for a stage whose YAML file matches (for example l0_a100) and whose name contains [Post-Merge] if the YAML entry uses stage: post_merge.
    • 
 
  • The resulting stage name(s) are what you pass to Jenkins via the stage_list parameter when triggering a job.
    • 
 
-
    
-
    Example#
    
-
    triton_server/test_triton.py::test_gpt_ib_ptuning[gpt-ib-ptuning] appears in l0_a100.yml under stage: post_merge and backend: triton.  The corresponding Jenkins stages are A100X-Triton-[Post-Merge]-1 and A100X-Triton-[Post-Merge]-2 (two shards).
    
+
    
+
    Using test_to_stage_mapping.py#
    
+
    Manually searching YAML and Groovy files can be tedious.  The helper script
+scripts/test_to_stage_mapping.py automates the lookup:
    
+
    python scripts/test_to_stage_mapping.py --tests "triton_server/test_triton.py::test_gpt_ib_ptuning[gpt-ib-ptuning]"
+python scripts/test_to_stage_mapping.py --tests gpt_ib_ptuning
+python scripts/test_to_stage_mapping.py --stages A100X-Triton-Post-Merge-1
+python scripts/test_to_stage_mapping.py --test-list my_tests.txt
+python scripts/test_to_stage_mapping.py --test-list my_tests.yml
+
    
+
    
+
    The first two commands print the Jenkins stages that run the specified tests or
+patterns. Patterns are matched by substring, so partial test names are
+supported out of the box. The third lists every test executed in the given stage. When
+providing tests on the command line, quote each test string so the shell does
+not interpret the [ and ] characters as globs. Alternatively, store the
+tests in a newline‑separated text file or a YAML list and supply it with
+--test-list.
    
 
    To run the same tests on your pull request, comment:
    
 
    /bot run --stage-list "A100X-Triton-[Post-Merge]-1,A100X-Triton-[Post-Merge]-2"
 
    
@@ -656,7 +675,7 @@ selective keeps CI turnaround fast and conserves hardware resources.
    
 
  • Unit tests
    • 
 
  • Jenkins stage names
    • 
 
  • Finding the stage for a test
 
    • 
 
  • Waiving tests
    • 
@@ -759,9 +778,9 @@ selective keeps CI turnaround fast and conserves hardware resources.
    
         
    
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    
   
 
    
       
diff --git a/latest/reference/dev-containers.html b/latest/reference/dev-containers.html
index d457a52b2d..bf402e3ba4 100644
--- a/latest/reference/dev-containers.html
+++ b/latest/reference/dev-containers.html
@@ -58,7 +58,7 @@
     
@@ -70,7 +70,7 @@
 
   
   
-  
+  
 
 
   
@@ -349,6 +349,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    • 
 
  • Run LLM-API with pytorch backend on Slurm
    • 
 
  • Run trtllm-bench with pytorch backend on Slurm
    • 
 
  • Run trtllm-serve with pytorch backend on Slurm
    • 
@@ -384,6 +386,8 @@
 
 
    Command-Line Reference
    
 
@@ -736,9 +740,9 @@ initialization script will create one with the contents listed above.
    
         
    
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    
   
 
    
       
diff --git a/latest/reference/memory.html b/latest/reference/memory.html
index f271ea75a6..ae00254317 100644
--- a/latest/reference/memory.html
+++ b/latest/reference/memory.html
@@ -58,7 +58,7 @@
     
@@ -70,7 +70,7 @@
 
   
   
-  
+  
 
 
   
@@ -349,6 +349,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    • 
 
  • Run LLM-API with pytorch backend on Slurm
    • 
 
  • Run trtllm-bench with pytorch backend on Slurm
    • 
 
  • Run trtllm-serve with pytorch backend on Slurm
    • 
@@ -384,6 +386,8 @@
 
 
    Command-Line Reference
    
 
@@ -770,9 +774,9 @@ Here some explanations on how these values affect the memory:
    
         
    
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    
   
 
    
       
diff --git a/latest/reference/precision.html b/latest/reference/precision.html
index 49ad6771cd..1494a516de 100644
--- a/latest/reference/precision.html
+++ b/latest/reference/precision.html
@@ -58,7 +58,7 @@
     
@@ -70,7 +70,7 @@
 
   
   
-  
+  
 
 
   
@@ -349,6 +349,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    • 
 
  • Run LLM-API with pytorch backend on Slurm
    • 
 
  • Run trtllm-bench with pytorch backend on Slurm
    • 
 
  • Run trtllm-serve with pytorch backend on Slurm
    • 
@@ -384,6 +386,8 @@
 
 
    Command-Line Reference
    
 
@@ -1266,9 +1270,9 @@ are:
    
         
    
 
    
   
-  
    Last updated on July 14, 2025.
    
+  
    Last updated on July 19, 2025.
    
   
-  
    This page is generated by TensorRT-LLM commit cfcb97a.
    
+  
    This page is generated by TensorRT-LLM commit 69e9f6d.
    
   
 
    
       
diff --git a/latest/reference/support-matrix.html b/latest/reference/support-matrix.html
index 014ef5a633..1ea0c6bb39 100644
--- a/latest/reference/support-matrix.html
+++ b/latest/reference/support-matrix.html
@@ -58,7 +58,7 @@
     
@@ -70,7 +70,7 @@
 
   
   
-  
+  
 
 
   
@@ -349,6 +349,8 @@
 
  • Control generated text using logits processor
    • 
 
  • Generate text with multiple LoRA adapters
    • 
 
  • Speculative Decoding
    • 
+
  • Runtime Configuration Examples
    • 
+
  • Sampling Techniques Showcase
    • 
 
  • Run LLM-API with pytorch backend on Slurm
    • 
 
  • Run trtllm-bench with pytorch backend on Slurm
    • 
 
  • Run trtllm-serve with pytorch backend on Slurm
    • 
@@ -384,6 +386,8 @@
 
 
    Command-Line Reference
    
 
@@ -702,6 +706,7 @@ In addition, older architectures can have limitations for newer software release

    GPU Model Architectures

    Command-Line Reference

    @@ -956,9 +960,9 @@ dedicated MPI environment, not the one provided by your Slurm allocation.

    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/release-notes.html b/latest/release-notes.html index 378c4aa0c6..a125dc7ce4 100644 --- a/latest/release-notes.html +++ b/latest/release-notes.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -2033,9 +2037,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/scripts/disaggregated/README.html b/latest/scripts/disaggregated/README.html index 26bff2efe8..a3f26fa127 100644 --- a/latest/scripts/disaggregated/README.html +++ b/latest/scripts/disaggregated/README.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -347,6 +347,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -382,6 +384,8 @@

    Command-Line Reference

    @@ -722,9 +726,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/search.html b/latest/search.html index 4afb7b62cf..b14e17e888 100644 --- a/latest/search.html +++ b/latest/search.html @@ -58,7 +58,7 @@ @@ -76,7 +76,7 @@ - + @@ -351,6 +351,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -386,6 +388,8 @@

    Command-Line Reference

    @@ -611,9 +615,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/searchindex.js b/latest/searchindex.js index 42bc248c6d..4242e02038 100644 --- a/latest/searchindex.js +++ b/latest/searchindex.js @@ -1 +1 @@ -Search.setIndex({"alltitles": {"1. Download TensorRT-LLM": [[21, "download-tensorrt-llm"]], "1. Using a Model from the Hugging Face Hub": [[67, "using-a-model-from-the-hugging-face-hub"]], "1. Weights size": [[89, "weights-size"]], "2. Activation size": [[89, "activation-size"]], "2. Download the DeepSeek R1 models": [[21, "download-the-deepseek-r1-models"]], "2. Using a Local Hugging Face Model": [[67, "using-a-local-hugging-face-model"]], "3. Build and run TensorRT-LLM container": [[21, "build-and-run-tensorrt-llm-container"]], "3. I/O tensors": [[89, "i-o-tensors"]], "3.1 Runtime and decoder buffers except KV cache tensor": [[89, "runtime-and-decoder-buffers-except-kv-cache-tensor"]], "3.2 KV cache tensor": [[89, "kv-cache-tensor"]], "4. Compile and Install TensorRT-LLM": [[21, "compile-and-install-tensorrt-llm"]], "5. Optional: Tune GPU clocks": [[21, "optional-tune-gpu-clocks"]], "6. Dataset preparation": [[21, "dataset-preparation"]], "@record_signature to Decorate Functionals Requiring FLayerInfo": [[7, "record-signature-to-decorate-functionals-requiring-flayerinfo"]], "ALiBi": [[5, "alibi"]], "API": [[3, "api"]], "API Changes": [[14, "api-changes"], [93, "api-changes"], [93, "id9"], [93, "id14"], [93, "id19"], [93, "id24"], [93, "id31"], [93, "id36"], [93, "id42"], [93, "id48"], [93, "id54"]], "API Reference": [[68, null]], "AWQ Quantization Scaling Factors": [[16, "awq-quantization-scaling-factors"]], "About": [[34, "about"]], "About Speculative Sampling": [[13, "about-speculative-sampling"]], "About TensorRT-LLM": [[69, "about-tensorrt-llm"]], "Accuracy": [[26, "accuracy"]], "Accuracy studies for Relaxed Acceptance": [[28, "accuracy-studies-for-relaxed-acceptance"]], "Achieving speedup with MTP speculative decoding": [[28, "achieving-speedup-with-mtp-speculative-decoding"]], "Acknowledgement": [[30, "acknowledgement"], [31, "acknowledgement"]], "Acknowledgment": [[27, "acknowledgment"], [28, "acknowledgment"], [29, "acknowledgment"]], "Activation": [[81, "module-tensorrt_llm.layers.activation"]], "Adding a Model": [[15, null]], "Adding a New Model in PyTorch Backend": [[96, null]], "Advanced": [[62, null]], "Advanced topics": [[63, "advanced-topics"]], "Algorithm": [[11, "algorithm"]], "Announcements": [[93, "announcements"], [93, "id52"]], "Architecture": [[62, null]], "Architecture Ovewiew": [[97, null]], "Asyncio-Based Generation": [[40, "asyncio-based-generation"]], "Attention": [[81, "module-tensorrt_llm.layers.attention"], [98, null]], "Attention Backends": [[98, "attention-backends"]], "Attention Kernel": [[27, "attention-kernel"]], "Attention Weights": [[16, "attention-weights"]], "Attention for MTP": [[28, "attention-for-mtp"]], "Auto parallel arguments": [[33, "tensorrt_llm.commands.build-parse_arguments-auto-parallel-arguments"]], "Autoregressive MTP Layers": [[27, "autoregressive-mtp-layers"]], "Avoiding unnecessary --disable-fail-fast usage": [[87, "avoiding-unnecessary-disable-fail-fast-usage"]], "B200 max-throughput for R1 with FP16 KV cache": [[21, "b200-max-throughput-for-r1-with-fp16-kv-cache"]], "B200 max-throughput for R1-0528 with FP8 KV cache": [[21, "b200-max-throughput-for-r1-0528-with-fp8-kv-cache"]], "B200 min-latency": [[21, "b200-min-latency"]], "Background": [[27, "background"], [28, "background"]], "Basic Implementation": [[28, "basic-implementation"]], "Basics": [[45, "basics"]], "Beam-Search": [[5, "beam-search"]], "Before Benchmarking": [[71, "before-benchmarking"]], "Before You Begin: TensorRT-LLM LLM-API": [[73, "before-you-begin-tensorrt-llm-llm-api"]], "Benchmark": [[21, "benchmark"], [21, "id1"], [26, "benchmark"], [34, "benchmark"]], "Benchmarking Default Performance": [[73, null]], "Benchmarking a non-Medusa Low Latency Engine": [[71, "benchmarking-a-non-medusa-low-latency-engine"]], "Benchmarking with LoRA Adapters in PyTorch workflow": [[71, "benchmarking-with-lora-adapters-in-pytorch-workflow"]], "Benchmarking with trtllm-bench": [[73, "benchmarking-with-trtllm-bench"]], "Best practices to choose the right quantization methods": [[26, "best-practices-to-choose-the-right-quantization-methods"]], "Block": [[8, "block"]], "Boost settings": [[71, "boost-settings"]], "Build APIs": [[20, "build-apis"]], "Build Checkpoint into TensorRT Engine": [[16, "build-checkpoint-into-tensorrt-engine"]], "Build Configuration": [[40, "build-configuration"]], "Build TensorRT-LLM": [[63, "build-tensorrt-llm"]], "Build the TensorRT-LLM Docker Image": [[35, null]], "Build the TensorRT-LLM Docker Image and Upload to DockerHub": [[35, "build-the-tensorrt-llm-docker-image-and-upload-to-dockerhub"], [36, "build-the-tensorrt-llm-docker-image-and-upload-to-dockerhub"]], "Building a Benchmark Engine": [[71, "building-a-benchmark-engine"]], "Building a Medusa Low-Latency Engine": [[71, "building-a-medusa-low-latency-engine"]], "Building a TensorRT-LLM Docker Image": [[63, "building-a-tensorrt-llm-docker-image"]], "Building and Saving Engines via CLI": [[73, "building-and-saving-engines-via-cli"]], "Building and Saving the Engine": [[73, "building-and-saving-the-engine"]], "Building from Source Code on Linux": [[63, null]], "Building the Python Bindings for the C++ Runtime": [[63, "building-the-python-bindings-for-the-c-runtime"]], "C++ Executor API Example": [[3, "c-executor-api-example"]], "C++ GPT Runtime": [[6, null]], "C++ extension": [[30, "c-extension"]], "C++ runtime": [[89, "c-runtime"], [89, "id1"]], "CI pipelines": [[87, "ci-pipelines"]], "CLI Tools": [[20, "cli-tools"]], "CUDA Graph & Programmatic Dependent Launch": [[27, "cuda-graph-programmatic-dependent-launch"]], "CUTLASS Backend (default backend)": [[27, "cutlass-backend-default-backend"]], "Cache Layout Transformation": [[31, "cache-layout-transformation"]], "Capacity Scheduler Policy": [[79, "capacity-scheduler-policy"]], "Cast": [[81, "module-tensorrt_llm.layers.cast"]], "Chat API": [[34, "chat-api"]], "Chunked Context": [[5, "chunked-context"]], "Classical Workflow": [[7, "classical-workflow"]], "Closing": [[22, "closing"], [25, "closing"]], "Collect PyTorch profiler results": [[70, "collect-pytorch-profiler-results"]], "Command Overview": [[72, "command-overview"]], "Common LLM Support": [[69, "common-llm-support"]], "Communication Kernel": [[27, "communication-kernel"]], "Compilation": [[17, "compilation"]], "Compile the Model into a TensorRT Engine": [[86, "compile-the-model-into-a-tensorrt-engine"]], "Completions API": [[34, "completions-api"], [34, "id1"]], "Conclusion": [[75, "conclusion"], [77, "conclusion"], [78, "conclusion"]], "Config": [[16, "config"]], "Configure SSH Key": [[36, "configure-ssh-key"]], "Configure The Executor": [[3, "configure-the-executor"]], "Connect to the Pod": [[36, "connect-to-the-pod"]], "Container image selection": [[88, "container-image-selection"]], "Container image tags": [[64, null], [86, null]], "Context Chunking Policy": [[79, "context-chunking-policy"]], "Context Phase": [[5, "context-phase"]], "Context and Generation Phases": [[5, "context-and-generation-phases"]], "Contiguous KV Cache": [[5, "contiguous-kv-cache"]], "Continuous Integration Overview": [[87, null]], "Control generated text using logits processor": [[51, null]], "Controlling output with Logits Post-Processor": [[3, "controlling-output-with-logits-post-processor"]], "Conv": [[81, "module-tensorrt_llm.layers.conv"]], "Conversion APIs": [[20, "conversion-apis"]], "Coordinating with NVIDIA Nsight Systems Launch": [[70, "coordinating-with-nvidia-nsight-systems-launch"]], "Coordinating with PyTorch profiler (PyTorch workflow only)": [[70, "coordinating-with-pytorch-profiler-pytorch-workflow-only"]], "Core Models": [[96, "core-models"]], "Core implementations of the GPU logic": [[30, "core-implementations-of-the-gpu-logic"]], "Core implementations of the host logic": [[30, "core-implementations-of-the-host-logic"]], "Create a Pod Template": [[36, "create-a-pod-template"]], "Create a Runpod account": [[36, "create-a-runpod-account"]], "Cross Attention": [[5, "cross-attention"]], "Curl Chat Client": [[37, null]], "Curl Chat Client For Multimodal": [[38, null]], "Curl Completion Client": [[39, null]], "Customization": [[45, "customization"]], "Customize KV Cache Manager": [[103, "customize-kv-cache-manager"]], "Customize Your Own Scheduler": [[104, "customize-your-own-scheduler"]], "Data Parallel for Attention module (ADP)": [[29, "data-parallel-for-attention-module-adp"]], "Debug Execution Errors": [[92, "debug-execution-errors"]], "Debug on E2E Models": [[92, "debug-on-e2e-models"]], "Debug on Unit Tests": [[92, "debug-on-unit-tests"]], "Debugging FAQs": [[2, "debugging-faqs"]], "Deciding Model Sharding Strategy": [[74, null]], "Decoder": [[97, "decoder"]], "DeepSeek R1": [[31, "deepseek-r1"]], "DeepSeek R1 MTP Implementation and Optimization": [[28, null]], "Deepseek R1 Reasoning Parser": [[41, null]], "Default Build Behavior": [[71, "default-build-behavior"]], "Dense GEMM optimization": [[27, "dense-gemm-optimization"]], "Deploy with Triton Inference Server": [[86, "deploy-with-triton-inference-server"]], "Deploy with trtllm-serve": [[86, "deploy-with-trtllm-serve"]], "Develop TensorRT-LLM on Runpod": [[36, null]], "Developer Guide": [[95, "developer-guide"]], "Disable Tokenizer": [[40, "disable-tokenizer"]], "Disaggregated Inference Benchmark Scripts": [[94, null]], "Disaggregated Serving in TensorRT-LLM": [[31, null], [31, "id1"]], "Disaggregated-Service (Experimental)": [[2, null]], "Distributed LLM Generation": [[50, null]], "DoRA": [[10, "dora"]], "Documentation": [[93, "documentation"], [93, "id28"]], "Download Artifacts": [[32, "download-artifacts"]], "Draft-Target-Model": [[13, "draft-target-model"]], "Dynamo": [[31, "dynamo"]], "E2E evaluation": [[30, "e2e-evaluation"]], "EAGLE": [[13, "eagle"]], "EP Load Balancer": [[30, "ep-load-balancer"]], "EP communication kernels": [[30, "ep-communication-kernels"]], "EP communication kernels implementation": [[30, "ep-communication-kernels-implementation"]], "Eagle3 support": [[28, "eagle3-support"]], "Embedding": [[81, "module-tensorrt_llm.layers.embedding"]], "Enable GIL information in NVTX markers": [[70, "enable-gil-information-in-nvtx-markers"]], "Enable garbage collection (GC) NVTX markers": [[70, "enable-garbage-collection-gc-nvtx-markers"]], "Enable kv cache reuse for p-tuning": [[9, "enable-kv-cache-reuse-for-p-tuning"]], "Enable more NVTX markers for debugging": [[70, "enable-more-nvtx-markers-for-debugging"]], "Enable ssh access to the container": [[35, "enable-ssh-access-to-the-container"]], "Enabling GEMM + SwiGLU Fusion": [[75, "enabling-gemm-swiglu-fusion"]], "Enabling GEMM Plugin": [[78, "enabling-gemm-plugin"]], "Enabling Low Latency GEMM plugin": [[75, "enabling-low-latency-gemm-plugin"]], "Enabling Paged Context Attention": [[78, "enabling-paged-context-attention"]], "Enabling Quantization": [[75, "enabling-quantization"]], "Enabling Quantized KV Cache": [[75, "enabling-quantized-kv-cache"]], "Enabling Reduce Norm Fusion Plugin": [[78, "enabling-reduce-norm-fusion-plugin"]], "Enabling Reduce Norm Fusion with User Buffers": [[75, "enabling-reduce-norm-fusion-with-user-buffers"]], "Enabling building with multiple profiles": [[78, "enabling-building-with-multiple-profiles"]], "Environment Variables": [[2, "environment-variables"]], "Evaluation": [[28, "evaluation"]], "Events in KVCacheEventManager": [[8, "events-in-kvcacheeventmanager"]], "Everything in One Diagram": [[27, "everything-in-one-diagram"]], "Example": [[16, "example"], [87, "example"]], "Example LoRA tensors": [[10, "example-lora-tensors"]], "Example of Build Subcommand Output:": [[71, "example-of-build-subcommand-output"]], "Examples": [[17, "examples"], [18, "examples"], [70, "examples"]], "Executor": [[0, null]], "Executor API": [[3, null]], "Expanded thoughts": [[30, "expanded-thoughts"]], "Expected Result Format": [[21, "expected-result-format"], [21, "id2"], [21, "id3"], [21, "id4"]], "Expected Results": [[21, "expected-results"]], "Expert Parallelism in TensorRT-LLM": [[4, null]], "Expert parallel for MoE (EP)": [[29, "expert-parallel-for-moe-ep"]], "Exploring more ISL/OSL combinations": [[21, "exploring-more-isl-osl-combinations"]], "FAQ": [[89, "faq"]], "FLayerInfo for Retrieving High-Level Information for a Functional": [[7, "flayerinfo-for-retrieving-high-level-information-for-a-functional"]], "FP32, FP16 and BF16": [[90, "fp32-fp16-and-bf16"]], "FP4 Models:": [[72, "fp4-models"]], "FP8 (Hopper)": [[90, "fp8-hopper"]], "FP8 Context FMHA": [[5, "fp8-context-fmha"]], "FP8 Models:": [[72, "fp8-models"]], "FP8 Quantization": [[75, null]], "FP8 Quantization Scaling Factors": [[16, "fp8-quantization-scaling-factors"]], "FP8 Support": [[69, "fp8-support"]], "FP8 \u201cBaseline\u201d Performance": [[75, "fp8-baseline-performance"]], "Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100": [[22, null]], "Falcon-180B on a single H200 with INT4 AWQ": [[22, "falcon-180b-on-a-single-h200-with-int4-awq"]], "Feature Combination Matrix": [[99, null]], "Feature Descriptions": [[70, "feature-descriptions"]], "Features": [[95, "features"]], "File Descriptions": [[94, "file-descriptions"]], "Finding the stage for a test": [[87, "finding-the-stage-for-a-test"]], "Fixed Issues": [[93, "fixed-issues"], [93, "id11"], [93, "id15"], [93, "id21"], [93, "id26"], [93, "id33"], [93, "id38"], [93, "id44"], [93, "id50"], [93, "id56"], [93, "id61"]], "Fully customized": [[18, "fully-customized"]], "Functionals": [[80, null]], "Fuse_A_GEMM": [[27, "fuse-a-gemm"]], "Future Work": [[31, "future-work"]], "Future Works": [[27, "future-works"], [28, "future-works"], [29, "future-works"]], "Future-Style Generation": [[40, "future-style-generation"]], "GEMM + SwiGLU Fusion in Gated-MLP": [[75, "gemm-swiglu-fusion-in-gated-mlp"]], "GEMM Plugin": [[78, "gemm-plugin"]], "GPTQ and AWQ (W4A16)": [[90, "gptq-and-awq-w4a16"]], "GPU Clock Management": [[71, "gpu-clock-management"]], "Genai Perf Client": [[42, null]], "Genai Perf Client For Multimodal": [[43, null]], "General FAQs": [[2, "general-faqs"]], "Generate text": [[47, null]], "Generate text asynchronously": [[48, null]], "Generate text in streaming": [[49, null]], "Generate text with guided decoding": [[46, null]], "Generate text with multiple LoRA adapters": [[55, null]], "Generation": [[40, "generation"]], "Generation Phase": [[5, "generation-phase"]], "Getting Started": [[62, null]], "Graph Rewriting APIs": [[7, "graph-rewriting-apis"]], "Graph Rewriting Module": [[7, null]], "Grouped GEMM": [[27, "grouped-gemm"]], "H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token": [[23, null]], "H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM": [[24, null]], "H200 max-throughput": [[21, "h200-max-throughput"]], "H200 min-latency": [[21, "h200-min-latency"]], "H200 vs H100": [[24, "h200-vs-h100"]], "Hardware": [[91, "hardware"]], "Hierarchy: Pool, Block, and Page": [[8, "hierarchy-pool-block-and-page"]], "High-level design introduction": [[30, "high-level-design-introduction"]], "How It Works": [[100, "how-it-works"]], "How the Benchmarker Works": [[71, "how-the-benchmarker-works"]], "How to Enable": [[4, "how-to-enable"]], "How to Think about Model Sharding: Communication is Key": [[74, "how-to-think-about-model-sharding-communication-is-key"]], "How to change Max Batch Size": [[77, "how-to-change-max-batch-size"]], "How to change Max Num Tokens": [[77, "how-to-change-max-num-tokens"]], "How to enable kv cache reuse": [[9, "how-to-enable-kv-cache-reuse"]], "How to get best performance on DeepSeek-R1 in TensorRT-LLM": [[21, null]], "How to launch Llama4 Maverick + Eagle3 TensorRT-LLM server": [[32, null]], "How to reproduce": [[27, "how-to-reproduce"], [29, "how-to-reproduce"]], "How to run DeepSeek models with MTP": [[28, "how-to-run-deepseek-models-with-mtp"]], "How to run the DeepSeek-R1 model with Relaxed Acceptance": [[28, "how-to-run-the-deepseek-r1-model-with-relaxed-acceptance"]], "How to set Tensor Parallelism and Pipeline Parallelism": [[74, "how-to-set-tensor-parallelism-and-pipeline-parallelism"]], "INT4 and INT8 Weight-Only (W4A16 and W8A16)": [[90, "int4-and-int8-weight-only-w4a16-and-w8a16"]], "INT8 SmoothQuant (W8A8)": [[90, "int8-smoothquant-w8a8"]], "INT8/FP8 KV Caches": [[5, "int8-fp8-kv-caches"]], "ISL 4096 - OSL 1024 (Machine Translation Dataset)": [[31, "isl-4096-osl-1024-machine-translation-dataset"]], "ISL 4400 - OSL 1200 (Machine Translation Dataset)": [[31, "isl-4400-osl-1200-machine-translation-dataset"]], "ISL 8192 - OSL 1024 (Machine Translation Dataset)": [[31, "isl-8192-osl-1024-machine-translation-dataset"]], "ISL 8192 - OSL 256 (Synthetic Dataset)": [[31, "isl-8192-osl-256-synthetic-dataset"]], "Implement AttentionBackend": [[98, "implement-attentionbackend"]], "Implement AttentionMetadata": [[98, "implement-attentionmetadata"]], "Implement a New Attention Backend": [[98, "implement-a-new-attention-backend"]], "Implementation Configuration": [[27, "implementation-configuration"]], "Important Note": [[5, "important-note"]], "In-Flight Batching and Paged Attention": [[69, "in-flight-batching-and-paged-attention"]], "In-flight Batching": [[5, "in-flight-batching"]], "In-flight Batching with the Triton Inference Server": [[3, "in-flight-batching-with-the-triton-inference-server"]], "Indices and tables": [[62, "indices-and-tables"]], "Inference Endpoints": [[34, "inference-endpoints"]], "Infrastructure Changes": [[93, "infrastructure-changes"], [93, "id4"], [93, "id7"], [93, "id12"], [93, "id16"], [93, "id22"], [93, "id27"], [93, "id34"], [93, "id39"], [93, "id45"]], "Infrastructure changes": [[93, "id51"]], "Input QKV tensor": [[5, "input-qkv-tensor"]], "Installation": [[62, null], [86, "installation"]], "Installation Errors": [[92, "installation-errors"]], "Installing on Linux via pip": [[65, null]], "Interfaces": [[103, "interfaces"]], "Internal Components": [[6, "internal-components"]], "Introduction": [[29, "introduction"], [96, "introduction"]], "Jenkins stage names": [[87, "jenkins-stage-names"]], "KV Cache": [[5, "kv-cache"]], "KV Cache Exchange": [[31, "kv-cache-exchange"]], "KV Cache Management: Pools, Blocks, and Events": [[8, null]], "KV Cache Manager": [[103, null]], "KV Cache Manager Introduction": [[103, "kv-cache-manager-introduction"]], "KV Cache Pool Management": [[8, "kv-cache-pool-management"]], "KV Cache Quantization Scaling Factors": [[16, "kv-cache-quantization-scaling-factors"]], "KV cache reuse": [[9, null]], "KVCacheManager": [[97, "kvcachemanager"]], "Kernel Level optimizations": [[27, "kernel-level-optimizations"]], "Kernel fusion": [[27, "kernel-fusion"]], "Key Components": [[95, "key-components"]], "Key Features": [[66, null]], "Key Features and Enhancements": [[93, "key-features-and-enhancements"], [93, "id2"], [93, "id3"], [93, "id5"], [93, "id8"], [93, "id13"], [93, "id18"], [93, "id23"], [93, "id30"], [93, "id35"], [93, "id41"], [93, "id47"], [93, "id53"], [93, "id57"], [93, "id59"]], "Key Optimizations": [[27, "key-optimizations"]], "Known Issues": [[89, "known-issues"], [93, "known-issues"], [93, "id6"], [93, "id10"], [93, "id17"], [93, "id29"], [93, "id40"], [93, "id46"], [93, "id62"], [95, "known-issues"]], "Known Limitations": [[63, "known-limitations"]], "LLM API": [[86, "llm-api"]], "LLM API Introduction": [[67, null]], "LLM Common Customizations": [[40, null]], "LLM Examples": [[45, null]], "LLM Examples Introduction": [[44, null]], "LLM Models": [[91, "llm-models"]], "Latest GPU Support": [[69, "latest-gpu-support"]], "Latest HBM Memory": [[24, "latest-hbm-memory"]], "Launching the server": [[32, "launching-the-server"]], "LayerNorm Weights": [[16, "layernorm-weights"]], "Layers": [[81, null]], "Limitations": [[13, "limitations"], [93, "limitations"]], "Limitations and Caveats": [[71, "limitations-and-caveats"]], "Linear": [[81, "module-tensorrt_llm.layers.linear"]], "Linking with the TensorRT-LLM C++ Runtime": [[63, "linking-with-the-tensorrt-llm-c-runtime"]], "Llama 3.1 405B": [[17, "llama-3-1-405b"]], "Llama 3.1 405B FP4": [[72, "llama-3-1-405b-fp4"]], "Llama 3.1 405B FP8": [[72, "llama-3-1-405b-fp8"]], "Llama 3.1 70B": [[17, "llama-3-1-70b"]], "Llama 3.1 70B FP8": [[72, "llama-3-1-70b-fp8"]], "Llama 3.1 8B FP8": [[72, "llama-3-1-8b-fp8"]], "Llama 3.3 70B FP4": [[72, "llama-3-3-70b-fp4"]], "Llama-70B on H200 up to 2.4x increased throughput with XQA within same latency budget": [[25, "llama-70b-on-h200-up-to-2-4x-increased-throughput-with-xqa-within-same-latency-budget"]], "Llama-70B on H200 up to 6.7x A100": [[22, "llama-70b-on-h200-up-to-6-7x-a100"]], "LoRA Module id mapping": [[10, "lora-module-id-mapping"]], "LoRA arguments": [[33, "tensorrt_llm.commands.build-parse_arguments-lora-arguments"]], "LoRA tensor format details": [[10, "lora-tensor-format-details"]], "LoRA with tensor parallel": [[10, "lora-with-tensor-parallel"]], "Loading function": [[18, "loading-function"]], "Logits arguments": [[33, "tensorrt_llm.commands.build-parse_arguments-logits-arguments"]], "Lookahead Decoding": [[13, "lookahead-decoding"]], "LoraCache configuration": [[10, "loracache-configuration"]], "Low Latency Benchmark": [[71, "low-latency-benchmark"]], "Low Latency GEMM Plugin": [[75, "low-latency-gemm-plugin"]], "Low Latency TensorRT-LLM Engine for Llama-3 70B": [[71, "low-latency-tensorrt-llm-engine-for-llama-3-70b"]], "Low-Precision-AllReduce": [[11, null]], "MLA Layers Optimizations": [[29, "mla-layers-optimizations"]], "MLP": [[81, "module-tensorrt_llm.layers.mlp"]], "MLP Weights": [[16, "mlp-weights"]], "MLPerf on H100 with FP8": [[23, "mlperf-on-h100-with-fp8"]], "MTP": [[27, "mtp"]], "MTP Eagle": [[28, "mtp-eagle"]], "MTP Modules": [[28, "mtp-modules"]], "MTP Vanilla": [[28, "mtp-vanilla"]], "MTP for inference": [[28, "mtp-for-inference"]], "MTP implementation in TensorRT-LLM": [[28, "mtp-implementation-in-tensorrt-llm"]], "MTP optimization - Relaxed Acceptance": [[28, "mtp-optimization-relaxed-acceptance"]], "Make Evaluation": [[16, "make-evaluation"]], "Mark Tensors As Output": [[3, "mark-tensors-as-output"]], "Max Throughput Benchmark": [[71, "max-throughput-benchmark"]], "Max Tokens in Paged KV Cache and KV Cache Free GPU Memory Fraction": [[79, "max-tokens-in-paged-kv-cache-and-kv-cache-free-gpu-memory-fraction"]], "Maximum Attention Window Size": [[79, "maximum-attention-window-size"]], "Measurement Methodology": [[31, "measurement-methodology"]], "Medusa": [[13, "medusa"]], "Medusa Tree": [[13, "medusa-tree"]], "Memory Usage of TensorRT-LLM": [[89, null]], "Memory pool": [[89, "memory-pool"]], "Metrics Endpoint": [[34, "metrics-endpoint"]], "Miscellaneous": [[30, "miscellaneous"]], "Mixed ETP": [[27, "mixed-etp"]], "Mixture of Experts (MoE)": [[4, "mixture-of-experts-moe"]], "MoE Layers Optimizations": [[29, "moe-layers-optimizations"]], "Model Architecture": [[27, "model-architecture"]], "Model Configuration": [[6, "model-configuration"], [96, "model-configuration"]], "Model Definition": [[17, null], [96, "model-definition"]], "Model Definition API": [[86, "model-definition-api"]], "Model Engine": [[17, "model-engine"], [97, "model-engine"]], "Model Input": [[67, "model-input"]], "Model Registration": [[96, "model-registration"]], "Model Updates": [[93, "model-updates"], [93, "id20"], [93, "id25"], [93, "id32"], [93, "id37"], [93, "id43"], [93, "id49"], [93, "id55"], [93, "id58"], [93, "id60"]], "Model Weights": [[19, "model-weights"]], "Models": [[82, null]], "Models (PyTorch Backend)": [[91, "models-pytorch-backend"]], "Models (TensorRT Backend)": [[91, "models-tensorrt-backend"]], "Models with customized key names": [[18, "models-with-customized-key-names"]], "Models with customized weight layout": [[18, "models-with-customized-weight-layout"]], "Motivation": [[31, "motivation"]], "Motivation for large-scale EP": [[30, "motivation-for-large-scale-ep"]], "Motivation of EP communication kernels for GB200": [[30, "motivation-of-ep-communication-kernels-for-gb200"]], "Multi-GPU Multi-Node Inference": [[69, "multi-gpu-multi-node-inference"]], "Multi-GPU and Multi-Node Support": [[17, "multi-gpu-and-multi-node-support"]], "Multi-Head, Multi-Query, and Group-Query Attention": [[5, null]], "Multi-Modal Models 3": [[91, "multi-modal-models"]], "Multi-backend Support": [[31, "multi-backend-support"]], "Multi-node Serving with Slurm": [[34, "multi-node-serving-with-slurm"]], "Multi-streams": [[27, "multi-streams"]], "Multimodal Serving": [[34, "multimodal-serving"]], "Multiple Profiles": [[78, "multiple-profiles"]], "NVFP4 (Blackwell)": [[90, "nvfp4-blackwell"]], "Named Arguments": [[33, "tensorrt_llm.commands.build-parse_arguments-named-arguments"]], "Native Windows Support": [[69, "native-windows-support"]], "Natively supported models": [[18, "natively-supported-models"]], "New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget": [[25, null]], "Next Steps": [[86, "next-steps"]], "Normalization": [[81, "module-tensorrt_llm.layers.normalization"]], "Not supported: MLA chunked context support on Hopper": [[21, "not-supported-mla-chunked-context-support-on-hopper"]], "Note on context outputs": [[3, "note-on-context-outputs"]], "Numerical Precision": [[90, null]], "Observation over GSM8K dataset": [[30, "observation-over-gsm8k-dataset"]], "Observations over one machine translation dataset": [[30, "observations-over-one-machine-translation-dataset"]], "Obtaining Arbitrary Output Tensors": [[3, "obtaining-arbitrary-output-tensors"]], "Offline EP Load Balancer": [[30, "offline-ep-load-balancer"], [30, "id1"]], "Offloading to host memory": [[9, "offloading-to-host-memory"]], "Online EP Load Balancer": [[30, "online-ep-load-balancer"], [30, "id2"]], "Online Serving Examples": [[61, null]], "Only collect specific iterations": [[70, "only-collect-specific-iterations"]], "OpenAI Chat Client": [[57, null]], "OpenAI Chat Client for Multimodal": [[58, null]], "OpenAI Completion Client": [[59, null]], "Openai Completion Client For Lora": [[60, null]], "Optimizing DeepSeek R1 Throughput on NVIDIA Blackwell GPUs: A Deep Dive for Developers": [[29, null]], "Option 1. Use weekly release NGC docker image": [[32, "option-1-use-weekly-release-ngc-docker-image"]], "Option 1: Build TensorRT-LLM in One Step": [[63, "option-1-build-tensorrt-llm-in-one-step"]], "Option 1: Full Build with C++ Compilation": [[63, "option-1-full-build-with-c-compilation"]], "Option 2. Build TensorRT-LLM Docker image (Alternative way)": [[32, "option-2-build-tensorrt-llm-docker-image-alternative-way"]], "Option 2: Container for building TensorRT-LLM Step-by-Step": [[63, "option-2-container-for-building-tensorrt-llm-step-by-step"]], "Option 2: Python-Only Build without C++ Compilation": [[63, "option-2-python-only-build-without-c-compilation"]], "Other Build Modes": [[71, "other-build-modes"]], "Out of memory issues": [[21, "out-of-memory-issues"]], "Out-of-Tree Models": [[96, "out-of-tree-models"]], "Overlap Optimization": [[31, "overlap-optimization"]], "Overlap Scheduler": [[100, null]], "Overriding Docker Compose configuration": [[88, "overriding-docker-compose-configuration"]], "Overview": [[6, "overview"], [16, "overview"], [18, "overview"], [20, "overview"], [69, null], [72, null], [94, "overview"]], "Padded and Packed Tensors": [[5, "padded-and-packed-tensors"]], "Page": [[8, "page"]], "Paged Context Attention": [[78, "paged-context-attention"]], "Paged KV Cache": [[5, "paged-kv-cache"]], "Parallel strategy": [[29, "parallel-strategy"]], "Parallelism Mapping Support": [[71, "parallelism-mapping-support"]], "Parallelism Strategy": [[27, "parallelism-strategy"]], "Pattern and Pattern Manager": [[7, "pattern-and-pattern-manager"]], "Pattern-Matching and Fusion": [[17, "pattern-matching-and-fusion"]], "Performance": [[26, "performance"], [62, null], [78, "performance"]], "Performance Analysis": [[70, null]], "Performance Improvements": [[13, "performance-improvements"]], "Performance Studies": [[31, "performance-studies"]], "Performance Tuning": [[32, "performance-tuning"]], "Performance Tuning Guide": [[76, null]], "Performance and Accuracy Considerations": [[11, "performance-and-accuracy-considerations"]], "Performance expectations": [[9, "performance-expectations"]], "Performance study": [[30, "performance-study"]], "Performance with GEMM + SwiGLU Fusion": [[75, "performance-with-gemm-swiglu-fusion"]], "Performance with GEMM Plugin": [[78, "performance-with-gemm-plugin"]], "Performance with Low Latency GEMM plugin": [[75, "performance-with-low-latency-gemm-plugin"]], "Performance with Quantized KV Cache": [[75, "performance-with-quantized-kv-cache"]], "Performance with Reduce Norm Fusion": [[78, "performance-with-reduce-norm-fusion"]], "Performance with Reduce Norm Fusion + User Buffers:": [[75, "performance-with-reduce-norm-fusion-user-buffers"]], "Performance with multiple profiles": [[78, "performance-with-multiple-profiles"]], "Persistence mode": [[71, "persistence-mode"]], "Pipeline Parallel Reduce Scatter Optimization": [[78, "pipeline-parallel-reduce-scatter-optimization"]], "Plugin": [[83, null]], "Plugin config arguments": [[33, "tensorrt_llm.commands.build-parse_arguments-plugin-config-arguments"]], "Plugins": [[17, "plugins"]], "Pool": [[8, "pool"]], "Pooling": [[81, "module-tensorrt_llm.layers.pooling"]], "Postprocessing functions": [[18, "postprocessing-functions"]], "Pre-built release container images on NGC": [[64, null]], "Precision Strategy": [[27, "precision-strategy"]], "Precision strategy": [[29, "precision-strategy"]], "Prepare": [[36, "prepare"]], "Prepare Dataset": [[73, "prepare-dataset"]], "Prepare the TensorRT-LLM Checkpoint": [[16, "prepare-the-tensorrt-llm-checkpoint"]], "Preparing a Dataset": [[71, "preparing-a-dataset"], [72, "preparing-a-dataset"]], "Prerequisite Knowledge": [[76, "prerequisite-knowledge"]], "Prerequisites": [[32, "prerequisites"], [63, "prerequisites"], [86, "prerequisites"], [96, "prerequisites"]], "Prerequisites: Install TensorRT-LLM and download models": [[21, "prerequisites-install-tensorrt-llm-and-download-models"]], "Profiling specific iterations on a trtllm-bench/trtllm-serve run": [[70, "profiling-specific-iterations-on-a-trtllm-bench-trtllm-serve-run"]], "Prompt-Lookup-Decoding": [[13, "prompt-lookup-decoding"]], "Pushing Latency Boundaries: Optimizing DeepSeek-R1 Performance on NVIDIA B200 GPUs": [[27, null]], "PyExecutor": [[97, "pyexecutor"]], "PyTorch Backend": [[95, null]], "Python Bindings for the Executor API": [[3, "python-bindings-for-the-executor-api"]], "Python Interface": [[30, "python-interface"]], "Python runtime (Not recommended to be used)": [[89, "python-runtime-not-recommended-to-be-used"]], "Quantization": [[40, "quantization"], [84, null], [101, null]], "Quantization APIs": [[20, "quantization-apis"]], "Quantization and Dequantization (Q/DQ)": [[90, "quantization-and-dequantization-q-dq"]], "Quantization in TensorRT-LLM": [[26, "quantization-in-tensorrt-llm"]], "Quantization in the PyTorch Flow": [[71, "quantization-in-the-pytorch-flow"]], "Quantized KV-Cache": [[75, "quantized-kv-cache"]], "Quick Start": [[95, "quick-start"]], "Quick Start Example": [[67, "quick-start-example"]], "Quick Start Guide": [[86, null]], "Quickstart": [[71, "quickstart"]], "Qwen 3": [[31, "qwen-3"]], "Rank Weights": [[16, "rank-weights"]], "Re-balanced the sparse experts": [[27, "re-balanced-the-sparse-experts"]], "ReDrafter": [[13, "redrafter"]], "Reduce Norm Fusion Plugin for Llama models:": [[78, "reduce-norm-fusion-plugin-for-llama-models"]], "Reduce Norm Fusion with User Buffers for Llama Models": [[75, "reduce-norm-fusion-with-user-buffers-for-llama-models"]], "Reference": [[15, "reference"], [62, null]], "References": [[100, "references"]], "Related Information": [[86, "related-information"]], "Relative Attention Bias (RAB)": [[5, "relative-attention-bias-rab"]], "Relax Acceptance Verification": [[27, "relax-acceptance-verification"]], "Relaxed Acceptance": [[28, "relaxed-acceptance"]], "Release Notes": [[93, null]], "Reproducing Benchmarked Results": [[72, "reproducing-benchmarked-results"]], "Reproducing Steps": [[31, "reproducing-steps"]], "Reproducing steps": [[21, "reproducing-steps"], [30, "reproducing-steps"]], "Request Additional Output": [[3, "request-additional-output"]], "ResourceManager": [[97, "resourcemanager"]], "Results": [[73, "results"]], "Revisiting Paged Context Attention and Context Chunking": [[77, "revisiting-paged-context-attention-and-context-chunking"]], "Rotary Positional Embedding (RoPE)": [[5, "rotary-positional-embedding-rope"]], "RouterGEMM": [[27, "routergemm"]], "Run LLM-API with pytorch backend on Slurm": [[52, null]], "Run gpt-2b + LoRA using Executor / cpp runtime": [[10, null]], "Run the Model": [[86, "run-the-model"]], "Run trtllm-bench with pytorch backend on Slurm": [[53, null]], "Run trtllm-serve with pytorch backend on Slurm": [[54, null]], "Running Throughput and Latency Benchmarks": [[73, "running-throughput-and-latency-benchmarks"]], "Running With Weight Streaming to Reduce GPU Memory Consumption": [[14, null]], "Running multi-modal models in the PyTorch Workflow": [[71, "running-multi-modal-models-in-the-pytorch-workflow"]], "Running the Benchmark": [[72, "running-the-benchmark"]], "Running with the PyTorch Workflow": [[71, "running-with-the-pytorch-workflow"]], "Runtime": [[1, null], [17, "runtime"], [85, null]], "Runtime Customization": [[40, "runtime-customization"]], "Runtime Optimizations": [[29, "runtime-optimizations"]], "Sampling": [[40, "sampling"], [102, null]], "Sampling Parameters": [[6, "sampling-parameters"]], "Scaling Expert Parallelism in TensorRT-LLM (Part 1: Design and Implementation of Large-scale EP)": [[30, null]], "Scaling factor(s)": [[5, "scaling-factor-s"]], "Scheduler": [[97, "scheduler"], [104, null]], "Scheduler Introduction": [[104, "scheduler-introduction"]], "Sending Requests with Different Beam Widths": [[3, "sending-requests-with-different-beam-widths"]], "Set power limits": [[71, "set-power-limits"]], "Situations that can prevent kv cache reuse": [[9, "situations-that-can-prevent-kv-cache-reuse"]], "Sliding Window Attention, Cyclic (Rolling Buffer) KV Cache": [[5, "sliding-window-attention-cyclic-rolling-buffer-kv-cache"]], "Slurm": [[45, "slurm"]], "Smart Router": [[27, "smart-router"]], "Software": [[91, "software"]], "Sparse Experts as GEMMs (only works when moe_backend=CUTLASS)": [[27, "sparse-experts-as-gemms-only-works-when-moe-backend-cutlass"]], "Speculative Decoding": [[56, null]], "Speculative Sampling": [[13, null]], "Speculative decoding arguments": [[33, "tensorrt_llm.commands.build-parse_arguments-speculative-decoding-arguments"]], "Speed up inference with SOTA quantization techniques in TRT-LLM": [[26, null]], "Starting a Server": [[34, "starting-a-server"]], "Step 1. Write Modeling Part": [[15, "step-1-write-modeling-part"]], "Step 1: Clone the repository": [[32, "step-1-clone-the-repository"]], "Step 1: Run inference and collect statistics": [[30, "step-1-run-inference-and-collect-statistics"]], "Step 2. Implement Weight Conversion": [[15, "step-2-implement-weight-conversion"]], "Step 2: Generate the EPLB configuration": [[30, "step-2-generate-the-eplb-configuration"]], "Step 2: Prepare the TensorRT-LLM release Docker image": [[32, "step-2-prepare-the-tensorrt-llm-release-docker-image"]], "Step 3. Register New Model": [[15, "step-3-register-new-model"]], "Step 3: (Optional) Tag and push the Docker image to your registry": [[32, "step-3-optional-tag-and-push-the-docker-image-to-your-registry"]], "Step 3: Run inference with the EPLB configuration": [[30, "step-3-run-inference-with-the-eplb-configuration"]], "Step 4. Verify New Model": [[15, "step-4-verify-new-model"]], "Step 4: Start the TensorRT-LLM server": [[32, "step-4-start-the-tensorrt-llm-server"]], "Step 5: Test the server with a sample request": [[32, "step-5-test-the-server-with-a-sample-request"]], "Step 6: (Optional) Monitor server logs": [[32, "step-6-optional-monitor-server-logs"]], "Step 7: (Optional) Stop the server": [[32, "step-7-optional-stop-the-server"]], "Step-by-Step Guide": [[96, "step-by-step-guide"]], "StreamingLLM": [[5, "streamingllm"]], "Structured output with guided decoding": [[3, "structured-output-with-guided-decoding"]], "Summary": [[71, "summary"]], "Summary of Configuration Option Recommendations:": [[75, "summary-of-configuration-option-recommendations"], [78, "summary-of-configuration-option-recommendations"]], "Support Matrix": [[91, null]], "Support matrix": [[90, "support-matrix"]], "Supported C++ Header Files": [[63, "supported-c-header-files"]], "Supported Quantization Modes": [[71, "supported-quantization-modes"]], "Syntax": [[34, "syntax"]], "System Level optimizations": [[27, "system-level-optimizations"]], "TRTLLM Backend": [[27, "trtllm-backend"]], "Table of Contents": [[21, "table-of-contents"], [27, "table-of-contents"], [28, "table-of-contents"], [29, "table-of-contents"], [30, "table-of-contents"], [76, "table-of-contents"], [87, "table-of-contents"], [96, "table-of-contents"]], "Technical Detail: The QuantMode Flags": [[90, "technical-detail-the-quantmode-flags"]], "Tensor Parallel vs Expert Parallel": [[4, "tensor-parallel-vs-expert-parallel"]], "Tensor-Related Methods": [[7, "tensor-related-methods"]], "TensorRT Compiler": [[17, "tensorrt-compiler"]], "TensorRT-LLM Architecture": [[19, null]], "TensorRT-LLM Benchmarking": [[71, null]], "TensorRT-LLM Build Workflow": [[20, null]], "TensorRT-LLM Checkpoint": [[16, null]], "TensorRT-LLM Model Weights Loader": [[18, null]], "TensorRT-LLM Release 0.10.0": [[93, "tensorrt-llm-release-0-10-0"]], "TensorRT-LLM Release 0.11.0": [[93, "tensorrt-llm-release-0-11-0"]], "TensorRT-LLM Release 0.12.0": [[93, "tensorrt-llm-release-0-12-0"]], "TensorRT-LLM Release 0.13.0": [[93, "tensorrt-llm-release-0-13-0"]], "TensorRT-LLM Release 0.14.0": [[93, "tensorrt-llm-release-0-14-0"]], "TensorRT-LLM Release 0.15.0": [[93, "tensorrt-llm-release-0-15-0"]], "TensorRT-LLM Release 0.16.0": [[93, "tensorrt-llm-release-0-16-0"]], "TensorRT-LLM Release 0.17.0": [[93, "tensorrt-llm-release-0-17-0"]], "TensorRT-LLM Release 0.18.0": [[93, "tensorrt-llm-release-0-18-0"]], "TensorRT-LLM Release 0.18.1": [[93, "tensorrt-llm-release-0-18-1"]], "TensorRT-LLM Release 0.18.2": [[93, "tensorrt-llm-release-0-18-2"]], "TensorRT-LLM Release 0.19.0": [[93, "tensorrt-llm-release-0-19-0"]], "TensorRT-LLM Release 0.7.1": [[93, "tensorrt-llm-release-0-7-1"]], "TensorRT-LLM Release 0.8.0": [[93, "tensorrt-llm-release-0-8-0"]], "TensorRT-LLM Release 0.9.0": [[93, "tensorrt-llm-release-0-9-0"]], "Test definitions": [[87, "test-definitions"]], "The Executor Class": [[3, "the-executor-class"]], "The Request Class": [[3, "the-request-class"]], "The Response Class": [[3, "the-response-class"]], "The Result Class": [[3, "the-result-class"]], "The effect of EP Load Balancer": [[30, "the-effect-of-ep-load-balancer"], [30, "id3"]], "Throughput Benchmarking": [[71, "throughput-benchmarking"]], "Throughput Measurements": [[72, "throughput-measurements"]], "Tips": [[92, "tips"]], "Tips and Troubleshooting": [[67, "tips-and-troubleshooting"]], "Tokenizer Customization": [[40, "tokenizer-customization"]], "Top Level API": [[97, "top-level-api"]], "Topology Requirements": [[11, "topology-requirements"]], "Tradeoff": [[100, "tradeoff"]], "Translator": [[18, "translator"]], "Tree-based speculative decoding support": [[28, "tree-based-speculative-decoding-support"]], "Triggering CI Best Practices": [[87, "triggering-ci-best-practices"]], "Triggering Post-merge tests": [[87, "triggering-post-merge-tests"]], "Triton Inference Server": [[31, "triton-inference-server"]], "Trouble shooting": [[18, "trouble-shooting"]], "Troubleshooting": [[92, null]], "Troubleshooting Tips": [[32, "troubleshooting-tips"]], "Troubleshooting Tips and Pitfalls To Avoid": [[73, "troubleshooting-tips-and-pitfalls-to-avoid"]], "Troubleshooting and FAQ": [[2, "troubleshooting-and-faq"]], "Tuning Case Study": [[77, "tuning-case-study"], [77, "id2"]], "Tuning Max Batch Size": [[77, "tuning-max-batch-size"]], "Tuning Max Batch Size and Max Num Tokens": [[77, null]], "Tuning Max Num Tokens": [[77, "tuning-max-num-tokens"]], "Types of Events": [[8, "types-of-events"]], "Understand inference time GPU memory usage": [[89, "understand-inference-time-gpu-memory-usage"]], "Understanding the TensorRT-LLM scheduler": [[77, "understanding-the-tensorrt-llm-scheduler"]], "Unit tests": [[87, "unit-tests"]], "Upload the Docker Image to DockerHub": [[35, "upload-the-docker-image-to-dockerhub"]], "Usage": [[11, "usage"], [100, "usage"]], "Useful Build-Time Flags": [[78, null]], "Useful Runtime Options": [[79, null]], "Using Dev Containers": [[88, null]], "Using Medusa with TensorRT-LLM": [[13, "using-medusa-with-tensorrt-llm"]], "Validated Networks for Benchmarking": [[71, "validated-networks-for-benchmarking"]], "Variables": [[72, "variables"]], "Visualize the PyTorch profiler results": [[70, "visualize-the-pytorch-profiler-results"]], "Volume Mounts": [[88, "volume-mounts"]], "WIP: Enable more features by default": [[21, "wip-enable-more-features-by-default"]], "Waiving tests": [[87, "waiving-tests"]], "Weight Bindings": [[17, "weight-bindings"]], "Weight Loading": [[96, "weight-loading"]], "Weights absorb and MQA": [[29, "weights-absorb-and-mqa"]], "Welcome to TensorRT-LLM\u2019s Documentation!": [[62, null]], "What Can You Do With TensorRT-LLM?": [[69, "what-can-you-do-with-tensorrt-llm"]], "What Triggers an Event?": [[8, "what-triggers-an-event"]], "What is H100 FP8?": [[23, "what-is-h100-fp8"]], "What\u2019s coming next": [[26, "whats-coming-next"]], "When to Use Graph Rewriting?": [[7, "when-to-use-graph-rewriting"]], "WindowBlockManager/BlockManager": [[8, "windowblockmanager-blockmanager"]], "Workflow": [[18, "workflow"], [71, "workflow"], [94, "workflow"]], "Workload Profile": [[27, "workload-profile"]], "World Configuration": [[6, "world-configuration"]], "XQA Optimization": [[5, "xqa-optimization"]], "bufferManager.h": [[1, "buffermanager-h"]], "cacheCommunicator.h": [[0, "cachecommunicator-h"]], "common.h": [[1, "common-h"]], "cudaEvent.h": [[1, "cudaevent-h"]], "cudaStream.h": [[1, "cudastream-h"]], "dataTransceiverState.h": [[0, "datatransceiverstate-h"]], "decoderState.h": [[1, "decoderstate-h"]], "decodingInput.h": [[1, "decodinginput-h"]], "decodingOutput.h": [[1, "decodingoutput-h"]], "disaggServerUtil.h": [[0, "disaggserverutil-h"]], "disaggr_torch.slurm": [[94, "disaggr-torch-slurm"]], "disaggregated": [[34, "trtllm-serve-disaggregated"]], "disaggregated_mpi_worker": [[34, "trtllm-serve-disaggregated-mpi-worker"]], "eagleBuffers.h": [[1, "eaglebuffers-h"]], "eagleModule.h": [[1, "eaglemodule-h"]], "executor.h": [[0, "executor-h"]], "explicitDraftTokensBuffers.h": [[1, "explicitdrafttokensbuffers-h"]], "gen_yaml.py": [[94, "gen-yaml-py"]], "gptDecoder.h": [[1, "gptdecoder-h"]], "gptDecoderBatched.h": [[1, "gptdecoderbatched-h"]], "gptJsonConfig.h": [[1, "gptjsonconfig-h"]], "iBuffer.h": [[1, "ibuffer-h"]], "iGptDecoderBatched.h": [[1, "igptdecoderbatched-h"]], "iTensor.h": [[1, "itensor-h"]], "ipcNvlsMemory.h": [[1, "ipcnvlsmemory-h"]], "ipcUtils.h": [[1, "ipcutils-h"]], "lookaheadBuffers.h": [[1, "lookaheadbuffers-h"]], "lookaheadModule.h": [[1, "lookaheadmodule-h"]], "loraCache.h": [[1, "loracache-h"]], "loraCachePageManagerConfig.h": [[1, "loracachepagemanagerconfig-h"]], "loraModule.h": [[1, "loramodule-h"]], "medusaModule.h": [[1, "medusamodule-h"]], "memoryCounters.h": [[1, "memorycounters-h"]], "modelConfig.h": [[1, "modelconfig-h"]], "promptTuningParams.h": [[1, "prompttuningparams-h"]], "rawEngine.h": [[1, "rawengine-h"]], "request.h": [[1, "request-h"]], "run_benchmark.sh": [[94, "run-benchmark-sh"]], "runtimeDefaults.h": [[1, "runtimedefaults-h"]], "samplingConfig.h": [[1, "samplingconfig-h"]], "serialization.h": [[0, "serialization-h"]], "serve": [[34, "trtllm-serve-serve"]], "speculativeDecodingMode.h": [[1, "speculativedecodingmode-h"]], "speculativeDecodingModule.h": [[1, "speculativedecodingmodule-h"]], "start_worker.sh": [[94, "start-worker-sh"]], "submit.sh": [[94, "submit-sh"]], "tensor.h": [[0, "tensor-h"]], "tllmLogger.h": [[1, "tllmlogger-h"]], "transferAgent.h": [[0, "transferagent-h"]], "trtllm-build": [[33, null]], "trtllm-serve": [[31, "trtllm-serve"], [34, null], [34, "trtllm-serve"]], "types.h": [[0, "types-h"]], "worldConfig.h": [[1, "worldconfig-h"]]}, "docnames": ["_cpp_gen/executor", "_cpp_gen/runtime", "advanced/disaggregated-service", "advanced/executor", "advanced/expert-parallelism", "advanced/gpt-attention", "advanced/gpt-runtime", "advanced/graph-rewriting", "advanced/kv-cache-management", "advanced/kv-cache-reuse", "advanced/lora", "advanced/lowprecision-pcie-allreduce", "advanced/open-sourced-cutlass-kernels", "advanced/speculative-decoding", "advanced/weight-streaming", "architecture/add-model", "architecture/checkpoint", "architecture/core-concepts", "architecture/model-weights-loader", "architecture/overview", "architecture/workflow", "blogs/Best_perf_practice_on_DeepSeek-R1_in_TensorRT-LLM", "blogs/Falcon180B-H200", "blogs/H100vsA100", "blogs/H200launch", "blogs/XQA-kernel", "blogs/quantization-in-TRT-LLM", "blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs", "blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization", "blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs", "blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM", "blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM", "blogs/tech_blog/blog6_Llama4_maverick_eagle_guide", "commands/trtllm-build", "commands/trtllm-serve", "dev-on-cloud/build-image-to-dockerhub", "dev-on-cloud/dev-on-runpod", "examples/curl_chat_client", "examples/curl_chat_client_for_multimodal", "examples/curl_completion_client", "examples/customization", "examples/deepseek_r1_reasoning_parser", "examples/genai_perf_client", "examples/genai_perf_client_for_multimodal", "examples/index", "examples/llm_api_examples", "examples/llm_guided_decoding", "examples/llm_inference", "examples/llm_inference_async", "examples/llm_inference_async_streaming", "examples/llm_inference_distributed", "examples/llm_logits_processor", "examples/llm_mgmn_llm_distributed", "examples/llm_mgmn_trtllm_bench", "examples/llm_mgmn_trtllm_serve", "examples/llm_multilora", "examples/llm_speculative_decoding", "examples/openai_chat_client", "examples/openai_chat_client_for_multimodal", "examples/openai_completion_client", "examples/openai_completion_client_for_lora", "examples/trtllm_serve_examples", "index", "installation/build-from-source-linux", "installation/containers", "installation/linux", "key-features", "llm-api/index", "llm-api/reference", "overview", "performance/perf-analysis", "performance/perf-benchmarking", "performance/perf-overview", "performance/performance-tuning-guide/benchmarking-default-performance", "performance/performance-tuning-guide/deciding-model-sharding-strategy", "performance/performance-tuning-guide/fp8-quantization", "performance/performance-tuning-guide/index", "performance/performance-tuning-guide/tuning-max-batch-size-and-max-num-tokens", "performance/performance-tuning-guide/useful-build-time-flags", "performance/performance-tuning-guide/useful-runtime-flags", "python-api/tensorrt_llm.functional", "python-api/tensorrt_llm.layers", "python-api/tensorrt_llm.models", "python-api/tensorrt_llm.plugin", "python-api/tensorrt_llm.quantization", "python-api/tensorrt_llm.runtime", "quick-start-guide", "reference/ci-overview", "reference/dev-containers", "reference/memory", "reference/precision", "reference/support-matrix", "reference/troubleshooting", "release-notes", "scripts/disaggregated/README", "torch", "torch/adding_new_model", "torch/arch_overview", "torch/attention", "torch/features/feature_combination_matrix", "torch/features/overlap_scheduler", "torch/features/quantization", "torch/features/sampling", "torch/kv_cache_manager", "torch/scheduler"], "envversion": {"sphinx": 62, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.todo": 2, "sphinx.ext.viewcode": 1}, "filenames": ["_cpp_gen/executor.rst", "_cpp_gen/runtime.rst", "advanced/disaggregated-service.md", "advanced/executor.md", "advanced/expert-parallelism.md", "advanced/gpt-attention.md", "advanced/gpt-runtime.md", "advanced/graph-rewriting.md", "advanced/kv-cache-management.md", "advanced/kv-cache-reuse.md", "advanced/lora.md", "advanced/lowprecision-pcie-allreduce.md", "advanced/open-sourced-cutlass-kernels.md", "advanced/speculative-decoding.md", "advanced/weight-streaming.md", "architecture/add-model.md", "architecture/checkpoint.md", "architecture/core-concepts.md", "architecture/model-weights-loader.md", "architecture/overview.md", "architecture/workflow.md", "blogs/Best_perf_practice_on_DeepSeek-R1_in_TensorRT-LLM.md", "blogs/Falcon180B-H200.md", "blogs/H100vsA100.md", "blogs/H200launch.md", "blogs/XQA-kernel.md", "blogs/quantization-in-TRT-LLM.md", "blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.md", "blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.md", "blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.md", "blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.md", "blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.md", "blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.md", "commands/trtllm-build.rst", "commands/trtllm-serve.rst", "dev-on-cloud/build-image-to-dockerhub.md", "dev-on-cloud/dev-on-runpod.md", "examples/curl_chat_client.rst", "examples/curl_chat_client_for_multimodal.rst", "examples/curl_completion_client.rst", "examples/customization.md", "examples/deepseek_r1_reasoning_parser.rst", "examples/genai_perf_client.rst", "examples/genai_perf_client_for_multimodal.rst", "examples/index.rst", "examples/llm_api_examples.rst", "examples/llm_guided_decoding.rst", "examples/llm_inference.rst", "examples/llm_inference_async.rst", "examples/llm_inference_async_streaming.rst", "examples/llm_inference_distributed.rst", "examples/llm_logits_processor.rst", "examples/llm_mgmn_llm_distributed.rst", "examples/llm_mgmn_trtllm_bench.rst", "examples/llm_mgmn_trtllm_serve.rst", "examples/llm_multilora.rst", "examples/llm_speculative_decoding.rst", "examples/openai_chat_client.rst", "examples/openai_chat_client_for_multimodal.rst", "examples/openai_completion_client.rst", "examples/openai_completion_client_for_lora.rst", "examples/trtllm_serve_examples.rst", "index.rst", "installation/build-from-source-linux.md", "installation/containers.md", "installation/linux.md", "key-features.md", "llm-api/index.md", "llm-api/reference.rst", "overview.md", "performance/perf-analysis.md", "performance/perf-benchmarking.md", "performance/perf-overview.md", "performance/performance-tuning-guide/benchmarking-default-performance.md", "performance/performance-tuning-guide/deciding-model-sharding-strategy.md", "performance/performance-tuning-guide/fp8-quantization.md", "performance/performance-tuning-guide/index.rst", "performance/performance-tuning-guide/tuning-max-batch-size-and-max-num-tokens.md", "performance/performance-tuning-guide/useful-build-time-flags.md", "performance/performance-tuning-guide/useful-runtime-flags.md", "python-api/tensorrt_llm.functional.rst", "python-api/tensorrt_llm.layers.rst", "python-api/tensorrt_llm.models.rst", "python-api/tensorrt_llm.plugin.rst", "python-api/tensorrt_llm.quantization.rst", "python-api/tensorrt_llm.runtime.rst", "quick-start-guide.md", "reference/ci-overview.md", "reference/dev-containers.md", "reference/memory.md", "reference/precision.md", "reference/support-matrix.md", "reference/troubleshooting.md", "release-notes.md", "scripts/disaggregated/README.md", "torch.md", "torch/adding_new_model.md", "torch/arch_overview.md", "torch/attention.md", "torch/features/feature_combination_matrix.md", "torch/features/overlap_scheduler.md", "torch/features/quantization.md", "torch/features/sampling.md", "torch/kv_cache_manager.md", "torch/scheduler.md"], "indexentries": {"--backend": [[34, "cmdoption-trtllm-serve-serve-backend", false]], "--cluster_size": [[34, "cmdoption-trtllm-serve-serve-cluster_size", false]], "--config_file": [[34, "cmdoption-trtllm-serve-disaggregated-c", false], [34, "cmdoption-trtllm-serve-disaggregated_mpi_worker-c", false]], "--ep_size": [[34, "cmdoption-trtllm-serve-serve-ep_size", false]], "--extra_llm_api_options": [[34, "cmdoption-trtllm-serve-serve-extra_llm_api_options", false]], "--gpus_per_node": [[34, "cmdoption-trtllm-serve-serve-gpus_per_node", false]], "--host": [[34, "cmdoption-trtllm-serve-serve-host", false]], "--kv_cache_free_gpu_memory_fraction": [[34, "cmdoption-trtllm-serve-serve-kv_cache_free_gpu_memory_fraction", false]], "--log_level": [[34, "cmdoption-trtllm-serve-disaggregated-l", false], [34, "cmdoption-trtllm-serve-disaggregated_mpi_worker-log_level", false], [34, "cmdoption-trtllm-serve-serve-log_level", false]], "--max_batch_size": [[34, "cmdoption-trtllm-serve-serve-max_batch_size", false]], "--max_beam_width": [[34, "cmdoption-trtllm-serve-serve-max_beam_width", false]], "--max_num_tokens": [[34, "cmdoption-trtllm-serve-serve-max_num_tokens", false]], "--max_seq_len": [[34, "cmdoption-trtllm-serve-serve-max_seq_len", false]], "--metadata_server_config_file": [[34, "cmdoption-trtllm-serve-disaggregated-m", false], [34, "cmdoption-trtllm-serve-serve-metadata_server_config_file", false]], "--num_postprocess_workers": [[34, "cmdoption-trtllm-serve-serve-num_postprocess_workers", false]], "--port": [[34, "cmdoption-trtllm-serve-serve-port", false]], "--pp_size": [[34, "cmdoption-trtllm-serve-serve-pp_size", false]], "--reasoning_parser": [[34, "cmdoption-trtllm-serve-serve-reasoning_parser", false]], "--request_timeout": [[34, "cmdoption-trtllm-serve-disaggregated-r", false]], "--server_role": [[34, "cmdoption-trtllm-serve-serve-server_role", false]], "--server_start_timeout": [[34, "cmdoption-trtllm-serve-disaggregated-t", false]], "--tokenizer": [[34, "cmdoption-trtllm-serve-serve-tokenizer", false]], "--tp_size": [[34, "cmdoption-trtllm-serve-serve-tp_size", false]], "--trust_remote_code": [[34, "cmdoption-trtllm-serve-serve-trust_remote_code", false]], "-c": [[34, "cmdoption-trtllm-serve-disaggregated-c", false], [34, "cmdoption-trtllm-serve-disaggregated_mpi_worker-c", false]], "-l": [[34, "cmdoption-trtllm-serve-disaggregated-l", false]], "-m": [[34, "cmdoption-trtllm-serve-disaggregated-m", false]], "-r": [[34, "cmdoption-trtllm-serve-disaggregated-r", false]], "-t": [[34, "cmdoption-trtllm-serve-disaggregated-t", false]], "__init__() (tensorrt_llm.llmapi.buildcacheconfig method)": [[68, "tensorrt_llm.llmapi.BuildCacheConfig.__init__", false]], "__init__() (tensorrt_llm.llmapi.buildconfig method)": [[68, "tensorrt_llm.llmapi.BuildConfig.__init__", false]], "__init__() (tensorrt_llm.llmapi.completionoutput method)": [[68, "tensorrt_llm.llmapi.CompletionOutput.__init__", false]], "__init__() (tensorrt_llm.llmapi.disaggregatedparams method)": [[68, "tensorrt_llm.llmapi.DisaggregatedParams.__init__", false]], "__init__() (tensorrt_llm.llmapi.guideddecodingparams method)": [[68, "tensorrt_llm.llmapi.GuidedDecodingParams.__init__", false]], "__init__() (tensorrt_llm.llmapi.kvcacheretentionconfig method)": [[68, "tensorrt_llm.llmapi.KvCacheRetentionConfig.__init__", false]], "__init__() (tensorrt_llm.llmapi.kvcacheretentionconfig.tokenrangeretentionconfig method)": [[68, "tensorrt_llm.llmapi.KvCacheRetentionConfig.TokenRangeRetentionConfig.__init__", false]], "__init__() (tensorrt_llm.llmapi.lookaheaddecodingconfig method)": [[68, "tensorrt_llm.llmapi.LookaheadDecodingConfig.__init__", false]], "__init__() (tensorrt_llm.llmapi.mpicommsession method)": [[68, "tensorrt_llm.llmapi.MpiCommSession.__init__", false]], "__init__() (tensorrt_llm.llmapi.quantconfig method)": [[68, "tensorrt_llm.llmapi.QuantConfig.__init__", false]], "__init__() (tensorrt_llm.llmapi.requestoutput method)": [[68, "tensorrt_llm.llmapi.RequestOutput.__init__", false]], "__init__() (tensorrt_llm.llmapi.samplingparams method)": [[68, "tensorrt_llm.llmapi.SamplingParams.__init__", false]], "abort() (tensorrt_llm.llmapi.mpicommsession method)": [[68, "tensorrt_llm.llmapi.MpiCommSession.abort", false]], "abs() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.abs", false]], "abs() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.abs", false]], "activation() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.activation", false]], "adalayernorm (class in tensorrt_llm.layers.normalization)": [[81, "tensorrt_llm.layers.normalization.AdaLayerNorm", false]], "adalayernormcontinuous (class in tensorrt_llm.layers.normalization)": [[81, "tensorrt_llm.layers.normalization.AdaLayerNormContinuous", false]], "adalayernormzero (class in tensorrt_llm.layers.normalization)": [[81, "tensorrt_llm.layers.normalization.AdaLayerNormZero", false]], "adalayernormzerosingle (class in tensorrt_llm.layers.normalization)": [[81, "tensorrt_llm.layers.normalization.AdaLayerNormZeroSingle", false]], "add() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.add", false]], "add_input() (tensorrt_llm.functional.conditional method)": [[80, "tensorrt_llm.functional.Conditional.add_input", false]], "add_output() (tensorrt_llm.functional.conditional method)": [[80, "tensorrt_llm.functional.Conditional.add_output", false]], "add_sequence() (tensorrt_llm.runtime.kvcachemanager method)": [[85, "tensorrt_llm.runtime.KVCacheManager.add_sequence", false]], "add_special_tokens (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.add_special_tokens", false]], "additional_model_outputs (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.additional_model_outputs", false]], "alibi (tensorrt_llm.functional.positionembeddingtype attribute)": [[80, "tensorrt_llm.functional.PositionEmbeddingType.alibi", false]], "alibi_with_scale (tensorrt_llm.functional.positionembeddingtype attribute)": [[80, "tensorrt_llm.functional.PositionEmbeddingType.alibi_with_scale", false]], "allgather() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.allgather", false]], "allreduce() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.allreduce", false]], "allreduce_strategy (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.allreduce_strategy", false]], "allreducefusionop (class in tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.AllReduceFusionOp", false]], "allreduceparams (class in tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.AllReduceParams", false]], "allreducestrategy (class in tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.AllReduceStrategy", false]], "apply_batched_logits_processor (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.apply_batched_logits_processor", false]], "apply_llama3_scaling() (tensorrt_llm.functional.ropeembeddingutils static method)": [[80, "tensorrt_llm.functional.RopeEmbeddingUtils.apply_llama3_scaling", false]], "apply_rotary_pos_emb() (tensorrt_llm.functional.ropeembeddingutils static method)": [[80, "tensorrt_llm.functional.RopeEmbeddingUtils.apply_rotary_pos_emb", false]], "apply_rotary_pos_emb_chatglm() (tensorrt_llm.functional.ropeembeddingutils static method)": [[80, "tensorrt_llm.functional.RopeEmbeddingUtils.apply_rotary_pos_emb_chatglm", false]], "apply_rotary_pos_emb_cogvlm() (tensorrt_llm.functional.ropeembeddingutils static method)": [[80, "tensorrt_llm.functional.RopeEmbeddingUtils.apply_rotary_pos_emb_cogvlm", false]], "arange() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.arange", false]], "argmax() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.argmax", false]], "assert_valid_quant_algo() (tensorrt_llm.models.gemmaforcausallm class method)": [[82, "tensorrt_llm.models.GemmaForCausalLM.assert_valid_quant_algo", false]], "assertion() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.assertion", false]], "attention (class in tensorrt_llm.layers.attention)": [[81, "tensorrt_llm.layers.attention.Attention", false]], "attentionmaskparams (class in tensorrt_llm.layers.attention)": [[81, "tensorrt_llm.layers.attention.AttentionMaskParams", false]], "attentionmasktype (class in tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.AttentionMaskType", false]], "attentionparams (class in tensorrt_llm.layers.attention)": [[81, "tensorrt_llm.layers.attention.AttentionParams", false]], "attn_backend (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.attn_backend", false]], "attn_processors (tensorrt_llm.models.sd3transformer2dmodel property)": [[82, "tensorrt_llm.models.SD3Transformer2DModel.attn_processors", false]], "audio_engine_dir (tensorrt_llm.runtime.multimodalmodelrunner property)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.audio_engine_dir", false]], "auto (tensorrt_llm.functional.allreducestrategy attribute)": [[80, "tensorrt_llm.functional.AllReduceStrategy.AUTO", false]], "auto_parallel (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.auto_parallel", false]], "auto_parallel_config (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.auto_parallel_config", false]], "auto_parallel_config (tensorrt_llm.llmapi.trtllmargs property)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.auto_parallel_config", false]], "auto_parallel_world_size (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.auto_parallel_world_size", false]], "avg_pool2d() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.avg_pool2d", false]], "avgpool2d (class in tensorrt_llm.layers.pooling)": [[81, "tensorrt_llm.layers.pooling.AvgPool2d", false]], "axes (tensorrt_llm.functional.sliceinputtype attribute)": [[80, "tensorrt_llm.functional.SliceInputType.axes", false]], "bad (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.bad", false]], "bad_token_ids (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.bad_token_ids", false]], "bad_words_list (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.bad_words_list", false]], "baichuanforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.BaichuanForCausalLM", false]], "batch_size (tensorrt_llm.runtime.generationsession attribute)": [[85, "tensorrt_llm.runtime.GenerationSession.batch_size", false]], "batch_sizes (tensorrt_llm.llmapi.cudagraphconfig attribute)": [[68, "tensorrt_llm.llmapi.CudaGraphConfig.batch_sizes", false]], "batchingtype (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.BatchingType", false]], "beam_search_diversity_rate (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.beam_search_diversity_rate", false]], "beam_search_diversity_rate (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.beam_search_diversity_rate", false]], "beam_width_array (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.beam_width_array", false]], "begin_thinking_phase_token (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.MTPDecodingConfig.BEGIN_THINKING_PHASE_TOKEN", false]], "bert_attention() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.bert_attention", false]], "bertattention (class in tensorrt_llm.layers.attention)": [[81, "tensorrt_llm.layers.attention.BertAttention", false]], "bertforquestionanswering (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.BertForQuestionAnswering", false]], "bertforsequenceclassification (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.BertForSequenceClassification", false]], "bertmodel (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.BertModel", false]], "best_of (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.best_of", false]], "bidirectional (tensorrt_llm.functional.attentionmasktype attribute)": [[80, "tensorrt_llm.functional.AttentionMaskType.bidirectional", false]], "bidirectionalglm (tensorrt_llm.functional.attentionmasktype attribute)": [[80, "tensorrt_llm.functional.AttentionMaskType.bidirectionalglm", false]], "blocksparse (tensorrt_llm.functional.attentionmasktype attribute)": [[80, "tensorrt_llm.functional.AttentionMaskType.blocksparse", false]], "blocksparseattnparams (class in tensorrt_llm.layers.attention)": [[81, "tensorrt_llm.layers.attention.BlockSparseAttnParams", false]], "bloomforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.BloomForCausalLM", false]], "bloommodel (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.BloomModel", false]], "broadcast_helper() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.broadcast_helper", false]], "buffer_allocated (tensorrt_llm.runtime.generationsession attribute)": [[85, "tensorrt_llm.runtime.GenerationSession.buffer_allocated", false]], "build_config (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.build_config", false]], "build_config (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.build_config", false]], "buildcacheconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.BuildCacheConfig", false]], "buildconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.BuildConfig", false]], "cache_root (tensorrt_llm.llmapi.buildcacheconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildCacheConfig.cache_root", false]], "cache_root (tensorrt_llm.llmapi.buildcacheconfig property)": [[68, "id7", false]], "cachetransceiverconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.CacheTransceiverConfig", false]], "calculate_speculative_resource() (tensorrt_llm.llmapi.lookaheaddecodingconfig method)": [[68, "tensorrt_llm.llmapi.LookaheadDecodingConfig.calculate_speculative_resource", false]], "calib_batch_size (tensorrt_llm.llmapi.calibconfig attribute)": [[68, "tensorrt_llm.llmapi.CalibConfig.calib_batch_size", false]], "calib_batches (tensorrt_llm.llmapi.calibconfig attribute)": [[68, "tensorrt_llm.llmapi.CalibConfig.calib_batches", false]], "calib_config (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.calib_config", false]], "calib_dataset (tensorrt_llm.llmapi.calibconfig attribute)": [[68, "tensorrt_llm.llmapi.CalibConfig.calib_dataset", false]], "calib_max_seq_length (tensorrt_llm.llmapi.calibconfig attribute)": [[68, "tensorrt_llm.llmapi.CalibConfig.calib_max_seq_length", false]], "calibconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.CalibConfig", false]], "capacity_scheduler_policy (tensorrt_llm.llmapi.schedulerconfig attribute)": [[68, "tensorrt_llm.llmapi.SchedulerConfig.capacity_scheduler_policy", false]], "capacityschedulerpolicy (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.CapacitySchedulerPolicy", false]], "cast (class in tensorrt_llm.layers.cast)": [[81, "tensorrt_llm.layers.cast.Cast", false]], "cast() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.cast", false]], "cast() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.cast", false]], "categorical_sample() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.categorical_sample", false]], "causal (tensorrt_llm.functional.attentionmasktype attribute)": [[80, "tensorrt_llm.functional.AttentionMaskType.causal", false]], "chatglm (tensorrt_llm.functional.positionembeddingtype attribute)": [[80, "tensorrt_llm.functional.PositionEmbeddingType.chatglm", false]], "chatglmconfig (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.ChatGLMConfig", false]], "chatglmforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.ChatGLMForCausalLM", false]], "chatglmgenerationsession (class in tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.ChatGLMGenerationSession", false]], "chatglmmodel (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.ChatGLMModel", false]], "check_config() (tensorrt_llm.models.decodermodel method)": [[82, "tensorrt_llm.models.DecoderModel.check_config", false]], "check_config() (tensorrt_llm.models.dit method)": [[82, "tensorrt_llm.models.DiT.check_config", false]], "check_config() (tensorrt_llm.models.encodermodel method)": [[82, "tensorrt_llm.models.EncoderModel.check_config", false]], "check_config() (tensorrt_llm.models.falconforcausallm method)": [[82, "tensorrt_llm.models.FalconForCausalLM.check_config", false]], "check_config() (tensorrt_llm.models.mptforcausallm method)": [[82, "tensorrt_llm.models.MPTForCausalLM.check_config", false]], "check_config() (tensorrt_llm.models.optforcausallm method)": [[82, "tensorrt_llm.models.OPTForCausalLM.check_config", false]], "check_config() (tensorrt_llm.models.phiforcausallm method)": [[82, "tensorrt_llm.models.PhiForCausalLM.check_config", false]], "check_config() (tensorrt_llm.models.pretrainedmodel method)": [[82, "tensorrt_llm.models.PretrainedModel.check_config", false]], "choices() (tensorrt_llm.functional.positionembeddingtype static method)": [[80, "tensorrt_llm.functional.PositionEmbeddingType.choices", false]], "chunk() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.chunk", false]], "clamp_val (tensorrt_llm.llmapi.quantconfig attribute)": [[68, "tensorrt_llm.llmapi.QuantConfig.clamp_val", false]], "clip() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.clip", false]], "clipvisiontransformer (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.CLIPVisionTransformer", false]], "cogvlmattention (class in tensorrt_llm.layers.attention)": [[81, "tensorrt_llm.layers.attention.CogVLMAttention", false]], "cogvlmconfig (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.CogVLMConfig", false]], "cogvlmforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.CogVLMForCausalLM", false]], "cohereforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.CohereForCausalLM", false]], "collect_and_bias() (tensorrt_llm.layers.linear.linear method)": [[81, "tensorrt_llm.layers.linear.Linear.collect_and_bias", false]], "collect_and_bias() (tensorrt_llm.layers.linear.linearbase method)": [[81, "tensorrt_llm.layers.linear.LinearBase.collect_and_bias", false]], "collect_and_bias() (tensorrt_llm.layers.linear.rowlinear method)": [[81, "tensorrt_llm.layers.linear.RowLinear.collect_and_bias", false]], "columnlinear (in module tensorrt_llm.layers.linear)": [[81, "tensorrt_llm.layers.linear.ColumnLinear", false]], "combinedtimesteplabelembeddings (class in tensorrt_llm.layers.embedding)": [[81, "tensorrt_llm.layers.embedding.CombinedTimestepLabelEmbeddings", false]], "combinedtimesteptextprojembeddings (class in tensorrt_llm.layers.embedding)": [[81, "tensorrt_llm.layers.embedding.CombinedTimestepTextProjEmbeddings", false]], "completionoutput (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.CompletionOutput", false]], "compute_relative_bias() (in module tensorrt_llm.layers.attention)": [[81, "tensorrt_llm.layers.attention.compute_relative_bias", false]], "concat() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.concat", false]], "conditional (class in tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.Conditional", false]], "config_class (tensorrt_llm.models.baichuanforcausallm attribute)": [[82, "tensorrt_llm.models.BaichuanForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.chatglmforcausallm attribute)": [[82, "tensorrt_llm.models.ChatGLMForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.cogvlmforcausallm attribute)": [[82, "tensorrt_llm.models.CogVLMForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.cohereforcausallm attribute)": [[82, "tensorrt_llm.models.CohereForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.dbrxforcausallm attribute)": [[82, "tensorrt_llm.models.DbrxForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.deepseekforcausallm attribute)": [[82, "tensorrt_llm.models.DeepseekForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.deepseekv2forcausallm attribute)": [[82, "tensorrt_llm.models.DeepseekV2ForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.eagleforcausallm attribute)": [[82, "tensorrt_llm.models.EagleForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.falconforcausallm attribute)": [[82, "tensorrt_llm.models.FalconForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.gemmaforcausallm attribute)": [[82, "tensorrt_llm.models.GemmaForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.gptforcausallm attribute)": [[82, "tensorrt_llm.models.GPTForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.gptjforcausallm attribute)": [[82, "tensorrt_llm.models.GPTJForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.llamaforcausallm attribute)": [[82, "tensorrt_llm.models.LLaMAForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.mambaforcausallm attribute)": [[82, "tensorrt_llm.models.MambaForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.medusaforcausallm attribute)": [[82, "tensorrt_llm.models.MedusaForCausalLm.config_class", false]], "config_class (tensorrt_llm.models.mllamaforcausallm attribute)": [[82, "tensorrt_llm.models.MLLaMAForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.phi3forcausallm attribute)": [[82, "tensorrt_llm.models.Phi3ForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.phiforcausallm attribute)": [[82, "tensorrt_llm.models.PhiForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.sd3transformer2dmodel attribute)": [[82, "tensorrt_llm.models.SD3Transformer2DModel.config_class", false]], "constant() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.constant", false]], "constant_to_tensor_() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.constant_to_tensor_", false]], "constants_to_tensors_() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.constants_to_tensors_", false]], "context (tensorrt_llm.runtime.session property)": [[85, "tensorrt_llm.runtime.Session.context", false]], "context_chunking_policy (tensorrt_llm.llmapi.schedulerconfig attribute)": [[68, "tensorrt_llm.llmapi.SchedulerConfig.context_chunking_policy", false]], "context_logits (tensorrt_llm.llmapi.requestoutput attribute)": [[68, "tensorrt_llm.llmapi.RequestOutput.context_logits", false]], "context_mem_size (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.context_mem_size", false]], "context_mem_size (tensorrt_llm.runtime.session property)": [[85, "tensorrt_llm.runtime.Session.context_mem_size", false]], "contextchunkingpolicy (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.ContextChunkingPolicy", false]], "conv1d (class in tensorrt_llm.layers.conv)": [[81, "tensorrt_llm.layers.conv.Conv1d", false]], "conv1d() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.conv1d", false]], "conv2d (class in tensorrt_llm.layers.conv)": [[81, "tensorrt_llm.layers.conv.Conv2d", false]], "conv2d() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.conv2d", false]], "conv3d (class in tensorrt_llm.layers.conv)": [[81, "tensorrt_llm.layers.conv.Conv3d", false]], "conv3d() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.conv3d", false]], "conv_kernel (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.conv_kernel", false]], "conv_kernel (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.conv_kernel", false]], "conv_transpose2d() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.conv_transpose2d", false]], "convert_load_format() (tensorrt_llm.llmapi.torchllmargs class method)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.convert_load_format", false]], "convtranspose2d (class in tensorrt_llm.layers.conv)": [[81, "tensorrt_llm.layers.conv.ConvTranspose2d", false]], "copy_on_partial_reuse (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[68, "tensorrt_llm.llmapi.KvCacheConfig.copy_on_partial_reuse", false]], "cos() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.cos", false]], "cp_split_plugin() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.cp_split_plugin", false]], "cpp_e2e (tensorrt_llm.runtime.multimodalmodelrunner property)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.cpp_e2e", false]], "cpp_llm_only (tensorrt_llm.runtime.multimodalmodelrunner property)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.cpp_llm_only", false]], "create_allreduce_plugin() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.create_allreduce_plugin", false]], "create_attention_const_params() (tensorrt_llm.layers.attention.attention static method)": [[81, "tensorrt_llm.layers.attention.Attention.create_attention_const_params", false]], "create_fake_weight() (tensorrt_llm.functional.ropeembeddingutils static method)": [[80, "tensorrt_llm.functional.RopeEmbeddingUtils.create_fake_weight", false]], "create_runtime_defaults() (tensorrt_llm.models.pretrainedconfig static method)": [[82, "tensorrt_llm.models.PretrainedConfig.create_runtime_defaults", false]], "create_sinusoidal_positions() (tensorrt_llm.functional.ropeembeddingutils static method)": [[80, "tensorrt_llm.functional.RopeEmbeddingUtils.create_sinusoidal_positions", false]], "create_sinusoidal_positions_for_attention_plugin() (tensorrt_llm.functional.ropeembeddingutils static method)": [[80, "tensorrt_llm.functional.RopeEmbeddingUtils.create_sinusoidal_positions_for_attention_plugin", false]], "create_sinusoidal_positions_for_cogvlm_attention_plugin() (tensorrt_llm.functional.ropeembeddingutils static method)": [[80, "tensorrt_llm.functional.RopeEmbeddingUtils.create_sinusoidal_positions_for_cogvlm_attention_plugin", false]], "create_sinusoidal_positions_long_rope() (tensorrt_llm.functional.ropeembeddingutils method)": [[80, "tensorrt_llm.functional.RopeEmbeddingUtils.create_sinusoidal_positions_long_rope", false]], "create_sinusoidal_positions_yarn() (tensorrt_llm.functional.ropeembeddingutils static method)": [[80, "tensorrt_llm.functional.RopeEmbeddingUtils.create_sinusoidal_positions_yarn", false]], "cropped_pos_embed() (tensorrt_llm.layers.embedding.sd3patchembed method)": [[81, "tensorrt_llm.layers.embedding.SD3PatchEmbed.cropped_pos_embed", false]], "cross_attention (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.cross_attention", false]], "cross_attention (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.cross_attention", false]], "cross_kv_cache_fraction (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[68, "tensorrt_llm.llmapi.KvCacheConfig.cross_kv_cache_fraction", false]], "ctx_request_id (tensorrt_llm.llmapi.disaggregatedparams attribute)": [[68, "tensorrt_llm.llmapi.DisaggregatedParams.ctx_request_id", false]], "cuda_graph_cache_size (tensorrt_llm.llmapi.extendedruntimeperfknobconfig attribute)": [[68, "tensorrt_llm.llmapi.ExtendedRuntimePerfKnobConfig.cuda_graph_cache_size", false]], "cuda_graph_config (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.cuda_graph_config", false]], "cuda_graph_mode (tensorrt_llm.llmapi.extendedruntimeperfknobconfig attribute)": [[68, "tensorrt_llm.llmapi.ExtendedRuntimePerfKnobConfig.cuda_graph_mode", false]], "cuda_graph_mode (tensorrt_llm.runtime.generationsession attribute)": [[85, "tensorrt_llm.runtime.GenerationSession.cuda_graph_mode", false]], "cuda_stream_guard() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.cuda_stream_guard", false]], "cuda_stream_sync() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.cuda_stream_sync", false]], "cudagraphconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.CudaGraphConfig", false]], "cumsum() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.cumsum", false]], "cumulative_logprob (tensorrt_llm.llmapi.completionoutput attribute)": [[68, "tensorrt_llm.llmapi.CompletionOutput.cumulative_logprob", false]], "custom_mask (tensorrt_llm.functional.attentionmasktype attribute)": [[80, "tensorrt_llm.functional.AttentionMaskType.custom_mask", false]], "data (tensorrt_llm.functional.sliceinputtype attribute)": [[80, "tensorrt_llm.functional.SliceInputType.data", false]], "dbrxconfig (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.DbrxConfig", false]], "dbrxforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.DbrxForCausalLM", false]], "debug_mode (tensorrt_llm.runtime.generationsession attribute)": [[85, "tensorrt_llm.runtime.GenerationSession.debug_mode", false]], "debug_tensors_to_save (tensorrt_llm.runtime.generationsession attribute)": [[85, "tensorrt_llm.runtime.GenerationSession.debug_tensors_to_save", false]], "decode() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.decode", false]], "decode_batch() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.decode_batch", false]], "decode_duration_ms (tensorrt_llm.llmapi.kvcacheretentionconfig property)": [[68, "tensorrt_llm.llmapi.KvCacheRetentionConfig.decode_duration_ms", false]], "decode_regular() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.decode_regular", false]], "decode_retention_priority (tensorrt_llm.llmapi.kvcacheretentionconfig property)": [[68, "tensorrt_llm.llmapi.KvCacheRetentionConfig.decode_retention_priority", false]], "decode_stream() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.decode_stream", false]], "decode_words_list() (in module tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.decode_words_list", false]], "decodermodel (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.DecoderModel", false]], "decoding_config (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.decoding_config", false]], "decoding_config (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.decoding_config", false]], "decoding_type (tensorrt_llm.llmapi.drafttargetdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.DraftTargetDecodingConfig.decoding_type", false]], "decoding_type (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.EagleDecodingConfig.decoding_type", false]], "decoding_type (tensorrt_llm.llmapi.lookaheaddecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.LookaheadDecodingConfig.decoding_type", false]], "decoding_type (tensorrt_llm.llmapi.medusadecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.MedusaDecodingConfig.decoding_type", false]], "decoding_type (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.MTPDecodingConfig.decoding_type", false]], "decoding_type (tensorrt_llm.llmapi.ngramdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.NGramDecodingConfig.decoding_type", false]], "decoding_type (tensorrt_llm.llmapi.userprovideddecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.UserProvidedDecodingConfig.decoding_type", false]], "deepseekforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.DeepseekForCausalLM", false]], "deepseekv2attention (class in tensorrt_llm.layers.attention)": [[81, "tensorrt_llm.layers.attention.DeepseekV2Attention", false]], "deepseekv2forcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.DeepseekV2ForCausalLM", false]], "default_plugin_config() (tensorrt_llm.models.cogvlmforcausallm method)": [[82, "tensorrt_llm.models.CogVLMForCausalLM.default_plugin_config", false]], "default_plugin_config() (tensorrt_llm.models.llamaforcausallm method)": [[82, "tensorrt_llm.models.LLaMAForCausalLM.default_plugin_config", false]], "deferred (tensorrt_llm.functional.positionembeddingtype attribute)": [[80, "tensorrt_llm.functional.PositionEmbeddingType.deferred", false]], "detokenize (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.detokenize", false]], "device (tensorrt_llm.llmapi.calibconfig attribute)": [[68, "tensorrt_llm.llmapi.CalibConfig.device", false]], "device (tensorrt_llm.runtime.generationsession attribute)": [[85, "tensorrt_llm.runtime.GenerationSession.device", false]], "diffusersattention (class in tensorrt_llm.layers.attention)": [[81, "tensorrt_llm.layers.attention.DiffusersAttention", false]], "dimrange (class in tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.DimRange", false]], "directory (tensorrt_llm.llmapi.kvcacheretentionconfig property)": [[68, "tensorrt_llm.llmapi.KvCacheRetentionConfig.directory", false]], "disable (tensorrt_llm.functional.sidestreamidtype attribute)": [[80, "tensorrt_llm.functional.SideStreamIDType.disable", false]], "disable_forward_chunking() (tensorrt_llm.models.sd3transformer2dmodel method)": [[82, "tensorrt_llm.models.SD3Transformer2DModel.disable_forward_chunking", false]], "disable_overlap_scheduler (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.disable_overlap_scheduler", false]], "disaggregated_params (tensorrt_llm.llmapi.completionoutput attribute)": [[68, "tensorrt_llm.llmapi.CompletionOutput.disaggregated_params", false]], "disaggregatedparams (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.DisaggregatedParams", false]], "dit (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.DiT", false]], "div() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.div", false]], "dora_plugin() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.dora_plugin", false]], "draft_tokens (tensorrt_llm.llmapi.disaggregatedparams attribute)": [[68, "tensorrt_llm.llmapi.DisaggregatedParams.draft_tokens", false]], "draft_tokens_external (tensorrt_llm.models.speculativedecodingmode attribute)": [[82, "tensorrt_llm.models.SpeculativeDecodingMode.DRAFT_TOKENS_EXTERNAL", false]], "drafter (tensorrt_llm.llmapi.userprovideddecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.UserProvidedDecodingConfig.drafter", false]], "drafttargetdecodingconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.DraftTargetDecodingConfig", false]], "dry_run (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.dry_run", false]], "dtype (tensorrt_llm.functional.tensor property)": [[80, "tensorrt_llm.functional.Tensor.dtype", false]], "dtype (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.dtype", false]], "dtype (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.dtype", false]], "dtype (tensorrt_llm.runtime.modelrunner property)": [[85, "tensorrt_llm.runtime.ModelRunner.dtype", false]], "dtype (tensorrt_llm.runtime.modelrunnercpp property)": [[85, "tensorrt_llm.runtime.ModelRunnerCpp.dtype", false]], "dtype (tensorrt_llm.runtime.tensorinfo attribute)": [[85, "tensorrt_llm.runtime.TensorInfo.dtype", false]], "dump_debug_buffers() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.dump_debug_buffers", false]], "duration_ms (tensorrt_llm.llmapi.kvcacheretentionconfig.tokenrangeretentionconfig property)": [[68, "tensorrt_llm.llmapi.KvCacheRetentionConfig.TokenRangeRetentionConfig.duration_ms", false]], "dynamic (tensorrt_llm.functional.rotaryscalingtype attribute)": [[80, "tensorrt_llm.functional.RotaryScalingType.dynamic", false]], "dynamic_batch_config (tensorrt_llm.llmapi.schedulerconfig attribute)": [[68, "tensorrt_llm.llmapi.SchedulerConfig.dynamic_batch_config", false]], "dynamic_batch_moving_average_window (tensorrt_llm.llmapi.dynamicbatchconfig attribute)": [[68, "tensorrt_llm.llmapi.DynamicBatchConfig.dynamic_batch_moving_average_window", false]], "dynamic_tree_max_topk (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.EagleDecodingConfig.dynamic_tree_max_topK", false]], "dynamicbatchconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.DynamicBatchConfig", false]], "eagle (tensorrt_llm.models.speculativedecodingmode attribute)": [[82, "tensorrt_llm.models.SpeculativeDecodingMode.EAGLE", false]], "eagle3_one_model (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.EagleDecodingConfig.eagle3_one_model", false]], "eagle_choices (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.EagleDecodingConfig.eagle_choices", false]], "eagledecodingconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.EagleDecodingConfig", false]], "eagleforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.EagleForCausalLM", false]], "early_stop_criteria() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.early_stop_criteria", false]], "early_stopping (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.early_stopping", false]], "early_stopping (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.early_stopping", false]], "einsum() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.einsum", false]], "elementwise_binary() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.elementwise_binary", false]], "embedding (class in tensorrt_llm.layers.embedding)": [[81, "tensorrt_llm.layers.embedding.Embedding", false]], "embedding() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.embedding", false]], "embedding_bias (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.embedding_bias", false]], "embedding_parallel_mode (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.embedding_parallel_mode", false]], "enable_autotuner (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.enable_autotuner", false]], "enable_batch_size_tuning (tensorrt_llm.llmapi.dynamicbatchconfig attribute)": [[68, "tensorrt_llm.llmapi.DynamicBatchConfig.enable_batch_size_tuning", false]], "enable_block_reuse (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[68, "tensorrt_llm.llmapi.KvCacheConfig.enable_block_reuse", false]], "enable_build_cache (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.enable_build_cache", false]], "enable_context_fmha_fp32_acc (tensorrt_llm.llmapi.extendedruntimeperfknobconfig attribute)": [[68, "tensorrt_llm.llmapi.ExtendedRuntimePerfKnobConfig.enable_context_fmha_fp32_acc", false]], "enable_debug_output (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.enable_debug_output", false]], "enable_forward_chunking() (tensorrt_llm.models.sd3transformer2dmodel method)": [[82, "tensorrt_llm.models.SD3Transformer2DModel.enable_forward_chunking", false]], "enable_fullgraph (tensorrt_llm.llmapi.torchcompileconfig attribute)": [[68, "tensorrt_llm.llmapi.TorchCompileConfig.enable_fullgraph", false]], "enable_inductor (tensorrt_llm.llmapi.torchcompileconfig attribute)": [[68, "tensorrt_llm.llmapi.TorchCompileConfig.enable_inductor", false]], "enable_iter_perf_stats (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.enable_iter_perf_stats", false]], "enable_iter_req_stats (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.enable_iter_req_stats", false]], "enable_layerwise_nvtx_marker (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.enable_layerwise_nvtx_marker", false]], "enable_max_num_tokens_tuning (tensorrt_llm.llmapi.dynamicbatchconfig attribute)": [[68, "tensorrt_llm.llmapi.DynamicBatchConfig.enable_max_num_tokens_tuning", false]], "enable_min_latency (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.enable_min_latency", false]], "enable_mixed_sampler (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.enable_mixed_sampler", false]], "enable_partial_reuse (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[68, "tensorrt_llm.llmapi.KvCacheConfig.enable_partial_reuse", false]], "enable_piecewise_cuda_graph (tensorrt_llm.llmapi.torchcompileconfig attribute)": [[68, "tensorrt_llm.llmapi.TorchCompileConfig.enable_piecewise_cuda_graph", false]], "enable_prompt_adapter (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.enable_prompt_adapter", false]], "enable_tqdm (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.enable_tqdm", false]], "enable_trtllm_sampler (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.enable_trtllm_sampler", false]], "enable_userbuffers (tensorrt_llm.llmapi.torchcompileconfig attribute)": [[68, "tensorrt_llm.llmapi.TorchCompileConfig.enable_userbuffers", false]], "encdecmodelrunner (class in tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.EncDecModelRunner", false]], "encoder_run() (tensorrt_llm.runtime.encdecmodelrunner method)": [[85, "tensorrt_llm.runtime.EncDecModelRunner.encoder_run", false]], "encodermodel (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.EncoderModel", false]], "end_id (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.end_id", false]], "end_id (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.end_id", false]], "end_thinking_phase_token (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.MTPDecodingConfig.END_THINKING_PHASE_TOKEN", false]], "engine (tensorrt_llm.runtime.session property)": [[85, "tensorrt_llm.runtime.Session.engine", false]], "engine_inspector (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.engine_inspector", false]], "eq() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.eq", false]], "equal_progress (tensorrt_llm.llmapi.contextchunkingpolicy attribute)": [[68, "tensorrt_llm.llmapi.ContextChunkingPolicy.EQUAL_PROGRESS", false]], "event_buffer_max_size (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[68, "tensorrt_llm.llmapi.KvCacheConfig.event_buffer_max_size", false]], "exclude_input_from_output (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.exclude_input_from_output", false]], "exclude_modules (tensorrt_llm.llmapi.quantconfig attribute)": [[68, "tensorrt_llm.llmapi.QuantConfig.exclude_modules", false]], "exp() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.exp", false]], "expand() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.expand", false]], "expand_dims() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.expand_dims", false]], "expand_dims_like() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.expand_dims_like", false]], "expand_mask() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.expand_mask", false]], "explicit_draft_tokens (tensorrt_llm.models.speculativedecodingmode attribute)": [[82, "tensorrt_llm.models.SpeculativeDecodingMode.EXPLICIT_DRAFT_TOKENS", false]], "extended_runtime_perf_knob_config (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.extended_runtime_perf_knob_config", false]], "extendedruntimeperfknobconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.ExtendedRuntimePerfKnobConfig", false]], "extra_resource_managers (tensorrt_llm.llmapi.torchllmargs property)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.extra_resource_managers", false]], "falconconfig (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.FalconConfig", false]], "falconforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.FalconForCausalLM", false]], "falconmodel (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.FalconModel", false]], "fast_build (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.fast_build", false]], "fc_gate() (tensorrt_llm.layers.mlp.fusedgatedmlp method)": [[81, "tensorrt_llm.layers.mlp.FusedGatedMLP.fc_gate", false]], "fc_gate_dora() (in module tensorrt_llm.layers.mlp)": [[81, "tensorrt_llm.layers.mlp.fc_gate_dora", false]], "fc_gate_lora() (in module tensorrt_llm.layers.mlp)": [[81, "tensorrt_llm.layers.mlp.fc_gate_lora", false]], "fc_gate_plugin() (tensorrt_llm.layers.mlp.fusedgatedmlp method)": [[81, "tensorrt_llm.layers.mlp.FusedGatedMLP.fc_gate_plugin", false]], "field_name (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "id12", false], [68, "id15", false], [68, "id18", false], [68, "tensorrt_llm.llmapi.TorchLlmArgs.field_name", false]], "field_name (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "id21", false], [68, "id24", false], [68, "id27", false], [68, "id30", false], [68, "id33", false], [68, "tensorrt_llm.llmapi.TrtLlmArgs.field_name", false]], "fill_attention_const_params_for_long_rope() (tensorrt_llm.layers.attention.attentionparams method)": [[81, "tensorrt_llm.layers.attention.AttentionParams.fill_attention_const_params_for_long_rope", false]], "fill_attention_const_params_for_rope() (tensorrt_llm.layers.attention.attentionparams method)": [[81, "tensorrt_llm.layers.attention.AttentionParams.fill_attention_const_params_for_rope", false]], "fill_attention_params() (tensorrt_llm.layers.attention.attention static method)": [[81, "tensorrt_llm.layers.attention.Attention.fill_attention_params", false]], "fill_none_tensor_list() (tensorrt_llm.layers.attention.keyvaluecacheparams method)": [[81, "tensorrt_llm.layers.attention.KeyValueCacheParams.fill_none_tensor_list", false]], "fill_value (tensorrt_llm.functional.sliceinputtype attribute)": [[80, "tensorrt_llm.functional.SliceInputType.fill_value", false]], "filter_medusa_logits() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.filter_medusa_logits", false]], "finalize_decoder() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.finalize_decoder", false]], "find_best_medusa_path() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.find_best_medusa_path", false]], "finish_reason (tensorrt_llm.llmapi.completionoutput attribute)": [[68, "tensorrt_llm.llmapi.CompletionOutput.finish_reason", false]], "finished (tensorrt_llm.llmapi.requestoutput attribute)": [[68, "tensorrt_llm.llmapi.RequestOutput.finished", false]], "first_come_first_served (tensorrt_llm.llmapi.contextchunkingpolicy attribute)": [[68, "tensorrt_llm.llmapi.ContextChunkingPolicy.FIRST_COME_FIRST_SERVED", false]], "first_gen_tokens (tensorrt_llm.llmapi.disaggregatedparams attribute)": [[68, "tensorrt_llm.llmapi.DisaggregatedParams.first_gen_tokens", false]], "first_layer (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.first_layer", false]], "flatten() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.flatten", false]], "flatten() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.flatten", false]], "flip() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.flip", false]], "floordiv() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.floordiv", false]], "fmt_dim (c macro)": [[1, "c.FMT_DIM", false]], "for_each_rank() (tensorrt_llm.models.pretrainedconfig method)": [[82, "tensorrt_llm.models.PretrainedConfig.for_each_rank", false]], "force_dynamic_quantization (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.force_dynamic_quantization", false]], "force_num_profiles (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.force_num_profiles", false]], "forward() (tensorrt_llm.layers.activation.mish method)": [[81, "tensorrt_llm.layers.activation.Mish.forward", false]], "forward() (tensorrt_llm.layers.attention.attention method)": [[81, "tensorrt_llm.layers.attention.Attention.forward", false]], "forward() (tensorrt_llm.layers.attention.bertattention method)": [[81, "tensorrt_llm.layers.attention.BertAttention.forward", false]], "forward() (tensorrt_llm.layers.attention.cogvlmattention method)": [[81, "tensorrt_llm.layers.attention.CogVLMAttention.forward", false]], "forward() (tensorrt_llm.layers.attention.deepseekv2attention method)": [[81, "tensorrt_llm.layers.attention.DeepseekV2Attention.forward", false]], "forward() (tensorrt_llm.layers.attention.diffusersattention method)": [[81, "tensorrt_llm.layers.attention.DiffusersAttention.forward", false]], "forward() (tensorrt_llm.layers.cast.cast method)": [[81, "tensorrt_llm.layers.cast.Cast.forward", false]], "forward() (tensorrt_llm.layers.conv.conv1d method)": [[81, "tensorrt_llm.layers.conv.Conv1d.forward", false]], "forward() (tensorrt_llm.layers.conv.conv2d method)": [[81, "tensorrt_llm.layers.conv.Conv2d.forward", false]], "forward() (tensorrt_llm.layers.conv.conv3d method)": [[81, "tensorrt_llm.layers.conv.Conv3d.forward", false]], "forward() (tensorrt_llm.layers.conv.convtranspose2d method)": [[81, "tensorrt_llm.layers.conv.ConvTranspose2d.forward", false]], "forward() (tensorrt_llm.layers.embedding.combinedtimesteplabelembeddings method)": [[81, "tensorrt_llm.layers.embedding.CombinedTimestepLabelEmbeddings.forward", false]], "forward() (tensorrt_llm.layers.embedding.combinedtimesteptextprojembeddings method)": [[81, "tensorrt_llm.layers.embedding.CombinedTimestepTextProjEmbeddings.forward", false]], "forward() (tensorrt_llm.layers.embedding.embedding method)": [[81, "tensorrt_llm.layers.embedding.Embedding.forward", false]], "forward() (tensorrt_llm.layers.embedding.labelembedding method)": [[81, "tensorrt_llm.layers.embedding.LabelEmbedding.forward", false]], "forward() (tensorrt_llm.layers.embedding.pixartalphatextprojection method)": [[81, "tensorrt_llm.layers.embedding.PixArtAlphaTextProjection.forward", false]], "forward() (tensorrt_llm.layers.embedding.prompttuningembedding method)": [[81, "tensorrt_llm.layers.embedding.PromptTuningEmbedding.forward", false]], "forward() (tensorrt_llm.layers.embedding.sd3patchembed method)": [[81, "tensorrt_llm.layers.embedding.SD3PatchEmbed.forward", false]], "forward() (tensorrt_llm.layers.embedding.timestepembedding method)": [[81, "tensorrt_llm.layers.embedding.TimestepEmbedding.forward", false]], "forward() (tensorrt_llm.layers.embedding.timesteps method)": [[81, "tensorrt_llm.layers.embedding.Timesteps.forward", false]], "forward() (tensorrt_llm.layers.linear.linearbase method)": [[81, "tensorrt_llm.layers.linear.LinearBase.forward", false]], "forward() (tensorrt_llm.layers.mlp.fusedgatedmlp method)": [[81, "tensorrt_llm.layers.mlp.FusedGatedMLP.forward", false]], "forward() (tensorrt_llm.layers.mlp.gatedmlp method)": [[81, "tensorrt_llm.layers.mlp.GatedMLP.forward", false]], "forward() (tensorrt_llm.layers.mlp.linearactivation method)": [[81, "tensorrt_llm.layers.mlp.LinearActivation.forward", false]], "forward() (tensorrt_llm.layers.mlp.linearapproximategelu method)": [[81, "tensorrt_llm.layers.mlp.LinearApproximateGELU.forward", false]], "forward() (tensorrt_llm.layers.mlp.lineargeglu method)": [[81, "tensorrt_llm.layers.mlp.LinearGEGLU.forward", false]], "forward() (tensorrt_llm.layers.mlp.lineargelu method)": [[81, "tensorrt_llm.layers.mlp.LinearGELU.forward", false]], "forward() (tensorrt_llm.layers.mlp.linearswiglu method)": [[81, "tensorrt_llm.layers.mlp.LinearSwiGLU.forward", false]], "forward() (tensorrt_llm.layers.mlp.mlp method)": [[81, "tensorrt_llm.layers.mlp.MLP.forward", false]], "forward() (tensorrt_llm.layers.normalization.adalayernorm method)": [[81, "tensorrt_llm.layers.normalization.AdaLayerNorm.forward", false]], "forward() (tensorrt_llm.layers.normalization.adalayernormcontinuous method)": [[81, "tensorrt_llm.layers.normalization.AdaLayerNormContinuous.forward", false]], "forward() (tensorrt_llm.layers.normalization.adalayernormzero method)": [[81, "tensorrt_llm.layers.normalization.AdaLayerNormZero.forward", false]], "forward() (tensorrt_llm.layers.normalization.adalayernormzerosingle method)": [[81, "tensorrt_llm.layers.normalization.AdaLayerNormZeroSingle.forward", false]], "forward() (tensorrt_llm.layers.normalization.groupnorm method)": [[81, "tensorrt_llm.layers.normalization.GroupNorm.forward", false]], "forward() (tensorrt_llm.layers.normalization.layernorm method)": [[81, "tensorrt_llm.layers.normalization.LayerNorm.forward", false]], "forward() (tensorrt_llm.layers.normalization.rmsnorm method)": [[81, "tensorrt_llm.layers.normalization.RmsNorm.forward", false]], "forward() (tensorrt_llm.layers.normalization.sd35adalayernormzerox method)": [[81, "tensorrt_llm.layers.normalization.SD35AdaLayerNormZeroX.forward", false]], "forward() (tensorrt_llm.layers.pooling.avgpool2d method)": [[81, "tensorrt_llm.layers.pooling.AvgPool2d.forward", false]], "forward() (tensorrt_llm.models.bertforquestionanswering method)": [[82, "tensorrt_llm.models.BertForQuestionAnswering.forward", false]], "forward() (tensorrt_llm.models.bertforsequenceclassification method)": [[82, "tensorrt_llm.models.BertForSequenceClassification.forward", false]], "forward() (tensorrt_llm.models.bertmodel method)": [[82, "tensorrt_llm.models.BertModel.forward", false]], "forward() (tensorrt_llm.models.bloommodel method)": [[82, "tensorrt_llm.models.BloomModel.forward", false]], "forward() (tensorrt_llm.models.chatglmmodel method)": [[82, "tensorrt_llm.models.ChatGLMModel.forward", false]], "forward() (tensorrt_llm.models.clipvisiontransformer method)": [[82, "tensorrt_llm.models.CLIPVisionTransformer.forward", false]], "forward() (tensorrt_llm.models.decodermodel method)": [[82, "tensorrt_llm.models.DecoderModel.forward", false]], "forward() (tensorrt_llm.models.dit method)": [[82, "tensorrt_llm.models.DiT.forward", false]], "forward() (tensorrt_llm.models.eagleforcausallm method)": [[82, "tensorrt_llm.models.EagleForCausalLM.forward", false]], "forward() (tensorrt_llm.models.encodermodel method)": [[82, "tensorrt_llm.models.EncoderModel.forward", false]], "forward() (tensorrt_llm.models.falconmodel method)": [[82, "tensorrt_llm.models.FalconModel.forward", false]], "forward() (tensorrt_llm.models.gptjmodel method)": [[82, "tensorrt_llm.models.GPTJModel.forward", false]], "forward() (tensorrt_llm.models.gptmodel method)": [[82, "tensorrt_llm.models.GPTModel.forward", false]], "forward() (tensorrt_llm.models.gptneoxmodel method)": [[82, "tensorrt_llm.models.GPTNeoXModel.forward", false]], "forward() (tensorrt_llm.models.llamamodel method)": [[82, "tensorrt_llm.models.LLaMAModel.forward", false]], "forward() (tensorrt_llm.models.llavanextvisionwrapper method)": [[82, "tensorrt_llm.models.LlavaNextVisionWrapper.forward", false]], "forward() (tensorrt_llm.models.mambaforcausallm method)": [[82, "tensorrt_llm.models.MambaForCausalLM.forward", false]], "forward() (tensorrt_llm.models.mllamaforcausallm method)": [[82, "tensorrt_llm.models.MLLaMAForCausalLM.forward", false]], "forward() (tensorrt_llm.models.mptmodel method)": [[82, "tensorrt_llm.models.MPTModel.forward", false]], "forward() (tensorrt_llm.models.optmodel method)": [[82, "tensorrt_llm.models.OPTModel.forward", false]], "forward() (tensorrt_llm.models.phi3model method)": [[82, "tensorrt_llm.models.Phi3Model.forward", false]], "forward() (tensorrt_llm.models.phimodel method)": [[82, "tensorrt_llm.models.PhiModel.forward", false]], "forward() (tensorrt_llm.models.recurrentgemmaforcausallm method)": [[82, "tensorrt_llm.models.RecurrentGemmaForCausalLM.forward", false]], "forward() (tensorrt_llm.models.sd3transformer2dmodel method)": [[82, "tensorrt_llm.models.SD3Transformer2DModel.forward", false]], "forward() (tensorrt_llm.models.whisperencoder method)": [[82, "tensorrt_llm.models.WhisperEncoder.forward", false]], "forward_with_cfg() (tensorrt_llm.models.dit method)": [[82, "tensorrt_llm.models.DiT.forward_with_cfg", false]], "forward_without_cfg() (tensorrt_llm.models.dit method)": [[82, "tensorrt_llm.models.DiT.forward_without_cfg", false]], "fp8 (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.FP8", false]], "fp8_block_scales (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.FP8_BLOCK_SCALES", false]], "fp8_per_channel_per_token (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.FP8_PER_CHANNEL_PER_TOKEN", false]], "free_gpu_memory_fraction (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[68, "tensorrt_llm.llmapi.KvCacheConfig.free_gpu_memory_fraction", false]], "frequency_penalty (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.frequency_penalty", false]], "frequency_penalty (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.frequency_penalty", false]], "from_arguments() (tensorrt_llm.models.speculativedecodingmode static method)": [[82, "tensorrt_llm.models.SpeculativeDecodingMode.from_arguments", false]], "from_checkpoint() (tensorrt_llm.models.pretrainedconfig class method)": [[82, "tensorrt_llm.models.PretrainedConfig.from_checkpoint", false]], "from_checkpoint() (tensorrt_llm.models.pretrainedmodel class method)": [[82, "tensorrt_llm.models.PretrainedModel.from_checkpoint", false]], "from_config() (tensorrt_llm.models.pretrainedmodel class method)": [[82, "tensorrt_llm.models.PretrainedModel.from_config", false]], "from_dict() (tensorrt_llm.llmapi.buildconfig class method)": [[68, "tensorrt_llm.llmapi.BuildConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.calibconfig class method)": [[68, "tensorrt_llm.llmapi.CalibConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.drafttargetdecodingconfig class method)": [[68, "tensorrt_llm.llmapi.DraftTargetDecodingConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.eagledecodingconfig class method)": [[68, "tensorrt_llm.llmapi.EagleDecodingConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.lookaheaddecodingconfig class method)": [[68, "tensorrt_llm.llmapi.LookaheadDecodingConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.medusadecodingconfig class method)": [[68, "tensorrt_llm.llmapi.MedusaDecodingConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.mtpdecodingconfig class method)": [[68, "tensorrt_llm.llmapi.MTPDecodingConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.ngramdecodingconfig class method)": [[68, "tensorrt_llm.llmapi.NGramDecodingConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.quantconfig class method)": [[68, "tensorrt_llm.llmapi.QuantConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.userprovideddecodingconfig class method)": [[68, "tensorrt_llm.llmapi.UserProvidedDecodingConfig.from_dict", false]], "from_dict() (tensorrt_llm.models.pretrainedconfig class method)": [[82, "tensorrt_llm.models.PretrainedConfig.from_dict", false]], "from_dir() (tensorrt_llm.runtime.modelrunner class method)": [[85, "tensorrt_llm.runtime.ModelRunner.from_dir", false]], "from_dir() (tensorrt_llm.runtime.modelrunnercpp class method)": [[85, "tensorrt_llm.runtime.ModelRunnerCpp.from_dir", false]], "from_engine() (tensorrt_llm.runtime.encdecmodelrunner class method)": [[85, "tensorrt_llm.runtime.EncDecModelRunner.from_engine", false]], "from_engine() (tensorrt_llm.runtime.modelrunner class method)": [[85, "tensorrt_llm.runtime.ModelRunner.from_engine", false]], "from_engine() (tensorrt_llm.runtime.session static method)": [[85, "tensorrt_llm.runtime.Session.from_engine", false]], "from_hugging_face() (tensorrt_llm.models.baichuanforcausallm class method)": [[82, "tensorrt_llm.models.BaichuanForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.chatglmconfig class method)": [[82, "tensorrt_llm.models.ChatGLMConfig.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.chatglmforcausallm class method)": [[82, "tensorrt_llm.models.ChatGLMForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.cogvlmforcausallm class method)": [[82, "tensorrt_llm.models.CogVLMForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.cohereforcausallm class method)": [[82, "tensorrt_llm.models.CohereForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.deepseekforcausallm class method)": [[82, "tensorrt_llm.models.DeepseekForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.deepseekv2forcausallm class method)": [[82, "tensorrt_llm.models.DeepseekV2ForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.eagleforcausallm class method)": [[82, "tensorrt_llm.models.EagleForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.falconconfig class method)": [[82, "tensorrt_llm.models.FalconConfig.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.falconforcausallm class method)": [[82, "tensorrt_llm.models.FalconForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.gemmaconfig class method)": [[82, "tensorrt_llm.models.GemmaConfig.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.gemmaforcausallm class method)": [[82, "tensorrt_llm.models.GemmaForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.gptconfig class method)": [[82, "tensorrt_llm.models.GPTConfig.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.gptforcausallm class method)": [[82, "tensorrt_llm.models.GPTForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.gptjconfig class method)": [[82, "tensorrt_llm.models.GPTJConfig.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.gptjforcausallm class method)": [[82, "tensorrt_llm.models.GPTJForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.llamaconfig class method)": [[82, "tensorrt_llm.models.LLaMAConfig.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.llamaforcausallm class method)": [[82, "tensorrt_llm.models.LLaMAForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.llavanextvisionconfig class method)": [[82, "tensorrt_llm.models.LlavaNextVisionConfig.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.llavanextvisionwrapper class method)": [[82, "tensorrt_llm.models.LlavaNextVisionWrapper.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.mambaforcausallm class method)": [[82, "tensorrt_llm.models.MambaForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.medusaconfig class method)": [[82, "tensorrt_llm.models.MedusaConfig.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.medusaforcausallm class method)": [[82, "tensorrt_llm.models.MedusaForCausalLm.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.mllamaforcausallm class method)": [[82, "tensorrt_llm.models.MLLaMAForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.phi3forcausallm class method)": [[82, "tensorrt_llm.models.Phi3ForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.phiforcausallm class method)": [[82, "tensorrt_llm.models.PhiForCausalLM.from_hugging_face", false]], "from_json_file() (tensorrt_llm.llmapi.buildconfig class method)": [[68, "tensorrt_llm.llmapi.BuildConfig.from_json_file", false]], "from_json_file() (tensorrt_llm.models.pretrainedconfig class method)": [[82, "tensorrt_llm.models.PretrainedConfig.from_json_file", false]], "from_meta_ckpt() (tensorrt_llm.models.llamaconfig class method)": [[82, "tensorrt_llm.models.LLaMAConfig.from_meta_ckpt", false]], "from_meta_ckpt() (tensorrt_llm.models.llamaforcausallm class method)": [[82, "tensorrt_llm.models.LLaMAForCausalLM.from_meta_ckpt", false]], "from_nemo() (tensorrt_llm.models.gptconfig class method)": [[82, "tensorrt_llm.models.GPTConfig.from_nemo", false]], "from_nemo() (tensorrt_llm.models.gptforcausallm class method)": [[82, "tensorrt_llm.models.GPTForCausalLM.from_nemo", false]], "from_pretrained() (tensorrt_llm.models.sd3transformer2dmodel class method)": [[82, "tensorrt_llm.models.SD3Transformer2DModel.from_pretrained", false]], "from_serialized_engine() (tensorrt_llm.runtime.session static method)": [[85, "tensorrt_llm.runtime.Session.from_serialized_engine", false]], "from_string() (tensorrt_llm.functional.positionembeddingtype static method)": [[80, "tensorrt_llm.functional.PositionEmbeddingType.from_string", false]], "from_string() (tensorrt_llm.functional.rotaryscalingtype static method)": [[80, "tensorrt_llm.functional.RotaryScalingType.from_string", false]], "fuse_qkv_projections() (tensorrt_llm.models.sd3transformer2dmodel method)": [[82, "tensorrt_llm.models.SD3Transformer2DModel.fuse_qkv_projections", false]], "fusedgatedmlp (class in tensorrt_llm.layers.mlp)": [[81, "tensorrt_llm.layers.mlp.FusedGatedMLP", false]], "fusedgatedmlp (tensorrt_llm.functional.mlptype attribute)": [[80, "tensorrt_llm.functional.MLPType.FusedGatedMLP", false]], "garbage_collection_gen0_threshold (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.garbage_collection_gen0_threshold", false]], "gatedmlp (class in tensorrt_llm.layers.mlp)": [[81, "tensorrt_llm.layers.mlp.GatedMLP", false]], "gatedmlp (tensorrt_llm.functional.mlptype attribute)": [[80, "tensorrt_llm.functional.MLPType.GatedMLP", false]], "gather() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.gather", false]], "gather_context_logits (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.gather_context_logits", false]], "gather_context_logits (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.gather_context_logits", false]], "gather_context_logits (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.gather_context_logits", false]], "gather_context_logits (tensorrt_llm.runtime.modelrunner property)": [[85, "tensorrt_llm.runtime.ModelRunner.gather_context_logits", false]], "gather_context_logits (tensorrt_llm.runtime.modelrunnercpp property)": [[85, "tensorrt_llm.runtime.ModelRunnerCpp.gather_context_logits", false]], "gather_generation_logits (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.gather_generation_logits", false]], "gather_generation_logits (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.gather_generation_logits", false]], "gather_generation_logits (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.gather_generation_logits", false]], "gather_generation_logits (tensorrt_llm.runtime.modelrunner property)": [[85, "tensorrt_llm.runtime.ModelRunner.gather_generation_logits", false]], "gather_generation_logits (tensorrt_llm.runtime.modelrunnercpp property)": [[85, "tensorrt_llm.runtime.ModelRunnerCpp.gather_generation_logits", false]], "gather_last_token_logits() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.gather_last_token_logits", false]], "gather_nd() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.gather_nd", false]], "gegelu() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.gegelu", false]], "geglu() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.geglu", false]], "gelu() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.gelu", false]], "gemm_allreduce() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.gemm_allreduce", false]], "gemm_allreduce_plugin (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.gemm_allreduce_plugin", false]], "gemm_allreduce_plugin (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.gemm_allreduce_plugin", false]], "gemm_swiglu() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.gemm_swiglu", false]], "gemma2_added_fields (tensorrt_llm.models.gemmaconfig attribute)": [[82, "tensorrt_llm.models.GemmaConfig.GEMMA2_ADDED_FIELDS", false]], "gemma2_config() (tensorrt_llm.models.gemmaconfig method)": [[82, "tensorrt_llm.models.GemmaConfig.gemma2_config", false]], "gemma3_added_fields (tensorrt_llm.models.gemmaconfig attribute)": [[82, "tensorrt_llm.models.GemmaConfig.GEMMA3_ADDED_FIELDS", false]], "gemma3_config() (tensorrt_llm.models.gemmaconfig method)": [[82, "tensorrt_llm.models.GemmaConfig.gemma3_config", false]], "gemma_added_fields (tensorrt_llm.models.gemmaconfig attribute)": [[82, "tensorrt_llm.models.GemmaConfig.GEMMA_ADDED_FIELDS", false]], "gemmaconfig (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.GemmaConfig", false]], "gemmaforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.GemmaForCausalLM", false]], "generate() (tensorrt_llm.llmapi.llm method)": [[68, "tensorrt_llm.llmapi.LLM.generate", false]], "generate() (tensorrt_llm.runtime.encdecmodelrunner method)": [[85, "tensorrt_llm.runtime.EncDecModelRunner.generate", false]], "generate() (tensorrt_llm.runtime.modelrunner method)": [[85, "tensorrt_llm.runtime.ModelRunner.generate", false]], "generate() (tensorrt_llm.runtime.modelrunnercpp method)": [[85, "tensorrt_llm.runtime.ModelRunnerCpp.generate", false]], "generate() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.generate", false]], "generate() (tensorrt_llm.runtime.qwenforcausallmgenerationsession method)": [[85, "tensorrt_llm.runtime.QWenForCausalLMGenerationSession.generate", false]], "generate_alibi_biases() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.generate_alibi_biases", false]], "generate_alibi_slopes() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.generate_alibi_slopes", false]], "generate_async() (tensorrt_llm.llmapi.llm method)": [[68, "tensorrt_llm.llmapi.LLM.generate_async", false]], "generate_logn_scaling() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.generate_logn_scaling", false]], "generation_logits (tensorrt_llm.llmapi.completionoutput attribute)": [[68, "tensorrt_llm.llmapi.CompletionOutput.generation_logits", false]], "generationsequence (class in tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.GenerationSequence", false]], "generationsession (class in tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.GenerationSession", false]], "get_1d_sincos_pos_embed_from_grid() (in module tensorrt_llm.layers.embedding)": [[81, "tensorrt_llm.layers.embedding.get_1d_sincos_pos_embed_from_grid", false]], "get_2d_sincos_pos_embed() (in module tensorrt_llm.layers.embedding)": [[81, "tensorrt_llm.layers.embedding.get_2d_sincos_pos_embed", false]], "get_2d_sincos_pos_embed_from_grid() (in module tensorrt_llm.layers.embedding)": [[81, "tensorrt_llm.layers.embedding.get_2d_sincos_pos_embed_from_grid", false]], "get_audio_features() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.get_audio_features", false]], "get_batch_idx() (tensorrt_llm.runtime.generationsequence method)": [[85, "tensorrt_llm.runtime.GenerationSequence.get_batch_idx", false]], "get_block_offsets() (tensorrt_llm.runtime.kvcachemanager method)": [[85, "tensorrt_llm.runtime.KVCacheManager.get_block_offsets", false]], "get_comm() (tensorrt_llm.llmapi.mpicommsession method)": [[68, "tensorrt_llm.llmapi.MpiCommSession.get_comm", false]], "get_config_group() (tensorrt_llm.models.pretrainedconfig method)": [[82, "tensorrt_llm.models.PretrainedConfig.get_config_group", false]], "get_context_phase_params() (tensorrt_llm.llmapi.disaggregatedparams method)": [[68, "tensorrt_llm.llmapi.DisaggregatedParams.get_context_phase_params", false]], "get_draft_model_prompt() (tensorrt_llm.llmapi.eagledecodingconfig method)": [[68, "tensorrt_llm.llmapi.EagleDecodingConfig.get_draft_model_prompt", false]], "get_first_past_key_value() (tensorrt_llm.layers.attention.keyvaluecacheparams method)": [[81, "tensorrt_llm.layers.attention.KeyValueCacheParams.get_first_past_key_value", false]], "get_hf_config() (tensorrt_llm.models.gemmaconfig static method)": [[82, "tensorrt_llm.models.GemmaConfig.get_hf_config", false]], "get_kv_cache_events() (tensorrt_llm.llmapi.llm method)": [[68, "tensorrt_llm.llmapi.LLM.get_kv_cache_events", false]], "get_kv_cache_events_async() (tensorrt_llm.llmapi.llm method)": [[68, "tensorrt_llm.llmapi.LLM.get_kv_cache_events_async", false]], "get_next_medusa_tokens() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.get_next_medusa_tokens", false]], "get_num_heads_kv() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.get_num_heads_kv", false]], "get_parent() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.get_parent", false]], "get_pytorch_backend_config() (tensorrt_llm.llmapi.torchllmargs method)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.get_pytorch_backend_config", false]], "get_request_type() (tensorrt_llm.llmapi.disaggregatedparams method)": [[68, "tensorrt_llm.llmapi.DisaggregatedParams.get_request_type", false]], "get_rope_index() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.get_rope_index", false]], "get_seq_idx() (tensorrt_llm.runtime.generationsequence method)": [[85, "tensorrt_llm.runtime.GenerationSequence.get_seq_idx", false]], "get_stats() (tensorrt_llm.llmapi.llm method)": [[68, "tensorrt_llm.llmapi.LLM.get_stats", false]], "get_stats_async() (tensorrt_llm.llmapi.llm method)": [[68, "tensorrt_llm.llmapi.LLM.get_stats_async", false]], "get_timestep_embedding() (in module tensorrt_llm.layers.embedding)": [[81, "tensorrt_llm.layers.embedding.get_timestep_embedding", false]], "get_users() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.get_users", false]], "get_visual_features() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.get_visual_features", false]], "get_weight() (tensorrt_llm.layers.linear.linearbase method)": [[81, "tensorrt_llm.layers.linear.LinearBase.get_weight", false]], "gpt_attention() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.gpt_attention", false]], "gpt_attention_plugin (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.gpt_attention_plugin", false]], "gptconfig (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.GPTConfig", false]], "gptforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.GPTForCausalLM", false]], "gptjconfig (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.GPTJConfig", false]], "gptjforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.GPTJForCausalLM", false]], "gptjmodel (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.GPTJModel", false]], "gptmodel (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.GPTModel", false]], "gptneoxforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.GPTNeoXForCausalLM", false]], "gptneoxmodel (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.GPTNeoXModel", false]], "gpu_weights_percent (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.gpu_weights_percent", false]], "grammar (tensorrt_llm.llmapi.guideddecodingparams attribute)": [[68, "tensorrt_llm.llmapi.GuidedDecodingParams.grammar", false]], "greedy_sampling (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.EagleDecodingConfig.greedy_sampling", false]], "group_norm() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.group_norm", false]], "group_size (tensorrt_llm.llmapi.quantconfig attribute)": [[68, "tensorrt_llm.llmapi.QuantConfig.group_size", false]], "groupnorm (class in tensorrt_llm.layers.normalization)": [[81, "tensorrt_llm.layers.normalization.GroupNorm", false]], "groupnorm (tensorrt_llm.functional.layernormtype attribute)": [[80, "tensorrt_llm.functional.LayerNormType.GroupNorm", false]], "gt() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.gt", false]], "guaranteed_no_evict (tensorrt_llm.llmapi.capacityschedulerpolicy attribute)": [[68, "tensorrt_llm.llmapi.CapacitySchedulerPolicy.GUARANTEED_NO_EVICT", false]], "guided_decoding (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.guided_decoding", false]], "guideddecodingparams (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.GuidedDecodingParams", false]], "handle_per_step() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.handle_per_step", false]], "has_affine() (tensorrt_llm.functional.allreduceparams method)": [[80, "tensorrt_llm.functional.AllReduceParams.has_affine", false]], "has_bias() (tensorrt_llm.functional.allreduceparams method)": [[80, "tensorrt_llm.functional.AllReduceParams.has_bias", false]], "has_config_group() (tensorrt_llm.models.pretrainedconfig method)": [[82, "tensorrt_llm.models.PretrainedConfig.has_config_group", false]], "has_position_embedding (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.has_position_embedding", false]], "has_position_embedding (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.has_position_embedding", false]], "has_scale() (tensorrt_llm.functional.allreduceparams method)": [[80, "tensorrt_llm.functional.AllReduceParams.has_scale", false]], "has_token_type_embedding (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.has_token_type_embedding", false]], "has_token_type_embedding (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.has_token_type_embedding", false]], "has_zero_point (tensorrt_llm.llmapi.quantconfig attribute)": [[68, "tensorrt_llm.llmapi.QuantConfig.has_zero_point", false]], "head_size (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.head_size", false]], "head_size (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.head_size", false]], "hidden_size (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.hidden_size", false]], "hidden_size (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.hidden_size", false]], "hidden_size (tensorrt_llm.runtime.modelrunner property)": [[85, "tensorrt_llm.runtime.ModelRunner.hidden_size", false]], "hidden_size (tensorrt_llm.runtime.modelrunnercpp property)": [[85, "tensorrt_llm.runtime.ModelRunnerCpp.hidden_size", false]], "host_cache_size (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[68, "tensorrt_llm.llmapi.KvCacheConfig.host_cache_size", false]], "identity() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.identity", false]], "ignore_eos (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.ignore_eos", false]], "include_stop_str_in_output (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.include_stop_str_in_output", false]], "index (tensorrt_llm.llmapi.completionoutput attribute)": [[68, "tensorrt_llm.llmapi.CompletionOutput.index", false]], "index_select() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.index_select", false]], "infer_shapes() (tensorrt_llm.runtime.session method)": [[85, "tensorrt_llm.runtime.Session.infer_shapes", false]], "inflight (tensorrt_llm.llmapi.batchingtype attribute)": [[68, "tensorrt_llm.llmapi.BatchingType.INFLIGHT", false]], "init_audio_encoder() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.init_audio_encoder", false]], "init_backend() (tensorrt_llm.llmapi.torchllmargs class method)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.init_backend", false]], "init_calib_config() (tensorrt_llm.llmapi.trtllmargs class method)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.init_calib_config", false]], "init_image_encoder() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.init_image_encoder", false]], "init_llm() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.init_llm", false]], "init_processor() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.init_processor", false]], "init_tokenizer() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.init_tokenizer", false]], "input_timing_cache (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.input_timing_cache", false]], "int8 (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.INT8", false]], "int_clip() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.int_clip", false]], "interpolate() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.interpolate", false]], "is_alibi() (tensorrt_llm.functional.positionembeddingtype method)": [[80, "tensorrt_llm.functional.PositionEmbeddingType.is_alibi", false]], "is_deferred() (tensorrt_llm.functional.positionembeddingtype method)": [[80, "tensorrt_llm.functional.PositionEmbeddingType.is_deferred", false]], "is_dynamic() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.is_dynamic", false]], "is_gated_activation() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.is_gated_activation", false]], "is_gemma_2 (tensorrt_llm.models.gemmaconfig property)": [[82, "tensorrt_llm.models.GemmaConfig.is_gemma_2", false]], "is_gemma_3 (tensorrt_llm.models.gemmaconfig property)": [[82, "tensorrt_llm.models.GemmaConfig.is_gemma_3", false]], "is_keep_all (tensorrt_llm.llmapi.ngramdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.NGramDecodingConfig.is_keep_all", false]], "is_medusa_mode (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.is_medusa_mode", false]], "is_module_excluded_from_quantization() (tensorrt_llm.llmapi.quantconfig method)": [[68, "tensorrt_llm.llmapi.QuantConfig.is_module_excluded_from_quantization", false]], "is_mrope() (tensorrt_llm.functional.positionembeddingtype method)": [[80, "tensorrt_llm.functional.PositionEmbeddingType.is_mrope", false]], "is_public_pool (tensorrt_llm.llmapi.ngramdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.NGramDecodingConfig.is_public_pool", false]], "is_redrafter_mode (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.is_redrafter_mode", false]], "is_rope() (tensorrt_llm.functional.positionembeddingtype method)": [[80, "tensorrt_llm.functional.PositionEmbeddingType.is_rope", false]], "is_trt_wrapper() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.is_trt_wrapper", false]], "is_use_oldest (tensorrt_llm.llmapi.ngramdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.NGramDecodingConfig.is_use_oldest", false]], "is_valid() (tensorrt_llm.functional.moeallreduceparams method)": [[80, "tensorrt_llm.functional.MoEAllReduceParams.is_valid", false]], "is_valid() (tensorrt_llm.layers.attention.attentionparams method)": [[81, "tensorrt_llm.layers.attention.AttentionParams.is_valid", false]], "is_valid() (tensorrt_llm.layers.attention.keyvaluecacheparams method)": [[81, "tensorrt_llm.layers.attention.KeyValueCacheParams.is_valid", false]], "is_valid_cross_attn() (tensorrt_llm.layers.attention.attentionparams method)": [[81, "tensorrt_llm.layers.attention.AttentionParams.is_valid_cross_attn", false]], "joint_attn_forward() (tensorrt_llm.layers.attention.diffusersattention method)": [[81, "tensorrt_llm.layers.attention.DiffusersAttention.joint_attn_forward", false]], "json (tensorrt_llm.llmapi.guideddecodingparams attribute)": [[68, "tensorrt_llm.llmapi.GuidedDecodingParams.json", false]], "json_object (tensorrt_llm.llmapi.guideddecodingparams attribute)": [[68, "tensorrt_llm.llmapi.GuidedDecodingParams.json_object", false]], "keyvaluecacheparams (class in tensorrt_llm.layers.attention)": [[81, "tensorrt_llm.layers.attention.KeyValueCacheParams", false]], "kv_cache_dtype (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.kv_cache_dtype", false]], "kv_cache_quant_algo (tensorrt_llm.llmapi.quantconfig attribute)": [[68, "tensorrt_llm.llmapi.QuantConfig.kv_cache_quant_algo", false]], "kv_cache_type (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.kv_cache_type", false]], "kv_cache_type (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.kv_cache_type", false]], "kv_cache_type (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.kv_cache_type", false]], "kv_dtype (tensorrt_llm.models.pretrainedconfig property)": [[82, "tensorrt_llm.models.PretrainedConfig.kv_dtype", false]], "kvcacheconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.KvCacheConfig", false]], "kvcachemanager (class in tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.KVCacheManager", false]], "kvcacheretentionconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.KvCacheRetentionConfig", false]], "kvcacheretentionconfig.tokenrangeretentionconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.KvCacheRetentionConfig.TokenRangeRetentionConfig", false]], "labelembedding (class in tensorrt_llm.layers.embedding)": [[81, "tensorrt_llm.layers.embedding.LabelEmbedding", false]], "language_adapter_config (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.language_adapter_config", false]], "last_layer (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.last_layer", false]], "last_process_for_ub (tensorrt_llm.functional.allreducefusionop attribute)": [[80, "tensorrt_llm.functional.AllReduceFusionOp.LAST_PROCESS_FOR_UB", false]], "layer_norm() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.layer_norm", false]], "layer_quant_mode (tensorrt_llm.llmapi.quantconfig property)": [[68, "tensorrt_llm.llmapi.QuantConfig.layer_quant_mode", false]], "layer_types (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.layer_types", false]], "layernorm (class in tensorrt_llm.layers.normalization)": [[81, "tensorrt_llm.layers.normalization.LayerNorm", false]], "layernorm (tensorrt_llm.functional.layernormtype attribute)": [[80, "tensorrt_llm.functional.LayerNormType.LayerNorm", false]], "layernormpositiontype (class in tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.LayerNormPositionType", false]], "layernormtype (class in tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.LayerNormType", false]], "learned_absolute (tensorrt_llm.functional.positionembeddingtype attribute)": [[80, "tensorrt_llm.functional.PositionEmbeddingType.learned_absolute", false]], "length (tensorrt_llm.llmapi.completionoutput attribute)": [[68, "tensorrt_llm.llmapi.CompletionOutput.length", false]], "length (tensorrt_llm.llmapi.completionoutput property)": [[68, "id2", false]], "length_penalty (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.length_penalty", false]], "length_penalty (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.length_penalty", false]], "linear (class in tensorrt_llm.layers.linear)": [[81, "tensorrt_llm.layers.linear.Linear", false]], "linear (tensorrt_llm.functional.rotaryscalingtype attribute)": [[80, "tensorrt_llm.functional.RotaryScalingType.linear", false]], "linearactivation (class in tensorrt_llm.layers.mlp)": [[81, "tensorrt_llm.layers.mlp.LinearActivation", false]], "linearapproximategelu (class in tensorrt_llm.layers.mlp)": [[81, "tensorrt_llm.layers.mlp.LinearApproximateGELU", false]], "linearbase (class in tensorrt_llm.layers.linear)": [[81, "tensorrt_llm.layers.linear.LinearBase", false]], "lineargeglu (class in tensorrt_llm.layers.mlp)": [[81, "tensorrt_llm.layers.mlp.LinearGEGLU", false]], "lineargelu (class in tensorrt_llm.layers.mlp)": [[81, "tensorrt_llm.layers.mlp.LinearGELU", false]], "linearswiglu (class in tensorrt_llm.layers.mlp)": [[81, "tensorrt_llm.layers.mlp.LinearSwiGLU", false]], "llama3 (tensorrt_llm.functional.rotaryscalingtype attribute)": [[80, "tensorrt_llm.functional.RotaryScalingType.llama3", false]], "llamaconfig (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.LLaMAConfig", false]], "llamaforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.LLaMAForCausalLM", false]], "llamamodel (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.LLaMAModel", false]], "llavanextvisionconfig (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.LlavaNextVisionConfig", false]], "llavanextvisionwrapper (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.LlavaNextVisionWrapper", false]], "llm (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.LLM", false]], "llm_engine_dir (tensorrt_llm.runtime.multimodalmodelrunner property)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.llm_engine_dir", false]], "llm_id (tensorrt_llm.llmapi.llm attribute)": [[68, "tensorrt_llm.llmapi.LLM.llm_id", false]], "llm_id (tensorrt_llm.llmapi.llm property)": [[68, "id0", false]], "llmargs (in module tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.LlmArgs", false]], "load() (tensorrt_llm.models.pretrainedmodel method)": [[82, "tensorrt_llm.models.PretrainedModel.load", false]], "load() (tensorrt_llm.models.sd3transformer2dmodel method)": [[82, "tensorrt_llm.models.SD3Transformer2DModel.load", false]], "load_format (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.load_format", false]], "load_test_audio() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.load_test_audio", false]], "load_test_data() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.load_test_data", false]], "locate_accepted_draft_tokens() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.locate_accepted_draft_tokens", false]], "location (tensorrt_llm.functional.tensor property)": [[80, "tensorrt_llm.functional.Tensor.location", false]], "log() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.log", false]], "log() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.log", false]], "log_softmax() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.log_softmax", false]], "logits_processor (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.logits_processor", false]], "logitsprocessor (class in tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.LogitsProcessor", false]], "logitsprocessorlist (class in tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.LogitsProcessorList", false]], "logprobs (tensorrt_llm.llmapi.completionoutput attribute)": [[68, "tensorrt_llm.llmapi.CompletionOutput.logprobs", false]], "logprobs (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.logprobs", false]], "logprobs_diff (tensorrt_llm.llmapi.completionoutput attribute)": [[68, "tensorrt_llm.llmapi.CompletionOutput.logprobs_diff", false]], "logprobs_diff (tensorrt_llm.llmapi.completionoutput property)": [[68, "id3", false]], "long_rope (tensorrt_llm.functional.positionembeddingtype attribute)": [[80, "tensorrt_llm.functional.PositionEmbeddingType.long_rope", false]], "longrope (tensorrt_llm.functional.rotaryscalingtype attribute)": [[80, "tensorrt_llm.functional.RotaryScalingType.longrope", false]], "lookahead_config (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.lookahead_config", false]], "lookahead_decoding (tensorrt_llm.models.speculativedecodingmode attribute)": [[82, "tensorrt_llm.models.SpeculativeDecodingMode.LOOKAHEAD_DECODING", false]], "lookaheaddecodingconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.LookaheadDecodingConfig", false]], "lora_config (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.lora_config", false]], "lora_plugin (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.lora_plugin", false]], "lora_plugin() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.lora_plugin", false]], "lora_target_modules (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.lora_target_modules", false]], "low_latency_gemm() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.low_latency_gemm", false]], "low_latency_gemm_swiglu() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.low_latency_gemm_swiglu", false]], "lowprecision (tensorrt_llm.functional.allreducestrategy attribute)": [[80, "tensorrt_llm.functional.AllReduceStrategy.LOWPRECISION", false]], "lt() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.lt", false]], "make_causal_mask() (in module tensorrt_llm.layers.attention)": [[81, "tensorrt_llm.layers.attention.make_causal_mask", false]], "mamba_conv1d() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.mamba_conv1d", false]], "mamba_conv1d_plugin (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.mamba_conv1d_plugin", false]], "mambaforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.MambaForCausalLM", false]], "mapping (tensorrt_llm.runtime.generationsession attribute)": [[85, "tensorrt_llm.runtime.GenerationSession.mapping", false]], "mapping (tensorrt_llm.runtime.modelrunner property)": [[85, "tensorrt_llm.runtime.ModelRunner.mapping", false]], "mark_output() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.mark_output", false]], "masked_scatter() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.masked_scatter", false]], "masked_select() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.masked_select", false]], "matmul() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.matmul", false]], "max() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.max", false]], "max() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.max", false]], "max_attention_window (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[68, "tensorrt_llm.llmapi.KvCacheConfig.max_attention_window", false]], "max_attention_window_size (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.max_attention_window_size", false]], "max_batch_size (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.max_batch_size", false]], "max_batch_size (tensorrt_llm.llmapi.cudagraphconfig attribute)": [[68, "tensorrt_llm.llmapi.CudaGraphConfig.max_batch_size", false]], "max_batch_size (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.max_batch_size", false]], "max_beam_width (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.max_beam_width", false]], "max_beam_width (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.max_beam_width", false]], "max_cache_storage_gb (tensorrt_llm.llmapi.buildcacheconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildCacheConfig.max_cache_storage_gb", false]], "max_cache_storage_gb (tensorrt_llm.llmapi.buildcacheconfig property)": [[68, "id8", false]], "max_cpu_loras (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.max_cpu_loras", false]], "max_cpu_loras (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.max_cpu_loras", false]], "max_draft_len (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.max_draft_len", false]], "max_draft_tokens (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.max_draft_tokens", false]], "max_encoder_input_len (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.max_encoder_input_len", false]], "max_input_len (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.max_input_len", false]], "max_lora_rank (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.max_lora_rank", false]], "max_lora_rank (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.max_lora_rank", false]], "max_loras (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.max_loras", false]], "max_loras (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.max_loras", false]], "max_matching_ngram_size (tensorrt_llm.llmapi.ngramdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.NGramDecodingConfig.max_matching_ngram_size", false]], "max_medusa_tokens (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.max_medusa_tokens", false]], "max_new_tokens (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.max_new_tokens", false]], "max_ngram_size (tensorrt_llm.llmapi.lookaheaddecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.LookaheadDecodingConfig.max_ngram_size", false]], "max_non_leaves_per_layer (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.EagleDecodingConfig.max_non_leaves_per_layer", false]], "max_num_tokens (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.max_num_tokens", false]], "max_num_tokens (tensorrt_llm.llmapi.cachetransceiverconfig attribute)": [[68, "tensorrt_llm.llmapi.CacheTransceiverConfig.max_num_tokens", false]], "max_prompt_adapter_token (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.max_prompt_adapter_token", false]], "max_prompt_embedding_table_size (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.max_prompt_embedding_table_size", false]], "max_prompt_embedding_table_size (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.max_prompt_embedding_table_size", false]], "max_prompt_embedding_table_size (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.max_prompt_embedding_table_size", false]], "max_prompt_embedding_table_size (tensorrt_llm.runtime.modelrunner property)": [[85, "tensorrt_llm.runtime.ModelRunner.max_prompt_embedding_table_size", false]], "max_prompt_embedding_table_size (tensorrt_llm.runtime.modelrunnercpp property)": [[85, "tensorrt_llm.runtime.ModelRunnerCpp.max_prompt_embedding_table_size", false]], "max_records (tensorrt_llm.llmapi.buildcacheconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildCacheConfig.max_records", false]], "max_records (tensorrt_llm.llmapi.buildcacheconfig property)": [[68, "id9", false]], "max_seq_len (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.max_seq_len", false]], "max_sequence_length (tensorrt_llm.runtime.modelrunner property)": [[85, "tensorrt_llm.runtime.ModelRunner.max_sequence_length", false]], "max_sequence_length (tensorrt_llm.runtime.modelrunnercpp property)": [[85, "tensorrt_llm.runtime.ModelRunnerCpp.max_sequence_length", false]], "max_tokens (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[68, "tensorrt_llm.llmapi.KvCacheConfig.max_tokens", false]], "max_tokens (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.max_tokens", false]], "max_utilization (tensorrt_llm.llmapi.capacityschedulerpolicy attribute)": [[68, "tensorrt_llm.llmapi.CapacitySchedulerPolicy.MAX_UTILIZATION", false]], "max_verification_set_size (tensorrt_llm.llmapi.lookaheaddecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.LookaheadDecodingConfig.max_verification_set_size", false]], "max_window_size (tensorrt_llm.llmapi.lookaheaddecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.LookaheadDecodingConfig.max_window_size", false]], "maximum() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.maximum", false]], "mean() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.mean", false]], "mean() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.mean", false]], "medusa (tensorrt_llm.models.speculativedecodingmode attribute)": [[82, "tensorrt_llm.models.SpeculativeDecodingMode.MEDUSA", false]], "medusa_choices (tensorrt_llm.llmapi.medusadecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.MedusaDecodingConfig.medusa_choices", false]], "medusa_decode_and_verify() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.medusa_decode_and_verify", false]], "medusa_paths (tensorrt_llm.runtime.generationsession attribute)": [[85, "tensorrt_llm.runtime.GenerationSession.medusa_paths", false]], "medusa_position_offsets (tensorrt_llm.runtime.generationsession attribute)": [[85, "tensorrt_llm.runtime.GenerationSession.medusa_position_offsets", false]], "medusa_temperature (tensorrt_llm.runtime.generationsession attribute)": [[85, "tensorrt_llm.runtime.GenerationSession.medusa_temperature", false]], "medusa_topks (tensorrt_llm.runtime.generationsession attribute)": [[85, "tensorrt_llm.runtime.GenerationSession.medusa_topks", false]], "medusa_tree_ids (tensorrt_llm.runtime.generationsession attribute)": [[85, "tensorrt_llm.runtime.GenerationSession.medusa_tree_ids", false]], "medusaconfig (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.MedusaConfig", false]], "medusadecodingconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.MedusaDecodingConfig", false]], "medusaforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.MedusaForCausalLm", false]], "meshgrid2d() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.meshgrid2d", false]], "min() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.min", false]], "min_latency (tensorrt_llm.functional.allreducestrategy attribute)": [[80, "tensorrt_llm.functional.AllReduceStrategy.MIN_LATENCY", false]], "min_length (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.min_length", false]], "min_p (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.min_p", false]], "min_p (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.min_p", false]], "min_tokens (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.min_tokens", false]], "minimum() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.minimum", false]], "mish (class in tensorrt_llm.layers.activation)": [[81, "tensorrt_llm.layers.activation.Mish", false]], "mixed_precision (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.MIXED_PRECISION", false]], "mllamaforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.MLLaMAForCausalLM", false]], "mlp (class in tensorrt_llm.layers.mlp)": [[81, "tensorrt_llm.layers.mlp.MLP", false]], "mlp (tensorrt_llm.functional.mlptype attribute)": [[80, "tensorrt_llm.functional.MLPType.MLP", false]], "mlptype (class in tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.MLPType", false]], "mnnvl (tensorrt_llm.functional.allreducestrategy attribute)": [[80, "tensorrt_llm.functional.AllReduceStrategy.MNNVL", false]], "model": [[34, "cmdoption-trtllm-serve-serve-arg-MODEL", false]], "model_config (tensorrt_llm.llmapi.cachetransceiverconfig attribute)": [[68, "tensorrt_llm.llmapi.CacheTransceiverConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.calibconfig attribute)": [[68, "tensorrt_llm.llmapi.CalibConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.cudagraphconfig attribute)": [[68, "tensorrt_llm.llmapi.CudaGraphConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.drafttargetdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.DraftTargetDecodingConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.dynamicbatchconfig attribute)": [[68, "tensorrt_llm.llmapi.DynamicBatchConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.EagleDecodingConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.extendedruntimeperfknobconfig attribute)": [[68, "tensorrt_llm.llmapi.ExtendedRuntimePerfKnobConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[68, "tensorrt_llm.llmapi.KvCacheConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.lookaheaddecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.LookaheadDecodingConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.medusadecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.MedusaDecodingConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.MTPDecodingConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.ngramdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.NGramDecodingConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.schedulerconfig attribute)": [[68, "tensorrt_llm.llmapi.SchedulerConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.torchcompileconfig attribute)": [[68, "tensorrt_llm.llmapi.TorchCompileConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.model_config", false]], "model_config (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.model_config", false]], "model_config (tensorrt_llm.llmapi.userprovideddecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.UserProvidedDecodingConfig.model_config", false]], "model_name (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.model_name", false]], "model_post_init() (tensorrt_llm.llmapi.torchllmargs method)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.model_post_init", false]], "model_post_init() (tensorrt_llm.llmapi.trtllmargs method)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.model_post_init", false]], "modelconfig (class in tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.ModelConfig", false]], "modelrunner (class in tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.ModelRunner", false]], "modelrunnercpp (class in tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.ModelRunnerCpp", false]], "module": [[80, "module-tensorrt_llm", false], [80, "module-tensorrt_llm.functional", false], [81, "module-tensorrt_llm", false], [81, "module-tensorrt_llm.layers.activation", false], [81, "module-tensorrt_llm.layers.attention", false], [81, "module-tensorrt_llm.layers.cast", false], [81, "module-tensorrt_llm.layers.conv", false], [81, "module-tensorrt_llm.layers.embedding", false], [81, "module-tensorrt_llm.layers.linear", false], [81, "module-tensorrt_llm.layers.mlp", false], [81, "module-tensorrt_llm.layers.normalization", false], [81, "module-tensorrt_llm.layers.pooling", false], [82, "module-tensorrt_llm", false], [82, "module-tensorrt_llm.models", false], [83, "module-tensorrt_llm", false], [83, "module-tensorrt_llm.plugin", false], [84, "module-tensorrt_llm", false], [84, "module-tensorrt_llm.quantization", false], [85, "module-tensorrt_llm", false], [85, "module-tensorrt_llm.runtime", false]], "modulo() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.modulo", false]], "moe (tensorrt_llm.functional.sidestreamidtype attribute)": [[80, "tensorrt_llm.functional.SideStreamIDType.moe", false]], "moe_backend (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.moe_backend", false]], "moe_finalize_allreduce_residual_rms_norm (tensorrt_llm.functional.allreducefusionop attribute)": [[80, "tensorrt_llm.functional.AllReduceFusionOp.MOE_FINALIZE_ALLREDUCE_RESIDUAL_RMS_NORM", false]], "moe_load_balancer (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.moe_load_balancer", false]], "moe_max_num_tokens (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.moe_max_num_tokens", false]], "moeallreduceparams (class in tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.MoEAllReduceParams", false]], "monitor_memory (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.monitor_memory", false]], "mpicommsession (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.MpiCommSession", false]], "mptforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.MPTForCausalLM", false]], "mptmodel (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.MPTModel", false]], "mrope (tensorrt_llm.functional.positionembeddingtype attribute)": [[80, "tensorrt_llm.functional.PositionEmbeddingType.mrope", false]], "mrope (tensorrt_llm.functional.rotaryscalingtype attribute)": [[80, "tensorrt_llm.functional.RotaryScalingType.mrope", false]], "mropeparams (class in tensorrt_llm.layers.attention)": [[81, "tensorrt_llm.layers.attention.MropeParams", false]], "msg (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "id10", false], [68, "id13", false], [68, "id16", false], [68, "tensorrt_llm.llmapi.TorchLlmArgs.msg", false]], "msg (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "id19", false], [68, "id22", false], [68, "id25", false], [68, "id28", false], [68, "id31", false], [68, "tensorrt_llm.llmapi.TrtLlmArgs.msg", false]], "mtpdecodingconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.MTPDecodingConfig", false]], "mul() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.mul", false]], "multi_block_mode (tensorrt_llm.llmapi.extendedruntimeperfknobconfig attribute)": [[68, "tensorrt_llm.llmapi.ExtendedRuntimePerfKnobConfig.multi_block_mode", false]], "multimodalmodelrunner (class in tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner", false]], "multiply_and_lora() (tensorrt_llm.layers.linear.linearbase method)": [[81, "tensorrt_llm.layers.linear.LinearBase.multiply_and_lora", false]], "multiply_collect() (tensorrt_llm.layers.linear.linearbase method)": [[81, "tensorrt_llm.layers.linear.LinearBase.multiply_collect", false]], "multiply_collect() (tensorrt_llm.layers.linear.rowlinear method)": [[81, "tensorrt_llm.layers.linear.RowLinear.multiply_collect", false]], "n (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.n", false]], "name (tensorrt_llm.functional.tensor property)": [[80, "tensorrt_llm.functional.Tensor.name", false]], "name (tensorrt_llm.runtime.tensorinfo attribute)": [[85, "tensorrt_llm.runtime.TensorInfo.name", false]], "native_quant_flow (tensorrt_llm.models.gemmaforcausallm attribute)": [[82, "tensorrt_llm.models.GemmaForCausalLM.NATIVE_QUANT_FLOW", false]], "nccl (tensorrt_llm.functional.allreducestrategy attribute)": [[80, "tensorrt_llm.functional.AllReduceStrategy.NCCL", false]], "ndim() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.ndim", false]], "network (tensorrt_llm.functional.tensor property)": [[80, "tensorrt_llm.functional.Tensor.network", false]], "next_medusa_input_ids() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.next_medusa_input_ids", false]], "ngram (tensorrt_llm.models.speculativedecodingmode attribute)": [[82, "tensorrt_llm.models.SpeculativeDecodingMode.NGRAM", false]], "ngramdecodingconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.NGramDecodingConfig", false]], "no_quant (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.NO_QUANT", false]], "no_repeat_ngram_size (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.no_repeat_ngram_size", false]], "no_repeat_ngram_size (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.no_repeat_ngram_size", false]], "non_gated_version() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.non_gated_version", false]], "none (tensorrt_llm.functional.allreducefusionop attribute)": [[80, "tensorrt_llm.functional.AllReduceFusionOp.NONE", false]], "none (tensorrt_llm.functional.rotaryscalingtype attribute)": [[80, "tensorrt_llm.functional.RotaryScalingType.none", false]], "none (tensorrt_llm.models.speculativedecodingmode attribute)": [[82, "tensorrt_llm.models.SpeculativeDecodingMode.NONE", false]], "nonzero() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.nonzero", false]], "not_op() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.not_op", false]], "num_beams (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.num_beams", false]], "num_draft_tokens (tensorrt_llm.runtime.generationsession attribute)": [[85, "tensorrt_llm.runtime.GenerationSession.num_draft_tokens", false]], "num_eagle_layers (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.EagleDecodingConfig.num_eagle_layers", false]], "num_heads (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.num_heads", false]], "num_heads (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.num_heads", false]], "num_heads (tensorrt_llm.runtime.modelrunner property)": [[85, "tensorrt_llm.runtime.ModelRunner.num_heads", false]], "num_heads (tensorrt_llm.runtime.modelrunnercpp property)": [[85, "tensorrt_llm.runtime.ModelRunnerCpp.num_heads", false]], "num_kv_heads (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.num_kv_heads", false]], "num_kv_heads_per_cross_attn_layer (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.num_kv_heads_per_cross_attn_layer", false]], "num_kv_heads_per_layer (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.num_kv_heads_per_layer", false]], "num_layers (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.num_layers", false]], "num_layers (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.num_layers", false]], "num_layers (tensorrt_llm.runtime.modelrunner property)": [[85, "tensorrt_llm.runtime.ModelRunner.num_layers", false]], "num_layers (tensorrt_llm.runtime.modelrunnercpp property)": [[85, "tensorrt_llm.runtime.ModelRunnerCpp.num_layers", false]], "num_medusa_heads (tensorrt_llm.llmapi.medusadecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.MedusaDecodingConfig.num_medusa_heads", false]], "num_medusa_heads (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.num_medusa_heads", false]], "num_medusa_heads (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.num_medusa_heads", false]], "num_nextn_predict_layers (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.MTPDecodingConfig.num_nextn_predict_layers", false]], "num_nextn_predict_layers_from_model_config (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.MTPDecodingConfig.num_nextn_predict_layers_from_model_config", false]], "num_return_sequences (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.num_return_sequences", false]], "numel() (tensorrt_llm.runtime.tensorinfo method)": [[85, "tensorrt_llm.runtime.TensorInfo.numel", false]], "nvfp4 (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.NVFP4", false]], "nvinfer1 (c++ type)": [[1, "_CPPv48nvinfer1", false]], "onboard_blocks (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[68, "tensorrt_llm.llmapi.KvCacheConfig.onboard_blocks", false]], "oneshot (tensorrt_llm.functional.allreducestrategy attribute)": [[80, "tensorrt_llm.functional.AllReduceStrategy.ONESHOT", false]], "op_and() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.op_and", false]], "op_or() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.op_or", false]], "op_xor() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.op_xor", false]], "opaque_state (tensorrt_llm.llmapi.disaggregatedparams attribute)": [[68, "tensorrt_llm.llmapi.DisaggregatedParams.opaque_state", false]], "opt_batch_size (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.opt_batch_size", false]], "opt_num_tokens (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.opt_num_tokens", false]], "optforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.OPTForCausalLM", false]], "optmodel (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.OPTModel", false]], "outer() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.outer", false]], "output_cum_log_probs (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.output_cum_log_probs", false]], "output_log_probs (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.output_log_probs", false]], "output_sequence_lengths (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.output_sequence_lengths", false]], "output_timing_cache (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.output_timing_cache", false]], "outputs (tensorrt_llm.llmapi.requestoutput attribute)": [[68, "tensorrt_llm.llmapi.RequestOutput.outputs", false]], "pad() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.pad", false]], "pad_id (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.pad_id", false]], "pad_id (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.pad_id", false]], "padding (tensorrt_llm.functional.attentionmasktype attribute)": [[80, "tensorrt_llm.functional.AttentionMaskType.padding", false]], "padding_enabled (tensorrt_llm.llmapi.cudagraphconfig attribute)": [[68, "tensorrt_llm.llmapi.CudaGraphConfig.padding_enabled", false]], "paged_kv_cache (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.paged_kv_cache", false]], "paged_state (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.paged_state", false]], "paged_state (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.paged_state", false]], "permute() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.permute", false]], "permute() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.permute", false]], "phi3forcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.Phi3ForCausalLM", false]], "phi3model (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.Phi3Model", false]], "phiforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.PhiForCausalLM", false]], "phimodel (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.PhiModel", false]], "pixartalphatextprojection (class in tensorrt_llm.layers.embedding)": [[81, "tensorrt_llm.layers.embedding.PixArtAlphaTextProjection", false]], "plugin_config (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.plugin_config", false]], "pluginconfig (class in tensorrt_llm.plugin)": [[83, "tensorrt_llm.plugin.PluginConfig", false]], "positionembeddingtype (class in tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.PositionEmbeddingType", false]], "post_layernorm (tensorrt_llm.functional.layernormpositiontype attribute)": [[80, "tensorrt_llm.functional.LayerNormPositionType.post_layernorm", false]], "posterior_threshold (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.EagleDecodingConfig.posterior_threshold", false]], "postprocess() (tensorrt_llm.layers.attention.attention method)": [[81, "tensorrt_llm.layers.attention.Attention.postprocess", false]], "postprocess() (tensorrt_llm.layers.attention.deepseekv2attention method)": [[81, "tensorrt_llm.layers.attention.DeepseekV2Attention.postprocess", false]], "postprocess() (tensorrt_llm.layers.embedding.embedding method)": [[81, "tensorrt_llm.layers.embedding.Embedding.postprocess", false]], "postprocess() (tensorrt_llm.layers.linear.linear method)": [[81, "tensorrt_llm.layers.linear.Linear.postprocess", false]], "pow() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.pow", false]], "pp_communicate_final_output_ids() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.pp_communicate_final_output_ids", false]], "pp_communicate_new_tokens() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.pp_communicate_new_tokens", false]], "pre_layernorm (tensorrt_llm.functional.layernormpositiontype attribute)": [[80, "tensorrt_llm.functional.LayerNormPositionType.pre_layernorm", false]], "pre_quant_scale (tensorrt_llm.llmapi.quantconfig attribute)": [[68, "tensorrt_llm.llmapi.QuantConfig.pre_quant_scale", false]], "precompute_relative_attention_bias() (tensorrt_llm.models.decodermodel method)": [[82, "tensorrt_llm.models.DecoderModel.precompute_relative_attention_bias", false]], "precompute_relative_attention_bias() (tensorrt_llm.models.encodermodel method)": [[82, "tensorrt_llm.models.EncoderModel.precompute_relative_attention_bias", false]], "precompute_relative_attention_bias() (tensorrt_llm.models.whisperencoder method)": [[82, "tensorrt_llm.models.WhisperEncoder.precompute_relative_attention_bias", false]], "prepare_inputs() (tensorrt_llm.models.chatglmforcausallm method)": [[82, "tensorrt_llm.models.ChatGLMForCausalLM.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.decodermodel method)": [[82, "tensorrt_llm.models.DecoderModel.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.dit method)": [[82, "tensorrt_llm.models.DiT.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.eagleforcausallm method)": [[82, "tensorrt_llm.models.EagleForCausalLM.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.encodermodel method)": [[82, "tensorrt_llm.models.EncoderModel.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.llavanextvisionwrapper method)": [[82, "tensorrt_llm.models.LlavaNextVisionWrapper.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.mambaforcausallm method)": [[82, "tensorrt_llm.models.MambaForCausalLM.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.mllamaforcausallm method)": [[82, "tensorrt_llm.models.MLLaMAForCausalLM.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.pretrainedmodel method)": [[82, "tensorrt_llm.models.PretrainedModel.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.recurrentgemmaforcausallm method)": [[82, "tensorrt_llm.models.RecurrentGemmaForCausalLM.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.sd3transformer2dmodel method)": [[82, "tensorrt_llm.models.SD3Transformer2DModel.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.whisperencoder method)": [[82, "tensorrt_llm.models.WhisperEncoder.prepare_inputs", false]], "prepare_position_ids_for_cogvlm() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.prepare_position_ids_for_cogvlm", false]], "prepare_recurrent_inputs() (tensorrt_llm.models.recurrentgemmaforcausallm method)": [[82, "tensorrt_llm.models.RecurrentGemmaForCausalLM.prepare_recurrent_inputs", false]], "preprocess() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.preprocess", false]], "presence_penalty (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.presence_penalty", false]], "presence_penalty (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.presence_penalty", false]], "pretrainedconfig (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.PretrainedConfig", false]], "pretrainedmodel (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.PretrainedModel", false]], "print_iter_log (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.print_iter_log", false]], "priority (tensorrt_llm.llmapi.kvcacheretentionconfig.tokenrangeretentionconfig property)": [[68, "tensorrt_llm.llmapi.KvCacheRetentionConfig.TokenRangeRetentionConfig.priority", false]], "process_input() (tensorrt_llm.runtime.encdecmodelrunner method)": [[85, "tensorrt_llm.runtime.EncDecModelRunner.process_input", false]], "process_logits_including_draft() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.process_logits_including_draft", false]], "prod() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.prod", false]], "profiler (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.profiler", false]], "profiling_verbosity (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.profiling_verbosity", false]], "prompt (tensorrt_llm.llmapi.requestoutput attribute)": [[68, "tensorrt_llm.llmapi.RequestOutput.prompt", false]], "prompt (tensorrt_llm.llmapi.requestoutput property)": [[68, "id6", false]], "prompt_logprobs (tensorrt_llm.llmapi.completionoutput attribute)": [[68, "tensorrt_llm.llmapi.CompletionOutput.prompt_logprobs", false]], "prompt_logprobs (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.prompt_logprobs", false]], "prompt_token_ids (tensorrt_llm.llmapi.requestoutput attribute)": [[68, "tensorrt_llm.llmapi.RequestOutput.prompt_token_ids", false]], "prompttuningembedding (class in tensorrt_llm.layers.embedding)": [[81, "tensorrt_llm.layers.embedding.PromptTuningEmbedding", false]], "ptuning_setup() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.ptuning_setup", false]], "ptuning_setup_fuyu() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.ptuning_setup_fuyu", false]], "ptuning_setup_llava_next() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.ptuning_setup_llava_next", false]], "ptuning_setup_phi3() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.ptuning_setup_phi3", false]], "ptuning_setup_pixtral() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.ptuning_setup_pixtral", false]], "python_e2e (tensorrt_llm.runtime.multimodalmodelrunner property)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.python_e2e", false]], "quant_algo (tensorrt_llm.llmapi.quantconfig attribute)": [[68, "tensorrt_llm.llmapi.QuantConfig.quant_algo", false]], "quant_algo (tensorrt_llm.models.pretrainedconfig property)": [[82, "tensorrt_llm.models.PretrainedConfig.quant_algo", false]], "quant_mode (tensorrt_llm.llmapi.quantconfig property)": [[68, "tensorrt_llm.llmapi.QuantConfig.quant_mode", false]], "quant_mode (tensorrt_llm.models.pretrainedconfig property)": [[82, "tensorrt_llm.models.PretrainedConfig.quant_mode", false]], "quant_mode (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.quant_mode", false]], "quant_mode (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.quant_mode", false]], "quantalgo (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.QuantAlgo", false]], "quantalgo (class in tensorrt_llm.quantization)": [[84, "tensorrt_llm.quantization.QuantAlgo", false]], "quantconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.QuantConfig", false]], "quantize() (tensorrt_llm.models.baichuanforcausallm class method)": [[82, "tensorrt_llm.models.BaichuanForCausalLM.quantize", false]], "quantize() (tensorrt_llm.models.chatglmforcausallm class method)": [[82, "tensorrt_llm.models.ChatGLMForCausalLM.quantize", false]], "quantize() (tensorrt_llm.models.cogvlmforcausallm class method)": [[82, "tensorrt_llm.models.CogVLMForCausalLM.quantize", false]], "quantize() (tensorrt_llm.models.gemmaforcausallm class method)": [[82, "tensorrt_llm.models.GemmaForCausalLM.quantize", false]], "quantize() (tensorrt_llm.models.gptforcausallm class method)": [[82, "tensorrt_llm.models.GPTForCausalLM.quantize", false]], "quantize() (tensorrt_llm.models.llamaforcausallm class method)": [[82, "tensorrt_llm.models.LLaMAForCausalLM.quantize", false]], "quantize() (tensorrt_llm.models.pretrainedmodel class method)": [[82, "tensorrt_llm.models.PretrainedModel.quantize", false]], "quantize_and_export() (in module tensorrt_llm.quantization)": [[84, "tensorrt_llm.quantization.quantize_and_export", false]], "quantmode (class in tensorrt_llm.quantization)": [[84, "tensorrt_llm.quantization.QuantMode", false]], "quick_gelu() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.quick_gelu", false]], "qwenforcausallmgenerationsession (class in tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.QWenForCausalLMGenerationSession", false]], "rand() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.rand", false]], "random_seed (tensorrt_llm.llmapi.calibconfig attribute)": [[68, "tensorrt_llm.llmapi.CalibConfig.random_seed", false]], "random_seed (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.random_seed", false]], "rank() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.rank", false]], "rearrange() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.rearrange", false]], "recurrentgemmaforcausallm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.RecurrentGemmaForCausalLM", false]], "recv() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.recv", false]], "redrafter_draft_len_per_beam (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.redrafter_draft_len_per_beam", false]], "redrafter_num_beams (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.redrafter_num_beams", false]], "redrafterforllamalm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.ReDrafterForLLaMALM", false]], "redrafterforqwenlm (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.ReDrafterForQWenLM", false]], "reduce() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.reduce", false]], "reduce_scatter() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.reduce_scatter", false]], "regex (tensorrt_llm.llmapi.guideddecodingparams attribute)": [[68, "tensorrt_llm.llmapi.GuidedDecodingParams.regex", false]], "relative (tensorrt_llm.functional.positionembeddingtype attribute)": [[80, "tensorrt_llm.functional.PositionEmbeddingType.relative", false]], "relaxed_delta (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.MTPDecodingConfig.relaxed_delta", false]], "relaxed_topk (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.MTPDecodingConfig.relaxed_topk", false]], "release() (tensorrt_llm.models.pretrainedmodel method)": [[82, "tensorrt_llm.models.PretrainedModel.release", false]], "relu() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.relu", false]], "remove_input_padding (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.remove_input_padding", false]], "remove_input_padding (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.remove_input_padding", false]], "remove_input_padding (tensorrt_llm.runtime.modelrunner property)": [[85, "tensorrt_llm.runtime.ModelRunner.remove_input_padding", false]], "remove_input_padding (tensorrt_llm.runtime.modelrunnercpp property)": [[85, "tensorrt_llm.runtime.ModelRunnerCpp.remove_input_padding", false]], "reorder_kv_cache_for_beam_search() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.reorder_kv_cache_for_beam_search", false]], "repeat() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.repeat", false]], "repeat() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.repeat", false]], "repeat_interleave() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.repeat_interleave", false]], "repetition_penalty (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.repetition_penalty", false]], "repetition_penalty (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.repetition_penalty", false]], "replace_all_uses_with() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.replace_all_uses_with", false]], "request_id (tensorrt_llm.llmapi.requestoutput attribute)": [[68, "tensorrt_llm.llmapi.RequestOutput.request_id", false]], "request_perf_metrics (tensorrt_llm.llmapi.completionoutput attribute)": [[68, "tensorrt_llm.llmapi.CompletionOutput.request_perf_metrics", false]], "request_type (tensorrt_llm.llmapi.disaggregatedparams attribute)": [[68, "tensorrt_llm.llmapi.DisaggregatedParams.request_type", false]], "requesterror (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.RequestError", false]], "requestoutput (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.RequestOutput", false]], "residual_rms_norm (tensorrt_llm.functional.allreducefusionop attribute)": [[80, "tensorrt_llm.functional.AllReduceFusionOp.RESIDUAL_RMS_NORM", false]], "residual_rms_norm_out_quant_fp8 (tensorrt_llm.functional.allreducefusionop attribute)": [[80, "tensorrt_llm.functional.AllReduceFusionOp.RESIDUAL_RMS_NORM_OUT_QUANT_FP8", false]], "residual_rms_norm_out_quant_nvfp4 (tensorrt_llm.functional.allreducefusionop attribute)": [[80, "tensorrt_llm.functional.AllReduceFusionOp.RESIDUAL_RMS_NORM_OUT_QUANT_NVFP4", false]], "residual_rms_norm_quant_fp8 (tensorrt_llm.functional.allreducefusionop attribute)": [[80, "tensorrt_llm.functional.AllReduceFusionOp.RESIDUAL_RMS_NORM_QUANT_FP8", false]], "residual_rms_norm_quant_nvfp4 (tensorrt_llm.functional.allreducefusionop attribute)": [[80, "tensorrt_llm.functional.AllReduceFusionOp.RESIDUAL_RMS_NORM_QUANT_NVFP4", false]], "residual_rms_prepost_norm (tensorrt_llm.functional.allreducefusionop attribute)": [[80, "tensorrt_llm.functional.AllReduceFusionOp.RESIDUAL_RMS_PREPOST_NORM", false]], "return_context_logits (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.return_context_logits", false]], "return_dict (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.return_dict", false]], "return_encoder_output (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.return_encoder_output", false]], "return_generation_logits (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.return_generation_logits", false]], "return_perf_metrics (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.return_perf_metrics", false]], "rg_lru() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.rg_lru", false]], "rms_norm() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.rms_norm", false]], "rmsnorm (class in tensorrt_llm.layers.normalization)": [[81, "tensorrt_llm.layers.normalization.RmsNorm", false]], "rmsnorm (tensorrt_llm.functional.layernormtype attribute)": [[80, "tensorrt_llm.functional.LayerNormType.RmsNorm", false]], "rnn_conv_dim_size (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.rnn_conv_dim_size", false]], "rnn_conv_dim_size (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.rnn_conv_dim_size", false]], "rnn_head_size (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.rnn_head_size", false]], "rnn_head_size (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.rnn_head_size", false]], "rnn_hidden_size (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.rnn_hidden_size", false]], "rnn_hidden_size (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.rnn_hidden_size", false]], "robertaforquestionanswering (in module tensorrt_llm.models)": [[82, "tensorrt_llm.models.RobertaForQuestionAnswering", false]], "robertaforsequenceclassification (in module tensorrt_llm.models)": [[82, "tensorrt_llm.models.RobertaForSequenceClassification", false]], "robertamodel (in module tensorrt_llm.models)": [[82, "tensorrt_llm.models.RobertaModel", false]], "rope_gpt_neox (tensorrt_llm.functional.positionembeddingtype attribute)": [[80, "tensorrt_llm.functional.PositionEmbeddingType.rope_gpt_neox", false]], "rope_gptj (tensorrt_llm.functional.positionembeddingtype attribute)": [[80, "tensorrt_llm.functional.PositionEmbeddingType.rope_gptj", false]], "ropeembeddingutils (class in tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.RopeEmbeddingUtils", false]], "rotaryscalingtype (class in tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.RotaryScalingType", false]], "rotate_every_two() (tensorrt_llm.functional.ropeembeddingutils static method)": [[80, "tensorrt_llm.functional.RopeEmbeddingUtils.rotate_every_two", false]], "rotate_half() (tensorrt_llm.functional.ropeembeddingutils static method)": [[80, "tensorrt_llm.functional.RopeEmbeddingUtils.rotate_half", false]], "round() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.round", false]], "rowlinear (class in tensorrt_llm.layers.linear)": [[81, "tensorrt_llm.layers.linear.RowLinear", false]], "run() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.run", false]], "run() (tensorrt_llm.runtime.session method)": [[85, "tensorrt_llm.runtime.Session.run", false]], "runtime (tensorrt_llm.runtime.generationsession attribute)": [[85, "tensorrt_llm.runtime.GenerationSession.runtime", false]], "runtime (tensorrt_llm.runtime.session property)": [[85, "tensorrt_llm.runtime.Session.runtime", false]], "samplingconfig (class in tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.SamplingConfig", false]], "samplingparams (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.SamplingParams", false]], "save_checkpoint() (tensorrt_llm.models.llavanextvisionwrapper method)": [[82, "tensorrt_llm.models.LlavaNextVisionWrapper.save_checkpoint", false]], "save_checkpoint() (tensorrt_llm.models.pretrainedmodel method)": [[82, "tensorrt_llm.models.PretrainedModel.save_checkpoint", false]], "scatter() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.scatter", false]], "scatter_nd() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.scatter_nd", false]], "schedulerconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.SchedulerConfig", false]], "sd35adalayernormzerox (class in tensorrt_llm.layers.normalization)": [[81, "tensorrt_llm.layers.normalization.SD35AdaLayerNormZeroX", false]], "sd3patchembed (class in tensorrt_llm.layers.embedding)": [[81, "tensorrt_llm.layers.embedding.SD3PatchEmbed", false]], "sd3transformer2dmodel (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.SD3Transformer2DModel", false]], "secondary_offload_min_priority (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[68, "tensorrt_llm.llmapi.KvCacheConfig.secondary_offload_min_priority", false]], "seed (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.seed", false]], "select() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.select", false]], "select() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.select", false]], "selective_scan() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.selective_scan", false]], "send() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.send", false]], "serialize_engine() (tensorrt_llm.runtime.modelrunner method)": [[85, "tensorrt_llm.runtime.ModelRunner.serialize_engine", false]], "session (class in tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.Session", false]], "set_attn_processor() (tensorrt_llm.models.sd3transformer2dmodel method)": [[82, "tensorrt_llm.models.SD3Transformer2DModel.set_attn_processor", false]], "set_from_optional (c macro)": [[1, "c.SET_FROM_OPTIONAL", false]], "set_if_not_exist() (tensorrt_llm.models.pretrainedconfig method)": [[82, "tensorrt_llm.models.PretrainedConfig.set_if_not_exist", false]], "set_rank() (tensorrt_llm.models.pretrainedconfig method)": [[82, "tensorrt_llm.models.PretrainedConfig.set_rank", false]], "set_rel_attn_table() (tensorrt_llm.layers.attention.attention method)": [[81, "tensorrt_llm.layers.attention.Attention.set_rel_attn_table", false]], "set_shapes() (tensorrt_llm.runtime.session method)": [[85, "tensorrt_llm.runtime.Session.set_shapes", false]], "setup() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.setup", false]], "setup_embedding_parallel_mode() (tensorrt_llm.llmapi.trtllmargs method)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.setup_embedding_parallel_mode", false]], "setup_fake_prompts() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.setup_fake_prompts", false]], "setup_fake_prompts_qwen2vl() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.setup_fake_prompts_qwen2vl", false]], "setup_fake_prompts_vila() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.setup_fake_prompts_vila", false]], "setup_inputs() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.setup_inputs", false]], "shape (tensorrt_llm.functional.tensor property)": [[80, "tensorrt_llm.functional.Tensor.shape", false]], "shape (tensorrt_llm.runtime.tensorinfo attribute)": [[85, "tensorrt_llm.runtime.TensorInfo.shape", false]], "shape() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.shape", false]], "shutdown() (tensorrt_llm.llmapi.llm method)": [[68, "tensorrt_llm.llmapi.LLM.shutdown", false]], "shutdown() (tensorrt_llm.llmapi.mpicommsession method)": [[68, "tensorrt_llm.llmapi.MpiCommSession.shutdown", false]], "sidestreamidtype (class in tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.SideStreamIDType", false]], "sigmoid() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.sigmoid", false]], "silu() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.silu", false]], "sin() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.sin", false]], "sink_token_length (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[68, "tensorrt_llm.llmapi.KvCacheConfig.sink_token_length", false]], "sink_token_length (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.sink_token_length", false]], "size (tensorrt_llm.functional.sliceinputtype attribute)": [[80, "tensorrt_llm.functional.SliceInputType.size", false]], "size() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.size", false]], "skip_cross_attn_blocks (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.skip_cross_attn_blocks", false]], "skip_cross_kv (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.skip_cross_kv", false]], "skip_special_tokens (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.skip_special_tokens", false]], "slice() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.slice", false]], "sliceinputtype (class in tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.SliceInputType", false]], "sliding_window_causal (tensorrt_llm.functional.attentionmasktype attribute)": [[80, "tensorrt_llm.functional.AttentionMaskType.sliding_window_causal", false]], "smoothquant_val (tensorrt_llm.llmapi.quantconfig attribute)": [[68, "tensorrt_llm.llmapi.QuantConfig.smoothquant_val", false]], "softmax() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.softmax", false]], "softplus() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.softplus", false]], "spaces_between_special_tokens (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.spaces_between_special_tokens", false]], "spec_dec_mode (tensorrt_llm.llmapi.eagledecodingconfig property)": [[68, "tensorrt_llm.llmapi.EagleDecodingConfig.spec_dec_mode", false]], "spec_dec_mode (tensorrt_llm.llmapi.mtpdecodingconfig property)": [[68, "tensorrt_llm.llmapi.MTPDecodingConfig.spec_dec_mode", false]], "specdecodingparams (class in tensorrt_llm.layers.attention)": [[81, "tensorrt_llm.layers.attention.SpecDecodingParams", false]], "speculative_decoding_mode (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.speculative_decoding_mode", false]], "speculativedecodingmode (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.SpeculativeDecodingMode", false]], "split() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.split", false]], "split() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.split", false]], "split_prompt_by_images() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.split_prompt_by_images", false]], "sqrt() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.sqrt", false]], "sqrt() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.sqrt", false]], "squared_relu() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.squared_relu", false]], "squeeze() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.squeeze", false]], "squeeze() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.squeeze", false]], "squeeze() (tensorrt_llm.runtime.tensorinfo method)": [[85, "tensorrt_llm.runtime.TensorInfo.squeeze", false]], "stack() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.stack", false]], "start (tensorrt_llm.functional.sliceinputtype attribute)": [[80, "tensorrt_llm.functional.SliceInputType.start", false]], "state_dtype (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.state_dtype", false]], "state_dtype (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.state_dtype", false]], "state_size (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.state_size", false]], "state_size (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.state_size", false]], "static (tensorrt_llm.llmapi.batchingtype attribute)": [[68, "tensorrt_llm.llmapi.BatchingType.STATIC", false]], "static_batch (tensorrt_llm.llmapi.capacityschedulerpolicy attribute)": [[68, "tensorrt_llm.llmapi.CapacitySchedulerPolicy.STATIC_BATCH", false]], "step() (tensorrt_llm.runtime.kvcachemanager method)": [[85, "tensorrt_llm.runtime.KVCacheManager.step", false]], "stop (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.stop", false]], "stop_reason (tensorrt_llm.llmapi.completionoutput attribute)": [[68, "tensorrt_llm.llmapi.CompletionOutput.stop_reason", false]], "stop_token_ids (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.stop_token_ids", false]], "stop_words_list (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.stop_words_list", false]], "stoppingcriteria (class in tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.StoppingCriteria", false]], "stoppingcriterialist (class in tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.StoppingCriteriaList", false]], "stream_interval (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.stream_interval", false]], "stride (tensorrt_llm.functional.sliceinputtype attribute)": [[80, "tensorrt_llm.functional.SliceInputType.stride", false]], "strongly_typed (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.strongly_typed", false]], "structural_tag (tensorrt_llm.llmapi.guideddecodingparams attribute)": [[68, "tensorrt_llm.llmapi.GuidedDecodingParams.structural_tag", false]], "sub() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.sub", false]], "submit() (tensorrt_llm.llmapi.mpicommsession method)": [[68, "tensorrt_llm.llmapi.MpiCommSession.submit", false]], "submit_sync() (tensorrt_llm.llmapi.mpicommsession method)": [[68, "tensorrt_llm.llmapi.MpiCommSession.submit_sync", false]], "sum() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.sum", false]], "supports_backend() (tensorrt_llm.llmapi.drafttargetdecodingconfig method)": [[68, "tensorrt_llm.llmapi.DraftTargetDecodingConfig.supports_backend", false]], "supports_backend() (tensorrt_llm.llmapi.lookaheaddecodingconfig method)": [[68, "tensorrt_llm.llmapi.LookaheadDecodingConfig.supports_backend", false]], "supports_backend() (tensorrt_llm.llmapi.medusadecodingconfig method)": [[68, "tensorrt_llm.llmapi.MedusaDecodingConfig.supports_backend", false]], "supports_backend() (tensorrt_llm.llmapi.mtpdecodingconfig method)": [[68, "tensorrt_llm.llmapi.MTPDecodingConfig.supports_backend", false]], "supports_backend() (tensorrt_llm.llmapi.ngramdecodingconfig method)": [[68, "tensorrt_llm.llmapi.NGramDecodingConfig.supports_backend", false]], "swiglu() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.swiglu", false]], "tanh() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.tanh", false]], "temperature (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.temperature", false]], "temperature (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.temperature", false]], "tensor (class in tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.Tensor", false]], "tensorinfo (class in tensorrt_llm.runtime)": [[85, "tensorrt_llm.runtime.TensorInfo", false]], "tensorrt_llm": [[80, "module-tensorrt_llm", false], [81, "module-tensorrt_llm", false], [82, "module-tensorrt_llm", false], [83, "module-tensorrt_llm", false], [84, "module-tensorrt_llm", false], [85, "module-tensorrt_llm", false]], "tensorrt_llm (c++ type)": [[0, "_CPPv412tensorrt_llm", false], [1, "_CPPv412tensorrt_llm", false]], "tensorrt_llm.functional": [[80, "module-tensorrt_llm.functional", false]], "tensorrt_llm.layers.activation": [[81, "module-tensorrt_llm.layers.activation", false]], "tensorrt_llm.layers.attention": [[81, "module-tensorrt_llm.layers.attention", false]], "tensorrt_llm.layers.cast": [[81, "module-tensorrt_llm.layers.cast", false]], "tensorrt_llm.layers.conv": [[81, "module-tensorrt_llm.layers.conv", false]], "tensorrt_llm.layers.embedding": [[81, "module-tensorrt_llm.layers.embedding", false]], "tensorrt_llm.layers.linear": [[81, "module-tensorrt_llm.layers.linear", false]], "tensorrt_llm.layers.mlp": [[81, "module-tensorrt_llm.layers.mlp", false]], "tensorrt_llm.layers.normalization": [[81, "module-tensorrt_llm.layers.normalization", false]], "tensorrt_llm.layers.pooling": [[81, "module-tensorrt_llm.layers.pooling", false]], "tensorrt_llm.models": [[82, "module-tensorrt_llm.models", false]], "tensorrt_llm.plugin": [[83, "module-tensorrt_llm.plugin", false]], "tensorrt_llm.quantization": [[84, "module-tensorrt_llm.quantization", false]], "tensorrt_llm.runtime": [[85, "module-tensorrt_llm.runtime", false]], "tensorrt_llm::batch_manager (c++ type)": [[0, "_CPPv4N12tensorrt_llm13batch_managerE", false], [1, "_CPPv4N12tensorrt_llm13batch_managerE", false]], "tensorrt_llm::batch_manager::kv_cache_manager (c++ type)": [[0, "_CPPv4N12tensorrt_llm13batch_manager16kv_cache_managerE", false]], "tensorrt_llm::executor (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executorE", false]], "tensorrt_llm::executor::additionalmodeloutput (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutputE", false]], "tensorrt_llm::executor::additionalmodeloutput::additionalmodeloutput (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutput21AdditionalModelOutputENSt6stringEb", false]], "tensorrt_llm::executor::additionalmodeloutput::gathercontext (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutput13gatherContextE", false]], "tensorrt_llm::executor::additionalmodeloutput::name (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutput4nameE", false]], "tensorrt_llm::executor::additionalmodeloutput::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor21AdditionalModelOutputeqERK21AdditionalModelOutput", false]], "tensorrt_llm::executor::additionaloutput (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputE", false]], "tensorrt_llm::executor::additionaloutput::additionaloutput (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputENSt6stringE6Tensor", false], [0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputERK16AdditionalOutput", false], [0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputERR16AdditionalOutput", false]], "tensorrt_llm::executor::additionaloutput::name (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput4nameE", false]], "tensorrt_llm::executor::additionaloutput::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputaSERK16AdditionalOutput", false], [0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputaSERR16AdditionalOutput", false]], "tensorrt_llm::executor::additionaloutput::output (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput6outputE", false]], "tensorrt_llm::executor::additionaloutput::~additionaloutput (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputD0Ev", false]], "tensorrt_llm::executor::batchingtype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor12BatchingTypeE", false]], "tensorrt_llm::executor::batchingtype::kinflight (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12BatchingType9kINFLIGHTE", false]], "tensorrt_llm::executor::batchingtype::kstatic (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12BatchingType7kSTATICE", false]], "tensorrt_llm::executor::beamtokens (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor10BeamTokensE", false]], "tensorrt_llm::executor::bufferview (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor10BufferViewE", false]], "tensorrt_llm::executor::cachetransceiverconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfigE", false]], "tensorrt_llm::executor::cachetransceiverconfig::cachetransceiverconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig22CacheTransceiverConfigENSt8optionalI6size_tEE", false]], "tensorrt_llm::executor::cachetransceiverconfig::getmaxnumtokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22CacheTransceiverConfig15getMaxNumTokensEv", false]], "tensorrt_llm::executor::cachetransceiverconfig::mmaxnumtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig13mMaxNumTokensE", false]], "tensorrt_llm::executor::cachetransceiverconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22CacheTransceiverConfigeqERK22CacheTransceiverConfig", false]], "tensorrt_llm::executor::cachetransceiverconfig::setmaxnumtokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig15setMaxNumTokensE6size_t", false]], "tensorrt_llm::executor::capacityschedulerpolicy (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicyE", false]], "tensorrt_llm::executor::capacityschedulerpolicy::kguaranteed_no_evict (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicy20kGUARANTEED_NO_EVICTE", false]], "tensorrt_llm::executor::capacityschedulerpolicy::kmax_utilization (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicy16kMAX_UTILIZATIONE", false]], "tensorrt_llm::executor::capacityschedulerpolicy::kstatic_batch (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicy13kSTATIC_BATCHE", false]], "tensorrt_llm::executor::communicationmode (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor17CommunicationModeE", false]], "tensorrt_llm::executor::communicationmode::kleader (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor17CommunicationMode7kLEADERE", false]], "tensorrt_llm::executor::communicationmode::korchestrator (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor17CommunicationMode13kORCHESTRATORE", false]], "tensorrt_llm::executor::communicationtype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor17CommunicationTypeE", false]], "tensorrt_llm::executor::communicationtype::kmpi (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor17CommunicationType4kMPIE", false]], "tensorrt_llm::executor::contextchunkingpolicy (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicyE", false]], "tensorrt_llm::executor::contextchunkingpolicy::kequal_progress (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicy15kEQUAL_PROGRESSE", false]], "tensorrt_llm::executor::contextchunkingpolicy::kfirst_come_first_served (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicy24kFIRST_COME_FIRST_SERVEDE", false]], "tensorrt_llm::executor::contextphaseparams (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsE", false]], "tensorrt_llm::executor::contextphaseparams::contextphaseparams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeNSt8optionalI9VecTokensEE", false], [0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypePvNSt8optionalI9VecTokensEE", false], [0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeRKNSt6vectorIcEENSt8optionalI9VecTokensEE", false], [0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsERK18ContextPhaseParams", false], [0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsERR18ContextPhaseParams", false]], "tensorrt_llm::executor::contextphaseparams::deleter (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams7deleterEPKv", false]], "tensorrt_llm::executor::contextphaseparams::getdrafttokens (c++ function)": [[0, "_CPPv4NKR12tensorrt_llm8executor18ContextPhaseParams14getDraftTokensEv", false]], "tensorrt_llm::executor::contextphaseparams::getfirstgentokens (c++ function)": [[0, "_CPPv4NKR12tensorrt_llm8executor18ContextPhaseParams17getFirstGenTokensEv", false]], "tensorrt_llm::executor::contextphaseparams::getreqid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParams8getReqIdEv", false]], "tensorrt_llm::executor::contextphaseparams::getserializedstate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParams18getSerializedStateEv", false]], "tensorrt_llm::executor::contextphaseparams::getstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams8getStateEv", false], [0, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParams8getStateEv", false]], "tensorrt_llm::executor::contextphaseparams::mdrafttokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams12mDraftTokensE", false]], "tensorrt_llm::executor::contextphaseparams::mfirstgentokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams15mFirstGenTokensE", false]], "tensorrt_llm::executor::contextphaseparams::mreqid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams6mReqIdE", false]], "tensorrt_llm::executor::contextphaseparams::mstate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams6mStateE", false]], "tensorrt_llm::executor::contextphaseparams::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsaSERK18ContextPhaseParams", false], [0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsaSERR18ContextPhaseParams", false]], "tensorrt_llm::executor::contextphaseparams::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParamseqERK18ContextPhaseParams", false]], "tensorrt_llm::executor::contextphaseparams::popfirstgentokens (c++ function)": [[0, "_CPPv4NO12tensorrt_llm8executor18ContextPhaseParams17popFirstGenTokensEv", false]], "tensorrt_llm::executor::contextphaseparams::releasestate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams12releaseStateEv", false]], "tensorrt_llm::executor::contextphaseparams::requestidtype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams13RequestIdTypeE", false]], "tensorrt_llm::executor::contextphaseparams::stateptr (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams8StatePtrE", false]], "tensorrt_llm::executor::contextphaseparams::~contextphaseparams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsD0Ev", false]], "tensorrt_llm::executor::datatransceiverstate (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor20DataTransceiverStateE", false]], "tensorrt_llm::executor::datatransceiverstate::datatransceiverstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState20DataTransceiverStateEN8kv_cache10CacheStateEN8kv_cache9CommStateE", false], [0, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState20DataTransceiverStateEv", false]], "tensorrt_llm::executor::datatransceiverstate::getcachestate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverState13getCacheStateEv", false]], "tensorrt_llm::executor::datatransceiverstate::getcommstate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverState12getCommStateEv", false]], "tensorrt_llm::executor::datatransceiverstate::mcachestate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState11mCacheStateE", false]], "tensorrt_llm::executor::datatransceiverstate::mcommstate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState10mCommStateE", false]], "tensorrt_llm::executor::datatransceiverstate::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverStateeqERK20DataTransceiverState", false]], "tensorrt_llm::executor::datatransceiverstate::setcachestate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState13setCacheStateEN8kv_cache10CacheStateE", false]], "tensorrt_llm::executor::datatransceiverstate::setcommstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState12setCommStateEN8kv_cache9CommStateE", false]], "tensorrt_llm::executor::datatransceiverstate::tostring (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverState8toStringEv", false]], "tensorrt_llm::executor::datatype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor8DataTypeE", false]], "tensorrt_llm::executor::datatype::kbf16 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType5kBF16E", false]], "tensorrt_llm::executor::datatype::kbool (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType5kBOOLE", false]], "tensorrt_llm::executor::datatype::kfp16 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType5kFP16E", false]], "tensorrt_llm::executor::datatype::kfp32 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType5kFP32E", false]], "tensorrt_llm::executor::datatype::kfp8 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType4kFP8E", false]], "tensorrt_llm::executor::datatype::kint32 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType6kINT32E", false]], "tensorrt_llm::executor::datatype::kint64 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType6kINT64E", false]], "tensorrt_llm::executor::datatype::kint8 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType5kINT8E", false]], "tensorrt_llm::executor::datatype::kuint8 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType6kUINT8E", false]], "tensorrt_llm::executor::datatype::kunknown (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType8kUNKNOWNE", false]], "tensorrt_llm::executor::debugconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfigE", false]], "tensorrt_llm::executor::debugconfig::debugconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig11DebugConfigEbb9StringVec10SizeType32", false]], "tensorrt_llm::executor::debugconfig::getdebuginputtensors (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11DebugConfig20getDebugInputTensorsEv", false]], "tensorrt_llm::executor::debugconfig::getdebugoutputtensors (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11DebugConfig21getDebugOutputTensorsEv", false]], "tensorrt_llm::executor::debugconfig::getdebugtensornames (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11DebugConfig19getDebugTensorNamesEv", false]], "tensorrt_llm::executor::debugconfig::getdebugtensorsmaxiterations (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11DebugConfig28getDebugTensorsMaxIterationsEv", false]], "tensorrt_llm::executor::debugconfig::mdebuginputtensors (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig18mDebugInputTensorsE", false]], "tensorrt_llm::executor::debugconfig::mdebugoutputtensors (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig19mDebugOutputTensorsE", false]], "tensorrt_llm::executor::debugconfig::mdebugtensornames (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig17mDebugTensorNamesE", false]], "tensorrt_llm::executor::debugconfig::mdebugtensorsmaxiterations (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig26mDebugTensorsMaxIterationsE", false]], "tensorrt_llm::executor::debugconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11DebugConfigeqERK11DebugConfig", false]], "tensorrt_llm::executor::debugconfig::setdebuginputtensors (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig20setDebugInputTensorsEb", false]], "tensorrt_llm::executor::debugconfig::setdebugoutputtensors (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig21setDebugOutputTensorsEb", false]], "tensorrt_llm::executor::debugconfig::setdebugtensornames (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig19setDebugTensorNamesERK9StringVec", false]], "tensorrt_llm::executor::debugconfig::setdebugtensorsmaxiterations (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig28setDebugTensorsMaxIterationsE10SizeType32", false]], "tensorrt_llm::executor::debugconfig::stringvec (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig9StringVecE", false]], "tensorrt_llm::executor::debugtensorsperiteration (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor24DebugTensorsPerIterationE", false]], "tensorrt_llm::executor::debugtensorsperiteration::debugtensors (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor24DebugTensorsPerIteration12debugTensorsE", false]], "tensorrt_llm::executor::debugtensorsperiteration::iter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor24DebugTensorsPerIteration4iterE", false]], "tensorrt_llm::executor::decodingconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfigE", false]], "tensorrt_llm::executor::decodingconfig::decodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14DecodingConfigENSt8optionalI12DecodingModeEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI13MedusaChoicesEENSt8optionalI11EagleConfigEE", false]], "tensorrt_llm::executor::decodingconfig::enableseamlesslookaheaddecoding (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig31enableSeamlessLookaheadDecodingEv", false]], "tensorrt_llm::executor::decodingconfig::getdecodingmode (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig15getDecodingModeEv", false]], "tensorrt_llm::executor::decodingconfig::geteagleconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig14getEagleConfigEv", false]], "tensorrt_llm::executor::decodingconfig::getlookaheaddecodingconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig26getLookaheadDecodingConfigEv", false]], "tensorrt_llm::executor::decodingconfig::getlookaheaddecodingmaxnumrequest (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig33getLookaheadDecodingMaxNumRequestEv", false]], "tensorrt_llm::executor::decodingconfig::getmedusachoices (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig16getMedusaChoicesEv", false]], "tensorrt_llm::executor::decodingconfig::mdecodingmode (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig13mDecodingModeE", false]], "tensorrt_llm::executor::decodingconfig::meagleconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig12mEagleConfigE", false]], "tensorrt_llm::executor::decodingconfig::mlookaheaddecodingconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig24mLookaheadDecodingConfigE", false]], "tensorrt_llm::executor::decodingconfig::mlookaheaddecodingmaxnumrequest (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig31mLookaheadDecodingMaxNumRequestE", false]], "tensorrt_llm::executor::decodingconfig::mmedusachoices (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14mMedusaChoicesE", false]], "tensorrt_llm::executor::decodingconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14DecodingConfigeqERK14DecodingConfig", false]], "tensorrt_llm::executor::decodingconfig::setdecodingmode (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig15setDecodingModeERK12DecodingMode", false]], "tensorrt_llm::executor::decodingconfig::seteagleconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14setEagleConfigERK11EagleConfig", false]], "tensorrt_llm::executor::decodingconfig::setlookaheaddecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig26setLookaheadDecodingConfigERK23LookaheadDecodingConfig", false]], "tensorrt_llm::executor::decodingconfig::setmedusachoices (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig16setMedusaChoicesERK13MedusaChoices", false]], "tensorrt_llm::executor::decodingmode (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingModeE", false]], "tensorrt_llm::executor::decodingmode::allbitset (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9allBitSetE14UnderlyingType", false]], "tensorrt_llm::executor::decodingmode::anybitset (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9anyBitSetE14UnderlyingType", false]], "tensorrt_llm::executor::decodingmode::auto (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode4AutoEv", false]], "tensorrt_llm::executor::decodingmode::beamsearch (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode10BeamSearchEv", false]], "tensorrt_llm::executor::decodingmode::decodingmode (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode12DecodingModeE14UnderlyingType", false]], "tensorrt_llm::executor::decodingmode::eagle (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode5EagleEv", false]], "tensorrt_llm::executor::decodingmode::explicitdrafttokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode19ExplicitDraftTokensEv", false]], "tensorrt_llm::executor::decodingmode::externaldrafttokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode19ExternalDraftTokensEv", false]], "tensorrt_llm::executor::decodingmode::getname (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode7getNameEv", false]], "tensorrt_llm::executor::decodingmode::getstate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode8getStateEv", false]], "tensorrt_llm::executor::decodingmode::isauto (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isAutoEv", false]], "tensorrt_llm::executor::decodingmode::isbeamsearch (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isBeamSearchEv", false]], "tensorrt_llm::executor::decodingmode::iseagle (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode7isEagleEv", false]], "tensorrt_llm::executor::decodingmode::isexplicitdrafttokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode21isExplicitDraftTokensEv", false]], "tensorrt_llm::executor::decodingmode::isexternaldrafttokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode21isExternalDraftTokensEv", false]], "tensorrt_llm::executor::decodingmode::islookahead (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode11isLookaheadEv", false]], "tensorrt_llm::executor::decodingmode::ismedusa (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode8isMedusaEv", false]], "tensorrt_llm::executor::decodingmode::istopk (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isTopKEv", false]], "tensorrt_llm::executor::decodingmode::istopkandtopp (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode13isTopKandTopPEv", false]], "tensorrt_llm::executor::decodingmode::istopkortopp (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isTopKorTopPEv", false]], "tensorrt_llm::executor::decodingmode::istopp (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isTopPEv", false]], "tensorrt_llm::executor::decodingmode::isusebantokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseBanTokensEv", false]], "tensorrt_llm::executor::decodingmode::isusebanwords (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode13isUseBanWordsEv", false]], "tensorrt_llm::executor::decodingmode::isuseexpliciteosstop (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode20isUseExplicitEosStopEv", false]], "tensorrt_llm::executor::decodingmode::isusefrequencypenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode21isUseFrequencyPenaltyEv", false]], "tensorrt_llm::executor::decodingmode::isusemaxlengthstop (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode18isUseMaxLengthStopEv", false]], "tensorrt_llm::executor::decodingmode::isuseminlength (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseMinLengthEv", false]], "tensorrt_llm::executor::decodingmode::isuseminp (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9isUseMinPEv", false]], "tensorrt_llm::executor::decodingmode::isusenorepeatngramsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseNoRepeatNgramSizeEv", false]], "tensorrt_llm::executor::decodingmode::isuseoccurrencepenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseOccurrencePenaltyEv", false]], "tensorrt_llm::executor::decodingmode::isusepenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isUsePenaltyEv", false]], "tensorrt_llm::executor::decodingmode::isusepresencepenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode20isUsePresencePenaltyEv", false]], "tensorrt_llm::executor::decodingmode::isuserepetitionpenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseRepetitionPenaltyEv", false]], "tensorrt_llm::executor::decodingmode::isusestopcriteria (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode17isUseStopCriteriaEv", false]], "tensorrt_llm::executor::decodingmode::isusestopwords (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseStopWordsEv", false]], "tensorrt_llm::executor::decodingmode::isusetemperature (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode16isUseTemperatureEv", false]], "tensorrt_llm::executor::decodingmode::isusevariablebeamwidthsearch (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode28isUseVariableBeamWidthSearchEv", false]], "tensorrt_llm::executor::decodingmode::kauto (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kAutoE", false]], "tensorrt_llm::executor::decodingmode::kbeamsearch (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode11kBeamSearchE", false]], "tensorrt_llm::executor::decodingmode::keagle (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode6kEagleE", false]], "tensorrt_llm::executor::decodingmode::kexplicitdrafttokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode20kExplicitDraftTokensE", false]], "tensorrt_llm::executor::decodingmode::kexternaldrafttokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode20kExternalDraftTokensE", false]], "tensorrt_llm::executor::decodingmode::klookahead (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode10kLookaheadE", false]], "tensorrt_llm::executor::decodingmode::kmedusa (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode7kMedusaE", false]], "tensorrt_llm::executor::decodingmode::knumflags (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode9kNumFlagsE", false]], "tensorrt_llm::executor::decodingmode::ktopk (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kTopKE", false]], "tensorrt_llm::executor::decodingmode::ktopktopp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode9kTopKTopPE", false]], "tensorrt_llm::executor::decodingmode::ktopp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kTopPE", false]], "tensorrt_llm::executor::decodingmode::kusebantokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseBanTokensE", false]], "tensorrt_llm::executor::decodingmode::kusebanwords (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode12kUseBanWordsE", false]], "tensorrt_llm::executor::decodingmode::kuseexpliciteosstop (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode19kUseExplicitEosStopE", false]], "tensorrt_llm::executor::decodingmode::kusefrequencypenalties (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode22kUseFrequencyPenaltiesE", false]], "tensorrt_llm::executor::decodingmode::kusemaxlengthstop (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode17kUseMaxLengthStopE", false]], "tensorrt_llm::executor::decodingmode::kuseminlength (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseMinLengthE", false]], "tensorrt_llm::executor::decodingmode::kuseminp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode8kUseMinPE", false]], "tensorrt_llm::executor::decodingmode::kusenorepeatngramsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode21kUseNoRepeatNgramSizeE", false]], "tensorrt_llm::executor::decodingmode::kuseoccurrencepenalties (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode23kUseOccurrencePenaltiesE", false]], "tensorrt_llm::executor::decodingmode::kusepenalties (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUsePenaltiesE", false]], "tensorrt_llm::executor::decodingmode::kusepresencepenalties (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode21kUsePresencePenaltiesE", false]], "tensorrt_llm::executor::decodingmode::kuserepetitionpenalties (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode23kUseRepetitionPenaltiesE", false]], "tensorrt_llm::executor::decodingmode::kusestandardstopcriteria (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode24kUseStandardStopCriteriaE", false]], "tensorrt_llm::executor::decodingmode::kusestopwords (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseStopWordsE", false]], "tensorrt_llm::executor::decodingmode::kusetemperature (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode15kUseTemperatureE", false]], "tensorrt_llm::executor::decodingmode::kusevariablebeamwidthsearch (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode27kUseVariableBeamWidthSearchE", false]], "tensorrt_llm::executor::decodingmode::lookahead (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode9LookaheadEv", false]], "tensorrt_llm::executor::decodingmode::medusa (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode6MedusaEv", false]], "tensorrt_llm::executor::decodingmode::mstate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode6mStateE", false]], "tensorrt_llm::executor::decodingmode::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingModeeqERK12DecodingMode", false]], "tensorrt_llm::executor::decodingmode::setbitto (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode8setBitToE14UnderlyingTypeb", false]], "tensorrt_llm::executor::decodingmode::topk (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode4TopKEv", false]], "tensorrt_llm::executor::decodingmode::topktopp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode8TopKTopPEv", false]], "tensorrt_llm::executor::decodingmode::topp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode4TopPEv", false]], "tensorrt_llm::executor::decodingmode::underlyingtype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode14UnderlyingTypeE", false]], "tensorrt_llm::executor::decodingmode::usebantokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useBanTokensEb", false]], "tensorrt_llm::executor::decodingmode::usebanwords (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode11useBanWordsEb", false]], "tensorrt_llm::executor::decodingmode::useexpliciteosstop (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode18useExplicitEosStopEb", false]], "tensorrt_llm::executor::decodingmode::usefrequencypenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode19useFrequencyPenaltyEb", false]], "tensorrt_llm::executor::decodingmode::usemaxlengthstop (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode16useMaxLengthStopEb", false]], "tensorrt_llm::executor::decodingmode::useminlength (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useMinLengthEb", false]], "tensorrt_llm::executor::decodingmode::useminp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode7useMinPEb", false]], "tensorrt_llm::executor::decodingmode::usenorepeatngramsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useNoRepeatNgramSizeEb", false]], "tensorrt_llm::executor::decodingmode::useoccurrencepenalties (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode22useOccurrencePenaltiesEb", false]], "tensorrt_llm::executor::decodingmode::usepresencepenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode18usePresencePenaltyEb", false]], "tensorrt_llm::executor::decodingmode::userepetitionpenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useRepetitionPenaltyEb", false]], "tensorrt_llm::executor::decodingmode::usestopwords (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useStopWordsEb", false]], "tensorrt_llm::executor::decodingmode::usetemperature (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode14useTemperatureEb", false]], "tensorrt_llm::executor::decodingmode::usevariablebeamwidthsearch (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode26useVariableBeamWidthSearchEb", false]], "tensorrt_llm::executor::detail (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor6detailE", false]], "tensorrt_llm::executor::detail::dimtype64 (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor6detail9DimType64E", false]], "tensorrt_llm::executor::detail::ofitensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE", false]], "tensorrt_llm::executor::detail::toitensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6detail9toITensorERK6Tensor", false]], "tensorrt_llm::executor::disagg_executor (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executorE", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestratorE", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::awaitcontextresponses (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator21awaitContextResponsesERKNSt8optionalINSt6chrono12millisecondsEEENSt8optionalIiEE", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::awaitgenerationresponses (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator24awaitGenerationResponsesERKNSt8optionalINSt6chrono12millisecondsEEENSt8optionalIiEE", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::canenqueue (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator10canEnqueueEv", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::disaggexecutororchestrator (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator26DisaggExecutorOrchestratorERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorIN8executor14ExecutorConfigEEERKNSt6vectorIN8executor14ExecutorConfigEEEbb", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::enqueuecontext (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator14enqueueContextERKNSt6vectorIN5texec7RequestEEENSt8optionalIiEEb", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::enqueuegeneration (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator17enqueueGenerationERKNSt6vectorIN5texec7RequestEEERKNSt6vectorI6IdTypeEENSt8optionalIiEEb", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::getcontextexecutors (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator19getContextExecutorsEv", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::getgenexecutors (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator15getGenExecutorsEv", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::mimpl (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator5mImplE", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::~disaggexecutororchestrator (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestratorD0Ev", false]], "tensorrt_llm::executor::disagg_executor::responsewithid (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdE", false]], "tensorrt_llm::executor::disagg_executor::responsewithid::gid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId3gidE", false]], "tensorrt_llm::executor::disagg_executor::responsewithid::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdaSERK14ResponseWithId", false], [0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdaSERR14ResponseWithId", false]], "tensorrt_llm::executor::disagg_executor::responsewithid::response (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId8responseE", false]], "tensorrt_llm::executor::disagg_executor::responsewithid::responsewithid (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERK14ResponseWithId", false], [0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERKN12tensorrt_llm8executor8ResponseE6IdType", false], [0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERR14ResponseWithId", false], [0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERRN12tensorrt_llm8executor8ResponseE6IdType", false]], "tensorrt_llm::executor::disagg_executor::responsewithid::~responsewithid (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdD0Ev", false]], "tensorrt_llm::executor::disservingrequeststats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor22DisServingRequestStatsE", false]], "tensorrt_llm::executor::disservingrequeststats::kvcachesize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22DisServingRequestStats11kvCacheSizeE", false]], "tensorrt_llm::executor::disservingrequeststats::kvcachetransferms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22DisServingRequestStats17kvCacheTransferMSE", false]], "tensorrt_llm::executor::dynamicbatchconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfigE", false]], "tensorrt_llm::executor::dynamicbatchconfig::dynamicbatchconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig18DynamicBatchConfigEbb10SizeType32NSt6vectorINSt4pairI10SizeType3210SizeType32EEEE", false]], "tensorrt_llm::executor::dynamicbatchconfig::getbatchsizetable (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18DynamicBatchConfig17getBatchSizeTableEv", false]], "tensorrt_llm::executor::dynamicbatchconfig::getdynamicbatchmovingaveragewindow (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18DynamicBatchConfig34getDynamicBatchMovingAverageWindowEv", false]], "tensorrt_llm::executor::dynamicbatchconfig::getenablebatchsizetuning (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18DynamicBatchConfig24getEnableBatchSizeTuningEv", false]], "tensorrt_llm::executor::dynamicbatchconfig::getenablemaxnumtokenstuning (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18DynamicBatchConfig27getEnableMaxNumTokensTuningEv", false]], "tensorrt_llm::executor::dynamicbatchconfig::kdefaultbatchsizetable (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig22kDefaultBatchSizeTableE", false]], "tensorrt_llm::executor::dynamicbatchconfig::kdefaultdynamicbatchmovingaveragewindow (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig39kDefaultDynamicBatchMovingAverageWindowE", false]], "tensorrt_llm::executor::dynamicbatchconfig::mbatchsizetable (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig15mBatchSizeTableE", false]], "tensorrt_llm::executor::dynamicbatchconfig::mdynamicbatchmovingaveragewindow (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig32mDynamicBatchMovingAverageWindowE", false]], "tensorrt_llm::executor::dynamicbatchconfig::menablebatchsizetuning (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig22mEnableBatchSizeTuningE", false]], "tensorrt_llm::executor::dynamicbatchconfig::menablemaxnumtokenstuning (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig25mEnableMaxNumTokensTuningE", false]], "tensorrt_llm::executor::eaglechoices (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor12EagleChoicesE", false]], "tensorrt_llm::executor::eagleconfig (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor11EagleConfigE", false]], "tensorrt_llm::executor::eagleconfig::checkposteriorvalue (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11EagleConfig19checkPosteriorValueERKNSt8optionalIfEE", false]], "tensorrt_llm::executor::eagleconfig::eagleconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11EagleConfig11EagleConfigENSt8optionalI12EagleChoicesEEbNSt8optionalIfEEbNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::eagleconfig::getdynamictreemaxtopk (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11EagleConfig21getDynamicTreeMaxTopKEv", false]], "tensorrt_llm::executor::eagleconfig::geteaglechoices (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11EagleConfig15getEagleChoicesEv", false]], "tensorrt_llm::executor::eagleconfig::getposteriorthreshold (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11EagleConfig21getPosteriorThresholdEv", false]], "tensorrt_llm::executor::eagleconfig::isgreedysampling (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11EagleConfig16isGreedySamplingEv", false]], "tensorrt_llm::executor::eagleconfig::mdynamictreemaxtopk (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11EagleConfig19mDynamicTreeMaxTopKE", false]], "tensorrt_llm::executor::eagleconfig::meaglechoices (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11EagleConfig13mEagleChoicesE", false]], "tensorrt_llm::executor::eagleconfig::mgreedysampling (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11EagleConfig15mGreedySamplingE", false]], "tensorrt_llm::executor::eagleconfig::mposteriorthreshold (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11EagleConfig19mPosteriorThresholdE", false]], "tensorrt_llm::executor::eagleconfig::musedynamictree (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11EagleConfig15mUseDynamicTreeE", false]], "tensorrt_llm::executor::eagleconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11EagleConfigeqERK11EagleConfig", false]], "tensorrt_llm::executor::eagleconfig::usedynamictree (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11EagleConfig14useDynamicTreeEv", false]], "tensorrt_llm::executor::executor (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8ExecutorE", false]], "tensorrt_llm::executor::executor::awaitresponses (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERK6IdTypeRKNSt8optionalINSt6chrono12millisecondsEEE", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt6vectorI6IdTypeEERKNSt8optionalINSt6chrono12millisecondsEEE", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt8optionalINSt6chrono12millisecondsEEE", false]], "tensorrt_llm::executor::executor::cancelrequest (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor13cancelRequestE6IdType", false]], "tensorrt_llm::executor::executor::canenqueuerequests (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Executor18canEnqueueRequestsEv", false]], "tensorrt_llm::executor::executor::enqueuerequest (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor14enqueueRequestERK7Request", false]], "tensorrt_llm::executor::executor::enqueuerequests (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor15enqueueRequestsERKNSt6vectorI7RequestEE", false]], "tensorrt_llm::executor::executor::executor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEENSt10shared_ptrI5ModelEERK14ExecutorConfig", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEERK14ExecutorConfig", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK8Executor", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERR8Executor", false]], "tensorrt_llm::executor::executor::getkvcacheeventmanager (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Executor22getKVCacheEventManagerEv", false]], "tensorrt_llm::executor::executor::getlatestdebugtensors (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor21getLatestDebugTensorsEv", false]], "tensorrt_llm::executor::executor::getlatestiterationstats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor23getLatestIterationStatsEv", false]], "tensorrt_llm::executor::executor::getlatestrequeststats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor21getLatestRequestStatsEv", false]], "tensorrt_llm::executor::executor::getnumresponsesready (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Executor20getNumResponsesReadyERKNSt8optionalI6IdTypeEE", false]], "tensorrt_llm::executor::executor::isparticipant (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Executor13isParticipantEv", false]], "tensorrt_llm::executor::executor::mimpl (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor5mImplE", false]], "tensorrt_llm::executor::executor::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8ExecutoraSERK8Executor", false], [0, "_CPPv4N12tensorrt_llm8executor8ExecutoraSERR8Executor", false]], "tensorrt_llm::executor::executor::shutdown (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor8shutdownEv", false]], "tensorrt_llm::executor::executor::~executor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8ExecutorD0Ev", false]], "tensorrt_llm::executor::executorconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfigE", false]], "tensorrt_llm::executor::executorconfig::executorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", false]], "tensorrt_llm::executor::executorconfig::getadditionalmodeloutputs (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getAdditionalModelOutputsEv", false]], "tensorrt_llm::executor::executorconfig::getbatchingtype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getBatchingTypeEv", false]], "tensorrt_llm::executor::executorconfig::getcachetransceiverconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getCacheTransceiverConfigEv", false]], "tensorrt_llm::executor::executorconfig::getdebugconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig14getDebugConfigEv", false]], "tensorrt_llm::executor::executorconfig::getdecodingconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig17getDecodingConfigEv", false]], "tensorrt_llm::executor::executorconfig::getenablechunkedcontext (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig23getEnableChunkedContextEv", false]], "tensorrt_llm::executor::executorconfig::getenabletrtoverlap (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig19getEnableTrtOverlapEv", false]], "tensorrt_llm::executor::executorconfig::getextendedruntimeperfknobconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig32getExtendedRuntimePerfKnobConfigEv", false]], "tensorrt_llm::executor::executorconfig::getgathergenerationlogits (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getGatherGenerationLogitsEv", false]], "tensorrt_llm::executor::executorconfig::getgpuweightspercent (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig20getGpuWeightsPercentEv", false]], "tensorrt_llm::executor::executorconfig::getguideddecodingconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig23getGuidedDecodingConfigEv", false]], "tensorrt_llm::executor::executorconfig::getiterstatsmaxiterations (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getIterStatsMaxIterationsEv", false]], "tensorrt_llm::executor::executorconfig::getkvcacheconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig16getKvCacheConfigEv", false]], "tensorrt_llm::executor::executorconfig::getkvcacheconfigref (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19getKvCacheConfigRefEv", false]], "tensorrt_llm::executor::executorconfig::getlogitspostprocessorconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig28getLogitsPostProcessorConfigEv", false]], "tensorrt_llm::executor::executorconfig::getmaxbatchsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxBatchSizeEv", false]], "tensorrt_llm::executor::executorconfig::getmaxbeamwidth (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxBeamWidthEv", false]], "tensorrt_llm::executor::executorconfig::getmaxnumtokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxNumTokensEv", false]], "tensorrt_llm::executor::executorconfig::getmaxqueuesize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxQueueSizeEv", false]], "tensorrt_llm::executor::executorconfig::getmaxseqidlemicroseconds (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getMaxSeqIdleMicrosecondsEv", false]], "tensorrt_llm::executor::executorconfig::getnormalizelogprobs (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig20getNormalizeLogProbsEv", false]], "tensorrt_llm::executor::executorconfig::getparallelconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig17getParallelConfigEv", false]], "tensorrt_llm::executor::executorconfig::getpeftcacheconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig18getPeftCacheConfigEv", false]], "tensorrt_llm::executor::executorconfig::getprompttableoffloading (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig24getPromptTableOffloadingEv", false]], "tensorrt_llm::executor::executorconfig::getrecvpollperiodms (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig19getRecvPollPeriodMsEv", false]], "tensorrt_llm::executor::executorconfig::getrequeststatsmaxiterations (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig28getRequestStatsMaxIterationsEv", false]], "tensorrt_llm::executor::executorconfig::getschedulerconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig18getSchedulerConfigEv", false]], "tensorrt_llm::executor::executorconfig::getschedulerconfigref (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig21getSchedulerConfigRefEv", false]], "tensorrt_llm::executor::executorconfig::getspecdecconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig16getSpecDecConfigEv", false]], "tensorrt_llm::executor::executorconfig::getusegpudirectstorage (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig22getUseGpuDirectStorageEv", false]], "tensorrt_llm::executor::executorconfig::kdefaultiterstatsmaxiterations (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig30kDefaultIterStatsMaxIterationsE", false]], "tensorrt_llm::executor::executorconfig::kdefaultmaxseqidlemicroseconds (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig30kDefaultMaxSeqIdleMicrosecondsE", false]], "tensorrt_llm::executor::executorconfig::kdefaultrequeststatsmaxiterations (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig33kDefaultRequestStatsMaxIterationsE", false]], "tensorrt_llm::executor::executorconfig::madditionalmodeloutputs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mAdditionalModelOutputsE", false]], "tensorrt_llm::executor::executorconfig::mbatchingtype (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mBatchingTypeE", false]], "tensorrt_llm::executor::executorconfig::mcachetransceiverconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mCacheTransceiverConfigE", false]], "tensorrt_llm::executor::executorconfig::mdebugconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig12mDebugConfigE", false]], "tensorrt_llm::executor::executorconfig::mdecodingconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15mDecodingConfigE", false]], "tensorrt_llm::executor::executorconfig::menablechunkedcontext (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig21mEnableChunkedContextE", false]], "tensorrt_llm::executor::executorconfig::menabletrtoverlap (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17mEnableTrtOverlapE", false]], "tensorrt_llm::executor::executorconfig::mextendedruntimeperfknobconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig30mExtendedRuntimePerfKnobConfigE", false]], "tensorrt_llm::executor::executorconfig::mgathergenerationlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mGatherGenerationLogitsE", false]], "tensorrt_llm::executor::executorconfig::mgpuweightspercent (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18mGpuWeightsPercentE", false]], "tensorrt_llm::executor::executorconfig::mguideddecodingconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig21mGuidedDecodingConfigE", false]], "tensorrt_llm::executor::executorconfig::miterstatsmaxiterations (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mIterStatsMaxIterationsE", false]], "tensorrt_llm::executor::executorconfig::mkvcacheconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14mKvCacheConfigE", false]], "tensorrt_llm::executor::executorconfig::mlogitspostprocessorconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig26mLogitsPostProcessorConfigE", false]], "tensorrt_llm::executor::executorconfig::mmaxbatchsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxBatchSizeE", false]], "tensorrt_llm::executor::executorconfig::mmaxbeamwidth (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxBeamWidthE", false]], "tensorrt_llm::executor::executorconfig::mmaxnumtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxNumTokensE", false]], "tensorrt_llm::executor::executorconfig::mmaxqueuesize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxQueueSizeE", false]], "tensorrt_llm::executor::executorconfig::mmaxseqidlemicroseconds (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mMaxSeqIdleMicrosecondsE", false]], "tensorrt_llm::executor::executorconfig::mnormalizelogprobs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18mNormalizeLogProbsE", false]], "tensorrt_llm::executor::executorconfig::mparallelconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15mParallelConfigE", false]], "tensorrt_llm::executor::executorconfig::mpeftcacheconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16mPeftCacheConfigE", false]], "tensorrt_llm::executor::executorconfig::mprompttableoffloading (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig22mPromptTableOffloadingE", false]], "tensorrt_llm::executor::executorconfig::mrecvpollperiodms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17mRecvPollPeriodMsE", false]], "tensorrt_llm::executor::executorconfig::mrequeststatsmaxiterations (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig26mRequestStatsMaxIterationsE", false]], "tensorrt_llm::executor::executorconfig::mschedulerconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16mSchedulerConfigE", false]], "tensorrt_llm::executor::executorconfig::mspeculativedecodingconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig26mSpeculativeDecodingConfigE", false]], "tensorrt_llm::executor::executorconfig::musegpudirectstorage (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20mUseGpuDirectStorageE", false]], "tensorrt_llm::executor::executorconfig::setadditionalmodeloutputs (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setAdditionalModelOutputsERKNSt6vectorI21AdditionalModelOutputEE", false]], "tensorrt_llm::executor::executorconfig::setbatchingtype (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setBatchingTypeE12BatchingType", false]], "tensorrt_llm::executor::executorconfig::setcachetransceiverconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setCacheTransceiverConfigERK22CacheTransceiverConfig", false]], "tensorrt_llm::executor::executorconfig::setdebugconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14setDebugConfigERK11DebugConfig", false]], "tensorrt_llm::executor::executorconfig::setdecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setDecodingConfigERK14DecodingConfig", false]], "tensorrt_llm::executor::executorconfig::setenablechunkedcontext (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23setEnableChunkedContextEb", false]], "tensorrt_llm::executor::executorconfig::setenabletrtoverlap (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19setEnableTrtOverlapEb", false]], "tensorrt_llm::executor::executorconfig::setextendedruntimeperfknobconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig32setExtendedRuntimePerfKnobConfigERK29ExtendedRuntimePerfKnobConfig", false]], "tensorrt_llm::executor::executorconfig::setgathergenerationlogits (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setGatherGenerationLogitsEb", false]], "tensorrt_llm::executor::executorconfig::setgpuweightspercent (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setGpuWeightsPercentERKf", false]], "tensorrt_llm::executor::executorconfig::setguideddecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23setGuidedDecodingConfigERK20GuidedDecodingConfig", false]], "tensorrt_llm::executor::executorconfig::setiterstatsmaxiterations (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setIterStatsMaxIterationsE10SizeType32", false]], "tensorrt_llm::executor::executorconfig::setkvcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16setKvCacheConfigERK13KvCacheConfig", false]], "tensorrt_llm::executor::executorconfig::setlogitspostprocessorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setLogitsPostProcessorConfigERK25LogitsPostProcessorConfig", false]], "tensorrt_llm::executor::executorconfig::setmaxbatchsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBatchSizeE10SizeType32", false]], "tensorrt_llm::executor::executorconfig::setmaxbeamwidth (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBeamWidthE10SizeType32", false]], "tensorrt_llm::executor::executorconfig::setmaxnumtokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxNumTokensE10SizeType32", false]], "tensorrt_llm::executor::executorconfig::setmaxqueuesize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxQueueSizeERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::executorconfig::setmaxseqidlemicroseconds (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setMaxSeqIdleMicrosecondsE8uint64_t", false]], "tensorrt_llm::executor::executorconfig::setnormalizelogprobs (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setNormalizeLogProbsEb", false]], "tensorrt_llm::executor::executorconfig::setparallelconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setParallelConfigERK14ParallelConfig", false]], "tensorrt_llm::executor::executorconfig::setpeftcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setPeftCacheConfigERK15PeftCacheConfig", false]], "tensorrt_llm::executor::executorconfig::setprompttableoffloading (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig24setPromptTableOffloadingEb", false]], "tensorrt_llm::executor::executorconfig::setrecvpollperiodms (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19setRecvPollPeriodMsERK10SizeType32", false]], "tensorrt_llm::executor::executorconfig::setrequeststatsmaxiterations (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setRequestStatsMaxIterationsE10SizeType32", false]], "tensorrt_llm::executor::executorconfig::setschedulerconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setSchedulerConfigERK15SchedulerConfig", false]], "tensorrt_llm::executor::executorconfig::setspecdecconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16setSpecDecConfigERK25SpeculativeDecodingConfig", false]], "tensorrt_llm::executor::executorconfig::setusegpudirectstorage (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig22setUseGpuDirectStorageERKb", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfigE", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::extendedruntimeperfknobconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig29ExtendedRuntimePerfKnobConfigEbbb10SizeType32", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::getcudagraphcachesize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig21getCudaGraphCacheSizeEv", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::getcudagraphmode (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig16getCudaGraphModeEv", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::getenablecontextfmhafp32acc (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig27getEnableContextFMHAFP32AccEv", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::getmultiblockmode (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig17getMultiBlockModeEv", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::mcudagraphcachesize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig19mCudaGraphCacheSizeE", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::mcudagraphmode (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig14mCudaGraphModeE", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::menablecontextfmhafp32acc (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig25mEnableContextFMHAFP32AccE", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::mmultiblockmode (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig15mMultiBlockModeE", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfigeqERK29ExtendedRuntimePerfKnobConfig", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::setcudagraphcachesize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig21setCudaGraphCacheSizeE10SizeType32", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::setcudagraphmode (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig16setCudaGraphModeEb", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::setenablecontextfmhafp32acc (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig27setEnableContextFMHAFP32AccEb", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::setmultiblockmode (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig17setMultiBlockModeEb", false]], "tensorrt_llm::executor::externaldrafttokensconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfigE", false]], "tensorrt_llm::executor::externaldrafttokensconfig::externaldrafttokensconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig25ExternalDraftTokensConfigE9VecTokensNSt8optionalI6TensorEERKNSt8optionalI9FloatTypeEERKNSt8optionalIbEE", false]], "tensorrt_llm::executor::externaldrafttokensconfig::getacceptancethreshold (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig22getAcceptanceThresholdEv", false]], "tensorrt_llm::executor::externaldrafttokensconfig::getfastlogits (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig13getFastLogitsEv", false]], "tensorrt_llm::executor::externaldrafttokensconfig::getlogits (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig9getLogitsEv", false]], "tensorrt_llm::executor::externaldrafttokensconfig::gettokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig9getTokensEv", false]], "tensorrt_llm::executor::externaldrafttokensconfig::macceptancethreshold (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig20mAcceptanceThresholdE", false]], "tensorrt_llm::executor::externaldrafttokensconfig::mfastlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig11mFastLogitsE", false]], "tensorrt_llm::executor::externaldrafttokensconfig::mlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig7mLogitsE", false]], "tensorrt_llm::executor::externaldrafttokensconfig::mtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig7mTokensE", false]], "tensorrt_llm::executor::finishreason (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReasonE", false]], "tensorrt_llm::executor::finishreason::kcancelled (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReason10kCANCELLEDE", false]], "tensorrt_llm::executor::finishreason::kend_id (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReason7kEND_IDE", false]], "tensorrt_llm::executor::finishreason::klength (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReason7kLENGTHE", false]], "tensorrt_llm::executor::finishreason::knot_finished (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReason13kNOT_FINISHEDE", false]], "tensorrt_llm::executor::finishreason::kstop_words (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReason11kSTOP_WORDSE", false]], "tensorrt_llm::executor::finishreason::ktimed_out (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReason10kTIMED_OUTE", false]], "tensorrt_llm::executor::floattype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor9FloatTypeE", false]], "tensorrt_llm::executor::guideddecodingconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfigE", false]], "tensorrt_llm::executor::guideddecodingconfig::getbackend (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig10getBackendEv", false]], "tensorrt_llm::executor::guideddecodingconfig::getencodedvocab (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig15getEncodedVocabEv", false]], "tensorrt_llm::executor::guideddecodingconfig::getstoptokenids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig15getStopTokenIdsEv", false]], "tensorrt_llm::executor::guideddecodingconfig::gettokenizerstr (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig15getTokenizerStrEv", false]], "tensorrt_llm::executor::guideddecodingconfig::guideddecodingbackend (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig21GuidedDecodingBackendE", false]], "tensorrt_llm::executor::guideddecodingconfig::guideddecodingbackend::kllguidance (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig21GuidedDecodingBackend11kLLGUIDANCEE", false]], "tensorrt_llm::executor::guideddecodingconfig::guideddecodingbackend::kxgrammar (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig21GuidedDecodingBackend9kXGRAMMARE", false]], "tensorrt_llm::executor::guideddecodingconfig::guideddecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig20GuidedDecodingConfigE21GuidedDecodingBackendNSt8optionalINSt6vectorINSt6stringEEEEENSt8optionalINSt6stringEEENSt8optionalINSt6vectorI11TokenIdTypeEEEE", false]], "tensorrt_llm::executor::guideddecodingconfig::mbackend (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig8mBackendE", false]], "tensorrt_llm::executor::guideddecodingconfig::mencodedvocab (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig13mEncodedVocabE", false]], "tensorrt_llm::executor::guideddecodingconfig::mstoptokenids (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig13mStopTokenIdsE", false]], "tensorrt_llm::executor::guideddecodingconfig::mtokenizerstr (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig13mTokenizerStrE", false]], "tensorrt_llm::executor::guideddecodingconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfigeqERK20GuidedDecodingConfig", false]], "tensorrt_llm::executor::guideddecodingconfig::setbackend (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig10setBackendERK21GuidedDecodingBackend", false]], "tensorrt_llm::executor::guideddecodingconfig::setencodedvocab (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setEncodedVocabERKNSt6vectorINSt6stringEEE", false]], "tensorrt_llm::executor::guideddecodingconfig::setstoptokenids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setStopTokenIdsERKNSt6vectorI11TokenIdTypeEE", false]], "tensorrt_llm::executor::guideddecodingconfig::settokenizerstr (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setTokenizerStrERKNSt6stringE", false]], "tensorrt_llm::executor::guideddecodingconfig::validate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig8validateEv", false]], "tensorrt_llm::executor::guideddecodingparams (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParamsE", false]], "tensorrt_llm::executor::guideddecodingparams::getguide (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingParams8getGuideEv", false]], "tensorrt_llm::executor::guideddecodingparams::getguidetype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingParams12getGuideTypeEv", false]], "tensorrt_llm::executor::guideddecodingparams::guideddecodingparams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams20GuidedDecodingParamsE9GuideTypeNSt8optionalINSt6stringEEE", false]], "tensorrt_llm::executor::guideddecodingparams::guidetype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideTypeE", false]], "tensorrt_llm::executor::guideddecodingparams::guidetype::kebnf_grammar (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType13kEBNF_GRAMMARE", false]], "tensorrt_llm::executor::guideddecodingparams::guidetype::kjson (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType5kJSONE", false]], "tensorrt_llm::executor::guideddecodingparams::guidetype::kjson_schema (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType12kJSON_SCHEMAE", false]], "tensorrt_llm::executor::guideddecodingparams::guidetype::kregex (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType6kREGEXE", false]], "tensorrt_llm::executor::guideddecodingparams::guidetype::kstructural_tag (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType15kSTRUCTURAL_TAGE", false]], "tensorrt_llm::executor::guideddecodingparams::mguide (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams6mGuideE", false]], "tensorrt_llm::executor::guideddecodingparams::mguidetype (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams10mGuideTypeE", false]], "tensorrt_llm::executor::guideddecodingparams::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingParamseqERK20GuidedDecodingParams", false]], "tensorrt_llm::executor::idtype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor6IdTypeE", false]], "tensorrt_llm::executor::inflightbatchingstats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStatsE", false]], "tensorrt_llm::executor::inflightbatchingstats::avgnumdecodedtokensperiter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats26avgNumDecodedTokensPerIterE", false]], "tensorrt_llm::executor::inflightbatchingstats::microbatchid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats12microBatchIdE", false]], "tensorrt_llm::executor::inflightbatchingstats::numcontextrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats18numContextRequestsE", false]], "tensorrt_llm::executor::inflightbatchingstats::numctxtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats12numCtxTokensE", false]], "tensorrt_llm::executor::inflightbatchingstats::numgenrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats14numGenRequestsE", false]], "tensorrt_llm::executor::inflightbatchingstats::numpausedrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats17numPausedRequestsE", false]], "tensorrt_llm::executor::inflightbatchingstats::numscheduledrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats20numScheduledRequestsE", false]], "tensorrt_llm::executor::iterationstats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStatsE", false]], "tensorrt_llm::executor::iterationstats::cpumemusage (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats11cpuMemUsageE", false]], "tensorrt_llm::executor::iterationstats::crosskvcachestats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats17crossKvCacheStatsE", false]], "tensorrt_llm::executor::iterationstats::gpumemusage (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats11gpuMemUsageE", false]], "tensorrt_llm::executor::iterationstats::inflightbatchingstats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats21inflightBatchingStatsE", false]], "tensorrt_llm::executor::iterationstats::iter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats4iterE", false]], "tensorrt_llm::executor::iterationstats::iterlatencyms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats13iterLatencyMSE", false]], "tensorrt_llm::executor::iterationstats::kvcachestats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats12kvCacheStatsE", false]], "tensorrt_llm::executor::iterationstats::maxbatchsizeruntime (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats19maxBatchSizeRuntimeE", false]], "tensorrt_llm::executor::iterationstats::maxbatchsizestatic (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats18maxBatchSizeStaticE", false]], "tensorrt_llm::executor::iterationstats::maxbatchsizetunerrecommended (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats28maxBatchSizeTunerRecommendedE", false]], "tensorrt_llm::executor::iterationstats::maxnumactiverequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats20maxNumActiveRequestsE", false]], "tensorrt_llm::executor::iterationstats::maxnumtokensruntime (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats19maxNumTokensRuntimeE", false]], "tensorrt_llm::executor::iterationstats::maxnumtokensstatic (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats18maxNumTokensStaticE", false]], "tensorrt_llm::executor::iterationstats::maxnumtokenstunerrecommended (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats28maxNumTokensTunerRecommendedE", false]], "tensorrt_llm::executor::iterationstats::newactiverequestsqueuelatencyms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats31newActiveRequestsQueueLatencyMSE", false]], "tensorrt_llm::executor::iterationstats::numactiverequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats17numActiveRequestsE", false]], "tensorrt_llm::executor::iterationstats::numcompletedrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats20numCompletedRequestsE", false]], "tensorrt_llm::executor::iterationstats::numnewactiverequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats20numNewActiveRequestsE", false]], "tensorrt_llm::executor::iterationstats::numqueuedrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats17numQueuedRequestsE", false]], "tensorrt_llm::executor::iterationstats::pinnedmemusage (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats14pinnedMemUsageE", false]], "tensorrt_llm::executor::iterationstats::specdecodingstats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats17specDecodingStatsE", false]], "tensorrt_llm::executor::iterationstats::staticbatchingstats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats19staticBatchingStatsE", false]], "tensorrt_llm::executor::iterationstats::timestamp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats9timestampE", false]], "tensorrt_llm::executor::iterationtype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor13IterationTypeE", false]], "tensorrt_llm::executor::jsonserialization (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor17JsonSerializationE", false]], "tensorrt_llm::executor::jsonserialization::tojsonstr (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK12RequestStats", false], [0, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK14IterationStats", false], [0, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK24RequestStatsPerIteration", false]], "tensorrt_llm::executor::kv_cache (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cacheE", false]], "tensorrt_llm::executor::kv_cache::agentdesc (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache9AgentDescE", false]], "tensorrt_llm::executor::kv_cache::agentdesc::agentdesc (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache9AgentDesc9AgentDescENSt6stringE", false]], "tensorrt_llm::executor::kv_cache::agentdesc::getbackendagentdesc (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9AgentDesc19getBackendAgentDescEv", false]], "tensorrt_llm::executor::kv_cache::agentdesc::mbackendagentdesc (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache9AgentDesc17mBackendAgentDescE", false]], "tensorrt_llm::executor::kv_cache::agentstate (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentStateE", false]], "tensorrt_llm::executor::kv_cache::agentstate::agentstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState10AgentStateENSt6stringENSt6stringE", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState10AgentStateEv", false]], "tensorrt_llm::executor::kv_cache::agentstate::magentname (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState10mAgentNameE", false]], "tensorrt_llm::executor::kv_cache::agentstate::mconnectioninfo (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState15mConnectionInfoE", false]], "tensorrt_llm::executor::kv_cache::agentstate::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10AgentStateeqERK10AgentState", false]], "tensorrt_llm::executor::kv_cache::agentstate::tostring (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10AgentState8toStringEv", false]], "tensorrt_llm::executor::kv_cache::baseagentconfig (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15BaseAgentConfigE", false]], "tensorrt_llm::executor::kv_cache::baseagentconfig::mname (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15BaseAgentConfig5mNameE", false]], "tensorrt_llm::executor::kv_cache::baseagentconfig::useprogthread (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15BaseAgentConfig13useProgThreadE", false]], "tensorrt_llm::executor::kv_cache::basetransferagent (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgentE", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::checkremotedescs (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent16checkRemoteDescsERKNSt6stringERK11MemoryDescs", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::connectremoteagent (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent18connectRemoteAgentERKNSt6stringERK18ConnectionInfoType", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::deregistermemory (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent16deregisterMemoryERK13RegisterDescs", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::getconnectioninfo (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent17getConnectionInfoEv", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::getlocalagentdesc (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent17getLocalAgentDescEv", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::getnotifiedsyncmessages (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent23getNotifiedSyncMessagesEv", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::invalidateremoteagent (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent21invalidateRemoteAgentERKNSt6stringE", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::loadremoteagent (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent15loadRemoteAgentERKNSt6stringERK9AgentDesc", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::notifysyncmessage (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent17notifySyncMessageERKNSt6stringERK11SyncMessage", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::registermemory (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent14registerMemoryERK13RegisterDescs", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::submittransferrequests (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent22submitTransferRequestsERK15TransferRequest", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::~basetransferagent (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgentD0Ev", false]], "tensorrt_llm::executor::kv_cache::cachestate (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheStateE", false]], "tensorrt_llm::executor::kv_cache::cachestate::attentionconfig (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfigE", false]], "tensorrt_llm::executor::kv_cache::cachestate::attentionconfig::attentionconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfig15AttentionConfigE13AttentionTypei", false]], "tensorrt_llm::executor::kv_cache::cachestate::attentionconfig::mattentiontype (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfig14mAttentionTypeE", false]], "tensorrt_llm::executor::kv_cache::cachestate::attentionconfig::mkvfactor (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfig9mKvFactorE", false]], "tensorrt_llm::executor::kv_cache::cachestate::attentiontype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState13AttentionTypeE", false]], "tensorrt_llm::executor::kv_cache::cachestate::attentiontype::kdefault (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState13AttentionType8kDEFAULTE", false]], "tensorrt_llm::executor::kv_cache::cachestate::attentiontype::kmla (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState13AttentionType4kMLAE", false]], "tensorrt_llm::executor::kv_cache::cachestate::cachestate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE11ModelConfigRKN7runtime11WorldConfigEN8nvinfer18DataTypeE13AttentionTypei", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", false]], "tensorrt_llm::executor::kv_cache::cachestate::getattentionconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState18getAttentionConfigEv", false]], "tensorrt_llm::executor::kv_cache::cachestate::getdatatype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState11getDataTypeEv", false]], "tensorrt_llm::executor::kv_cache::cachestate::getmodelconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState14getModelConfigEv", false]], "tensorrt_llm::executor::kv_cache::cachestate::getparallelconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState17getParallelConfigEv", false]], "tensorrt_llm::executor::kv_cache::cachestate::mattentionconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState16mAttentionConfigE", false]], "tensorrt_llm::executor::kv_cache::cachestate::mdatatype (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState9mDataTypeE", false]], "tensorrt_llm::executor::kv_cache::cachestate::mmodelconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState12mModelConfigE", false]], "tensorrt_llm::executor::kv_cache::cachestate::modelconfig (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState11ModelConfigE", false]], "tensorrt_llm::executor::kv_cache::cachestate::modelconfig::mnbkvheadsperlayer (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState11ModelConfig18mNbKvHeadsPerLayerE", false]], "tensorrt_llm::executor::kv_cache::cachestate::modelconfig::msizeperhead (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState11ModelConfig12mSizePerHeadE", false]], "tensorrt_llm::executor::kv_cache::cachestate::modelconfig::mtokensperblock (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState11ModelConfig15mTokensPerBlockE", false]], "tensorrt_llm::executor::kv_cache::cachestate::modelconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState11ModelConfigeqERK11ModelConfig", false]], "tensorrt_llm::executor::kv_cache::cachestate::mparallelconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15mParallelConfigE", false]], "tensorrt_llm::executor::kv_cache::cachestate::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheStateeqERKN8kv_cache10CacheStateE", false]], "tensorrt_llm::executor::kv_cache::cachestate::parallelconfig (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfigE", false]], "tensorrt_llm::executor::kv_cache::cachestate::parallelconfig::mdprank (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig7mDPrankE", false]], "tensorrt_llm::executor::kv_cache::cachestate::parallelconfig::mdpsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig7mDPsizeE", false]], "tensorrt_llm::executor::kv_cache::cachestate::parallelconfig::menableattentiondp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig18mEnableAttentionDPE", false]], "tensorrt_llm::executor::kv_cache::cachestate::parallelconfig::mpipelineparallelism (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig20mPipelineParallelismE", false]], "tensorrt_llm::executor::kv_cache::cachestate::parallelconfig::mtensorparallelism (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig18mTensorParallelismE", false]], "tensorrt_llm::executor::kv_cache::cachestate::parallelconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfigeqERK14ParallelConfig", false]], "tensorrt_llm::executor::kv_cache::cachestate::tostring (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState8toStringEv", false]], "tensorrt_llm::executor::kv_cache::commstate (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommStateE", false]], "tensorrt_llm::executor::kv_cache::commstate::commstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI10AgentStateEEi", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI10SizeType32EEi", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI11SocketStateEEi", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt8uint16_tENSt6stringE", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateEv", false]], "tensorrt_llm::executor::kv_cache::commstate::getagentstate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState13getAgentStateEv", false]], "tensorrt_llm::executor::kv_cache::commstate::getmpistate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState11getMpiStateEv", false]], "tensorrt_llm::executor::kv_cache::commstate::getselfidx (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState10getSelfIdxEv", false]], "tensorrt_llm::executor::kv_cache::commstate::getsocketstate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState14getSocketStateEv", false]], "tensorrt_llm::executor::kv_cache::commstate::isagentstate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState12isAgentStateEv", false]], "tensorrt_llm::executor::kv_cache::commstate::ismpistate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState10isMpiStateEv", false]], "tensorrt_llm::executor::kv_cache::commstate::issocketstate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState13isSocketStateEv", false]], "tensorrt_llm::executor::kv_cache::commstate::mselfidx (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState8mSelfIdxE", false]], "tensorrt_llm::executor::kv_cache::commstate::mstate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState6mStateE", false]], "tensorrt_llm::executor::kv_cache::commstate::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommStateeqERK9CommState", false]], "tensorrt_llm::executor::kv_cache::commstate::tostring (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState8toStringEv", false]], "tensorrt_llm::executor::kv_cache::connection (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10ConnectionE", false]], "tensorrt_llm::executor::kv_cache::connection::isthreadsafe (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection12isThreadSafeEv", false]], "tensorrt_llm::executor::kv_cache::connection::recv (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4recvERK11DataContextPv6size_t", false]], "tensorrt_llm::executor::kv_cache::connection::send (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4sendERK11DataContextPKv6size_t", false]], "tensorrt_llm::executor::kv_cache::connection::~connection (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10ConnectionD0Ev", false]], "tensorrt_llm::executor::kv_cache::connectioninfotype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache18ConnectionInfoTypeE", false]], "tensorrt_llm::executor::kv_cache::connectionmanager (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManagerE", false]], "tensorrt_llm::executor::kv_cache::connectionmanager::getcommstate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache17ConnectionManager12getCommStateEv", false]], "tensorrt_llm::executor::kv_cache::connectionmanager::getconnections (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManager14getConnectionsERK9CommState", false]], "tensorrt_llm::executor::kv_cache::connectionmanager::recvconnect (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManager11recvConnectERK11DataContextPv6size_t", false]], "tensorrt_llm::executor::kv_cache::connectionmanager::~connectionmanager (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManagerD0Ev", false]], "tensorrt_llm::executor::kv_cache::datacontext (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11DataContextE", false]], "tensorrt_llm::executor::kv_cache::datacontext::datacontext (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11DataContext11DataContextEi", false]], "tensorrt_llm::executor::kv_cache::datacontext::gettag (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache11DataContext6getTagEv", false]], "tensorrt_llm::executor::kv_cache::datacontext::mtag (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11DataContext4mTagE", false]], "tensorrt_llm::executor::kv_cache::dynlibloader (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoaderE", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::dlsym (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader5dlSymEPvPKc", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::dynlibloader (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader12DynLibLoaderERK12DynLibLoader", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader12DynLibLoaderEv", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::getfunctionpointer (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor8kv_cache12DynLibLoader18getFunctionPointerE9FunctionTRKNSt6stringERKNSt6stringE", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::gethandle (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader9getHandleERKNSt6stringE", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::getinstance (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader11getInstanceEv", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::mdllmutex (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader9mDllMutexE", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::mhandlers (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader9mHandlersE", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoaderaSERK12DynLibLoader", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::~dynlibloader (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoaderD0Ev", false]], "tensorrt_llm::executor::kv_cache::maketransferagent (c++ function)": [[0, "_CPPv4IDpEN12tensorrt_llm8executor8kv_cache17makeTransferAgentENSt10unique_ptrI17BaseTransferAgentEERKNSt6stringEDpRR4Args", false]], "tensorrt_llm::executor::kv_cache::memorydesc (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDescE", false]], "tensorrt_llm::executor::kv_cache::memorydesc::deserialize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc11deserializeERNSt7istreamE", false]], "tensorrt_llm::executor::kv_cache::memorydesc::getaddr (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10MemoryDesc7getAddrEv", false]], "tensorrt_llm::executor::kv_cache::memorydesc::getdeviceid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10MemoryDesc11getDeviceIdEv", false]], "tensorrt_llm::executor::kv_cache::memorydesc::getlen (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10MemoryDesc6getLenEv", false]], "tensorrt_llm::executor::kv_cache::memorydesc::maddr (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc5mAddrE", false]], "tensorrt_llm::executor::kv_cache::memorydesc::mdeviceid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc9mDeviceIdE", false]], "tensorrt_llm::executor::kv_cache::memorydesc::memorydesc (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescE9uintptr_t6size_t8uint32_t", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescEPv6size_t8uint32_t", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescERKNSt6vectorIcEE8uint32_t", false]], "tensorrt_llm::executor::kv_cache::memorydesc::mlen (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc4mLenE", false]], "tensorrt_llm::executor::kv_cache::memorydesc::serialize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc9serializeERK10MemoryDescRNSt7ostreamE", false]], "tensorrt_llm::executor::kv_cache::memorydesc::serializedsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc14serializedSizeERK10MemoryDesc", false]], "tensorrt_llm::executor::kv_cache::memorydescs (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescsE", false]], "tensorrt_llm::executor::kv_cache::memorydescs::getdescs (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache11MemoryDescs8getDescsEv", false]], "tensorrt_llm::executor::kv_cache::memorydescs::gettype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache11MemoryDescs7getTypeEv", false]], "tensorrt_llm::executor::kv_cache::memorydescs::mdescs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescs6mDescsE", false]], "tensorrt_llm::executor::kv_cache::memorydescs::memorydescs (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescs11MemoryDescsE10MemoryTypeNSt6vectorI10MemoryDescEE", false]], "tensorrt_llm::executor::kv_cache::memorydescs::mtype (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescs5mTypeE", false]], "tensorrt_llm::executor::kv_cache::memorytype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryTypeE", false]], "tensorrt_llm::executor::kv_cache::memorytype::kblk (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType4kBLKE", false]], "tensorrt_llm::executor::kv_cache::memorytype::kdram (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType5kDRAME", false]], "tensorrt_llm::executor::kv_cache::memorytype::kfile (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType5kFILEE", false]], "tensorrt_llm::executor::kv_cache::memorytype::kobj (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType4kOBJE", false]], "tensorrt_llm::executor::kv_cache::memorytype::kvram (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType5kVRAME", false]], "tensorrt_llm::executor::kv_cache::mpistate (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache8MpiStateE", false]], "tensorrt_llm::executor::kv_cache::mpistate::mranks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache8MpiState6mRanksE", false]], "tensorrt_llm::executor::kv_cache::mpistate::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache8MpiStateeqERK8MpiState", false]], "tensorrt_llm::executor::kv_cache::mpistate::tostring (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache8MpiState8toStringEv", false]], "tensorrt_llm::executor::kv_cache::registerdescs (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache13RegisterDescsE", false]], "tensorrt_llm::executor::kv_cache::socketstate (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11SocketStateE", false]], "tensorrt_llm::executor::kv_cache::socketstate::mip (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11SocketState3mIpE", false]], "tensorrt_llm::executor::kv_cache::socketstate::mport (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11SocketState5mPortE", false]], "tensorrt_llm::executor::kv_cache::socketstate::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache11SocketStateeqERK11SocketState", false]], "tensorrt_llm::executor::kv_cache::socketstate::tostring (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache11SocketState8toStringEv", false]], "tensorrt_llm::executor::kv_cache::syncmessage (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11SyncMessageE", false]], "tensorrt_llm::executor::kv_cache::transferdescs (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache13TransferDescsE", false]], "tensorrt_llm::executor::kv_cache::transferop (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10TransferOpE", false]], "tensorrt_llm::executor::kv_cache::transferop::kread (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10TransferOp5kREADE", false]], "tensorrt_llm::executor::kv_cache::transferop::kwrite (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10TransferOp6kWRITEE", false]], "tensorrt_llm::executor::kv_cache::transferrequest (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequestE", false]], "tensorrt_llm::executor::kv_cache::transferrequest::getdstdescs (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest11getDstDescsEv", false]], "tensorrt_llm::executor::kv_cache::transferrequest::getop (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest5getOpEv", false]], "tensorrt_llm::executor::kv_cache::transferrequest::getremotename (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest13getRemoteNameEv", false]], "tensorrt_llm::executor::kv_cache::transferrequest::getsrcdescs (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest11getSrcDescsEv", false]], "tensorrt_llm::executor::kv_cache::transferrequest::getsyncmessage (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest14getSyncMessageEv", false]], "tensorrt_llm::executor::kv_cache::transferrequest::mdstdescs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest9mDstDescsE", false]], "tensorrt_llm::executor::kv_cache::transferrequest::mop (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest3mOpE", false]], "tensorrt_llm::executor::kv_cache::transferrequest::mremotename (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest11mRemoteNameE", false]], "tensorrt_llm::executor::kv_cache::transferrequest::msrcdescs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest9mSrcDescsE", false]], "tensorrt_llm::executor::kv_cache::transferrequest::msyncmessage (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest12mSyncMessageE", false]], "tensorrt_llm::executor::kv_cache::transferrequest::transferrequest (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest15TransferRequestE10TransferOp13TransferDescs13TransferDescsRKNSt6stringENSt8optionalI11SyncMessageEE", false]], "tensorrt_llm::executor::kv_cache::transferstatus (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache14TransferStatusE", false]], "tensorrt_llm::executor::kv_cache::transferstatus::iscompleted (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache14TransferStatus11isCompletedEv", false]], "tensorrt_llm::executor::kv_cache::transferstatus::wait (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache14TransferStatus4waitEv", false]], "tensorrt_llm::executor::kv_cache::transferstatus::~transferstatus (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache14TransferStatusD0Ev", false]], "tensorrt_llm::executor::kvcacheconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfigE", false]], "tensorrt_llm::executor::kvcacheconfig::fillemptyfieldsfromruntimedefaults (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig34fillEmptyFieldsFromRuntimeDefaultsERKN12tensorrt_llm7runtime15RuntimeDefaultsE", false]], "tensorrt_llm::executor::kvcacheconfig::getcopyonpartialreuse (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig21getCopyOnPartialReuseEv", false]], "tensorrt_llm::executor::kvcacheconfig::getcrosskvcachefraction (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig23getCrossKvCacheFractionEv", false]], "tensorrt_llm::executor::kvcacheconfig::getenableblockreuse (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig19getEnableBlockReuseEv", false]], "tensorrt_llm::executor::kvcacheconfig::getenablepartialreuse (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig21getEnablePartialReuseEv", false]], "tensorrt_llm::executor::kvcacheconfig::geteventbuffermaxsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig21getEventBufferMaxSizeEv", false]], "tensorrt_llm::executor::kvcacheconfig::getfreegpumemoryfraction (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig24getFreeGpuMemoryFractionEv", false]], "tensorrt_llm::executor::kvcacheconfig::gethostcachesize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig16getHostCacheSizeEv", false]], "tensorrt_llm::executor::kvcacheconfig::getmaxattentionwindowvec (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig24getMaxAttentionWindowVecEv", false]], "tensorrt_llm::executor::kvcacheconfig::getmaxtokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig12getMaxTokensEv", false]], "tensorrt_llm::executor::kvcacheconfig::getonboardblocks (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig16getOnboardBlocksEv", false]], "tensorrt_llm::executor::kvcacheconfig::getsecondaryoffloadminpriority (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig30getSecondaryOffloadMinPriorityEv", false]], "tensorrt_llm::executor::kvcacheconfig::getsinktokenlength (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig18getSinkTokenLengthEv", false]], "tensorrt_llm::executor::kvcacheconfig::getuseuvm (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig9getUseUvmEv", false]], "tensorrt_llm::executor::kvcacheconfig::kdefaultgpumemfraction (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig22kDefaultGpuMemFractionE", false]], "tensorrt_llm::executor::kvcacheconfig::kvcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", false]], "tensorrt_llm::executor::kvcacheconfig::mcopyonpartialreuse (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19mCopyOnPartialReuseE", false]], "tensorrt_llm::executor::kvcacheconfig::mcrosskvcachefraction (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21mCrossKvCacheFractionE", false]], "tensorrt_llm::executor::kvcacheconfig::menableblockreuse (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig17mEnableBlockReuseE", false]], "tensorrt_llm::executor::kvcacheconfig::menablepartialreuse (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19mEnablePartialReuseE", false]], "tensorrt_llm::executor::kvcacheconfig::meventbuffermaxsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19mEventBufferMaxSizeE", false]], "tensorrt_llm::executor::kvcacheconfig::mfreegpumemoryfraction (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig22mFreeGpuMemoryFractionE", false]], "tensorrt_llm::executor::kvcacheconfig::mhostcachesize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig14mHostCacheSizeE", false]], "tensorrt_llm::executor::kvcacheconfig::mmaxattentionwindowvec (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig22mMaxAttentionWindowVecE", false]], "tensorrt_llm::executor::kvcacheconfig::mmaxtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig10mMaxTokensE", false]], "tensorrt_llm::executor::kvcacheconfig::monboardblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig14mOnboardBlocksE", false]], "tensorrt_llm::executor::kvcacheconfig::msecondaryoffloadminpriority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig28mSecondaryOffloadMinPriorityE", false]], "tensorrt_llm::executor::kvcacheconfig::msinktokenlength (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16mSinkTokenLengthE", false]], "tensorrt_llm::executor::kvcacheconfig::museuvm (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig7mUseUvmE", false]], "tensorrt_llm::executor::kvcacheconfig::setcopyonpartialreuse (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setCopyOnPartialReuseEb", false]], "tensorrt_llm::executor::kvcacheconfig::setcrosskvcachefraction (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig23setCrossKvCacheFractionE9FloatType", false]], "tensorrt_llm::executor::kvcacheconfig::setenableblockreuse (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19setEnableBlockReuseEb", false]], "tensorrt_llm::executor::kvcacheconfig::setenablepartialreuse (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setEnablePartialReuseEb", false]], "tensorrt_llm::executor::kvcacheconfig::seteventbuffermaxsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setEventBufferMaxSizeE6size_t", false]], "tensorrt_llm::executor::kvcacheconfig::setfreegpumemoryfraction (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setFreeGpuMemoryFractionE9FloatType", false]], "tensorrt_llm::executor::kvcacheconfig::sethostcachesize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setHostCacheSizeE6size_t", false]], "tensorrt_llm::executor::kvcacheconfig::setmaxattentionwindowvec (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setMaxAttentionWindowVecENSt6vectorI10SizeType32EE", false]], "tensorrt_llm::executor::kvcacheconfig::setmaxtokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig12setMaxTokensE10SizeType32", false]], "tensorrt_llm::executor::kvcacheconfig::setonboardblocks (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setOnboardBlocksEb", false]], "tensorrt_llm::executor::kvcacheconfig::setsecondaryoffloadminpriority (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig30setSecondaryOffloadMinPriorityENSt8optionalI17RetentionPriorityEE", false]], "tensorrt_llm::executor::kvcacheconfig::setsinktokenlength (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig18setSinkTokenLengthE10SizeType32", false]], "tensorrt_llm::executor::kvcacheconfig::setuseuvm (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig9setUseUvmEb", false]], "tensorrt_llm::executor::kvcachecreateddata (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheCreatedDataE", false]], "tensorrt_llm::executor::kvcachecreateddata::numblockspercachelevel (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheCreatedData22numBlocksPerCacheLevelE", false]], "tensorrt_llm::executor::kvcacheevent (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor12KVCacheEventE", false]], "tensorrt_llm::executor::kvcacheevent::data (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent4dataE", false]], "tensorrt_llm::executor::kvcacheevent::eventid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent7eventIdE", false]], "tensorrt_llm::executor::kvcacheevent::kvcacheevent (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent12KVCacheEventE6IdType16KVCacheEventData10SizeType32", false]], "tensorrt_llm::executor::kvcacheevent::windowsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent10windowSizeE", false]], "tensorrt_llm::executor::kvcacheeventdata (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor16KVCacheEventDataE", false]], "tensorrt_llm::executor::kvcacheeventdiff (c++ struct)": [[0, "_CPPv4I0EN12tensorrt_llm8executor16KVCacheEventDiffE", false]], "tensorrt_llm::executor::kvcacheeventdiff::newvalue (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor16KVCacheEventDiff8newValueE", false]], "tensorrt_llm::executor::kvcacheeventdiff::oldvalue (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor16KVCacheEventDiff8oldValueE", false]], "tensorrt_llm::executor::kvcacheeventmanager (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManagerE", false]], "tensorrt_llm::executor::kvcacheeventmanager::getlatestevents (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManager15getLatestEventsENSt8optionalINSt6chrono12millisecondsEEE", false]], "tensorrt_llm::executor::kvcacheeventmanager::kvcacheeventmanager (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManager19KVCacheEventManagerENSt10shared_ptrIN12tensorrt_llm13batch_manager16kv_cache_manager18BaseKVCacheManagerEEE", false]], "tensorrt_llm::executor::kvcacheeventmanager::kvcachemanager (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManager14kvCacheManagerE", false]], "tensorrt_llm::executor::kvcacheremoveddata (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheRemovedDataE", false]], "tensorrt_llm::executor::kvcacheremoveddata::blockhashes (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheRemovedData11blockHashesE", false]], "tensorrt_llm::executor::kvcacheretentionconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfigE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::getdecodedurationms (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig19getDecodeDurationMsEv", false]], "tensorrt_llm::executor::kvcacheretentionconfig::getdecoderetentionpriority (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig26getDecodeRetentionPriorityEv", false]], "tensorrt_llm::executor::kvcacheretentionconfig::getdirectory (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig12getDirectoryEv", false]], "tensorrt_llm::executor::kvcacheretentionconfig::getperblockretentionpriorityduration (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig36getPerBlockRetentionPriorityDurationE10SizeType3210SizeType32", false]], "tensorrt_llm::executor::kvcacheretentionconfig::gettokenrangeretentionconfigs (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig29getTokenRangeRetentionConfigsEv", false]], "tensorrt_llm::executor::kvcacheretentionconfig::gettransfermode (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig15getTransferModeEv", false]], "tensorrt_llm::executor::kvcacheretentionconfig::kdefaultretentionpriority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25kDefaultRetentionPriorityE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::kmaxretentionpriority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig21kMaxRetentionPriorityE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::kminretentionpriority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig21kMinRetentionPriorityE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::kvcacheretentionconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigERKNSt6vectorI25TokenRangeRetentionConfigEE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE19KvCacheTransferModeNSt8optionalINSt6stringEEE", false], [0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigEv", false]], "tensorrt_llm::executor::kvcacheretentionconfig::mdecodedurationms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig17mDecodeDurationMsE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::mdecoderetentionpriority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig24mDecodeRetentionPriorityE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::mdirectory (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig10mDirectoryE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::mtokenrangeretentionconfigs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig27mTokenRangeRetentionConfigsE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::mtransfermode (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig13mTransferModeE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfigeqERK22KvCacheRetentionConfig", false]], "tensorrt_llm::executor::kvcacheretentionconfig::tokenrangeretentionconfig (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfigE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::tokenrangeretentionconfig::durationms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig10durationMsE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::tokenrangeretentionconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfigeqERK25TokenRangeRetentionConfig", false]], "tensorrt_llm::executor::kvcacheretentionconfig::tokenrangeretentionconfig::priority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig8priorityE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::tokenrangeretentionconfig::tokenend (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig8tokenEndE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::tokenrangeretentionconfig::tokenrangeretentionconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig25TokenRangeRetentionConfigE10SizeType32NSt8optionalI10SizeType32EE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::tokenrangeretentionconfig::tokenstart (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig10tokenStartE", false]], "tensorrt_llm::executor::kvcachestats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStatsE", false]], "tensorrt_llm::executor::kvcachestats::allocnewblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats14allocNewBlocksE", false]], "tensorrt_llm::executor::kvcachestats::alloctotalblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats16allocTotalBlocksE", false]], "tensorrt_llm::executor::kvcachestats::cachehitrate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12cacheHitRateE", false]], "tensorrt_llm::executor::kvcachestats::freenumblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats13freeNumBlocksE", false]], "tensorrt_llm::executor::kvcachestats::maxnumblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12maxNumBlocksE", false]], "tensorrt_llm::executor::kvcachestats::missedblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12missedBlocksE", false]], "tensorrt_llm::executor::kvcachestats::reusedblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12reusedBlocksE", false]], "tensorrt_llm::executor::kvcachestats::tokensperblock (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats14tokensPerBlockE", false]], "tensorrt_llm::executor::kvcachestats::usednumblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats13usedNumBlocksE", false]], "tensorrt_llm::executor::kvcachestoredblockdata (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockDataE", false]], "tensorrt_llm::executor::kvcachestoredblockdata::blockhash (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData9blockHashE", false]], "tensorrt_llm::executor::kvcachestoredblockdata::cachelevel (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData10cacheLevelE", false]], "tensorrt_llm::executor::kvcachestoredblockdata::kvcachestoredblockdata (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData22KVCacheStoredBlockDataE6IdTypeN12tensorrt_llm7runtime15VecUniqueTokensENSt8optionalIN12tensorrt_llm7runtime14LoraTaskIdTypeEEE10SizeType3210SizeType32", false]], "tensorrt_llm::executor::kvcachestoredblockdata::loraid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData6loraIdE", false]], "tensorrt_llm::executor::kvcachestoredblockdata::priority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData8priorityE", false]], "tensorrt_llm::executor::kvcachestoredblockdata::tokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData6tokensE", false]], "tensorrt_llm::executor::kvcachestoreddata (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor17KVCacheStoredDataE", false]], "tensorrt_llm::executor::kvcachestoreddata::blocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor17KVCacheStoredData6blocksE", false]], "tensorrt_llm::executor::kvcachestoreddata::parenthash (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor17KVCacheStoredData10parentHashE", false]], "tensorrt_llm::executor::kvcachetransfermode (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor19KvCacheTransferModeE", false]], "tensorrt_llm::executor::kvcachetransfermode::dram (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor19KvCacheTransferMode4DRAME", false]], "tensorrt_llm::executor::kvcachetransfermode::gds (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor19KvCacheTransferMode3GDSE", false]], "tensorrt_llm::executor::kvcachetransfermode::posix_debug_fallback (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor19KvCacheTransferMode20POSIX_DEBUG_FALLBACKE", false]], "tensorrt_llm::executor::kvcacheupdateddata (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedDataE", false]], "tensorrt_llm::executor::kvcacheupdateddata::blockhash (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData9blockHashE", false]], "tensorrt_llm::executor::kvcacheupdateddata::cachelevel (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData10cacheLevelE", false]], "tensorrt_llm::executor::kvcacheupdateddata::cachelevelupdated (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData17cacheLevelUpdatedE10SizeType3210SizeType32", false]], "tensorrt_llm::executor::kvcacheupdateddata::kvcacheupdateddata (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData18KVCacheUpdatedDataE6IdType", false]], "tensorrt_llm::executor::kvcacheupdateddata::priority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData8priorityE", false]], "tensorrt_llm::executor::kvcacheupdateddata::priorityupdated (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData15priorityUpdatedE10SizeType3210SizeType32", false]], "tensorrt_llm::executor::logitspostprocessor (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor19LogitsPostProcessorE", false]], "tensorrt_llm::executor::logitspostprocessorbatched (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor26LogitsPostProcessorBatchedE", false]], "tensorrt_llm::executor::logitspostprocessorconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfigE", false]], "tensorrt_llm::executor::logitspostprocessorconfig::getprocessorbatched (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig19getProcessorBatchedEv", false]], "tensorrt_llm::executor::logitspostprocessorconfig::getprocessormap (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig15getProcessorMapEv", false]], "tensorrt_llm::executor::logitspostprocessorconfig::getreplicate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig12getReplicateEv", false]], "tensorrt_llm::executor::logitspostprocessorconfig::logitspostprocessorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig25LogitsPostProcessorConfigENSt8optionalI22LogitsPostProcessorMapEENSt8optionalI26LogitsPostProcessorBatchedEEb", false]], "tensorrt_llm::executor::logitspostprocessorconfig::mprocessorbatched (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig17mProcessorBatchedE", false]], "tensorrt_llm::executor::logitspostprocessorconfig::mprocessormap (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig13mProcessorMapE", false]], "tensorrt_llm::executor::logitspostprocessorconfig::mreplicate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig10mReplicateE", false]], "tensorrt_llm::executor::logitspostprocessorconfig::setprocessorbatched (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig19setProcessorBatchedERK26LogitsPostProcessorBatched", false]], "tensorrt_llm::executor::logitspostprocessorconfig::setprocessormap (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig15setProcessorMapERK22LogitsPostProcessorMap", false]], "tensorrt_llm::executor::logitspostprocessorconfig::setreplicate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig12setReplicateEb", false]], "tensorrt_llm::executor::logitspostprocessormap (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor22LogitsPostProcessorMapE", false]], "tensorrt_llm::executor::lookaheaddecodingconfig (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfigE", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::calculatespeculativeresource (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig28calculateSpeculativeResourceEv", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::calculatespeculativeresourcetuple (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig33calculateSpeculativeResourceTupleE10SizeType3210SizeType3210SizeType32", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::get (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig3getEv", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::getngramsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig12getNgramSizeEv", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::getverificationsetsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig22getVerificationSetSizeEv", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::getwindowsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig13getWindowSizeEv", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::isle (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig4isLEERK23LookaheadDecodingConfig", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::islegal (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig7isLegalE10SizeType3210SizeType3210SizeType32", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::kdefaultlookaheaddecodingngram (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig30kDefaultLookaheadDecodingNgramE", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::kdefaultlookaheaddecodingverificationset (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig40kDefaultLookaheadDecodingVerificationSetE", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::kdefaultlookaheaddecodingwindow (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig31kDefaultLookaheadDecodingWindowE", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::lookaheaddecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigE10SizeType3210SizeType3210SizeType32", false], [0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigEv", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::mngramsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig10mNgramSizeE", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::mverificationsetsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig20mVerificationSetSizeE", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::mwindowsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig11mWindowSizeE", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfigeqERK23LookaheadDecodingConfig", false]], "tensorrt_llm::executor::loraconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor10LoraConfigE", false]], "tensorrt_llm::executor::loraconfig::getconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor10LoraConfig9getConfigEv", false]], "tensorrt_llm::executor::loraconfig::gettaskid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor10LoraConfig9getTaskIdEv", false]], "tensorrt_llm::executor::loraconfig::getweights (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor10LoraConfig10getWeightsEv", false]], "tensorrt_llm::executor::loraconfig::loraconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor10LoraConfig10LoraConfigE6IdTypeNSt8optionalI6TensorEENSt8optionalI6TensorEE", false]], "tensorrt_llm::executor::loraconfig::mconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10LoraConfig7mConfigE", false]], "tensorrt_llm::executor::loraconfig::mtaskid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10LoraConfig7mTaskIdE", false]], "tensorrt_llm::executor::loraconfig::mweights (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10LoraConfig8mWeightsE", false]], "tensorrt_llm::executor::medusachoices (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor13MedusaChoicesE", false]], "tensorrt_llm::executor::memorytype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryTypeE", false]], "tensorrt_llm::executor::memorytype::kcpu (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType4kCPUE", false]], "tensorrt_llm::executor::memorytype::kcpu_pinned (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType11kCPU_PINNEDE", false]], "tensorrt_llm::executor::memorytype::kcpu_pinnedpool (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType15kCPU_PINNEDPOOLE", false]], "tensorrt_llm::executor::memorytype::kgpu (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType4kGPUE", false]], "tensorrt_llm::executor::memorytype::kunknown (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType8kUNKNOWNE", false]], "tensorrt_llm::executor::memorytype::kuvm (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType4kUVME", false]], "tensorrt_llm::executor::millisecondstype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor16MillisecondsTypeE", false]], "tensorrt_llm::executor::modeltype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor9ModelTypeE", false]], "tensorrt_llm::executor::modeltype::kdecoder_only (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor9ModelType13kDECODER_ONLYE", false]], "tensorrt_llm::executor::modeltype::kencoder_decoder (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor9ModelType16kENCODER_DECODERE", false]], "tensorrt_llm::executor::modeltype::kencoder_only (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor9ModelType13kENCODER_ONLYE", false]], "tensorrt_llm::executor::mropeconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor11MropeConfigE", false]], "tensorrt_llm::executor::mropeconfig::getmropepositiondeltas (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11MropeConfig22getMRopePositionDeltasEv", false]], "tensorrt_llm::executor::mropeconfig::getmroperotarycossin (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11MropeConfig20getMRopeRotaryCosSinEv", false]], "tensorrt_llm::executor::mropeconfig::mmropepositiondeltas (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11MropeConfig20mMRopePositionDeltasE", false]], "tensorrt_llm::executor::mropeconfig::mmroperotarycossin (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11MropeConfig18mMRopeRotaryCosSinE", false]], "tensorrt_llm::executor::mropeconfig::mropeconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11MropeConfig11MropeConfigE6Tensor10SizeType32", false]], "tensorrt_llm::executor::multimodalinput (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor15MultimodalInputE", false]], "tensorrt_llm::executor::multimodalinput::getmultimodalhashes (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15MultimodalInput19getMultimodalHashesEv", false]], "tensorrt_llm::executor::multimodalinput::getmultimodallengths (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15MultimodalInput20getMultimodalLengthsEv", false]], "tensorrt_llm::executor::multimodalinput::getmultimodalpositions (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15MultimodalInput22getMultimodalPositionsEv", false]], "tensorrt_llm::executor::multimodalinput::mmultimodalhashes (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15MultimodalInput17mMultimodalHashesE", false]], "tensorrt_llm::executor::multimodalinput::mmultimodallengths (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15MultimodalInput18mMultimodalLengthsE", false]], "tensorrt_llm::executor::multimodalinput::mmultimodalpositions (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15MultimodalInput20mMultimodalPositionsE", false]], "tensorrt_llm::executor::multimodalinput::multimodalinput (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15MultimodalInput15MultimodalInputENSt6vectorINSt6vectorI10SizeType32EEEENSt6vectorI10SizeType32EENSt6vectorI10SizeType32EE", false]], "tensorrt_llm::executor::operator<< (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE21ContextChunkingPolicy", false], [0, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE23CapacitySchedulerPolicy", false]], "tensorrt_llm::executor::orchestratorconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfigE", false]], "tensorrt_llm::executor::orchestratorconfig::getisorchestrator (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getIsOrchestratorEv", false]], "tensorrt_llm::executor::orchestratorconfig::getorchleadercomm (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getOrchLeaderCommEv", false]], "tensorrt_llm::executor::orchestratorconfig::getspawnprocesses (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getSpawnProcessesEv", false]], "tensorrt_llm::executor::orchestratorconfig::getworkerexecutablepath (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig23getWorkerExecutablePathEv", false]], "tensorrt_llm::executor::orchestratorconfig::misorchestrator (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mIsOrchestratorE", false]], "tensorrt_llm::executor::orchestratorconfig::morchleadercomm (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mOrchLeaderCommE", false]], "tensorrt_llm::executor::orchestratorconfig::mspawnprocesses (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mSpawnProcessesE", false]], "tensorrt_llm::executor::orchestratorconfig::mworkerexecutablepath (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig21mWorkerExecutablePathE", false]], "tensorrt_llm::executor::orchestratorconfig::orchestratorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb", false]], "tensorrt_llm::executor::orchestratorconfig::setisorchestrator (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setIsOrchestratorEb", false]], "tensorrt_llm::executor::orchestratorconfig::setorchleadercomm (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setOrchLeaderCommERKNSt10shared_ptrIN3mpi7MpiCommEEE", false]], "tensorrt_llm::executor::orchestratorconfig::setspawnprocesses (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setSpawnProcessesEb", false]], "tensorrt_llm::executor::orchestratorconfig::setworkerexecutablepath (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig23setWorkerExecutablePathERKNSt6stringE", false]], "tensorrt_llm::executor::outputconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfigE", false]], "tensorrt_llm::executor::outputconfig::additionalmodeloutputs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig22additionalModelOutputsE", false]], "tensorrt_llm::executor::outputconfig::excludeinputfromoutput (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig22excludeInputFromOutputE", false]], "tensorrt_llm::executor::outputconfig::outputconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", false]], "tensorrt_llm::executor::outputconfig::returncontextlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig19returnContextLogitsE", false]], "tensorrt_llm::executor::outputconfig::returnencoderoutput (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig19returnEncoderOutputE", false]], "tensorrt_llm::executor::outputconfig::returngenerationlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig22returnGenerationLogitsE", false]], "tensorrt_llm::executor::outputconfig::returnlogprobs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig14returnLogProbsE", false]], "tensorrt_llm::executor::outputconfig::returnperfmetrics (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig17returnPerfMetricsE", false]], "tensorrt_llm::executor::parallelconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfigE", false]], "tensorrt_llm::executor::parallelconfig::getcommunicationmode (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig20getCommunicationModeEv", false]], "tensorrt_llm::executor::parallelconfig::getcommunicationtype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig20getCommunicationTypeEv", false]], "tensorrt_llm::executor::parallelconfig::getdeviceids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig12getDeviceIdsEv", false]], "tensorrt_llm::executor::parallelconfig::getnumnodes (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig11getNumNodesEv", false]], "tensorrt_llm::executor::parallelconfig::getorchestratorconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig21getOrchestratorConfigEv", false]], "tensorrt_llm::executor::parallelconfig::getparticipantids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig17getParticipantIdsEv", false]], "tensorrt_llm::executor::parallelconfig::mcommmode (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig9mCommModeE", false]], "tensorrt_llm::executor::parallelconfig::mcommtype (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig9mCommTypeE", false]], "tensorrt_llm::executor::parallelconfig::mdeviceids (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig10mDeviceIdsE", false]], "tensorrt_llm::executor::parallelconfig::mnumnodes (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig9mNumNodesE", false]], "tensorrt_llm::executor::parallelconfig::morchestratorconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig19mOrchestratorConfigE", false]], "tensorrt_llm::executor::parallelconfig::mparticipantids (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig15mParticipantIdsE", false]], "tensorrt_llm::executor::parallelconfig::parallelconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEENSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::parallelconfig::setcommunicationmode (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationModeE17CommunicationMode", false]], "tensorrt_llm::executor::parallelconfig::setcommunicationtype (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationTypeE17CommunicationType", false]], "tensorrt_llm::executor::parallelconfig::setdeviceids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig12setDeviceIdsERKNSt6vectorI10SizeType32EE", false]], "tensorrt_llm::executor::parallelconfig::setnumnodes (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig11setNumNodesE10SizeType32", false]], "tensorrt_llm::executor::parallelconfig::setorchestratorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig21setOrchestratorConfigERK18OrchestratorConfig", false]], "tensorrt_llm::executor::parallelconfig::setparticipantids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig17setParticipantIdsERKNSt6vectorI10SizeType32EE", false]], "tensorrt_llm::executor::peftcacheconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfigE", false]], "tensorrt_llm::executor::peftcacheconfig::getdevicecachepercent (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getDeviceCachePercentEv", false]], "tensorrt_llm::executor::peftcacheconfig::gethostcachesize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig16getHostCacheSizeEv", false]], "tensorrt_llm::executor::peftcacheconfig::getloraprefetchdir (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig18getLoraPrefetchDirEv", false]], "tensorrt_llm::executor::peftcacheconfig::getmaxadaptersize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig17getMaxAdapterSizeEv", false]], "tensorrt_llm::executor::peftcacheconfig::getmaxpagesperblockdevice (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig25getMaxPagesPerBlockDeviceEv", false]], "tensorrt_llm::executor::peftcacheconfig::getmaxpagesperblockhost (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig23getMaxPagesPerBlockHostEv", false]], "tensorrt_llm::executor::peftcacheconfig::getnumcopystreams (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig17getNumCopyStreamsEv", false]], "tensorrt_llm::executor::peftcacheconfig::getnumdevicemodulelayer (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig23getNumDeviceModuleLayerEv", false]], "tensorrt_llm::executor::peftcacheconfig::getnumensureworkers (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig19getNumEnsureWorkersEv", false]], "tensorrt_llm::executor::peftcacheconfig::getnumhostmodulelayer (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getNumHostModuleLayerEv", false]], "tensorrt_llm::executor::peftcacheconfig::getnumputworkers (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig16getNumPutWorkersEv", false]], "tensorrt_llm::executor::peftcacheconfig::getoptimaladaptersize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getOptimalAdapterSizeEv", false]], "tensorrt_llm::executor::peftcacheconfig::kdefaultmaxadaptersize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig22kDefaultMaxAdapterSizeE", false]], "tensorrt_llm::executor::peftcacheconfig::kdefaultmaxpagesperblockdevice (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig30kDefaultMaxPagesPerBlockDeviceE", false]], "tensorrt_llm::executor::peftcacheconfig::kdefaultmaxpagesperblockhost (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig28kDefaultMaxPagesPerBlockHostE", false]], "tensorrt_llm::executor::peftcacheconfig::kdefaultoptimaladaptersize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig26kDefaultOptimalAdapterSizeE", false]], "tensorrt_llm::executor::peftcacheconfig::mdevicecachepercent (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mDeviceCachePercentE", false]], "tensorrt_llm::executor::peftcacheconfig::mhostcachesize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig14mHostCacheSizeE", false]], "tensorrt_llm::executor::peftcacheconfig::mloraprefetchdir (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig16mLoraPrefetchDirE", false]], "tensorrt_llm::executor::peftcacheconfig::mmaxadaptersize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15mMaxAdapterSizeE", false]], "tensorrt_llm::executor::peftcacheconfig::mmaxpagesperblockdevice (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig23mMaxPagesPerBlockDeviceE", false]], "tensorrt_llm::executor::peftcacheconfig::mmaxpagesperblockhost (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig21mMaxPagesPerBlockHostE", false]], "tensorrt_llm::executor::peftcacheconfig::mnumcopystreams (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15mNumCopyStreamsE", false]], "tensorrt_llm::executor::peftcacheconfig::mnumdevicemodulelayer (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig21mNumDeviceModuleLayerE", false]], "tensorrt_llm::executor::peftcacheconfig::mnumensureworkers (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig17mNumEnsureWorkersE", false]], "tensorrt_llm::executor::peftcacheconfig::mnumhostmodulelayer (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mNumHostModuleLayerE", false]], "tensorrt_llm::executor::peftcacheconfig::mnumputworkers (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig14mNumPutWorkersE", false]], "tensorrt_llm::executor::peftcacheconfig::moptimaladaptersize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mOptimalAdapterSizeE", false]], "tensorrt_llm::executor::peftcacheconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfigeqERK15PeftCacheConfig", false]], "tensorrt_llm::executor::peftcacheconfig::peftcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", false]], "tensorrt_llm::executor::prioritytype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor12PriorityTypeE", false]], "tensorrt_llm::executor::prompttuningconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfigE", false]], "tensorrt_llm::executor::prompttuningconfig::getembeddingtable (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18PromptTuningConfig17getEmbeddingTableEv", false]], "tensorrt_llm::executor::prompttuningconfig::getinputtokenextraids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18PromptTuningConfig21getInputTokenExtraIdsEv", false]], "tensorrt_llm::executor::prompttuningconfig::membeddingtable (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig15mEmbeddingTableE", false]], "tensorrt_llm::executor::prompttuningconfig::minputtokenextraids (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig19mInputTokenExtraIdsE", false]], "tensorrt_llm::executor::prompttuningconfig::prompttuningconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig18PromptTuningConfigE6TensorNSt8optionalI16VecTokenExtraIdsEE", false]], "tensorrt_llm::executor::randomseedtype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor14RandomSeedTypeE", false]], "tensorrt_llm::executor::request (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor7RequestE", false]], "tensorrt_llm::executor::request::getadditionaloutputnames (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request24getAdditionalOutputNamesEv", false]], "tensorrt_llm::executor::request::getallottedtimems (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request17getAllottedTimeMsEv", false]], "tensorrt_llm::executor::request::getbadwords (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request11getBadWordsEv", false]], "tensorrt_llm::executor::request::getclientid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request11getClientIdEv", false]], "tensorrt_llm::executor::request::getcontextphaseparams (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request21getContextPhaseParamsEv", false]], "tensorrt_llm::executor::request::getcrossattentionmask (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request21getCrossAttentionMaskEv", false]], "tensorrt_llm::executor::request::geteagleconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request14getEagleConfigEv", false]], "tensorrt_llm::executor::request::getembeddingbias (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request16getEmbeddingBiasEv", false]], "tensorrt_llm::executor::request::getencoderinputfeatures (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request23getEncoderInputFeaturesEv", false]], "tensorrt_llm::executor::request::getencoderinputtokenids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request23getEncoderInputTokenIdsEv", false]], "tensorrt_llm::executor::request::getencoderoutputlength (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request22getEncoderOutputLengthEv", false]], "tensorrt_llm::executor::request::getendid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request8getEndIdEv", false]], "tensorrt_llm::executor::request::getexternaldrafttokensconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request28getExternalDraftTokensConfigEv", false]], "tensorrt_llm::executor::request::getguideddecodingparams (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request23getGuidedDecodingParamsEv", false]], "tensorrt_llm::executor::request::getinputtokenids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request16getInputTokenIdsEv", false]], "tensorrt_llm::executor::request::getkvcacheretentionconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request25getKvCacheRetentionConfigEv", false]], "tensorrt_llm::executor::request::getlanguageadapteruid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request21getLanguageAdapterUidEv", false]], "tensorrt_llm::executor::request::getlogitspostprocessor (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request22getLogitsPostProcessorEv", false]], "tensorrt_llm::executor::request::getlogitspostprocessorname (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request26getLogitsPostProcessorNameEv", false]], "tensorrt_llm::executor::request::getlookaheadconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request18getLookaheadConfigEv", false]], "tensorrt_llm::executor::request::getloraconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request13getLoraConfigEv", false]], "tensorrt_llm::executor::request::getmaxtokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request12getMaxTokensEv", false]], "tensorrt_llm::executor::request::getmropeconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request14getMropeConfigEv", false]], "tensorrt_llm::executor::request::getmultimodalembedding (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request22getMultimodalEmbeddingEv", false]], "tensorrt_llm::executor::request::getmultimodalinput (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request18getMultimodalInputEv", false]], "tensorrt_llm::executor::request::getoutputconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request15getOutputConfigEv", false]], "tensorrt_llm::executor::request::getpadid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request8getPadIdEv", false]], "tensorrt_llm::executor::request::getpositionids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request14getPositionIdsEv", false]], "tensorrt_llm::executor::request::getpriority (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request11getPriorityEv", false]], "tensorrt_llm::executor::request::getprompttuningconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request21getPromptTuningConfigEv", false]], "tensorrt_llm::executor::request::getrequesttype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request14getRequestTypeEv", false]], "tensorrt_llm::executor::request::getreturnallgeneratedtokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request27getReturnAllGeneratedTokensEv", false]], "tensorrt_llm::executor::request::getsamplingconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request17getSamplingConfigEv", false]], "tensorrt_llm::executor::request::getskipcrossattnblocks (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request22getSkipCrossAttnBlocksEv", false]], "tensorrt_llm::executor::request::getstopwords (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request12getStopWordsEv", false]], "tensorrt_llm::executor::request::getstreaming (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request12getStreamingEv", false]], "tensorrt_llm::executor::request::kbatchedpostprocessorname (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor7Request25kBatchedPostProcessorNameE", false]], "tensorrt_llm::executor::request::kdefaultpriority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor7Request16kDefaultPriorityE", false]], "tensorrt_llm::executor::request::kdynamicpostprocessornameprefix (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor7Request31kDynamicPostProcessorNamePrefixE", false]], "tensorrt_llm::executor::request::mimpl (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor7Request5mImplE", false]], "tensorrt_llm::executor::request::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7RequestaSERK7Request", false], [0, "_CPPv4N12tensorrt_llm8executor7RequestaSERR7Request", false]], "tensorrt_llm::executor::request::request (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", false], [0, "_CPPv4N12tensorrt_llm8executor7Request7RequestERK7Request", false], [0, "_CPPv4N12tensorrt_llm8executor7Request7RequestERR7Request", false]], "tensorrt_llm::executor::request::setallottedtimems (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request17setAllottedTimeMsE16MillisecondsType", false]], "tensorrt_llm::executor::request::setbadwords (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request11setBadWordsERKNSt4listI9VecTokensEE", false]], "tensorrt_llm::executor::request::setclientid (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request11setClientIdE6IdType", false]], "tensorrt_llm::executor::request::setcontextphaseparams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request21setContextPhaseParamsE18ContextPhaseParams", false]], "tensorrt_llm::executor::request::setcrossattentionmask (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request21setCrossAttentionMaskE6Tensor", false]], "tensorrt_llm::executor::request::seteagleconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request14setEagleConfigERKNSt8optionalI11EagleConfigEE", false]], "tensorrt_llm::executor::request::setembeddingbias (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request16setEmbeddingBiasERK6Tensor", false]], "tensorrt_llm::executor::request::setencoderinputfeatures (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputFeaturesE6Tensor", false]], "tensorrt_llm::executor::request::setencoderinputtokenids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputTokenIdsERK9VecTokens", false]], "tensorrt_llm::executor::request::setencoderoutputlength (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request22setEncoderOutputLengthE10SizeType32", false]], "tensorrt_llm::executor::request::setendid (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request8setEndIdE10SizeType32", false]], "tensorrt_llm::executor::request::setexternaldrafttokensconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request28setExternalDraftTokensConfigERK25ExternalDraftTokensConfig", false]], "tensorrt_llm::executor::request::setguideddecodingparams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request23setGuidedDecodingParamsERK20GuidedDecodingParams", false]], "tensorrt_llm::executor::request::setkvcacheretentionconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request25setKvCacheRetentionConfigERK22KvCacheRetentionConfig", false]], "tensorrt_llm::executor::request::setlanguageadapteruid (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request21setLanguageAdapterUidE10SizeType32", false]], "tensorrt_llm::executor::request::setlogitspostprocessor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request22setLogitsPostProcessorERKNSt8optionalI19LogitsPostProcessorEE", false]], "tensorrt_llm::executor::request::setlogitspostprocessorname (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request26setLogitsPostProcessorNameERKNSt6stringE", false]], "tensorrt_llm::executor::request::setlookaheadconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request18setLookaheadConfigERK23LookaheadDecodingConfig", false]], "tensorrt_llm::executor::request::setloraconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request13setLoraConfigERK10LoraConfig", false]], "tensorrt_llm::executor::request::setmropeconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request14setMropeConfigERK11MropeConfig", false]], "tensorrt_llm::executor::request::setmultimodalembedding (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request22setMultimodalEmbeddingERK6Tensor", false]], "tensorrt_llm::executor::request::setmultimodalinput (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request18setMultimodalInputERK15MultimodalInput", false]], "tensorrt_llm::executor::request::setoutputconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request15setOutputConfigERK12OutputConfig", false]], "tensorrt_llm::executor::request::setpadid (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request8setPadIdE10SizeType32", false]], "tensorrt_llm::executor::request::setpositionids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request14setPositionIdsERKNSt6vectorI10SizeType32EE", false]], "tensorrt_llm::executor::request::setpriority (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request11setPriorityE12PriorityType", false]], "tensorrt_llm::executor::request::setprompttuningconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request21setPromptTuningConfigERK18PromptTuningConfig", false]], "tensorrt_llm::executor::request::setrequesttype (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request14setRequestTypeERK11RequestType", false]], "tensorrt_llm::executor::request::setreturnallgeneratedtokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request27setReturnAllGeneratedTokensEb", false]], "tensorrt_llm::executor::request::setsamplingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request17setSamplingConfigERK14SamplingConfig", false]], "tensorrt_llm::executor::request::setskipcrossattnblocks (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request22setSkipCrossAttnBlocksE6Tensor", false]], "tensorrt_llm::executor::request::setstopwords (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request12setStopWordsERKNSt4listI9VecTokensEE", false]], "tensorrt_llm::executor::request::setstreaming (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request12setStreamingEb", false]], "tensorrt_llm::executor::request::~request (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7RequestD0Ev", false]], "tensorrt_llm::executor::requestperfmetrics (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetricsE", false]], "tensorrt_llm::executor::requestperfmetrics::firstiter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics9firstIterE", false]], "tensorrt_llm::executor::requestperfmetrics::iter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics4iterE", false]], "tensorrt_llm::executor::requestperfmetrics::kvcachemetrics (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14kvCacheMetricsE", false]], "tensorrt_llm::executor::requestperfmetrics::kvcachemetrics (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetricsE", false]], "tensorrt_llm::executor::requestperfmetrics::kvcachemetrics::kvcachehitrate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics14kvCacheHitRateE", false]], "tensorrt_llm::executor::requestperfmetrics::kvcachemetrics::nummissedblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics15numMissedBlocksE", false]], "tensorrt_llm::executor::requestperfmetrics::kvcachemetrics::numnewallocatedblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics21numNewAllocatedBlocksE", false]], "tensorrt_llm::executor::requestperfmetrics::kvcachemetrics::numreusedblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics15numReusedBlocksE", false]], "tensorrt_llm::executor::requestperfmetrics::kvcachemetrics::numtotalallocatedblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics23numTotalAllocatedBlocksE", false]], "tensorrt_llm::executor::requestperfmetrics::lastiter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics8lastIterE", false]], "tensorrt_llm::executor::requestperfmetrics::speculativedecoding (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics19speculativeDecodingE", false]], "tensorrt_llm::executor::requestperfmetrics::speculativedecodingmetrics (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics26SpeculativeDecodingMetricsE", false]], "tensorrt_llm::executor::requestperfmetrics::speculativedecodingmetrics::acceptancerate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics26SpeculativeDecodingMetrics14acceptanceRateE", false]], "tensorrt_llm::executor::requestperfmetrics::speculativedecodingmetrics::totalaccepteddrafttokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics26SpeculativeDecodingMetrics24totalAcceptedDraftTokensE", false]], "tensorrt_llm::executor::requestperfmetrics::speculativedecodingmetrics::totaldrafttokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics26SpeculativeDecodingMetrics16totalDraftTokensE", false]], "tensorrt_llm::executor::requestperfmetrics::timepoint (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics9TimePointE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13timingMetricsE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetricsE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics::arrivaltime (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics11arrivalTimeE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics::firstscheduledtime (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics18firstScheduledTimeE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics::firsttokentime (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics14firstTokenTimeE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics::kvcachesize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics11kvCacheSizeE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics::kvcachetransferend (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics18kvCacheTransferEndE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics::kvcachetransferstart (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics20kvCacheTransferStartE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics::lasttokentime (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics13lastTokenTimeE", false]], "tensorrt_llm::executor::requeststage (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStageE", false]], "tensorrt_llm::executor::requeststage::kcontext_in_progress (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStage20kCONTEXT_IN_PROGRESSE", false]], "tensorrt_llm::executor::requeststage::kencoder_in_progress (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStage20kENCODER_IN_PROGRESSE", false]], "tensorrt_llm::executor::requeststage::kgeneration_complete (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStage20kGENERATION_COMPLETEE", false]], "tensorrt_llm::executor::requeststage::kgeneration_in_progress (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStage23kGENERATION_IN_PROGRESSE", false]], "tensorrt_llm::executor::requeststage::kqueued (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStage7kQUEUEDE", false]], "tensorrt_llm::executor::requeststats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStatsE", false]], "tensorrt_llm::executor::requeststats::allocnewblocksperrequest (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats24allocNewBlocksPerRequestE", false]], "tensorrt_llm::executor::requeststats::alloctotalblocksperrequest (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats26allocTotalBlocksPerRequestE", false]], "tensorrt_llm::executor::requeststats::avgnumdecodedtokensperiter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats26avgNumDecodedTokensPerIterE", false]], "tensorrt_llm::executor::requeststats::contextprefillposition (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats22contextPrefillPositionE", false]], "tensorrt_llm::executor::requeststats::disservingstats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats15disServingStatsE", false]], "tensorrt_llm::executor::requeststats::id (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats2idE", false]], "tensorrt_llm::executor::requeststats::kvcachehitrateperrequest (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats24kvCacheHitRatePerRequestE", false]], "tensorrt_llm::executor::requeststats::missedblocksperrequest (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats22missedBlocksPerRequestE", false]], "tensorrt_llm::executor::requeststats::numgeneratedtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats18numGeneratedTokensE", false]], "tensorrt_llm::executor::requeststats::paused (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats6pausedE", false]], "tensorrt_llm::executor::requeststats::reusedblocksperrequest (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats22reusedBlocksPerRequestE", false]], "tensorrt_llm::executor::requeststats::scheduled (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats9scheduledE", false]], "tensorrt_llm::executor::requeststats::stage (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats5stageE", false]], "tensorrt_llm::executor::requeststatsperiteration (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIterationE", false]], "tensorrt_llm::executor::requeststatsperiteration::iter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIteration4iterE", false]], "tensorrt_llm::executor::requeststatsperiteration::requeststats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIteration12requestStatsE", false]], "tensorrt_llm::executor::requesttype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor11RequestTypeE", false]], "tensorrt_llm::executor::requesttype::request_type_context_and_generation (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor11RequestType35REQUEST_TYPE_CONTEXT_AND_GENERATIONE", false]], "tensorrt_llm::executor::requesttype::request_type_context_only (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor11RequestType25REQUEST_TYPE_CONTEXT_ONLYE", false]], "tensorrt_llm::executor::requesttype::request_type_generation_only (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor11RequestType28REQUEST_TYPE_GENERATION_ONLYE", false]], "tensorrt_llm::executor::response (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8ResponseE", false]], "tensorrt_llm::executor::response::getclientid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Response11getClientIdEv", false]], "tensorrt_llm::executor::response::geterrormsg (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Response11getErrorMsgEv", false]], "tensorrt_llm::executor::response::getrequestid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Response12getRequestIdEv", false]], "tensorrt_llm::executor::response::getresult (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Response9getResultEv", false]], "tensorrt_llm::executor::response::haserror (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Response8hasErrorEv", false]], "tensorrt_llm::executor::response::mimpl (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8Response5mImplE", false]], "tensorrt_llm::executor::response::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8ResponseaSERK8Response", false], [0, "_CPPv4N12tensorrt_llm8executor8ResponseaSERR8Response", false]], "tensorrt_llm::executor::response::response (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdType6ResultNSt8optionalI6IdTypeEE", false], [0, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdTypeNSt6stringENSt8optionalI6IdTypeEE", false], [0, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERK8Response", false], [0, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERR8Response", false]], "tensorrt_llm::executor::response::~response (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8ResponseD0Ev", false]], "tensorrt_llm::executor::result (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor6ResultE", false]], "tensorrt_llm::executor::result::additionaloutputs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result17additionalOutputsE", false]], "tensorrt_llm::executor::result::contextlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result13contextLogitsE", false]], "tensorrt_llm::executor::result::contextphaseparams (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result18contextPhaseParamsE", false]], "tensorrt_llm::executor::result::cumlogprobs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result11cumLogProbsE", false]], "tensorrt_llm::executor::result::decodingiter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result12decodingIterE", false]], "tensorrt_llm::executor::result::encoderoutput (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result13encoderOutputE", false]], "tensorrt_llm::executor::result::finishreasons (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result13finishReasonsE", false]], "tensorrt_llm::executor::result::generationlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result16generationLogitsE", false]], "tensorrt_llm::executor::result::isfinal (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result7isFinalE", false]], "tensorrt_llm::executor::result::issequencefinal (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result15isSequenceFinalE", false]], "tensorrt_llm::executor::result::logprobs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result8logProbsE", false]], "tensorrt_llm::executor::result::outputtokenids (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result14outputTokenIdsE", false]], "tensorrt_llm::executor::result::requestperfmetrics (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result18requestPerfMetricsE", false]], "tensorrt_llm::executor::result::sequenceindex (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result13sequenceIndexE", false]], "tensorrt_llm::executor::result::specdecfastlogitsinfo (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result21specDecFastLogitsInfoE", false]], "tensorrt_llm::executor::retentionpriority (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor17RetentionPriorityE", false]], "tensorrt_llm::executor::retentionpriorityandduration (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDurationE", false]], "tensorrt_llm::executor::retentionpriorityandduration::durationms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDuration10durationMsE", false]], "tensorrt_llm::executor::retentionpriorityandduration::retentionpriority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDuration17retentionPriorityE", false]], "tensorrt_llm::executor::retentionpriorityandduration::retentionpriorityandduration (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDuration28RetentionPriorityAndDurationERKNSt8optionalI17RetentionPriorityEERKNSt8optionalINSt6chrono12millisecondsEEE", false]], "tensorrt_llm::executor::samplingconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfigE", false]], "tensorrt_llm::executor::samplingconfig::checkbeamsearchdiversityrate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig28checkBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checkbeamwidth (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkBeamWidthE10SizeType32", false]], "tensorrt_llm::executor::samplingconfig::checkbeamwidtharray (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19checkBeamWidthArrayERKNSt8optionalINSt6vectorI10SizeType32EEEEK10SizeType32", false]], "tensorrt_llm::executor::samplingconfig::checkearlystopping (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18checkEarlyStoppingERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::samplingconfig::checklengthpenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18checkLengthPenaltyERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checkminp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkMinPERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checkmintokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkMinTokensERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::samplingconfig::checknorepeatngramsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::samplingconfig::checknumreturnsequences (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig23checkNumReturnSequencesERKNSt8optionalI10SizeType32EE10SizeType32", false]], "tensorrt_llm::executor::samplingconfig::checkrepetitionpenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkRepetitionPenaltyERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checktemperature (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16checkTemperatureERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checktopk (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopKERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checktopp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopPERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checktoppdecay (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkTopPDecayERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checktoppmin (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12checkTopPMinERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checktoppresetids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17checkTopPResetIdsERKNSt8optionalI11TokenIdTypeEE", false]], "tensorrt_llm::executor::samplingconfig::getbeamsearchdiversityrate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig26getBeamSearchDiversityRateEv", false]], "tensorrt_llm::executor::samplingconfig::getbeamwidth (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getBeamWidthEv", false]], "tensorrt_llm::executor::samplingconfig::getbeamwidtharray (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig17getBeamWidthArrayEv", false]], "tensorrt_llm::executor::samplingconfig::getearlystopping (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig16getEarlyStoppingEv", false]], "tensorrt_llm::executor::samplingconfig::getfrequencypenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig19getFrequencyPenaltyEv", false]], "tensorrt_llm::executor::samplingconfig::getlengthpenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig16getLengthPenaltyEv", false]], "tensorrt_llm::executor::samplingconfig::getminp (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getMinPEv", false]], "tensorrt_llm::executor::samplingconfig::getmintokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getMinTokensEv", false]], "tensorrt_llm::executor::samplingconfig::getnorepeatngramsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig20getNoRepeatNgramSizeEv", false]], "tensorrt_llm::executor::samplingconfig::getnumreturnbeams (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig17getNumReturnBeamsEv", false]], "tensorrt_llm::executor::samplingconfig::getnumreturnsequences (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig21getNumReturnSequencesEv", false]], "tensorrt_llm::executor::samplingconfig::getpresencepenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig18getPresencePenaltyEv", false]], "tensorrt_llm::executor::samplingconfig::getrepetitionpenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig20getRepetitionPenaltyEv", false]], "tensorrt_llm::executor::samplingconfig::getseed (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getSeedEv", false]], "tensorrt_llm::executor::samplingconfig::gettemperature (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig14getTemperatureEv", false]], "tensorrt_llm::executor::samplingconfig::gettopk (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getTopKEv", false]], "tensorrt_llm::executor::samplingconfig::gettopp (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getTopPEv", false]], "tensorrt_llm::executor::samplingconfig::gettoppdecay (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getTopPDecayEv", false]], "tensorrt_llm::executor::samplingconfig::gettoppmin (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig10getTopPMinEv", false]], "tensorrt_llm::executor::samplingconfig::gettoppresetids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig15getTopPResetIdsEv", false]], "tensorrt_llm::executor::samplingconfig::mbeamsearchdiversityrate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig24mBeamSearchDiversityRateE", false]], "tensorrt_llm::executor::samplingconfig::mbeamwidth (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mBeamWidthE", false]], "tensorrt_llm::executor::samplingconfig::mbeamwidtharray (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig15mBeamWidthArrayE", false]], "tensorrt_llm::executor::samplingconfig::mearlystopping (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14mEarlyStoppingE", false]], "tensorrt_llm::executor::samplingconfig::mfrequencypenalty (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17mFrequencyPenaltyE", false]], "tensorrt_llm::executor::samplingconfig::mlengthpenalty (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14mLengthPenaltyE", false]], "tensorrt_llm::executor::samplingconfig::mminp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mMinPE", false]], "tensorrt_llm::executor::samplingconfig::mmintokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mMinTokensE", false]], "tensorrt_llm::executor::samplingconfig::mnorepeatngramsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18mNoRepeatNgramSizeE", false]], "tensorrt_llm::executor::samplingconfig::mnumreturnbeams (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig15mNumReturnBeamsE", false]], "tensorrt_llm::executor::samplingconfig::mnumreturnsequences (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19mNumReturnSequencesE", false]], "tensorrt_llm::executor::samplingconfig::mpresencepenalty (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16mPresencePenaltyE", false]], "tensorrt_llm::executor::samplingconfig::mrepetitionpenalty (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18mRepetitionPenaltyE", false]], "tensorrt_llm::executor::samplingconfig::mseed (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mSeedE", false]], "tensorrt_llm::executor::samplingconfig::mtemperature (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12mTemperatureE", false]], "tensorrt_llm::executor::samplingconfig::mtopk (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mTopKE", false]], "tensorrt_llm::executor::samplingconfig::mtopp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mTopPE", false]], "tensorrt_llm::executor::samplingconfig::mtoppdecay (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mTopPDecayE", false]], "tensorrt_llm::executor::samplingconfig::mtoppmin (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig8mTopPMinE", false]], "tensorrt_llm::executor::samplingconfig::mtoppresetids (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig13mTopPResetIdsE", false]], "tensorrt_llm::executor::samplingconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfigeqERK14SamplingConfig", false]], "tensorrt_llm::executor::samplingconfig::samplingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", false]], "tensorrt_llm::executor::samplingconfig::setbeamsearchdiversityrate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig26setBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::setbeamwidth (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setBeamWidthE10SizeType32", false]], "tensorrt_llm::executor::samplingconfig::setbeamwidtharray (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17setBeamWidthArrayERKNSt8optionalINSt6vectorI10SizeType32EEEE", false]], "tensorrt_llm::executor::samplingconfig::setearlystopping (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setEarlyStoppingERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::samplingconfig::setfrequencypenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19setFrequencyPenaltyERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::setlengthpenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setLengthPenaltyERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::setminp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setMinPERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::setmintokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setMinTokensERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::samplingconfig::setnorepeatngramsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::samplingconfig::setnumreturnsequences (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig21setNumReturnSequencesERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::samplingconfig::setpresencepenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18setPresencePenaltyERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::setrepetitionpenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setRepetitionPenaltyERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::setseed (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setSeedERKNSt8optionalI14RandomSeedTypeEE", false]], "tensorrt_llm::executor::samplingconfig::settemperature (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14setTemperatureERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::settopk (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopKERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::samplingconfig::settopp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopPERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::settoppdecay (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setTopPDecayERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::settoppmin (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10setTopPMinERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::settoppresetids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig15setTopPResetIdsERKNSt8optionalI11TokenIdTypeEE", false]], "tensorrt_llm::executor::samplingconfig::updatenumreturnbeams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20updateNumReturnBeamsEv", false]], "tensorrt_llm::executor::schedulerconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor15SchedulerConfigE", false]], "tensorrt_llm::executor::schedulerconfig::getcapacityschedulerpolicy (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfig26getCapacitySchedulerPolicyEv", false]], "tensorrt_llm::executor::schedulerconfig::getcontextchunkingpolicy (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfig24getContextChunkingPolicyEv", false]], "tensorrt_llm::executor::schedulerconfig::getdynamicbatchconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfig21getDynamicBatchConfigEv", false]], "tensorrt_llm::executor::schedulerconfig::mcapacityschedulerpolicy (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig24mCapacitySchedulerPolicyE", false]], "tensorrt_llm::executor::schedulerconfig::mcontextchunkingpolicy (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig22mContextChunkingPolicyE", false]], "tensorrt_llm::executor::schedulerconfig::mdynamicbatchconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig19mDynamicBatchConfigE", false]], "tensorrt_llm::executor::schedulerconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfigeqERK15SchedulerConfig", false]], "tensorrt_llm::executor::schedulerconfig::schedulerconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig15SchedulerConfigE23CapacitySchedulerPolicyNSt8optionalI21ContextChunkingPolicyEENSt8optionalI18DynamicBatchConfigEE", false]], "tensorrt_llm::executor::serialization (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor13SerializationE", false]], "tensorrt_llm::executor::serialization::deserializeadditionalmodeloutput (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeAdditionalModelOutputERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeadditionaloutput (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization27deserializeAdditionalOutputERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeagentstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeAgentStateERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializebool (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization15deserializeBoolERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializecachestate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeCacheStateERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializecachetransceiverconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeCacheTransceiverConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializecommstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeCommStateERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializecontextphaseparams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeContextPhaseParamsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializedatatransceiverstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeDataTransceiverStateERNSt6vectorIcEE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeDataTransceiverStateERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializedebugconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeDebugConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializedecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeDecodingConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializedecodingmode (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeDecodingModeERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializedisservingrequeststats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeDisServingRequestStatsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializedynamicbatchconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeDynamicBatchConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeeagleconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeEagleConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeexecutorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeExecutorConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeextendedruntimeperfknobconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization40deserializeExtendedRuntimePerfKnobConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeexternaldrafttokensconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeExternalDraftTokensConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeguideddecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeGuidedDecodingConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeguideddecodingparams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeGuidedDecodingParamsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeinflightbatchingstats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeInflightBatchingStatsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeiterationstats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt6vectorIcEE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeiterationstatsvec (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization28deserializeIterationStatsVecERNSt6vectorIcEE", false]], "tensorrt_llm::executor::serialization::deserializekvcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization24deserializeKvCacheConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializekvcacheretentionconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeKvCacheRetentionConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializekvcachestats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeKvCacheStatsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializelookaheaddecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization34deserializeLookaheadDecodingConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeloraconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeLoraConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializemodeltype (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeModelTypeERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializemropeconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeMropeConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializemultimodalinput (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializeMultimodalInputERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeorchestratorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeOrchestratorConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeoutputconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeOutputConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeparallelconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeParallelConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializepeftcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializePeftCacheConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeprompttuningconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializePromptTuningConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializerequest (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization18deserializeRequestERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializerequestperfmetrics (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeRequestPerfMetricsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializerequeststage (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeRequestStageERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializerequeststats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeRequestStatsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializerequeststatsperiteration (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization35deserializeRequestStatsPerIterationERNSt6vectorIcEE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization35deserializeRequestStatsPerIterationERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializerequeststatsperiterationvec (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization38deserializeRequestStatsPerIterationVecERNSt6vectorIcEE", false]], "tensorrt_llm::executor::serialization::deserializeresponse (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization19deserializeResponseERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeresponses (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeResponsesERNSt6vectorIcEE", false]], "tensorrt_llm::executor::serialization::deserializeresult (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeResultERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializesamplingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeSamplingConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeschedulerconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializeSchedulerConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializesocketstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeSocketStateERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializespecdecfastlogitsinfo (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeSpecDecFastLogitsInfoERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializespecdecodingstats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization28deserializeSpecDecodingStatsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializespeculativedecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeSpeculativeDecodingConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializestaticbatchingstats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization30deserializeStaticBatchingStatsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializestring (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeStringERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializetensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeTensorERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializetimepoint (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeTimePointERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializetokenrangeretentionconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeTokenRangeRetentionConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::serialize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK10LoraConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11DebugConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11EagleConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11MropeConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12DecodingModeRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12KvCacheStatsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12OutputConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12RequestStageRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12RequestStatsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK13KvCacheConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14DecodingConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ExecutorConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStats", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStatsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ParallelConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14SamplingConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15MultimodalInputRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15PeftCacheConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15SchedulerConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK16AdditionalOutputRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK17SpecDecodingStatsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18ContextPhaseParamsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18DynamicBatchConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18OrchestratorConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18PromptTuningConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18RequestPerfMetricsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK19StaticBatchingStatsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20DataTransceiverState", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20DataTransceiverStateRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20GuidedDecodingConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20GuidedDecodingParamsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21AdditionalModelOutputRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21InflightBatchingStatsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22CacheTransceiverConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22DisServingRequestStatsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22KvCacheRetentionConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK23LookaheadDecodingConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK24RequestStatsPerIteration", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK24RequestStatsPerIterationRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25ExternalDraftTokensConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25SpeculativeDecodingConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK29ExtendedRuntimePerfKnobConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK33SpeculativeDecodingFastLogitsInfoRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6ResultRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6TensorRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK7RequestRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK8ResponseRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN18RequestPerfMetrics9TimePointERNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN22KvCacheRetentionConfig25TokenRangeRetentionConfigERNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10AgentStateERNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10CacheStateERNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache11SocketStateERNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache9CommStateERNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI14IterationStatsEE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI24RequestStatsPerIterationEE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI8ResponseEE", false]], "tensorrt_llm::executor::serialization::serializedsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK10LoraConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11DebugConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11EagleConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11MropeConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12DecodingMode", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12KvCacheStats", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12OutputConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12RequestStage", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12RequestStats", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK13KvCacheConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14DecodingConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ExecutorConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14IterationStats", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ParallelConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14SamplingConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15MultimodalInput", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15PeftCacheConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15SchedulerConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK16AdditionalOutput", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK17SpecDecodingStats", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18ContextPhaseParams", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18DynamicBatchConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18OrchestratorConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18PromptTuningConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18RequestPerfMetrics", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK19StaticBatchingStats", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20DataTransceiverState", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20GuidedDecodingConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20GuidedDecodingParams", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK21AdditionalModelOutput", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK21InflightBatchingStats", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22CacheTransceiverConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22DisServingRequestStats", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22KvCacheRetentionConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK23LookaheadDecodingConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK24RequestStatsPerIteration", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK25ExternalDraftTokensConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK25SpeculativeDecodingConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK29ExtendedRuntimePerfKnobConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK33SpeculativeDecodingFastLogitsInfo", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Result", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Tensor", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK7Request", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK8Response", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN18RequestPerfMetrics9TimePointE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN22KvCacheRetentionConfig25TokenRangeRetentionConfigE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache10AgentStateE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache10CacheStateE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache11SocketStateE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache9CommStateE", false]], "tensorrt_llm::executor::shape (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor5ShapeE", false]], "tensorrt_llm::executor::shape::base (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor5Shape4BaseE", false]], "tensorrt_llm::executor::shape::dimtype64 (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor5Shape9DimType64E", false]], "tensorrt_llm::executor::shape::shape (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeENSt16initializer_listI9DimType64EE", false], [0, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEPK9DimType64N4Base9size_typeE", false], [0, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEv", false]], "tensorrt_llm::executor::sizetype32 (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor10SizeType32E", false]], "tensorrt_llm::executor::sizetype64 (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor10SizeType64E", false]], "tensorrt_llm::executor::specdecodingstats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStatsE", false]], "tensorrt_llm::executor::specdecodingstats::acceptancelength (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats16acceptanceLengthE", false]], "tensorrt_llm::executor::specdecodingstats::draftoverhead (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats13draftOverheadE", false]], "tensorrt_llm::executor::specdecodingstats::iterlatencyms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats13iterLatencyMSE", false]], "tensorrt_llm::executor::specdecodingstats::numacceptedtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats17numAcceptedTokensE", false]], "tensorrt_llm::executor::specdecodingstats::numdrafttokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats14numDraftTokensE", false]], "tensorrt_llm::executor::specdecodingstats::numrequestswithdrafttokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats26numRequestsWithDraftTokensE", false]], "tensorrt_llm::executor::speculativedecodingconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor25SpeculativeDecodingConfigE", false]], "tensorrt_llm::executor::speculativedecodingconfig::fastlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25SpeculativeDecodingConfig10fastLogitsE", false]], "tensorrt_llm::executor::speculativedecodingconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25SpeculativeDecodingConfigeqERK25SpeculativeDecodingConfig", false]], "tensorrt_llm::executor::speculativedecodingconfig::speculativedecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor25SpeculativeDecodingConfig25SpeculativeDecodingConfigEb", false]], "tensorrt_llm::executor::speculativedecodingfastlogitsinfo (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor33SpeculativeDecodingFastLogitsInfoE", false]], "tensorrt_llm::executor::speculativedecodingfastlogitsinfo::draftparticipantid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor33SpeculativeDecodingFastLogitsInfo18draftParticipantIdE", false]], "tensorrt_llm::executor::speculativedecodingfastlogitsinfo::draftrequestid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor33SpeculativeDecodingFastLogitsInfo14draftRequestIdE", false]], "tensorrt_llm::executor::speculativedecodingfastlogitsinfo::totensor (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor33SpeculativeDecodingFastLogitsInfo8toTensorEv", false]], "tensorrt_llm::executor::staticbatchingstats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStatsE", false]], "tensorrt_llm::executor::staticbatchingstats::emptygenslots (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats13emptyGenSlotsE", false]], "tensorrt_llm::executor::staticbatchingstats::numcontextrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats18numContextRequestsE", false]], "tensorrt_llm::executor::staticbatchingstats::numctxtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats12numCtxTokensE", false]], "tensorrt_llm::executor::staticbatchingstats::numgentokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats12numGenTokensE", false]], "tensorrt_llm::executor::staticbatchingstats::numscheduledrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats20numScheduledRequestsE", false]], "tensorrt_llm::executor::streamptr (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor9StreamPtrE", false]], "tensorrt_llm::executor::tensor (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor6TensorE", false]], "tensorrt_llm::executor::tensor::copyto (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor6copyToENSt10shared_ptrI4ImplEE13CudaStreamPtr", false]], "tensorrt_llm::executor::tensor::copytocpu (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToCpuEN6Tensor13CudaStreamPtrE", false]], "tensorrt_llm::executor::tensor::copytogpu (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToGpuEN6Tensor13CudaStreamPtrE", false]], "tensorrt_llm::executor::tensor::copytomanaged (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor13copyToManagedEN6Tensor13CudaStreamPtrE", false]], "tensorrt_llm::executor::tensor::copytopinned (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor12copyToPinnedEN6Tensor13CudaStreamPtrE", false]], "tensorrt_llm::executor::tensor::copytopooledpinned (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor18copyToPooledPinnedEN6Tensor13CudaStreamPtrE", false]], "tensorrt_llm::executor::tensor::cpu (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3cpuE6Tensor5Shape", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor3cpuE8DataType5Shape", false]], "tensorrt_llm::executor::tensor::cudastreamptr (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor13CudaStreamPtrE", false]], "tensorrt_llm::executor::tensor::detail::ofitensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE", false]], "tensorrt_llm::executor::tensor::detail::toitensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9toITensorERK6Tensor", false]], "tensorrt_llm::executor::tensor::getdata (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor7getDataEv", false], [0, "_CPPv4NK12tensorrt_llm8executor6Tensor7getDataEv", false]], "tensorrt_llm::executor::tensor::getdatatype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor11getDataTypeEv", false]], "tensorrt_llm::executor::tensor::getmemorytype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor13getMemoryTypeEv", false]], "tensorrt_llm::executor::tensor::getruntimetype (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor14getRuntimeTypeE8DataTypev", false]], "tensorrt_llm::executor::tensor::getshape (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor8getShapeEv", false]], "tensorrt_llm::executor::tensor::getsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor7getSizeEv", false]], "tensorrt_llm::executor::tensor::getsizeinbytes (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor14getSizeInBytesEv", false]], "tensorrt_llm::executor::tensor::gpu (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3gpuE6Tensor13CudaStreamPtr5Shape", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor3gpuE8DataType13CudaStreamPtr5Shape", false]], "tensorrt_llm::executor::tensor::impl (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor4ImplE", false]], "tensorrt_llm::executor::tensor::managed (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor7managedE6Tensor5Shape", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor7managedE8DataType5Shape", false]], "tensorrt_llm::executor::tensor::mtensor (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor7mTensorE", false]], "tensorrt_llm::executor::tensor::of (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorP1T5Shape", false], [0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorR1T", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor2ofE8DataTypePv5Shape", false]], "tensorrt_llm::executor::tensor::operator bool (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6TensorcvbEv", false]], "tensorrt_llm::executor::tensor::operator!= (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6TensorneERK6Tensor", false]], "tensorrt_llm::executor::tensor::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6TensoraSERK6Tensor", false], [0, "_CPPv4N12tensorrt_llm8executor6TensoraSERR6Tensor", false]], "tensorrt_llm::executor::tensor::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6TensoreqERK6Tensor", false]], "tensorrt_llm::executor::tensor::pinned (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor6pinnedE6Tensor5Shape", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor6pinnedE8DataType5Shape", false]], "tensorrt_llm::executor::tensor::pooledpinned (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor12pooledPinnedE6Tensor5Shape", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor12pooledPinnedE8DataType5Shape", false]], "tensorrt_llm::executor::tensor::setfrom (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor7setFromERK6Tensor13CudaStreamPtr", false]], "tensorrt_llm::executor::tensor::setzero (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor7setZeroE13CudaStreamPtr", false]], "tensorrt_llm::executor::tensor::tensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorENSt10shared_ptrIN7runtime7ITensorEEE", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERK6Tensor", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERR6Tensor", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorEv", false]], "tensorrt_llm::executor::tensor::~tensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6TensorD0Ev", false]], "tensorrt_llm::executor::tensorptr (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor9TensorPtrE", false]], "tensorrt_llm::executor::tokenidtype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor11TokenIdTypeE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4I0_bEN12tensorrt_llm8executor10TypeTraitsE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsIbEE", false]], "tensorrt_llm::executor::typetraits::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIbE5valueE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsIfEE", false]], "tensorrt_llm::executor::typetraits::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIfE5valueE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsI4halfEE", false]], "tensorrt_llm::executor::typetraits::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsI4halfE5valueE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7int32_tEEE", false]], "tensorrt_llm::executor::typetraits::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7int32_tEE5valueE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7int64_tEEE", false]], "tensorrt_llm::executor::typetraits::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7int64_tEE5valueE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt6int8_tEEE", false]], "tensorrt_llm::executor::typetraits::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt6int8_tEE5valueE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7uint8_tEEE", false]], "tensorrt_llm::executor::typetraits::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7uint8_tEE5valueE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4I0EN12tensorrt_llm8executor10TypeTraitsIP1TEE", false]], "tensorrt_llm::executor::typetraits::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIP1TE5valueE", false]], "tensorrt_llm::executor::veclogprobs (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor11VecLogProbsE", false]], "tensorrt_llm::executor::vectokenextraids (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor16VecTokenExtraIdsE", false]], "tensorrt_llm::executor::vectokens (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor9VecTokensE", false]], "tensorrt_llm::executor::version (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7versionEv", false]], "tensorrt_llm::layers (c++ type)": [[1, "_CPPv4N12tensorrt_llm6layersE", false]], "tensorrt_llm::mpi (c++ type)": [[0, "_CPPv4N12tensorrt_llm3mpiE", false]], "tensorrt_llm::runtime (c++ type)": [[0, "_CPPv4N12tensorrt_llm7runtimeE", false], [1, "_CPPv4N12tensorrt_llm7runtimeE", false]], "tensorrt_llm::runtime::allreducebuffers (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffersE", false]], "tensorrt_llm::runtime::allreducebuffers::allreducebuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", false]], "tensorrt_llm::runtime::allreducebuffers::mallreducecommptrs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers18mAllReduceCommPtrsE", false]], "tensorrt_llm::runtime::allreducebuffers::mflagptrs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers9mFlagPtrsE", false]], "tensorrt_llm::runtime::allreducebuffers::mipcmemoryhandles (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers17mIpcMemoryHandlesE", false]], "tensorrt_llm::runtime::allreducebuffers::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers9TensorPtrE", false]], "tensorrt_llm::runtime::buffercast (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEP1TR7IBuffer", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEPK1TRK7IBuffer", false]], "tensorrt_llm::runtime::buffercastornull (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7IBuffer9SharedPtrE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7ITensor9SharedPtrE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7IBuffer9SharedPtrEEE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7ITensor9SharedPtrEEE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7IBuffer14SharedConstPtrE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7ITensor14SharedConstPtrE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7IBuffer14SharedConstPtrEEE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7ITensor14SharedConstPtrEEE", false]], "tensorrt_llm::runtime::bufferdatatype (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataTypeE", false]], "tensorrt_llm::runtime::bufferdatatype::bufferdatatype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb", false]], "tensorrt_llm::runtime::bufferdatatype::getdatatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType11getDataTypeEv", false]], "tensorrt_llm::runtime::bufferdatatype::getsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType7getSizeEv", false]], "tensorrt_llm::runtime::bufferdatatype::getsizeinbits (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType13getSizeInBitsEv", false]], "tensorrt_llm::runtime::bufferdatatype::ispointer (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType9isPointerEv", false]], "tensorrt_llm::runtime::bufferdatatype::isunsigned (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType10isUnsignedEv", false]], "tensorrt_llm::runtime::bufferdatatype::ktrtpointertype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType15kTrtPointerTypeE", false]], "tensorrt_llm::runtime::bufferdatatype::mdatatype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType9mDataTypeE", false]], "tensorrt_llm::runtime::bufferdatatype::mpointer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType8mPointerE", false]], "tensorrt_llm::runtime::bufferdatatype::munsigned (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType9mUnsignedE", false]], "tensorrt_llm::runtime::bufferdatatype::operator nvinfer1::datatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataTypecvN8nvinfer18DataTypeEEv", false]], "tensorrt_llm::runtime::buffermanager (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManagerE", false]], "tensorrt_llm::runtime::buffermanager::allocate (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE", false], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::buffermanager (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager13BufferManagerE13CudaStreamPtrb", false]], "tensorrt_llm::runtime::buffermanager::copy (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer", false], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType", false], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv", false], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType", false], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferR7IBuffer", false]], "tensorrt_llm::runtime::buffermanager::copyfrom (c++ function)": [[1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10IBufferPtrRKNSt6vectorI1TEE10MemoryType", false], [1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType", false], [1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType", false], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7IBuffer10MemoryType", false], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7ITensor10MemoryType", false]], "tensorrt_llm::runtime::buffermanager::cpu (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", false], [1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuENSt6size_tEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::cudamempoolptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager14CudaMemPoolPtrE", false]], "tensorrt_llm::runtime::buffermanager::cudastreamptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager13CudaStreamPtrE", false]], "tensorrt_llm::runtime::buffermanager::emptybuffer (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyBufferE10MemoryTypeN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::emptytensor (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyTensorE10MemoryTypeN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::getstream (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager9getStreamEv", false]], "tensorrt_llm::runtime::buffermanager::gpu (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", false], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuENSt6size_tEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::gpusync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncEN8nvinfer14DimsEN8nvinfer18DataTypeE", false], [1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncENSt6size_tEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::ibufferptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10IBufferPtrE", false]], "tensorrt_llm::runtime::buffermanager::ipcnvls (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7ipcNvlsENSt3setIiEEN8nvinfer14DimsEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::itensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10ITensorPtrE", false]], "tensorrt_llm::runtime::buffermanager::kbyte_type (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE", false]], "tensorrt_llm::runtime::buffermanager::managed (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedEN8nvinfer14DimsEN8nvinfer18DataTypeE", false], [1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedENSt6size_tEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::memorypoolfree (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager14memoryPoolFreeEv", false]], "tensorrt_llm::runtime::buffermanager::memorypoolreserved (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager18memoryPoolReservedEv", false]], "tensorrt_llm::runtime::buffermanager::memorypooltrimto (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager16memoryPoolTrimToENSt6size_tE", false]], "tensorrt_llm::runtime::buffermanager::memorypoolused (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager14memoryPoolUsedEv", false]], "tensorrt_llm::runtime::buffermanager::mpool (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager5mPoolE", false]], "tensorrt_llm::runtime::buffermanager::mstream (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7mStreamE", false]], "tensorrt_llm::runtime::buffermanager::mtrimpool (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager9mTrimPoolE", false]], "tensorrt_llm::runtime::buffermanager::pinned (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedEN8nvinfer14DimsEN8nvinfer18DataTypeE", false], [1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedENSt6size_tEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::pinnedpool (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolEN8nvinfer14DimsEN8nvinfer18DataTypeE", false], [1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolENSt6size_tEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::setmem (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager6setMemER7IBuffer7int32_t", false]], "tensorrt_llm::runtime::buffermanager::setzero (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager7setZeroER7IBuffer", false]], "tensorrt_llm::runtime::buffermanager::~buffermanager (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManagerD0Ev", false]], "tensorrt_llm::runtime::bufferrange (c++ class)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime11BufferRangeE", false]], "tensorrt_llm::runtime::bufferrange::base (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime11BufferRange4BaseE", false]], "tensorrt_llm::runtime::bufferrange::bufferrange (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI1UEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeERK7IBuffer", false], [1, "_CPPv4I0_NSt11enable_if_tIXntNSt10is_const_vI1UEEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeER7IBuffer", false], [1, "_CPPv4N12tensorrt_llm7runtime11BufferRange11BufferRangeEP1T9size_type", false]], "tensorrt_llm::runtime::canaccesspeer (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13canAccessPeerERK11WorldConfig", false]], "tensorrt_llm::runtime::constpointercast (c++ function)": [[1, "_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERKNSt10shared_ptrI1TEE", false]], "tensorrt_llm::runtime::cudaevent (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEventE", false]], "tensorrt_llm::runtime::cudaevent::cudaevent (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventE7pointerb", false], [1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventEj", false]], "tensorrt_llm::runtime::cudaevent::deleter (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7DeleterE", false]], "tensorrt_llm::runtime::cudaevent::deleter::deleter (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEb", false], [1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEv", false]], "tensorrt_llm::runtime::cudaevent::deleter::mownsevent (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter10mOwnsEventE", false]], "tensorrt_llm::runtime::cudaevent::deleter::operator() (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent7DeleterclE7pointer", false]], "tensorrt_llm::runtime::cudaevent::element_type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent12element_typeE", false]], "tensorrt_llm::runtime::cudaevent::eventptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent8EventPtrE", false]], "tensorrt_llm::runtime::cudaevent::get (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent3getEv", false]], "tensorrt_llm::runtime::cudaevent::mevent (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent6mEventE", false]], "tensorrt_llm::runtime::cudaevent::pointer (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7pointerE", false]], "tensorrt_llm::runtime::cudaevent::synchronize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent11synchronizeEv", false]], "tensorrt_llm::runtime::cudastream (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStreamE", false]], "tensorrt_llm::runtime::cudastream::cudastream (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_t", false], [1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib", false], [1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamEji", false]], "tensorrt_llm::runtime::cudastream::deleter (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7DeleterE", false]], "tensorrt_llm::runtime::cudastream::deleter::deleter (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEb", false], [1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEv", false]], "tensorrt_llm::runtime::cudastream::deleter::mownsstream (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter11mOwnsStreamE", false]], "tensorrt_llm::runtime::cudastream::deleter::operator() (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream7DeleterclE12cudaStream_t", false]], "tensorrt_llm::runtime::cudastream::get (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream3getEv", false]], "tensorrt_llm::runtime::cudastream::getdevice (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream9getDeviceEv", false]], "tensorrt_llm::runtime::cudastream::mdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7mDeviceE", false]], "tensorrt_llm::runtime::cudastream::mstream (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7mStreamE", false]], "tensorrt_llm::runtime::cudastream::record (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordEN9CudaEvent7pointerE", false], [1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordERK9CudaEvent", false]], "tensorrt_llm::runtime::cudastream::streamptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream9StreamPtrE", false]], "tensorrt_llm::runtime::cudastream::synchronize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream11synchronizeEv", false]], "tensorrt_llm::runtime::cudastream::wait (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitEN9CudaEvent7pointerE", false], [1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitERK9CudaEvent", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4I_N8nvinfer18DataTypeE_b_bEN12tensorrt_llm7runtime14DataTypeTraitsE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4typeE", false]], "tensorrt_llm::runtime::decoder (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoderE", false]], "tensorrt_llm::runtime::decoder::beamsearchbuffers (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffersE", false]], "tensorrt_llm::runtime::decoder::beamsearchbuffers::beamsearchbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers17BeamSearchBuffersERK13BufferManager", false]], "tensorrt_llm::runtime::decoder::beamsearchbuffers::mcumlogprobstmp (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers15mCumLogProbsTmpE", false]], "tensorrt_llm::runtime::decoder::beamsearchbuffers::mnumsms (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers7mNumSMsE", false]], "tensorrt_llm::runtime::decoder::beamsearchbuffers::moutputbeamhypotheses (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers21mOutputBeamHypothesesE", false]], "tensorrt_llm::runtime::decoder::beamsearchbuffers::reshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers7reshapeE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::decoder::decoderstate (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderStateE", false]], "tensorrt_llm::runtime::decoder::decoderstate::decoderstate (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState12DecoderStateEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::decodinginputptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState16DecodingInputPtrE", false]], "tensorrt_llm::runtime::decoder::decoderstate::decodingoutputptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState17DecodingOutputPtrE", false]], "tensorrt_llm::runtime::decoder::decoderstate::disablelookahead (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState16disableLookaheadERK13RequestVector", false]], "tensorrt_llm::runtime::decoder::decoderstate::getacceptedlengthscumsum (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState24getAcceptedLengthsCumSumEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getacceptedpackedpaths (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState22getAcceptedPackedPathsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getallnewtokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState15getAllNewTokensEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getbeamsearchbuffers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState20getBeamSearchBuffersEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getcacheindirectioninput (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState24getCacheIndirectionInputEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getcacheindirectionoutput (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState25getCacheIndirectionOutputEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getcumlogprobs (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getCumLogProbsE10SizeType32", false], [1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getCumLogProbsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::geteaglebuffers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState15getEagleBuffersEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getexplicitdrafttokensbuffers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState29getExplicitDraftTokensBuffersEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getfinishedsteps (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState16getFinishedStepsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getfinishedsum (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getFinishedSumEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getfinishreasons (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState16getFinishReasonsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getgatheredids (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getGatheredIdsE10SizeType32", false], [1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getGatheredIdsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getgenerationsteps (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getGenerationStepsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getids (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState6getIdsE10SizeType32", false], [1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState6getIdsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getjointdecodinginput (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState21getJointDecodingInputEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getjointdecodingoutput (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState22getJointDecodingOutputEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getlogprobs (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState11getLogProbsE10SizeType32", false], [1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState11getLogProbsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getlookaheadbuffers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState19getLookaheadBuffersEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getmaxbatchsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState15getMaxBatchSizeEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getmaxbeamwidth (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState15getMaxBeamWidthEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getmaxdecodingdecodertokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState27getMaxDecodingDecoderTokensEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getmaxdecodingenginetokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getMaxDecodingEngineTokensEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getmaxsequencelength (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState20getMaxSequenceLengthEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getnextdrafttokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getNextDraftTokensEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getnextdrafttokenslengths (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState25getNextDraftTokensLengthsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getnumdecodingenginetokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getNumDecodingEngineTokensE10SizeType32", false], [1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getNumDecodingEngineTokensEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getparentids (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState12getParentIdsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getprevdrafttokenslengths (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState25getPrevDraftTokensLengthsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getsequencelengths (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getSequenceLengthsE10SizeType32", false], [1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getSequenceLengthsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getspeculativedecodingmode (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getSpeculativeDecodingModeEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::llmrequestptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState13LlmRequestPtrE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mbeamsearchbuffers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState18mBeamSearchBuffersE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mfinishedsteps (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14mFinishedStepsE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mjointdecodinginput (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState19mJointDecodingInputE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mjointdecodingoutput (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState20mJointDecodingOutputE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mmaxbatchsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState13mMaxBatchSizeE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mmaxbeamwidth (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState13mMaxBeamWidthE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mmaxdecodingdecodertokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState25mMaxDecodingDecoderTokensE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mmaxdecodingenginetokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24mMaxDecodingEngineTokensE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mmaxsequencelength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState18mMaxSequenceLengthE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mnumdecodingenginetokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24mNumDecodingEngineTokensE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mspeculativedecodingmode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24mSpeculativeDecodingModeE", false]], "tensorrt_llm::runtime::decoder::decoderstate::requestvector (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState13RequestVectorE", false]], "tensorrt_llm::runtime::decoder::decoderstate::reshapebuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", false]], "tensorrt_llm::runtime::decoder::decoderstate::reshapecacheindirectionbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState30reshapeCacheIndirectionBuffersE10SizeType3210SizeType3210SizeType32", false]], "tensorrt_llm::runtime::decoder::decoderstate::reshapespeculativedecodingbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState33reshapeSpeculativeDecodingBuffersERK23SpeculativeDecodingMode10SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", false]], "tensorrt_llm::runtime::decoder::decoderstate::setgenerationsteps (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState18setGenerationStepsERKNSt6vectorI10SizeType32EE", false]], "tensorrt_llm::runtime::decoder::decoderstate::setnumdecodingenginetokens (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState26setNumDecodingEngineTokensE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::decoder::decoderstate::setup (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", false]], "tensorrt_llm::runtime::decoder::decoderstate::setupbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState12setupBuffersEN8nvinfer18DataTypeERK13BufferManager", false]], "tensorrt_llm::runtime::decoder::decoderstate::setupcacheindirection (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState21setupCacheIndirectionE10SizeType3210SizeType3210SizeType32RK13BufferManager", false]], "tensorrt_llm::runtime::decoder::decoderstate::setupcacheindirectionbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState28setupCacheIndirectionBuffersERK13BufferManager", false]], "tensorrt_llm::runtime::decoder::decoderstate::setupspeculativedecoding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24setupSpeculativeDecodingERK23SpeculativeDecodingMode10SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", false]], "tensorrt_llm::runtime::decoder::decoderstate::setupspeculativedecodingbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState31setupSpeculativeDecodingBuffersE23SpeculativeDecodingModeN8nvinfer18DataTypeERK13BufferManager", false]], "tensorrt_llm::runtime::decoder::decoderstate::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState9TensorPtrE", false]], "tensorrt_llm::runtime::decoder_batch (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batchE", false]], "tensorrt_llm::runtime::decoder_batch::input (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5InputE", false]], "tensorrt_llm::runtime::decoder_batch::input::batchslots (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input10batchSlotsE", false]], "tensorrt_llm::runtime::decoder_batch::input::input (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI14TensorConstPtrEE", false], [1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorINSt6vectorI14TensorConstPtrEEEE10SizeType32", false]], "tensorrt_llm::runtime::decoder_batch::input::logits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input6logitsE", false]], "tensorrt_llm::runtime::decoder_batch::input::maxdecodersteps (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input15maxDecoderStepsE", false]], "tensorrt_llm::runtime::decoder_batch::input::tensorconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input14TensorConstPtrE", false]], "tensorrt_llm::runtime::decoder_batch::input::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input9TensorPtrE", false]], "tensorrt_llm::runtime::decoder_batch::request (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7RequestE", false]], "tensorrt_llm::runtime::decoder_batch::request::badwordslist (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request12badWordsListE", false]], "tensorrt_llm::runtime::decoder_batch::request::bufferptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9BufferPtrE", false]], "tensorrt_llm::runtime::decoder_batch::request::draftlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11draftLogitsE", false]], "tensorrt_llm::runtime::decoder_batch::request::drafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11draftTokensE", false]], "tensorrt_llm::runtime::decoder_batch::request::eagleconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11eagleConfigE", false]], "tensorrt_llm::runtime::decoder_batch::request::embeddingbias (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13embeddingBiasE", false]], "tensorrt_llm::runtime::decoder_batch::request::endid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request5endIdE", false]], "tensorrt_llm::runtime::decoder_batch::request::generatedtokensperenginestep (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request28generatedTokensPerEngineStepE", false]], "tensorrt_llm::runtime::decoder_batch::request::ids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request3idsE", false]], "tensorrt_llm::runtime::decoder_batch::request::inputlen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request8inputLenE", false]], "tensorrt_llm::runtime::decoder_batch::request::lookaheadruntimeconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request22lookaheadRuntimeConfigE", false]], "tensorrt_llm::runtime::decoder_batch::request::maxnewtokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request12maxNewTokensE", false]], "tensorrt_llm::runtime::decoder_batch::request::medusapaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11medusaPathsE", false]], "tensorrt_llm::runtime::decoder_batch::request::medusatreeids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13medusaTreeIdsE", false]], "tensorrt_llm::runtime::decoder_batch::request::request (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14TensorConstPtr10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", false]], "tensorrt_llm::runtime::decoder_batch::request::stopwordslist (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13stopWordsListE", false]], "tensorrt_llm::runtime::decoder_batch::request::tensorconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request14TensorConstPtrE", false]], "tensorrt_llm::runtime::decoder_batch::request::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9TensorPtrE", false]], "tensorrt_llm::runtime::decodinginput (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInputE", false]], "tensorrt_llm::runtime::decodinginput::badwordslens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12badWordsLensE", false]], "tensorrt_llm::runtime::decodinginput::badwordslists (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13badWordsListsE", false]], "tensorrt_llm::runtime::decodinginput::badwordsptrs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12badWordsPtrsE", false]], "tensorrt_llm::runtime::decodinginput::batchsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9batchSizeE", false]], "tensorrt_llm::runtime::decodinginput::batchslots (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput10batchSlotsE", false]], "tensorrt_llm::runtime::decodinginput::beamwidths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput10beamWidthsE", false]], "tensorrt_llm::runtime::decodinginput::cacheindirection (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput16cacheIndirectionE", false]], "tensorrt_llm::runtime::decodinginput::decodinginput (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13DecodingInputEv", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11eagleInputsE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputsE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::acceptedlens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs12acceptedLensE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::acceptedpathids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs15acceptedPathIdsE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::acceptedtokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs14acceptedTokensE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::chunkedcontextnexttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs24chunkedContextNextTokensE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::lastdraftlens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs13lastDraftLensE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::lastdraftpaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs14lastDraftPathsE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::lastdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs15lastDraftTokensE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::nextdraftlens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs13nextDraftLensE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::nextdraftpaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs14nextDraftPathsE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::nextdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs15nextDraftTokensE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::seqslots (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs8seqSlotsE", false]], "tensorrt_llm::runtime::decodinginput::embeddingbias (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13embeddingBiasE", false]], "tensorrt_llm::runtime::decodinginput::endids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput6endIdsE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputsE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25explicitDraftTokensInputsE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::bestpathindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15bestPathIndicesE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::bestpathlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15bestPathLengthsE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::lastdraftindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs16lastDraftIndicesE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::lastdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15lastDraftTokensE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::lastgenerationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs21lastGenerationLengthsE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::lastpositionidsbase (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs19lastPositionIdsBaseE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::masks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs5masksE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::maxgenlengthdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs18maxGenLengthDeviceE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::nextdraftindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs16nextDraftIndicesE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::nextdraftprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs14nextDraftProbsE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::nextdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15nextDraftTokensE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::nextflattokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs14nextFlatTokensE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::nextgenerationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs21nextGenerationLengthsE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::packedpositionids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs17packedPositionIdsE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::seqslots (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs8seqSlotsE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputsE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25externalDraftTokensInputsE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::constantthreshold (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs17constantThresholdE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::draftlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs11draftLogitsE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::draftprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs10draftProbsE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::drafttokenids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs13draftTokenIdsE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::numdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs14numDraftTokensE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::numdrafttokenshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs18numDraftTokensHostE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::step (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs4stepE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::targetprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs11targetProbsE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::usedraftlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs14useDraftLogitsE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::usedraftlogitshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs18useDraftLogitsHostE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::userandomacceptancethreshold (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs28useRandomAcceptanceThresholdE", false]], "tensorrt_llm::runtime::decodinginput::finishreasons (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13finishReasonsE", false]], "tensorrt_llm::runtime::decodinginput::generationsteps (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15generationStepsE", false]], "tensorrt_llm::runtime::decodinginput::lengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput7lengthsE", false]], "tensorrt_llm::runtime::decodinginput::logitsvec (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9logitsVecE", false]], "tensorrt_llm::runtime::decodinginput::lookaheadinputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15lookaheadInputsE", false]], "tensorrt_llm::runtime::decodinginput::lookaheadinputs (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15LookaheadInputsE", false]], "tensorrt_llm::runtime::decodinginput::lookaheadinputs::tokensperstep (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15LookaheadInputs13tokensPerStepE", false]], "tensorrt_llm::runtime::decodinginput::maxattentionwindow (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput18maxAttentionWindowE", false]], "tensorrt_llm::runtime::decodinginput::maxbadwordslen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput14maxBadWordsLenE", false]], "tensorrt_llm::runtime::decodinginput::maxlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9maxLengthE", false]], "tensorrt_llm::runtime::decodinginput::maxstopwordslen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15maxStopWordsLenE", false]], "tensorrt_llm::runtime::decodinginput::medusainputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputsE", false]], "tensorrt_llm::runtime::decodinginput::medusainputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12medusaInputsE", false]], "tensorrt_llm::runtime::decodinginput::medusainputs::medusacurtokensperstep (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs22medusaCurTokensPerStepE", false]], "tensorrt_llm::runtime::decodinginput::medusainputs::medusalogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs12medusaLogitsE", false]], "tensorrt_llm::runtime::decodinginput::medusainputs::medusapaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs11medusaPathsE", false]], "tensorrt_llm::runtime::decodinginput::medusainputs::medusatargettokensperstep (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs25medusaTargetTokensPerStepE", false]], "tensorrt_llm::runtime::decodinginput::medusainputs::medusatreeids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs13medusaTreeIdsE", false]], "tensorrt_llm::runtime::decodinginput::norepeatngramsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput17noRepeatNgramSizeE", false]], "tensorrt_llm::runtime::decodinginput::sequencelimitlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput19sequenceLimitLengthE", false]], "tensorrt_llm::runtime::decodinginput::sinktokenlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15sinkTokenLengthE", false]], "tensorrt_llm::runtime::decodinginput::step (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput4stepE", false]], "tensorrt_llm::runtime::decodinginput::stopwordslens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13stopWordsLensE", false]], "tensorrt_llm::runtime::decodinginput::stopwordslists (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput14stopWordsListsE", false]], "tensorrt_llm::runtime::decodinginput::stopwordsptrs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13stopWordsPtrsE", false]], "tensorrt_llm::runtime::decodinginput::tensorconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput14TensorConstPtrE", false]], "tensorrt_llm::runtime::decodinginput::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE", false]], "tensorrt_llm::runtime::decodingoutput (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutputE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypothesesE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14beamHypothesesE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::batchdones (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses10batchDonesE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::cumlogprobscba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses14cumLogProbsCBAE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::empty (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5emptyERK13BufferManager", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::init (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses4initERK13BufferManager11TokenIdType", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::logprobscba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses11logProbsCBAE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::minnormedscorescba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses18minNormedScoresCBAE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::normedscorescba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses15normedScoresCBAE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::numbeamscba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses11numBeamsCBAE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::outputidscba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses12outputIdsCBAE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::release (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7releaseEv", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::reshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE10SizeType3210SizeType3210SizeType32", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::sequencelengthscba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses18sequenceLengthsCBAE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::slice (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5sliceE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::decodingoutput::cacheindirection (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput16cacheIndirectionE", false]], "tensorrt_llm::runtime::decodingoutput::cumlogprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11cumLogProbsE", false]], "tensorrt_llm::runtime::decodingoutput::decodingoutput (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14DecodingOutputEv", false]], "tensorrt_llm::runtime::decodingoutput::eaglebuffers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput12eagleBuffersE", false]], "tensorrt_llm::runtime::decodingoutput::explicitdrafttokensbuffers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26explicitDraftTokensBuffersE", false]], "tensorrt_llm::runtime::decodingoutput::finishedsum (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11finishedSumE", false]], "tensorrt_llm::runtime::decodingoutput::finishreasons (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput13finishReasonsE", false]], "tensorrt_llm::runtime::decodingoutput::gatheredids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11gatheredIdsE", false]], "tensorrt_llm::runtime::decodingoutput::ids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput3idsE", false]], "tensorrt_llm::runtime::decodingoutput::knegativeinfinity (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput17kNegativeInfinityE", false]], "tensorrt_llm::runtime::decodingoutput::lengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput7lengthsE", false]], "tensorrt_llm::runtime::decodingoutput::logprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput8logProbsE", false]], "tensorrt_llm::runtime::decodingoutput::logprobstiled (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput13logProbsTiledE", false]], "tensorrt_llm::runtime::decodingoutput::lookaheadoutputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput16lookaheadOutputsE", false]], "tensorrt_llm::runtime::decodingoutput::newtokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9newTokensE", false]], "tensorrt_llm::runtime::decodingoutput::newtokenssteps (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14newTokensStepsE", false]], "tensorrt_llm::runtime::decodingoutput::newtokensvec (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput12newTokensVecE", false]], "tensorrt_llm::runtime::decodingoutput::parentids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9parentIdsE", false]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputsE", false]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26speculativeDecodingOutputsE", false]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::acceptedlengthscumsum (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs21acceptedLengthsCumSumE", false]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::acceptedtokenslen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs17acceptedTokensLenE", false]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::nextdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs15nextDraftTokensE", false]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::nextdrafttokenslen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs18nextDraftTokensLenE", false]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::pathsoffsets (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs12pathsOffsetsE", false]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::prevdrafttokenslen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs18prevDraftTokensLenE", false]], "tensorrt_llm::runtime::decodingoutput::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE", false]], "tensorrt_llm::runtime::deviceallocationnvls (c++ class)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime20DeviceAllocationNvlsE", false]], "tensorrt_llm::runtime::deviceallocationnvls::_capacity (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls9_capacityE", false]], "tensorrt_llm::runtime::deviceallocationnvls::_handle (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls7_handleE", false]], "tensorrt_llm::runtime::deviceallocationnvls::deviceallocationnvls (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls20DeviceAllocationNvlsEv", false]], "tensorrt_llm::runtime::deviceallocationnvls::free (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls4freeEv", false]], "tensorrt_llm::runtime::deviceallocationnvls::getcapacity (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime20DeviceAllocationNvls11getCapacityEv", false]], "tensorrt_llm::runtime::deviceallocationnvls::getipcunicastpointers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls21getIpcUnicastPointersEv", false]], "tensorrt_llm::runtime::deviceallocationnvls::getmulticastpointer (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime20DeviceAllocationNvls19getMulticastPointerEv", false]], "tensorrt_llm::runtime::deviceallocationnvls::getunicastpointer (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime20DeviceAllocationNvls17getUnicastPointerEv", false]], "tensorrt_llm::runtime::deviceallocationnvls::reset (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls5resetE6size_tNSt3setIiEE", false]], "tensorrt_llm::runtime::deviceallocationnvls::~deviceallocationnvls (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvlsD0Ev", false]], "tensorrt_llm::runtime::eaglebuffers (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffersE", false]], "tensorrt_llm::runtime::eaglebuffers::bufferptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers9BufferPtrE", false]], "tensorrt_llm::runtime::eaglebuffers::chunkedcontextnexttokenshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers28chunkedContextNextTokensHostE", false]], "tensorrt_llm::runtime::eaglebuffers::cumsumgenerationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers23cumSumGenerationLengthsE", false]], "tensorrt_llm::runtime::eaglebuffers::eaglebuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12EagleBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigE", false]], "tensorrt_llm::runtime::eaglebuffers::engineinputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12engineInputsE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputsE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13engineOutputsE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs::acceptedlens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs12acceptedLensE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs::acceptedpaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs13acceptedPathsE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs::acceptedtokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs14acceptedTokensE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs::chunkedcontextnexttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs24chunkedContextNextTokensE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs::nextdraftlens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs13nextDraftLensE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs::nextdraftpaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs14nextDraftPathsE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs::nextdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs15nextDraftTokensE", false]], "tensorrt_llm::runtime::eaglebuffers::greedysamplinghost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers18greedySamplingHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6InputsE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::alllayersdrafttokenids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs22allLayersDraftTokenIdsE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::alllayersdrafttokenidspredecessor (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs33allLayersDraftTokenIdsPredecessorE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::alllayersscores (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs15allLayersScoresE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::chunkedcontextnexttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs24chunkedContextNextTokensE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::create (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs6createE10SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfig", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::currentexpandindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs20currentExpandIndicesE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::draftlens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs9draftLensE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::draftpaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs10draftPathsE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::draftpathshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs14draftPathsHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::drafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs11draftTokensE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::dynamictreemaxtopkhost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs22dynamicTreeMaxTopKHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::eaglenetctxcontextlengthshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs29eagleNetCtxContextLengthsHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::eaglenetctxpastkeyvaluelengthshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs34eagleNetCtxPastKeyValueLengthsHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::eaglenetctxrequesttypeshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs27eagleNetCtxRequestTypesHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::eaglenetgencontextlengthshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs29eagleNetGenContextLengthsHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::eaglenetgenpastkeyvaluelengthshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs34eagleNetGenPastKeyValueLengthsHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::eaglenetgenrequesttypeshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs27eagleNetGenRequestTypesHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::inputgentokenshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs18inputGenTokensHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::posterioralpha (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs14posteriorAlphaE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::posteriorthreshold (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs18posteriorThresholdE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::prevscores (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs10prevScoresE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::randomdatasample (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs16randomDataSampleE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::randomdatavalidation (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs20randomDataValidationE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::specdecodinggenerationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs29specDecodingGenerationLengthsE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::specdecodinggenerationlengthshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs33specDecodingGenerationLengthsHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::specdecodingpackedmasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs23specDecodingPackedMasksE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::specdecodingpositionoffsets (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs27specDecodingPositionOffsetsE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::temperatures (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs12temperaturesE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::usedynamictreehost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs18useDynamicTreeHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::usespecdecoding (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs15useSpecDecodingE", false]], "tensorrt_llm::runtime::eaglebuffers::insertinputtensors (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", false]], "tensorrt_llm::runtime::eaglebuffers::itensor (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers7ITensorE", false]], "tensorrt_llm::runtime::eaglebuffers::llmrequestptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13LlmRequestPtrE", false]], "tensorrt_llm::runtime::eaglebuffers::maxgenerationlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers19maxGenerationLengthE", false]], "tensorrt_llm::runtime::eaglebuffers::mdefaultposteriorthreshold (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers26mDefaultPosteriorThresholdE", false]], "tensorrt_llm::runtime::eaglebuffers::mdogreedysampling (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers17mDoGreedySamplingE", false]], "tensorrt_llm::runtime::eaglebuffers::posterioralphahost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers18posteriorAlphaHostE", false]], "tensorrt_llm::runtime::eaglebuffers::posteriorthresholdhost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers22posteriorThresholdHostE", false]], "tensorrt_llm::runtime::eaglebuffers::requestvector (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13RequestVectorE", false]], "tensorrt_llm::runtime::eaglebuffers::reshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", false]], "tensorrt_llm::runtime::eaglebuffers::scanreducetempstorage (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers21scanReduceTempStorageE", false]], "tensorrt_llm::runtime::eaglebuffers::scanreducetempstoragebytes (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers26scanReduceTempStorageBytesE", false]], "tensorrt_llm::runtime::eaglebuffers::setfrominputs (c++ function)": [[1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", false], [1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", false]], "tensorrt_llm::runtime::eaglebuffers::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers10SizeType32E", false]], "tensorrt_llm::runtime::eaglebuffers::tensormap (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers9TensorMapE", false]], "tensorrt_llm::runtime::eaglebuffers::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers9TensorPtrE", false]], "tensorrt_llm::runtime::eaglemodule (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime11EagleModuleE", false]], "tensorrt_llm::runtime::eaglemodule::eaglemodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11EagleModule11EagleModuleE10SizeType3210SizeType3210SizeType3210SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime11EagleModule11EagleModuleEv", false]], "tensorrt_llm::runtime::eaglemodule::getdefaulteaglechoices (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11EagleModule22getDefaultEagleChoicesEv", false]], "tensorrt_llm::runtime::eaglemodule::getmaxnonleafnodesperlayer (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11EagleModule26getMaxNonLeafNodesPerLayerEv", false]], "tensorrt_llm::runtime::eaglemodule::getnumtransformerlayers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11EagleModule23getNumTransformerLayersEv", false]], "tensorrt_llm::runtime::eaglemodule::mdefaulteaglechoices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11EagleModule20mDefaultEagleChoicesE", false]], "tensorrt_llm::runtime::eaglemodule::mmaxnonleafnodesperlayer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11EagleModule24mMaxNonLeafNodesPerLayerE", false]], "tensorrt_llm::runtime::eaglemodule::mnumtransformerslayer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11EagleModule21mNumTransformersLayerE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffersE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::bufferptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers9BufferPtrE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::cumsumgenerationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers23cumSumGenerationLengthsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineinputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineinputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12engineInputsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineinputs::positionoffsets (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputs15positionOffsetsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineinputs::requesttypesdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputs18requestTypesDeviceE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13engineOutputsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::bestpathindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15bestPathIndicesE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::bestpathlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15bestPathLengthsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::masks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs5masksE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::maxgentoken (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs11maxGenTokenE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextdraftindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs16nextDraftIndicesE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextdraftprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs14nextDraftProbsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15nextDraftTokensE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextflattokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs14nextFlatTokensE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextgenerationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs21nextGenerationLengthsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextpositionoffsets (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs19nextPositionOffsetsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::packedpositionids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs17packedPositionIdsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::totalgentoken (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs13totalGenTokenE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::explicitdrafttokensbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6InputsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::create (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::draftindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs12draftIndicesE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::draftprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs10draftProbsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::drafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11draftTokensE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::generationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs17generationLengthsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::generationlengthshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs21generationLengthsHostE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::maxgenlengthhost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs16maxGenLengthHostE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::packedmasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11packedMasksE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::positionids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11positionIdsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::positionidsbase (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs15positionIdsBaseE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::randomdatasample (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs16randomDataSampleE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::randomdatavalidation (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs20randomDataValidationE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::temperatures (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs12temperaturesE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::usespecdecoding (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs15useSpecDecodingE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::insertinputtensors (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::itensor (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7ITensorE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::reshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::scantempstorage (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers15scanTempStorageE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::scantempstoragebytes (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers20scanTempStorageBytesE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::setfrominputs (c++ function)": [[1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", false], [1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers10SizeType32E", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::tensormap (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers9TensorMapE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers9TensorPtrE", false]], "tensorrt_llm::runtime::genericprompttuningparams (c++ class)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime25GenericPromptTuningParamsE", false]], "tensorrt_llm::runtime::genericprompttuningparams::embeddingtable (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams14embeddingTableE", false]], "tensorrt_llm::runtime::genericprompttuningparams::genericprompttuningparams (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", false]], "tensorrt_llm::runtime::genericprompttuningparams::prompttuningenabled (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams19promptTuningEnabledE", false]], "tensorrt_llm::runtime::genericprompttuningparams::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams10SizeType32E", false]], "tensorrt_llm::runtime::genericprompttuningparams::tasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams5tasksE", false]], "tensorrt_llm::runtime::genericprompttuningparams::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE", false]], "tensorrt_llm::runtime::genericprompttuningparams::vocabsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9vocabSizeE", false]], "tensorrt_llm::runtime::getdefaultbatchslots (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20getDefaultBatchSlotsEN7runtime10SizeType32E", false]], "tensorrt_llm::runtime::gptdecoder (c++ class)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime10GptDecoderE", false]], "tensorrt_llm::runtime::gptdecoder::cudastreamptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13CudaStreamPtrE", false]], "tensorrt_llm::runtime::gptdecoder::disablelookahead (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", false]], "tensorrt_llm::runtime::gptdecoder::forwardasync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", false]], "tensorrt_llm::runtime::gptdecoder::forwardsync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", false]], "tensorrt_llm::runtime::gptdecoder::getsamplingconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder17getSamplingConfigEv", false]], "tensorrt_llm::runtime::gptdecoder::gptdecoder (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", false]], "tensorrt_llm::runtime::gptdecoder::mdecodinglayerworkspace (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder23mDecodingLayerWorkspaceE", false]], "tensorrt_llm::runtime::gptdecoder::mdecodingmode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13mDecodingModeE", false]], "tensorrt_llm::runtime::gptdecoder::mdynamicdecodelayer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder19mDynamicDecodeLayerE", false]], "tensorrt_llm::runtime::gptdecoder::mmanager (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder8mManagerE", false]], "tensorrt_llm::runtime::gptdecoder::mmaxbatchsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13mMaxBatchSizeE", false]], "tensorrt_llm::runtime::gptdecoder::msamplingconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder15mSamplingConfigE", false]], "tensorrt_llm::runtime::gptdecoder::mvocabsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10mVocabSizeE", false]], "tensorrt_llm::runtime::gptdecoder::mvocabsizepadded (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder16mVocabSizePaddedE", false]], "tensorrt_llm::runtime::gptdecoder::setup (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", false]], "tensorrt_llm::runtime::gptdecoder::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder9TensorPtrE", false]], "tensorrt_llm::runtime::gptdecoderbatched (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatchedE", false]], "tensorrt_llm::runtime::gptdecoderbatched::cudastreamptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13CudaStreamPtrE", false]], "tensorrt_llm::runtime::gptdecoderbatched::disablelookahead (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16disableLookaheadERK13RequestVectorRK9TensorPtr", false]], "tensorrt_llm::runtime::gptdecoderbatched::finalize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", false]], "tensorrt_llm::runtime::gptdecoderbatched::forward (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched7forwardERKN7decoder12DecoderStateERKN13decoder_batch5InputE", false]], "tensorrt_llm::runtime::gptdecoderbatched::forwardasync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12forwardAsyncERKN7decoder12DecoderStateERKN13decoder_batch5InputE", false]], "tensorrt_llm::runtime::gptdecoderbatched::forwarddispatch (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15forwardDispatchERKN7decoder12DecoderStateERKN13decoder_batch5InputE", false]], "tensorrt_llm::runtime::gptdecoderbatched::getbuffermanager (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched16getBufferManagerEv", false]], "tensorrt_llm::runtime::gptdecoderbatched::getdecoderstream (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched16getDecoderStreamEv", false]], "tensorrt_llm::runtime::gptdecoderbatched::getunderlyingdecoder (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched20getUnderlyingDecoderEv", false]], "tensorrt_llm::runtime::gptdecoderbatched::gptdecoderbatched (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched17GptDecoderBatchedE13CudaStreamPtr", false]], "tensorrt_llm::runtime::gptdecoderbatched::gptdecoderptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13GptDecoderPtrE", false]], "tensorrt_llm::runtime::gptdecoderbatched::llmrequestptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13LlmRequestPtrE", false]], "tensorrt_llm::runtime::gptdecoderbatched::mbuffermanager (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mBufferManagerE", false]], "tensorrt_llm::runtime::gptdecoderbatched::mdecoder (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched8mDecoderE", false]], "tensorrt_llm::runtime::gptdecoderbatched::mdecoderstream (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mDecoderStreamE", false]], "tensorrt_llm::runtime::gptdecoderbatched::mruntimestream (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mRuntimeStreamE", false]], "tensorrt_llm::runtime::gptdecoderbatched::requestvector (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13RequestVectorE", false]], "tensorrt_llm::runtime::gptdecoderbatched::setup (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", false]], "tensorrt_llm::runtime::gptdecoderbatched::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched9TensorPtrE", false]], "tensorrt_llm::runtime::gptjsonconfig (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfigE", false]], "tensorrt_llm::runtime::gptjsonconfig::enginefilename (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfig", false], [1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfigRKNSt6stringE", false]], "tensorrt_llm::runtime::gptjsonconfig::getcontextparallelism (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig21getContextParallelismEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getgpuspernode (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14getGpusPerNodeEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getmodelconfig (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14getModelConfigEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getmodelconfigmutable (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig21getModelConfigMutableEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getname (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig7getNameEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getpipelineparallelism (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig22getPipelineParallelismEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getprecision (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getPrecisionEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getruntimedefaults (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig18getRuntimeDefaultsEv", false]], "tensorrt_llm::runtime::gptjsonconfig::gettensorparallelism (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig20getTensorParallelismEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getversion (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig10getVersionEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getworldsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getWorldSizeEv", false]], "tensorrt_llm::runtime::gptjsonconfig::gptjsonconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", false]], "tensorrt_llm::runtime::gptjsonconfig::mcontextparallelism (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig19mContextParallelismE", false]], "tensorrt_llm::runtime::gptjsonconfig::mgpuspernode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig12mGpusPerNodeE", false]], "tensorrt_llm::runtime::gptjsonconfig::mmodelconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig12mModelConfigE", false]], "tensorrt_llm::runtime::gptjsonconfig::mname (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5mNameE", false]], "tensorrt_llm::runtime::gptjsonconfig::mpipelineparallelism (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig20mPipelineParallelismE", false]], "tensorrt_llm::runtime::gptjsonconfig::mprecision (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig10mPrecisionE", false]], "tensorrt_llm::runtime::gptjsonconfig::mruntimedefaults (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig16mRuntimeDefaultsE", false]], "tensorrt_llm::runtime::gptjsonconfig::mtensorparallelism (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig18mTensorParallelismE", false]], "tensorrt_llm::runtime::gptjsonconfig::mversion (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig8mVersionE", false]], "tensorrt_llm::runtime::gptjsonconfig::parse (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt10filesystem4pathE", false], [1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt6stringE", false], [1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERNSt7istreamE", false]], "tensorrt_llm::runtime::ibuffer (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBufferE", false]], "tensorrt_llm::runtime::ibuffer::data (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE", false], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4dataEv", false], [1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE", false], [1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataEv", false]], "tensorrt_llm::runtime::ibuffer::datatype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer8DataTypeE", false]], "tensorrt_llm::runtime::ibuffer::getcapacity (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer11getCapacityEv", false]], "tensorrt_llm::runtime::ibuffer::getdatatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer11getDataTypeEv", false]], "tensorrt_llm::runtime::ibuffer::getdatatypename (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer15getDataTypeNameE8DataType", false], [1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer15getDataTypeNameEv", false]], "tensorrt_llm::runtime::ibuffer::getmemorytype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer13getMemoryTypeEv", false]], "tensorrt_llm::runtime::ibuffer::getmemorytypename (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer17getMemoryTypeNameEv", false]], "tensorrt_llm::runtime::ibuffer::getsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer7getSizeEv", false]], "tensorrt_llm::runtime::ibuffer::getsizeinbytes (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer14getSizeInBytesEv", false]], "tensorrt_llm::runtime::ibuffer::ibuffer (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferERK7IBuffer", false], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferEv", false]], "tensorrt_llm::runtime::ibuffer::memorytype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer10memoryTypeEPKv", false]], "tensorrt_llm::runtime::ibuffer::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBufferaSERK7IBuffer", false]], "tensorrt_llm::runtime::ibuffer::release (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer7releaseEv", false]], "tensorrt_llm::runtime::ibuffer::resize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer6resizeENSt6size_tE", false]], "tensorrt_llm::runtime::ibuffer::sharedconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer14SharedConstPtrE", false]], "tensorrt_llm::runtime::ibuffer::sharedptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer9SharedPtrE", false]], "tensorrt_llm::runtime::ibuffer::slice (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", false], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", false], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tE", false], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE", false]], "tensorrt_llm::runtime::ibuffer::tobytes (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer7toBytesENSt6size_tE", false]], "tensorrt_llm::runtime::ibuffer::uniqueconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer14UniqueConstPtrE", false]], "tensorrt_llm::runtime::ibuffer::uniqueptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE", false]], "tensorrt_llm::runtime::ibuffer::view (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE", false], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtr", false], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtrNSt6size_tE", false]], "tensorrt_llm::runtime::ibuffer::wrap (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrRNSt6vectorI1TEE", false], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE", false], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE", false]], "tensorrt_llm::runtime::ibuffer::~ibuffer (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBufferD0Ev", false]], "tensorrt_llm::runtime::igptdecoder (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoderE", false]], "tensorrt_llm::runtime::igptdecoder::create (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", false]], "tensorrt_llm::runtime::igptdecoder::disablelookahead (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", false]], "tensorrt_llm::runtime::igptdecoder::forwardasync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", false]], "tensorrt_llm::runtime::igptdecoder::forwardsync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", false]], "tensorrt_llm::runtime::igptdecoder::getsamplingconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder17getSamplingConfigEv", false]], "tensorrt_llm::runtime::igptdecoder::setup (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", false]], "tensorrt_llm::runtime::igptdecoder::tensorconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder14TensorConstPtrE", false]], "tensorrt_llm::runtime::igptdecoder::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder9TensorPtrE", false]], "tensorrt_llm::runtime::igptdecoder::~igptdecoder (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoderD0Ev", false]], "tensorrt_llm::runtime::igptdecoderbatched (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatchedE", false]], "tensorrt_llm::runtime::igptdecoderbatched::cudastreamptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched13CudaStreamPtrE", false]], "tensorrt_llm::runtime::igptdecoderbatched::disablelookahead (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched16disableLookaheadERK13RequestVectorRK9TensorPtr", false]], "tensorrt_llm::runtime::igptdecoderbatched::finalize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", false]], "tensorrt_llm::runtime::igptdecoderbatched::forward (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched7forwardERKN7decoder12DecoderStateERKN13decoder_batch5InputE", false]], "tensorrt_llm::runtime::igptdecoderbatched::forwardasync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched12forwardAsyncERKN7decoder12DecoderStateERKN13decoder_batch5InputE", false]], "tensorrt_llm::runtime::igptdecoderbatched::igptdecoderbatched (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched18IGptDecoderBatchedEv", false]], "tensorrt_llm::runtime::igptdecoderbatched::llmrequestptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched13LlmRequestPtrE", false]], "tensorrt_llm::runtime::igptdecoderbatched::requestvector (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched13RequestVectorE", false]], "tensorrt_llm::runtime::igptdecoderbatched::setup (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", false]], "tensorrt_llm::runtime::igptdecoderbatched::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched9TensorPtrE", false]], "tensorrt_llm::runtime::igptdecoderbatched::~igptdecoderbatched (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatchedD0Ev", false]], "tensorrt_llm::runtime::ipcmemory (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryE", false]], "tensorrt_llm::runtime::ipcmemory::allocateipcmemory (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfig", false]], "tensorrt_llm::runtime::ipcmemory::bufferptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9BufferPtrE", false]], "tensorrt_llm::runtime::ipcmemory::destroyipcmemory (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory16destroyIpcMemoryEv", false]], "tensorrt_llm::runtime::ipcmemory::flags_size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory10FLAGS_SIZEE", false]], "tensorrt_llm::runtime::ipcmemory::getcommptrs (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9IpcMemory11getCommPtrsEv", false]], "tensorrt_llm::runtime::ipcmemory::ipcmemory (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb", false], [1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryERK9IpcMemory", false], [1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryERR9IpcMemory", false]], "tensorrt_llm::runtime::ipcmemory::mbuffer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory7mBufferE", false]], "tensorrt_llm::runtime::ipcmemory::mcommptrs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9mCommPtrsE", false]], "tensorrt_llm::runtime::ipcmemory::mopenipc (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory8mOpenIpcE", false]], "tensorrt_llm::runtime::ipcmemory::mtprank (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory7mTpRankE", false]], "tensorrt_llm::runtime::ipcmemory::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryaSERK9IpcMemory", false], [1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryaSERR9IpcMemory", false]], "tensorrt_llm::runtime::ipcmemory::~ipcmemory (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryD0Ev", false]], "tensorrt_llm::runtime::ipcnvlsallocate (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime15ipcNvlsAllocateE6size_tNSt3setIiEE", false]], "tensorrt_llm::runtime::ipcnvlsfree (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ipcNvlsFreeEP13IpcNvlsHandle", false]], "tensorrt_llm::runtime::ipcnvlshandle (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandleE", false]], "tensorrt_llm::runtime::ipcnvlshandle::ipc_uc_handles (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle14ipc_uc_handlesE", false]], "tensorrt_llm::runtime::ipcnvlshandle::ipc_uc_ptrs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle11ipc_uc_ptrsE", false]], "tensorrt_llm::runtime::ipcnvlshandle::ipc_uc_vas (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle10ipc_uc_vasE", false]], "tensorrt_llm::runtime::ipcnvlshandle::mc_handle (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle9mc_handleE", false]], "tensorrt_llm::runtime::ipcnvlshandle::mc_ptr (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle6mc_ptrE", false]], "tensorrt_llm::runtime::ipcnvlshandle::mc_va (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle5mc_vaE", false]], "tensorrt_llm::runtime::ipcnvlshandle::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle4sizeE", false]], "tensorrt_llm::runtime::ipcnvlshandle::uc_handle (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle9uc_handleE", false]], "tensorrt_llm::runtime::ipcnvlshandle::uc_ptr (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle6uc_ptrE", false]], "tensorrt_llm::runtime::ipcnvlshandle::uc_va (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle5uc_vaE", false]], "tensorrt_llm::runtime::ipcnvlssupported (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime16ipcNvlsSupportedEv", false]], "tensorrt_llm::runtime::itensor (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensorE", false]], "tensorrt_llm::runtime::itensor::at (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atE14UniqueConstPtrRR9TConstPtrRK5Shape", false], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atEN7ITensor14UniqueConstPtrERR9TConstPtrRKNSt16initializer_listI9DimType64EE", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRK5Shape", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRKNSt16initializer_listI9DimType64EE", false]], "tensorrt_llm::runtime::itensor::castsize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor8castSizeE6size_t", false]], "tensorrt_llm::runtime::itensor::dimtype64 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9DimType64E", false]], "tensorrt_llm::runtime::itensor::flattenn (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor8flattenNE9SharedPtrNSt7int64_tE", false]], "tensorrt_llm::runtime::itensor::getdimension (c++ function)": [[1, "_CPPv4I_10SizeType32ENK12tensorrt_llm7runtime7ITensor12getDimensionE9DimType64v", false]], "tensorrt_llm::runtime::itensor::getshape (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7ITensor8getShapeEv", false]], "tensorrt_llm::runtime::itensor::itensor (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorERK7ITensor", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorEv", false]], "tensorrt_llm::runtime::itensor::makeshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9makeShapeERKNSt16initializer_listI9DimType64EE", false]], "tensorrt_llm::runtime::itensor::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensoraSERK7ITensor", false]], "tensorrt_llm::runtime::itensor::reshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor7reshapeERK5Shape", false]], "tensorrt_llm::runtime::itensor::resize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor6resizeENSt6size_tE", false]], "tensorrt_llm::runtime::itensor::shape (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE", false]], "tensorrt_llm::runtime::itensor::shapeequals (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T10SizeType32", false], [1, "_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T10SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapeRK5Shape", false], [1, "_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERK5Shape", false], [1, "_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERKNSt16initializer_listI10SizeType32EE", false]], "tensorrt_llm::runtime::itensor::sharedconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor14SharedConstPtrE", false]], "tensorrt_llm::runtime::itensor::sharedptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE", false]], "tensorrt_llm::runtime::itensor::slice (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", false], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", false], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5Shape", false], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5ShapeNSt6size_tE", false], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EE", false], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EENSt6size_tE", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tE", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape9DimType64", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE9DimType64", false]], "tensorrt_llm::runtime::itensor::squeeze (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeE10SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeERK5Shape10SizeType32", false]], "tensorrt_llm::runtime::itensor::strides (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor7stridesERK5Shape", false]], "tensorrt_llm::runtime::itensor::tensormap (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9TensorMapE", false]], "tensorrt_llm::runtime::itensor::tostring (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor8toStringERK5Shape", false]], "tensorrt_llm::runtime::itensor::uniqueconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor14UniqueConstPtrE", false]], "tensorrt_llm::runtime::itensor::uniqueptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE", false]], "tensorrt_llm::runtime::itensor::unsqueeze (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeE10SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeERK5Shape10SizeType32", false]], "tensorrt_llm::runtime::itensor::view (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewE9SharedPtr", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewEN7IBuffer9SharedPtrERK5Shape", false]], "tensorrt_llm::runtime::itensor::volume (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor6volumeERK5Shape", false]], "tensorrt_llm::runtime::itensor::volumenonnegative (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor17volumeNonNegativeERK5Shape", false]], "tensorrt_llm::runtime::itensor::wrap (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE", false]], "tensorrt_llm::runtime::itensor::~itensor (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensorD0Ev", false]], "tensorrt_llm::runtime::lamportinitializeall (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20lamportInitializeAllEPvPvPv6size_t", false]], "tensorrt_llm::runtime::lookaheaddecodingbuffers (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffersE", false]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::generationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers17generationLengthsE", false]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::lookaheaddecodingbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers24LookaheadDecodingBuffersE10SizeType3210SizeType32RK13BufferManager", false]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::packedmasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers11packedMasksE", false]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::positionids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers11positionIdsE", false]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::positionoffsets (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers15positionOffsetsE", false]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers9TensorPtrE", false]], "tensorrt_llm::runtime::lookaheadmodule (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModuleE", false]], "tensorrt_llm::runtime::lookaheadmodule::getexecutionconfig (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime15LookaheadModule18getExecutionConfigEv", false]], "tensorrt_llm::runtime::lookaheadmodule::lookaheadmodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleE10SizeType3210SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleEv", false]], "tensorrt_llm::runtime::lookaheadmodule::mexecutionconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule16mExecutionConfigE", false]], "tensorrt_llm::runtime::lookaheadmodule::setexecutionconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule18setExecutionConfigERKN8executor23LookaheadDecodingConfigE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffersE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::batchslotshostcopy (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers18batchSlotsHostCopyE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::cumsumlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers12cumSumLengthE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::disablelookaheaddecoding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers24disableLookaheadDecodingEv", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::enablelookaheaddecoding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23enableLookaheadDecodingE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::generationlengthsdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23generationLengthsDeviceE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::generationlengthshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers21generationLengthsHostE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::generationlengthshostcopy (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers25generationLengthsHostCopyE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::insertinputtensors (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers18insertInputTensorsER9TensorMapR9TensorMapRK11WorldConfig", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::lookaheadruntimebuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::packedmaskhost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers14packedMaskHostE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::packedmaskhostcopy (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers18packedMaskHostCopyE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::packedmasksdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers17packedMasksDeviceE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionidsdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers17positionIdsDeviceE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionidshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers15positionIdsHostE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionidshostcopy (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers19positionIdsHostCopyE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionoffsetsdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers21positionOffsetsDeviceE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionoffsetshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers19positionOffsetsHostE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionoffsetshostcopy (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23positionOffsetsHostCopyE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::reshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers7reshapeE10SizeType3210SizeType3210SizeType32", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::setfrominputs (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::tensormap (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers9TensorMapE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers9TensorPtrE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::usespecdecoding (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers15useSpecDecodingE", false]], "tensorrt_llm::runtime::loracache (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCacheE", false]], "tensorrt_llm::runtime::loracache::bump (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache4bumpE10TaskIdType", false]], "tensorrt_llm::runtime::loracache::bumptaskinprogress (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache18bumpTaskInProgressE10TaskIdType", false]], "tensorrt_llm::runtime::loracache::claimpageswithevict (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache19claimPagesWithEvictE10SizeType32", false]], "tensorrt_llm::runtime::loracache::copytask (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache8copyTaskE10TaskIdTypeR9LoraCacheb", false]], "tensorrt_llm::runtime::loracache::copytaskmappages (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache", false]], "tensorrt_llm::runtime::loracache::copytopages (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", false]], "tensorrt_llm::runtime::loracache::determinenumpages (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE10TaskIdType", false], [1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE9TensorPtr", false]], "tensorrt_llm::runtime::loracache::fits (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache4fitsE9TensorPtr", false]], "tensorrt_llm::runtime::loracache::get (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3getE10TaskIdType", false]], "tensorrt_llm::runtime::loracache::getnumpages (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache11getNumPagesEv", false]], "tensorrt_llm::runtime::loracache::getpageptr (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache10getPagePtrE6size_t", false]], "tensorrt_llm::runtime::loracache::getstatus (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache9getStatusE10TaskIdType", false]], "tensorrt_llm::runtime::loracache::has (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache3hasE10TaskIdType", false]], "tensorrt_llm::runtime::loracache::isdone (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache6isDoneE10TaskIdType", false]], "tensorrt_llm::runtime::loracache::isloaded (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache8isLoadedE10TaskIdType", false]], "tensorrt_llm::runtime::loracache::loadweights (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsE10TaskIdType9TensorPtr9TensorPtr", false], [1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsER9TaskValue9TensorPtr9TensorPtr", false]], "tensorrt_llm::runtime::loracache::loracache (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager", false]], "tensorrt_llm::runtime::loracache::markalldone (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11markAllDoneEv", false]], "tensorrt_llm::runtime::loracache::marktaskdone (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12markTaskDoneE10TaskIdType", false]], "tensorrt_llm::runtime::loracache::mbuffermanager (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache14mBufferManagerE", false]], "tensorrt_llm::runtime::loracache::mcachemap (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9mCacheMapE", false]], "tensorrt_llm::runtime::loracache::mcachemutex (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11mCacheMutexE", false]], "tensorrt_llm::runtime::loracache::mcachepagemanager (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17mCachePageManagerE", false]], "tensorrt_llm::runtime::loracache::mdevicebuffermanagers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21mDeviceBufferManagersE", false]], "tensorrt_llm::runtime::loracache::mdonetasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache10mDoneTasksE", false]], "tensorrt_llm::runtime::loracache::minprogresstasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16mInProgressTasksE", false]], "tensorrt_llm::runtime::loracache::mmodelconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12mModelConfigE", false]], "tensorrt_llm::runtime::loracache::mmoduleidtomodule (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17mModuleIdToModuleE", false]], "tensorrt_llm::runtime::loracache::mpagemanagerconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache18mPageManagerConfigE", false]], "tensorrt_llm::runtime::loracache::mpagesmutex (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11mPagesMutexE", false]], "tensorrt_llm::runtime::loracache::mworldconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12mWorldConfigE", false]], "tensorrt_llm::runtime::loracache::put (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb", false]], "tensorrt_llm::runtime::loracache::splittransposecpu (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loracache::splittransposecpuinner (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loracache::taskidtype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache10TaskIdTypeE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfigE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::adaptersize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig11adapterSizeE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::insize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig6inSizeE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::layerid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7layerIdE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::moduleid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8moduleIdE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::numslots (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8numSlotsE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::operator== (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfigeqERKN9LoraCache21TaskLayerModuleConfigE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::outsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7outSizeE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::pageid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig6pageIdE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::scalingvecpointer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig17scalingVecPointerE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::slotidx (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7slotIdxE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::tostring (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8toStringEv", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::weightsinpointer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig16weightsInPointerE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::weightsoutpointer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig17weightsOutPointerE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfiglistptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache28TaskLayerModuleConfigListPtrE", false]], "tensorrt_llm::runtime::loracache::taskvalue (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueE", false]], "tensorrt_llm::runtime::loracache::taskvalue::configs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue7configsE", false]], "tensorrt_llm::runtime::loracache::taskvalue::done (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue4doneE", false]], "tensorrt_llm::runtime::loracache::taskvalue::inprogress (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue10inProgressE", false]], "tensorrt_llm::runtime::loracache::taskvalue::it (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue2itE", false]], "tensorrt_llm::runtime::loracache::taskvalue::loaded (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue6loadedE", false]], "tensorrt_llm::runtime::loracache::taskvalue::loadinprogress (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue14loadInProgressE", false]], "tensorrt_llm::runtime::loracache::taskvalue::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueaSERR9TaskValue", false]], "tensorrt_llm::runtime::loracache::taskvalue::pageids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue7pageIdsE", false]], "tensorrt_llm::runtime::loracache::taskvalue::taskvalue (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", false], [1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERR9TaskValue", false], [1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueEv", false]], "tensorrt_llm::runtime::loracache::taskvalue::~taskvalue (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueD0Ev", false]], "tensorrt_llm::runtime::loracache::taskvalueptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12TaskValuePtrE", false]], "tensorrt_llm::runtime::loracache::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TensorPtrE", false]], "tensorrt_llm::runtime::loracache::valuestatus (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatusE", false]], "tensorrt_llm::runtime::loracache::valuestatus::kvalue_status_loaded (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus20kVALUE_STATUS_LOADEDE", false]], "tensorrt_llm::runtime::loracache::valuestatus::kvalue_status_missing (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus21kVALUE_STATUS_MISSINGE", false]], "tensorrt_llm::runtime::loracache::valuestatus::kvalue_status_processing (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus24kVALUE_STATUS_PROCESSINGE", false]], "tensorrt_llm::runtime::loracachefullexception (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullExceptionE", false]], "tensorrt_llm::runtime::loracachefullexception::loracachefullexception (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullException22LoraCacheFullExceptionERKNSt6stringE", false]], "tensorrt_llm::runtime::loracachefullexception::~loracachefullexception (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullExceptionD0Ev", false]], "tensorrt_llm::runtime::loracachepagemanager (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManagerE", false]], "tensorrt_llm::runtime::loracachepagemanager::blockptr (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager8blockPtrE10SizeType32", false]], "tensorrt_llm::runtime::loracachepagemanager::claimpages (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10claimPagesE10SizeType32", false]], "tensorrt_llm::runtime::loracachepagemanager::initialize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10initializeERK13BufferManager", false]], "tensorrt_llm::runtime::loracachepagemanager::loracachepagemanager (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager20LoraCachePageManagerERK26LoraCachePageManagerConfigRK13BufferManager", false]], "tensorrt_llm::runtime::loracachepagemanager::mconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager7mConfigE", false]], "tensorrt_llm::runtime::loracachepagemanager::mfreepageids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager12mFreePageIdsE", false]], "tensorrt_llm::runtime::loracachepagemanager::mispagefree (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager11mIsPageFreeE", false]], "tensorrt_llm::runtime::loracachepagemanager::mpageblocks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager11mPageBlocksE", false]], "tensorrt_llm::runtime::loracachepagemanager::mutablepageptr (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager14mutablePagePtrENSt6size_tE", false]], "tensorrt_llm::runtime::loracachepagemanager::numavailablepages (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager17numAvailablePagesEv", false]], "tensorrt_llm::runtime::loracachepagemanager::pageptr (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager7pagePtrENSt6size_tE", false]], "tensorrt_llm::runtime::loracachepagemanager::releasepages (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager12releasePagesERKNSt6vectorINSt6size_tEEE", false]], "tensorrt_llm::runtime::loracachepagemanager::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager9TensorPtrE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfigE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getdatatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig11getDataTypeEv", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getinittozero (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig13getInitToZeroEv", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getmaxpagesperblock (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig19getMaxPagesPerBlockEv", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getmemorytype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig13getMemoryTypeEv", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getnumcopystreams (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig17getNumCopyStreamsEv", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getpagewidth (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig12getPageWidthEv", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getslotsperpage (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig15getSlotsPerPageEv", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::gettotalnumpages (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig16getTotalNumPagesEv", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::loracachepagemanagerconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mdatatype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig9mDataTypeE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::minittozero (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11mInitToZeroE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mmaxpagesperblock (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig17mMaxPagesPerBlockE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mmemorytype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11mMemoryTypeE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mnumcopystreams (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15mNumCopyStreamsE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mpagewidth (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig10mPageWidthE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mslotsperpage (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13mSlotsPerPageE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mtotalnumpages (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig14mTotalNumPagesE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setdatatype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11setDataTypeERKN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setinittozero (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setInitToZeroEb", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setmaxpagesperblock (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig19setMaxPagesPerBlockERK10SizeType32", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setmemorytype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setMemoryTypeERKN7runtime10MemoryTypeE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setnumcopystreams (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig17setNumCopyStreamsE10SizeType32", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setpagewidth (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig12setPageWidthERK10SizeType32", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setslotsperpage (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setSlotsPerPageERK10SizeType32", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::settotalnumpage (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setTotalNumPageERK10SizeType32", false]], "tensorrt_llm::runtime::loraexpectedexception (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedExceptionE", false]], "tensorrt_llm::runtime::loraexpectedexception::loraexpectedexception (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedException21LoraExpectedExceptionERKNSt6stringE", false]], "tensorrt_llm::runtime::loraexpectedexception::~loraexpectedexception (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedExceptionD0Ev", false]], "tensorrt_llm::runtime::loramodule (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModuleE", false]], "tensorrt_llm::runtime::loramodule::createloramodules (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loramodule::flattenedinoutsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18flattenedInOutSizeE10SizeType32b", false]], "tensorrt_llm::runtime::loramodule::indim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule5inDimEv", false]], "tensorrt_llm::runtime::loramodule::indimfirst (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule10inDimFirstEv", false]], "tensorrt_llm::runtime::loramodule::insize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule6inSizeE10SizeType32", false]], "tensorrt_llm::runtime::loramodule::intpsplitdim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12inTpSplitDimEv", false]], "tensorrt_llm::runtime::loramodule::localinadaptersize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18localInAdapterSizeE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loramodule::localindim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule10localInDimE10SizeType32", false]], "tensorrt_llm::runtime::loramodule::localinoutsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localInOutSizeE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loramodule::localinsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localInSizeE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loramodule::localoutadaptersize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule19localOutAdapterSizeE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loramodule::localoutdim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localOutDimE10SizeType32", false]], "tensorrt_llm::runtime::loramodule::localoutsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12localOutSizeE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loramodule::localscalessize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule15localScalesSizeE10SizeType32b", false]], "tensorrt_llm::runtime::loramodule::localtotalsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localTotalSizeE10SizeType3210SizeType32b", false]], "tensorrt_llm::runtime::loramodule::loramodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10LoraModule", false], [1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleEv", false]], "tensorrt_llm::runtime::loramodule::mindim (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule6mInDimE", false]], "tensorrt_llm::runtime::loramodule::mindimfirst (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule11mInDimFirstE", false]], "tensorrt_llm::runtime::loramodule::mintpsplitdim (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule13mInTpSplitDimE", false]], "tensorrt_llm::runtime::loramodule::moduletype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleTypeE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kattn_dense (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kATTN_DENSEE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kattn_k (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_KE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kattn_q (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_QE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kattn_qkv (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kATTN_QKVE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kattn_v (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_VE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kcross_attn_dense (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType17kCROSS_ATTN_DENSEE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kcross_attn_k (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_KE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kcross_attn_q (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_QE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kcross_attn_qkv (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType15kCROSS_ATTN_QKVE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kcross_attn_v (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_VE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kinvalid (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType8kINVALIDE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmlp_4h_to_h (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMLP_4H_TO_HE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmlp_gate (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kMLP_GATEE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmlp_gate_up (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMLP_GATE_UPE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmlp_h_to_4h (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMLP_H_TO_4HE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmlp_router (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kMLP_ROUTERE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmoe_4h_to_h (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMOE_4H_TO_HE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmoe_gate (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kMOE_GATEE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmoe_h_to_4h (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMOE_H_TO_4HE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmoe_router (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kMOE_ROUTERE", false]], "tensorrt_llm::runtime::loramodule::moutdim (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule7mOutDimE", false]], "tensorrt_llm::runtime::loramodule::moutdimfirst (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12mOutDimFirstE", false]], "tensorrt_llm::runtime::loramodule::mouttpsplitdim (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule14mOutTpSplitDimE", false]], "tensorrt_llm::runtime::loramodule::mtype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule5mTypeE", false]], "tensorrt_llm::runtime::loramodule::name (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule4nameEv", false]], "tensorrt_llm::runtime::loramodule::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModuleaSERK10LoraModule", false]], "tensorrt_llm::runtime::loramodule::outdim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule6outDimEv", false]], "tensorrt_llm::runtime::loramodule::outdimfirst (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11outDimFirstEv", false]], "tensorrt_llm::runtime::loramodule::outsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule7outSizeE10SizeType32", false]], "tensorrt_llm::runtime::loramodule::outtpsplitdim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule13outTpSplitDimEv", false]], "tensorrt_llm::runtime::loramodule::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule9TensorPtrE", false]], "tensorrt_llm::runtime::loramodule::tomodulename (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10ModuleType", false], [1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10SizeType32", false]], "tensorrt_llm::runtime::loramodule::tomoduletype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleTypeERKNSt11string_viewE", false]], "tensorrt_llm::runtime::loramodule::value (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule5valueEv", false]], "tensorrt_llm::runtime::lorataskidtype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14LoraTaskIdTypeE", false]], "tensorrt_llm::runtime::medusamodule (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModuleE", false]], "tensorrt_llm::runtime::medusamodule::getmedusachoices (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule16getMedusaChoicesEv", false]], "tensorrt_llm::runtime::medusamodule::mdefaultmedusachoices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule21mDefaultMedusaChoicesE", false]], "tensorrt_llm::runtime::medusamodule::medusachoices (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule13MedusaChoicesE", false]], "tensorrt_llm::runtime::medusamodule::medusamodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleE10SizeType3210SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleEv", false]], "tensorrt_llm::runtime::medusamodule::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule9TensorPtrE", false]], "tensorrt_llm::runtime::memorycounters (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCountersE", false]], "tensorrt_llm::runtime::memorycounters::allocate (c++ function)": [[1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters8allocateEv10SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8allocateE10MemoryType10SizeType32", false]], "tensorrt_llm::runtime::memorycounters::bytestostring (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE10SizeType32i", false], [1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8DiffTypei", false]], "tensorrt_llm::runtime::memorycounters::deallocate (c++ function)": [[1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters10deallocateEv10SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10deallocateE10MemoryType10SizeType32", false]], "tensorrt_llm::runtime::memorycounters::difftype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE", false]], "tensorrt_llm::runtime::memorycounters::getcpu (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getCpuEv", false]], "tensorrt_llm::runtime::memorycounters::getcpudiff (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getCpuDiffEv", false]], "tensorrt_llm::runtime::memorycounters::getgpu (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getGpuEv", false]], "tensorrt_llm::runtime::memorycounters::getgpudiff (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getGpuDiffEv", false]], "tensorrt_llm::runtime::memorycounters::getinstance (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11getInstanceEv", false]], "tensorrt_llm::runtime::memorycounters::getpinned (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters9getPinnedEv", false]], "tensorrt_llm::runtime::memorycounters::getpinneddiff (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters13getPinnedDiffEv", false]], "tensorrt_llm::runtime::memorycounters::getpinnedpool (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters13getPinnedPoolEv", false]], "tensorrt_llm::runtime::memorycounters::getpinnedpooldiff (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters17getPinnedPoolDiffEv", false]], "tensorrt_llm::runtime::memorycounters::getuvm (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getUVMEv", false]], "tensorrt_llm::runtime::memorycounters::getuvmdiff (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getUVMDiffEv", false]], "tensorrt_llm::runtime::memorycounters::mcpu (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mCpuE", false]], "tensorrt_llm::runtime::memorycounters::mcpudiff (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mCpuDiffE", false]], "tensorrt_llm::runtime::memorycounters::memorycounters (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters14MemoryCountersEv", false]], "tensorrt_llm::runtime::memorycounters::mgpu (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mGpuE", false]], "tensorrt_llm::runtime::memorycounters::mgpudiff (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mGpuDiffE", false]], "tensorrt_llm::runtime::memorycounters::mpinned (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters7mPinnedE", false]], "tensorrt_llm::runtime::memorycounters::mpinneddiff (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11mPinnedDiffE", false]], "tensorrt_llm::runtime::memorycounters::mpinnedpool (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11mPinnedPoolE", false]], "tensorrt_llm::runtime::memorycounters::mpinnedpooldiff (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters15mPinnedPoolDiffE", false]], "tensorrt_llm::runtime::memorycounters::muvm (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mUVME", false]], "tensorrt_llm::runtime::memorycounters::muvmdiff (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mUVMDiffE", false]], "tensorrt_llm::runtime::memorycounters::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10SizeType32E", false]], "tensorrt_llm::runtime::memorycounters::tostring (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters8toStringEv", false]], "tensorrt_llm::runtime::memorytype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryTypeE", false]], "tensorrt_llm::runtime::memorytype::kcpu (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kCPUE", false]], "tensorrt_llm::runtime::memorytype::kgpu (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kGPUE", false]], "tensorrt_llm::runtime::memorytype::kpinned (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryType7kPINNEDE", false]], "tensorrt_llm::runtime::memorytype::kpinnedpool (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryType11kPINNEDPOOLE", false]], "tensorrt_llm::runtime::memorytype::kuvm (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kUVME", false]], "tensorrt_llm::runtime::memorytypestring (c++ struct)": [[1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime16MemoryTypeStringE", false]], "tensorrt_llm::runtime::memorytypestring (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEEE", false]], "tensorrt_llm::runtime::memorytypestring::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEE5valueE", false]], "tensorrt_llm::runtime::memorytypestring (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEEE", false]], "tensorrt_llm::runtime::memorytypestring::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEE5valueE", false]], "tensorrt_llm::runtime::memorytypestring (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEEE", false]], "tensorrt_llm::runtime::memorytypestring::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEE5valueE", false]], "tensorrt_llm::runtime::memorytypestring (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType11kPINNEDPOOLEEE", false]], "tensorrt_llm::runtime::memorytypestring::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType11kPINNEDPOOLEE5valueE", false]], "tensorrt_llm::runtime::memorytypestring (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kUVMEEE", false]], "tensorrt_llm::runtime::memorytypestring::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kUVMEE5valueE", false]], "tensorrt_llm::runtime::modelconfig (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfigE", false]], "tensorrt_llm::runtime::modelconfig::computecontextlogits (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20computeContextLogitsEb", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20computeContextLogitsEv", false]], "tensorrt_llm::runtime::modelconfig::computegenerationlogits (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23computeGenerationLogitsEb", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig23computeGenerationLogitsEv", false]], "tensorrt_llm::runtime::modelconfig::countlocallayers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16countLocalLayersE9LayerType10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::modelconfig::countlowerranklayers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20countLowerRankLayersE9LayerType10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::modelconfig::disableseamlesslookaheaddecoding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig32disableSeamlessLookaheadDecodingEv", false]], "tensorrt_llm::runtime::modelconfig::enableseamlesslookaheaddecoding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig31enableSeamlessLookaheadDecodingE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::getcontextfmha (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getContextFMHAEv", false]], "tensorrt_llm::runtime::modelconfig::getdatatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig11getDataTypeEv", false]], "tensorrt_llm::runtime::modelconfig::getencoderhiddensize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getEncoderHiddenSizeEv", false]], "tensorrt_llm::runtime::modelconfig::getfirstlocallayer (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getFirstLocalLayerE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::modelconfig::getgemmallreducedtype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21getGemmAllReduceDtypeEv", false]], "tensorrt_llm::runtime::modelconfig::gethiddensize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getHiddenSizeEv", false]], "tensorrt_llm::runtime::modelconfig::getkvcachetype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getKVCacheTypeEv", false]], "tensorrt_llm::runtime::modelconfig::getkvdatatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getKvDataTypeEv", false]], "tensorrt_llm::runtime::modelconfig::getlayertypes (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getLayerTypesEv", false]], "tensorrt_llm::runtime::modelconfig::getlogitsdtype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getLogitsDtypeEv", false]], "tensorrt_llm::runtime::modelconfig::getloramodules (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getLoraModulesEv", false]], "tensorrt_llm::runtime::modelconfig::getmanageweightstype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getManageWeightsTypeEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxbatchsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxBatchSizeEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxbeamwidth (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxBeamWidthEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxdecodingdrafttokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig25getMaxDecodingDraftTokensEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxdecodingtokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getMaxDecodingTokensEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxencoderlen (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16getMaxEncoderLenEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxinputlen (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getMaxInputLenEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxlorarank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getMaxLoraRankEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxnumtokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxNumTokensEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxpositionembeddings (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig24getMaxPositionEmbeddingsEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxpromptembeddingtablesize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig30getMaxPromptEmbeddingTableSizeEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxsequencelen (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17getMaxSequenceLenEv", false]], "tensorrt_llm::runtime::modelconfig::getmlphiddensize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16getMlpHiddenSizeEv", false]], "tensorrt_llm::runtime::modelconfig::getmodelname (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getModelNameEv", false]], "tensorrt_llm::runtime::modelconfig::getmodelvariant (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getModelVariantEv", false]], "tensorrt_llm::runtime::modelconfig::getnbattentionlayers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getNbAttentionLayersE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::modelconfig::getnbheads (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig10getNbHeadsEv", false]], "tensorrt_llm::runtime::modelconfig::getnbkvheads (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getNbKvHeadsE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::getnblayers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig11getNbLayersE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::modelconfig::getnbrnnlayers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getNbRnnLayersE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::modelconfig::getnumkvheadsforgivenlayers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig27getNumKvHeadsForGivenLayersERKNSt6vectorI10SizeType32EEb", false]], "tensorrt_llm::runtime::modelconfig::getnumkvheadsperlayer (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21getNumKvHeadsPerLayerEv", false]], "tensorrt_llm::runtime::modelconfig::getnumkvheadsperlayerlocalrange (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig31getNumKvHeadsPerLayerLocalRangeE10SizeType3210SizeType32b", false]], "tensorrt_llm::runtime::modelconfig::getnumlanguages (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getNumLanguagesEv", false]], "tensorrt_llm::runtime::modelconfig::getoptprofilessplitpoints (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig25getOptProfilesSplitPointsEv", false]], "tensorrt_llm::runtime::modelconfig::getpagedcontextfmha (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig19getPagedContextFMHAEv", false]], "tensorrt_llm::runtime::modelconfig::getppreducescatter (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getPpReduceScatterEv", false]], "tensorrt_llm::runtime::modelconfig::getquantmode (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getQuantModeEv", false]], "tensorrt_llm::runtime::modelconfig::getrnnconfig (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getRnnConfigEv", false]], "tensorrt_llm::runtime::modelconfig::getrotaryembeddingdim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21getRotaryEmbeddingDimEv", false]], "tensorrt_llm::runtime::modelconfig::getsizeperhead (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getSizePerHeadEv", false]], "tensorrt_llm::runtime::modelconfig::getspeculativedecodingmode (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig26getSpeculativeDecodingModeEv", false]], "tensorrt_llm::runtime::modelconfig::getspeculativedecodingmodule (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig28getSpeculativeDecodingModuleEv", false]], "tensorrt_llm::runtime::modelconfig::getspeculativedecodingmoduleptr (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig31getSpeculativeDecodingModulePtrEv", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig31getSpeculativeDecodingModulePtrEv", false]], "tensorrt_llm::runtime::modelconfig::gettokensperblock (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17getTokensPerBlockEv", false]], "tensorrt_llm::runtime::modelconfig::getvocabsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getVocabSizeEv", false]], "tensorrt_llm::runtime::modelconfig::getvocabsizepadded (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getVocabSizePaddedE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::hasrnnconfig (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12hasRnnConfigEv", false]], "tensorrt_llm::runtime::modelconfig::hasspeculativedecodingmodule (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig28hasSpeculativeDecodingModuleEv", false]], "tensorrt_llm::runtime::modelconfig::iscontinuouskvcache (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig19isContinuousKVCacheEv", false]], "tensorrt_llm::runtime::modelconfig::iskvcacheenabled (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16isKVCacheEnabledEv", false]], "tensorrt_llm::runtime::modelconfig::ismultimodal (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12isMultiModalEv", false]], "tensorrt_llm::runtime::modelconfig::ispagedkvcache (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14isPagedKVCacheEv", false]], "tensorrt_llm::runtime::modelconfig::isrnnbased (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig10isRnnBasedEv", false]], "tensorrt_llm::runtime::modelconfig::istransformerbased (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18isTransformerBasedEv", false]], "tensorrt_llm::runtime::modelconfig::iswhisper (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig9isWhisperEv", false]], "tensorrt_llm::runtime::modelconfig::kdefault_num_tokens_per_block (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig29kDEFAULT_NUM_TOKENS_PER_BLOCKE", false]], "tensorrt_llm::runtime::modelconfig::kopt_profiles_split_points (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26kOPT_PROFILES_SPLIT_POINTSE", false]], "tensorrt_llm::runtime::modelconfig::kvcachetype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheTypeE", false]], "tensorrt_llm::runtime::modelconfig::kvcachetype::kcontinuous (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType11kCONTINUOUSE", false]], "tensorrt_llm::runtime::modelconfig::kvcachetype::kdisabled (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType9kDISABLEDE", false]], "tensorrt_llm::runtime::modelconfig::kvcachetype::kpaged (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType6kPAGEDE", false]], "tensorrt_llm::runtime::modelconfig::kvcachetypefromstring (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21KVCacheTypeFromStringENSt6stringE", false]], "tensorrt_llm::runtime::modelconfig::layertype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerTypeE", false]], "tensorrt_llm::runtime::modelconfig::layertype::kattention (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType10kATTENTIONE", false]], "tensorrt_llm::runtime::modelconfig::layertype::klinear (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType7kLINEARE", false]], "tensorrt_llm::runtime::modelconfig::layertype::knoop (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType5kNOOPE", false]], "tensorrt_llm::runtime::modelconfig::layertype::krecurrent (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType10kRECURRENTE", false]], "tensorrt_llm::runtime::modelconfig::manageweightstype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsTypeE", false]], "tensorrt_llm::runtime::modelconfig::manageweightstype::kdisabled (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsType9kDisabledE", false]], "tensorrt_llm::runtime::modelconfig::manageweightstype::kenabled (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsType8kEnabledE", false]], "tensorrt_llm::runtime::modelconfig::mcomputecontextlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mComputeContextLogitsE", false]], "tensorrt_llm::runtime::modelconfig::mcomputegenerationlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24mComputeGenerationLogitsE", false]], "tensorrt_llm::runtime::modelconfig::mcontextfmha (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mContextFMHAE", false]], "tensorrt_llm::runtime::modelconfig::mdatatype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9mDataTypeE", false]], "tensorrt_llm::runtime::modelconfig::mencoderhiddensize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mEncoderHiddenSizeE", false]], "tensorrt_llm::runtime::modelconfig::mgemmallreducedtype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig19mGemmAllReduceDtypeE", false]], "tensorrt_llm::runtime::modelconfig::mhiddensize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mHiddenSizeE", false]], "tensorrt_llm::runtime::modelconfig::minputpacked (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mInputPackedE", false]], "tensorrt_llm::runtime::modelconfig::mkvcachetype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mKVCacheTypeE", false]], "tensorrt_llm::runtime::modelconfig::mlayertypes (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mLayerTypesE", false]], "tensorrt_llm::runtime::modelconfig::mlogitsdtype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mLogitsDtypeE", false]], "tensorrt_llm::runtime::modelconfig::mloramodules (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mLoraModulesE", false]], "tensorrt_llm::runtime::modelconfig::mmanageweightstype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mManageWeightsTypeE", false]], "tensorrt_llm::runtime::modelconfig::mmaxbatchsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxBatchSizeE", false]], "tensorrt_llm::runtime::modelconfig::mmaxbeamwidth (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxBeamWidthE", false]], "tensorrt_llm::runtime::modelconfig::mmaxencoderlen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mMaxEncoderLenE", false]], "tensorrt_llm::runtime::modelconfig::mmaxinputlen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mMaxInputLenE", false]], "tensorrt_llm::runtime::modelconfig::mmaxlorarank (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mMaxLoraRankE", false]], "tensorrt_llm::runtime::modelconfig::mmaxnumtokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxNumTokensE", false]], "tensorrt_llm::runtime::modelconfig::mmaxpositionembeddings (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22mMaxPositionEmbeddingsE", false]], "tensorrt_llm::runtime::modelconfig::mmaxpromptembeddingtablesize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28mMaxPromptEmbeddingTableSizeE", false]], "tensorrt_llm::runtime::modelconfig::mmaxsequencelen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15mMaxSequenceLenE", false]], "tensorrt_llm::runtime::modelconfig::mmlphiddensize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mMlpHiddenSizeE", false]], "tensorrt_llm::runtime::modelconfig::mmodelname (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mModelNameE", false]], "tensorrt_llm::runtime::modelconfig::mmodelvariant (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mModelVariantE", false]], "tensorrt_llm::runtime::modelconfig::mnbattentionlayers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mNbAttentionLayersE", false]], "tensorrt_llm::runtime::modelconfig::mnbheads (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig8mNbHeadsE", false]], "tensorrt_llm::runtime::modelconfig::mnblayers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9mNbLayersE", false]], "tensorrt_llm::runtime::modelconfig::mnbrnnlayers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mNbRnnLayersE", false]], "tensorrt_llm::runtime::modelconfig::mnumkvheadsperattentionlayer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28mNumKvHeadsPerAttentionLayerE", false]], "tensorrt_llm::runtime::modelconfig::mnumkvheadspercrossattentionlayer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig33mNumKvHeadsPerCrossAttentionLayerE", false]], "tensorrt_llm::runtime::modelconfig::mnumlanguages (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mNumLanguagesE", false]], "tensorrt_llm::runtime::modelconfig::modelconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::modelconfig::modelvariant (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariantE", false]], "tensorrt_llm::runtime::modelconfig::modelvariant::kchatglm (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant8kChatGlmE", false]], "tensorrt_llm::runtime::modelconfig::modelvariant::kencdec (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant7kEncDecE", false]], "tensorrt_llm::runtime::modelconfig::modelvariant::kglm (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant4kGlmE", false]], "tensorrt_llm::runtime::modelconfig::modelvariant::kgpt (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant4kGptE", false]], "tensorrt_llm::runtime::modelconfig::modelvariant::kmamba (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant6kMambaE", false]], "tensorrt_llm::runtime::modelconfig::modelvariant::krecurrentgemma (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant15kRecurrentGemmaE", false]], "tensorrt_llm::runtime::modelconfig::mpagedcontextfmha (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17mPagedContextFMHAE", false]], "tensorrt_llm::runtime::modelconfig::mpagedstate (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mPagedStateE", false]], "tensorrt_llm::runtime::modelconfig::mppreducescatter (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16mPpReduceScatterE", false]], "tensorrt_llm::runtime::modelconfig::mquantmode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mQuantModeE", false]], "tensorrt_llm::runtime::modelconfig::mrnnconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mRnnConfigE", false]], "tensorrt_llm::runtime::modelconfig::mrotaryembeddingdim (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig19mRotaryEmbeddingDimE", false]], "tensorrt_llm::runtime::modelconfig::msizeperhead (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mSizePerHeadE", false]], "tensorrt_llm::runtime::modelconfig::mskipcrossattnblocks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20mSkipCrossAttnBlocksE", false]], "tensorrt_llm::runtime::modelconfig::mspeculativedecodingmode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24mSpeculativeDecodingModeE", false]], "tensorrt_llm::runtime::modelconfig::mspeculativedecodingmodule (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26mSpeculativeDecodingModuleE", false]], "tensorrt_llm::runtime::modelconfig::mtokensperblock (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15mTokensPerBlockE", false]], "tensorrt_llm::runtime::modelconfig::musecrossattention (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mUseCrossAttentionE", false]], "tensorrt_llm::runtime::modelconfig::musegemmallreduceplugin (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23mUseGemmAllReducePluginE", false]], "tensorrt_llm::runtime::modelconfig::musegptattentionplugin (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22mUseGptAttentionPluginE", false]], "tensorrt_llm::runtime::modelconfig::museloraplugin (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mUseLoraPluginE", false]], "tensorrt_llm::runtime::modelconfig::musemambaconv1dplugin (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mUseMambaConv1dPluginE", false]], "tensorrt_llm::runtime::modelconfig::musemrope (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9mUseMropeE", false]], "tensorrt_llm::runtime::modelconfig::musepositionembedding (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mUsePositionEmbeddingE", false]], "tensorrt_llm::runtime::modelconfig::museshapeinference (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mUseShapeInferenceE", false]], "tensorrt_llm::runtime::modelconfig::musetokentypeembedding (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22mUseTokenTypeEmbeddingE", false]], "tensorrt_llm::runtime::modelconfig::mvocabsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mVocabSizeE", false]], "tensorrt_llm::runtime::modelconfig::resetspeculativedecodingmodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig30resetSpeculativeDecodingModuleEv", false]], "tensorrt_llm::runtime::modelconfig::rnnconfig (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfigE", false]], "tensorrt_llm::runtime::modelconfig::rnnconfig::convkernel (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig10convKernelE", false]], "tensorrt_llm::runtime::modelconfig::rnnconfig::rnnconvdimsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig14rnnConvDimSizeE", false]], "tensorrt_llm::runtime::modelconfig::rnnconfig::rnnheadsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig11rnnHeadSizeE", false]], "tensorrt_llm::runtime::modelconfig::rnnconfig::rnnhiddensize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig13rnnHiddenSizeE", false]], "tensorrt_llm::runtime::modelconfig::rnnconfig::statesize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig9stateSizeE", false]], "tensorrt_llm::runtime::modelconfig::setcontextfmha (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setContextFMHAEb", false]], "tensorrt_llm::runtime::modelconfig::setencoderhiddensize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setEncoderHiddenSizeE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setgemmallreducedtype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setGemmAllReduceDtypeEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::modelconfig::setkvcachetype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setKVCacheTypeE11KVCacheType", false]], "tensorrt_llm::runtime::modelconfig::setlayertypes (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13setLayerTypesERKNSt6vectorI9LayerTypeEE", false]], "tensorrt_llm::runtime::modelconfig::setlogitsdtype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLogitsDtypeEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::modelconfig::setloramodules (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLoraModulesERKNSt6vectorI10LoraModuleEE", false]], "tensorrt_llm::runtime::modelconfig::setmanageweightstype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setManageWeightsTypeEK17ManageWeightsType", false]], "tensorrt_llm::runtime::modelconfig::setmaxbatchsize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBatchSizeE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmaxbeamwidth (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBeamWidthE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmaxencoderlen (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMaxEncoderLenE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmaxinputlen (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxInputLenE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmaxlorarank (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxLoraRankE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmaxnumtokens (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxNumTokensENSt8optionalI10SizeType32EE", false]], "tensorrt_llm::runtime::modelconfig::setmaxpositionembeddings (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24setMaxPositionEmbeddingsE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmaxpromptembeddingtablesize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig30setMaxPromptEmbeddingTableSizeE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmaxsequencelen (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setMaxSequenceLenE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmlphiddensize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMlpHiddenSizeE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmodelname (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setModelNameERKNSt6stringE", false]], "tensorrt_llm::runtime::modelconfig::setmodelvariant (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setModelVariantE12ModelVariant", false]], "tensorrt_llm::runtime::modelconfig::setnbcrosskvheads (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setNbCrossKvHeadsE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setnbkvheads (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setNbKvHeadsE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setnumkvheadspercrosslayer (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26setNumKvHeadsPerCrossLayerERKNSt6vectorI10SizeType32EE", false]], "tensorrt_llm::runtime::modelconfig::setnumkvheadsperlayer (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setNumKvHeadsPerLayerERKNSt6vectorI10SizeType32EE", false]], "tensorrt_llm::runtime::modelconfig::setnumlanguages (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setNumLanguagesENSt8optionalI10SizeType32EE", false]], "tensorrt_llm::runtime::modelconfig::setpagedcontextfmha (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig19setPagedContextFMHAEb", false]], "tensorrt_llm::runtime::modelconfig::setppreducescatter (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18setPpReduceScatterEb", false]], "tensorrt_llm::runtime::modelconfig::setquantmode (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setQuantModeEN6common9QuantModeE", false]], "tensorrt_llm::runtime::modelconfig::setrnnconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setRnnConfigERK9RnnConfig", false]], "tensorrt_llm::runtime::modelconfig::setrotaryembeddingdim (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setRotaryEmbeddingDimE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setsizeperhead (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setSizePerHeadE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setskipcrossattnblocks (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22setSkipCrossAttnBlocksEb", false]], "tensorrt_llm::runtime::modelconfig::setspeculativedecodingmode (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26setSpeculativeDecodingModeE23SpeculativeDecodingMode", false]], "tensorrt_llm::runtime::modelconfig::setspeculativedecodingmodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28setSpeculativeDecodingModuleERKNSt10shared_ptrI25SpeculativeDecodingModuleEE", false]], "tensorrt_llm::runtime::modelconfig::settokensperblock (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setTokensPerBlockE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setusecrossattention (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseCrossAttentionEb", false]], "tensorrt_llm::runtime::modelconfig::setusemrope (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11setUseMropeEb", false]], "tensorrt_llm::runtime::modelconfig::setusepositionembedding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23setUsePositionEmbeddingEb", false]], "tensorrt_llm::runtime::modelconfig::setuseshapeinference (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseShapeInferenceEb", false]], "tensorrt_llm::runtime::modelconfig::setusetokentypeembedding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24setUseTokenTypeEmbeddingEb", false]], "tensorrt_llm::runtime::modelconfig::skipcrossattnblocks (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig19skipCrossAttnBlocksEv", false]], "tensorrt_llm::runtime::modelconfig::supportsinflightbatching (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig24supportsInflightBatchingEv", false]], "tensorrt_llm::runtime::modelconfig::usecrossattention (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17useCrossAttentionEv", false]], "tensorrt_llm::runtime::modelconfig::usegemmallreduceplugin (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22useGemmAllReducePluginEb", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig22useGemmAllReducePluginEv", false]], "tensorrt_llm::runtime::modelconfig::usegptattentionplugin (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21useGptAttentionPluginEb", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21useGptAttentionPluginEv", false]], "tensorrt_llm::runtime::modelconfig::uselanguageadapter (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18useLanguageAdapterEv", false]], "tensorrt_llm::runtime::modelconfig::useloraplugin (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13useLoraPluginEb", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13useLoraPluginEv", false]], "tensorrt_llm::runtime::modelconfig::usemambaconv1dplugin (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20useMambaConv1dPluginEb", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20useMambaConv1dPluginEv", false]], "tensorrt_llm::runtime::modelconfig::usemrope (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig8useMropeEv", false]], "tensorrt_llm::runtime::modelconfig::usepackedinput (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14usePackedInputEb", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14usePackedInputEv", false]], "tensorrt_llm::runtime::modelconfig::usepagedstate (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13usePagedStateEb", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13usePagedStateEv", false]], "tensorrt_llm::runtime::modelconfig::usepositionembedding (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20usePositionEmbeddingEv", false]], "tensorrt_llm::runtime::modelconfig::useprompttuning (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15usePromptTuningEv", false]], "tensorrt_llm::runtime::modelconfig::useshapeinference (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17useShapeInferenceEv", false]], "tensorrt_llm::runtime::modelconfig::usetokentypeembedding (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21useTokenTypeEmbeddingEv", false]], "tensorrt_llm::runtime::mpi_group_barrier (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17MPI_group_barrierENSt3setIiEE", false]], "tensorrt_llm::runtime::operator<< (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK10LoraModule", false], [1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK26LoraCachePageManagerConfig", false], [1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7IBuffer", false], [1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7ITensor", false], [1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN7ITensor5ShapeE", false], [1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN9LoraCache21TaskLayerModuleConfigE", false]], "tensorrt_llm::runtime::pointerelementtype (c++ type)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE", false]], "tensorrt_llm::runtime::prompttuningparams (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParamsE", false]], "tensorrt_llm::runtime::prompttuningparams::filltaskstensor (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", false]], "tensorrt_llm::runtime::prompttuningparams::prompttuningparams (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", false]], "tensorrt_llm::runtime::prompttuningparams::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams10SizeType32E", false]], "tensorrt_llm::runtime::prompttuningparams::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams9TensorPtrE", false]], "tensorrt_llm::runtime::rawengine (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngineE", false]], "tensorrt_llm::runtime::rawengine::getaddress (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine10getAddressEv", false]], "tensorrt_llm::runtime::rawengine::gethostmemory (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine13getHostMemoryEv", false]], "tensorrt_llm::runtime::rawengine::getmanagedweightsmapopt (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine23getManagedWeightsMapOptEv", false]], "tensorrt_llm::runtime::rawengine::getpath (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getPathEv", false]], "tensorrt_llm::runtime::rawengine::getpathopt (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine10getPathOptEv", false]], "tensorrt_llm::runtime::rawengine::getsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getSizeEv", false]], "tensorrt_llm::runtime::rawengine::gettype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getTypeEv", false]], "tensorrt_llm::runtime::rawengine::mengineaddr (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEngineAddrE", false]], "tensorrt_llm::runtime::rawengine::menginebuffer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine13mEngineBufferE", false]], "tensorrt_llm::runtime::rawengine::menginepath (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEnginePathE", false]], "tensorrt_llm::runtime::rawengine::menginesize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEngineSizeE", false]], "tensorrt_llm::runtime::rawengine::mmanagedweightsmap (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine18mManagedWeightsMapE", false]], "tensorrt_llm::runtime::rawengine::mtype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine5mTypeE", false]], "tensorrt_llm::runtime::rawengine::rawengine (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineENSt10filesystem4pathE", false], [1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKN8nvinfer111IHostMemoryE", false], [1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKvNSt6size_tE", false]], "tensorrt_llm::runtime::rawengine::setmanagedweightsmap (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine20setManagedWeightsMapENSt3mapINSt6stringEN12tensorrt_llm8executor6TensorEEE", false]], "tensorrt_llm::runtime::rawengine::setpath (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine7setPathENSt10filesystem4pathE", false]], "tensorrt_llm::runtime::rawengine::type (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4TypeE", false]], "tensorrt_llm::runtime::rawengine::type::addresswithsize (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type15AddressWithSizeE", false]], "tensorrt_llm::runtime::rawengine::type::filepath (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type8FilePathE", false]], "tensorrt_llm::runtime::rawengine::type::hostmemory (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type10HostMemoryE", false]], "tensorrt_llm::runtime::requesttype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime11RequestTypeE", false]], "tensorrt_llm::runtime::requesttype::kcontext (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11RequestType8kCONTEXTE", false]], "tensorrt_llm::runtime::requesttype::kgeneration (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11RequestType11kGENERATIONE", false]], "tensorrt_llm::runtime::runtimedefaults (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaultsE", false]], "tensorrt_llm::runtime::runtimedefaults::maxattentionwindowvec (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults21maxAttentionWindowVecE", false]], "tensorrt_llm::runtime::runtimedefaults::runtimedefaults (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults15RuntimeDefaultsENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalI10SizeType32EE", false], [1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults15RuntimeDefaultsEv", false]], "tensorrt_llm::runtime::runtimedefaults::sinktokenlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults15sinkTokenLengthE", false]], "tensorrt_llm::runtime::samplingconfig (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfigE", false]], "tensorrt_llm::runtime::samplingconfig::beamsearchdiversityrate (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig23beamSearchDiversityRateE", false]], "tensorrt_llm::runtime::samplingconfig::beamwidth (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9beamWidthE", false]], "tensorrt_llm::runtime::samplingconfig::beamwidtharray (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14beamWidthArrayE", false]], "tensorrt_llm::runtime::samplingconfig::cumlogprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig11cumLogProbsE", false]], "tensorrt_llm::runtime::samplingconfig::draftacceptancethreshold (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig24draftAcceptanceThresholdE", false]], "tensorrt_llm::runtime::samplingconfig::earlystopping (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig13earlyStoppingE", false]], "tensorrt_llm::runtime::samplingconfig::floattype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE", false]], "tensorrt_llm::runtime::samplingconfig::frequencypenalty (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig16frequencyPenaltyE", false]], "tensorrt_llm::runtime::samplingconfig::fusevalues (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T", false]], "tensorrt_llm::runtime::samplingconfig::getmaxbeamwidth (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14SamplingConfig15getMaxBeamWidthEv", false]], "tensorrt_llm::runtime::samplingconfig::getnumreturnbeams (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14SamplingConfig17getNumReturnBeamsEv", false]], "tensorrt_llm::runtime::samplingconfig::lengthpenalty (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig13lengthPenaltyE", false]], "tensorrt_llm::runtime::samplingconfig::minlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9minLengthE", false]], "tensorrt_llm::runtime::samplingconfig::minp (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig4minPE", false]], "tensorrt_llm::runtime::samplingconfig::norepeatngramsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17noRepeatNgramSizeE", false]], "tensorrt_llm::runtime::samplingconfig::normalizelogprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17normalizeLogProbsE", false]], "tensorrt_llm::runtime::samplingconfig::numreturnsequences (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig18numReturnSequencesE", false]], "tensorrt_llm::runtime::samplingconfig::operator== (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14SamplingConfigeqERK14SamplingConfig", false]], "tensorrt_llm::runtime::samplingconfig::optvec (c++ type)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE", false]], "tensorrt_llm::runtime::samplingconfig::originaltemperature (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig19originalTemperatureE", false]], "tensorrt_llm::runtime::samplingconfig::outputlogprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14outputLogProbsE", false]], "tensorrt_llm::runtime::samplingconfig::presencepenalty (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig15presencePenaltyE", false]], "tensorrt_llm::runtime::samplingconfig::randomseed (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig10randomSeedE", false]], "tensorrt_llm::runtime::samplingconfig::repetitionpenalty (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17repetitionPenaltyE", false]], "tensorrt_llm::runtime::samplingconfig::samplingconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigE10SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKN8executor14SamplingConfigERKNSt8optionalIN8executor25ExternalDraftTokensConfigEEE", false], [1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKNSt6vectorI14SamplingConfigEE", false]], "tensorrt_llm::runtime::samplingconfig::temperature (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig11temperatureE", false]], "tensorrt_llm::runtime::samplingconfig::topk (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topKE", false]], "tensorrt_llm::runtime::samplingconfig::topkmedusaheads (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig15topKMedusaHeadsE", false]], "tensorrt_llm::runtime::samplingconfig::topp (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topPE", false]], "tensorrt_llm::runtime::samplingconfig::toppdecay (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9topPDecayE", false]], "tensorrt_llm::runtime::samplingconfig::toppmin (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig7topPMinE", false]], "tensorrt_llm::runtime::samplingconfig::toppresetids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig12topPResetIdsE", false]], "tensorrt_llm::runtime::samplingconfig::usedefaultvalues (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig16useDefaultValuesEbRK6OptVecI1TE1T", false]], "tensorrt_llm::runtime::samplingconfig::validate (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig8validateEv", false]], "tensorrt_llm::runtime::samplingconfig::validatevec (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", false]], "tensorrt_llm::runtime::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10SizeType32E", false]], "tensorrt_llm::runtime::sizetype64 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10SizeType64E", false]], "tensorrt_llm::runtime::speculativedecodingmode (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingModeE", false]], "tensorrt_llm::runtime::speculativedecodingmode::allbitset (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9allBitSetE14UnderlyingType", false]], "tensorrt_llm::runtime::speculativedecodingmode::anybitset (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9anyBitSetE14UnderlyingType", false]], "tensorrt_llm::runtime::speculativedecodingmode::drafttokensexternal (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode19DraftTokensExternalEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::eagle (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode5EagleEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::explicitdrafttokens (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode19ExplicitDraftTokensEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::hasdraftlogits (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode14hasDraftLogitsEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::isdrafttokensexternal (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21isDraftTokensExternalEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::iseagle (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode7isEagleEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::isexplicitdrafttokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21isExplicitDraftTokensEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::islookaheaddecoding (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19isLookaheadDecodingEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::ismedusa (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode8isMedusaEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::isnone (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode6isNoneEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::kdrafttokensexternal (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode20kDraftTokensExternalE", false]], "tensorrt_llm::runtime::speculativedecodingmode::keagle (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode6kEagleE", false]], "tensorrt_llm::runtime::speculativedecodingmode::kexplicitdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode20kExplicitDraftTokensE", false]], "tensorrt_llm::runtime::speculativedecodingmode::klookaheaddecoding (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode18kLookaheadDecodingE", false]], "tensorrt_llm::runtime::speculativedecodingmode::kmedusa (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode7kMedusaE", false]], "tensorrt_llm::runtime::speculativedecodingmode::knone (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode5kNoneE", false]], "tensorrt_llm::runtime::speculativedecodingmode::lookaheaddecoding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode17LookaheadDecodingEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::medusa (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode6MedusaEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::mstate (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode6mStateE", false]], "tensorrt_llm::runtime::speculativedecodingmode::needsdecoderprologue (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode20needsDecoderPrologueEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::needskvcacherewind (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode18needsKVCacheRewindEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::none (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode4NoneEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::operator== (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingModeeqERK23SpeculativeDecodingMode", false]], "tensorrt_llm::runtime::speculativedecodingmode::predictsdrafttokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19predictsDraftTokensEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::requiresattentionmask (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21requiresAttentionMaskEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::speculativedecodingmode (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode23SpeculativeDecodingModeE14UnderlyingType", false]], "tensorrt_llm::runtime::speculativedecodingmode::underlyingtype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode14UnderlyingTypeE", false]], "tensorrt_llm::runtime::speculativedecodingmode::updatespositionids (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode18updatesPositionIdsEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::variabledraftlength (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19variableDraftLengthEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleE", false]], "tensorrt_llm::runtime::speculativedecodingmodule::computenumpackedmasks (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule21computeNumPackedMasksEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule::getmaxdecodingdrafttokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule25getMaxDecodingDraftTokensEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule::getmaxdecodingtokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule20getMaxDecodingTokensEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule::getmaxdraftpathlen (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule18getMaxDraftPathLenEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule::getmaxnumpaths (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule14getMaxNumPathsEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule::getmaxpathlen (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule13getMaxPathLenEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule::getnumpackedmasks (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule17getNumPackedMasksEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule::mmaxdecodingdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule23mMaxDecodingDraftTokensE", false]], "tensorrt_llm::runtime::speculativedecodingmodule::mmaxdraftpathlen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule16mMaxDraftPathLenE", false]], "tensorrt_llm::runtime::speculativedecodingmodule::mmaxnumpackedmasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule18mMaxNumPackedMasksE", false]], "tensorrt_llm::runtime::speculativedecodingmodule::mmaxnumpaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule12mMaxNumPathsE", false]], "tensorrt_llm::runtime::speculativedecodingmodule::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleaSERK25SpeculativeDecodingModule", false]], "tensorrt_llm::runtime::speculativedecodingmodule::setmaxdraftpathlen (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule18setMaxDraftPathLenE10SizeType32", false]], "tensorrt_llm::runtime::speculativedecodingmodule::setmaxdrafttokens (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule17setMaxDraftTokensE10SizeType32", false]], "tensorrt_llm::runtime::speculativedecodingmodule::setmaxnumpaths (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule14setMaxNumPathsE10SizeType32", false]], "tensorrt_llm::runtime::speculativedecodingmodule::speculativedecodingmodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleE10SizeType3210SizeType3210SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleERK25SpeculativeDecodingModule", false], [1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule::~speculativedecodingmodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleD0Ev", false]], "tensorrt_llm::runtime::stringptrmap (c++ type)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime12StringPtrMapE", false]], "tensorrt_llm::runtime::tllmlogger (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime10TllmLoggerE", false]], "tensorrt_llm::runtime::tllmlogger::getlevel (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger8getLevelEv", false]], "tensorrt_llm::runtime::tllmlogger::log (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger3logE8SeverityPKN8nvinfer19AsciiCharE", false]], "tensorrt_llm::runtime::tllmlogger::setlevel (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger8setLevelE8Severity", false]], "tensorrt_llm::runtime::to_string (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9to_stringERK26LoraCachePageManagerConfig", false], [1, "_CPPv4N12tensorrt_llm7runtime9to_stringERKN9LoraCache21TaskLayerModuleConfigE", false]], "tensorrt_llm::runtime::tokenextraidtype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime16TokenExtraIdTypeE", false]], "tensorrt_llm::runtime::tokenidtype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime11TokenIdTypeE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4I0_bEN12tensorrt_llm7runtime11TRTDataTypeE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIbEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIbE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIfEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIfE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeI4halfEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeI4halfE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIN7kernels13FinishedStateEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIN7kernels13FinishedStateEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIN7kernels12KVCacheIndexEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIN7kernels12KVCacheIndexEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIN7runtime11RequestTypeEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIN7runtime11RequestTypeEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime11TRTDataTypeIP1TEE", false]], "tensorrt_llm::runtime::trtdatatype::kunderlyingtype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE15kUnderlyingTypeE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIPvEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIPvE5valueE", false]], "tensorrt_llm::runtime::uniquetoken (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime11UniqueTokenE", false]], "tensorrt_llm::runtime::uniquetoken::operator== (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11UniqueTokeneqERK11UniqueToken", false]], "tensorrt_llm::runtime::uniquetoken::tokenextraid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11UniqueToken12tokenExtraIdE", false]], "tensorrt_llm::runtime::uniquetoken::tokenid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11UniqueToken7tokenIdE", false]], "tensorrt_llm::runtime::vectokenextraids (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime16VecTokenExtraIdsE", false]], "tensorrt_llm::runtime::vecuniquetokens (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime15VecUniqueTokensE", false]], "tensorrt_llm::runtime::worldconfig (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfigE", false]], "tensorrt_llm::runtime::worldconfig::enableattentiondp (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig17enableAttentionDPEv", false]], "tensorrt_llm::runtime::worldconfig::getcontextparallelgroup (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig23getContextParallelGroupEv", false]], "tensorrt_llm::runtime::worldconfig::getcontextparallelism (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig21getContextParallelismEv", false]], "tensorrt_llm::runtime::worldconfig::getcontextparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getContextParallelRankEv", false]], "tensorrt_llm::runtime::worldconfig::getdevice (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig9getDeviceEv", false]], "tensorrt_llm::runtime::worldconfig::getdeviceof (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getDeviceOfE10SizeType32", false]], "tensorrt_llm::runtime::worldconfig::getgpuspergroup (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig15getGpusPerGroupEv", false]], "tensorrt_llm::runtime::worldconfig::getgpuspernode (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig14getGpusPerNodeEv", false]], "tensorrt_llm::runtime::worldconfig::getlastrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getLastRankEv", false]], "tensorrt_llm::runtime::worldconfig::getlocalrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig12getLocalRankEv", false]], "tensorrt_llm::runtime::worldconfig::getnoderank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getNodeRankEv", false]], "tensorrt_llm::runtime::worldconfig::getnoderankof (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig13getNodeRankOfE10SizeType32", false]], "tensorrt_llm::runtime::worldconfig::getpipelineparallelgroup (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig24getPipelineParallelGroupEv", false]], "tensorrt_llm::runtime::worldconfig::getpipelineparallelism (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getPipelineParallelismEv", false]], "tensorrt_llm::runtime::worldconfig::getpipelineparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig23getPipelineParallelRankEv", false]], "tensorrt_llm::runtime::worldconfig::getrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getRankEv", false]], "tensorrt_llm::runtime::worldconfig::getsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getSizeEv", false]], "tensorrt_llm::runtime::worldconfig::gettensorparallelgroup (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getTensorParallelGroupEv", false]], "tensorrt_llm::runtime::worldconfig::gettensorparallelism (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig20getTensorParallelismEv", false]], "tensorrt_llm::runtime::worldconfig::gettensorparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig21getTensorParallelRankEv", false]], "tensorrt_llm::runtime::worldconfig::iscontextparallel (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig17isContextParallelEv", false]], "tensorrt_llm::runtime::worldconfig::isfirstcontextparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig26isFirstContextParallelRankEv", false]], "tensorrt_llm::runtime::worldconfig::isfirstpipelineparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig27isFirstPipelineParallelRankEv", false]], "tensorrt_llm::runtime::worldconfig::isfirsttensorparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig25isFirstTensorParallelRankEv", false]], "tensorrt_llm::runtime::worldconfig::islastpipelineparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig26isLastPipelineParallelRankEv", false]], "tensorrt_llm::runtime::worldconfig::ispipelineparallel (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig18isPipelineParallelEv", false]], "tensorrt_llm::runtime::worldconfig::istensorparallel (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig16isTensorParallelEv", false]], "tensorrt_llm::runtime::worldconfig::kdefaultgpuspernode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig19kDefaultGpusPerNodeE", false]], "tensorrt_llm::runtime::worldconfig::mcontextparallelism (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig19mContextParallelismE", false]], "tensorrt_llm::runtime::worldconfig::mdeviceids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig10mDeviceIdsE", false]], "tensorrt_llm::runtime::worldconfig::menableattentiondp (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig18mEnableAttentionDPE", false]], "tensorrt_llm::runtime::worldconfig::mgpuspernode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig12mGpusPerNodeE", false]], "tensorrt_llm::runtime::worldconfig::mpi (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEEb", false]], "tensorrt_llm::runtime::worldconfig::mpipelineparallelism (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig20mPipelineParallelismE", false]], "tensorrt_llm::runtime::worldconfig::mrank (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig5mRankE", false]], "tensorrt_llm::runtime::worldconfig::mtensorparallelism (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig18mTensorParallelismE", false]], "tensorrt_llm::runtime::worldconfig::validmpiconfig (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig14validMpiConfigEv", false]], "tensorrt_llm::runtime::worldconfig::worldconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", false]], "text (tensorrt_llm.llmapi.completionoutput attribute)": [[68, "tensorrt_llm.llmapi.CompletionOutput.text", false]], "text_diff (tensorrt_llm.llmapi.completionoutput attribute)": [[68, "tensorrt_llm.llmapi.CompletionOutput.text_diff", false]], "text_diff (tensorrt_llm.llmapi.completionoutput property)": [[68, "id4", false]], "timestepembedding (class in tensorrt_llm.layers.embedding)": [[81, "tensorrt_llm.layers.embedding.TimestepEmbedding", false]], "timesteps (class in tensorrt_llm.layers.embedding)": [[81, "tensorrt_llm.layers.embedding.Timesteps", false]], "to_dict() (tensorrt_llm.llmapi.buildconfig method)": [[68, "tensorrt_llm.llmapi.BuildConfig.to_dict", false]], "to_dict() (tensorrt_llm.llmapi.calibconfig method)": [[68, "tensorrt_llm.llmapi.CalibConfig.to_dict", false]], "to_dict() (tensorrt_llm.llmapi.quantconfig method)": [[68, "tensorrt_llm.llmapi.QuantConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.chatglmconfig method)": [[82, "tensorrt_llm.models.ChatGLMConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.cogvlmconfig method)": [[82, "tensorrt_llm.models.CogVLMConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.dbrxconfig method)": [[82, "tensorrt_llm.models.DbrxConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.falconconfig method)": [[82, "tensorrt_llm.models.FalconConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.gemmaconfig method)": [[82, "tensorrt_llm.models.GemmaConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.gptconfig method)": [[82, "tensorrt_llm.models.GPTConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.gptjconfig method)": [[82, "tensorrt_llm.models.GPTJConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.llamaconfig method)": [[82, "tensorrt_llm.models.LLaMAConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.medusaconfig method)": [[82, "tensorrt_llm.models.MedusaConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.pretrainedconfig method)": [[82, "tensorrt_llm.models.PretrainedConfig.to_dict", false]], "to_json_file() (tensorrt_llm.models.pretrainedconfig method)": [[82, "tensorrt_llm.models.PretrainedConfig.to_json_file", false]], "to_layer_quant_config() (tensorrt_llm.models.pretrainedconfig method)": [[82, "tensorrt_llm.models.PretrainedConfig.to_layer_quant_config", false]], "to_legacy_setting() (tensorrt_llm.plugin.pluginconfig method)": [[83, "tensorrt_llm.plugin.PluginConfig.to_legacy_setting", false]], "token_drop() (tensorrt_llm.layers.embedding.labelembedding method)": [[81, "tensorrt_llm.layers.embedding.LabelEmbedding.token_drop", false]], "token_end (tensorrt_llm.llmapi.kvcacheretentionconfig.tokenrangeretentionconfig property)": [[68, "tensorrt_llm.llmapi.KvCacheRetentionConfig.TokenRangeRetentionConfig.token_end", false]], "token_ids (tensorrt_llm.llmapi.completionoutput attribute)": [[68, "tensorrt_llm.llmapi.CompletionOutput.token_ids", false]], "token_ids_diff (tensorrt_llm.llmapi.completionoutput attribute)": [[68, "tensorrt_llm.llmapi.CompletionOutput.token_ids_diff", false]], "token_ids_diff (tensorrt_llm.llmapi.completionoutput property)": [[68, "id5", false]], "token_range_retention_configs (tensorrt_llm.llmapi.kvcacheretentionconfig property)": [[68, "tensorrt_llm.llmapi.KvCacheRetentionConfig.token_range_retention_configs", false]], "token_start (tensorrt_llm.llmapi.kvcacheretentionconfig.tokenrangeretentionconfig property)": [[68, "tensorrt_llm.llmapi.KvCacheRetentionConfig.TokenRangeRetentionConfig.token_start", false]], "tokenizer (tensorrt_llm.llmapi.llm attribute)": [[68, "tensorrt_llm.llmapi.LLM.tokenizer", false]], "tokenizer (tensorrt_llm.llmapi.llm property)": [[68, "id1", false]], "tokenizer_image_token() (tensorrt_llm.runtime.multimodalmodelrunner static method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.tokenizer_image_token", false]], "tokenizer_max_seq_length (tensorrt_llm.llmapi.calibconfig attribute)": [[68, "tensorrt_llm.llmapi.CalibConfig.tokenizer_max_seq_length", false]], "tokens_per_block (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.tokens_per_block", false]], "tokens_per_block (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.tokens_per_block", false]], "top_k (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.top_k", false]], "top_k (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.top_k", false]], "top_p (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.top_p", false]], "top_p (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.top_p", false]], "top_p_decay (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.top_p_decay", false]], "top_p_decay (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.top_p_decay", false]], "top_p_min (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.top_p_min", false]], "top_p_min (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.top_p_min", false]], "top_p_reset_ids (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.top_p_reset_ids", false]], "top_p_reset_ids (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.top_p_reset_ids", false]], "topk() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.topk", false]], "torch_compile_config (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.torch_compile_config", false]], "torchcompileconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.TorchCompileConfig", false]], "torchllmargs (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs", false]], "tp_split_dim() (tensorrt_llm.layers.linear.linear class method)": [[81, "tensorrt_llm.layers.linear.Linear.tp_split_dim", false]], "tp_split_dim() (tensorrt_llm.layers.linear.linearbase class method)": [[81, "tensorrt_llm.layers.linear.LinearBase.tp_split_dim", false]], "tp_split_dim() (tensorrt_llm.layers.linear.rowlinear class method)": [[81, "tensorrt_llm.layers.linear.RowLinear.tp_split_dim", false]], "transfer_mode (tensorrt_llm.llmapi.kvcacheretentionconfig property)": [[68, "tensorrt_llm.llmapi.KvCacheRetentionConfig.transfer_mode", false]], "transpose() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.transpose", false]], "transpose() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.transpose", false]], "trtllm-serve-disaggregated command line option": [[34, "cmdoption-trtllm-serve-disaggregated-c", false], [34, "cmdoption-trtllm-serve-disaggregated-l", false], [34, "cmdoption-trtllm-serve-disaggregated-m", false], [34, "cmdoption-trtllm-serve-disaggregated-r", false], [34, "cmdoption-trtllm-serve-disaggregated-t", false]], "trtllm-serve-disaggregated_mpi_worker command line option": [[34, "cmdoption-trtllm-serve-disaggregated_mpi_worker-c", false], [34, "cmdoption-trtllm-serve-disaggregated_mpi_worker-log_level", false]], "trtllm-serve-serve command line option": [[34, "cmdoption-trtllm-serve-serve-arg-MODEL", false], [34, "cmdoption-trtllm-serve-serve-backend", false], [34, "cmdoption-trtllm-serve-serve-cluster_size", false], [34, "cmdoption-trtllm-serve-serve-ep_size", false], [34, "cmdoption-trtllm-serve-serve-extra_llm_api_options", false], [34, "cmdoption-trtllm-serve-serve-gpus_per_node", false], [34, "cmdoption-trtllm-serve-serve-host", false], [34, "cmdoption-trtllm-serve-serve-kv_cache_free_gpu_memory_fraction", false], [34, "cmdoption-trtllm-serve-serve-log_level", false], [34, "cmdoption-trtllm-serve-serve-max_batch_size", false], [34, "cmdoption-trtllm-serve-serve-max_beam_width", false], [34, "cmdoption-trtllm-serve-serve-max_num_tokens", false], [34, "cmdoption-trtllm-serve-serve-max_seq_len", false], [34, "cmdoption-trtllm-serve-serve-metadata_server_config_file", false], [34, "cmdoption-trtllm-serve-serve-num_postprocess_workers", false], [34, "cmdoption-trtllm-serve-serve-port", false], [34, "cmdoption-trtllm-serve-serve-pp_size", false], [34, "cmdoption-trtllm-serve-serve-reasoning_parser", false], [34, "cmdoption-trtllm-serve-serve-server_role", false], [34, "cmdoption-trtllm-serve-serve-tokenizer", false], [34, "cmdoption-trtllm-serve-serve-tp_size", false], [34, "cmdoption-trtllm-serve-serve-trust_remote_code", false]], "trtllm_modules_to_hf_modules (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.trtllm_modules_to_hf_modules", false]], "trtllmargs (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs", false]], "truncate_prompt_tokens (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.truncate_prompt_tokens", false]], "twoshot (tensorrt_llm.functional.allreducestrategy attribute)": [[80, "tensorrt_llm.functional.AllReduceStrategy.TWOSHOT", false]], "ub (tensorrt_llm.functional.allreducestrategy attribute)": [[80, "tensorrt_llm.functional.AllReduceStrategy.UB", false]], "unary() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.unary", false]], "unbind() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.unbind", false]], "unbind() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.unbind", false]], "unfuse_qkv_projections() (tensorrt_llm.models.sd3transformer2dmodel method)": [[82, "tensorrt_llm.models.SD3Transformer2DModel.unfuse_qkv_projections", false]], "unpatchify() (tensorrt_llm.models.dit method)": [[82, "tensorrt_llm.models.DiT.unpatchify", false]], "unsqueeze() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.unsqueeze", false]], "unsqueeze() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.unsqueeze", false]], "update() (tensorrt_llm.llmapi.buildconfig method)": [[68, "tensorrt_llm.llmapi.BuildConfig.update", false]], "update() (tensorrt_llm.runtime.samplingconfig method)": [[85, "tensorrt_llm.runtime.SamplingConfig.update", false]], "update_from_dict() (tensorrt_llm.llmapi.buildconfig method)": [[68, "tensorrt_llm.llmapi.BuildConfig.update_from_dict", false]], "update_from_model_config() (tensorrt_llm.llmapi.mtpdecodingconfig method)": [[68, "tensorrt_llm.llmapi.MTPDecodingConfig.update_from_model_config", false]], "update_kv_cache_type() (tensorrt_llm.llmapi.buildconfig method)": [[68, "tensorrt_llm.llmapi.BuildConfig.update_kv_cache_type", false]], "update_output_ids_by_offset() (tensorrt_llm.runtime.generationsession method)": [[85, "tensorrt_llm.runtime.GenerationSession.update_output_ids_by_offset", false]], "update_strategy() (tensorrt_llm.functional.allreduceparams method)": [[80, "tensorrt_llm.functional.AllReduceParams.update_strategy", false]], "use_beam_hyps (tensorrt_llm.runtime.samplingconfig attribute)": [[85, "tensorrt_llm.runtime.SamplingConfig.use_beam_hyps", false]], "use_beam_search (tensorrt_llm.llmapi.samplingparams attribute)": [[68, "tensorrt_llm.llmapi.SamplingParams.use_beam_search", false]], "use_dynamic_tree (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.EagleDecodingConfig.use_dynamic_tree", false]], "use_gemm_allreduce_plugin (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.use_gemm_allreduce_plugin", false]], "use_gpt_attention_plugin (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.use_gpt_attention_plugin", false]], "use_kv_cache (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.use_kv_cache", false]], "use_lora() (tensorrt_llm.models.decodermodel method)": [[82, "tensorrt_llm.models.DecoderModel.use_lora", false]], "use_lora() (tensorrt_llm.models.encodermodel method)": [[82, "tensorrt_llm.models.EncoderModel.use_lora", false]], "use_lora() (tensorrt_llm.models.gemmaforcausallm method)": [[82, "tensorrt_llm.models.GemmaForCausalLM.use_lora", false]], "use_lora() (tensorrt_llm.models.gptforcausallm method)": [[82, "tensorrt_llm.models.GPTForCausalLM.use_lora", false]], "use_lora() (tensorrt_llm.models.llamaforcausallm method)": [[82, "tensorrt_llm.models.LLaMAForCausalLM.use_lora", false]], "use_lora() (tensorrt_llm.models.mllamaforcausallm method)": [[82, "tensorrt_llm.models.MLLaMAForCausalLM.use_lora", false]], "use_lora() (tensorrt_llm.models.phi3forcausallm method)": [[82, "tensorrt_llm.models.Phi3ForCausalLM.use_lora", false]], "use_lora() (tensorrt_llm.models.phiforcausallm method)": [[82, "tensorrt_llm.models.PhiForCausalLM.use_lora", false]], "use_lora_plugin (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.use_lora_plugin", false]], "use_lora_plugin (tensorrt_llm.runtime.modelrunner property)": [[85, "tensorrt_llm.runtime.ModelRunner.use_lora_plugin", false]], "use_mamba_conv1d_plugin (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.use_mamba_conv1d_plugin", false]], "use_meta_recipe (tensorrt_llm.llmapi.quantconfig attribute)": [[68, "tensorrt_llm.llmapi.QuantConfig.use_meta_recipe", false]], "use_mrope (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.use_mrope", false]], "use_mtp_vanilla (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.MTPDecodingConfig.use_mtp_vanilla", false]], "use_prompt_tuning() (tensorrt_llm.models.encodermodel method)": [[82, "tensorrt_llm.models.EncoderModel.use_prompt_tuning", false]], "use_refit (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.use_refit", false]], "use_relaxed_acceptance_for_thinking (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[68, "tensorrt_llm.llmapi.MTPDecodingConfig.use_relaxed_acceptance_for_thinking", false]], "use_strip_plan (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.use_strip_plan", false]], "use_uvm (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[68, "tensorrt_llm.llmapi.KvCacheConfig.use_uvm", false]], "user_provided (tensorrt_llm.models.speculativedecodingmode attribute)": [[82, "tensorrt_llm.models.SpeculativeDecodingMode.USER_PROVIDED", false]], "userprovideddecodingconfig (class in tensorrt_llm.llmapi)": [[68, "tensorrt_llm.llmapi.UserProvidedDecodingConfig", false]], "validate() (tensorrt_llm.llmapi.eagledecodingconfig method)": [[68, "tensorrt_llm.llmapi.EagleDecodingConfig.validate", false]], "validate_auto_parallel() (tensorrt_llm.llmapi.trtllmargs method)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.validate_auto_parallel", false]], "validate_cuda_graph_config() (tensorrt_llm.llmapi.torchllmargs method)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.validate_cuda_graph_config", false]], "validate_cuda_graph_max_batch_size() (tensorrt_llm.llmapi.cudagraphconfig class method)": [[68, "tensorrt_llm.llmapi.CudaGraphConfig.validate_cuda_graph_max_batch_size", false]], "validate_enable_build_cache() (tensorrt_llm.llmapi.trtllmargs method)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.validate_enable_build_cache", false]], "validate_moe_load_balancer() (tensorrt_llm.llmapi.torchllmargs method)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.validate_moe_load_balancer", false]], "validate_positive_values() (tensorrt_llm.llmapi.lookaheaddecodingconfig class method)": [[68, "tensorrt_llm.llmapi.LookaheadDecodingConfig.validate_positive_values", false]], "validate_stream_interval() (tensorrt_llm.llmapi.torchllmargs method)": [[68, "tensorrt_llm.llmapi.TorchLlmArgs.validate_stream_interval", false]], "verbatim (tensorrt_llm.models.gemmaconfig attribute)": [[82, "tensorrt_llm.models.GemmaConfig.VERBATIM", false]], "video_preprocess() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.video_preprocess", false]], "view() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.view", false]], "view() (tensorrt_llm.functional.tensor method)": [[80, "tensorrt_llm.functional.Tensor.view", false]], "view() (tensorrt_llm.runtime.tensorinfo method)": [[85, "tensorrt_llm.runtime.TensorInfo.view", false]], "visual_engine_dir (tensorrt_llm.runtime.multimodalmodelrunner property)": [[85, "tensorrt_llm.runtime.MultimodalModelRunner.visual_engine_dir", false]], "visualize_network (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.visualize_network", false]], "vocab_size (tensorrt_llm.runtime.generationsession property)": [[85, "tensorrt_llm.runtime.GenerationSession.vocab_size", false]], "vocab_size (tensorrt_llm.runtime.modelconfig attribute)": [[85, "tensorrt_llm.runtime.ModelConfig.vocab_size", false]], "vocab_size (tensorrt_llm.runtime.modelrunner property)": [[85, "tensorrt_llm.runtime.ModelRunner.vocab_size", false]], "vocab_size (tensorrt_llm.runtime.modelrunnercpp property)": [[85, "tensorrt_llm.runtime.ModelRunnerCpp.vocab_size", false]], "vocab_size_padded (tensorrt_llm.runtime.modelrunner property)": [[85, "tensorrt_llm.runtime.ModelRunner.vocab_size_padded", false]], "vocab_size_padded (tensorrt_llm.runtime.modelrunnercpp property)": [[85, "tensorrt_llm.runtime.ModelRunnerCpp.vocab_size_padded", false]], "w4a16 (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.W4A16", false]], "w4a16_awq (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.W4A16_AWQ", false]], "w4a16_gptq (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.W4A16_GPTQ", false]], "w4a8_awq (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.W4A8_AWQ", false]], "w4a8_mxfp4_fp8 (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.W4A8_MXFP4_FP8", false]], "w4a8_qserve_per_channel (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.W4A8_QSERVE_PER_CHANNEL", false]], "w4a8_qserve_per_group (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.W4A8_QSERVE_PER_GROUP", false]], "w8a16 (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.W8A16", false]], "w8a16_gptq (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.W8A16_GPTQ", false]], "w8a8_sq_per_channel (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.W8A8_SQ_PER_CHANNEL", false]], "w8a8_sq_per_channel_per_tensor_plugin (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.W8A8_SQ_PER_CHANNEL_PER_TENSOR_PLUGIN", false]], "w8a8_sq_per_channel_per_token_plugin (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.W8A8_SQ_PER_CHANNEL_PER_TOKEN_PLUGIN", false]], "w8a8_sq_per_tensor_per_token_plugin (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.W8A8_SQ_PER_TENSOR_PER_TOKEN_PLUGIN", false]], "w8a8_sq_per_tensor_plugin (tensorrt_llm.llmapi.quantalgo attribute)": [[68, "tensorrt_llm.llmapi.QuantAlgo.W8A8_SQ_PER_TENSOR_PLUGIN", false]], "weight_loader() (tensorrt_llm.layers.attention.deepseekv2attention method)": [[81, "tensorrt_llm.layers.attention.DeepseekV2Attention.weight_loader", false]], "weight_loader() (tensorrt_llm.layers.embedding.embedding method)": [[81, "tensorrt_llm.layers.embedding.Embedding.weight_loader", false]], "weight_loader() (tensorrt_llm.layers.linear.linearbase method)": [[81, "tensorrt_llm.layers.linear.LinearBase.weight_loader", false]], "weight_sparsity (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.weight_sparsity", false]], "weight_streaming (tensorrt_llm.llmapi.buildconfig attribute)": [[68, "tensorrt_llm.llmapi.BuildConfig.weight_streaming", false]], "where() (in module tensorrt_llm.functional)": [[80, "tensorrt_llm.functional.where", false]], "whisperencoder (class in tensorrt_llm.models)": [[82, "tensorrt_llm.models.WhisperEncoder", false]], "workspace (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "tensorrt_llm.llmapi.TrtLlmArgs.workspace", false]], "wrapped_property (tensorrt_llm.llmapi.torchllmargs attribute)": [[68, "id11", false], [68, "id14", false], [68, "id17", false], [68, "tensorrt_llm.llmapi.TorchLlmArgs.wrapped_property", false]], "wrapped_property (tensorrt_llm.llmapi.trtllmargs attribute)": [[68, "id20", false], [68, "id23", false], [68, "id26", false], [68, "id29", false], [68, "id32", false], [68, "tensorrt_llm.llmapi.TrtLlmArgs.wrapped_property", false]], "yarn (tensorrt_llm.functional.positionembeddingtype attribute)": [[80, "tensorrt_llm.functional.PositionEmbeddingType.yarn", false]], "yarn (tensorrt_llm.functional.rotaryscalingtype attribute)": [[80, "tensorrt_llm.functional.RotaryScalingType.yarn", false]]}, "objects": {"": [[1, 0, 1, "c.FMT_DIM", "FMT_DIM"], [1, 0, 1, "c.SET_FROM_OPTIONAL", "SET_FROM_OPTIONAL"], [1, 1, 1, "_CPPv48nvinfer1", "nvinfer1"], [0, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [0, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [0, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [0, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [0, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [0, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [0, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [0, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [0, 1, 1, "_CPPv4N12tensorrt_llm13batch_managerE", "tensorrt_llm::batch_manager"], [1, 1, 1, "_CPPv4N12tensorrt_llm13batch_managerE", "tensorrt_llm::batch_manager"], [1, 1, 1, "_CPPv4N12tensorrt_llm13batch_managerE", "tensorrt_llm::batch_manager"], [1, 1, 1, "_CPPv4N12tensorrt_llm13batch_managerE", "tensorrt_llm::batch_manager"], [1, 1, 1, "_CPPv4N12tensorrt_llm13batch_managerE", "tensorrt_llm::batch_manager"], [0, 1, 1, "_CPPv4N12tensorrt_llm13batch_manager16kv_cache_managerE", "tensorrt_llm::batch_manager::kv_cache_manager"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executorE", "tensorrt_llm::executor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executorE", "tensorrt_llm::executor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executorE", "tensorrt_llm::executor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executorE", "tensorrt_llm::executor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executorE", "tensorrt_llm::executor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executorE", "tensorrt_llm::executor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executorE", "tensorrt_llm::executor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executorE", "tensorrt_llm::executor"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutputE", "tensorrt_llm::executor::AdditionalModelOutput"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutput21AdditionalModelOutputENSt6stringEb", "tensorrt_llm::executor::AdditionalModelOutput::AdditionalModelOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutput21AdditionalModelOutputENSt6stringEb", "tensorrt_llm::executor::AdditionalModelOutput::AdditionalModelOutput::gatherContext"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutput21AdditionalModelOutputENSt6stringEb", "tensorrt_llm::executor::AdditionalModelOutput::AdditionalModelOutput::name"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutput13gatherContextE", "tensorrt_llm::executor::AdditionalModelOutput::gatherContext"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutput4nameE", "tensorrt_llm::executor::AdditionalModelOutput::name"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor21AdditionalModelOutputeqERK21AdditionalModelOutput", "tensorrt_llm::executor::AdditionalModelOutput::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor21AdditionalModelOutputeqERK21AdditionalModelOutput", "tensorrt_llm::executor::AdditionalModelOutput::operator==::other"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputE", "tensorrt_llm::executor::AdditionalOutput"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputENSt6stringE6Tensor", "tensorrt_llm::executor::AdditionalOutput::AdditionalOutput"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputERK16AdditionalOutput", "tensorrt_llm::executor::AdditionalOutput::AdditionalOutput"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputERR16AdditionalOutput", "tensorrt_llm::executor::AdditionalOutput::AdditionalOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputENSt6stringE6Tensor", "tensorrt_llm::executor::AdditionalOutput::AdditionalOutput::name"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputERK16AdditionalOutput", "tensorrt_llm::executor::AdditionalOutput::AdditionalOutput::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputERR16AdditionalOutput", "tensorrt_llm::executor::AdditionalOutput::AdditionalOutput::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputENSt6stringE6Tensor", "tensorrt_llm::executor::AdditionalOutput::AdditionalOutput::output"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput4nameE", "tensorrt_llm::executor::AdditionalOutput::name"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputaSERK16AdditionalOutput", "tensorrt_llm::executor::AdditionalOutput::operator="], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputaSERR16AdditionalOutput", "tensorrt_llm::executor::AdditionalOutput::operator="], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputaSERK16AdditionalOutput", "tensorrt_llm::executor::AdditionalOutput::operator=::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputaSERR16AdditionalOutput", "tensorrt_llm::executor::AdditionalOutput::operator=::other"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput6outputE", "tensorrt_llm::executor::AdditionalOutput::output"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputD0Ev", "tensorrt_llm::executor::AdditionalOutput::~AdditionalOutput"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12BatchingTypeE", "tensorrt_llm::executor::BatchingType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12BatchingType9kINFLIGHTE", "tensorrt_llm::executor::BatchingType::kINFLIGHT"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12BatchingType7kSTATICE", "tensorrt_llm::executor::BatchingType::kSTATIC"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor10BeamTokensE", "tensorrt_llm::executor::BeamTokens"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor10BufferViewE", "tensorrt_llm::executor::BufferView"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfigE", "tensorrt_llm::executor::CacheTransceiverConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig22CacheTransceiverConfigENSt8optionalI6size_tEE", "tensorrt_llm::executor::CacheTransceiverConfig::CacheTransceiverConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig22CacheTransceiverConfigENSt8optionalI6size_tEE", "tensorrt_llm::executor::CacheTransceiverConfig::CacheTransceiverConfig::maxNumTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22CacheTransceiverConfig15getMaxNumTokensEv", "tensorrt_llm::executor::CacheTransceiverConfig::getMaxNumTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig13mMaxNumTokensE", "tensorrt_llm::executor::CacheTransceiverConfig::mMaxNumTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22CacheTransceiverConfigeqERK22CacheTransceiverConfig", "tensorrt_llm::executor::CacheTransceiverConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor22CacheTransceiverConfigeqERK22CacheTransceiverConfig", "tensorrt_llm::executor::CacheTransceiverConfig::operator==::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig15setMaxNumTokensE6size_t", "tensorrt_llm::executor::CacheTransceiverConfig::setMaxNumTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig15setMaxNumTokensE6size_t", "tensorrt_llm::executor::CacheTransceiverConfig::setMaxNumTokens::maxNumTokens"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicyE", "tensorrt_llm::executor::CapacitySchedulerPolicy"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicy20kGUARANTEED_NO_EVICTE", "tensorrt_llm::executor::CapacitySchedulerPolicy::kGUARANTEED_NO_EVICT"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicy16kMAX_UTILIZATIONE", "tensorrt_llm::executor::CapacitySchedulerPolicy::kMAX_UTILIZATION"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicy13kSTATIC_BATCHE", "tensorrt_llm::executor::CapacitySchedulerPolicy::kSTATIC_BATCH"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor17CommunicationModeE", "tensorrt_llm::executor::CommunicationMode"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor17CommunicationMode7kLEADERE", "tensorrt_llm::executor::CommunicationMode::kLEADER"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor17CommunicationMode13kORCHESTRATORE", "tensorrt_llm::executor::CommunicationMode::kORCHESTRATOR"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor17CommunicationTypeE", "tensorrt_llm::executor::CommunicationType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor17CommunicationType4kMPIE", "tensorrt_llm::executor::CommunicationType::kMPI"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicyE", "tensorrt_llm::executor::ContextChunkingPolicy"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicy15kEQUAL_PROGRESSE", "tensorrt_llm::executor::ContextChunkingPolicy::kEQUAL_PROGRESS"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicy24kFIRST_COME_FIRST_SERVEDE", "tensorrt_llm::executor::ContextChunkingPolicy::kFIRST_COME_FIRST_SERVED"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsE", "tensorrt_llm::executor::ContextPhaseParams"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypePvNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeRKNSt6vectorIcEENSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsERK18ContextPhaseParams", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsERR18ContextPhaseParams", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::draftTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypePvNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::draftTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeRKNSt6vectorIcEENSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::draftTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::firstGenTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypePvNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::firstGenTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeRKNSt6vectorIcEENSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::firstGenTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::reqId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypePvNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::reqId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeRKNSt6vectorIcEENSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::reqId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeRKNSt6vectorIcEENSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::serializedState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypePvNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::state"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams13RequestIdTypeE", "tensorrt_llm::executor::ContextPhaseParams::RequestIdType"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams8StatePtrE", "tensorrt_llm::executor::ContextPhaseParams::StatePtr"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams7deleterEPKv", "tensorrt_llm::executor::ContextPhaseParams::deleter"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams7deleterEPKv", "tensorrt_llm::executor::ContextPhaseParams::deleter::data"], [0, 3, 1, "_CPPv4NKR12tensorrt_llm8executor18ContextPhaseParams14getDraftTokensEv", "tensorrt_llm::executor::ContextPhaseParams::getDraftTokens"], [0, 3, 1, "_CPPv4NKR12tensorrt_llm8executor18ContextPhaseParams17getFirstGenTokensEv", "tensorrt_llm::executor::ContextPhaseParams::getFirstGenTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParams8getReqIdEv", "tensorrt_llm::executor::ContextPhaseParams::getReqId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParams18getSerializedStateEv", "tensorrt_llm::executor::ContextPhaseParams::getSerializedState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams8getStateEv", "tensorrt_llm::executor::ContextPhaseParams::getState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParams8getStateEv", "tensorrt_llm::executor::ContextPhaseParams::getState"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams12mDraftTokensE", "tensorrt_llm::executor::ContextPhaseParams::mDraftTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams15mFirstGenTokensE", "tensorrt_llm::executor::ContextPhaseParams::mFirstGenTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams6mReqIdE", "tensorrt_llm::executor::ContextPhaseParams::mReqId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams6mStateE", "tensorrt_llm::executor::ContextPhaseParams::mState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsaSERK18ContextPhaseParams", "tensorrt_llm::executor::ContextPhaseParams::operator="], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsaSERR18ContextPhaseParams", "tensorrt_llm::executor::ContextPhaseParams::operator="], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParamseqERK18ContextPhaseParams", "tensorrt_llm::executor::ContextPhaseParams::operator=="], [0, 3, 1, "_CPPv4NO12tensorrt_llm8executor18ContextPhaseParams17popFirstGenTokensEv", "tensorrt_llm::executor::ContextPhaseParams::popFirstGenTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams12releaseStateEv", "tensorrt_llm::executor::ContextPhaseParams::releaseState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsD0Ev", "tensorrt_llm::executor::ContextPhaseParams::~ContextPhaseParams"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverStateE", "tensorrt_llm::executor::DataTransceiverState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState20DataTransceiverStateEN8kv_cache10CacheStateEN8kv_cache9CommStateE", "tensorrt_llm::executor::DataTransceiverState::DataTransceiverState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState20DataTransceiverStateEv", "tensorrt_llm::executor::DataTransceiverState::DataTransceiverState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState20DataTransceiverStateEN8kv_cache10CacheStateEN8kv_cache9CommStateE", "tensorrt_llm::executor::DataTransceiverState::DataTransceiverState::cacheState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState20DataTransceiverStateEN8kv_cache10CacheStateEN8kv_cache9CommStateE", "tensorrt_llm::executor::DataTransceiverState::DataTransceiverState::commState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverState13getCacheStateEv", "tensorrt_llm::executor::DataTransceiverState::getCacheState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverState12getCommStateEv", "tensorrt_llm::executor::DataTransceiverState::getCommState"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState11mCacheStateE", "tensorrt_llm::executor::DataTransceiverState::mCacheState"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState10mCommStateE", "tensorrt_llm::executor::DataTransceiverState::mCommState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverStateeqERK20DataTransceiverState", "tensorrt_llm::executor::DataTransceiverState::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverStateeqERK20DataTransceiverState", "tensorrt_llm::executor::DataTransceiverState::operator==::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState13setCacheStateEN8kv_cache10CacheStateE", "tensorrt_llm::executor::DataTransceiverState::setCacheState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState13setCacheStateEN8kv_cache10CacheStateE", "tensorrt_llm::executor::DataTransceiverState::setCacheState::state"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState12setCommStateEN8kv_cache9CommStateE", "tensorrt_llm::executor::DataTransceiverState::setCommState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState12setCommStateEN8kv_cache9CommStateE", "tensorrt_llm::executor::DataTransceiverState::setCommState::state"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverState8toStringEv", "tensorrt_llm::executor::DataTransceiverState::toString"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8DataTypeE", "tensorrt_llm::executor::DataType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType5kBF16E", "tensorrt_llm::executor::DataType::kBF16"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType5kBOOLE", "tensorrt_llm::executor::DataType::kBOOL"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType5kFP16E", "tensorrt_llm::executor::DataType::kFP16"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType5kFP32E", "tensorrt_llm::executor::DataType::kFP32"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType4kFP8E", "tensorrt_llm::executor::DataType::kFP8"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType6kINT32E", "tensorrt_llm::executor::DataType::kINT32"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType6kINT64E", "tensorrt_llm::executor::DataType::kINT64"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType5kINT8E", "tensorrt_llm::executor::DataType::kINT8"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType6kUINT8E", "tensorrt_llm::executor::DataType::kUINT8"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType8kUNKNOWNE", "tensorrt_llm::executor::DataType::kUNKNOWN"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfigE", "tensorrt_llm::executor::DebugConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig11DebugConfigEbb9StringVec10SizeType32", "tensorrt_llm::executor::DebugConfig::DebugConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig11DebugConfigEbb9StringVec10SizeType32", "tensorrt_llm::executor::DebugConfig::DebugConfig::debugInputTensors"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig11DebugConfigEbb9StringVec10SizeType32", "tensorrt_llm::executor::DebugConfig::DebugConfig::debugOutputTensors"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig11DebugConfigEbb9StringVec10SizeType32", "tensorrt_llm::executor::DebugConfig::DebugConfig::debugTensorNames"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig11DebugConfigEbb9StringVec10SizeType32", "tensorrt_llm::executor::DebugConfig::DebugConfig::debugTensorsMaxIterations"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig9StringVecE", "tensorrt_llm::executor::DebugConfig::StringVec"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11DebugConfig20getDebugInputTensorsEv", "tensorrt_llm::executor::DebugConfig::getDebugInputTensors"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11DebugConfig21getDebugOutputTensorsEv", "tensorrt_llm::executor::DebugConfig::getDebugOutputTensors"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11DebugConfig19getDebugTensorNamesEv", "tensorrt_llm::executor::DebugConfig::getDebugTensorNames"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11DebugConfig28getDebugTensorsMaxIterationsEv", "tensorrt_llm::executor::DebugConfig::getDebugTensorsMaxIterations"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig18mDebugInputTensorsE", "tensorrt_llm::executor::DebugConfig::mDebugInputTensors"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig19mDebugOutputTensorsE", "tensorrt_llm::executor::DebugConfig::mDebugOutputTensors"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig17mDebugTensorNamesE", "tensorrt_llm::executor::DebugConfig::mDebugTensorNames"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig26mDebugTensorsMaxIterationsE", "tensorrt_llm::executor::DebugConfig::mDebugTensorsMaxIterations"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11DebugConfigeqERK11DebugConfig", "tensorrt_llm::executor::DebugConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor11DebugConfigeqERK11DebugConfig", "tensorrt_llm::executor::DebugConfig::operator==::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig20setDebugInputTensorsEb", "tensorrt_llm::executor::DebugConfig::setDebugInputTensors"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig20setDebugInputTensorsEb", "tensorrt_llm::executor::DebugConfig::setDebugInputTensors::debugInputTensors"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig21setDebugOutputTensorsEb", "tensorrt_llm::executor::DebugConfig::setDebugOutputTensors"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig21setDebugOutputTensorsEb", "tensorrt_llm::executor::DebugConfig::setDebugOutputTensors::debugOutputTensors"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig19setDebugTensorNamesERK9StringVec", "tensorrt_llm::executor::DebugConfig::setDebugTensorNames"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig19setDebugTensorNamesERK9StringVec", "tensorrt_llm::executor::DebugConfig::setDebugTensorNames::debugTensorNames"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig28setDebugTensorsMaxIterationsE10SizeType32", "tensorrt_llm::executor::DebugConfig::setDebugTensorsMaxIterations"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig28setDebugTensorsMaxIterationsE10SizeType32", "tensorrt_llm::executor::DebugConfig::setDebugTensorsMaxIterations::debugTensorsMaxIterations"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor24DebugTensorsPerIterationE", "tensorrt_llm::executor::DebugTensorsPerIteration"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor24DebugTensorsPerIteration12debugTensorsE", "tensorrt_llm::executor::DebugTensorsPerIteration::debugTensors"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor24DebugTensorsPerIteration4iterE", "tensorrt_llm::executor::DebugTensorsPerIteration::iter"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfigE", "tensorrt_llm::executor::DecodingConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14DecodingConfigENSt8optionalI12DecodingModeEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI13MedusaChoicesEENSt8optionalI11EagleConfigEE", "tensorrt_llm::executor::DecodingConfig::DecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14DecodingConfigENSt8optionalI12DecodingModeEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI13MedusaChoicesEENSt8optionalI11EagleConfigEE", "tensorrt_llm::executor::DecodingConfig::DecodingConfig::decodingMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14DecodingConfigENSt8optionalI12DecodingModeEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI13MedusaChoicesEENSt8optionalI11EagleConfigEE", "tensorrt_llm::executor::DecodingConfig::DecodingConfig::eagleConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14DecodingConfigENSt8optionalI12DecodingModeEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI13MedusaChoicesEENSt8optionalI11EagleConfigEE", "tensorrt_llm::executor::DecodingConfig::DecodingConfig::lookaheadDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14DecodingConfigENSt8optionalI12DecodingModeEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI13MedusaChoicesEENSt8optionalI11EagleConfigEE", "tensorrt_llm::executor::DecodingConfig::DecodingConfig::medusaChoices"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig31enableSeamlessLookaheadDecodingEv", "tensorrt_llm::executor::DecodingConfig::enableSeamlessLookaheadDecoding"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig15getDecodingModeEv", "tensorrt_llm::executor::DecodingConfig::getDecodingMode"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig14getEagleConfigEv", "tensorrt_llm::executor::DecodingConfig::getEagleConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig26getLookaheadDecodingConfigEv", "tensorrt_llm::executor::DecodingConfig::getLookaheadDecodingConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig33getLookaheadDecodingMaxNumRequestEv", "tensorrt_llm::executor::DecodingConfig::getLookaheadDecodingMaxNumRequest"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig16getMedusaChoicesEv", "tensorrt_llm::executor::DecodingConfig::getMedusaChoices"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig13mDecodingModeE", "tensorrt_llm::executor::DecodingConfig::mDecodingMode"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig12mEagleConfigE", "tensorrt_llm::executor::DecodingConfig::mEagleConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig24mLookaheadDecodingConfigE", "tensorrt_llm::executor::DecodingConfig::mLookaheadDecodingConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig31mLookaheadDecodingMaxNumRequestE", "tensorrt_llm::executor::DecodingConfig::mLookaheadDecodingMaxNumRequest"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14mMedusaChoicesE", "tensorrt_llm::executor::DecodingConfig::mMedusaChoices"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfigeqERK14DecodingConfig", "tensorrt_llm::executor::DecodingConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfigeqERK14DecodingConfig", "tensorrt_llm::executor::DecodingConfig::operator==::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig15setDecodingModeERK12DecodingMode", "tensorrt_llm::executor::DecodingConfig::setDecodingMode"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14setEagleConfigERK11EagleConfig", "tensorrt_llm::executor::DecodingConfig::setEagleConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig26setLookaheadDecodingConfigERK23LookaheadDecodingConfig", "tensorrt_llm::executor::DecodingConfig::setLookaheadDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig26setLookaheadDecodingConfigERK23LookaheadDecodingConfig", "tensorrt_llm::executor::DecodingConfig::setLookaheadDecodingConfig::lookaheadDecodingConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig16setMedusaChoicesERK13MedusaChoices", "tensorrt_llm::executor::DecodingConfig::setMedusaChoices"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor12DecodingModeE", "tensorrt_llm::executor::DecodingMode"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode4AutoEv", "tensorrt_llm::executor::DecodingMode::Auto"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode10BeamSearchEv", "tensorrt_llm::executor::DecodingMode::BeamSearch"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12DecodingModeE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::DecodingMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12DecodingModeE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::DecodingMode::state"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode5EagleEv", "tensorrt_llm::executor::DecodingMode::Eagle"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode19ExplicitDraftTokensEv", "tensorrt_llm::executor::DecodingMode::ExplicitDraftTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode19ExternalDraftTokensEv", "tensorrt_llm::executor::DecodingMode::ExternalDraftTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode9LookaheadEv", "tensorrt_llm::executor::DecodingMode::Lookahead"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode6MedusaEv", "tensorrt_llm::executor::DecodingMode::Medusa"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode4TopKEv", "tensorrt_llm::executor::DecodingMode::TopK"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode8TopKTopPEv", "tensorrt_llm::executor::DecodingMode::TopKTopP"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode4TopPEv", "tensorrt_llm::executor::DecodingMode::TopP"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode14UnderlyingTypeE", "tensorrt_llm::executor::DecodingMode::UnderlyingType"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9allBitSetE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::allBitSet"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9allBitSetE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::allBitSet::bits"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9anyBitSetE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::anyBitSet"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9anyBitSetE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::anyBitSet::bits"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode7getNameEv", "tensorrt_llm::executor::DecodingMode::getName"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode8getStateEv", "tensorrt_llm::executor::DecodingMode::getState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isAutoEv", "tensorrt_llm::executor::DecodingMode::isAuto"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isBeamSearchEv", "tensorrt_llm::executor::DecodingMode::isBeamSearch"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode7isEagleEv", "tensorrt_llm::executor::DecodingMode::isEagle"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode21isExplicitDraftTokensEv", "tensorrt_llm::executor::DecodingMode::isExplicitDraftTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode21isExternalDraftTokensEv", "tensorrt_llm::executor::DecodingMode::isExternalDraftTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode11isLookaheadEv", "tensorrt_llm::executor::DecodingMode::isLookahead"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode8isMedusaEv", "tensorrt_llm::executor::DecodingMode::isMedusa"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isTopKEv", "tensorrt_llm::executor::DecodingMode::isTopK"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode13isTopKandTopPEv", "tensorrt_llm::executor::DecodingMode::isTopKandTopP"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isTopKorTopPEv", "tensorrt_llm::executor::DecodingMode::isTopKorTopP"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isTopPEv", "tensorrt_llm::executor::DecodingMode::isTopP"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseBanTokensEv", "tensorrt_llm::executor::DecodingMode::isUseBanTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode13isUseBanWordsEv", "tensorrt_llm::executor::DecodingMode::isUseBanWords"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode20isUseExplicitEosStopEv", "tensorrt_llm::executor::DecodingMode::isUseExplicitEosStop"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode21isUseFrequencyPenaltyEv", "tensorrt_llm::executor::DecodingMode::isUseFrequencyPenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode18isUseMaxLengthStopEv", "tensorrt_llm::executor::DecodingMode::isUseMaxLengthStop"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseMinLengthEv", "tensorrt_llm::executor::DecodingMode::isUseMinLength"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9isUseMinPEv", "tensorrt_llm::executor::DecodingMode::isUseMinP"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseNoRepeatNgramSizeEv", "tensorrt_llm::executor::DecodingMode::isUseNoRepeatNgramSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseOccurrencePenaltyEv", "tensorrt_llm::executor::DecodingMode::isUseOccurrencePenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isUsePenaltyEv", "tensorrt_llm::executor::DecodingMode::isUsePenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode20isUsePresencePenaltyEv", "tensorrt_llm::executor::DecodingMode::isUsePresencePenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseRepetitionPenaltyEv", "tensorrt_llm::executor::DecodingMode::isUseRepetitionPenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode17isUseStopCriteriaEv", "tensorrt_llm::executor::DecodingMode::isUseStopCriteria"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseStopWordsEv", "tensorrt_llm::executor::DecodingMode::isUseStopWords"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode16isUseTemperatureEv", "tensorrt_llm::executor::DecodingMode::isUseTemperature"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode28isUseVariableBeamWidthSearchEv", "tensorrt_llm::executor::DecodingMode::isUseVariableBeamWidthSearch"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kAutoE", "tensorrt_llm::executor::DecodingMode::kAuto"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode11kBeamSearchE", "tensorrt_llm::executor::DecodingMode::kBeamSearch"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode6kEagleE", "tensorrt_llm::executor::DecodingMode::kEagle"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode20kExplicitDraftTokensE", "tensorrt_llm::executor::DecodingMode::kExplicitDraftTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode20kExternalDraftTokensE", "tensorrt_llm::executor::DecodingMode::kExternalDraftTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode10kLookaheadE", "tensorrt_llm::executor::DecodingMode::kLookahead"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode7kMedusaE", "tensorrt_llm::executor::DecodingMode::kMedusa"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode9kNumFlagsE", "tensorrt_llm::executor::DecodingMode::kNumFlags"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kTopKE", "tensorrt_llm::executor::DecodingMode::kTopK"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode9kTopKTopPE", "tensorrt_llm::executor::DecodingMode::kTopKTopP"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kTopPE", "tensorrt_llm::executor::DecodingMode::kTopP"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseBanTokensE", "tensorrt_llm::executor::DecodingMode::kUseBanTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12kUseBanWordsE", "tensorrt_llm::executor::DecodingMode::kUseBanWords"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode19kUseExplicitEosStopE", "tensorrt_llm::executor::DecodingMode::kUseExplicitEosStop"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode22kUseFrequencyPenaltiesE", "tensorrt_llm::executor::DecodingMode::kUseFrequencyPenalties"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode17kUseMaxLengthStopE", "tensorrt_llm::executor::DecodingMode::kUseMaxLengthStop"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseMinLengthE", "tensorrt_llm::executor::DecodingMode::kUseMinLength"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode8kUseMinPE", "tensorrt_llm::executor::DecodingMode::kUseMinP"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode21kUseNoRepeatNgramSizeE", "tensorrt_llm::executor::DecodingMode::kUseNoRepeatNgramSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode23kUseOccurrencePenaltiesE", "tensorrt_llm::executor::DecodingMode::kUseOccurrencePenalties"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUsePenaltiesE", "tensorrt_llm::executor::DecodingMode::kUsePenalties"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode21kUsePresencePenaltiesE", "tensorrt_llm::executor::DecodingMode::kUsePresencePenalties"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode23kUseRepetitionPenaltiesE", "tensorrt_llm::executor::DecodingMode::kUseRepetitionPenalties"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode24kUseStandardStopCriteriaE", "tensorrt_llm::executor::DecodingMode::kUseStandardStopCriteria"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseStopWordsE", "tensorrt_llm::executor::DecodingMode::kUseStopWords"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode15kUseTemperatureE", "tensorrt_llm::executor::DecodingMode::kUseTemperature"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode27kUseVariableBeamWidthSearchE", "tensorrt_llm::executor::DecodingMode::kUseVariableBeamWidthSearch"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode6mStateE", "tensorrt_llm::executor::DecodingMode::mState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingModeeqERK12DecodingMode", "tensorrt_llm::executor::DecodingMode::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingModeeqERK12DecodingMode", "tensorrt_llm::executor::DecodingMode::operator==::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode8setBitToE14UnderlyingTypeb", "tensorrt_llm::executor::DecodingMode::setBitTo"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode8setBitToE14UnderlyingTypeb", "tensorrt_llm::executor::DecodingMode::setBitTo::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode8setBitToE14UnderlyingTypeb", "tensorrt_llm::executor::DecodingMode::setBitTo::x"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useBanTokensEb", "tensorrt_llm::executor::DecodingMode::useBanTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useBanTokensEb", "tensorrt_llm::executor::DecodingMode::useBanTokens::banTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode11useBanWordsEb", "tensorrt_llm::executor::DecodingMode::useBanWords"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode11useBanWordsEb", "tensorrt_llm::executor::DecodingMode::useBanWords::banWords"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode18useExplicitEosStopEb", "tensorrt_llm::executor::DecodingMode::useExplicitEosStop"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode18useExplicitEosStopEb", "tensorrt_llm::executor::DecodingMode::useExplicitEosStop::explicitEosStop"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode19useFrequencyPenaltyEb", "tensorrt_llm::executor::DecodingMode::useFrequencyPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode19useFrequencyPenaltyEb", "tensorrt_llm::executor::DecodingMode::useFrequencyPenalty::usePenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode16useMaxLengthStopEb", "tensorrt_llm::executor::DecodingMode::useMaxLengthStop"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode16useMaxLengthStopEb", "tensorrt_llm::executor::DecodingMode::useMaxLengthStop::maxLengthStop"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useMinLengthEb", "tensorrt_llm::executor::DecodingMode::useMinLength"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useMinLengthEb", "tensorrt_llm::executor::DecodingMode::useMinLength::useMinLen"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode7useMinPEb", "tensorrt_llm::executor::DecodingMode::useMinP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode7useMinPEb", "tensorrt_llm::executor::DecodingMode::useMinP::useMinP"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useNoRepeatNgramSizeEb", "tensorrt_llm::executor::DecodingMode::useNoRepeatNgramSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useNoRepeatNgramSizeEb", "tensorrt_llm::executor::DecodingMode::useNoRepeatNgramSize::noRepeatNgramSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode22useOccurrencePenaltiesEb", "tensorrt_llm::executor::DecodingMode::useOccurrencePenalties"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode22useOccurrencePenaltiesEb", "tensorrt_llm::executor::DecodingMode::useOccurrencePenalties::usePenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode18usePresencePenaltyEb", "tensorrt_llm::executor::DecodingMode::usePresencePenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode18usePresencePenaltyEb", "tensorrt_llm::executor::DecodingMode::usePresencePenalty::usePenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useRepetitionPenaltyEb", "tensorrt_llm::executor::DecodingMode::useRepetitionPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useRepetitionPenaltyEb", "tensorrt_llm::executor::DecodingMode::useRepetitionPenalty::usePenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useStopWordsEb", "tensorrt_llm::executor::DecodingMode::useStopWords"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useStopWordsEb", "tensorrt_llm::executor::DecodingMode::useStopWords::stopWords"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode14useTemperatureEb", "tensorrt_llm::executor::DecodingMode::useTemperature"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode14useTemperatureEb", "tensorrt_llm::executor::DecodingMode::useTemperature::useTemp"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode26useVariableBeamWidthSearchEb", "tensorrt_llm::executor::DecodingMode::useVariableBeamWidthSearch"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode26useVariableBeamWidthSearchEb", "tensorrt_llm::executor::DecodingMode::useVariableBeamWidthSearch::useVariableBeamWidthSearch"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor22DisServingRequestStatsE", "tensorrt_llm::executor::DisServingRequestStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22DisServingRequestStats11kvCacheSizeE", "tensorrt_llm::executor::DisServingRequestStats::kvCacheSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22DisServingRequestStats17kvCacheTransferMSE", "tensorrt_llm::executor::DisServingRequestStats::kvCacheTransferMS"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfigE", "tensorrt_llm::executor::DynamicBatchConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig18DynamicBatchConfigEbb10SizeType32NSt6vectorINSt4pairI10SizeType3210SizeType32EEEE", "tensorrt_llm::executor::DynamicBatchConfig::DynamicBatchConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig18DynamicBatchConfigEbb10SizeType32NSt6vectorINSt4pairI10SizeType3210SizeType32EEEE", "tensorrt_llm::executor::DynamicBatchConfig::DynamicBatchConfig::batchSizeTable"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig18DynamicBatchConfigEbb10SizeType32NSt6vectorINSt4pairI10SizeType3210SizeType32EEEE", "tensorrt_llm::executor::DynamicBatchConfig::DynamicBatchConfig::dynamicBatchMovingAverageWindow"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig18DynamicBatchConfigEbb10SizeType32NSt6vectorINSt4pairI10SizeType3210SizeType32EEEE", "tensorrt_llm::executor::DynamicBatchConfig::DynamicBatchConfig::enableBatchSizeTuning"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig18DynamicBatchConfigEbb10SizeType32NSt6vectorINSt4pairI10SizeType3210SizeType32EEEE", "tensorrt_llm::executor::DynamicBatchConfig::DynamicBatchConfig::enableMaxNumTokensTuning"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18DynamicBatchConfig17getBatchSizeTableEv", "tensorrt_llm::executor::DynamicBatchConfig::getBatchSizeTable"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18DynamicBatchConfig34getDynamicBatchMovingAverageWindowEv", "tensorrt_llm::executor::DynamicBatchConfig::getDynamicBatchMovingAverageWindow"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18DynamicBatchConfig24getEnableBatchSizeTuningEv", "tensorrt_llm::executor::DynamicBatchConfig::getEnableBatchSizeTuning"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18DynamicBatchConfig27getEnableMaxNumTokensTuningEv", "tensorrt_llm::executor::DynamicBatchConfig::getEnableMaxNumTokensTuning"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig22kDefaultBatchSizeTableE", "tensorrt_llm::executor::DynamicBatchConfig::kDefaultBatchSizeTable"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig39kDefaultDynamicBatchMovingAverageWindowE", "tensorrt_llm::executor::DynamicBatchConfig::kDefaultDynamicBatchMovingAverageWindow"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig15mBatchSizeTableE", "tensorrt_llm::executor::DynamicBatchConfig::mBatchSizeTable"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig32mDynamicBatchMovingAverageWindowE", "tensorrt_llm::executor::DynamicBatchConfig::mDynamicBatchMovingAverageWindow"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig22mEnableBatchSizeTuningE", "tensorrt_llm::executor::DynamicBatchConfig::mEnableBatchSizeTuning"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig25mEnableMaxNumTokensTuningE", "tensorrt_llm::executor::DynamicBatchConfig::mEnableMaxNumTokensTuning"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor12EagleChoicesE", "tensorrt_llm::executor::EagleChoices"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfigE", "tensorrt_llm::executor::EagleConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig11EagleConfigENSt8optionalI12EagleChoicesEEbNSt8optionalIfEEbNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::EagleConfig::EagleConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig11EagleConfigENSt8optionalI12EagleChoicesEEbNSt8optionalIfEEbNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::EagleConfig::EagleConfig::dynamicTreeMaxTopK"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig11EagleConfigENSt8optionalI12EagleChoicesEEbNSt8optionalIfEEbNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::EagleConfig::EagleConfig::eagleChoices"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig11EagleConfigENSt8optionalI12EagleChoicesEEbNSt8optionalIfEEbNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::EagleConfig::EagleConfig::greedySampling"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig11EagleConfigENSt8optionalI12EagleChoicesEEbNSt8optionalIfEEbNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::EagleConfig::EagleConfig::posteriorThreshold"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig11EagleConfigENSt8optionalI12EagleChoicesEEbNSt8optionalIfEEbNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::EagleConfig::EagleConfig::useDynamicTree"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig19checkPosteriorValueERKNSt8optionalIfEE", "tensorrt_llm::executor::EagleConfig::checkPosteriorValue"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig19checkPosteriorValueERKNSt8optionalIfEE", "tensorrt_llm::executor::EagleConfig::checkPosteriorValue::value"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11EagleConfig21getDynamicTreeMaxTopKEv", "tensorrt_llm::executor::EagleConfig::getDynamicTreeMaxTopK"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11EagleConfig15getEagleChoicesEv", "tensorrt_llm::executor::EagleConfig::getEagleChoices"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11EagleConfig21getPosteriorThresholdEv", "tensorrt_llm::executor::EagleConfig::getPosteriorThreshold"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11EagleConfig16isGreedySamplingEv", "tensorrt_llm::executor::EagleConfig::isGreedySampling"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig19mDynamicTreeMaxTopKE", "tensorrt_llm::executor::EagleConfig::mDynamicTreeMaxTopK"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig13mEagleChoicesE", "tensorrt_llm::executor::EagleConfig::mEagleChoices"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig15mGreedySamplingE", "tensorrt_llm::executor::EagleConfig::mGreedySampling"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig19mPosteriorThresholdE", "tensorrt_llm::executor::EagleConfig::mPosteriorThreshold"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig15mUseDynamicTreeE", "tensorrt_llm::executor::EagleConfig::mUseDynamicTree"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11EagleConfigeqERK11EagleConfig", "tensorrt_llm::executor::EagleConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor11EagleConfigeqERK11EagleConfig", "tensorrt_llm::executor::EagleConfig::operator==::other"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11EagleConfig14useDynamicTreeEv", "tensorrt_llm::executor::EagleConfig::useDynamicTree"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8ExecutorE", "tensorrt_llm::executor::Executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK8Executor", "tensorrt_llm::executor::Executor::Executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERR8Executor", "tensorrt_llm::executor::Executor::Executor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::decoderEngineBuffer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::decoderJsonConfigStr"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::decoderModel"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::decoderModelPath"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::encoderEngineBuffer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::encoderJsonConfigStr"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::encoderModel"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::encoderModelPath"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor::engineBuffer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK8Executor", "tensorrt_llm::executor::Executor::Executor::executor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor::jsonConfigStr"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor::managedWeights"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::model"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::modelPath"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor::modelType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::modelType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::modelType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::modelType"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERK6IdTypeRKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt6vectorI6IdTypeEERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERK6IdTypeRKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses::requestId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt6vectorI6IdTypeEERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses::requestIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERK6IdTypeRKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses::timeout"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt6vectorI6IdTypeEERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses::timeout"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses::timeout"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Executor18canEnqueueRequestsEv", "tensorrt_llm::executor::Executor::canEnqueueRequests"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor13cancelRequestE6IdType", "tensorrt_llm::executor::Executor::cancelRequest"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor13cancelRequestE6IdType", "tensorrt_llm::executor::Executor::cancelRequest::requestId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor14enqueueRequestERK7Request", "tensorrt_llm::executor::Executor::enqueueRequest"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor14enqueueRequestERK7Request", "tensorrt_llm::executor::Executor::enqueueRequest::request"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor15enqueueRequestsERKNSt6vectorI7RequestEE", "tensorrt_llm::executor::Executor::enqueueRequests"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor15enqueueRequestsERKNSt6vectorI7RequestEE", "tensorrt_llm::executor::Executor::enqueueRequests::requests"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Executor22getKVCacheEventManagerEv", "tensorrt_llm::executor::Executor::getKVCacheEventManager"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor21getLatestDebugTensorsEv", "tensorrt_llm::executor::Executor::getLatestDebugTensors"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor23getLatestIterationStatsEv", "tensorrt_llm::executor::Executor::getLatestIterationStats"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor21getLatestRequestStatsEv", "tensorrt_llm::executor::Executor::getLatestRequestStats"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Executor20getNumResponsesReadyERKNSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Executor::getNumResponsesReady"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8Executor20getNumResponsesReadyERKNSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Executor::getNumResponsesReady::requestId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Executor13isParticipantEv", "tensorrt_llm::executor::Executor::isParticipant"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Executor5mImplE", "tensorrt_llm::executor::Executor::mImpl"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8ExecutoraSERK8Executor", "tensorrt_llm::executor::Executor::operator="], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8ExecutoraSERR8Executor", "tensorrt_llm::executor::Executor::operator="], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8ExecutoraSERK8Executor", "tensorrt_llm::executor::Executor::operator=::executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8shutdownEv", "tensorrt_llm::executor::Executor::shutdown"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8ExecutorD0Ev", "tensorrt_llm::executor::Executor::~Executor"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfigE", "tensorrt_llm::executor::ExecutorConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::additionalModelOutputs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::batchingType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::cacheTransceiverConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::debugConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::decodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::enableChunkedContext"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::enableTrtOverlap"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::extendedRuntimePerfKnobConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::gatherGenerationLogits"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::gpuWeightsPercent"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::guidedDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::iterStatsMaxIterations"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::kvCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::logitsPostProcessorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::maxBatchSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::maxBeamWidth"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::maxNumTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::maxQueueSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::maxSeqIdleMicroseconds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::normalizeLogProbs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::parallelConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::peftCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::promptTableOffloading"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::recvPollPeriodMs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::requestStatsMaxIterations"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::schedulerConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::specDecConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::useGpuDirectStorage"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getAdditionalModelOutputsEv", "tensorrt_llm::executor::ExecutorConfig::getAdditionalModelOutputs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getBatchingTypeEv", "tensorrt_llm::executor::ExecutorConfig::getBatchingType"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getCacheTransceiverConfigEv", "tensorrt_llm::executor::ExecutorConfig::getCacheTransceiverConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig14getDebugConfigEv", "tensorrt_llm::executor::ExecutorConfig::getDebugConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig17getDecodingConfigEv", "tensorrt_llm::executor::ExecutorConfig::getDecodingConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig23getEnableChunkedContextEv", "tensorrt_llm::executor::ExecutorConfig::getEnableChunkedContext"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig19getEnableTrtOverlapEv", "tensorrt_llm::executor::ExecutorConfig::getEnableTrtOverlap"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig32getExtendedRuntimePerfKnobConfigEv", "tensorrt_llm::executor::ExecutorConfig::getExtendedRuntimePerfKnobConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getGatherGenerationLogitsEv", "tensorrt_llm::executor::ExecutorConfig::getGatherGenerationLogits"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig20getGpuWeightsPercentEv", "tensorrt_llm::executor::ExecutorConfig::getGpuWeightsPercent"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig23getGuidedDecodingConfigEv", "tensorrt_llm::executor::ExecutorConfig::getGuidedDecodingConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getIterStatsMaxIterationsEv", "tensorrt_llm::executor::ExecutorConfig::getIterStatsMaxIterations"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig16getKvCacheConfigEv", "tensorrt_llm::executor::ExecutorConfig::getKvCacheConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19getKvCacheConfigRefEv", "tensorrt_llm::executor::ExecutorConfig::getKvCacheConfigRef"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig28getLogitsPostProcessorConfigEv", "tensorrt_llm::executor::ExecutorConfig::getLogitsPostProcessorConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxBatchSizeEv", "tensorrt_llm::executor::ExecutorConfig::getMaxBatchSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxBeamWidthEv", "tensorrt_llm::executor::ExecutorConfig::getMaxBeamWidth"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxNumTokensEv", "tensorrt_llm::executor::ExecutorConfig::getMaxNumTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxQueueSizeEv", "tensorrt_llm::executor::ExecutorConfig::getMaxQueueSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getMaxSeqIdleMicrosecondsEv", "tensorrt_llm::executor::ExecutorConfig::getMaxSeqIdleMicroseconds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig20getNormalizeLogProbsEv", "tensorrt_llm::executor::ExecutorConfig::getNormalizeLogProbs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig17getParallelConfigEv", "tensorrt_llm::executor::ExecutorConfig::getParallelConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig18getPeftCacheConfigEv", "tensorrt_llm::executor::ExecutorConfig::getPeftCacheConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig24getPromptTableOffloadingEv", "tensorrt_llm::executor::ExecutorConfig::getPromptTableOffloading"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig19getRecvPollPeriodMsEv", "tensorrt_llm::executor::ExecutorConfig::getRecvPollPeriodMs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig28getRequestStatsMaxIterationsEv", "tensorrt_llm::executor::ExecutorConfig::getRequestStatsMaxIterations"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig18getSchedulerConfigEv", "tensorrt_llm::executor::ExecutorConfig::getSchedulerConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig21getSchedulerConfigRefEv", "tensorrt_llm::executor::ExecutorConfig::getSchedulerConfigRef"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig16getSpecDecConfigEv", "tensorrt_llm::executor::ExecutorConfig::getSpecDecConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig22getUseGpuDirectStorageEv", "tensorrt_llm::executor::ExecutorConfig::getUseGpuDirectStorage"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig30kDefaultIterStatsMaxIterationsE", "tensorrt_llm::executor::ExecutorConfig::kDefaultIterStatsMaxIterations"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig30kDefaultMaxSeqIdleMicrosecondsE", "tensorrt_llm::executor::ExecutorConfig::kDefaultMaxSeqIdleMicroseconds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig33kDefaultRequestStatsMaxIterationsE", "tensorrt_llm::executor::ExecutorConfig::kDefaultRequestStatsMaxIterations"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mAdditionalModelOutputsE", "tensorrt_llm::executor::ExecutorConfig::mAdditionalModelOutputs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mBatchingTypeE", "tensorrt_llm::executor::ExecutorConfig::mBatchingType"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mCacheTransceiverConfigE", "tensorrt_llm::executor::ExecutorConfig::mCacheTransceiverConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig12mDebugConfigE", "tensorrt_llm::executor::ExecutorConfig::mDebugConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15mDecodingConfigE", "tensorrt_llm::executor::ExecutorConfig::mDecodingConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig21mEnableChunkedContextE", "tensorrt_llm::executor::ExecutorConfig::mEnableChunkedContext"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17mEnableTrtOverlapE", "tensorrt_llm::executor::ExecutorConfig::mEnableTrtOverlap"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig30mExtendedRuntimePerfKnobConfigE", "tensorrt_llm::executor::ExecutorConfig::mExtendedRuntimePerfKnobConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mGatherGenerationLogitsE", "tensorrt_llm::executor::ExecutorConfig::mGatherGenerationLogits"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18mGpuWeightsPercentE", "tensorrt_llm::executor::ExecutorConfig::mGpuWeightsPercent"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig21mGuidedDecodingConfigE", "tensorrt_llm::executor::ExecutorConfig::mGuidedDecodingConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mIterStatsMaxIterationsE", "tensorrt_llm::executor::ExecutorConfig::mIterStatsMaxIterations"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14mKvCacheConfigE", "tensorrt_llm::executor::ExecutorConfig::mKvCacheConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig26mLogitsPostProcessorConfigE", "tensorrt_llm::executor::ExecutorConfig::mLogitsPostProcessorConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxBatchSizeE", "tensorrt_llm::executor::ExecutorConfig::mMaxBatchSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxBeamWidthE", "tensorrt_llm::executor::ExecutorConfig::mMaxBeamWidth"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxNumTokensE", "tensorrt_llm::executor::ExecutorConfig::mMaxNumTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxQueueSizeE", "tensorrt_llm::executor::ExecutorConfig::mMaxQueueSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mMaxSeqIdleMicrosecondsE", "tensorrt_llm::executor::ExecutorConfig::mMaxSeqIdleMicroseconds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18mNormalizeLogProbsE", "tensorrt_llm::executor::ExecutorConfig::mNormalizeLogProbs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15mParallelConfigE", "tensorrt_llm::executor::ExecutorConfig::mParallelConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16mPeftCacheConfigE", "tensorrt_llm::executor::ExecutorConfig::mPeftCacheConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig22mPromptTableOffloadingE", "tensorrt_llm::executor::ExecutorConfig::mPromptTableOffloading"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17mRecvPollPeriodMsE", "tensorrt_llm::executor::ExecutorConfig::mRecvPollPeriodMs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig26mRequestStatsMaxIterationsE", "tensorrt_llm::executor::ExecutorConfig::mRequestStatsMaxIterations"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16mSchedulerConfigE", "tensorrt_llm::executor::ExecutorConfig::mSchedulerConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig26mSpeculativeDecodingConfigE", "tensorrt_llm::executor::ExecutorConfig::mSpeculativeDecodingConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20mUseGpuDirectStorageE", "tensorrt_llm::executor::ExecutorConfig::mUseGpuDirectStorage"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setAdditionalModelOutputsERKNSt6vectorI21AdditionalModelOutputEE", "tensorrt_llm::executor::ExecutorConfig::setAdditionalModelOutputs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setAdditionalModelOutputsERKNSt6vectorI21AdditionalModelOutputEE", "tensorrt_llm::executor::ExecutorConfig::setAdditionalModelOutputs::additionalModelOutputs"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setBatchingTypeE12BatchingType", "tensorrt_llm::executor::ExecutorConfig::setBatchingType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setBatchingTypeE12BatchingType", "tensorrt_llm::executor::ExecutorConfig::setBatchingType::batchingType"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setCacheTransceiverConfigERK22CacheTransceiverConfig", "tensorrt_llm::executor::ExecutorConfig::setCacheTransceiverConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setCacheTransceiverConfigERK22CacheTransceiverConfig", "tensorrt_llm::executor::ExecutorConfig::setCacheTransceiverConfig::cacheTransceiverConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14setDebugConfigERK11DebugConfig", "tensorrt_llm::executor::ExecutorConfig::setDebugConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14setDebugConfigERK11DebugConfig", "tensorrt_llm::executor::ExecutorConfig::setDebugConfig::debugConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setDecodingConfigERK14DecodingConfig", "tensorrt_llm::executor::ExecutorConfig::setDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setDecodingConfigERK14DecodingConfig", "tensorrt_llm::executor::ExecutorConfig::setDecodingConfig::decodingConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23setEnableChunkedContextEb", "tensorrt_llm::executor::ExecutorConfig::setEnableChunkedContext"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23setEnableChunkedContextEb", "tensorrt_llm::executor::ExecutorConfig::setEnableChunkedContext::enableChunkedContext"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19setEnableTrtOverlapEb", "tensorrt_llm::executor::ExecutorConfig::setEnableTrtOverlap"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19setEnableTrtOverlapEb", "tensorrt_llm::executor::ExecutorConfig::setEnableTrtOverlap::enableTrtOverlap"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig32setExtendedRuntimePerfKnobConfigERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::ExecutorConfig::setExtendedRuntimePerfKnobConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig32setExtendedRuntimePerfKnobConfigERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::ExecutorConfig::setExtendedRuntimePerfKnobConfig::extendedRuntimePerfKnobConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setGatherGenerationLogitsEb", "tensorrt_llm::executor::ExecutorConfig::setGatherGenerationLogits"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setGatherGenerationLogitsEb", "tensorrt_llm::executor::ExecutorConfig::setGatherGenerationLogits::gatherGenerationLogits"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setGpuWeightsPercentERKf", "tensorrt_llm::executor::ExecutorConfig::setGpuWeightsPercent"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setGpuWeightsPercentERKf", "tensorrt_llm::executor::ExecutorConfig::setGpuWeightsPercent::gpuWeightsPercent"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23setGuidedDecodingConfigERK20GuidedDecodingConfig", "tensorrt_llm::executor::ExecutorConfig::setGuidedDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23setGuidedDecodingConfigERK20GuidedDecodingConfig", "tensorrt_llm::executor::ExecutorConfig::setGuidedDecodingConfig::guidedDecodingConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setIterStatsMaxIterationsE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setIterStatsMaxIterations"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setIterStatsMaxIterationsE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setIterStatsMaxIterations::iterStatsMaxIterations"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16setKvCacheConfigERK13KvCacheConfig", "tensorrt_llm::executor::ExecutorConfig::setKvCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16setKvCacheConfigERK13KvCacheConfig", "tensorrt_llm::executor::ExecutorConfig::setKvCacheConfig::kvCacheConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setLogitsPostProcessorConfigERK25LogitsPostProcessorConfig", "tensorrt_llm::executor::ExecutorConfig::setLogitsPostProcessorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setLogitsPostProcessorConfigERK25LogitsPostProcessorConfig", "tensorrt_llm::executor::ExecutorConfig::setLogitsPostProcessorConfig::logitsPostProcessorConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBatchSizeE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxBatchSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBatchSizeE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxBatchSize::maxBatchSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBeamWidthE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxBeamWidth"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBeamWidthE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxBeamWidth::maxBeamWidth"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxNumTokensE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxNumTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxNumTokensE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxNumTokens::maxNumTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxQueueSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ExecutorConfig::setMaxQueueSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxQueueSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ExecutorConfig::setMaxQueueSize::maxQueueSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setMaxSeqIdleMicrosecondsE8uint64_t", "tensorrt_llm::executor::ExecutorConfig::setMaxSeqIdleMicroseconds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setMaxSeqIdleMicrosecondsE8uint64_t", "tensorrt_llm::executor::ExecutorConfig::setMaxSeqIdleMicroseconds::maxSeqIdleMicroseconds"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setNormalizeLogProbsEb", "tensorrt_llm::executor::ExecutorConfig::setNormalizeLogProbs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setNormalizeLogProbsEb", "tensorrt_llm::executor::ExecutorConfig::setNormalizeLogProbs::normalizeLogProbs"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setParallelConfigERK14ParallelConfig", "tensorrt_llm::executor::ExecutorConfig::setParallelConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setParallelConfigERK14ParallelConfig", "tensorrt_llm::executor::ExecutorConfig::setParallelConfig::parallelConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setPeftCacheConfigERK15PeftCacheConfig", "tensorrt_llm::executor::ExecutorConfig::setPeftCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setPeftCacheConfigERK15PeftCacheConfig", "tensorrt_llm::executor::ExecutorConfig::setPeftCacheConfig::peftCacheConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig24setPromptTableOffloadingEb", "tensorrt_llm::executor::ExecutorConfig::setPromptTableOffloading"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig24setPromptTableOffloadingEb", "tensorrt_llm::executor::ExecutorConfig::setPromptTableOffloading::promptTableOffloading"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19setRecvPollPeriodMsERK10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setRecvPollPeriodMs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19setRecvPollPeriodMsERK10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setRecvPollPeriodMs::recvPollPeriodMs"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setRequestStatsMaxIterationsE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setRequestStatsMaxIterations"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setRequestStatsMaxIterationsE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setRequestStatsMaxIterations::requestStatsMaxIterations"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setSchedulerConfigERK15SchedulerConfig", "tensorrt_llm::executor::ExecutorConfig::setSchedulerConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setSchedulerConfigERK15SchedulerConfig", "tensorrt_llm::executor::ExecutorConfig::setSchedulerConfig::schedulerConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16setSpecDecConfigERK25SpeculativeDecodingConfig", "tensorrt_llm::executor::ExecutorConfig::setSpecDecConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16setSpecDecConfigERK25SpeculativeDecodingConfig", "tensorrt_llm::executor::ExecutorConfig::setSpecDecConfig::specDecConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig22setUseGpuDirectStorageERKb", "tensorrt_llm::executor::ExecutorConfig::setUseGpuDirectStorage"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig22setUseGpuDirectStorageERKb", "tensorrt_llm::executor::ExecutorConfig::setUseGpuDirectStorage::useGpuDirectStorage"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfigE", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig29ExtendedRuntimePerfKnobConfigEbbb10SizeType32", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::ExtendedRuntimePerfKnobConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig29ExtendedRuntimePerfKnobConfigEbbb10SizeType32", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::ExtendedRuntimePerfKnobConfig::cudaGraphCacheSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig29ExtendedRuntimePerfKnobConfigEbbb10SizeType32", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::ExtendedRuntimePerfKnobConfig::cudaGraphMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig29ExtendedRuntimePerfKnobConfigEbbb10SizeType32", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::ExtendedRuntimePerfKnobConfig::enableContextFMHAFP32Acc"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig29ExtendedRuntimePerfKnobConfigEbbb10SizeType32", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::ExtendedRuntimePerfKnobConfig::multiBlockMode"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig21getCudaGraphCacheSizeEv", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::getCudaGraphCacheSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig16getCudaGraphModeEv", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::getCudaGraphMode"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig27getEnableContextFMHAFP32AccEv", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::getEnableContextFMHAFP32Acc"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig17getMultiBlockModeEv", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::getMultiBlockMode"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig19mCudaGraphCacheSizeE", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::mCudaGraphCacheSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig14mCudaGraphModeE", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::mCudaGraphMode"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig25mEnableContextFMHAFP32AccE", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::mEnableContextFMHAFP32Acc"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig15mMultiBlockModeE", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::mMultiBlockMode"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfigeqERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfigeqERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::operator==::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig21setCudaGraphCacheSizeE10SizeType32", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setCudaGraphCacheSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig21setCudaGraphCacheSizeE10SizeType32", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setCudaGraphCacheSize::cacheSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig16setCudaGraphModeEb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setCudaGraphMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig16setCudaGraphModeEb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setCudaGraphMode::cudaGraphMode"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig27setEnableContextFMHAFP32AccEb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setEnableContextFMHAFP32Acc"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig27setEnableContextFMHAFP32AccEb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setEnableContextFMHAFP32Acc::enableContextFMHAFP32Acc"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig17setMultiBlockModeEb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setMultiBlockMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig17setMultiBlockModeEb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setMultiBlockMode::multiBlockMode"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfigE", "tensorrt_llm::executor::ExternalDraftTokensConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig25ExternalDraftTokensConfigE9VecTokensNSt8optionalI6TensorEERKNSt8optionalI9FloatTypeEERKNSt8optionalIbEE", "tensorrt_llm::executor::ExternalDraftTokensConfig::ExternalDraftTokensConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig25ExternalDraftTokensConfigE9VecTokensNSt8optionalI6TensorEERKNSt8optionalI9FloatTypeEERKNSt8optionalIbEE", "tensorrt_llm::executor::ExternalDraftTokensConfig::ExternalDraftTokensConfig::acceptanceThreshold"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig25ExternalDraftTokensConfigE9VecTokensNSt8optionalI6TensorEERKNSt8optionalI9FloatTypeEERKNSt8optionalIbEE", "tensorrt_llm::executor::ExternalDraftTokensConfig::ExternalDraftTokensConfig::fastLogits"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig25ExternalDraftTokensConfigE9VecTokensNSt8optionalI6TensorEERKNSt8optionalI9FloatTypeEERKNSt8optionalIbEE", "tensorrt_llm::executor::ExternalDraftTokensConfig::ExternalDraftTokensConfig::logits"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig25ExternalDraftTokensConfigE9VecTokensNSt8optionalI6TensorEERKNSt8optionalI9FloatTypeEERKNSt8optionalIbEE", "tensorrt_llm::executor::ExternalDraftTokensConfig::ExternalDraftTokensConfig::tokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig22getAcceptanceThresholdEv", "tensorrt_llm::executor::ExternalDraftTokensConfig::getAcceptanceThreshold"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig13getFastLogitsEv", "tensorrt_llm::executor::ExternalDraftTokensConfig::getFastLogits"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig9getLogitsEv", "tensorrt_llm::executor::ExternalDraftTokensConfig::getLogits"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig9getTokensEv", "tensorrt_llm::executor::ExternalDraftTokensConfig::getTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig20mAcceptanceThresholdE", "tensorrt_llm::executor::ExternalDraftTokensConfig::mAcceptanceThreshold"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig11mFastLogitsE", "tensorrt_llm::executor::ExternalDraftTokensConfig::mFastLogits"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig7mLogitsE", "tensorrt_llm::executor::ExternalDraftTokensConfig::mLogits"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig7mTokensE", "tensorrt_llm::executor::ExternalDraftTokensConfig::mTokens"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12FinishReasonE", "tensorrt_llm::executor::FinishReason"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12FinishReason10kCANCELLEDE", "tensorrt_llm::executor::FinishReason::kCANCELLED"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12FinishReason7kEND_IDE", "tensorrt_llm::executor::FinishReason::kEND_ID"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12FinishReason7kLENGTHE", "tensorrt_llm::executor::FinishReason::kLENGTH"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12FinishReason13kNOT_FINISHEDE", "tensorrt_llm::executor::FinishReason::kNOT_FINISHED"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12FinishReason11kSTOP_WORDSE", "tensorrt_llm::executor::FinishReason::kSTOP_WORDS"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12FinishReason10kTIMED_OUTE", "tensorrt_llm::executor::FinishReason::kTIMED_OUT"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor9FloatTypeE", "tensorrt_llm::executor::FloatType"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfigE", "tensorrt_llm::executor::GuidedDecodingConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig21GuidedDecodingBackendE", "tensorrt_llm::executor::GuidedDecodingConfig::GuidedDecodingBackend"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig21GuidedDecodingBackend11kLLGUIDANCEE", "tensorrt_llm::executor::GuidedDecodingConfig::GuidedDecodingBackend::kLLGUIDANCE"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig21GuidedDecodingBackend9kXGRAMMARE", "tensorrt_llm::executor::GuidedDecodingConfig::GuidedDecodingBackend::kXGRAMMAR"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig20GuidedDecodingConfigE21GuidedDecodingBackendNSt8optionalINSt6vectorINSt6stringEEEEENSt8optionalINSt6stringEEENSt8optionalINSt6vectorI11TokenIdTypeEEEE", "tensorrt_llm::executor::GuidedDecodingConfig::GuidedDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig20GuidedDecodingConfigE21GuidedDecodingBackendNSt8optionalINSt6vectorINSt6stringEEEEENSt8optionalINSt6stringEEENSt8optionalINSt6vectorI11TokenIdTypeEEEE", "tensorrt_llm::executor::GuidedDecodingConfig::GuidedDecodingConfig::backend"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig20GuidedDecodingConfigE21GuidedDecodingBackendNSt8optionalINSt6vectorINSt6stringEEEEENSt8optionalINSt6stringEEENSt8optionalINSt6vectorI11TokenIdTypeEEEE", "tensorrt_llm::executor::GuidedDecodingConfig::GuidedDecodingConfig::encodedVocab"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig20GuidedDecodingConfigE21GuidedDecodingBackendNSt8optionalINSt6vectorINSt6stringEEEEENSt8optionalINSt6stringEEENSt8optionalINSt6vectorI11TokenIdTypeEEEE", "tensorrt_llm::executor::GuidedDecodingConfig::GuidedDecodingConfig::stopTokenIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig20GuidedDecodingConfigE21GuidedDecodingBackendNSt8optionalINSt6vectorINSt6stringEEEEENSt8optionalINSt6stringEEENSt8optionalINSt6vectorI11TokenIdTypeEEEE", "tensorrt_llm::executor::GuidedDecodingConfig::GuidedDecodingConfig::tokenizerStr"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig10getBackendEv", "tensorrt_llm::executor::GuidedDecodingConfig::getBackend"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig15getEncodedVocabEv", "tensorrt_llm::executor::GuidedDecodingConfig::getEncodedVocab"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig15getStopTokenIdsEv", "tensorrt_llm::executor::GuidedDecodingConfig::getStopTokenIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig15getTokenizerStrEv", "tensorrt_llm::executor::GuidedDecodingConfig::getTokenizerStr"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig8mBackendE", "tensorrt_llm::executor::GuidedDecodingConfig::mBackend"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig13mEncodedVocabE", "tensorrt_llm::executor::GuidedDecodingConfig::mEncodedVocab"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig13mStopTokenIdsE", "tensorrt_llm::executor::GuidedDecodingConfig::mStopTokenIds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig13mTokenizerStrE", "tensorrt_llm::executor::GuidedDecodingConfig::mTokenizerStr"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfigeqERK20GuidedDecodingConfig", "tensorrt_llm::executor::GuidedDecodingConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfigeqERK20GuidedDecodingConfig", "tensorrt_llm::executor::GuidedDecodingConfig::operator==::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig10setBackendERK21GuidedDecodingBackend", "tensorrt_llm::executor::GuidedDecodingConfig::setBackend"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig10setBackendERK21GuidedDecodingBackend", "tensorrt_llm::executor::GuidedDecodingConfig::setBackend::backend"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setEncodedVocabERKNSt6vectorINSt6stringEEE", "tensorrt_llm::executor::GuidedDecodingConfig::setEncodedVocab"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setEncodedVocabERKNSt6vectorINSt6stringEEE", "tensorrt_llm::executor::GuidedDecodingConfig::setEncodedVocab::encodedVocab"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setStopTokenIdsERKNSt6vectorI11TokenIdTypeEE", "tensorrt_llm::executor::GuidedDecodingConfig::setStopTokenIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setStopTokenIdsERKNSt6vectorI11TokenIdTypeEE", "tensorrt_llm::executor::GuidedDecodingConfig::setStopTokenIds::stopTokenIds"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setTokenizerStrERKNSt6stringE", "tensorrt_llm::executor::GuidedDecodingConfig::setTokenizerStr"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setTokenizerStrERKNSt6stringE", "tensorrt_llm::executor::GuidedDecodingConfig::setTokenizerStr::tokenizerStr"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig8validateEv", "tensorrt_llm::executor::GuidedDecodingConfig::validate"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParamsE", "tensorrt_llm::executor::GuidedDecodingParams"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideTypeE", "tensorrt_llm::executor::GuidedDecodingParams::GuideType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType13kEBNF_GRAMMARE", "tensorrt_llm::executor::GuidedDecodingParams::GuideType::kEBNF_GRAMMAR"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType5kJSONE", "tensorrt_llm::executor::GuidedDecodingParams::GuideType::kJSON"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType12kJSON_SCHEMAE", "tensorrt_llm::executor::GuidedDecodingParams::GuideType::kJSON_SCHEMA"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType6kREGEXE", "tensorrt_llm::executor::GuidedDecodingParams::GuideType::kREGEX"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType15kSTRUCTURAL_TAGE", "tensorrt_llm::executor::GuidedDecodingParams::GuideType::kSTRUCTURAL_TAG"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams20GuidedDecodingParamsE9GuideTypeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::GuidedDecodingParams::GuidedDecodingParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams20GuidedDecodingParamsE9GuideTypeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::GuidedDecodingParams::GuidedDecodingParams::guide"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams20GuidedDecodingParamsE9GuideTypeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::GuidedDecodingParams::GuidedDecodingParams::guideType"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingParams8getGuideEv", "tensorrt_llm::executor::GuidedDecodingParams::getGuide"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingParams12getGuideTypeEv", "tensorrt_llm::executor::GuidedDecodingParams::getGuideType"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams6mGuideE", "tensorrt_llm::executor::GuidedDecodingParams::mGuide"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams10mGuideTypeE", "tensorrt_llm::executor::GuidedDecodingParams::mGuideType"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingParamseqERK20GuidedDecodingParams", "tensorrt_llm::executor::GuidedDecodingParams::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingParamseqERK20GuidedDecodingParams", "tensorrt_llm::executor::GuidedDecodingParams::operator==::other"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor6IdTypeE", "tensorrt_llm::executor::IdType"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStatsE", "tensorrt_llm::executor::InflightBatchingStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats26avgNumDecodedTokensPerIterE", "tensorrt_llm::executor::InflightBatchingStats::avgNumDecodedTokensPerIter"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats12microBatchIdE", "tensorrt_llm::executor::InflightBatchingStats::microBatchId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats18numContextRequestsE", "tensorrt_llm::executor::InflightBatchingStats::numContextRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats12numCtxTokensE", "tensorrt_llm::executor::InflightBatchingStats::numCtxTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats14numGenRequestsE", "tensorrt_llm::executor::InflightBatchingStats::numGenRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats17numPausedRequestsE", "tensorrt_llm::executor::InflightBatchingStats::numPausedRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats20numScheduledRequestsE", "tensorrt_llm::executor::InflightBatchingStats::numScheduledRequests"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor14IterationStatsE", "tensorrt_llm::executor::IterationStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats11cpuMemUsageE", "tensorrt_llm::executor::IterationStats::cpuMemUsage"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats17crossKvCacheStatsE", "tensorrt_llm::executor::IterationStats::crossKvCacheStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats11gpuMemUsageE", "tensorrt_llm::executor::IterationStats::gpuMemUsage"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats21inflightBatchingStatsE", "tensorrt_llm::executor::IterationStats::inflightBatchingStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats4iterE", "tensorrt_llm::executor::IterationStats::iter"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats13iterLatencyMSE", "tensorrt_llm::executor::IterationStats::iterLatencyMS"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats12kvCacheStatsE", "tensorrt_llm::executor::IterationStats::kvCacheStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats19maxBatchSizeRuntimeE", "tensorrt_llm::executor::IterationStats::maxBatchSizeRuntime"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats18maxBatchSizeStaticE", "tensorrt_llm::executor::IterationStats::maxBatchSizeStatic"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats28maxBatchSizeTunerRecommendedE", "tensorrt_llm::executor::IterationStats::maxBatchSizeTunerRecommended"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats20maxNumActiveRequestsE", "tensorrt_llm::executor::IterationStats::maxNumActiveRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats19maxNumTokensRuntimeE", "tensorrt_llm::executor::IterationStats::maxNumTokensRuntime"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats18maxNumTokensStaticE", "tensorrt_llm::executor::IterationStats::maxNumTokensStatic"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats28maxNumTokensTunerRecommendedE", "tensorrt_llm::executor::IterationStats::maxNumTokensTunerRecommended"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats31newActiveRequestsQueueLatencyMSE", "tensorrt_llm::executor::IterationStats::newActiveRequestsQueueLatencyMS"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats17numActiveRequestsE", "tensorrt_llm::executor::IterationStats::numActiveRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats20numCompletedRequestsE", "tensorrt_llm::executor::IterationStats::numCompletedRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats20numNewActiveRequestsE", "tensorrt_llm::executor::IterationStats::numNewActiveRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats17numQueuedRequestsE", "tensorrt_llm::executor::IterationStats::numQueuedRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats14pinnedMemUsageE", "tensorrt_llm::executor::IterationStats::pinnedMemUsage"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats17specDecodingStatsE", "tensorrt_llm::executor::IterationStats::specDecodingStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats19staticBatchingStatsE", "tensorrt_llm::executor::IterationStats::staticBatchingStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats9timestampE", "tensorrt_llm::executor::IterationStats::timestamp"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor13IterationTypeE", "tensorrt_llm::executor::IterationType"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerializationE", "tensorrt_llm::executor::JsonSerialization"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK12RequestStats", "tensorrt_llm::executor::JsonSerialization::toJsonStr"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK14IterationStats", "tensorrt_llm::executor::JsonSerialization::toJsonStr"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK24RequestStatsPerIteration", "tensorrt_llm::executor::JsonSerialization::toJsonStr"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK14IterationStats", "tensorrt_llm::executor::JsonSerialization::toJsonStr::iterationStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK12RequestStats", "tensorrt_llm::executor::JsonSerialization::toJsonStr::requestStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK24RequestStatsPerIteration", "tensorrt_llm::executor::JsonSerialization::toJsonStr::requestStatsPerIter"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheCreatedDataE", "tensorrt_llm::executor::KVCacheCreatedData"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheCreatedData22numBlocksPerCacheLevelE", "tensorrt_llm::executor::KVCacheCreatedData::numBlocksPerCacheLevel"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor12KVCacheEventE", "tensorrt_llm::executor::KVCacheEvent"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent12KVCacheEventE6IdType16KVCacheEventData10SizeType32", "tensorrt_llm::executor::KVCacheEvent::KVCacheEvent"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent12KVCacheEventE6IdType16KVCacheEventData10SizeType32", "tensorrt_llm::executor::KVCacheEvent::KVCacheEvent::data"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent12KVCacheEventE6IdType16KVCacheEventData10SizeType32", "tensorrt_llm::executor::KVCacheEvent::KVCacheEvent::eventId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent12KVCacheEventE6IdType16KVCacheEventData10SizeType32", "tensorrt_llm::executor::KVCacheEvent::KVCacheEvent::windowSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent4dataE", "tensorrt_llm::executor::KVCacheEvent::data"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent7eventIdE", "tensorrt_llm::executor::KVCacheEvent::eventId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent10windowSizeE", "tensorrt_llm::executor::KVCacheEvent::windowSize"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor16KVCacheEventDataE", "tensorrt_llm::executor::KVCacheEventData"], [0, 2, 1, "_CPPv4I0EN12tensorrt_llm8executor16KVCacheEventDiffE", "tensorrt_llm::executor::KVCacheEventDiff"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor16KVCacheEventDiffE", "tensorrt_llm::executor::KVCacheEventDiff::T"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor16KVCacheEventDiff8newValueE", "tensorrt_llm::executor::KVCacheEventDiff::newValue"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor16KVCacheEventDiff8oldValueE", "tensorrt_llm::executor::KVCacheEventDiff::oldValue"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManagerE", "tensorrt_llm::executor::KVCacheEventManager"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManager19KVCacheEventManagerENSt10shared_ptrIN12tensorrt_llm13batch_manager16kv_cache_manager18BaseKVCacheManagerEEE", "tensorrt_llm::executor::KVCacheEventManager::KVCacheEventManager"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManager19KVCacheEventManagerENSt10shared_ptrIN12tensorrt_llm13batch_manager16kv_cache_manager18BaseKVCacheManagerEEE", "tensorrt_llm::executor::KVCacheEventManager::KVCacheEventManager::kvCacheManager"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManager15getLatestEventsENSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::KVCacheEventManager::getLatestEvents"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManager15getLatestEventsENSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::KVCacheEventManager::getLatestEvents::timeout"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManager14kvCacheManagerE", "tensorrt_llm::executor::KVCacheEventManager::kvCacheManager"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheRemovedDataE", "tensorrt_llm::executor::KVCacheRemovedData"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheRemovedData11blockHashesE", "tensorrt_llm::executor::KVCacheRemovedData::blockHashes"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockDataE", "tensorrt_llm::executor::KVCacheStoredBlockData"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData22KVCacheStoredBlockDataE6IdTypeN12tensorrt_llm7runtime15VecUniqueTokensENSt8optionalIN12tensorrt_llm7runtime14LoraTaskIdTypeEEE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheStoredBlockData::KVCacheStoredBlockData"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData22KVCacheStoredBlockDataE6IdTypeN12tensorrt_llm7runtime15VecUniqueTokensENSt8optionalIN12tensorrt_llm7runtime14LoraTaskIdTypeEEE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheStoredBlockData::KVCacheStoredBlockData::blockHash"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData22KVCacheStoredBlockDataE6IdTypeN12tensorrt_llm7runtime15VecUniqueTokensENSt8optionalIN12tensorrt_llm7runtime14LoraTaskIdTypeEEE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheStoredBlockData::KVCacheStoredBlockData::cacheLevel"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData22KVCacheStoredBlockDataE6IdTypeN12tensorrt_llm7runtime15VecUniqueTokensENSt8optionalIN12tensorrt_llm7runtime14LoraTaskIdTypeEEE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheStoredBlockData::KVCacheStoredBlockData::loraId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData22KVCacheStoredBlockDataE6IdTypeN12tensorrt_llm7runtime15VecUniqueTokensENSt8optionalIN12tensorrt_llm7runtime14LoraTaskIdTypeEEE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheStoredBlockData::KVCacheStoredBlockData::priority"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData22KVCacheStoredBlockDataE6IdTypeN12tensorrt_llm7runtime15VecUniqueTokensENSt8optionalIN12tensorrt_llm7runtime14LoraTaskIdTypeEEE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheStoredBlockData::KVCacheStoredBlockData::tokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData9blockHashE", "tensorrt_llm::executor::KVCacheStoredBlockData::blockHash"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData10cacheLevelE", "tensorrt_llm::executor::KVCacheStoredBlockData::cacheLevel"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData6loraIdE", "tensorrt_llm::executor::KVCacheStoredBlockData::loraId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData8priorityE", "tensorrt_llm::executor::KVCacheStoredBlockData::priority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData6tokensE", "tensorrt_llm::executor::KVCacheStoredBlockData::tokens"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor17KVCacheStoredDataE", "tensorrt_llm::executor::KVCacheStoredData"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17KVCacheStoredData6blocksE", "tensorrt_llm::executor::KVCacheStoredData::blocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17KVCacheStoredData10parentHashE", "tensorrt_llm::executor::KVCacheStoredData::parentHash"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedDataE", "tensorrt_llm::executor::KVCacheUpdatedData"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData18KVCacheUpdatedDataE6IdType", "tensorrt_llm::executor::KVCacheUpdatedData::KVCacheUpdatedData"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData18KVCacheUpdatedDataE6IdType", "tensorrt_llm::executor::KVCacheUpdatedData::KVCacheUpdatedData::blockHash"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData9blockHashE", "tensorrt_llm::executor::KVCacheUpdatedData::blockHash"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData10cacheLevelE", "tensorrt_llm::executor::KVCacheUpdatedData::cacheLevel"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData17cacheLevelUpdatedE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheUpdatedData::cacheLevelUpdated"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData17cacheLevelUpdatedE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheUpdatedData::cacheLevelUpdated::newValue"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData17cacheLevelUpdatedE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheUpdatedData::cacheLevelUpdated::oldValue"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData8priorityE", "tensorrt_llm::executor::KVCacheUpdatedData::priority"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData15priorityUpdatedE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheUpdatedData::priorityUpdated"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData15priorityUpdatedE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheUpdatedData::priorityUpdated::newValue"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData15priorityUpdatedE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheUpdatedData::priorityUpdated::oldValue"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfigE", "tensorrt_llm::executor::KvCacheConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::copyOnPartialReuse"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::crossKvCacheFraction"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::enableBlockReuse"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::enablePartialReuse"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::eventBufferMaxSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::freeGpuMemoryFraction"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::hostCacheSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::maxAttentionWindowVec"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::maxTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::onboardBlocks"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::runtimeDefaults"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::secondaryOffloadMinPriority"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::sinkTokenLength"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::useUvm"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig34fillEmptyFieldsFromRuntimeDefaultsERKN12tensorrt_llm7runtime15RuntimeDefaultsE", "tensorrt_llm::executor::KvCacheConfig::fillEmptyFieldsFromRuntimeDefaults"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig34fillEmptyFieldsFromRuntimeDefaultsERKN12tensorrt_llm7runtime15RuntimeDefaultsE", "tensorrt_llm::executor::KvCacheConfig::fillEmptyFieldsFromRuntimeDefaults::runtimeDefaults"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig21getCopyOnPartialReuseEv", "tensorrt_llm::executor::KvCacheConfig::getCopyOnPartialReuse"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig23getCrossKvCacheFractionEv", "tensorrt_llm::executor::KvCacheConfig::getCrossKvCacheFraction"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig19getEnableBlockReuseEv", "tensorrt_llm::executor::KvCacheConfig::getEnableBlockReuse"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig21getEnablePartialReuseEv", "tensorrt_llm::executor::KvCacheConfig::getEnablePartialReuse"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig21getEventBufferMaxSizeEv", "tensorrt_llm::executor::KvCacheConfig::getEventBufferMaxSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig24getFreeGpuMemoryFractionEv", "tensorrt_llm::executor::KvCacheConfig::getFreeGpuMemoryFraction"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig16getHostCacheSizeEv", "tensorrt_llm::executor::KvCacheConfig::getHostCacheSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig24getMaxAttentionWindowVecEv", "tensorrt_llm::executor::KvCacheConfig::getMaxAttentionWindowVec"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig12getMaxTokensEv", "tensorrt_llm::executor::KvCacheConfig::getMaxTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig16getOnboardBlocksEv", "tensorrt_llm::executor::KvCacheConfig::getOnboardBlocks"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig30getSecondaryOffloadMinPriorityEv", "tensorrt_llm::executor::KvCacheConfig::getSecondaryOffloadMinPriority"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig18getSinkTokenLengthEv", "tensorrt_llm::executor::KvCacheConfig::getSinkTokenLength"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig9getUseUvmEv", "tensorrt_llm::executor::KvCacheConfig::getUseUvm"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig22kDefaultGpuMemFractionE", "tensorrt_llm::executor::KvCacheConfig::kDefaultGpuMemFraction"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19mCopyOnPartialReuseE", "tensorrt_llm::executor::KvCacheConfig::mCopyOnPartialReuse"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21mCrossKvCacheFractionE", "tensorrt_llm::executor::KvCacheConfig::mCrossKvCacheFraction"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig17mEnableBlockReuseE", "tensorrt_llm::executor::KvCacheConfig::mEnableBlockReuse"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19mEnablePartialReuseE", "tensorrt_llm::executor::KvCacheConfig::mEnablePartialReuse"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19mEventBufferMaxSizeE", "tensorrt_llm::executor::KvCacheConfig::mEventBufferMaxSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig22mFreeGpuMemoryFractionE", "tensorrt_llm::executor::KvCacheConfig::mFreeGpuMemoryFraction"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig14mHostCacheSizeE", "tensorrt_llm::executor::KvCacheConfig::mHostCacheSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig22mMaxAttentionWindowVecE", "tensorrt_llm::executor::KvCacheConfig::mMaxAttentionWindowVec"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig10mMaxTokensE", "tensorrt_llm::executor::KvCacheConfig::mMaxTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig14mOnboardBlocksE", "tensorrt_llm::executor::KvCacheConfig::mOnboardBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig28mSecondaryOffloadMinPriorityE", "tensorrt_llm::executor::KvCacheConfig::mSecondaryOffloadMinPriority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16mSinkTokenLengthE", "tensorrt_llm::executor::KvCacheConfig::mSinkTokenLength"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig7mUseUvmE", "tensorrt_llm::executor::KvCacheConfig::mUseUvm"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setCopyOnPartialReuseEb", "tensorrt_llm::executor::KvCacheConfig::setCopyOnPartialReuse"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setCopyOnPartialReuseEb", "tensorrt_llm::executor::KvCacheConfig::setCopyOnPartialReuse::copyOnPartialReuse"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig23setCrossKvCacheFractionE9FloatType", "tensorrt_llm::executor::KvCacheConfig::setCrossKvCacheFraction"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig23setCrossKvCacheFractionE9FloatType", "tensorrt_llm::executor::KvCacheConfig::setCrossKvCacheFraction::crossKvCacheFraction"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19setEnableBlockReuseEb", "tensorrt_llm::executor::KvCacheConfig::setEnableBlockReuse"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19setEnableBlockReuseEb", "tensorrt_llm::executor::KvCacheConfig::setEnableBlockReuse::enableBlockReuse"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setEnablePartialReuseEb", "tensorrt_llm::executor::KvCacheConfig::setEnablePartialReuse"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setEnablePartialReuseEb", "tensorrt_llm::executor::KvCacheConfig::setEnablePartialReuse::enablePartialReuse"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setEventBufferMaxSizeE6size_t", "tensorrt_llm::executor::KvCacheConfig::setEventBufferMaxSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setEventBufferMaxSizeE6size_t", "tensorrt_llm::executor::KvCacheConfig::setEventBufferMaxSize::eventBufferMaxSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setFreeGpuMemoryFractionE9FloatType", "tensorrt_llm::executor::KvCacheConfig::setFreeGpuMemoryFraction"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setFreeGpuMemoryFractionE9FloatType", "tensorrt_llm::executor::KvCacheConfig::setFreeGpuMemoryFraction::freeGpuMemoryFraction"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setHostCacheSizeE6size_t", "tensorrt_llm::executor::KvCacheConfig::setHostCacheSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setHostCacheSizeE6size_t", "tensorrt_llm::executor::KvCacheConfig::setHostCacheSize::hostCacheSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setMaxAttentionWindowVecENSt6vectorI10SizeType32EE", "tensorrt_llm::executor::KvCacheConfig::setMaxAttentionWindowVec"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setMaxAttentionWindowVecENSt6vectorI10SizeType32EE", "tensorrt_llm::executor::KvCacheConfig::setMaxAttentionWindowVec::maxAttentionWindowVec"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig12setMaxTokensE10SizeType32", "tensorrt_llm::executor::KvCacheConfig::setMaxTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig12setMaxTokensE10SizeType32", "tensorrt_llm::executor::KvCacheConfig::setMaxTokens::maxTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setOnboardBlocksEb", "tensorrt_llm::executor::KvCacheConfig::setOnboardBlocks"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setOnboardBlocksEb", "tensorrt_llm::executor::KvCacheConfig::setOnboardBlocks::onboardBlocks"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig30setSecondaryOffloadMinPriorityENSt8optionalI17RetentionPriorityEE", "tensorrt_llm::executor::KvCacheConfig::setSecondaryOffloadMinPriority"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig30setSecondaryOffloadMinPriorityENSt8optionalI17RetentionPriorityEE", "tensorrt_llm::executor::KvCacheConfig::setSecondaryOffloadMinPriority::secondaryOffloadMinPriority"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig18setSinkTokenLengthE10SizeType32", "tensorrt_llm::executor::KvCacheConfig::setSinkTokenLength"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig18setSinkTokenLengthE10SizeType32", "tensorrt_llm::executor::KvCacheConfig::setSinkTokenLength::sinkTokenLength"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig9setUseUvmEb", "tensorrt_llm::executor::KvCacheConfig::setUseUvm"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig9setUseUvmEb", "tensorrt_llm::executor::KvCacheConfig::setUseUvm::useUvm"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfigE", "tensorrt_llm::executor::KvCacheRetentionConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigERKNSt6vectorI25TokenRangeRetentionConfigEE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE19KvCacheTransferModeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::KvCacheRetentionConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigEv", "tensorrt_llm::executor::KvCacheRetentionConfig::KvCacheRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigERKNSt6vectorI25TokenRangeRetentionConfigEE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE19KvCacheTransferModeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::KvCacheRetentionConfig::decodeDurationMs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigERKNSt6vectorI25TokenRangeRetentionConfigEE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE19KvCacheTransferModeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::KvCacheRetentionConfig::decodeRetentionPriority"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigERKNSt6vectorI25TokenRangeRetentionConfigEE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE19KvCacheTransferModeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::KvCacheRetentionConfig::directory"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigERKNSt6vectorI25TokenRangeRetentionConfigEE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE19KvCacheTransferModeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::KvCacheRetentionConfig::tokenRangeRetentionPriorities"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigERKNSt6vectorI25TokenRangeRetentionConfigEE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE19KvCacheTransferModeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::KvCacheRetentionConfig::transferMode"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfigE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig25TokenRangeRetentionConfigE10SizeType32NSt8optionalI10SizeType32EE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::TokenRangeRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig25TokenRangeRetentionConfigE10SizeType32NSt8optionalI10SizeType32EE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::TokenRangeRetentionConfig::durationMs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig25TokenRangeRetentionConfigE10SizeType32NSt8optionalI10SizeType32EE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::TokenRangeRetentionConfig::priority"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig25TokenRangeRetentionConfigE10SizeType32NSt8optionalI10SizeType32EE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::TokenRangeRetentionConfig::tokenEnd"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig25TokenRangeRetentionConfigE10SizeType32NSt8optionalI10SizeType32EE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::TokenRangeRetentionConfig::tokenStart"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig10durationMsE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::durationMs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfigeqERK25TokenRangeRetentionConfig", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfigeqERK25TokenRangeRetentionConfig", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::operator==::other"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig8priorityE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::priority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig8tokenEndE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::tokenEnd"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig10tokenStartE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::tokenStart"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig19getDecodeDurationMsEv", "tensorrt_llm::executor::KvCacheRetentionConfig::getDecodeDurationMs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig26getDecodeRetentionPriorityEv", "tensorrt_llm::executor::KvCacheRetentionConfig::getDecodeRetentionPriority"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig12getDirectoryEv", "tensorrt_llm::executor::KvCacheRetentionConfig::getDirectory"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig36getPerBlockRetentionPriorityDurationE10SizeType3210SizeType32", "tensorrt_llm::executor::KvCacheRetentionConfig::getPerBlockRetentionPriorityDuration"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig36getPerBlockRetentionPriorityDurationE10SizeType3210SizeType32", "tensorrt_llm::executor::KvCacheRetentionConfig::getPerBlockRetentionPriorityDuration::blockSize"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig36getPerBlockRetentionPriorityDurationE10SizeType3210SizeType32", "tensorrt_llm::executor::KvCacheRetentionConfig::getPerBlockRetentionPriorityDuration::seqLen"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig29getTokenRangeRetentionConfigsEv", "tensorrt_llm::executor::KvCacheRetentionConfig::getTokenRangeRetentionConfigs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig15getTransferModeEv", "tensorrt_llm::executor::KvCacheRetentionConfig::getTransferMode"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25kDefaultRetentionPriorityE", "tensorrt_llm::executor::KvCacheRetentionConfig::kDefaultRetentionPriority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig21kMaxRetentionPriorityE", "tensorrt_llm::executor::KvCacheRetentionConfig::kMaxRetentionPriority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig21kMinRetentionPriorityE", "tensorrt_llm::executor::KvCacheRetentionConfig::kMinRetentionPriority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig17mDecodeDurationMsE", "tensorrt_llm::executor::KvCacheRetentionConfig::mDecodeDurationMs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig24mDecodeRetentionPriorityE", "tensorrt_llm::executor::KvCacheRetentionConfig::mDecodeRetentionPriority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig10mDirectoryE", "tensorrt_llm::executor::KvCacheRetentionConfig::mDirectory"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig27mTokenRangeRetentionConfigsE", "tensorrt_llm::executor::KvCacheRetentionConfig::mTokenRangeRetentionConfigs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig13mTransferModeE", "tensorrt_llm::executor::KvCacheRetentionConfig::mTransferMode"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfigeqERK22KvCacheRetentionConfig", "tensorrt_llm::executor::KvCacheRetentionConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfigeqERK22KvCacheRetentionConfig", "tensorrt_llm::executor::KvCacheRetentionConfig::operator==::other"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStatsE", "tensorrt_llm::executor::KvCacheStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats14allocNewBlocksE", "tensorrt_llm::executor::KvCacheStats::allocNewBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats16allocTotalBlocksE", "tensorrt_llm::executor::KvCacheStats::allocTotalBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12cacheHitRateE", "tensorrt_llm::executor::KvCacheStats::cacheHitRate"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats13freeNumBlocksE", "tensorrt_llm::executor::KvCacheStats::freeNumBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12maxNumBlocksE", "tensorrt_llm::executor::KvCacheStats::maxNumBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12missedBlocksE", "tensorrt_llm::executor::KvCacheStats::missedBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12reusedBlocksE", "tensorrt_llm::executor::KvCacheStats::reusedBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats14tokensPerBlockE", "tensorrt_llm::executor::KvCacheStats::tokensPerBlock"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats13usedNumBlocksE", "tensorrt_llm::executor::KvCacheStats::usedNumBlocks"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor19KvCacheTransferModeE", "tensorrt_llm::executor::KvCacheTransferMode"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor19KvCacheTransferMode4DRAME", "tensorrt_llm::executor::KvCacheTransferMode::DRAM"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor19KvCacheTransferMode3GDSE", "tensorrt_llm::executor::KvCacheTransferMode::GDS"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor19KvCacheTransferMode20POSIX_DEBUG_FALLBACKE", "tensorrt_llm::executor::KvCacheTransferMode::POSIX_DEBUG_FALLBACK"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor19LogitsPostProcessorE", "tensorrt_llm::executor::LogitsPostProcessor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor26LogitsPostProcessorBatchedE", "tensorrt_llm::executor::LogitsPostProcessorBatched"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfigE", "tensorrt_llm::executor::LogitsPostProcessorConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig25LogitsPostProcessorConfigENSt8optionalI22LogitsPostProcessorMapEENSt8optionalI26LogitsPostProcessorBatchedEEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::LogitsPostProcessorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig25LogitsPostProcessorConfigENSt8optionalI22LogitsPostProcessorMapEENSt8optionalI26LogitsPostProcessorBatchedEEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::LogitsPostProcessorConfig::processorBatched"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig25LogitsPostProcessorConfigENSt8optionalI22LogitsPostProcessorMapEENSt8optionalI26LogitsPostProcessorBatchedEEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::LogitsPostProcessorConfig::processorMap"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig25LogitsPostProcessorConfigENSt8optionalI22LogitsPostProcessorMapEENSt8optionalI26LogitsPostProcessorBatchedEEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::LogitsPostProcessorConfig::replicate"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig19getProcessorBatchedEv", "tensorrt_llm::executor::LogitsPostProcessorConfig::getProcessorBatched"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig15getProcessorMapEv", "tensorrt_llm::executor::LogitsPostProcessorConfig::getProcessorMap"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig12getReplicateEv", "tensorrt_llm::executor::LogitsPostProcessorConfig::getReplicate"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig17mProcessorBatchedE", "tensorrt_llm::executor::LogitsPostProcessorConfig::mProcessorBatched"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig13mProcessorMapE", "tensorrt_llm::executor::LogitsPostProcessorConfig::mProcessorMap"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig10mReplicateE", "tensorrt_llm::executor::LogitsPostProcessorConfig::mReplicate"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig19setProcessorBatchedERK26LogitsPostProcessorBatched", "tensorrt_llm::executor::LogitsPostProcessorConfig::setProcessorBatched"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig19setProcessorBatchedERK26LogitsPostProcessorBatched", "tensorrt_llm::executor::LogitsPostProcessorConfig::setProcessorBatched::processorBatched"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig15setProcessorMapERK22LogitsPostProcessorMap", "tensorrt_llm::executor::LogitsPostProcessorConfig::setProcessorMap"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig15setProcessorMapERK22LogitsPostProcessorMap", "tensorrt_llm::executor::LogitsPostProcessorConfig::setProcessorMap::processorMap"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig12setReplicateEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::setReplicate"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig12setReplicateEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::setReplicate::replicate"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor22LogitsPostProcessorMapE", "tensorrt_llm::executor::LogitsPostProcessorMap"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfigE", "tensorrt_llm::executor::LookaheadDecodingConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::LookaheadDecodingConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigEv", "tensorrt_llm::executor::LookaheadDecodingConfig::LookaheadDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::LookaheadDecodingConfig::ngramSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::LookaheadDecodingConfig::verificationSetSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::LookaheadDecodingConfig::windowSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig28calculateSpeculativeResourceEv", "tensorrt_llm::executor::LookaheadDecodingConfig::calculateSpeculativeResource"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig33calculateSpeculativeResourceTupleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::calculateSpeculativeResourceTuple"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig33calculateSpeculativeResourceTupleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::calculateSpeculativeResourceTuple::ngramSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig33calculateSpeculativeResourceTupleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::calculateSpeculativeResourceTuple::verificationSetSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig33calculateSpeculativeResourceTupleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::calculateSpeculativeResourceTuple::windowSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig3getEv", "tensorrt_llm::executor::LookaheadDecodingConfig::get"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig12getNgramSizeEv", "tensorrt_llm::executor::LookaheadDecodingConfig::getNgramSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig22getVerificationSetSizeEv", "tensorrt_llm::executor::LookaheadDecodingConfig::getVerificationSetSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig13getWindowSizeEv", "tensorrt_llm::executor::LookaheadDecodingConfig::getWindowSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig4isLEERK23LookaheadDecodingConfig", "tensorrt_llm::executor::LookaheadDecodingConfig::isLE"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig4isLEERK23LookaheadDecodingConfig", "tensorrt_llm::executor::LookaheadDecodingConfig::isLE::that"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig7isLegalE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::isLegal"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig7isLegalE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::isLegal::ngramSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig7isLegalE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::isLegal::verificationSetSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig7isLegalE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::isLegal::windowSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig30kDefaultLookaheadDecodingNgramE", "tensorrt_llm::executor::LookaheadDecodingConfig::kDefaultLookaheadDecodingNgram"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig40kDefaultLookaheadDecodingVerificationSetE", "tensorrt_llm::executor::LookaheadDecodingConfig::kDefaultLookaheadDecodingVerificationSet"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig31kDefaultLookaheadDecodingWindowE", "tensorrt_llm::executor::LookaheadDecodingConfig::kDefaultLookaheadDecodingWindow"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig10mNgramSizeE", "tensorrt_llm::executor::LookaheadDecodingConfig::mNgramSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig20mVerificationSetSizeE", "tensorrt_llm::executor::LookaheadDecodingConfig::mVerificationSetSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig11mWindowSizeE", "tensorrt_llm::executor::LookaheadDecodingConfig::mWindowSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfigeqERK23LookaheadDecodingConfig", "tensorrt_llm::executor::LookaheadDecodingConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfigeqERK23LookaheadDecodingConfig", "tensorrt_llm::executor::LookaheadDecodingConfig::operator==::other"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfigE", "tensorrt_llm::executor::LoraConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig10LoraConfigE6IdTypeNSt8optionalI6TensorEENSt8optionalI6TensorEE", "tensorrt_llm::executor::LoraConfig::LoraConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig10LoraConfigE6IdTypeNSt8optionalI6TensorEENSt8optionalI6TensorEE", "tensorrt_llm::executor::LoraConfig::LoraConfig::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig10LoraConfigE6IdTypeNSt8optionalI6TensorEENSt8optionalI6TensorEE", "tensorrt_llm::executor::LoraConfig::LoraConfig::taskId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig10LoraConfigE6IdTypeNSt8optionalI6TensorEENSt8optionalI6TensorEE", "tensorrt_llm::executor::LoraConfig::LoraConfig::weights"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor10LoraConfig9getConfigEv", "tensorrt_llm::executor::LoraConfig::getConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor10LoraConfig9getTaskIdEv", "tensorrt_llm::executor::LoraConfig::getTaskId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor10LoraConfig10getWeightsEv", "tensorrt_llm::executor::LoraConfig::getWeights"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig7mConfigE", "tensorrt_llm::executor::LoraConfig::mConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig7mTaskIdE", "tensorrt_llm::executor::LoraConfig::mTaskId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig8mWeightsE", "tensorrt_llm::executor::LoraConfig::mWeights"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor13MedusaChoicesE", "tensorrt_llm::executor::MedusaChoices"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor10MemoryTypeE", "tensorrt_llm::executor::MemoryType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType4kCPUE", "tensorrt_llm::executor::MemoryType::kCPU"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType11kCPU_PINNEDE", "tensorrt_llm::executor::MemoryType::kCPU_PINNED"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType15kCPU_PINNEDPOOLE", "tensorrt_llm::executor::MemoryType::kCPU_PINNEDPOOL"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType4kGPUE", "tensorrt_llm::executor::MemoryType::kGPU"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType8kUNKNOWNE", "tensorrt_llm::executor::MemoryType::kUNKNOWN"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType4kUVME", "tensorrt_llm::executor::MemoryType::kUVM"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor16MillisecondsTypeE", "tensorrt_llm::executor::MillisecondsType"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor9ModelTypeE", "tensorrt_llm::executor::ModelType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor9ModelType13kDECODER_ONLYE", "tensorrt_llm::executor::ModelType::kDECODER_ONLY"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor9ModelType16kENCODER_DECODERE", "tensorrt_llm::executor::ModelType::kENCODER_DECODER"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor9ModelType13kENCODER_ONLYE", "tensorrt_llm::executor::ModelType::kENCODER_ONLY"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor11MropeConfigE", "tensorrt_llm::executor::MropeConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11MropeConfig11MropeConfigE6Tensor10SizeType32", "tensorrt_llm::executor::MropeConfig::MropeConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11MropeConfig11MropeConfigE6Tensor10SizeType32", "tensorrt_llm::executor::MropeConfig::MropeConfig::mropePositionDeltas"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11MropeConfig11MropeConfigE6Tensor10SizeType32", "tensorrt_llm::executor::MropeConfig::MropeConfig::mropeRoratySinCos"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11MropeConfig22getMRopePositionDeltasEv", "tensorrt_llm::executor::MropeConfig::getMRopePositionDeltas"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11MropeConfig20getMRopeRotaryCosSinEv", "tensorrt_llm::executor::MropeConfig::getMRopeRotaryCosSin"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11MropeConfig20mMRopePositionDeltasE", "tensorrt_llm::executor::MropeConfig::mMRopePositionDeltas"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11MropeConfig18mMRopeRotaryCosSinE", "tensorrt_llm::executor::MropeConfig::mMRopeRotaryCosSin"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor15MultimodalInputE", "tensorrt_llm::executor::MultimodalInput"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15MultimodalInput15MultimodalInputENSt6vectorINSt6vectorI10SizeType32EEEENSt6vectorI10SizeType32EENSt6vectorI10SizeType32EE", "tensorrt_llm::executor::MultimodalInput::MultimodalInput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15MultimodalInput15MultimodalInputENSt6vectorINSt6vectorI10SizeType32EEEENSt6vectorI10SizeType32EENSt6vectorI10SizeType32EE", "tensorrt_llm::executor::MultimodalInput::MultimodalInput::multimodalHashes"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15MultimodalInput15MultimodalInputENSt6vectorINSt6vectorI10SizeType32EEEENSt6vectorI10SizeType32EENSt6vectorI10SizeType32EE", "tensorrt_llm::executor::MultimodalInput::MultimodalInput::multimodalLengths"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15MultimodalInput15MultimodalInputENSt6vectorINSt6vectorI10SizeType32EEEENSt6vectorI10SizeType32EENSt6vectorI10SizeType32EE", "tensorrt_llm::executor::MultimodalInput::MultimodalInput::multimodalPositions"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15MultimodalInput19getMultimodalHashesEv", "tensorrt_llm::executor::MultimodalInput::getMultimodalHashes"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15MultimodalInput20getMultimodalLengthsEv", "tensorrt_llm::executor::MultimodalInput::getMultimodalLengths"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15MultimodalInput22getMultimodalPositionsEv", "tensorrt_llm::executor::MultimodalInput::getMultimodalPositions"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15MultimodalInput17mMultimodalHashesE", "tensorrt_llm::executor::MultimodalInput::mMultimodalHashes"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15MultimodalInput18mMultimodalLengthsE", "tensorrt_llm::executor::MultimodalInput::mMultimodalLengths"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15MultimodalInput20mMultimodalPositionsE", "tensorrt_llm::executor::MultimodalInput::mMultimodalPositions"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfigE", "tensorrt_llm::executor::OrchestratorConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb", "tensorrt_llm::executor::OrchestratorConfig::OrchestratorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb", "tensorrt_llm::executor::OrchestratorConfig::OrchestratorConfig::isOrchestrator"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb", "tensorrt_llm::executor::OrchestratorConfig::OrchestratorConfig::orchLeaderComm"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb", "tensorrt_llm::executor::OrchestratorConfig::OrchestratorConfig::spawnProcesses"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb", "tensorrt_llm::executor::OrchestratorConfig::OrchestratorConfig::workerExecutablePath"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getIsOrchestratorEv", "tensorrt_llm::executor::OrchestratorConfig::getIsOrchestrator"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getOrchLeaderCommEv", "tensorrt_llm::executor::OrchestratorConfig::getOrchLeaderComm"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getSpawnProcessesEv", "tensorrt_llm::executor::OrchestratorConfig::getSpawnProcesses"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig23getWorkerExecutablePathEv", "tensorrt_llm::executor::OrchestratorConfig::getWorkerExecutablePath"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mIsOrchestratorE", "tensorrt_llm::executor::OrchestratorConfig::mIsOrchestrator"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mOrchLeaderCommE", "tensorrt_llm::executor::OrchestratorConfig::mOrchLeaderComm"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mSpawnProcessesE", "tensorrt_llm::executor::OrchestratorConfig::mSpawnProcesses"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig21mWorkerExecutablePathE", "tensorrt_llm::executor::OrchestratorConfig::mWorkerExecutablePath"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setIsOrchestratorEb", "tensorrt_llm::executor::OrchestratorConfig::setIsOrchestrator"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setIsOrchestratorEb", "tensorrt_llm::executor::OrchestratorConfig::setIsOrchestrator::isOrchestrator"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setOrchLeaderCommERKNSt10shared_ptrIN3mpi7MpiCommEEE", "tensorrt_llm::executor::OrchestratorConfig::setOrchLeaderComm"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setOrchLeaderCommERKNSt10shared_ptrIN3mpi7MpiCommEEE", "tensorrt_llm::executor::OrchestratorConfig::setOrchLeaderComm::orchLeaderComm"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setSpawnProcessesEb", "tensorrt_llm::executor::OrchestratorConfig::setSpawnProcesses"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setSpawnProcessesEb", "tensorrt_llm::executor::OrchestratorConfig::setSpawnProcesses::spawnProcesses"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig23setWorkerExecutablePathERKNSt6stringE", "tensorrt_llm::executor::OrchestratorConfig::setWorkerExecutablePath"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig23setWorkerExecutablePathERKNSt6stringE", "tensorrt_llm::executor::OrchestratorConfig::setWorkerExecutablePath::workerExecutablePath"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfigE", "tensorrt_llm::executor::OutputConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", "tensorrt_llm::executor::OutputConfig::OutputConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", "tensorrt_llm::executor::OutputConfig::OutputConfig::additionalModelOutputs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", "tensorrt_llm::executor::OutputConfig::OutputConfig::excludeInputFromOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", "tensorrt_llm::executor::OutputConfig::OutputConfig::returnContextLogits"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", "tensorrt_llm::executor::OutputConfig::OutputConfig::returnEncoderOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", "tensorrt_llm::executor::OutputConfig::OutputConfig::returnGenerationLogits"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", "tensorrt_llm::executor::OutputConfig::OutputConfig::returnLogProbs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", "tensorrt_llm::executor::OutputConfig::OutputConfig::returnPerfMetrics"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig22additionalModelOutputsE", "tensorrt_llm::executor::OutputConfig::additionalModelOutputs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig22excludeInputFromOutputE", "tensorrt_llm::executor::OutputConfig::excludeInputFromOutput"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig19returnContextLogitsE", "tensorrt_llm::executor::OutputConfig::returnContextLogits"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig19returnEncoderOutputE", "tensorrt_llm::executor::OutputConfig::returnEncoderOutput"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig22returnGenerationLogitsE", "tensorrt_llm::executor::OutputConfig::returnGenerationLogits"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig14returnLogProbsE", "tensorrt_llm::executor::OutputConfig::returnLogProbs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig17returnPerfMetricsE", "tensorrt_llm::executor::OutputConfig::returnPerfMetrics"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfigE", "tensorrt_llm::executor::ParallelConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEENSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEENSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig::commMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEENSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig::commType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEENSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig::deviceIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEENSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig::numNodes"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEENSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig::orchestratorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEENSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig::participantIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig20getCommunicationModeEv", "tensorrt_llm::executor::ParallelConfig::getCommunicationMode"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig20getCommunicationTypeEv", "tensorrt_llm::executor::ParallelConfig::getCommunicationType"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig12getDeviceIdsEv", "tensorrt_llm::executor::ParallelConfig::getDeviceIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig11getNumNodesEv", "tensorrt_llm::executor::ParallelConfig::getNumNodes"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig21getOrchestratorConfigEv", "tensorrt_llm::executor::ParallelConfig::getOrchestratorConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig17getParticipantIdsEv", "tensorrt_llm::executor::ParallelConfig::getParticipantIds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig9mCommModeE", "tensorrt_llm::executor::ParallelConfig::mCommMode"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig9mCommTypeE", "tensorrt_llm::executor::ParallelConfig::mCommType"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig10mDeviceIdsE", "tensorrt_llm::executor::ParallelConfig::mDeviceIds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig9mNumNodesE", "tensorrt_llm::executor::ParallelConfig::mNumNodes"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig19mOrchestratorConfigE", "tensorrt_llm::executor::ParallelConfig::mOrchestratorConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig15mParticipantIdsE", "tensorrt_llm::executor::ParallelConfig::mParticipantIds"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationModeE17CommunicationMode", "tensorrt_llm::executor::ParallelConfig::setCommunicationMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationModeE17CommunicationMode", "tensorrt_llm::executor::ParallelConfig::setCommunicationMode::mode"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationTypeE17CommunicationType", "tensorrt_llm::executor::ParallelConfig::setCommunicationType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationTypeE17CommunicationType", "tensorrt_llm::executor::ParallelConfig::setCommunicationType::type"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig12setDeviceIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::setDeviceIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig12setDeviceIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::setDeviceIds::deviceIds"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig11setNumNodesE10SizeType32", "tensorrt_llm::executor::ParallelConfig::setNumNodes"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig11setNumNodesE10SizeType32", "tensorrt_llm::executor::ParallelConfig::setNumNodes::numNodes"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig21setOrchestratorConfigERK18OrchestratorConfig", "tensorrt_llm::executor::ParallelConfig::setOrchestratorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig21setOrchestratorConfigERK18OrchestratorConfig", "tensorrt_llm::executor::ParallelConfig::setOrchestratorConfig::orchestratorConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig17setParticipantIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::setParticipantIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig17setParticipantIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::setParticipantIds::participantIds"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfigE", "tensorrt_llm::executor::PeftCacheConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::deviceCachePercent"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::hostCacheSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::loraPrefetchDir"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::maxAdapterSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::maxPagesPerBlockDevice"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::maxPagesPerBlockHost"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::numCopyStreams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::numDeviceModuleLayer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::numEnsureWorkers"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::numHostModuleLayer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::numPutWorkers"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::optimalAdapterSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getDeviceCachePercentEv", "tensorrt_llm::executor::PeftCacheConfig::getDeviceCachePercent"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig16getHostCacheSizeEv", "tensorrt_llm::executor::PeftCacheConfig::getHostCacheSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig18getLoraPrefetchDirEv", "tensorrt_llm::executor::PeftCacheConfig::getLoraPrefetchDir"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig17getMaxAdapterSizeEv", "tensorrt_llm::executor::PeftCacheConfig::getMaxAdapterSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig25getMaxPagesPerBlockDeviceEv", "tensorrt_llm::executor::PeftCacheConfig::getMaxPagesPerBlockDevice"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig23getMaxPagesPerBlockHostEv", "tensorrt_llm::executor::PeftCacheConfig::getMaxPagesPerBlockHost"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig17getNumCopyStreamsEv", "tensorrt_llm::executor::PeftCacheConfig::getNumCopyStreams"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig23getNumDeviceModuleLayerEv", "tensorrt_llm::executor::PeftCacheConfig::getNumDeviceModuleLayer"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig19getNumEnsureWorkersEv", "tensorrt_llm::executor::PeftCacheConfig::getNumEnsureWorkers"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getNumHostModuleLayerEv", "tensorrt_llm::executor::PeftCacheConfig::getNumHostModuleLayer"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig16getNumPutWorkersEv", "tensorrt_llm::executor::PeftCacheConfig::getNumPutWorkers"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getOptimalAdapterSizeEv", "tensorrt_llm::executor::PeftCacheConfig::getOptimalAdapterSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig22kDefaultMaxAdapterSizeE", "tensorrt_llm::executor::PeftCacheConfig::kDefaultMaxAdapterSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig30kDefaultMaxPagesPerBlockDeviceE", "tensorrt_llm::executor::PeftCacheConfig::kDefaultMaxPagesPerBlockDevice"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig28kDefaultMaxPagesPerBlockHostE", "tensorrt_llm::executor::PeftCacheConfig::kDefaultMaxPagesPerBlockHost"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig26kDefaultOptimalAdapterSizeE", "tensorrt_llm::executor::PeftCacheConfig::kDefaultOptimalAdapterSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mDeviceCachePercentE", "tensorrt_llm::executor::PeftCacheConfig::mDeviceCachePercent"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig14mHostCacheSizeE", "tensorrt_llm::executor::PeftCacheConfig::mHostCacheSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig16mLoraPrefetchDirE", "tensorrt_llm::executor::PeftCacheConfig::mLoraPrefetchDir"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15mMaxAdapterSizeE", "tensorrt_llm::executor::PeftCacheConfig::mMaxAdapterSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig23mMaxPagesPerBlockDeviceE", "tensorrt_llm::executor::PeftCacheConfig::mMaxPagesPerBlockDevice"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig21mMaxPagesPerBlockHostE", "tensorrt_llm::executor::PeftCacheConfig::mMaxPagesPerBlockHost"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15mNumCopyStreamsE", "tensorrt_llm::executor::PeftCacheConfig::mNumCopyStreams"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig21mNumDeviceModuleLayerE", "tensorrt_llm::executor::PeftCacheConfig::mNumDeviceModuleLayer"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig17mNumEnsureWorkersE", "tensorrt_llm::executor::PeftCacheConfig::mNumEnsureWorkers"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mNumHostModuleLayerE", "tensorrt_llm::executor::PeftCacheConfig::mNumHostModuleLayer"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig14mNumPutWorkersE", "tensorrt_llm::executor::PeftCacheConfig::mNumPutWorkers"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mOptimalAdapterSizeE", "tensorrt_llm::executor::PeftCacheConfig::mOptimalAdapterSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfigeqERK15PeftCacheConfig", "tensorrt_llm::executor::PeftCacheConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfigeqERK15PeftCacheConfig", "tensorrt_llm::executor::PeftCacheConfig::operator==::other"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor12PriorityTypeE", "tensorrt_llm::executor::PriorityType"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfigE", "tensorrt_llm::executor::PromptTuningConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig18PromptTuningConfigE6TensorNSt8optionalI16VecTokenExtraIdsEE", "tensorrt_llm::executor::PromptTuningConfig::PromptTuningConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig18PromptTuningConfigE6TensorNSt8optionalI16VecTokenExtraIdsEE", "tensorrt_llm::executor::PromptTuningConfig::PromptTuningConfig::embeddingTable"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig18PromptTuningConfigE6TensorNSt8optionalI16VecTokenExtraIdsEE", "tensorrt_llm::executor::PromptTuningConfig::PromptTuningConfig::inputTokenExtraIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18PromptTuningConfig17getEmbeddingTableEv", "tensorrt_llm::executor::PromptTuningConfig::getEmbeddingTable"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18PromptTuningConfig21getInputTokenExtraIdsEv", "tensorrt_llm::executor::PromptTuningConfig::getInputTokenExtraIds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig15mEmbeddingTableE", "tensorrt_llm::executor::PromptTuningConfig::mEmbeddingTable"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig19mInputTokenExtraIdsE", "tensorrt_llm::executor::PromptTuningConfig::mInputTokenExtraIds"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor14RandomSeedTypeE", "tensorrt_llm::executor::RandomSeedType"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor7RequestE", "tensorrt_llm::executor::Request"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestERK7Request", "tensorrt_llm::executor::Request::Request"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestERR7Request", "tensorrt_llm::executor::Request::Request"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::allottedTimeMs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::badWords"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::clientId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::contextPhaseParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::crossAttentionMask"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::eagleConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::embeddingBias"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::encoderInputFeatures"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::encoderInputTokenIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::encoderOutputLength"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::endId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::externalDraftTokensConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::guidedDecodingParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::inputTokenIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::kvCacheRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::languageAdapterUid"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::logitsPostProcessor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::logitsPostProcessorName"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::lookaheadConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::loraConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::mRopeConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::maxTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::multimodalEmbedding"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::multimodalInput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::numReturnSequences"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestERK7Request", "tensorrt_llm::executor::Request::Request::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestERR7Request", "tensorrt_llm::executor::Request::Request::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::outputConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::pTuningConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::padId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::positionIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::priority"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::returnAllGeneratedTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::samplingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::skipCrossAttnBlocks"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::stopWords"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::streaming"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::type"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request24getAdditionalOutputNamesEv", "tensorrt_llm::executor::Request::getAdditionalOutputNames"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request17getAllottedTimeMsEv", "tensorrt_llm::executor::Request::getAllottedTimeMs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request11getBadWordsEv", "tensorrt_llm::executor::Request::getBadWords"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request11getClientIdEv", "tensorrt_llm::executor::Request::getClientId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request21getContextPhaseParamsEv", "tensorrt_llm::executor::Request::getContextPhaseParams"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request21getCrossAttentionMaskEv", "tensorrt_llm::executor::Request::getCrossAttentionMask"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request14getEagleConfigEv", "tensorrt_llm::executor::Request::getEagleConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request16getEmbeddingBiasEv", "tensorrt_llm::executor::Request::getEmbeddingBias"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request23getEncoderInputFeaturesEv", "tensorrt_llm::executor::Request::getEncoderInputFeatures"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request23getEncoderInputTokenIdsEv", "tensorrt_llm::executor::Request::getEncoderInputTokenIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request22getEncoderOutputLengthEv", "tensorrt_llm::executor::Request::getEncoderOutputLength"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request8getEndIdEv", "tensorrt_llm::executor::Request::getEndId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request28getExternalDraftTokensConfigEv", "tensorrt_llm::executor::Request::getExternalDraftTokensConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request23getGuidedDecodingParamsEv", "tensorrt_llm::executor::Request::getGuidedDecodingParams"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request16getInputTokenIdsEv", "tensorrt_llm::executor::Request::getInputTokenIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request25getKvCacheRetentionConfigEv", "tensorrt_llm::executor::Request::getKvCacheRetentionConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request21getLanguageAdapterUidEv", "tensorrt_llm::executor::Request::getLanguageAdapterUid"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request22getLogitsPostProcessorEv", "tensorrt_llm::executor::Request::getLogitsPostProcessor"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request26getLogitsPostProcessorNameEv", "tensorrt_llm::executor::Request::getLogitsPostProcessorName"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request18getLookaheadConfigEv", "tensorrt_llm::executor::Request::getLookaheadConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request13getLoraConfigEv", "tensorrt_llm::executor::Request::getLoraConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request12getMaxTokensEv", "tensorrt_llm::executor::Request::getMaxTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request14getMropeConfigEv", "tensorrt_llm::executor::Request::getMropeConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request22getMultimodalEmbeddingEv", "tensorrt_llm::executor::Request::getMultimodalEmbedding"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request18getMultimodalInputEv", "tensorrt_llm::executor::Request::getMultimodalInput"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request15getOutputConfigEv", "tensorrt_llm::executor::Request::getOutputConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request8getPadIdEv", "tensorrt_llm::executor::Request::getPadId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request14getPositionIdsEv", "tensorrt_llm::executor::Request::getPositionIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request11getPriorityEv", "tensorrt_llm::executor::Request::getPriority"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request21getPromptTuningConfigEv", "tensorrt_llm::executor::Request::getPromptTuningConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request14getRequestTypeEv", "tensorrt_llm::executor::Request::getRequestType"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request27getReturnAllGeneratedTokensEv", "tensorrt_llm::executor::Request::getReturnAllGeneratedTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request17getSamplingConfigEv", "tensorrt_llm::executor::Request::getSamplingConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request22getSkipCrossAttnBlocksEv", "tensorrt_llm::executor::Request::getSkipCrossAttnBlocks"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request12getStopWordsEv", "tensorrt_llm::executor::Request::getStopWords"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request12getStreamingEv", "tensorrt_llm::executor::Request::getStreaming"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request25kBatchedPostProcessorNameE", "tensorrt_llm::executor::Request::kBatchedPostProcessorName"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request16kDefaultPriorityE", "tensorrt_llm::executor::Request::kDefaultPriority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request31kDynamicPostProcessorNamePrefixE", "tensorrt_llm::executor::Request::kDynamicPostProcessorNamePrefix"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request5mImplE", "tensorrt_llm::executor::Request::mImpl"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7RequestaSERK7Request", "tensorrt_llm::executor::Request::operator="], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7RequestaSERR7Request", "tensorrt_llm::executor::Request::operator="], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7RequestaSERK7Request", "tensorrt_llm::executor::Request::operator=::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7RequestaSERR7Request", "tensorrt_llm::executor::Request::operator=::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request17setAllottedTimeMsE16MillisecondsType", "tensorrt_llm::executor::Request::setAllottedTimeMs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request17setAllottedTimeMsE16MillisecondsType", "tensorrt_llm::executor::Request::setAllottedTimeMs::allottedTimeMs"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request11setBadWordsERKNSt4listI9VecTokensEE", "tensorrt_llm::executor::Request::setBadWords"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request11setBadWordsERKNSt4listI9VecTokensEE", "tensorrt_llm::executor::Request::setBadWords::badWords"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request11setClientIdE6IdType", "tensorrt_llm::executor::Request::setClientId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request11setClientIdE6IdType", "tensorrt_llm::executor::Request::setClientId::clientId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request21setContextPhaseParamsE18ContextPhaseParams", "tensorrt_llm::executor::Request::setContextPhaseParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request21setContextPhaseParamsE18ContextPhaseParams", "tensorrt_llm::executor::Request::setContextPhaseParams::contextPhaseParams"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request21setCrossAttentionMaskE6Tensor", "tensorrt_llm::executor::Request::setCrossAttentionMask"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request21setCrossAttentionMaskE6Tensor", "tensorrt_llm::executor::Request::setCrossAttentionMask::crossAttentionMask"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request14setEagleConfigERKNSt8optionalI11EagleConfigEE", "tensorrt_llm::executor::Request::setEagleConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request14setEagleConfigERKNSt8optionalI11EagleConfigEE", "tensorrt_llm::executor::Request::setEagleConfig::eagleConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request16setEmbeddingBiasERK6Tensor", "tensorrt_llm::executor::Request::setEmbeddingBias"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request16setEmbeddingBiasERK6Tensor", "tensorrt_llm::executor::Request::setEmbeddingBias::embeddingBias"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputFeaturesE6Tensor", "tensorrt_llm::executor::Request::setEncoderInputFeatures"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputFeaturesE6Tensor", "tensorrt_llm::executor::Request::setEncoderInputFeatures::encoderInputFeatures"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputTokenIdsERK9VecTokens", "tensorrt_llm::executor::Request::setEncoderInputTokenIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputTokenIdsERK9VecTokens", "tensorrt_llm::executor::Request::setEncoderInputTokenIds::encoderInputTokenIds"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request22setEncoderOutputLengthE10SizeType32", "tensorrt_llm::executor::Request::setEncoderOutputLength"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request22setEncoderOutputLengthE10SizeType32", "tensorrt_llm::executor::Request::setEncoderOutputLength::encoderOutputLength"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request8setEndIdE10SizeType32", "tensorrt_llm::executor::Request::setEndId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request8setEndIdE10SizeType32", "tensorrt_llm::executor::Request::setEndId::endId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request28setExternalDraftTokensConfigERK25ExternalDraftTokensConfig", "tensorrt_llm::executor::Request::setExternalDraftTokensConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request28setExternalDraftTokensConfigERK25ExternalDraftTokensConfig", "tensorrt_llm::executor::Request::setExternalDraftTokensConfig::externalDraftTokensConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request23setGuidedDecodingParamsERK20GuidedDecodingParams", "tensorrt_llm::executor::Request::setGuidedDecodingParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request23setGuidedDecodingParamsERK20GuidedDecodingParams", "tensorrt_llm::executor::Request::setGuidedDecodingParams::guidedDecodingParams"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request25setKvCacheRetentionConfigERK22KvCacheRetentionConfig", "tensorrt_llm::executor::Request::setKvCacheRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request25setKvCacheRetentionConfigERK22KvCacheRetentionConfig", "tensorrt_llm::executor::Request::setKvCacheRetentionConfig::kvCacheRetentionConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request21setLanguageAdapterUidE10SizeType32", "tensorrt_llm::executor::Request::setLanguageAdapterUid"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request21setLanguageAdapterUidE10SizeType32", "tensorrt_llm::executor::Request::setLanguageAdapterUid::languageAdapterUid"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request22setLogitsPostProcessorERKNSt8optionalI19LogitsPostProcessorEE", "tensorrt_llm::executor::Request::setLogitsPostProcessor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request22setLogitsPostProcessorERKNSt8optionalI19LogitsPostProcessorEE", "tensorrt_llm::executor::Request::setLogitsPostProcessor::logitsPostProcessor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request26setLogitsPostProcessorNameERKNSt6stringE", "tensorrt_llm::executor::Request::setLogitsPostProcessorName"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request26setLogitsPostProcessorNameERKNSt6stringE", "tensorrt_llm::executor::Request::setLogitsPostProcessorName::logitsPostProcessorName"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request18setLookaheadConfigERK23LookaheadDecodingConfig", "tensorrt_llm::executor::Request::setLookaheadConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request18setLookaheadConfigERK23LookaheadDecodingConfig", "tensorrt_llm::executor::Request::setLookaheadConfig::lookaheadConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request13setLoraConfigERK10LoraConfig", "tensorrt_llm::executor::Request::setLoraConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request13setLoraConfigERK10LoraConfig", "tensorrt_llm::executor::Request::setLoraConfig::loraConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request14setMropeConfigERK11MropeConfig", "tensorrt_llm::executor::Request::setMropeConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request14setMropeConfigERK11MropeConfig", "tensorrt_llm::executor::Request::setMropeConfig::mRopeConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request22setMultimodalEmbeddingERK6Tensor", "tensorrt_llm::executor::Request::setMultimodalEmbedding"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request22setMultimodalEmbeddingERK6Tensor", "tensorrt_llm::executor::Request::setMultimodalEmbedding::multimodalEmbedding"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request18setMultimodalInputERK15MultimodalInput", "tensorrt_llm::executor::Request::setMultimodalInput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request18setMultimodalInputERK15MultimodalInput", "tensorrt_llm::executor::Request::setMultimodalInput::multimodalInput"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request15setOutputConfigERK12OutputConfig", "tensorrt_llm::executor::Request::setOutputConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request15setOutputConfigERK12OutputConfig", "tensorrt_llm::executor::Request::setOutputConfig::outputConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request8setPadIdE10SizeType32", "tensorrt_llm::executor::Request::setPadId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request8setPadIdE10SizeType32", "tensorrt_llm::executor::Request::setPadId::padId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request14setPositionIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::Request::setPositionIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request14setPositionIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::Request::setPositionIds::positionIds"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request11setPriorityE12PriorityType", "tensorrt_llm::executor::Request::setPriority"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request11setPriorityE12PriorityType", "tensorrt_llm::executor::Request::setPriority::priority"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request21setPromptTuningConfigERK18PromptTuningConfig", "tensorrt_llm::executor::Request::setPromptTuningConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request21setPromptTuningConfigERK18PromptTuningConfig", "tensorrt_llm::executor::Request::setPromptTuningConfig::pTuningConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request14setRequestTypeERK11RequestType", "tensorrt_llm::executor::Request::setRequestType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request14setRequestTypeERK11RequestType", "tensorrt_llm::executor::Request::setRequestType::requestType"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request27setReturnAllGeneratedTokensEb", "tensorrt_llm::executor::Request::setReturnAllGeneratedTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request27setReturnAllGeneratedTokensEb", "tensorrt_llm::executor::Request::setReturnAllGeneratedTokens::returnAllGeneratedTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request17setSamplingConfigERK14SamplingConfig", "tensorrt_llm::executor::Request::setSamplingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request17setSamplingConfigERK14SamplingConfig", "tensorrt_llm::executor::Request::setSamplingConfig::config"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request22setSkipCrossAttnBlocksE6Tensor", "tensorrt_llm::executor::Request::setSkipCrossAttnBlocks"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request22setSkipCrossAttnBlocksE6Tensor", "tensorrt_llm::executor::Request::setSkipCrossAttnBlocks::skipCrossAttnBlocks"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request12setStopWordsERKNSt4listI9VecTokensEE", "tensorrt_llm::executor::Request::setStopWords"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request12setStopWordsERKNSt4listI9VecTokensEE", "tensorrt_llm::executor::Request::setStopWords::stopWords"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request12setStreamingEb", "tensorrt_llm::executor::Request::setStreaming"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request12setStreamingEb", "tensorrt_llm::executor::Request::setStreaming::streaming"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7RequestD0Ev", "tensorrt_llm::executor::Request::~Request"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetricsE", "tensorrt_llm::executor::RequestPerfMetrics"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetricsE", "tensorrt_llm::executor::RequestPerfMetrics::KvCacheMetrics"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics14kvCacheHitRateE", "tensorrt_llm::executor::RequestPerfMetrics::KvCacheMetrics::kvCacheHitRate"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics15numMissedBlocksE", "tensorrt_llm::executor::RequestPerfMetrics::KvCacheMetrics::numMissedBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics21numNewAllocatedBlocksE", "tensorrt_llm::executor::RequestPerfMetrics::KvCacheMetrics::numNewAllocatedBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics15numReusedBlocksE", "tensorrt_llm::executor::RequestPerfMetrics::KvCacheMetrics::numReusedBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics23numTotalAllocatedBlocksE", "tensorrt_llm::executor::RequestPerfMetrics::KvCacheMetrics::numTotalAllocatedBlocks"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics26SpeculativeDecodingMetricsE", "tensorrt_llm::executor::RequestPerfMetrics::SpeculativeDecodingMetrics"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics26SpeculativeDecodingMetrics14acceptanceRateE", "tensorrt_llm::executor::RequestPerfMetrics::SpeculativeDecodingMetrics::acceptanceRate"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics26SpeculativeDecodingMetrics24totalAcceptedDraftTokensE", "tensorrt_llm::executor::RequestPerfMetrics::SpeculativeDecodingMetrics::totalAcceptedDraftTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics26SpeculativeDecodingMetrics16totalDraftTokensE", "tensorrt_llm::executor::RequestPerfMetrics::SpeculativeDecodingMetrics::totalDraftTokens"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics9TimePointE", "tensorrt_llm::executor::RequestPerfMetrics::TimePoint"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetricsE", "tensorrt_llm::executor::RequestPerfMetrics::TimingMetrics"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics11arrivalTimeE", "tensorrt_llm::executor::RequestPerfMetrics::TimingMetrics::arrivalTime"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics18firstScheduledTimeE", "tensorrt_llm::executor::RequestPerfMetrics::TimingMetrics::firstScheduledTime"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics14firstTokenTimeE", "tensorrt_llm::executor::RequestPerfMetrics::TimingMetrics::firstTokenTime"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics11kvCacheSizeE", "tensorrt_llm::executor::RequestPerfMetrics::TimingMetrics::kvCacheSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics18kvCacheTransferEndE", "tensorrt_llm::executor::RequestPerfMetrics::TimingMetrics::kvCacheTransferEnd"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics20kvCacheTransferStartE", "tensorrt_llm::executor::RequestPerfMetrics::TimingMetrics::kvCacheTransferStart"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics13lastTokenTimeE", "tensorrt_llm::executor::RequestPerfMetrics::TimingMetrics::lastTokenTime"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics9firstIterE", "tensorrt_llm::executor::RequestPerfMetrics::firstIter"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics4iterE", "tensorrt_llm::executor::RequestPerfMetrics::iter"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14kvCacheMetricsE", "tensorrt_llm::executor::RequestPerfMetrics::kvCacheMetrics"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics8lastIterE", "tensorrt_llm::executor::RequestPerfMetrics::lastIter"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics19speculativeDecodingE", "tensorrt_llm::executor::RequestPerfMetrics::speculativeDecoding"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13timingMetricsE", "tensorrt_llm::executor::RequestPerfMetrics::timingMetrics"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12RequestStageE", "tensorrt_llm::executor::RequestStage"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12RequestStage20kCONTEXT_IN_PROGRESSE", "tensorrt_llm::executor::RequestStage::kCONTEXT_IN_PROGRESS"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12RequestStage20kENCODER_IN_PROGRESSE", "tensorrt_llm::executor::RequestStage::kENCODER_IN_PROGRESS"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12RequestStage20kGENERATION_COMPLETEE", "tensorrt_llm::executor::RequestStage::kGENERATION_COMPLETE"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12RequestStage23kGENERATION_IN_PROGRESSE", "tensorrt_llm::executor::RequestStage::kGENERATION_IN_PROGRESS"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12RequestStage7kQUEUEDE", "tensorrt_llm::executor::RequestStage::kQUEUED"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor12RequestStatsE", "tensorrt_llm::executor::RequestStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats24allocNewBlocksPerRequestE", "tensorrt_llm::executor::RequestStats::allocNewBlocksPerRequest"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats26allocTotalBlocksPerRequestE", "tensorrt_llm::executor::RequestStats::allocTotalBlocksPerRequest"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats26avgNumDecodedTokensPerIterE", "tensorrt_llm::executor::RequestStats::avgNumDecodedTokensPerIter"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats22contextPrefillPositionE", "tensorrt_llm::executor::RequestStats::contextPrefillPosition"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats15disServingStatsE", "tensorrt_llm::executor::RequestStats::disServingStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats2idE", "tensorrt_llm::executor::RequestStats::id"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats24kvCacheHitRatePerRequestE", "tensorrt_llm::executor::RequestStats::kvCacheHitRatePerRequest"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats22missedBlocksPerRequestE", "tensorrt_llm::executor::RequestStats::missedBlocksPerRequest"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats18numGeneratedTokensE", "tensorrt_llm::executor::RequestStats::numGeneratedTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats6pausedE", "tensorrt_llm::executor::RequestStats::paused"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats22reusedBlocksPerRequestE", "tensorrt_llm::executor::RequestStats::reusedBlocksPerRequest"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats9scheduledE", "tensorrt_llm::executor::RequestStats::scheduled"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats5stageE", "tensorrt_llm::executor::RequestStats::stage"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIterationE", "tensorrt_llm::executor::RequestStatsPerIteration"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIteration4iterE", "tensorrt_llm::executor::RequestStatsPerIteration::iter"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIteration12requestStatsE", "tensorrt_llm::executor::RequestStatsPerIteration::requestStats"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor11RequestTypeE", "tensorrt_llm::executor::RequestType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor11RequestType35REQUEST_TYPE_CONTEXT_AND_GENERATIONE", "tensorrt_llm::executor::RequestType::REQUEST_TYPE_CONTEXT_AND_GENERATION"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor11RequestType25REQUEST_TYPE_CONTEXT_ONLYE", "tensorrt_llm::executor::RequestType::REQUEST_TYPE_CONTEXT_ONLY"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor11RequestType28REQUEST_TYPE_GENERATION_ONLYE", "tensorrt_llm::executor::RequestType::REQUEST_TYPE_GENERATION_ONLY"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8ResponseE", "tensorrt_llm::executor::Response"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdType6ResultNSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Response::Response"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdTypeNSt6stringENSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Response::Response"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERK8Response", "tensorrt_llm::executor::Response::Response"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERR8Response", "tensorrt_llm::executor::Response::Response"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdType6ResultNSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Response::Response::Result"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdType6ResultNSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Response::Response::clientId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdTypeNSt6stringENSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Response::Response::clientId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdTypeNSt6stringENSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Response::Response::errorMsg"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERK8Response", "tensorrt_llm::executor::Response::Response::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERR8Response", "tensorrt_llm::executor::Response::Response::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdType6ResultNSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Response::Response::requestId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdTypeNSt6stringENSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Response::Response::requestId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Response11getClientIdEv", "tensorrt_llm::executor::Response::getClientId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Response11getErrorMsgEv", "tensorrt_llm::executor::Response::getErrorMsg"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Response12getRequestIdEv", "tensorrt_llm::executor::Response::getRequestId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Response9getResultEv", "tensorrt_llm::executor::Response::getResult"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Response8hasErrorEv", "tensorrt_llm::executor::Response::hasError"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Response5mImplE", "tensorrt_llm::executor::Response::mImpl"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8ResponseaSERK8Response", "tensorrt_llm::executor::Response::operator="], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8ResponseaSERR8Response", "tensorrt_llm::executor::Response::operator="], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8ResponseaSERK8Response", "tensorrt_llm::executor::Response::operator=::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8ResponseaSERR8Response", "tensorrt_llm::executor::Response::operator=::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8ResponseD0Ev", "tensorrt_llm::executor::Response::~Response"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor6ResultE", "tensorrt_llm::executor::Result"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result17additionalOutputsE", "tensorrt_llm::executor::Result::additionalOutputs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result13contextLogitsE", "tensorrt_llm::executor::Result::contextLogits"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result18contextPhaseParamsE", "tensorrt_llm::executor::Result::contextPhaseParams"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result11cumLogProbsE", "tensorrt_llm::executor::Result::cumLogProbs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result12decodingIterE", "tensorrt_llm::executor::Result::decodingIter"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result13encoderOutputE", "tensorrt_llm::executor::Result::encoderOutput"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result13finishReasonsE", "tensorrt_llm::executor::Result::finishReasons"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result16generationLogitsE", "tensorrt_llm::executor::Result::generationLogits"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result7isFinalE", "tensorrt_llm::executor::Result::isFinal"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result15isSequenceFinalE", "tensorrt_llm::executor::Result::isSequenceFinal"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result8logProbsE", "tensorrt_llm::executor::Result::logProbs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result14outputTokenIdsE", "tensorrt_llm::executor::Result::outputTokenIds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result18requestPerfMetricsE", "tensorrt_llm::executor::Result::requestPerfMetrics"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result13sequenceIndexE", "tensorrt_llm::executor::Result::sequenceIndex"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result21specDecFastLogitsInfoE", "tensorrt_llm::executor::Result::specDecFastLogitsInfo"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor17RetentionPriorityE", "tensorrt_llm::executor::RetentionPriority"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDurationE", "tensorrt_llm::executor::RetentionPriorityAndDuration"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDuration28RetentionPriorityAndDurationERKNSt8optionalI17RetentionPriorityEERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::RetentionPriorityAndDuration::RetentionPriorityAndDuration"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDuration28RetentionPriorityAndDurationERKNSt8optionalI17RetentionPriorityEERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::RetentionPriorityAndDuration::RetentionPriorityAndDuration::durationMs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDuration28RetentionPriorityAndDurationERKNSt8optionalI17RetentionPriorityEERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::RetentionPriorityAndDuration::RetentionPriorityAndDuration::retentionPriority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDuration10durationMsE", "tensorrt_llm::executor::RetentionPriorityAndDuration::durationMs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDuration17retentionPriorityE", "tensorrt_llm::executor::RetentionPriorityAndDuration::retentionPriority"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfigE", "tensorrt_llm::executor::SamplingConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::beamSearchDiversityRate"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::beamWidth"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::beamWidthArray"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::earlyStopping"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::frequencyPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::lengthPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::minP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::minTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::noRepeatNgramSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::numReturnSequences"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::presencePenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::repetitionPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::seed"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::temperature"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::topK"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::topP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::topPDecay"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::topPMin"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::topPResetIds"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig28checkBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkBeamSearchDiversityRate"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig28checkBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkBeamSearchDiversityRate::beamSearchDiversityRate"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkBeamWidthE10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkBeamWidth"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkBeamWidthE10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkBeamWidth::beamWidth"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19checkBeamWidthArrayERKNSt8optionalINSt6vectorI10SizeType32EEEEK10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkBeamWidthArray"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19checkBeamWidthArrayERKNSt8optionalINSt6vectorI10SizeType32EEEEK10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkBeamWidthArray::beamWidth"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19checkBeamWidthArrayERKNSt8optionalINSt6vectorI10SizeType32EEEEK10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkBeamWidthArray::beamWidthArray"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18checkEarlyStoppingERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::checkEarlyStopping"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18checkEarlyStoppingERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::checkEarlyStopping::earlyStopping"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18checkLengthPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkLengthPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18checkLengthPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkLengthPenalty::lengthPenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkMinPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkMinP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkMinPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkMinP::minP"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkMinTokensERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::checkMinTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkMinTokensERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::checkMinTokens::minTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::checkNoRepeatNgramSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::checkNoRepeatNgramSize::noRepeatNgramSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig23checkNumReturnSequencesERKNSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkNumReturnSequences"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig23checkNumReturnSequencesERKNSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkNumReturnSequences::beamWidth"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig23checkNumReturnSequencesERKNSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkNumReturnSequences::numReturnSequences"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkRepetitionPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkRepetitionPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkRepetitionPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkRepetitionPenalty::repetitionpenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16checkTemperatureERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTemperature"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16checkTemperatureERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTemperature::temperature"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopKERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopK"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopKERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopK::topK"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopP::topP"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkTopPDecayERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPDecay"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkTopPDecayERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPDecay::topPDecay"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12checkTopPMinERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPMin"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12checkTopPMinERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPMin::topPMin"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17checkTopPResetIdsERKNSt8optionalI11TokenIdTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPResetIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17checkTopPResetIdsERKNSt8optionalI11TokenIdTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPResetIds::topPResetIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig26getBeamSearchDiversityRateEv", "tensorrt_llm::executor::SamplingConfig::getBeamSearchDiversityRate"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getBeamWidthEv", "tensorrt_llm::executor::SamplingConfig::getBeamWidth"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig17getBeamWidthArrayEv", "tensorrt_llm::executor::SamplingConfig::getBeamWidthArray"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig16getEarlyStoppingEv", "tensorrt_llm::executor::SamplingConfig::getEarlyStopping"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig19getFrequencyPenaltyEv", "tensorrt_llm::executor::SamplingConfig::getFrequencyPenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig16getLengthPenaltyEv", "tensorrt_llm::executor::SamplingConfig::getLengthPenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getMinPEv", "tensorrt_llm::executor::SamplingConfig::getMinP"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getMinTokensEv", "tensorrt_llm::executor::SamplingConfig::getMinTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig20getNoRepeatNgramSizeEv", "tensorrt_llm::executor::SamplingConfig::getNoRepeatNgramSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig17getNumReturnBeamsEv", "tensorrt_llm::executor::SamplingConfig::getNumReturnBeams"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig21getNumReturnSequencesEv", "tensorrt_llm::executor::SamplingConfig::getNumReturnSequences"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig18getPresencePenaltyEv", "tensorrt_llm::executor::SamplingConfig::getPresencePenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig20getRepetitionPenaltyEv", "tensorrt_llm::executor::SamplingConfig::getRepetitionPenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getSeedEv", "tensorrt_llm::executor::SamplingConfig::getSeed"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig14getTemperatureEv", "tensorrt_llm::executor::SamplingConfig::getTemperature"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getTopKEv", "tensorrt_llm::executor::SamplingConfig::getTopK"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getTopPEv", "tensorrt_llm::executor::SamplingConfig::getTopP"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getTopPDecayEv", "tensorrt_llm::executor::SamplingConfig::getTopPDecay"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig10getTopPMinEv", "tensorrt_llm::executor::SamplingConfig::getTopPMin"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig15getTopPResetIdsEv", "tensorrt_llm::executor::SamplingConfig::getTopPResetIds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig24mBeamSearchDiversityRateE", "tensorrt_llm::executor::SamplingConfig::mBeamSearchDiversityRate"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mBeamWidthE", "tensorrt_llm::executor::SamplingConfig::mBeamWidth"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig15mBeamWidthArrayE", "tensorrt_llm::executor::SamplingConfig::mBeamWidthArray"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14mEarlyStoppingE", "tensorrt_llm::executor::SamplingConfig::mEarlyStopping"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17mFrequencyPenaltyE", "tensorrt_llm::executor::SamplingConfig::mFrequencyPenalty"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14mLengthPenaltyE", "tensorrt_llm::executor::SamplingConfig::mLengthPenalty"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mMinPE", "tensorrt_llm::executor::SamplingConfig::mMinP"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mMinTokensE", "tensorrt_llm::executor::SamplingConfig::mMinTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18mNoRepeatNgramSizeE", "tensorrt_llm::executor::SamplingConfig::mNoRepeatNgramSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig15mNumReturnBeamsE", "tensorrt_llm::executor::SamplingConfig::mNumReturnBeams"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19mNumReturnSequencesE", "tensorrt_llm::executor::SamplingConfig::mNumReturnSequences"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16mPresencePenaltyE", "tensorrt_llm::executor::SamplingConfig::mPresencePenalty"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18mRepetitionPenaltyE", "tensorrt_llm::executor::SamplingConfig::mRepetitionPenalty"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mSeedE", "tensorrt_llm::executor::SamplingConfig::mSeed"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12mTemperatureE", "tensorrt_llm::executor::SamplingConfig::mTemperature"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mTopKE", "tensorrt_llm::executor::SamplingConfig::mTopK"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mTopPE", "tensorrt_llm::executor::SamplingConfig::mTopP"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mTopPDecayE", "tensorrt_llm::executor::SamplingConfig::mTopPDecay"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig8mTopPMinE", "tensorrt_llm::executor::SamplingConfig::mTopPMin"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig13mTopPResetIdsE", "tensorrt_llm::executor::SamplingConfig::mTopPResetIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfigeqERK14SamplingConfig", "tensorrt_llm::executor::SamplingConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfigeqERK14SamplingConfig", "tensorrt_llm::executor::SamplingConfig::operator==::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig26setBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setBeamSearchDiversityRate"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig26setBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setBeamSearchDiversityRate::beamSearchDiversityRate"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setBeamWidthE10SizeType32", "tensorrt_llm::executor::SamplingConfig::setBeamWidth"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setBeamWidthE10SizeType32", "tensorrt_llm::executor::SamplingConfig::setBeamWidth::beamWidth"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17setBeamWidthArrayERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::setBeamWidthArray"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17setBeamWidthArrayERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::setBeamWidthArray::beamWidthArray"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setEarlyStoppingERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setEarlyStopping"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setEarlyStoppingERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setEarlyStopping::earlyStopping"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19setFrequencyPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setFrequencyPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19setFrequencyPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setFrequencyPenalty::frequencyPenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setLengthPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setLengthPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setLengthPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setLengthPenalty::lengthPenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setMinPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setMinP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setMinPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setMinP::minP"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setMinTokensERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setMinTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setMinTokensERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setMinTokens::minTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setNoRepeatNgramSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setNoRepeatNgramSize::noRepeatNgramSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig21setNumReturnSequencesERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setNumReturnSequences"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig21setNumReturnSequencesERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setNumReturnSequences::numReturnSequences"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18setPresencePenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setPresencePenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18setPresencePenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setPresencePenalty::presencePenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setRepetitionPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setRepetitionPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setRepetitionPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setRepetitionPenalty::repetitionPenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setSeedERKNSt8optionalI14RandomSeedTypeEE", "tensorrt_llm::executor::SamplingConfig::setSeed"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setSeedERKNSt8optionalI14RandomSeedTypeEE", "tensorrt_llm::executor::SamplingConfig::setSeed::seed"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14setTemperatureERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTemperature"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14setTemperatureERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTemperature::temperature"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopKERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setTopK"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopKERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setTopK::topK"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopP::topP"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setTopPDecayERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPDecay"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setTopPDecayERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPDecay::topPDecay"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10setTopPMinERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPMin"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10setTopPMinERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPMin::topPMin"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig15setTopPResetIdsERKNSt8optionalI11TokenIdTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPResetIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig15setTopPResetIdsERKNSt8optionalI11TokenIdTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPResetIds::topPResetIds"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20updateNumReturnBeamsEv", "tensorrt_llm::executor::SamplingConfig::updateNumReturnBeams"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfigE", "tensorrt_llm::executor::SchedulerConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig15SchedulerConfigE23CapacitySchedulerPolicyNSt8optionalI21ContextChunkingPolicyEENSt8optionalI18DynamicBatchConfigEE", "tensorrt_llm::executor::SchedulerConfig::SchedulerConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig15SchedulerConfigE23CapacitySchedulerPolicyNSt8optionalI21ContextChunkingPolicyEENSt8optionalI18DynamicBatchConfigEE", "tensorrt_llm::executor::SchedulerConfig::SchedulerConfig::capacitySchedulerPolicy"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig15SchedulerConfigE23CapacitySchedulerPolicyNSt8optionalI21ContextChunkingPolicyEENSt8optionalI18DynamicBatchConfigEE", "tensorrt_llm::executor::SchedulerConfig::SchedulerConfig::contextChunkingPolicy"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig15SchedulerConfigE23CapacitySchedulerPolicyNSt8optionalI21ContextChunkingPolicyEENSt8optionalI18DynamicBatchConfigEE", "tensorrt_llm::executor::SchedulerConfig::SchedulerConfig::dynamicBatchConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfig26getCapacitySchedulerPolicyEv", "tensorrt_llm::executor::SchedulerConfig::getCapacitySchedulerPolicy"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfig24getContextChunkingPolicyEv", "tensorrt_llm::executor::SchedulerConfig::getContextChunkingPolicy"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfig21getDynamicBatchConfigEv", "tensorrt_llm::executor::SchedulerConfig::getDynamicBatchConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig24mCapacitySchedulerPolicyE", "tensorrt_llm::executor::SchedulerConfig::mCapacitySchedulerPolicy"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig22mContextChunkingPolicyE", "tensorrt_llm::executor::SchedulerConfig::mContextChunkingPolicy"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig19mDynamicBatchConfigE", "tensorrt_llm::executor::SchedulerConfig::mDynamicBatchConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfigeqERK15SchedulerConfig", "tensorrt_llm::executor::SchedulerConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfigeqERK15SchedulerConfig", "tensorrt_llm::executor::SchedulerConfig::operator==::other"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor13SerializationE", "tensorrt_llm::executor::Serialization"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeAdditionalModelOutputERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeAdditionalModelOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeAdditionalModelOutputERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeAdditionalModelOutput::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization27deserializeAdditionalOutputERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeAdditionalOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization27deserializeAdditionalOutputERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeAdditionalOutput::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeAgentStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeAgentState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeAgentStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeAgentState::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization15deserializeBoolERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeBool"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization15deserializeBoolERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeBool::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeCacheStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeCacheState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeCacheStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeCacheState::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeCacheTransceiverConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeCacheTransceiverConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeCacheTransceiverConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeCacheTransceiverConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeCommStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeCommState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeCommStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeCommState::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeContextPhaseParamsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeContextPhaseParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeContextPhaseParamsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeContextPhaseParams::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeDataTransceiverStateERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeDataTransceiverState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeDataTransceiverStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDataTransceiverState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeDataTransceiverStateERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeDataTransceiverState::buffer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeDataTransceiverStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDataTransceiverState::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeDebugConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDebugConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeDebugConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDebugConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDecodingConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeDecodingModeERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDecodingMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeDecodingModeERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDecodingMode::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeDisServingRequestStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDisServingRequestStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeDisServingRequestStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDisServingRequestStats::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeDynamicBatchConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDynamicBatchConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeDynamicBatchConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDynamicBatchConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeEagleConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeEagleConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeEagleConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeEagleConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeExecutorConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExecutorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeExecutorConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExecutorConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization40deserializeExtendedRuntimePerfKnobConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExtendedRuntimePerfKnobConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization40deserializeExtendedRuntimePerfKnobConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExtendedRuntimePerfKnobConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeExternalDraftTokensConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExternalDraftTokensConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeExternalDraftTokensConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExternalDraftTokensConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeGuidedDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeGuidedDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeGuidedDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeGuidedDecodingConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeGuidedDecodingParamsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeGuidedDecodingParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeGuidedDecodingParamsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeGuidedDecodingParams::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeInflightBatchingStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeInflightBatchingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeInflightBatchingStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeInflightBatchingStats::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeIterationStats"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeIterationStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeIterationStats::buffer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeIterationStats::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization28deserializeIterationStatsVecERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeIterationStatsVec"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization28deserializeIterationStatsVecERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeIterationStatsVec::buffer"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization24deserializeKvCacheConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeKvCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization24deserializeKvCacheConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeKvCacheConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeKvCacheRetentionConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeKvCacheRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeKvCacheRetentionConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeKvCacheRetentionConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeKvCacheStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeKvCacheStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeKvCacheStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeKvCacheStats::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization34deserializeLookaheadDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeLookaheadDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization34deserializeLookaheadDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeLookaheadDecodingConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeLoraConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeLoraConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeLoraConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeLoraConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeModelTypeERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeModelType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeModelTypeERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeModelType::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeMropeConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeMropeConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeMropeConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeMropeConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializeMultimodalInputERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeMultimodalInput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializeMultimodalInputERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeMultimodalInput::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeOrchestratorConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeOrchestratorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeOrchestratorConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeOrchestratorConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeOutputConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeOutputConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeOutputConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeOutputConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeParallelConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeParallelConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeParallelConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeParallelConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializePeftCacheConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializePeftCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializePeftCacheConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializePeftCacheConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializePromptTuningConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializePromptTuningConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializePromptTuningConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializePromptTuningConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization18deserializeRequestERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequest"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization18deserializeRequestERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequest::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeRequestPerfMetricsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequestPerfMetrics"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeRequestPerfMetricsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequestPerfMetrics::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeRequestStageERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequestStage"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeRequestStageERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequestStage::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeRequestStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequestStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeRequestStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequestStats::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization35deserializeRequestStatsPerIterationERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeRequestStatsPerIteration"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization35deserializeRequestStatsPerIterationERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequestStatsPerIteration"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization35deserializeRequestStatsPerIterationERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeRequestStatsPerIteration::buffer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization35deserializeRequestStatsPerIterationERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequestStatsPerIteration::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization38deserializeRequestStatsPerIterationVecERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeRequestStatsPerIterationVec"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization38deserializeRequestStatsPerIterationVecERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeRequestStatsPerIterationVec::buffer"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization19deserializeResponseERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeResponse"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization19deserializeResponseERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeResponse::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeResponsesERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeResponses"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeResponsesERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeResponses::buffer"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeResultERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeResult"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeResultERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeResult::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeSamplingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSamplingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeSamplingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSamplingConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializeSchedulerConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSchedulerConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializeSchedulerConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSchedulerConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeSocketStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSocketState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeSocketStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSocketState::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeSpecDecFastLogitsInfoERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSpecDecFastLogitsInfo"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeSpecDecFastLogitsInfoERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSpecDecFastLogitsInfo::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization28deserializeSpecDecodingStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSpecDecodingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization28deserializeSpecDecodingStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSpecDecodingStats::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeSpeculativeDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSpeculativeDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeSpeculativeDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSpeculativeDecodingConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization30deserializeStaticBatchingStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeStaticBatchingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization30deserializeStaticBatchingStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeStaticBatchingStats::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeStringERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeString"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeStringERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeString::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeTensorERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeTensor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeTensorERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeTensor::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeTimePointERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeTimePoint"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeTimePointERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeTimePoint::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeTokenRangeRetentionConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeTokenRangeRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeTokenRangeRetentionConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeTokenRangeRetentionConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK10LoraConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11DebugConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11EagleConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11MropeConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12DecodingModeRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12KvCacheStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12OutputConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12RequestStageRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12RequestStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK13KvCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14DecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ExecutorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStats", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ParallelConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14SamplingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15MultimodalInputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15PeftCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15SchedulerConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK16AdditionalOutputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK17SpecDecodingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18ContextPhaseParamsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18DynamicBatchConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18OrchestratorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18PromptTuningConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18RequestPerfMetricsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK19StaticBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20DataTransceiverState", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20DataTransceiverStateRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20GuidedDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20GuidedDecodingParamsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21AdditionalModelOutputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21InflightBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22CacheTransceiverConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22DisServingRequestStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22KvCacheRetentionConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK23LookaheadDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK24RequestStatsPerIteration", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK24RequestStatsPerIterationRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25ExternalDraftTokensConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25SpeculativeDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK29ExtendedRuntimePerfKnobConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK33SpeculativeDecodingFastLogitsInfoRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6ResultRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6TensorRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK7RequestRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK8ResponseRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN18RequestPerfMetrics9TimePointERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN22KvCacheRetentionConfig25TokenRangeRetentionConfigERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10AgentStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10CacheStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache11SocketStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache9CommStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI14IterationStatsEE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI24RequestStatsPerIterationEE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI8ResponseEE", "tensorrt_llm::executor::Serialization::serialize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21AdditionalModelOutputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::additionalModelOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK16AdditionalOutputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::additionalOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22CacheTransceiverConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::cacheTransceiverConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK10LoraConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11MropeConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12OutputConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14SamplingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18PromptTuningConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25ExternalDraftTokensConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18ContextPhaseParamsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::contextPhaseParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20DataTransceiverState", "tensorrt_llm::executor::Serialization::serialize::dataTransceiverState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20DataTransceiverStateRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::dataTransceiverState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11DebugConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::debugConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14DecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::decodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12DecodingModeRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::decodingMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18DynamicBatchConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::dynamicBatchConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11EagleConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::eagleConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ExecutorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::executorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK29ExtendedRuntimePerfKnobConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::extendedRuntimePerfKnobConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20GuidedDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::guidedDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20GuidedDecodingParamsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::guidedDecodingParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21InflightBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::inflightBatchingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK33SpeculativeDecodingFastLogitsInfoRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::info"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStats", "tensorrt_llm::executor::Serialization::serialize::iterStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::iterStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI14IterationStatsEE", "tensorrt_llm::executor::Serialization::serialize::iterStatsVec"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK13KvCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::kvCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22KvCacheRetentionConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::kvCacheRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12KvCacheStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::kvCacheStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK23LookaheadDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::lookaheadDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18RequestPerfMetricsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::metrics"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15MultimodalInputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::multimodalInput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18OrchestratorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::orchestratorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK10LoraConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11DebugConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11EagleConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11MropeConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12DecodingModeRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12KvCacheStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12OutputConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12RequestStageRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12RequestStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK13KvCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14DecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ExecutorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ParallelConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14SamplingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15MultimodalInputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15PeftCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15SchedulerConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK16AdditionalOutputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK17SpecDecodingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18ContextPhaseParamsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18DynamicBatchConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18OrchestratorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18PromptTuningConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18RequestPerfMetricsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK19StaticBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20DataTransceiverStateRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20GuidedDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20GuidedDecodingParamsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21AdditionalModelOutputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21InflightBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22CacheTransceiverConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22DisServingRequestStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22KvCacheRetentionConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK23LookaheadDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK24RequestStatsPerIterationRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25ExternalDraftTokensConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25SpeculativeDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK29ExtendedRuntimePerfKnobConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK33SpeculativeDecodingFastLogitsInfoRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6ResultRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6TensorRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK7RequestRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK8ResponseRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN18RequestPerfMetrics9TimePointERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN22KvCacheRetentionConfig25TokenRangeRetentionConfigERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10AgentStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10CacheStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache11SocketStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache9CommStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ParallelConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::parallelConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15PeftCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::peftCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK7RequestRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::request"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12RequestStageRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::requestStage"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI24RequestStatsPerIterationEE", "tensorrt_llm::executor::Serialization::serialize::requestStatsVec"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK8ResponseRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::response"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI8ResponseEE", "tensorrt_llm::executor::Serialization::serialize::responses"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6ResultRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::result"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15SchedulerConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::schedulerConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25SpeculativeDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::specDecConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK17SpecDecodingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::specDecodingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12RequestStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK24RequestStatsPerIteration", "tensorrt_llm::executor::Serialization::serialize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK24RequestStatsPerIterationRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10AgentStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10CacheStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache11SocketStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache9CommStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK19StaticBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::staticBatchingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22DisServingRequestStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::stats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6TensorRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::tensor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN22KvCacheRetentionConfig25TokenRangeRetentionConfigERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::tokenRangeRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN18RequestPerfMetrics9TimePointERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::tp"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK10LoraConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11DebugConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11EagleConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11MropeConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12DecodingMode", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12KvCacheStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12OutputConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12RequestStage", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12RequestStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK13KvCacheConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14DecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ExecutorConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14IterationStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ParallelConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14SamplingConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15MultimodalInput", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15PeftCacheConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15SchedulerConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK16AdditionalOutput", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK17SpecDecodingStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18ContextPhaseParams", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18DynamicBatchConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18OrchestratorConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18PromptTuningConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18RequestPerfMetrics", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK19StaticBatchingStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20DataTransceiverState", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20GuidedDecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20GuidedDecodingParams", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK21AdditionalModelOutput", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK21InflightBatchingStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22CacheTransceiverConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22DisServingRequestStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22KvCacheRetentionConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK23LookaheadDecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK24RequestStatsPerIteration", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK25ExternalDraftTokensConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK25SpeculativeDecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK33SpeculativeDecodingFastLogitsInfo", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Result", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Tensor", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK7Request", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK8Response", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN18RequestPerfMetrics9TimePointE", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN22KvCacheRetentionConfig25TokenRangeRetentionConfigE", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache10AgentStateE", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache10CacheStateE", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache11SocketStateE", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache9CommStateE", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK21AdditionalModelOutput", "tensorrt_llm::executor::Serialization::serializedSize::additionalModelOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK16AdditionalOutput", "tensorrt_llm::executor::Serialization::serializedSize::additionalOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22CacheTransceiverConfig", "tensorrt_llm::executor::Serialization::serializedSize::cacheTransceiverConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK10LoraConfig", "tensorrt_llm::executor::Serialization::serializedSize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11MropeConfig", "tensorrt_llm::executor::Serialization::serializedSize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12OutputConfig", "tensorrt_llm::executor::Serialization::serializedSize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14SamplingConfig", "tensorrt_llm::executor::Serialization::serializedSize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18PromptTuningConfig", "tensorrt_llm::executor::Serialization::serializedSize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK25ExternalDraftTokensConfig", "tensorrt_llm::executor::Serialization::serializedSize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18ContextPhaseParams", "tensorrt_llm::executor::Serialization::serializedSize::contextPhaseParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20DataTransceiverState", "tensorrt_llm::executor::Serialization::serializedSize::dataTransceiverState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11DebugConfig", "tensorrt_llm::executor::Serialization::serializedSize::debugConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14DecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize::decodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12DecodingMode", "tensorrt_llm::executor::Serialization::serializedSize::decodingMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22DisServingRequestStats", "tensorrt_llm::executor::Serialization::serializedSize::disServingRequestStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18DynamicBatchConfig", "tensorrt_llm::executor::Serialization::serializedSize::dynamicBatchConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11EagleConfig", "tensorrt_llm::executor::Serialization::serializedSize::eagleConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ExecutorConfig", "tensorrt_llm::executor::Serialization::serializedSize::executorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::Serialization::serializedSize::extendedRuntimePerfKnobConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20GuidedDecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize::guidedDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20GuidedDecodingParams", "tensorrt_llm::executor::Serialization::serializedSize::guidedDecodingParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK21InflightBatchingStats", "tensorrt_llm::executor::Serialization::serializedSize::inflightBatchingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK33SpeculativeDecodingFastLogitsInfo", "tensorrt_llm::executor::Serialization::serializedSize::info"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14IterationStats", "tensorrt_llm::executor::Serialization::serializedSize::iterStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK13KvCacheConfig", "tensorrt_llm::executor::Serialization::serializedSize::kvCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22KvCacheRetentionConfig", "tensorrt_llm::executor::Serialization::serializedSize::kvCacheRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12KvCacheStats", "tensorrt_llm::executor::Serialization::serializedSize::kvCacheStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK23LookaheadDecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize::lookaheadDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18RequestPerfMetrics", "tensorrt_llm::executor::Serialization::serializedSize::metrics"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15MultimodalInput", "tensorrt_llm::executor::Serialization::serializedSize::multimodalInput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18OrchestratorConfig", "tensorrt_llm::executor::Serialization::serializedSize::orchestratorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ParallelConfig", "tensorrt_llm::executor::Serialization::serializedSize::parallelConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15PeftCacheConfig", "tensorrt_llm::executor::Serialization::serializedSize::peftCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK7Request", "tensorrt_llm::executor::Serialization::serializedSize::request"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12RequestStage", "tensorrt_llm::executor::Serialization::serializedSize::requestStage"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK8Response", "tensorrt_llm::executor::Serialization::serializedSize::response"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Result", "tensorrt_llm::executor::Serialization::serializedSize::result"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15SchedulerConfig", "tensorrt_llm::executor::Serialization::serializedSize::schedulerConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK25SpeculativeDecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize::specDecConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK17SpecDecodingStats", "tensorrt_llm::executor::Serialization::serializedSize::specDecodingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12RequestStats", "tensorrt_llm::executor::Serialization::serializedSize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK24RequestStatsPerIteration", "tensorrt_llm::executor::Serialization::serializedSize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache10AgentStateE", "tensorrt_llm::executor::Serialization::serializedSize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache10CacheStateE", "tensorrt_llm::executor::Serialization::serializedSize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache11SocketStateE", "tensorrt_llm::executor::Serialization::serializedSize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache9CommStateE", "tensorrt_llm::executor::Serialization::serializedSize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK19StaticBatchingStats", "tensorrt_llm::executor::Serialization::serializedSize::staticBatchingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Tensor", "tensorrt_llm::executor::Serialization::serializedSize::tensor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN22KvCacheRetentionConfig25TokenRangeRetentionConfigE", "tensorrt_llm::executor::Serialization::serializedSize::tokenRangeRetentionConfig"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor5ShapeE", "tensorrt_llm::executor::Shape"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor5Shape4BaseE", "tensorrt_llm::executor::Shape::Base"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor5Shape9DimType64E", "tensorrt_llm::executor::Shape::DimType64"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeENSt16initializer_listI9DimType64EE", "tensorrt_llm::executor::Shape::Shape"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEPK9DimType64N4Base9size_typeE", "tensorrt_llm::executor::Shape::Shape"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEv", "tensorrt_llm::executor::Shape::Shape"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEPK9DimType64N4Base9size_typeE", "tensorrt_llm::executor::Shape::Shape::data"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeENSt16initializer_listI9DimType64EE", "tensorrt_llm::executor::Shape::Shape::dims"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEPK9DimType64N4Base9size_typeE", "tensorrt_llm::executor::Shape::Shape::size"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor10SizeType32E", "tensorrt_llm::executor::SizeType32"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor10SizeType64E", "tensorrt_llm::executor::SizeType64"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStatsE", "tensorrt_llm::executor::SpecDecodingStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats16acceptanceLengthE", "tensorrt_llm::executor::SpecDecodingStats::acceptanceLength"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats13draftOverheadE", "tensorrt_llm::executor::SpecDecodingStats::draftOverhead"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats13iterLatencyMSE", "tensorrt_llm::executor::SpecDecodingStats::iterLatencyMS"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats17numAcceptedTokensE", "tensorrt_llm::executor::SpecDecodingStats::numAcceptedTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats14numDraftTokensE", "tensorrt_llm::executor::SpecDecodingStats::numDraftTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats26numRequestsWithDraftTokensE", "tensorrt_llm::executor::SpecDecodingStats::numRequestsWithDraftTokens"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor25SpeculativeDecodingConfigE", "tensorrt_llm::executor::SpeculativeDecodingConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor25SpeculativeDecodingConfig25SpeculativeDecodingConfigEb", "tensorrt_llm::executor::SpeculativeDecodingConfig::SpeculativeDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25SpeculativeDecodingConfig25SpeculativeDecodingConfigEb", "tensorrt_llm::executor::SpeculativeDecodingConfig::SpeculativeDecodingConfig::fastLogits"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25SpeculativeDecodingConfig10fastLogitsE", "tensorrt_llm::executor::SpeculativeDecodingConfig::fastLogits"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor25SpeculativeDecodingConfigeqERK25SpeculativeDecodingConfig", "tensorrt_llm::executor::SpeculativeDecodingConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor25SpeculativeDecodingConfigeqERK25SpeculativeDecodingConfig", "tensorrt_llm::executor::SpeculativeDecodingConfig::operator==::other"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor33SpeculativeDecodingFastLogitsInfoE", "tensorrt_llm::executor::SpeculativeDecodingFastLogitsInfo"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor33SpeculativeDecodingFastLogitsInfo18draftParticipantIdE", "tensorrt_llm::executor::SpeculativeDecodingFastLogitsInfo::draftParticipantId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor33SpeculativeDecodingFastLogitsInfo14draftRequestIdE", "tensorrt_llm::executor::SpeculativeDecodingFastLogitsInfo::draftRequestId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor33SpeculativeDecodingFastLogitsInfo8toTensorEv", "tensorrt_llm::executor::SpeculativeDecodingFastLogitsInfo::toTensor"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStatsE", "tensorrt_llm::executor::StaticBatchingStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats13emptyGenSlotsE", "tensorrt_llm::executor::StaticBatchingStats::emptyGenSlots"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats18numContextRequestsE", "tensorrt_llm::executor::StaticBatchingStats::numContextRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats12numCtxTokensE", "tensorrt_llm::executor::StaticBatchingStats::numCtxTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats12numGenTokensE", "tensorrt_llm::executor::StaticBatchingStats::numGenTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats20numScheduledRequestsE", "tensorrt_llm::executor::StaticBatchingStats::numScheduledRequests"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor9StreamPtrE", "tensorrt_llm::executor::StreamPtr"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor6TensorE", "tensorrt_llm::executor::Tensor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::CudaStreamPtr"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor6Tensor4ImplE", "tensorrt_llm::executor::Tensor::Impl"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::Tensor::Tensor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERK6Tensor", "tensorrt_llm::executor::Tensor::Tensor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERR6Tensor", "tensorrt_llm::executor::Tensor::Tensor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorEv", "tensorrt_llm::executor::Tensor::Tensor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERK6Tensor", "tensorrt_llm::executor::Tensor::Tensor::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERR6Tensor", "tensorrt_llm::executor::Tensor::Tensor::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::Tensor::Tensor::tensor"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor6copyToENSt10shared_ptrI4ImplEE13CudaStreamPtr", "tensorrt_llm::executor::Tensor::copyTo"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor6copyToENSt10shared_ptrI4ImplEE13CudaStreamPtr", "tensorrt_llm::executor::Tensor::copyTo::stream"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor6copyToENSt10shared_ptrI4ImplEE13CudaStreamPtr", "tensorrt_llm::executor::Tensor::copyTo::tensor"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToCpuEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToCpu"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToCpuEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToCpu::stream"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToGpuEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToGpu"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToGpuEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToGpu::stream"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor13copyToManagedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToManaged"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor13copyToManagedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToManaged::stream"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor12copyToPinnedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToPinned"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor12copyToPinnedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToPinned::stream"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor18copyToPooledPinnedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToPooledPinned"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor18copyToPooledPinnedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToPooledPinned::stream"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3cpuE6Tensor5Shape", "tensorrt_llm::executor::Tensor::cpu"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3cpuE8DataType5Shape", "tensorrt_llm::executor::Tensor::cpu"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3cpuE6Tensor5Shape", "tensorrt_llm::executor::Tensor::cpu::T"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3cpuE8DataType5Shape", "tensorrt_llm::executor::Tensor::cpu::dataType"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3cpuE6Tensor5Shape", "tensorrt_llm::executor::Tensor::cpu::shape"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3cpuE8DataType5Shape", "tensorrt_llm::executor::Tensor::cpu::shape"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::Tensor::detail::ofITensor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::Tensor::detail::ofITensor::tensor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9toITensorERK6Tensor", "tensorrt_llm::executor::Tensor::detail::toITensor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9toITensorERK6Tensor", "tensorrt_llm::executor::Tensor::detail::toITensor::tensor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7getDataEv", "tensorrt_llm::executor::Tensor::getData"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor7getDataEv", "tensorrt_llm::executor::Tensor::getData"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor11getDataTypeEv", "tensorrt_llm::executor::Tensor::getDataType"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor13getMemoryTypeEv", "tensorrt_llm::executor::Tensor::getMemoryType"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor14getRuntimeTypeE8DataTypev", "tensorrt_llm::executor::Tensor::getRuntimeType"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor14getRuntimeTypeE8DataTypev", "tensorrt_llm::executor::Tensor::getRuntimeType::T"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor8getShapeEv", "tensorrt_llm::executor::Tensor::getShape"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor7getSizeEv", "tensorrt_llm::executor::Tensor::getSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor14getSizeInBytesEv", "tensorrt_llm::executor::Tensor::getSizeInBytes"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3gpuE6Tensor13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3gpuE8DataType13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3gpuE6Tensor13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::T"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3gpuE8DataType13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::dataType"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3gpuE6Tensor13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::shape"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3gpuE8DataType13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::shape"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3gpuE6Tensor13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::stream"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3gpuE8DataType13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::stream"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7mTensorE", "tensorrt_llm::executor::Tensor::mTensor"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor7managedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::managed"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7managedE8DataType5Shape", "tensorrt_llm::executor::Tensor::managed"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor7managedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::managed::T"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7managedE8DataType5Shape", "tensorrt_llm::executor::Tensor::managed::dataType"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor7managedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::managed::shape"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7managedE8DataType5Shape", "tensorrt_llm::executor::Tensor::managed::shape"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorP1T5Shape", "tensorrt_llm::executor::Tensor::of"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorR1T", "tensorrt_llm::executor::Tensor::of"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor2ofE8DataTypePv5Shape", "tensorrt_llm::executor::Tensor::of"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorP1T5Shape", "tensorrt_llm::executor::Tensor::of::T"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorR1T", "tensorrt_llm::executor::Tensor::of::T"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorP1T5Shape", "tensorrt_llm::executor::Tensor::of::data"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorR1T", "tensorrt_llm::executor::Tensor::of::data"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor2ofE8DataTypePv5Shape", "tensorrt_llm::executor::Tensor::of::data"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor2ofE8DataTypePv5Shape", "tensorrt_llm::executor::Tensor::of::dataType"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorP1T5Shape", "tensorrt_llm::executor::Tensor::of::shape"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor2ofE8DataTypePv5Shape", "tensorrt_llm::executor::Tensor::of::shape"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6TensorcvbEv", "tensorrt_llm::executor::Tensor::operator bool"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6TensorneERK6Tensor", "tensorrt_llm::executor::Tensor::operator!="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6TensorneERK6Tensor", "tensorrt_llm::executor::Tensor::operator!=::rhs"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6TensoraSERK6Tensor", "tensorrt_llm::executor::Tensor::operator="], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6TensoraSERR6Tensor", "tensorrt_llm::executor::Tensor::operator="], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6TensoraSERK6Tensor", "tensorrt_llm::executor::Tensor::operator=::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6TensoraSERR6Tensor", "tensorrt_llm::executor::Tensor::operator=::other"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6TensoreqERK6Tensor", "tensorrt_llm::executor::Tensor::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6TensoreqERK6Tensor", "tensorrt_llm::executor::Tensor::operator==::rhs"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor6pinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pinned"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6pinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pinned"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor6pinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pinned::T"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6pinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pinned::dataType"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor6pinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pinned::shape"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6pinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pinned::shape"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor12pooledPinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pooledPinned"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor12pooledPinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pooledPinned"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor12pooledPinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pooledPinned::T"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor12pooledPinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pooledPinned::dataType"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor12pooledPinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pooledPinned::shape"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor12pooledPinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pooledPinned::shape"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7setFromERK6Tensor13CudaStreamPtr", "tensorrt_llm::executor::Tensor::setFrom"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7setFromERK6Tensor13CudaStreamPtr", "tensorrt_llm::executor::Tensor::setFrom::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7setFromERK6Tensor13CudaStreamPtr", "tensorrt_llm::executor::Tensor::setFrom::stream"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7setZeroE13CudaStreamPtr", "tensorrt_llm::executor::Tensor::setZero"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7setZeroE13CudaStreamPtr", "tensorrt_llm::executor::Tensor::setZero::stream"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6TensorD0Ev", "tensorrt_llm::executor::Tensor::~Tensor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor9TensorPtrE", "tensorrt_llm::executor::TensorPtr"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor11TokenIdTypeE", "tensorrt_llm::executor::TokenIdType"], [0, 2, 1, "_CPPv4I0_bEN12tensorrt_llm8executor10TypeTraitsE", "tensorrt_llm::executor::TypeTraits"], [0, 8, 1, "_CPPv4I0_bEN12tensorrt_llm8executor10TypeTraitsE", "tensorrt_llm::executor::TypeTraits::T"], [0, 2, 1, "_CPPv4I0EN12tensorrt_llm8executor10TypeTraitsIP1TEE", "tensorrt_llm::executor::TypeTraits<T*>"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor10TypeTraitsIP1TEE", "tensorrt_llm::executor::TypeTraits<T*>::T"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIP1TE5valueE", "tensorrt_llm::executor::TypeTraits<T*>::value"], [0, 2, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsIbEE", "tensorrt_llm::executor::TypeTraits<bool>"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIbE5valueE", "tensorrt_llm::executor::TypeTraits<bool>::value"], [0, 2, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsIfEE", "tensorrt_llm::executor::TypeTraits<float>"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIfE5valueE", "tensorrt_llm::executor::TypeTraits<float>::value"], [0, 2, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsI4halfEE", "tensorrt_llm::executor::TypeTraits<half>"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsI4halfE5valueE", "tensorrt_llm::executor::TypeTraits<half>::value"], [0, 2, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7int32_tEEE", "tensorrt_llm::executor::TypeTraits<std::int32_t>"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7int32_tEE5valueE", "tensorrt_llm::executor::TypeTraits<std::int32_t>::value"], [0, 2, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7int64_tEEE", "tensorrt_llm::executor::TypeTraits<std::int64_t>"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7int64_tEE5valueE", "tensorrt_llm::executor::TypeTraits<std::int64_t>::value"], [0, 2, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt6int8_tEEE", "tensorrt_llm::executor::TypeTraits<std::int8_t>"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt6int8_tEE5valueE", "tensorrt_llm::executor::TypeTraits<std::int8_t>::value"], [0, 2, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7uint8_tEEE", "tensorrt_llm::executor::TypeTraits<std::uint8_t>"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7uint8_tEE5valueE", "tensorrt_llm::executor::TypeTraits<std::uint8_t>::value"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor11VecLogProbsE", "tensorrt_llm::executor::VecLogProbs"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor16VecTokenExtraIdsE", "tensorrt_llm::executor::VecTokenExtraIds"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor9VecTokensE", "tensorrt_llm::executor::VecTokens"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor6detailE", "tensorrt_llm::executor::detail"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor6detail9DimType64E", "tensorrt_llm::executor::detail::DimType64"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::detail::ofITensor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::detail::ofITensor::tensor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6detail9toITensorERK6Tensor", "tensorrt_llm::executor::detail::toITensor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6detail9toITensorERK6Tensor", "tensorrt_llm::executor::detail::toITensor::tensor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executorE", "tensorrt_llm::executor::disagg_executor"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestratorE", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator26DisaggExecutorOrchestratorERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorIN8executor14ExecutorConfigEEERKNSt6vectorIN8executor14ExecutorConfigEEEbb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::DisaggExecutorOrchestrator"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator26DisaggExecutorOrchestratorERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorIN8executor14ExecutorConfigEEERKNSt6vectorIN8executor14ExecutorConfigEEEbb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::DisaggExecutorOrchestrator::ctxEnginePaths"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator26DisaggExecutorOrchestratorERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorIN8executor14ExecutorConfigEEERKNSt6vectorIN8executor14ExecutorConfigEEEbb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::DisaggExecutorOrchestrator::ctxExecutorConfigs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator26DisaggExecutorOrchestratorERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorIN8executor14ExecutorConfigEEERKNSt6vectorIN8executor14ExecutorConfigEEEbb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::DisaggExecutorOrchestrator::genEnginePaths"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator26DisaggExecutorOrchestratorERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorIN8executor14ExecutorConfigEEERKNSt6vectorIN8executor14ExecutorConfigEEEbb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::DisaggExecutorOrchestrator::genExecutorConfigs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator26DisaggExecutorOrchestratorERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorIN8executor14ExecutorConfigEEERKNSt6vectorIN8executor14ExecutorConfigEEEbb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::DisaggExecutorOrchestrator::hasContextAwaitThreads"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator26DisaggExecutorOrchestratorERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorIN8executor14ExecutorConfigEEERKNSt6vectorIN8executor14ExecutorConfigEEEbb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::DisaggExecutorOrchestrator::hasGenAwaitThreads"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator21awaitContextResponsesERKNSt8optionalINSt6chrono12millisecondsEEENSt8optionalIiEE", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::awaitContextResponses"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator21awaitContextResponsesERKNSt8optionalINSt6chrono12millisecondsEEENSt8optionalIiEE", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::awaitContextResponses::contextIdx"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator21awaitContextResponsesERKNSt8optionalINSt6chrono12millisecondsEEENSt8optionalIiEE", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::awaitContextResponses::timeout"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator24awaitGenerationResponsesERKNSt8optionalINSt6chrono12millisecondsEEENSt8optionalIiEE", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::awaitGenerationResponses"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator24awaitGenerationResponsesERKNSt8optionalINSt6chrono12millisecondsEEENSt8optionalIiEE", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::awaitGenerationResponses::genIdx"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator24awaitGenerationResponsesERKNSt8optionalINSt6chrono12millisecondsEEENSt8optionalIiEE", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::awaitGenerationResponses::timeout"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator10canEnqueueEv", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::canEnqueue"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator14enqueueContextERKNSt6vectorIN5texec7RequestEEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueContext"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator14enqueueContextERKNSt6vectorIN5texec7RequestEEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueContext::batch"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator14enqueueContextERKNSt6vectorIN5texec7RequestEEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueContext::requests"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator14enqueueContextERKNSt6vectorIN5texec7RequestEEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueContext::selectContextId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator17enqueueGenerationERKNSt6vectorIN5texec7RequestEEERKNSt6vectorI6IdTypeEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueGeneration"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator17enqueueGenerationERKNSt6vectorIN5texec7RequestEEERKNSt6vectorI6IdTypeEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueGeneration::batch"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator17enqueueGenerationERKNSt6vectorIN5texec7RequestEEERKNSt6vectorI6IdTypeEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueGeneration::globalRequestIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator17enqueueGenerationERKNSt6vectorIN5texec7RequestEEERKNSt6vectorI6IdTypeEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueGeneration::requests"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator17enqueueGenerationERKNSt6vectorIN5texec7RequestEEERKNSt6vectorI6IdTypeEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueGeneration::selectGenIdx"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator19getContextExecutorsEv", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::getContextExecutors"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator15getGenExecutorsEv", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::getGenExecutors"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator5mImplE", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::mImpl"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestratorD0Ev", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::~DisaggExecutorOrchestrator"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdE", "tensorrt_llm::executor::disagg_executor::ResponseWithId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERK14ResponseWithId", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERKN12tensorrt_llm8executor8ResponseE6IdType", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERR14ResponseWithId", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERRN12tensorrt_llm8executor8ResponseE6IdType", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERKN12tensorrt_llm8executor8ResponseE6IdType", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId::gid"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERRN12tensorrt_llm8executor8ResponseE6IdType", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId::gid"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERK14ResponseWithId", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERR14ResponseWithId", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERKN12tensorrt_llm8executor8ResponseE6IdType", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId::response"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERRN12tensorrt_llm8executor8ResponseE6IdType", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId::response"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId3gidE", "tensorrt_llm::executor::disagg_executor::ResponseWithId::gid"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdaSERK14ResponseWithId", "tensorrt_llm::executor::disagg_executor::ResponseWithId::operator="], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdaSERR14ResponseWithId", "tensorrt_llm::executor::disagg_executor::ResponseWithId::operator="], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdaSERK14ResponseWithId", "tensorrt_llm::executor::disagg_executor::ResponseWithId::operator=::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdaSERR14ResponseWithId", "tensorrt_llm::executor::disagg_executor::ResponseWithId::operator=::other"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId8responseE", "tensorrt_llm::executor::disagg_executor::ResponseWithId::response"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdD0Ev", "tensorrt_llm::executor::disagg_executor::ResponseWithId::~ResponseWithId"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor8kv_cacheE", "tensorrt_llm::executor::kv_cache"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor8kv_cacheE", "tensorrt_llm::executor::kv_cache"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor8kv_cacheE", "tensorrt_llm::executor::kv_cache"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor8kv_cacheE", "tensorrt_llm::executor::kv_cache"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9AgentDescE", "tensorrt_llm::executor::kv_cache::AgentDesc"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9AgentDesc9AgentDescENSt6stringE", "tensorrt_llm::executor::kv_cache::AgentDesc::AgentDesc"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9AgentDesc9AgentDescENSt6stringE", "tensorrt_llm::executor::kv_cache::AgentDesc::AgentDesc::backendAgentDesc"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9AgentDesc19getBackendAgentDescEv", "tensorrt_llm::executor::kv_cache::AgentDesc::getBackendAgentDesc"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9AgentDesc17mBackendAgentDescE", "tensorrt_llm::executor::kv_cache::AgentDesc::mBackendAgentDesc"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentStateE", "tensorrt_llm::executor::kv_cache::AgentState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState10AgentStateENSt6stringENSt6stringE", "tensorrt_llm::executor::kv_cache::AgentState::AgentState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState10AgentStateEv", "tensorrt_llm::executor::kv_cache::AgentState::AgentState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState10AgentStateENSt6stringENSt6stringE", "tensorrt_llm::executor::kv_cache::AgentState::AgentState::agentName"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState10AgentStateENSt6stringENSt6stringE", "tensorrt_llm::executor::kv_cache::AgentState::AgentState::connectionInfo"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState10mAgentNameE", "tensorrt_llm::executor::kv_cache::AgentState::mAgentName"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState15mConnectionInfoE", "tensorrt_llm::executor::kv_cache::AgentState::mConnectionInfo"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10AgentStateeqERK10AgentState", "tensorrt_llm::executor::kv_cache::AgentState::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10AgentStateeqERK10AgentState", "tensorrt_llm::executor::kv_cache::AgentState::operator==::other"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10AgentState8toStringEv", "tensorrt_llm::executor::kv_cache::AgentState::toString"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15BaseAgentConfigE", "tensorrt_llm::executor::kv_cache::BaseAgentConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15BaseAgentConfig5mNameE", "tensorrt_llm::executor::kv_cache::BaseAgentConfig::mName"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15BaseAgentConfig13useProgThreadE", "tensorrt_llm::executor::kv_cache::BaseAgentConfig::useProgThread"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgentE", "tensorrt_llm::executor::kv_cache::BaseTransferAgent"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent16checkRemoteDescsERKNSt6stringERK11MemoryDescs", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::checkRemoteDescs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent16checkRemoteDescsERKNSt6stringERK11MemoryDescs", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::checkRemoteDescs::memoryDescs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent16checkRemoteDescsERKNSt6stringERK11MemoryDescs", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::checkRemoteDescs::name"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent18connectRemoteAgentERKNSt6stringERK18ConnectionInfoType", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::connectRemoteAgent"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent18connectRemoteAgentERKNSt6stringERK18ConnectionInfoType", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::connectRemoteAgent::connectionInfo"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent18connectRemoteAgentERKNSt6stringERK18ConnectionInfoType", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::connectRemoteAgent::name"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent16deregisterMemoryERK13RegisterDescs", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::deregisterMemory"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent16deregisterMemoryERK13RegisterDescs", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::deregisterMemory::descs"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent17getConnectionInfoEv", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::getConnectionInfo"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent17getLocalAgentDescEv", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::getLocalAgentDesc"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent23getNotifiedSyncMessagesEv", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::getNotifiedSyncMessages"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent21invalidateRemoteAgentERKNSt6stringE", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::invalidateRemoteAgent"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent21invalidateRemoteAgentERKNSt6stringE", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::invalidateRemoteAgent::name"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent15loadRemoteAgentERKNSt6stringERK9AgentDesc", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::loadRemoteAgent"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent15loadRemoteAgentERKNSt6stringERK9AgentDesc", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::loadRemoteAgent::agentDesc"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent15loadRemoteAgentERKNSt6stringERK9AgentDesc", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::loadRemoteAgent::name"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent17notifySyncMessageERKNSt6stringERK11SyncMessage", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::notifySyncMessage"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent17notifySyncMessageERKNSt6stringERK11SyncMessage", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::notifySyncMessage::name"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent17notifySyncMessageERKNSt6stringERK11SyncMessage", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::notifySyncMessage::syncMessage"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent14registerMemoryERK13RegisterDescs", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::registerMemory"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent14registerMemoryERK13RegisterDescs", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::registerMemory::descs"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent22submitTransferRequestsERK15TransferRequest", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::submitTransferRequests"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent22submitTransferRequestsERK15TransferRequest", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::submitTransferRequests::request"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgentD0Ev", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::~BaseTransferAgent"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheStateE", "tensorrt_llm::executor::kv_cache::CacheState"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfigE", "tensorrt_llm::executor::kv_cache::CacheState::AttentionConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfig15AttentionConfigE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::AttentionConfig::AttentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfig15AttentionConfigE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::AttentionConfig::AttentionConfig::attentionType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfig15AttentionConfigE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::AttentionConfig::AttentionConfig::kvFactor"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfig14mAttentionTypeE", "tensorrt_llm::executor::kv_cache::CacheState::AttentionConfig::mAttentionType"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfig9mKvFactorE", "tensorrt_llm::executor::kv_cache::CacheState::AttentionConfig::mKvFactor"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState13AttentionTypeE", "tensorrt_llm::executor::kv_cache::CacheState::AttentionType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState13AttentionType8kDEFAULTE", "tensorrt_llm::executor::kv_cache::CacheState::AttentionType::kDEFAULT"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState13AttentionType4kMLAE", "tensorrt_llm::executor::kv_cache::CacheState::AttentionType::kMLA"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE11ModelConfigRKN7runtime11WorldConfigEN8nvinfer18DataTypeE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::CacheState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::DPrank"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::DPrank"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::DPsize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::DPsize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::attentionType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE11ModelConfigRKN7runtime11WorldConfigEN8nvinfer18DataTypeE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::attentionType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::attentionType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::dataType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE11ModelConfigRKN7runtime11WorldConfigEN8nvinfer18DataTypeE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::dataType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::dataType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::enableAttentionDP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::enableAttentionDP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::kvFactor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE11ModelConfigRKN7runtime11WorldConfigEN8nvinfer18DataTypeE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::kvFactor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::kvFactor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE11ModelConfigRKN7runtime11WorldConfigEN8nvinfer18DataTypeE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::modelConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::nbAttentionLayers"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::nbKvHeadPerLayer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::nbKvHeads"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::pipelineParallelism"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::pipelineParallelism"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::sizePerHead"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::sizePerHead"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::tensorParallelism"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::tensorParallelism"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::tokensPerBlock"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::tokensPerBlock"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE11ModelConfigRKN7runtime11WorldConfigEN8nvinfer18DataTypeE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::worldConfig"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState11ModelConfigE", "tensorrt_llm::executor::kv_cache::CacheState::ModelConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState11ModelConfig18mNbKvHeadsPerLayerE", "tensorrt_llm::executor::kv_cache::CacheState::ModelConfig::mNbKvHeadsPerLayer"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState11ModelConfig12mSizePerHeadE", "tensorrt_llm::executor::kv_cache::CacheState::ModelConfig::mSizePerHead"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState11ModelConfig15mTokensPerBlockE", "tensorrt_llm::executor::kv_cache::CacheState::ModelConfig::mTokensPerBlock"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState11ModelConfigeqERK11ModelConfig", "tensorrt_llm::executor::kv_cache::CacheState::ModelConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState11ModelConfigeqERK11ModelConfig", "tensorrt_llm::executor::kv_cache::CacheState::ModelConfig::operator==::other"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfigE", "tensorrt_llm::executor::kv_cache::CacheState::ParallelConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig7mDPrankE", "tensorrt_llm::executor::kv_cache::CacheState::ParallelConfig::mDPrank"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig7mDPsizeE", "tensorrt_llm::executor::kv_cache::CacheState::ParallelConfig::mDPsize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig18mEnableAttentionDPE", "tensorrt_llm::executor::kv_cache::CacheState::ParallelConfig::mEnableAttentionDP"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig20mPipelineParallelismE", "tensorrt_llm::executor::kv_cache::CacheState::ParallelConfig::mPipelineParallelism"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig18mTensorParallelismE", "tensorrt_llm::executor::kv_cache::CacheState::ParallelConfig::mTensorParallelism"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfigeqERK14ParallelConfig", "tensorrt_llm::executor::kv_cache::CacheState::ParallelConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfigeqERK14ParallelConfig", "tensorrt_llm::executor::kv_cache::CacheState::ParallelConfig::operator==::other"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState18getAttentionConfigEv", "tensorrt_llm::executor::kv_cache::CacheState::getAttentionConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState11getDataTypeEv", "tensorrt_llm::executor::kv_cache::CacheState::getDataType"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState14getModelConfigEv", "tensorrt_llm::executor::kv_cache::CacheState::getModelConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState17getParallelConfigEv", "tensorrt_llm::executor::kv_cache::CacheState::getParallelConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState16mAttentionConfigE", "tensorrt_llm::executor::kv_cache::CacheState::mAttentionConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState9mDataTypeE", "tensorrt_llm::executor::kv_cache::CacheState::mDataType"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState12mModelConfigE", "tensorrt_llm::executor::kv_cache::CacheState::mModelConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15mParallelConfigE", "tensorrt_llm::executor::kv_cache::CacheState::mParallelConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheStateeqERKN8kv_cache10CacheStateE", "tensorrt_llm::executor::kv_cache::CacheState::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheStateeqERKN8kv_cache10CacheStateE", "tensorrt_llm::executor::kv_cache::CacheState::operator==::other"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState8toStringEv", "tensorrt_llm::executor::kv_cache::CacheState::toString"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommStateE", "tensorrt_llm::executor::kv_cache::CommState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI10AgentStateEEi", "tensorrt_llm::executor::kv_cache::CommState::CommState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI10SizeType32EEi", "tensorrt_llm::executor::kv_cache::CommState::CommState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI11SocketStateEEi", "tensorrt_llm::executor::kv_cache::CommState::CommState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt8uint16_tENSt6stringE", "tensorrt_llm::executor::kv_cache::CommState::CommState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateEv", "tensorrt_llm::executor::kv_cache::CommState::CommState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI10AgentStateEEi", "tensorrt_llm::executor::kv_cache::CommState::CommState::agentState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt8uint16_tENSt6stringE", "tensorrt_llm::executor::kv_cache::CommState::CommState::ip"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt8uint16_tENSt6stringE", "tensorrt_llm::executor::kv_cache::CommState::CommState::port"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI10SizeType32EEi", "tensorrt_llm::executor::kv_cache::CommState::CommState::ranks"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI10AgentStateEEi", "tensorrt_llm::executor::kv_cache::CommState::CommState::selfIdx"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI10SizeType32EEi", "tensorrt_llm::executor::kv_cache::CommState::CommState::selfIdx"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI11SocketStateEEi", "tensorrt_llm::executor::kv_cache::CommState::CommState::selfIdx"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI11SocketStateEEi", "tensorrt_llm::executor::kv_cache::CommState::CommState::socketState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState13getAgentStateEv", "tensorrt_llm::executor::kv_cache::CommState::getAgentState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState11getMpiStateEv", "tensorrt_llm::executor::kv_cache::CommState::getMpiState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState10getSelfIdxEv", "tensorrt_llm::executor::kv_cache::CommState::getSelfIdx"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState14getSocketStateEv", "tensorrt_llm::executor::kv_cache::CommState::getSocketState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState12isAgentStateEv", "tensorrt_llm::executor::kv_cache::CommState::isAgentState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState10isMpiStateEv", "tensorrt_llm::executor::kv_cache::CommState::isMpiState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState13isSocketStateEv", "tensorrt_llm::executor::kv_cache::CommState::isSocketState"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState8mSelfIdxE", "tensorrt_llm::executor::kv_cache::CommState::mSelfIdx"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState6mStateE", "tensorrt_llm::executor::kv_cache::CommState::mState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommStateeqERK9CommState", "tensorrt_llm::executor::kv_cache::CommState::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommStateeqERK9CommState", "tensorrt_llm::executor::kv_cache::CommState::operator==::other"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState8toStringEv", "tensorrt_llm::executor::kv_cache::CommState::toString"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10ConnectionE", "tensorrt_llm::executor::kv_cache::Connection"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection12isThreadSafeEv", "tensorrt_llm::executor::kv_cache::Connection::isThreadSafe"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4recvERK11DataContextPv6size_t", "tensorrt_llm::executor::kv_cache::Connection::recv"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4recvERK11DataContextPv6size_t", "tensorrt_llm::executor::kv_cache::Connection::recv::ctx"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4recvERK11DataContextPv6size_t", "tensorrt_llm::executor::kv_cache::Connection::recv::data"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4recvERK11DataContextPv6size_t", "tensorrt_llm::executor::kv_cache::Connection::recv::size"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4sendERK11DataContextPKv6size_t", "tensorrt_llm::executor::kv_cache::Connection::send"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4sendERK11DataContextPKv6size_t", "tensorrt_llm::executor::kv_cache::Connection::send::ctx"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4sendERK11DataContextPKv6size_t", "tensorrt_llm::executor::kv_cache::Connection::send::data"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4sendERK11DataContextPKv6size_t", "tensorrt_llm::executor::kv_cache::Connection::send::size"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10ConnectionD0Ev", "tensorrt_llm::executor::kv_cache::Connection::~Connection"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache18ConnectionInfoTypeE", "tensorrt_llm::executor::kv_cache::ConnectionInfoType"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManagerE", "tensorrt_llm::executor::kv_cache::ConnectionManager"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache17ConnectionManager12getCommStateEv", "tensorrt_llm::executor::kv_cache::ConnectionManager::getCommState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManager14getConnectionsERK9CommState", "tensorrt_llm::executor::kv_cache::ConnectionManager::getConnections"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManager14getConnectionsERK9CommState", "tensorrt_llm::executor::kv_cache::ConnectionManager::getConnections::state"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManager11recvConnectERK11DataContextPv6size_t", "tensorrt_llm::executor::kv_cache::ConnectionManager::recvConnect"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManager11recvConnectERK11DataContextPv6size_t", "tensorrt_llm::executor::kv_cache::ConnectionManager::recvConnect::ctx"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManager11recvConnectERK11DataContextPv6size_t", "tensorrt_llm::executor::kv_cache::ConnectionManager::recvConnect::data"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManager11recvConnectERK11DataContextPv6size_t", "tensorrt_llm::executor::kv_cache::ConnectionManager::recvConnect::size"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManagerD0Ev", "tensorrt_llm::executor::kv_cache::ConnectionManager::~ConnectionManager"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11DataContextE", "tensorrt_llm::executor::kv_cache::DataContext"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11DataContext11DataContextEi", "tensorrt_llm::executor::kv_cache::DataContext::DataContext"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11DataContext11DataContextEi", "tensorrt_llm::executor::kv_cache::DataContext::DataContext::tag"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache11DataContext6getTagEv", "tensorrt_llm::executor::kv_cache::DataContext::getTag"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11DataContext4mTagE", "tensorrt_llm::executor::kv_cache::DataContext::mTag"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoaderE", "tensorrt_llm::executor::kv_cache::DynLibLoader"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader12DynLibLoaderERK12DynLibLoader", "tensorrt_llm::executor::kv_cache::DynLibLoader::DynLibLoader"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader12DynLibLoaderEv", "tensorrt_llm::executor::kv_cache::DynLibLoader::DynLibLoader"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader5dlSymEPvPKc", "tensorrt_llm::executor::kv_cache::DynLibLoader::dlSym"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader5dlSymEPvPKc", "tensorrt_llm::executor::kv_cache::DynLibLoader::dlSym::handle"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader5dlSymEPvPKc", "tensorrt_llm::executor::kv_cache::DynLibLoader::dlSym::symbol"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor8kv_cache12DynLibLoader18getFunctionPointerE9FunctionTRKNSt6stringERKNSt6stringE", "tensorrt_llm::executor::kv_cache::DynLibLoader::getFunctionPointer"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor8kv_cache12DynLibLoader18getFunctionPointerE9FunctionTRKNSt6stringERKNSt6stringE", "tensorrt_llm::executor::kv_cache::DynLibLoader::getFunctionPointer::FunctionT"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor8kv_cache12DynLibLoader18getFunctionPointerE9FunctionTRKNSt6stringERKNSt6stringE", "tensorrt_llm::executor::kv_cache::DynLibLoader::getFunctionPointer::funcName"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor8kv_cache12DynLibLoader18getFunctionPointerE9FunctionTRKNSt6stringERKNSt6stringE", "tensorrt_llm::executor::kv_cache::DynLibLoader::getFunctionPointer::libName"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader9getHandleERKNSt6stringE", "tensorrt_llm::executor::kv_cache::DynLibLoader::getHandle"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader9getHandleERKNSt6stringE", "tensorrt_llm::executor::kv_cache::DynLibLoader::getHandle::name"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader11getInstanceEv", "tensorrt_llm::executor::kv_cache::DynLibLoader::getInstance"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader9mDllMutexE", "tensorrt_llm::executor::kv_cache::DynLibLoader::mDllMutex"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader9mHandlersE", "tensorrt_llm::executor::kv_cache::DynLibLoader::mHandlers"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoaderaSERK12DynLibLoader", "tensorrt_llm::executor::kv_cache::DynLibLoader::operator="], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoaderD0Ev", "tensorrt_llm::executor::kv_cache::DynLibLoader::~DynLibLoader"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDescE", "tensorrt_llm::executor::kv_cache::MemoryDesc"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescE9uintptr_t6size_t8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescEPv6size_t8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescERKNSt6vectorIcEE8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescE9uintptr_t6size_t8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc::addr"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescEPv6size_t8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc::addr"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescE9uintptr_t6size_t8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc::deviceId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescEPv6size_t8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc::deviceId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescERKNSt6vectorIcEE8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc::deviceId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescE9uintptr_t6size_t8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc::len"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescEPv6size_t8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc::len"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescERKNSt6vectorIcEE8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc::vec"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc11deserializeERNSt7istreamE", "tensorrt_llm::executor::kv_cache::MemoryDesc::deserialize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc11deserializeERNSt7istreamE", "tensorrt_llm::executor::kv_cache::MemoryDesc::deserialize::is"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10MemoryDesc7getAddrEv", "tensorrt_llm::executor::kv_cache::MemoryDesc::getAddr"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10MemoryDesc11getDeviceIdEv", "tensorrt_llm::executor::kv_cache::MemoryDesc::getDeviceId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10MemoryDesc6getLenEv", "tensorrt_llm::executor::kv_cache::MemoryDesc::getLen"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc5mAddrE", "tensorrt_llm::executor::kv_cache::MemoryDesc::mAddr"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc9mDeviceIdE", "tensorrt_llm::executor::kv_cache::MemoryDesc::mDeviceId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc4mLenE", "tensorrt_llm::executor::kv_cache::MemoryDesc::mLen"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc9serializeERK10MemoryDescRNSt7ostreamE", "tensorrt_llm::executor::kv_cache::MemoryDesc::serialize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc9serializeERK10MemoryDescRNSt7ostreamE", "tensorrt_llm::executor::kv_cache::MemoryDesc::serialize::memoryDesc"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc9serializeERK10MemoryDescRNSt7ostreamE", "tensorrt_llm::executor::kv_cache::MemoryDesc::serialize::os"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc14serializedSizeERK10MemoryDesc", "tensorrt_llm::executor::kv_cache::MemoryDesc::serializedSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc14serializedSizeERK10MemoryDesc", "tensorrt_llm::executor::kv_cache::MemoryDesc::serializedSize::memoryDesc"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescsE", "tensorrt_llm::executor::kv_cache::MemoryDescs"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescs11MemoryDescsE10MemoryTypeNSt6vectorI10MemoryDescEE", "tensorrt_llm::executor::kv_cache::MemoryDescs::MemoryDescs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescs11MemoryDescsE10MemoryTypeNSt6vectorI10MemoryDescEE", "tensorrt_llm::executor::kv_cache::MemoryDescs::MemoryDescs::descs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescs11MemoryDescsE10MemoryTypeNSt6vectorI10MemoryDescEE", "tensorrt_llm::executor::kv_cache::MemoryDescs::MemoryDescs::type"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache11MemoryDescs8getDescsEv", "tensorrt_llm::executor::kv_cache::MemoryDescs::getDescs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache11MemoryDescs7getTypeEv", "tensorrt_llm::executor::kv_cache::MemoryDescs::getType"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescs6mDescsE", "tensorrt_llm::executor::kv_cache::MemoryDescs::mDescs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescs5mTypeE", "tensorrt_llm::executor::kv_cache::MemoryDescs::mType"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryTypeE", "tensorrt_llm::executor::kv_cache::MemoryType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType4kBLKE", "tensorrt_llm::executor::kv_cache::MemoryType::kBLK"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType5kDRAME", "tensorrt_llm::executor::kv_cache::MemoryType::kDRAM"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType5kFILEE", "tensorrt_llm::executor::kv_cache::MemoryType::kFILE"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType4kOBJE", "tensorrt_llm::executor::kv_cache::MemoryType::kOBJ"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType5kVRAME", "tensorrt_llm::executor::kv_cache::MemoryType::kVRAM"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache8MpiStateE", "tensorrt_llm::executor::kv_cache::MpiState"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache8MpiState6mRanksE", "tensorrt_llm::executor::kv_cache::MpiState::mRanks"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache8MpiStateeqERK8MpiState", "tensorrt_llm::executor::kv_cache::MpiState::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache8MpiStateeqERK8MpiState", "tensorrt_llm::executor::kv_cache::MpiState::operator==::other"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache8MpiState8toStringEv", "tensorrt_llm::executor::kv_cache::MpiState::toString"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache13RegisterDescsE", "tensorrt_llm::executor::kv_cache::RegisterDescs"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11SocketStateE", "tensorrt_llm::executor::kv_cache::SocketState"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11SocketState3mIpE", "tensorrt_llm::executor::kv_cache::SocketState::mIp"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11SocketState5mPortE", "tensorrt_llm::executor::kv_cache::SocketState::mPort"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache11SocketStateeqERK11SocketState", "tensorrt_llm::executor::kv_cache::SocketState::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache11SocketStateeqERK11SocketState", "tensorrt_llm::executor::kv_cache::SocketState::operator==::other"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache11SocketState8toStringEv", "tensorrt_llm::executor::kv_cache::SocketState::toString"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11SyncMessageE", "tensorrt_llm::executor::kv_cache::SyncMessage"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache13TransferDescsE", "tensorrt_llm::executor::kv_cache::TransferDescs"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10TransferOpE", "tensorrt_llm::executor::kv_cache::TransferOp"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10TransferOp5kREADE", "tensorrt_llm::executor::kv_cache::TransferOp::kREAD"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10TransferOp6kWRITEE", "tensorrt_llm::executor::kv_cache::TransferOp::kWRITE"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequestE", "tensorrt_llm::executor::kv_cache::TransferRequest"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest15TransferRequestE10TransferOp13TransferDescs13TransferDescsRKNSt6stringENSt8optionalI11SyncMessageEE", "tensorrt_llm::executor::kv_cache::TransferRequest::TransferRequest"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest15TransferRequestE10TransferOp13TransferDescs13TransferDescsRKNSt6stringENSt8optionalI11SyncMessageEE", "tensorrt_llm::executor::kv_cache::TransferRequest::TransferRequest::dstDescs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest15TransferRequestE10TransferOp13TransferDescs13TransferDescsRKNSt6stringENSt8optionalI11SyncMessageEE", "tensorrt_llm::executor::kv_cache::TransferRequest::TransferRequest::op"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest15TransferRequestE10TransferOp13TransferDescs13TransferDescsRKNSt6stringENSt8optionalI11SyncMessageEE", "tensorrt_llm::executor::kv_cache::TransferRequest::TransferRequest::remoteName"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest15TransferRequestE10TransferOp13TransferDescs13TransferDescsRKNSt6stringENSt8optionalI11SyncMessageEE", "tensorrt_llm::executor::kv_cache::TransferRequest::TransferRequest::srcDescs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest15TransferRequestE10TransferOp13TransferDescs13TransferDescsRKNSt6stringENSt8optionalI11SyncMessageEE", "tensorrt_llm::executor::kv_cache::TransferRequest::TransferRequest::syncMessage"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest11getDstDescsEv", "tensorrt_llm::executor::kv_cache::TransferRequest::getDstDescs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest5getOpEv", "tensorrt_llm::executor::kv_cache::TransferRequest::getOp"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest13getRemoteNameEv", "tensorrt_llm::executor::kv_cache::TransferRequest::getRemoteName"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest11getSrcDescsEv", "tensorrt_llm::executor::kv_cache::TransferRequest::getSrcDescs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest14getSyncMessageEv", "tensorrt_llm::executor::kv_cache::TransferRequest::getSyncMessage"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest9mDstDescsE", "tensorrt_llm::executor::kv_cache::TransferRequest::mDstDescs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest3mOpE", "tensorrt_llm::executor::kv_cache::TransferRequest::mOp"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest11mRemoteNameE", "tensorrt_llm::executor::kv_cache::TransferRequest::mRemoteName"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest9mSrcDescsE", "tensorrt_llm::executor::kv_cache::TransferRequest::mSrcDescs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest12mSyncMessageE", "tensorrt_llm::executor::kv_cache::TransferRequest::mSyncMessage"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache14TransferStatusE", "tensorrt_llm::executor::kv_cache::TransferStatus"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache14TransferStatus11isCompletedEv", "tensorrt_llm::executor::kv_cache::TransferStatus::isCompleted"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache14TransferStatus4waitEv", "tensorrt_llm::executor::kv_cache::TransferStatus::wait"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache14TransferStatusD0Ev", "tensorrt_llm::executor::kv_cache::TransferStatus::~TransferStatus"], [0, 3, 1, "_CPPv4IDpEN12tensorrt_llm8executor8kv_cache17makeTransferAgentENSt10unique_ptrI17BaseTransferAgentEERKNSt6stringEDpRR4Args", "tensorrt_llm::executor::kv_cache::makeTransferAgent"], [0, 8, 1, "_CPPv4IDpEN12tensorrt_llm8executor8kv_cache17makeTransferAgentENSt10unique_ptrI17BaseTransferAgentEERKNSt6stringEDpRR4Args", "tensorrt_llm::executor::kv_cache::makeTransferAgent::Args"], [0, 4, 1, "_CPPv4IDpEN12tensorrt_llm8executor8kv_cache17makeTransferAgentENSt10unique_ptrI17BaseTransferAgentEERKNSt6stringEDpRR4Args", "tensorrt_llm::executor::kv_cache::makeTransferAgent::args"], [0, 4, 1, "_CPPv4IDpEN12tensorrt_llm8executor8kv_cache17makeTransferAgentENSt10unique_ptrI17BaseTransferAgentEERKNSt6stringEDpRR4Args", "tensorrt_llm::executor::kv_cache::makeTransferAgent::backend"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE21ContextChunkingPolicy", "tensorrt_llm::executor::operator<<"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE23CapacitySchedulerPolicy", "tensorrt_llm::executor::operator<<"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE21ContextChunkingPolicy", "tensorrt_llm::executor::operator<<::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE23CapacitySchedulerPolicy", "tensorrt_llm::executor::operator<<::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE21ContextChunkingPolicy", "tensorrt_llm::executor::operator<<::policy"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE23CapacitySchedulerPolicy", "tensorrt_llm::executor::operator<<::policy"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7versionEv", "tensorrt_llm::executor::version"], [1, 1, 1, "_CPPv4N12tensorrt_llm6layersE", "tensorrt_llm::layers"], [0, 1, 1, "_CPPv4N12tensorrt_llm3mpiE", "tensorrt_llm::mpi"], [0, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [0, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffersE", "tensorrt_llm::runtime::AllReduceBuffers"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::fakeBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::hiddenSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::maxSequenceLength"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::worldConfig"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers9TensorPtrE", "tensorrt_llm::runtime::AllReduceBuffers::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers18mAllReduceCommPtrsE", "tensorrt_llm::runtime::AllReduceBuffers::mAllReduceCommPtrs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers9mFlagPtrsE", "tensorrt_llm::runtime::AllReduceBuffers::mFlagPtrs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers17mIpcMemoryHandlesE", "tensorrt_llm::runtime::AllReduceBuffers::mIpcMemoryHandles"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataTypeE", "tensorrt_llm::runtime::BufferDataType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb", "tensorrt_llm::runtime::BufferDataType::BufferDataType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb", "tensorrt_llm::runtime::BufferDataType::BufferDataType::_unsigned"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb", "tensorrt_llm::runtime::BufferDataType::BufferDataType::dataType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb", "tensorrt_llm::runtime::BufferDataType::BufferDataType::pointer"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType11getDataTypeEv", "tensorrt_llm::runtime::BufferDataType::getDataType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType7getSizeEv", "tensorrt_llm::runtime::BufferDataType::getSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType13getSizeInBitsEv", "tensorrt_llm::runtime::BufferDataType::getSizeInBits"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType9isPointerEv", "tensorrt_llm::runtime::BufferDataType::isPointer"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType10isUnsignedEv", "tensorrt_llm::runtime::BufferDataType::isUnsigned"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType15kTrtPointerTypeE", "tensorrt_llm::runtime::BufferDataType::kTrtPointerType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType9mDataTypeE", "tensorrt_llm::runtime::BufferDataType::mDataType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType8mPointerE", "tensorrt_llm::runtime::BufferDataType::mPointer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType9mUnsignedE", "tensorrt_llm::runtime::BufferDataType::mUnsigned"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataTypecvN8nvinfer18DataTypeEEv", "tensorrt_llm::runtime::BufferDataType::operator nvinfer1::DataType"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManagerE", "tensorrt_llm::runtime::BufferManager"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager13BufferManagerE13CudaStreamPtrb", "tensorrt_llm::runtime::BufferManager::BufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager13BufferManagerE13CudaStreamPtrb", "tensorrt_llm::runtime::BufferManager::BufferManager::stream"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager13BufferManagerE13CudaStreamPtrb", "tensorrt_llm::runtime::BufferManager::BufferManager::trimPool"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager14CudaMemPoolPtrE", "tensorrt_llm::runtime::BufferManager::CudaMemPoolPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::BufferManager::CudaStreamPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10IBufferPtrE", "tensorrt_llm::runtime::BufferManager::IBufferPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10ITensorPtrE", "tensorrt_llm::runtime::BufferManager::ITensorPtr"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::dims"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::memoryType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::memoryType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::size"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::type"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::type"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copy"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv", "tensorrt_llm::runtime::BufferManager::copy"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType", "tensorrt_llm::runtime::BufferManager::copy"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy::dst"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::dst"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv", "tensorrt_llm::runtime::BufferManager::copy::dst"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::dst"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy::dst"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::dstType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy::src"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::src"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv", "tensorrt_llm::runtime::BufferManager::copy::src"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::src"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy::src"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::srcType"], [1, 3, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10IBufferPtrRKNSt6vectorI1TEE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom"], [1, 3, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom"], [1, 3, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7ITensor10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom"], [1, 8, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10IBufferPtrRKNSt6vectorI1TEE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::T"], [1, 8, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::T"], [1, 8, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::T"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::dims"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::dims"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10IBufferPtrRKNSt6vectorI1TEE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::memoryType"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::memoryType"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::memoryType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::memoryType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7ITensor10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::memoryType"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10IBufferPtrRKNSt6vectorI1TEE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::src"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::src"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::src"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::src"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7ITensor10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::src"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu::dims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu::type"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu::type"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyBufferE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyBuffer"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyBufferE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyBuffer::memoryType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyBufferE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyBuffer::type"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyTensorE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyTensor"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyTensorE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyTensor::memoryType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyTensorE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyTensor::type"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager9getStreamEv", "tensorrt_llm::runtime::BufferManager::getStream"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu::dims"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu::size"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu::type"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu::type"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync::dims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync::type"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync::type"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7ipcNvlsENSt3setIiEEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::ipcNvls"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7ipcNvlsENSt3setIiEEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::ipcNvls::dims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7ipcNvlsENSt3setIiEEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::ipcNvls::ranks"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7ipcNvlsENSt3setIiEEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::ipcNvls::type"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE", "tensorrt_llm::runtime::BufferManager::kBYTE_TYPE"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager5mPoolE", "tensorrt_llm::runtime::BufferManager::mPool"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7mStreamE", "tensorrt_llm::runtime::BufferManager::mStream"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager9mTrimPoolE", "tensorrt_llm::runtime::BufferManager::mTrimPool"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed::dims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed::type"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed::type"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager14memoryPoolFreeEv", "tensorrt_llm::runtime::BufferManager::memoryPoolFree"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager18memoryPoolReservedEv", "tensorrt_llm::runtime::BufferManager::memoryPoolReserved"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager16memoryPoolTrimToENSt6size_tE", "tensorrt_llm::runtime::BufferManager::memoryPoolTrimTo"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager16memoryPoolTrimToENSt6size_tE", "tensorrt_llm::runtime::BufferManager::memoryPoolTrimTo::size"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager14memoryPoolUsedEv", "tensorrt_llm::runtime::BufferManager::memoryPoolUsed"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned::dims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned::type"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned::type"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool::dims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool::type"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool::type"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager6setMemER7IBuffer7int32_t", "tensorrt_llm::runtime::BufferManager::setMem"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager6setMemER7IBuffer7int32_t", "tensorrt_llm::runtime::BufferManager::setMem::buffer"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager6setMemER7IBuffer7int32_t", "tensorrt_llm::runtime::BufferManager::setMem::value"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager7setZeroER7IBuffer", "tensorrt_llm::runtime::BufferManager::setZero"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager7setZeroER7IBuffer", "tensorrt_llm::runtime::BufferManager::setZero::buffer"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManagerD0Ev", "tensorrt_llm::runtime::BufferManager::~BufferManager"], [1, 2, 1, "_CPPv4I0EN12tensorrt_llm7runtime11BufferRangeE", "tensorrt_llm::runtime::BufferRange"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime11BufferRange4BaseE", "tensorrt_llm::runtime::BufferRange::Base"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI1UEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeERK7IBuffer", "tensorrt_llm::runtime::BufferRange::BufferRange"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tIXntNSt10is_const_vI1UEEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeER7IBuffer", "tensorrt_llm::runtime::BufferRange::BufferRange"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11BufferRange11BufferRangeEP1T9size_type", "tensorrt_llm::runtime::BufferRange::BufferRange"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI1UEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeERK7IBuffer", "tensorrt_llm::runtime::BufferRange::BufferRange::U"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tIXntNSt10is_const_vI1UEEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeER7IBuffer", "tensorrt_llm::runtime::BufferRange::BufferRange::U"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI1UEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeERK7IBuffer", "tensorrt_llm::runtime::BufferRange::BufferRange::buffer"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tIXntNSt10is_const_vI1UEEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeER7IBuffer", "tensorrt_llm::runtime::BufferRange::BufferRange::buffer"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11BufferRange11BufferRangeEP1T9size_type", "tensorrt_llm::runtime::BufferRange::BufferRange::data"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11BufferRange11BufferRangeEP1T9size_type", "tensorrt_llm::runtime::BufferRange::BufferRange::size"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime11BufferRangeE", "tensorrt_llm::runtime::BufferRange::T"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEventE", "tensorrt_llm::runtime::CudaEvent"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventE7pointerb", "tensorrt_llm::runtime::CudaEvent::CudaEvent"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventEj", "tensorrt_llm::runtime::CudaEvent::CudaEvent"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventE7pointerb", "tensorrt_llm::runtime::CudaEvent::CudaEvent::event"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventEj", "tensorrt_llm::runtime::CudaEvent::CudaEvent::flags"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventE7pointerb", "tensorrt_llm::runtime::CudaEvent::CudaEvent::ownsEvent"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7DeleterE", "tensorrt_llm::runtime::CudaEvent::Deleter"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEb", "tensorrt_llm::runtime::CudaEvent::Deleter::Deleter"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEv", "tensorrt_llm::runtime::CudaEvent::Deleter::Deleter"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEb", "tensorrt_llm::runtime::CudaEvent::Deleter::Deleter::ownsEvent"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter10mOwnsEventE", "tensorrt_llm::runtime::CudaEvent::Deleter::mOwnsEvent"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent7DeleterclE7pointer", "tensorrt_llm::runtime::CudaEvent::Deleter::operator()"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent7DeleterclE7pointer", "tensorrt_llm::runtime::CudaEvent::Deleter::operator()::event"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent8EventPtrE", "tensorrt_llm::runtime::CudaEvent::EventPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent12element_typeE", "tensorrt_llm::runtime::CudaEvent::element_type"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent3getEv", "tensorrt_llm::runtime::CudaEvent::get"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent6mEventE", "tensorrt_llm::runtime::CudaEvent::mEvent"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7pointerE", "tensorrt_llm::runtime::CudaEvent::pointer"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent11synchronizeEv", "tensorrt_llm::runtime::CudaEvent::synchronize"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStreamE", "tensorrt_llm::runtime::CudaStream"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_t", "tensorrt_llm::runtime::CudaStream::CudaStream"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib", "tensorrt_llm::runtime::CudaStream::CudaStream"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamEji", "tensorrt_llm::runtime::CudaStream::CudaStream"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib", "tensorrt_llm::runtime::CudaStream::CudaStream::device"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamEji", "tensorrt_llm::runtime::CudaStream::CudaStream::flags"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib", "tensorrt_llm::runtime::CudaStream::CudaStream::ownsStream"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamEji", "tensorrt_llm::runtime::CudaStream::CudaStream::priority"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_t", "tensorrt_llm::runtime::CudaStream::CudaStream::stream"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib", "tensorrt_llm::runtime::CudaStream::CudaStream::stream"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7DeleterE", "tensorrt_llm::runtime::CudaStream::Deleter"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEb", "tensorrt_llm::runtime::CudaStream::Deleter::Deleter"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEv", "tensorrt_llm::runtime::CudaStream::Deleter::Deleter"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEb", "tensorrt_llm::runtime::CudaStream::Deleter::Deleter::ownsStream"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter11mOwnsStreamE", "tensorrt_llm::runtime::CudaStream::Deleter::mOwnsStream"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream7DeleterclE12cudaStream_t", "tensorrt_llm::runtime::CudaStream::Deleter::operator()"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream7DeleterclE12cudaStream_t", "tensorrt_llm::runtime::CudaStream::Deleter::operator()::stream"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream9StreamPtrE", "tensorrt_llm::runtime::CudaStream::StreamPtr"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream3getEv", "tensorrt_llm::runtime::CudaStream::get"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream9getDeviceEv", "tensorrt_llm::runtime::CudaStream::getDevice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7mDeviceE", "tensorrt_llm::runtime::CudaStream::mDevice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7mStreamE", "tensorrt_llm::runtime::CudaStream::mStream"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordEN9CudaEvent7pointerE", "tensorrt_llm::runtime::CudaStream::record"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordERK9CudaEvent", "tensorrt_llm::runtime::CudaStream::record"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordEN9CudaEvent7pointerE", "tensorrt_llm::runtime::CudaStream::record::event"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordERK9CudaEvent", "tensorrt_llm::runtime::CudaStream::record::event"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream11synchronizeEv", "tensorrt_llm::runtime::CudaStream::synchronize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitEN9CudaEvent7pointerE", "tensorrt_llm::runtime::CudaStream::wait"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitERK9CudaEvent", "tensorrt_llm::runtime::CudaStream::wait"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitEN9CudaEvent7pointerE", "tensorrt_llm::runtime::CudaStream::wait::event"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitERK9CudaEvent", "tensorrt_llm::runtime::CudaStream::wait::event"], [1, 2, 1, "_CPPv4I_N8nvinfer18DataTypeE_b_bEN12tensorrt_llm7runtime14DataTypeTraitsE", "tensorrt_llm::runtime::DataTypeTraits"], [1, 8, 1, "_CPPv4I_N8nvinfer18DataTypeE_b_bEN12tensorrt_llm7runtime14DataTypeTraitsE", "tensorrt_llm::runtime::DataTypeTraits::kDataType"], [1, 8, 1, "_CPPv4I_N8nvinfer18DataTypeE_b_bEN12tensorrt_llm7runtime14DataTypeTraitsE", "tensorrt_llm::runtime::DataTypeTraits::kIsPointer"], [1, 8, 1, "_CPPv4I_N8nvinfer18DataTypeE_b_bEN12tensorrt_llm7runtime14DataTypeTraitsE", "tensorrt_llm::runtime::DataTypeTraits::kIsUnsigned"], [1, 2, 1, "_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE", "tensorrt_llm::runtime::DataTypeTraits<kDataType, kUnsigned, true>"], [1, 8, 1, "_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE", "tensorrt_llm::runtime::DataTypeTraits<kDataType, kUnsigned, true>::kDataType"], [1, 8, 1, "_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE", "tensorrt_llm::runtime::DataTypeTraits<kDataType, kUnsigned, true>::kUnsigned"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4nameE", "tensorrt_llm::runtime::DataTypeTraits<kDataType, kUnsigned, true>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<kDataType, kUnsigned, true>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4typeE", "tensorrt_llm::runtime::DataTypeTraits<kDataType, kUnsigned, true>::type"], [1, 2, 1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kBOOL, kUnsigned>"], [1, 8, 1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kBOOL, kUnsigned>::kUnsigned"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kBOOL, kUnsigned>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kBOOL, kUnsigned>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kBOOL, kUnsigned>::type"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kFLOAT>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kFLOAT>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kFLOAT>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kFLOAT>::type"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kHALF>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kHALF>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kHALF>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kHALF>::type"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32, true>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32, true>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32, true>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32, true>::type"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32>::type"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64, true>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64, true>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64, true>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64, true>::type"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64>::type"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT8>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT8>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT8>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT8>::type"], [1, 2, 1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kUINT8, kUnsigned>"], [1, 8, 1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kUINT8, kUnsigned>::kUnsigned"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kUINT8, kUnsigned>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kUINT8, kUnsigned>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kUINT8, kUnsigned>::type"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInputE", "tensorrt_llm::runtime::DecodingInput"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13DecodingInputEv", "tensorrt_llm::runtime::DecodingInput::DecodingInput"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputsE", "tensorrt_llm::runtime::DecodingInput::EagleInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs12acceptedLensE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::acceptedLens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs15acceptedPathIdsE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::acceptedPathIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs14acceptedTokensE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::acceptedTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs24chunkedContextNextTokensE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::chunkedContextNextTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs13lastDraftLensE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::lastDraftLens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs14lastDraftPathsE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::lastDraftPaths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs15lastDraftTokensE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::lastDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs13nextDraftLensE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::nextDraftLens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs14nextDraftPathsE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::nextDraftPaths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs15nextDraftTokensE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::nextDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs8seqSlotsE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::seqSlots"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15bestPathIndicesE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::bestPathIndices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15bestPathLengthsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::bestPathLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs16lastDraftIndicesE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::lastDraftIndices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15lastDraftTokensE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::lastDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs21lastGenerationLengthsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::lastGenerationLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs19lastPositionIdsBaseE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::lastPositionIdsBase"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs5masksE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::masks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs18maxGenLengthDeviceE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::maxGenLengthDevice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs16nextDraftIndicesE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::nextDraftIndices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs14nextDraftProbsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::nextDraftProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15nextDraftTokensE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::nextDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs14nextFlatTokensE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::nextFlatTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs21nextGenerationLengthsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::nextGenerationLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs17packedPositionIdsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::packedPositionIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs8seqSlotsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::seqSlots"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputsE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs17constantThresholdE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::constantThreshold"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs11draftLogitsE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::draftLogits"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs10draftProbsE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::draftProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs13draftTokenIdsE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::draftTokenIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs14numDraftTokensE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::numDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs18numDraftTokensHostE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::numDraftTokensHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs4stepE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::step"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs11targetProbsE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::targetProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs14useDraftLogitsE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::useDraftLogits"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs18useDraftLogitsHostE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::useDraftLogitsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs28useRandomAcceptanceThresholdE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::useRandomAcceptanceThreshold"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15LookaheadInputsE", "tensorrt_llm::runtime::DecodingInput::LookaheadInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15LookaheadInputs13tokensPerStepE", "tensorrt_llm::runtime::DecodingInput::LookaheadInputs::tokensPerStep"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputsE", "tensorrt_llm::runtime::DecodingInput::MedusaInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs22medusaCurTokensPerStepE", "tensorrt_llm::runtime::DecodingInput::MedusaInputs::medusaCurTokensPerStep"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs12medusaLogitsE", "tensorrt_llm::runtime::DecodingInput::MedusaInputs::medusaLogits"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs11medusaPathsE", "tensorrt_llm::runtime::DecodingInput::MedusaInputs::medusaPaths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs25medusaTargetTokensPerStepE", "tensorrt_llm::runtime::DecodingInput::MedusaInputs::medusaTargetTokensPerStep"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs13medusaTreeIdsE", "tensorrt_llm::runtime::DecodingInput::MedusaInputs::medusaTreeIds"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput14TensorConstPtrE", "tensorrt_llm::runtime::DecodingInput::TensorConstPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE", "tensorrt_llm::runtime::DecodingInput::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12badWordsLensE", "tensorrt_llm::runtime::DecodingInput::badWordsLens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13badWordsListsE", "tensorrt_llm::runtime::DecodingInput::badWordsLists"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12badWordsPtrsE", "tensorrt_llm::runtime::DecodingInput::badWordsPtrs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9batchSizeE", "tensorrt_llm::runtime::DecodingInput::batchSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput10batchSlotsE", "tensorrt_llm::runtime::DecodingInput::batchSlots"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput10beamWidthsE", "tensorrt_llm::runtime::DecodingInput::beamWidths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput16cacheIndirectionE", "tensorrt_llm::runtime::DecodingInput::cacheIndirection"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11eagleInputsE", "tensorrt_llm::runtime::DecodingInput::eagleInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13embeddingBiasE", "tensorrt_llm::runtime::DecodingInput::embeddingBias"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput6endIdsE", "tensorrt_llm::runtime::DecodingInput::endIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25explicitDraftTokensInputsE", "tensorrt_llm::runtime::DecodingInput::explicitDraftTokensInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25externalDraftTokensInputsE", "tensorrt_llm::runtime::DecodingInput::externalDraftTokensInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13finishReasonsE", "tensorrt_llm::runtime::DecodingInput::finishReasons"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15generationStepsE", "tensorrt_llm::runtime::DecodingInput::generationSteps"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput7lengthsE", "tensorrt_llm::runtime::DecodingInput::lengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9logitsVecE", "tensorrt_llm::runtime::DecodingInput::logitsVec"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15lookaheadInputsE", "tensorrt_llm::runtime::DecodingInput::lookaheadInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput18maxAttentionWindowE", "tensorrt_llm::runtime::DecodingInput::maxAttentionWindow"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput14maxBadWordsLenE", "tensorrt_llm::runtime::DecodingInput::maxBadWordsLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9maxLengthE", "tensorrt_llm::runtime::DecodingInput::maxLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15maxStopWordsLenE", "tensorrt_llm::runtime::DecodingInput::maxStopWordsLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12medusaInputsE", "tensorrt_llm::runtime::DecodingInput::medusaInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput17noRepeatNgramSizeE", "tensorrt_llm::runtime::DecodingInput::noRepeatNgramSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput19sequenceLimitLengthE", "tensorrt_llm::runtime::DecodingInput::sequenceLimitLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15sinkTokenLengthE", "tensorrt_llm::runtime::DecodingInput::sinkTokenLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput4stepE", "tensorrt_llm::runtime::DecodingInput::step"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13stopWordsLensE", "tensorrt_llm::runtime::DecodingInput::stopWordsLens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput14stopWordsListsE", "tensorrt_llm::runtime::DecodingInput::stopWordsLists"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13stopWordsPtrsE", "tensorrt_llm::runtime::DecodingInput::stopWordsPtrs"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutputE", "tensorrt_llm::runtime::DecodingOutput"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypothesesE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses10batchDonesE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::batchDones"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses14cumLogProbsCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::cumLogProbsCBA"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5emptyERK13BufferManager", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::empty"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5emptyERK13BufferManager", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::empty::manager"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses4initERK13BufferManager11TokenIdType", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::init"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses4initERK13BufferManager11TokenIdType", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::init::endId"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses4initERK13BufferManager11TokenIdType", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::init::manager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses11logProbsCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::logProbsCBA"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses18minNormedScoresCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::minNormedScoresCBA"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses15normedScoresCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::normedScoresCBA"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses11numBeamsCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::numBeamsCBA"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses12outputIdsCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::outputIdsCBA"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7releaseEv", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::release"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::reshape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::reshape::batchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::reshape::beamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::reshape::maxSequenceLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses18sequenceLengthsCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::sequenceLengthsCBA"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5sliceE10SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::slice"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5sliceE10SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::slice::batchIndex"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5sliceE10SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::slice::size"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14DecodingOutputEv", "tensorrt_llm::runtime::DecodingOutput::DecodingOutput"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputsE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs21acceptedLengthsCumSumE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::acceptedLengthsCumSum"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs17acceptedTokensLenE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::acceptedTokensLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs15nextDraftTokensE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::nextDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs18nextDraftTokensLenE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::nextDraftTokensLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs12pathsOffsetsE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::pathsOffsets"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs18prevDraftTokensLenE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::prevDraftTokensLen"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE", "tensorrt_llm::runtime::DecodingOutput::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14beamHypothesesE", "tensorrt_llm::runtime::DecodingOutput::beamHypotheses"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput16cacheIndirectionE", "tensorrt_llm::runtime::DecodingOutput::cacheIndirection"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11cumLogProbsE", "tensorrt_llm::runtime::DecodingOutput::cumLogProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput12eagleBuffersE", "tensorrt_llm::runtime::DecodingOutput::eagleBuffers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26explicitDraftTokensBuffersE", "tensorrt_llm::runtime::DecodingOutput::explicitDraftTokensBuffers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput13finishReasonsE", "tensorrt_llm::runtime::DecodingOutput::finishReasons"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11finishedSumE", "tensorrt_llm::runtime::DecodingOutput::finishedSum"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11gatheredIdsE", "tensorrt_llm::runtime::DecodingOutput::gatheredIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput3idsE", "tensorrt_llm::runtime::DecodingOutput::ids"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput17kNegativeInfinityE", "tensorrt_llm::runtime::DecodingOutput::kNegativeInfinity"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput7lengthsE", "tensorrt_llm::runtime::DecodingOutput::lengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput8logProbsE", "tensorrt_llm::runtime::DecodingOutput::logProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput13logProbsTiledE", "tensorrt_llm::runtime::DecodingOutput::logProbsTiled"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput16lookaheadOutputsE", "tensorrt_llm::runtime::DecodingOutput::lookaheadOutputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9newTokensE", "tensorrt_llm::runtime::DecodingOutput::newTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14newTokensStepsE", "tensorrt_llm::runtime::DecodingOutput::newTokensSteps"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput12newTokensVecE", "tensorrt_llm::runtime::DecodingOutput::newTokensVec"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9parentIdsE", "tensorrt_llm::runtime::DecodingOutput::parentIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26speculativeDecodingOutputsE", "tensorrt_llm::runtime::DecodingOutput::speculativeDecodingOutputs"], [1, 2, 1, "_CPPv4I0EN12tensorrt_llm7runtime20DeviceAllocationNvlsE", "tensorrt_llm::runtime::DeviceAllocationNvls"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls20DeviceAllocationNvlsEv", "tensorrt_llm::runtime::DeviceAllocationNvls::DeviceAllocationNvls"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime20DeviceAllocationNvlsE", "tensorrt_llm::runtime::DeviceAllocationNvls::T"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls9_capacityE", "tensorrt_llm::runtime::DeviceAllocationNvls::_capacity"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls7_handleE", "tensorrt_llm::runtime::DeviceAllocationNvls::_handle"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls4freeEv", "tensorrt_llm::runtime::DeviceAllocationNvls::free"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime20DeviceAllocationNvls11getCapacityEv", "tensorrt_llm::runtime::DeviceAllocationNvls::getCapacity"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls21getIpcUnicastPointersEv", "tensorrt_llm::runtime::DeviceAllocationNvls::getIpcUnicastPointers"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime20DeviceAllocationNvls19getMulticastPointerEv", "tensorrt_llm::runtime::DeviceAllocationNvls::getMulticastPointer"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime20DeviceAllocationNvls17getUnicastPointerEv", "tensorrt_llm::runtime::DeviceAllocationNvls::getUnicastPointer"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls5resetE6size_tNSt3setIiEE", "tensorrt_llm::runtime::DeviceAllocationNvls::reset"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls5resetE6size_tNSt3setIiEE", "tensorrt_llm::runtime::DeviceAllocationNvls::reset::ranks"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls5resetE6size_tNSt3setIiEE", "tensorrt_llm::runtime::DeviceAllocationNvls::reset::size"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvlsD0Ev", "tensorrt_llm::runtime::DeviceAllocationNvls::~DeviceAllocationNvls"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffersE", "tensorrt_llm::runtime::EagleBuffers"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers9BufferPtrE", "tensorrt_llm::runtime::EagleBuffers::BufferPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12EagleBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigE", "tensorrt_llm::runtime::EagleBuffers::EagleBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12EagleBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigE", "tensorrt_llm::runtime::EagleBuffers::EagleBuffers::decodingConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12EagleBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigE", "tensorrt_llm::runtime::EagleBuffers::EagleBuffers::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12EagleBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigE", "tensorrt_llm::runtime::EagleBuffers::EagleBuffers::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12EagleBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigE", "tensorrt_llm::runtime::EagleBuffers::EagleBuffers::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12EagleBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigE", "tensorrt_llm::runtime::EagleBuffers::EagleBuffers::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12EagleBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigE", "tensorrt_llm::runtime::EagleBuffers::EagleBuffers::worldConfig"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputsE", "tensorrt_llm::runtime::EagleBuffers::EngineOutputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs12acceptedLensE", "tensorrt_llm::runtime::EagleBuffers::EngineOutputs::acceptedLens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs13acceptedPathsE", "tensorrt_llm::runtime::EagleBuffers::EngineOutputs::acceptedPaths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs14acceptedTokensE", "tensorrt_llm::runtime::EagleBuffers::EngineOutputs::acceptedTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs24chunkedContextNextTokensE", "tensorrt_llm::runtime::EagleBuffers::EngineOutputs::chunkedContextNextTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs13nextDraftLensE", "tensorrt_llm::runtime::EagleBuffers::EngineOutputs::nextDraftLens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs14nextDraftPathsE", "tensorrt_llm::runtime::EagleBuffers::EngineOutputs::nextDraftPaths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs15nextDraftTokensE", "tensorrt_llm::runtime::EagleBuffers::EngineOutputs::nextDraftTokens"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers7ITensorE", "tensorrt_llm::runtime::EagleBuffers::ITensor"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6InputsE", "tensorrt_llm::runtime::EagleBuffers::Inputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs22allLayersDraftTokenIdsE", "tensorrt_llm::runtime::EagleBuffers::Inputs::allLayersDraftTokenIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs33allLayersDraftTokenIdsPredecessorE", "tensorrt_llm::runtime::EagleBuffers::Inputs::allLayersDraftTokenIdsPredecessor"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs15allLayersScoresE", "tensorrt_llm::runtime::EagleBuffers::Inputs::allLayersScores"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs24chunkedContextNextTokensE", "tensorrt_llm::runtime::EagleBuffers::Inputs::chunkedContextNextTokens"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs6createE10SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::EagleBuffers::Inputs::create"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs6createE10SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::EagleBuffers::Inputs::create::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs6createE10SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::EagleBuffers::Inputs::create::maxNumSequences"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs6createE10SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::EagleBuffers::Inputs::create::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs6createE10SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::EagleBuffers::Inputs::create::worldConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs20currentExpandIndicesE", "tensorrt_llm::runtime::EagleBuffers::Inputs::currentExpandIndices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs9draftLensE", "tensorrt_llm::runtime::EagleBuffers::Inputs::draftLens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs10draftPathsE", "tensorrt_llm::runtime::EagleBuffers::Inputs::draftPaths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs14draftPathsHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::draftPathsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs11draftTokensE", "tensorrt_llm::runtime::EagleBuffers::Inputs::draftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs22dynamicTreeMaxTopKHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::dynamicTreeMaxTopKHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs29eagleNetCtxContextLengthsHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::eagleNetCtxContextLengthsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs34eagleNetCtxPastKeyValueLengthsHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::eagleNetCtxPastKeyValueLengthsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs27eagleNetCtxRequestTypesHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::eagleNetCtxRequestTypesHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs29eagleNetGenContextLengthsHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::eagleNetGenContextLengthsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs34eagleNetGenPastKeyValueLengthsHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::eagleNetGenPastKeyValueLengthsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs27eagleNetGenRequestTypesHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::eagleNetGenRequestTypesHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs18inputGenTokensHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::inputGenTokensHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs14posteriorAlphaE", "tensorrt_llm::runtime::EagleBuffers::Inputs::posteriorAlpha"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs18posteriorThresholdE", "tensorrt_llm::runtime::EagleBuffers::Inputs::posteriorThreshold"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs10prevScoresE", "tensorrt_llm::runtime::EagleBuffers::Inputs::prevScores"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs16randomDataSampleE", "tensorrt_llm::runtime::EagleBuffers::Inputs::randomDataSample"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs20randomDataValidationE", "tensorrt_llm::runtime::EagleBuffers::Inputs::randomDataValidation"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs29specDecodingGenerationLengthsE", "tensorrt_llm::runtime::EagleBuffers::Inputs::specDecodingGenerationLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs33specDecodingGenerationLengthsHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::specDecodingGenerationLengthsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs23specDecodingPackedMasksE", "tensorrt_llm::runtime::EagleBuffers::Inputs::specDecodingPackedMasks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs27specDecodingPositionOffsetsE", "tensorrt_llm::runtime::EagleBuffers::Inputs::specDecodingPositionOffsets"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs12temperaturesE", "tensorrt_llm::runtime::EagleBuffers::Inputs::temperatures"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs18useDynamicTreeHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::useDynamicTreeHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs15useSpecDecodingE", "tensorrt_llm::runtime::EagleBuffers::Inputs::useSpecDecoding"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13LlmRequestPtrE", "tensorrt_llm::runtime::EagleBuffers::LlmRequestPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13RequestVectorE", "tensorrt_llm::runtime::EagleBuffers::RequestVector"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers10SizeType32E", "tensorrt_llm::runtime::EagleBuffers::SizeType32"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers9TensorMapE", "tensorrt_llm::runtime::EagleBuffers::TensorMap"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers9TensorPtrE", "tensorrt_llm::runtime::EagleBuffers::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers28chunkedContextNextTokensHostE", "tensorrt_llm::runtime::EagleBuffers::chunkedContextNextTokensHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers23cumSumGenerationLengthsE", "tensorrt_llm::runtime::EagleBuffers::cumSumGenerationLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12engineInputsE", "tensorrt_llm::runtime::EagleBuffers::engineInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13engineOutputsE", "tensorrt_llm::runtime::EagleBuffers::engineOutputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers18greedySamplingHostE", "tensorrt_llm::runtime::EagleBuffers::greedySamplingHost"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::insertInputTensors"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::insertInputTensors::inputBuffers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::insertInputTensors::outputBuffers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::insertInputTensors::worldConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers26mDefaultPosteriorThresholdE", "tensorrt_llm::runtime::EagleBuffers::mDefaultPosteriorThreshold"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers17mDoGreedySamplingE", "tensorrt_llm::runtime::EagleBuffers::mDoGreedySampling"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers19maxGenerationLengthE", "tensorrt_llm::runtime::EagleBuffers::maxGenerationLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers18posteriorAlphaHostE", "tensorrt_llm::runtime::EagleBuffers::posteriorAlphaHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers22posteriorThresholdHostE", "tensorrt_llm::runtime::EagleBuffers::posteriorThresholdHost"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::EagleBuffers::reshape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::EagleBuffers::reshape::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::EagleBuffers::reshape::numCtxSequences"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::EagleBuffers::reshape::numGenSequences"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers21scanReduceTempStorageE", "tensorrt_llm::runtime::EagleBuffers::scanReduceTempStorage"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers26scanReduceTempStorageBytesE", "tensorrt_llm::runtime::EagleBuffers::scanReduceTempStorageBytes"], [1, 3, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs"], [1, 8, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::T"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::contextRequests"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::contextRequests"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::decoderBuffers"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::draftBuffers"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::eagleModule"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::genRequests"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::genRequests"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::manager"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::manager"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::modelConfig"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::requestTypes"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::seqSlots"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::seqSlots"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::vocabSizePadded"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::worldConfig"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModuleE", "tensorrt_llm::runtime::EagleModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule11EagleModuleE10SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::EagleModule::EagleModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule11EagleModuleEv", "tensorrt_llm::runtime::EagleModule::EagleModule"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule11EagleModuleE10SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::EagleModule::EagleModule::maxDecodingDraftTokens"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule11EagleModuleE10SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::EagleModule::EagleModule::maxDraftPathLen"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule11EagleModuleE10SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::EagleModule::EagleModule::maxNonLeafNodesPerLayer"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule11EagleModuleE10SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::EagleModule::EagleModule::numTransformersLayer"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11EagleModule22getDefaultEagleChoicesEv", "tensorrt_llm::runtime::EagleModule::getDefaultEagleChoices"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11EagleModule26getMaxNonLeafNodesPerLayerEv", "tensorrt_llm::runtime::EagleModule::getMaxNonLeafNodesPerLayer"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11EagleModule23getNumTransformerLayersEv", "tensorrt_llm::runtime::EagleModule::getNumTransformerLayers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule20mDefaultEagleChoicesE", "tensorrt_llm::runtime::EagleModule::mDefaultEagleChoices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule24mMaxNonLeafNodesPerLayerE", "tensorrt_llm::runtime::EagleModule::mMaxNonLeafNodesPerLayer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule21mNumTransformersLayerE", "tensorrt_llm::runtime::EagleModule::mNumTransformersLayer"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffersE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers9BufferPtrE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::BufferPtr"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputs15positionOffsetsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineInputs::positionOffsets"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputs18requestTypesDeviceE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineInputs::requestTypesDevice"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15bestPathIndicesE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::bestPathIndices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15bestPathLengthsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::bestPathLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs5masksE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::masks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs11maxGenTokenE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::maxGenToken"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs16nextDraftIndicesE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextDraftIndices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs14nextDraftProbsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextDraftProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15nextDraftTokensE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs14nextFlatTokensE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextFlatTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs21nextGenerationLengthsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextGenerationLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs19nextPositionOffsetsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextPositionOffsets"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs17packedPositionIdsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::packedPositionIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs13totalGenTokenE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::totalGenToken"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers::worldConfig"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7ITensorE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ITensor"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6InputsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::create"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::create::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::create::maxNumSequences"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::create::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::create::worldConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs12draftIndicesE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::draftIndices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs10draftProbsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::draftProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11draftTokensE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::draftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs17generationLengthsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::generationLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs21generationLengthsHostE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::generationLengthsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs16maxGenLengthHostE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::maxGenLengthHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11packedMasksE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::packedMasks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11positionIdsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::positionIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs15positionIdsBaseE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::positionIdsBase"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs16randomDataSampleE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::randomDataSample"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs20randomDataValidationE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::randomDataValidation"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs12temperaturesE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::temperatures"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs15useSpecDecodingE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::useSpecDecoding"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers10SizeType32E", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::SizeType32"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers9TensorMapE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::TensorMap"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers9TensorPtrE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers23cumSumGenerationLengthsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::cumSumGenerationLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12engineInputsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::engineInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13engineOutputsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::engineOutputs"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::insertInputTensors"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::insertInputTensors::inputBuffers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::insertInputTensors::outputBuffers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::insertInputTensors::worldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::reshape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::reshape::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::reshape::numCtxSequences"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::reshape::numGenSequences"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers15scanTempStorageE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::scanTempStorage"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers20scanTempStorageBytesE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::scanTempStorageBytes"], [1, 3, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs"], [1, 8, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::T"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::contextPositionIds"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::contextPositionIds"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::decoderBuffers"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::draftBuffers"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::explicitDraftTokensModule"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::manager"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::modelConfig"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::numCtxSequences"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::numCtxSequences"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::numGenSequences"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::numGenSequences"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::requestTypes"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::seqSlots"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::seqSlots"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::stream"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::stream"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::vocabSizePadded"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::worldConfig"], [1, 2, 1, "_CPPv4I0EN12tensorrt_llm7runtime25GenericPromptTuningParamsE", "tensorrt_llm::runtime::GenericPromptTuningParams"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::GenericPromptTuningParams::GenericPromptTuningParams"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::GenericPromptTuningParams::GenericPromptTuningParams::embeddingTable"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::GenericPromptTuningParams::GenericPromptTuningParams::tasks"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::GenericPromptTuningParams::GenericPromptTuningParams::vocabSize"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams10SizeType32E", "tensorrt_llm::runtime::GenericPromptTuningParams::SizeType32"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime25GenericPromptTuningParamsE", "tensorrt_llm::runtime::GenericPromptTuningParams::TTensor"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE", "tensorrt_llm::runtime::GenericPromptTuningParams::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams14embeddingTableE", "tensorrt_llm::runtime::GenericPromptTuningParams::embeddingTable"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams19promptTuningEnabledE", "tensorrt_llm::runtime::GenericPromptTuningParams::promptTuningEnabled"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams5tasksE", "tensorrt_llm::runtime::GenericPromptTuningParams::tasks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9vocabSizeE", "tensorrt_llm::runtime::GenericPromptTuningParams::vocabSize"], [1, 2, 1, "_CPPv4I0EN12tensorrt_llm7runtime10GptDecoderE", "tensorrt_llm::runtime::GptDecoder"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13CudaStreamPtrE", "tensorrt_llm::runtime::GptDecoder::CudaStreamPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::mode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::speculativeDecodingModule"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::stream"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::vocabSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::vocabSizePadded"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime10GptDecoderE", "tensorrt_llm::runtime::GptDecoder::T"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder9TensorPtrE", "tensorrt_llm::runtime::GptDecoder::TensorPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", "tensorrt_llm::runtime::GptDecoder::disableLookahead"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", "tensorrt_llm::runtime::GptDecoder::disableLookahead::batchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", "tensorrt_llm::runtime::GptDecoder::disableLookahead::batchSlots"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", "tensorrt_llm::runtime::GptDecoder::disableLookahead::samplingConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardAsync"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardAsync::input"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardAsync::output"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardSync"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardSync::input"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardSync::output"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder17getSamplingConfigEv", "tensorrt_llm::runtime::GptDecoder::getSamplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder23mDecodingLayerWorkspaceE", "tensorrt_llm::runtime::GptDecoder::mDecodingLayerWorkspace"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13mDecodingModeE", "tensorrt_llm::runtime::GptDecoder::mDecodingMode"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder19mDynamicDecodeLayerE", "tensorrt_llm::runtime::GptDecoder::mDynamicDecodeLayer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder8mManagerE", "tensorrt_llm::runtime::GptDecoder::mManager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13mMaxBatchSizeE", "tensorrt_llm::runtime::GptDecoder::mMaxBatchSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder15mSamplingConfigE", "tensorrt_llm::runtime::GptDecoder::mSamplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10mVocabSizeE", "tensorrt_llm::runtime::GptDecoder::mVocabSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder16mVocabSizePaddedE", "tensorrt_llm::runtime::GptDecoder::mVocabSizePadded"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::GptDecoder::setup"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::batchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::batchSlots"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::explicitDraftTokensDType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::lookaheadAlgoConfigs"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::lookaheadPrompt"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::output"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::samplingConfig"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatchedE", "tensorrt_llm::runtime::GptDecoderBatched"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13CudaStreamPtrE", "tensorrt_llm::runtime::GptDecoderBatched::CudaStreamPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched17GptDecoderBatchedE13CudaStreamPtr", "tensorrt_llm::runtime::GptDecoderBatched::GptDecoderBatched"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched17GptDecoderBatchedE13CudaStreamPtr", "tensorrt_llm::runtime::GptDecoderBatched::GptDecoderBatched::stream"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13GptDecoderPtrE", "tensorrt_llm::runtime::GptDecoderBatched::GptDecoderPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13LlmRequestPtrE", "tensorrt_llm::runtime::GptDecoderBatched::LlmRequestPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13RequestVectorE", "tensorrt_llm::runtime::GptDecoderBatched::RequestVector"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched9TensorPtrE", "tensorrt_llm::runtime::GptDecoderBatched::TensorPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16disableLookaheadERK13RequestVectorRK9TensorPtr", "tensorrt_llm::runtime::GptDecoderBatched::disableLookahead"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16disableLookaheadERK13RequestVectorRK9TensorPtr", "tensorrt_llm::runtime::GptDecoderBatched::disableLookahead::batchSlots"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16disableLookaheadERK13RequestVectorRK9TensorPtr", "tensorrt_llm::runtime::GptDecoderBatched::disableLookahead::genRequests"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::finalize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::finalize::batchSlot"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::finalize::decoderState"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::finalize::samplingConfig"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::finalize::streaming"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched7forwardERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forward"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched7forwardERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forward::decoderState"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched7forwardERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forward::input"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12forwardAsyncERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardAsync"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12forwardAsyncERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardAsync::decoderState"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12forwardAsyncERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardAsync::input"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15forwardDispatchERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardDispatch"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15forwardDispatchERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardDispatch::decoderState"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15forwardDispatchERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardDispatch::input"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched16getBufferManagerEv", "tensorrt_llm::runtime::GptDecoderBatched::getBufferManager"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched16getDecoderStreamEv", "tensorrt_llm::runtime::GptDecoderBatched::getDecoderStream"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched20getUnderlyingDecoderEv", "tensorrt_llm::runtime::GptDecoderBatched::getUnderlyingDecoder"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mBufferManagerE", "tensorrt_llm::runtime::GptDecoderBatched::mBufferManager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched8mDecoderE", "tensorrt_llm::runtime::GptDecoderBatched::mDecoder"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mDecoderStreamE", "tensorrt_llm::runtime::GptDecoderBatched::mDecoderStream"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mRuntimeStreamE", "tensorrt_llm::runtime::GptDecoderBatched::mRuntimeStream"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::dtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::mode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::worldConfig"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfigE", "tensorrt_llm::runtime::GptJsonConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::contextParallelism"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::gpusPerNode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::name"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::pipelineParallelism"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::precision"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::runtimeDefaults"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::tensorParallelism"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::version"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfig", "tensorrt_llm::runtime::GptJsonConfig::engineFilename"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfigRKNSt6stringE", "tensorrt_llm::runtime::GptJsonConfig::engineFilename"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfigRKNSt6stringE", "tensorrt_llm::runtime::GptJsonConfig::engineFilename::model"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfig", "tensorrt_llm::runtime::GptJsonConfig::engineFilename::worldConfig"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfigRKNSt6stringE", "tensorrt_llm::runtime::GptJsonConfig::engineFilename::worldConfig"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig21getContextParallelismEv", "tensorrt_llm::runtime::GptJsonConfig::getContextParallelism"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14getGpusPerNodeEv", "tensorrt_llm::runtime::GptJsonConfig::getGpusPerNode"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14getModelConfigEv", "tensorrt_llm::runtime::GptJsonConfig::getModelConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig21getModelConfigMutableEv", "tensorrt_llm::runtime::GptJsonConfig::getModelConfigMutable"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig7getNameEv", "tensorrt_llm::runtime::GptJsonConfig::getName"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig22getPipelineParallelismEv", "tensorrt_llm::runtime::GptJsonConfig::getPipelineParallelism"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getPrecisionEv", "tensorrt_llm::runtime::GptJsonConfig::getPrecision"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig18getRuntimeDefaultsEv", "tensorrt_llm::runtime::GptJsonConfig::getRuntimeDefaults"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig20getTensorParallelismEv", "tensorrt_llm::runtime::GptJsonConfig::getTensorParallelism"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig10getVersionEv", "tensorrt_llm::runtime::GptJsonConfig::getVersion"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getWorldSizeEv", "tensorrt_llm::runtime::GptJsonConfig::getWorldSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig19mContextParallelismE", "tensorrt_llm::runtime::GptJsonConfig::mContextParallelism"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig12mGpusPerNodeE", "tensorrt_llm::runtime::GptJsonConfig::mGpusPerNode"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig12mModelConfigE", "tensorrt_llm::runtime::GptJsonConfig::mModelConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5mNameE", "tensorrt_llm::runtime::GptJsonConfig::mName"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig20mPipelineParallelismE", "tensorrt_llm::runtime::GptJsonConfig::mPipelineParallelism"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig10mPrecisionE", "tensorrt_llm::runtime::GptJsonConfig::mPrecision"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig16mRuntimeDefaultsE", "tensorrt_llm::runtime::GptJsonConfig::mRuntimeDefaults"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig18mTensorParallelismE", "tensorrt_llm::runtime::GptJsonConfig::mTensorParallelism"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig8mVersionE", "tensorrt_llm::runtime::GptJsonConfig::mVersion"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt10filesystem4pathE", "tensorrt_llm::runtime::GptJsonConfig::parse"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt6stringE", "tensorrt_llm::runtime::GptJsonConfig::parse"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERNSt7istreamE", "tensorrt_llm::runtime::GptJsonConfig::parse"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt6stringE", "tensorrt_llm::runtime::GptJsonConfig::parse::json"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERNSt7istreamE", "tensorrt_llm::runtime::GptJsonConfig::parse::json"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt10filesystem4pathE", "tensorrt_llm::runtime::GptJsonConfig::parse::path"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime7IBufferE", "tensorrt_llm::runtime::IBuffer"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer8DataTypeE", "tensorrt_llm::runtime::IBuffer::DataType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferERK7IBuffer", "tensorrt_llm::runtime::IBuffer::IBuffer"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferEv", "tensorrt_llm::runtime::IBuffer::IBuffer"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer14SharedConstPtrE", "tensorrt_llm::runtime::IBuffer::SharedConstPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer9SharedPtrE", "tensorrt_llm::runtime::IBuffer::SharedPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer14UniqueConstPtrE", "tensorrt_llm::runtime::IBuffer::UniqueConstPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE", "tensorrt_llm::runtime::IBuffer::UniquePtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE", "tensorrt_llm::runtime::IBuffer::data"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4dataEv", "tensorrt_llm::runtime::IBuffer::data"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE", "tensorrt_llm::runtime::IBuffer::data"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataEv", "tensorrt_llm::runtime::IBuffer::data"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE", "tensorrt_llm::runtime::IBuffer::data::index"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE", "tensorrt_llm::runtime::IBuffer::data::index"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer11getCapacityEv", "tensorrt_llm::runtime::IBuffer::getCapacity"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer11getDataTypeEv", "tensorrt_llm::runtime::IBuffer::getDataType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer15getDataTypeNameE8DataType", "tensorrt_llm::runtime::IBuffer::getDataTypeName"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer15getDataTypeNameEv", "tensorrt_llm::runtime::IBuffer::getDataTypeName"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer15getDataTypeNameE8DataType", "tensorrt_llm::runtime::IBuffer::getDataTypeName::dataType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer13getMemoryTypeEv", "tensorrt_llm::runtime::IBuffer::getMemoryType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer17getMemoryTypeNameEv", "tensorrt_llm::runtime::IBuffer::getMemoryTypeName"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer7getSizeEv", "tensorrt_llm::runtime::IBuffer::getSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer14getSizeInBytesEv", "tensorrt_llm::runtime::IBuffer::getSizeInBytes"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer10memoryTypeEPKv", "tensorrt_llm::runtime::IBuffer::memoryType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer10memoryTypeEPKv", "tensorrt_llm::runtime::IBuffer::memoryType::data"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBufferaSERK7IBuffer", "tensorrt_llm::runtime::IBuffer::operator="], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer7releaseEv", "tensorrt_llm::runtime::IBuffer::release"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer6resizeENSt6size_tE", "tensorrt_llm::runtime::IBuffer::resize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer6resizeENSt6size_tE", "tensorrt_llm::runtime::IBuffer::resize::newSize"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::TConstPtr"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::TConstPtr"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::buffer"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::buffer"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::offset"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::offset"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::offset"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::offset"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::size"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::tensor"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::tensor"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer7toBytesENSt6size_tE", "tensorrt_llm::runtime::IBuffer::toBytes"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer7toBytesENSt6size_tE", "tensorrt_llm::runtime::IBuffer::toBytes::size"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtr", "tensorrt_llm::runtime::IBuffer::view"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view::TConstPtr"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view::size"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtr", "tensorrt_llm::runtime::IBuffer::view::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view::tensor"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrRNSt6vectorI1TEE", "tensorrt_llm::runtime::IBuffer::wrap"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrRNSt6vectorI1TEE", "tensorrt_llm::runtime::IBuffer::wrap::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::capacity"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::capacity"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::data"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::data"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::data"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::data"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::size"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::type"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::type"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrRNSt6vectorI1TEE", "tensorrt_llm::runtime::IBuffer::wrap::v"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBufferD0Ev", "tensorrt_llm::runtime::IBuffer::~IBuffer"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoderE", "tensorrt_llm::runtime::IGptDecoder"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder14TensorConstPtrE", "tensorrt_llm::runtime::IGptDecoder::TensorConstPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder9TensorPtrE", "tensorrt_llm::runtime::IGptDecoder::TensorPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::dtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::mode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::speculativeDecodingModule"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::stream"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::vocabSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::vocabSizePadded"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", "tensorrt_llm::runtime::IGptDecoder::disableLookahead"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", "tensorrt_llm::runtime::IGptDecoder::disableLookahead::batchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", "tensorrt_llm::runtime::IGptDecoder::disableLookahead::batchSlots"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", "tensorrt_llm::runtime::IGptDecoder::disableLookahead::samplingConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardAsync"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardAsync::input"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardAsync::output"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardSync"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardSync::input"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardSync::output"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder17getSamplingConfigEv", "tensorrt_llm::runtime::IGptDecoder::getSamplingConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::batchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::batchSlots"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::explicitDraftTokensDType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::lookaheadAlgoConfigs"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::lookaheadPrompt"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::output"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::samplingConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoderD0Ev", "tensorrt_llm::runtime::IGptDecoder::~IGptDecoder"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatchedE", "tensorrt_llm::runtime::IGptDecoderBatched"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoderBatched::CudaStreamPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched18IGptDecoderBatchedEv", "tensorrt_llm::runtime::IGptDecoderBatched::IGptDecoderBatched"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched13LlmRequestPtrE", "tensorrt_llm::runtime::IGptDecoderBatched::LlmRequestPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched13RequestVectorE", "tensorrt_llm::runtime::IGptDecoderBatched::RequestVector"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched9TensorPtrE", "tensorrt_llm::runtime::IGptDecoderBatched::TensorPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched16disableLookaheadERK13RequestVectorRK9TensorPtr", "tensorrt_llm::runtime::IGptDecoderBatched::disableLookahead"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched16disableLookaheadERK13RequestVectorRK9TensorPtr", "tensorrt_llm::runtime::IGptDecoderBatched::disableLookahead::batchSlots"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched16disableLookaheadERK13RequestVectorRK9TensorPtr", "tensorrt_llm::runtime::IGptDecoderBatched::disableLookahead::genRequests"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::IGptDecoderBatched::finalize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::IGptDecoderBatched::finalize::batchSlot"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::IGptDecoderBatched::finalize::decoderState"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::IGptDecoderBatched::finalize::samplingConfig"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::IGptDecoderBatched::finalize::streaming"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched7forwardERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forward"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched7forwardERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forward::decoderState"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched7forwardERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forward::input"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched12forwardAsyncERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forwardAsync"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched12forwardAsyncERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forwardAsync::decoderState"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched12forwardAsyncERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forwardAsync::input"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::IGptDecoderBatched::setup"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::IGptDecoderBatched::setup::dtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::IGptDecoderBatched::setup::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::IGptDecoderBatched::setup::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::IGptDecoderBatched::setup::mode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::IGptDecoderBatched::setup::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::IGptDecoderBatched::setup::worldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatchedD0Ev", "tensorrt_llm::runtime::IGptDecoderBatched::~IGptDecoderBatched"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime7ITensorE", "tensorrt_llm::runtime::ITensor"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9DimType64E", "tensorrt_llm::runtime::ITensor::DimType64"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorERK7ITensor", "tensorrt_llm::runtime::ITensor::ITensor"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorEv", "tensorrt_llm::runtime::ITensor::ITensor"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE", "tensorrt_llm::runtime::ITensor::Shape"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor14SharedConstPtrE", "tensorrt_llm::runtime::ITensor::SharedConstPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE", "tensorrt_llm::runtime::ITensor::SharedPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9TensorMapE", "tensorrt_llm::runtime::ITensor::TensorMap"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor14UniqueConstPtrE", "tensorrt_llm::runtime::ITensor::UniqueConstPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE", "tensorrt_llm::runtime::ITensor::UniquePtr"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atEN7ITensor14UniqueConstPtrERR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at::TConstPtr"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atEN7ITensor14UniqueConstPtrERR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at::TConstPtr"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at::offsetDims"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atEN7ITensor14UniqueConstPtrERR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at::offsetDims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at::offsetDims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at::offsetDims"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at::tensor"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atEN7ITensor14UniqueConstPtrERR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at::tensor"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8castSizeE6size_t", "tensorrt_llm::runtime::ITensor::castSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8castSizeE6size_t", "tensorrt_llm::runtime::ITensor::castSize::newSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8flattenNE9SharedPtrNSt7int64_tE", "tensorrt_llm::runtime::ITensor::flattenN"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8flattenNE9SharedPtrNSt7int64_tE", "tensorrt_llm::runtime::ITensor::flattenN::sliceN"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8flattenNE9SharedPtrNSt7int64_tE", "tensorrt_llm::runtime::ITensor::flattenN::tensor"], [1, 3, 1, "_CPPv4I_10SizeType32ENK12tensorrt_llm7runtime7ITensor12getDimensionE9DimType64v", "tensorrt_llm::runtime::ITensor::getDimension"], [1, 8, 1, "_CPPv4I_10SizeType32ENK12tensorrt_llm7runtime7ITensor12getDimensionE9DimType64v", "tensorrt_llm::runtime::ITensor::getDimension::n"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7ITensor8getShapeEv", "tensorrt_llm::runtime::ITensor::getShape"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9makeShapeERKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::makeShape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9makeShapeERKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::makeShape::dims"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensoraSERK7ITensor", "tensorrt_llm::runtime::ITensor::operator="], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7reshapeERK5Shape", "tensorrt_llm::runtime::ITensor::reshape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7reshapeERK5Shape", "tensorrt_llm::runtime::ITensor::reshape::dims"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor6resizeENSt6size_tE", "tensorrt_llm::runtime::ITensor::resize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor6resizeENSt6size_tE", "tensorrt_llm::runtime::ITensor::resize::newSize"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals"], [1, 3, 1, "_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapeRK5Shape", "tensorrt_llm::runtime::ITensor::shapeEquals"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERK5Shape", "tensorrt_llm::runtime::ITensor::shapeEquals"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERKNSt16initializer_listI10SizeType32EE", "tensorrt_llm::runtime::ITensor::shapeEquals"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::T"], [1, 8, 1, "_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::count"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::count"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::dims"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::dims"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::lhs"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapeRK5Shape", "tensorrt_llm::runtime::ITensor::shapeEquals::lhs"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERK5Shape", "tensorrt_llm::runtime::ITensor::shapeEquals::other"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERKNSt16initializer_listI10SizeType32EE", "tensorrt_llm::runtime::ITensor::shapeEquals::other"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapeRK5Shape", "tensorrt_llm::runtime::ITensor::shapeEquals::rhs"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape9DimType64", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE9DimType64", "tensorrt_llm::runtime::ITensor::slice"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::TConstPtr"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::TConstPtr"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice::TConstPtr"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::TConstPtr"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice::TConstPtr"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::TConstPtr"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offset"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offset"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offset"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offset"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape9DimType64", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE9DimType64", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape9DimType64", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE9DimType64", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape9DimType64", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE9DimType64", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeE10SizeType32", "tensorrt_llm::runtime::ITensor::squeeze"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::squeeze"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeE10SizeType32", "tensorrt_llm::runtime::ITensor::squeeze::dim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::squeeze::dim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::squeeze::shape"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7stridesERK5Shape", "tensorrt_llm::runtime::ITensor::strides"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7stridesERK5Shape", "tensorrt_llm::runtime::ITensor::strides::dims"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8toStringERK5Shape", "tensorrt_llm::runtime::ITensor::toString"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8toStringERK5Shape", "tensorrt_llm::runtime::ITensor::toString::dims"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeE10SizeType32", "tensorrt_llm::runtime::ITensor::unsqueeze"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::unsqueeze"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeE10SizeType32", "tensorrt_llm::runtime::ITensor::unsqueeze::dim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::unsqueeze::dim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::unsqueeze::shape"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::view"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewE9SharedPtr", "tensorrt_llm::runtime::ITensor::view"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewEN7IBuffer9SharedPtrERK5Shape", "tensorrt_llm::runtime::ITensor::view"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::view::TConstPtr"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewEN7IBuffer9SharedPtrERK5Shape", "tensorrt_llm::runtime::ITensor::view::buffer"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::view::dims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewEN7IBuffer9SharedPtrERK5Shape", "tensorrt_llm::runtime::ITensor::view::dims"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::view::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewE9SharedPtr", "tensorrt_llm::runtime::ITensor::view::tensor"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor6volumeERK5Shape", "tensorrt_llm::runtime::ITensor::volume"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor6volumeERK5Shape", "tensorrt_llm::runtime::ITensor::volume::dims"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor17volumeNonNegativeERK5Shape", "tensorrt_llm::runtime::ITensor::volumeNonNegative"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor17volumeNonNegativeERK5Shape", "tensorrt_llm::runtime::ITensor::volumeNonNegative::shape"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape", "tensorrt_llm::runtime::ITensor::wrap"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape", "tensorrt_llm::runtime::ITensor::wrap"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape", "tensorrt_llm::runtime::ITensor::wrap"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape", "tensorrt_llm::runtime::ITensor::wrap::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape", "tensorrt_llm::runtime::ITensor::wrap::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::capacity"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::capacity"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape", "tensorrt_llm::runtime::ITensor::wrap::data"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::data"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape", "tensorrt_llm::runtime::ITensor::wrap::data"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::data"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape", "tensorrt_llm::runtime::ITensor::wrap::shape"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::shape"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape", "tensorrt_llm::runtime::ITensor::wrap::shape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape", "tensorrt_llm::runtime::ITensor::wrap::shape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::shape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape", "tensorrt_llm::runtime::ITensor::wrap::type"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::type"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape", "tensorrt_llm::runtime::ITensor::wrap::v"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensorD0Ev", "tensorrt_llm::runtime::ITensor::~ITensor"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryE", "tensorrt_llm::runtime::IpcMemory"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9BufferPtrE", "tensorrt_llm::runtime::IpcMemory::BufferPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory10FLAGS_SIZEE", "tensorrt_llm::runtime::IpcMemory::FLAGS_SIZE"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb", "tensorrt_llm::runtime::IpcMemory::IpcMemory"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryERK9IpcMemory", "tensorrt_llm::runtime::IpcMemory::IpcMemory"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryERR9IpcMemory", "tensorrt_llm::runtime::IpcMemory::IpcMemory"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb", "tensorrt_llm::runtime::IpcMemory::IpcMemory::bufferSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb", "tensorrt_llm::runtime::IpcMemory::IpcMemory::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb", "tensorrt_llm::runtime::IpcMemory::IpcMemory::openIpc"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb", "tensorrt_llm::runtime::IpcMemory::IpcMemory::worldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::IpcMemory::allocateIpcMemory"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::IpcMemory::allocateIpcMemory::bufferSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::IpcMemory::allocateIpcMemory::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::IpcMemory::allocateIpcMemory::worldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory16destroyIpcMemoryEv", "tensorrt_llm::runtime::IpcMemory::destroyIpcMemory"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9IpcMemory11getCommPtrsEv", "tensorrt_llm::runtime::IpcMemory::getCommPtrs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory7mBufferE", "tensorrt_llm::runtime::IpcMemory::mBuffer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9mCommPtrsE", "tensorrt_llm::runtime::IpcMemory::mCommPtrs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory8mOpenIpcE", "tensorrt_llm::runtime::IpcMemory::mOpenIpc"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory7mTpRankE", "tensorrt_llm::runtime::IpcMemory::mTpRank"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryaSERK9IpcMemory", "tensorrt_llm::runtime::IpcMemory::operator="], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryaSERR9IpcMemory", "tensorrt_llm::runtime::IpcMemory::operator="], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryD0Ev", "tensorrt_llm::runtime::IpcMemory::~IpcMemory"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandleE", "tensorrt_llm::runtime::IpcNvlsHandle"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle14ipc_uc_handlesE", "tensorrt_llm::runtime::IpcNvlsHandle::ipc_uc_handles"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle11ipc_uc_ptrsE", "tensorrt_llm::runtime::IpcNvlsHandle::ipc_uc_ptrs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle10ipc_uc_vasE", "tensorrt_llm::runtime::IpcNvlsHandle::ipc_uc_vas"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle9mc_handleE", "tensorrt_llm::runtime::IpcNvlsHandle::mc_handle"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle6mc_ptrE", "tensorrt_llm::runtime::IpcNvlsHandle::mc_ptr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle5mc_vaE", "tensorrt_llm::runtime::IpcNvlsHandle::mc_va"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle4sizeE", "tensorrt_llm::runtime::IpcNvlsHandle::size"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle9uc_handleE", "tensorrt_llm::runtime::IpcNvlsHandle::uc_handle"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle6uc_ptrE", "tensorrt_llm::runtime::IpcNvlsHandle::uc_ptr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle5uc_vaE", "tensorrt_llm::runtime::IpcNvlsHandle::uc_va"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffersE", "tensorrt_llm::runtime::LookaheadDecodingBuffers"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers24LookaheadDecodingBuffersE10SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::LookaheadDecodingBuffers::LookaheadDecodingBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers24LookaheadDecodingBuffersE10SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::LookaheadDecodingBuffers::LookaheadDecodingBuffers::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers24LookaheadDecodingBuffersE10SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::LookaheadDecodingBuffers::LookaheadDecodingBuffers::maxNumSequences"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers24LookaheadDecodingBuffersE10SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::LookaheadDecodingBuffers::LookaheadDecodingBuffers::maxTokensPerStep"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers9TensorPtrE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers17generationLengthsE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::generationLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers11packedMasksE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::packedMasks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers11positionIdsE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::positionIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers15positionOffsetsE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::positionOffsets"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModuleE", "tensorrt_llm::runtime::LookaheadModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadModule::LookaheadModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleEv", "tensorrt_llm::runtime::LookaheadModule::LookaheadModule"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadModule::LookaheadModule::maxDecodingDraftTokens"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadModule::LookaheadModule::maxDraftPathLen"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime15LookaheadModule18getExecutionConfigEv", "tensorrt_llm::runtime::LookaheadModule::getExecutionConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule16mExecutionConfigE", "tensorrt_llm::runtime::LookaheadModule::mExecutionConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule18setExecutionConfigERKN8executor23LookaheadDecodingConfigE", "tensorrt_llm::runtime::LookaheadModule::setExecutionConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule18setExecutionConfigERKN8executor23LookaheadDecodingConfigE", "tensorrt_llm::runtime::LookaheadModule::setExecutionConfig::config"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffersE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::decodingConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::runtime"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::worldConfig"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers9TensorMapE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::TensorMap"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers9TensorPtrE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers18batchSlotsHostCopyE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::batchSlotsHostCopy"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers12cumSumLengthE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::cumSumLength"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers24disableLookaheadDecodingEv", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::disableLookaheadDecoding"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23enableLookaheadDecodingE10SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::enableLookaheadDecoding"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23enableLookaheadDecodingE10SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::enableLookaheadDecoding::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23enableLookaheadDecodingE10SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::enableLookaheadDecoding::tokensPerStep"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23generationLengthsDeviceE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::generationLengthsDevice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers21generationLengthsHostE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::generationLengthsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers25generationLengthsHostCopyE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::generationLengthsHostCopy"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers18insertInputTensorsER9TensorMapR9TensorMapRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::insertInputTensors"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers18insertInputTensorsER9TensorMapR9TensorMapRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::insertInputTensors::inputBuffers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers18insertInputTensorsER9TensorMapR9TensorMapRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::insertInputTensors::outputBuffers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers18insertInputTensorsER9TensorMapR9TensorMapRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::insertInputTensors::worldConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers14packedMaskHostE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::packedMaskHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers18packedMaskHostCopyE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::packedMaskHostCopy"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers17packedMasksDeviceE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::packedMasksDevice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers17positionIdsDeviceE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionIdsDevice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers15positionIdsHostE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionIdsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers19positionIdsHostCopyE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionIdsHostCopy"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers21positionOffsetsDeviceE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionOffsetsDevice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers19positionOffsetsHostE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionOffsetsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23positionOffsetsHostCopyE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionOffsetsHostCopy"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::reshape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::reshape::numCtxSequences"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::reshape::numGenSequences"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::reshape::tokensPerStep"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::decoderLookaheadBuffers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::modelConfig"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::numCtxSequences"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::numGenSequences"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::requestTypes"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::runtime"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::seqSlots"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::worldConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers15useSpecDecodingE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::useSpecDecoding"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCacheE", "tensorrt_llm::runtime::LoraCache"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCache::LoraCache"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCache::LoraCache::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCache::LoraCache::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCache::LoraCache::pageManagerConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCache::LoraCache::worldConfig"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache10TaskIdTypeE", "tensorrt_llm::runtime::LoraCache::TaskIdType"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig11adapterSizeE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::adapterSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig6inSizeE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::inSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7layerIdE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::layerId"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8moduleIdE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::moduleId"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8numSlotsE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::numSlots"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfigeqERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::operator=="], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfigeqERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::operator==::o"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7outSizeE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::outSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig6pageIdE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::pageId"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig17scalingVecPointerE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::scalingVecPointer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7slotIdxE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::slotIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8toStringEv", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::toString"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig16weightsInPointerE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::weightsInPointer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig17weightsOutPointerE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::weightsOutPointer"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache28TaskLayerModuleConfigListPtrE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfigListPtr"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueE", "tensorrt_llm::runtime::LoraCache::TaskValue"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERR9TaskValue", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueEv", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::configs"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::done"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::inProgress"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::it"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::loadInProgress"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::loaded"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERR9TaskValue", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::o"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::pageIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue7configsE", "tensorrt_llm::runtime::LoraCache::TaskValue::configs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue4doneE", "tensorrt_llm::runtime::LoraCache::TaskValue::done"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue10inProgressE", "tensorrt_llm::runtime::LoraCache::TaskValue::inProgress"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue2itE", "tensorrt_llm::runtime::LoraCache::TaskValue::it"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue14loadInProgressE", "tensorrt_llm::runtime::LoraCache::TaskValue::loadInProgress"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue6loadedE", "tensorrt_llm::runtime::LoraCache::TaskValue::loaded"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueaSERR9TaskValue", "tensorrt_llm::runtime::LoraCache::TaskValue::operator="], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueaSERR9TaskValue", "tensorrt_llm::runtime::LoraCache::TaskValue::operator=::o"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue7pageIdsE", "tensorrt_llm::runtime::LoraCache::TaskValue::pageIds"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueD0Ev", "tensorrt_llm::runtime::LoraCache::TaskValue::~TaskValue"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12TaskValuePtrE", "tensorrt_llm::runtime::LoraCache::TaskValuePtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TensorPtrE", "tensorrt_llm::runtime::LoraCache::TensorPtr"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatusE", "tensorrt_llm::runtime::LoraCache::ValueStatus"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus20kVALUE_STATUS_LOADEDE", "tensorrt_llm::runtime::LoraCache::ValueStatus::kVALUE_STATUS_LOADED"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus21kVALUE_STATUS_MISSINGE", "tensorrt_llm::runtime::LoraCache::ValueStatus::kVALUE_STATUS_MISSING"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus24kVALUE_STATUS_PROCESSINGE", "tensorrt_llm::runtime::LoraCache::ValueStatus::kVALUE_STATUS_PROCESSING"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache4bumpE10TaskIdType", "tensorrt_llm::runtime::LoraCache::bump"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache4bumpE10TaskIdType", "tensorrt_llm::runtime::LoraCache::bump::taskId"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache18bumpTaskInProgressE10TaskIdType", "tensorrt_llm::runtime::LoraCache::bumpTaskInProgress"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache18bumpTaskInProgressE10TaskIdType", "tensorrt_llm::runtime::LoraCache::bumpTaskInProgress::taskId"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache19claimPagesWithEvictE10SizeType32", "tensorrt_llm::runtime::LoraCache::claimPagesWithEvict"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache19claimPagesWithEvictE10SizeType32", "tensorrt_llm::runtime::LoraCache::claimPagesWithEvict::numPages"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache8copyTaskE10TaskIdTypeR9LoraCacheb", "tensorrt_llm::runtime::LoraCache::copyTask"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache8copyTaskE10TaskIdTypeR9LoraCacheb", "tensorrt_llm::runtime::LoraCache::copyTask::deviceCache"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache8copyTaskE10TaskIdTypeR9LoraCacheb", "tensorrt_llm::runtime::LoraCache::copyTask::markDone"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache8copyTaskE10TaskIdTypeR9LoraCacheb", "tensorrt_llm::runtime::LoraCache::copyTask::taskId"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache", "tensorrt_llm::runtime::LoraCache::copyTaskMapPages"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache", "tensorrt_llm::runtime::LoraCache::copyTaskMapPages::sourceTaskValue"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache", "tensorrt_llm::runtime::LoraCache::copyTaskMapPages::targetCache"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache", "tensorrt_llm::runtime::LoraCache::copyTaskMapPages::targetPageIds"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache", "tensorrt_llm::runtime::LoraCache::copyTaskMapPages::targetTaskValue"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::config"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::moduleIdToModel"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::pageIds"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::pages"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::weights"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::worldConfig"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE10TaskIdType", "tensorrt_llm::runtime::LoraCache::determineNumPages"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE9TensorPtr", "tensorrt_llm::runtime::LoraCache::determineNumPages"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE9TensorPtr", "tensorrt_llm::runtime::LoraCache::determineNumPages::config"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE10TaskIdType", "tensorrt_llm::runtime::LoraCache::determineNumPages::taskId"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache4fitsE9TensorPtr", "tensorrt_llm::runtime::LoraCache::fits"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache4fitsE9TensorPtr", "tensorrt_llm::runtime::LoraCache::fits::config"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3getE10TaskIdType", "tensorrt_llm::runtime::LoraCache::get"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3getE10TaskIdType", "tensorrt_llm::runtime::LoraCache::get::taskId"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache11getNumPagesEv", "tensorrt_llm::runtime::LoraCache::getNumPages"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache10getPagePtrE6size_t", "tensorrt_llm::runtime::LoraCache::getPagePtr"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache10getPagePtrE6size_t", "tensorrt_llm::runtime::LoraCache::getPagePtr::pageId"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache9getStatusE10TaskIdType", "tensorrt_llm::runtime::LoraCache::getStatus"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache9getStatusE10TaskIdType", "tensorrt_llm::runtime::LoraCache::getStatus::taskId"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache3hasE10TaskIdType", "tensorrt_llm::runtime::LoraCache::has"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache3hasE10TaskIdType", "tensorrt_llm::runtime::LoraCache::has::taskId"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache6isDoneE10TaskIdType", "tensorrt_llm::runtime::LoraCache::isDone"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache6isDoneE10TaskIdType", "tensorrt_llm::runtime::LoraCache::isDone::taskId"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache8isLoadedE10TaskIdType", "tensorrt_llm::runtime::LoraCache::isLoaded"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache8isLoadedE10TaskIdType", "tensorrt_llm::runtime::LoraCache::isLoaded::taskId"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus20kVALUE_STATUS_LOADEDE", "tensorrt_llm::runtime::LoraCache::kVALUE_STATUS_LOADED"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus21kVALUE_STATUS_MISSINGE", "tensorrt_llm::runtime::LoraCache::kVALUE_STATUS_MISSING"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus24kVALUE_STATUS_PROCESSINGE", "tensorrt_llm::runtime::LoraCache::kVALUE_STATUS_PROCESSING"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsE10TaskIdType9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsER9TaskValue9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsER9TaskValue9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::cacheValue"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsE10TaskIdType9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::config"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsER9TaskValue9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::config"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsE10TaskIdType9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::taskId"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsE10TaskIdType9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::weights"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsER9TaskValue9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::weights"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache14mBufferManagerE", "tensorrt_llm::runtime::LoraCache::mBufferManager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9mCacheMapE", "tensorrt_llm::runtime::LoraCache::mCacheMap"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11mCacheMutexE", "tensorrt_llm::runtime::LoraCache::mCacheMutex"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17mCachePageManagerE", "tensorrt_llm::runtime::LoraCache::mCachePageManager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21mDeviceBufferManagersE", "tensorrt_llm::runtime::LoraCache::mDeviceBufferManagers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache10mDoneTasksE", "tensorrt_llm::runtime::LoraCache::mDoneTasks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16mInProgressTasksE", "tensorrt_llm::runtime::LoraCache::mInProgressTasks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12mModelConfigE", "tensorrt_llm::runtime::LoraCache::mModelConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17mModuleIdToModuleE", "tensorrt_llm::runtime::LoraCache::mModuleIdToModule"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache18mPageManagerConfigE", "tensorrt_llm::runtime::LoraCache::mPageManagerConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11mPagesMutexE", "tensorrt_llm::runtime::LoraCache::mPagesMutex"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12mWorldConfigE", "tensorrt_llm::runtime::LoraCache::mWorldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11markAllDoneEv", "tensorrt_llm::runtime::LoraCache::markAllDone"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12markTaskDoneE10TaskIdType", "tensorrt_llm::runtime::LoraCache::markTaskDone"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12markTaskDoneE10TaskIdType", "tensorrt_llm::runtime::LoraCache::markTaskDone::taskId"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb", "tensorrt_llm::runtime::LoraCache::put"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb", "tensorrt_llm::runtime::LoraCache::put::config"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb", "tensorrt_llm::runtime::LoraCache::put::load"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb", "tensorrt_llm::runtime::LoraCache::put::taskId"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb", "tensorrt_llm::runtime::LoraCache::put::weights"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpu"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpu::input"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpu::output"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpu::tpRank"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpu::tpSize"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner::input"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner::output"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner::tpRank"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner::tpSize"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullExceptionE", "tensorrt_llm::runtime::LoraCacheFullException"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullException22LoraCacheFullExceptionERKNSt6stringE", "tensorrt_llm::runtime::LoraCacheFullException::LoraCacheFullException"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullException22LoraCacheFullExceptionERKNSt6stringE", "tensorrt_llm::runtime::LoraCacheFullException::LoraCacheFullException::msg"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullExceptionD0Ev", "tensorrt_llm::runtime::LoraCacheFullException::~LoraCacheFullException"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManagerE", "tensorrt_llm::runtime::LoraCachePageManager"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager20LoraCachePageManagerERK26LoraCachePageManagerConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCachePageManager::LoraCachePageManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager20LoraCachePageManagerERK26LoraCachePageManagerConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCachePageManager::LoraCachePageManager::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager20LoraCachePageManagerERK26LoraCachePageManagerConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCachePageManager::LoraCachePageManager::config"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager9TensorPtrE", "tensorrt_llm::runtime::LoraCachePageManager::TensorPtr"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager8blockPtrE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManager::blockPtr"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager8blockPtrE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManager::blockPtr::blockIdx"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10claimPagesE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManager::claimPages"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10claimPagesE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManager::claimPages::numPages"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10initializeERK13BufferManager", "tensorrt_llm::runtime::LoraCachePageManager::initialize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10initializeERK13BufferManager", "tensorrt_llm::runtime::LoraCachePageManager::initialize::bufferManager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager7mConfigE", "tensorrt_llm::runtime::LoraCachePageManager::mConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager12mFreePageIdsE", "tensorrt_llm::runtime::LoraCachePageManager::mFreePageIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager11mIsPageFreeE", "tensorrt_llm::runtime::LoraCachePageManager::mIsPageFree"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager11mPageBlocksE", "tensorrt_llm::runtime::LoraCachePageManager::mPageBlocks"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager14mutablePagePtrENSt6size_tE", "tensorrt_llm::runtime::LoraCachePageManager::mutablePagePtr"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager14mutablePagePtrENSt6size_tE", "tensorrt_llm::runtime::LoraCachePageManager::mutablePagePtr::pageIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager17numAvailablePagesEv", "tensorrt_llm::runtime::LoraCachePageManager::numAvailablePages"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager7pagePtrENSt6size_tE", "tensorrt_llm::runtime::LoraCachePageManager::pagePtr"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager7pagePtrENSt6size_tE", "tensorrt_llm::runtime::LoraCachePageManager::pagePtr::pageIdx"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager12releasePagesERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCachePageManager::releasePages"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager12releasePagesERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCachePageManager::releasePages::pages"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfigE", "tensorrt_llm::runtime::LoraCachePageManagerConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::dType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::maxPagesPerBlock"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::memType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::numCopyStreams"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::pageWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::slotsPerPage"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::totalNumPages"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig11getDataTypeEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getDataType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig13getInitToZeroEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getInitToZero"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig19getMaxPagesPerBlockEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getMaxPagesPerBlock"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig13getMemoryTypeEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getMemoryType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig17getNumCopyStreamsEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getNumCopyStreams"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig12getPageWidthEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getPageWidth"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig15getSlotsPerPageEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getSlotsPerPage"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig16getTotalNumPagesEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getTotalNumPages"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig9mDataTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mDataType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11mInitToZeroE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mInitToZero"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig17mMaxPagesPerBlockE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mMaxPagesPerBlock"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11mMemoryTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mMemoryType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15mNumCopyStreamsE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mNumCopyStreams"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig10mPageWidthE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mPageWidth"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13mSlotsPerPageE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mSlotsPerPage"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig14mTotalNumPagesE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mTotalNumPages"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11setDataTypeERKN8nvinfer18DataTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setDataType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11setDataTypeERKN8nvinfer18DataTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setDataType::dtype"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setInitToZeroEb", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setInitToZero"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setInitToZeroEb", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setInitToZero::initToZero"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig19setMaxPagesPerBlockERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setMaxPagesPerBlock"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig19setMaxPagesPerBlockERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setMaxPagesPerBlock::maxPagesPerBlock"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setMemoryTypeERKN7runtime10MemoryTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setMemoryType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setMemoryTypeERKN7runtime10MemoryTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setMemoryType::memoryType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig17setNumCopyStreamsE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setNumCopyStreams"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig17setNumCopyStreamsE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setNumCopyStreams::numCopyStreams"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig12setPageWidthERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setPageWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig12setPageWidthERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setPageWidth::pageWidth"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setSlotsPerPageERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setSlotsPerPage"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setSlotsPerPageERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setSlotsPerPage::slotsPerPage"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setTotalNumPageERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setTotalNumPage"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setTotalNumPageERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setTotalNumPage::totalNumPages"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedExceptionE", "tensorrt_llm::runtime::LoraExpectedException"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedException21LoraExpectedExceptionERKNSt6stringE", "tensorrt_llm::runtime::LoraExpectedException::LoraExpectedException"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedException21LoraExpectedExceptionERKNSt6stringE", "tensorrt_llm::runtime::LoraExpectedException::LoraExpectedException::msg"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedExceptionD0Ev", "tensorrt_llm::runtime::LoraExpectedException::~LoraExpectedException"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModuleE", "tensorrt_llm::runtime::LoraModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10LoraModule", "tensorrt_llm::runtime::LoraModule::LoraModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleEv", "tensorrt_llm::runtime::LoraModule::LoraModule"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::inDim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::inDimFirst"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::inTpSplitDim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10LoraModule", "tensorrt_llm::runtime::LoraModule::LoraModule::o"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::outDim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::outDimFirst"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::outTpSplitDim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::t"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleTypeE", "tensorrt_llm::runtime::LoraModule::ModuleType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kATTN_DENSEE", "tensorrt_llm::runtime::LoraModule::ModuleType::kATTN_DENSE"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_KE", "tensorrt_llm::runtime::LoraModule::ModuleType::kATTN_K"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_QE", "tensorrt_llm::runtime::LoraModule::ModuleType::kATTN_Q"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kATTN_QKVE", "tensorrt_llm::runtime::LoraModule::ModuleType::kATTN_QKV"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_VE", "tensorrt_llm::runtime::LoraModule::ModuleType::kATTN_V"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType17kCROSS_ATTN_DENSEE", "tensorrt_llm::runtime::LoraModule::ModuleType::kCROSS_ATTN_DENSE"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_KE", "tensorrt_llm::runtime::LoraModule::ModuleType::kCROSS_ATTN_K"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_QE", "tensorrt_llm::runtime::LoraModule::ModuleType::kCROSS_ATTN_Q"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType15kCROSS_ATTN_QKVE", "tensorrt_llm::runtime::LoraModule::ModuleType::kCROSS_ATTN_QKV"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_VE", "tensorrt_llm::runtime::LoraModule::ModuleType::kCROSS_ATTN_V"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType8kINVALIDE", "tensorrt_llm::runtime::LoraModule::ModuleType::kINVALID"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMLP_4H_TO_HE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMLP_4H_TO_H"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kMLP_GATEE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMLP_GATE"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMLP_GATE_UPE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMLP_GATE_UP"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMLP_H_TO_4HE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMLP_H_TO_4H"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kMLP_ROUTERE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMLP_ROUTER"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMOE_4H_TO_HE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMOE_4H_TO_H"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kMOE_GATEE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMOE_GATE"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMOE_H_TO_4HE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMOE_H_TO_4H"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kMOE_ROUTERE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMOE_ROUTER"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule9TensorPtrE", "tensorrt_llm::runtime::LoraModule::TensorPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::attentionHeadSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::hiddenSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::loraModuleNames"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::mlpHiddenSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::numAttentionHeads"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::numExperts"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::numKvAttentionHeads"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18flattenedInOutSizeE10SizeType32b", "tensorrt_llm::runtime::LoraModule::flattenedInOutSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18flattenedInOutSizeE10SizeType32b", "tensorrt_llm::runtime::LoraModule::flattenedInOutSize::adapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18flattenedInOutSizeE10SizeType32b", "tensorrt_llm::runtime::LoraModule::flattenedInOutSize::isDora"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule5inDimEv", "tensorrt_llm::runtime::LoraModule::inDim"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule10inDimFirstEv", "tensorrt_llm::runtime::LoraModule::inDimFirst"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule6inSizeE10SizeType32", "tensorrt_llm::runtime::LoraModule::inSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule6inSizeE10SizeType32", "tensorrt_llm::runtime::LoraModule::inSize::adapterSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12inTpSplitDimEv", "tensorrt_llm::runtime::LoraModule::inTpSplitDim"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18localInAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInAdapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18localInAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInAdapterSize::adapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18localInAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInAdapterSize::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule10localInDimE10SizeType32", "tensorrt_llm::runtime::LoraModule::localInDim"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule10localInDimE10SizeType32", "tensorrt_llm::runtime::LoraModule::localInDim::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localInOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInOutSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localInOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInOutSize::adapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localInOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInOutSize::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localInSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localInSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInSize::adapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localInSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInSize::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule19localOutAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutAdapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule19localOutAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutAdapterSize::adapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule19localOutAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutAdapterSize::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localOutDimE10SizeType32", "tensorrt_llm::runtime::LoraModule::localOutDim"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localOutDimE10SizeType32", "tensorrt_llm::runtime::LoraModule::localOutDim::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12localOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12localOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutSize::adapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12localOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutSize::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule15localScalesSizeE10SizeType32b", "tensorrt_llm::runtime::LoraModule::localScalesSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule15localScalesSizeE10SizeType32b", "tensorrt_llm::runtime::LoraModule::localScalesSize::isDora"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule15localScalesSizeE10SizeType32b", "tensorrt_llm::runtime::LoraModule::localScalesSize::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localTotalSizeE10SizeType3210SizeType32b", "tensorrt_llm::runtime::LoraModule::localTotalSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localTotalSizeE10SizeType3210SizeType32b", "tensorrt_llm::runtime::LoraModule::localTotalSize::adapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localTotalSizeE10SizeType3210SizeType32b", "tensorrt_llm::runtime::LoraModule::localTotalSize::isDora"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localTotalSizeE10SizeType3210SizeType32b", "tensorrt_llm::runtime::LoraModule::localTotalSize::tpSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule6mInDimE", "tensorrt_llm::runtime::LoraModule::mInDim"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule11mInDimFirstE", "tensorrt_llm::runtime::LoraModule::mInDimFirst"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule13mInTpSplitDimE", "tensorrt_llm::runtime::LoraModule::mInTpSplitDim"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule7mOutDimE", "tensorrt_llm::runtime::LoraModule::mOutDim"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12mOutDimFirstE", "tensorrt_llm::runtime::LoraModule::mOutDimFirst"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule14mOutTpSplitDimE", "tensorrt_llm::runtime::LoraModule::mOutTpSplitDim"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule5mTypeE", "tensorrt_llm::runtime::LoraModule::mType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule4nameEv", "tensorrt_llm::runtime::LoraModule::name"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModuleaSERK10LoraModule", "tensorrt_llm::runtime::LoraModule::operator="], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModuleaSERK10LoraModule", "tensorrt_llm::runtime::LoraModule::operator=::o"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule6outDimEv", "tensorrt_llm::runtime::LoraModule::outDim"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11outDimFirstEv", "tensorrt_llm::runtime::LoraModule::outDimFirst"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule7outSizeE10SizeType32", "tensorrt_llm::runtime::LoraModule::outSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule7outSizeE10SizeType32", "tensorrt_llm::runtime::LoraModule::outSize::adapterSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule13outTpSplitDimEv", "tensorrt_llm::runtime::LoraModule::outTpSplitDim"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10ModuleType", "tensorrt_llm::runtime::LoraModule::toModuleName"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10SizeType32", "tensorrt_llm::runtime::LoraModule::toModuleName"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10SizeType32", "tensorrt_llm::runtime::LoraModule::toModuleName::id"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10ModuleType", "tensorrt_llm::runtime::LoraModule::toModuleName::t"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleTypeERKNSt11string_viewE", "tensorrt_llm::runtime::LoraModule::toModuleType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleTypeERKNSt11string_viewE", "tensorrt_llm::runtime::LoraModule::toModuleType::name"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule5valueEv", "tensorrt_llm::runtime::LoraModule::value"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14LoraTaskIdTypeE", "tensorrt_llm::runtime::LoraTaskIdType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime17MPI_group_barrierENSt3setIiEE", "tensorrt_llm::runtime::MPI_group_barrier"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17MPI_group_barrierENSt3setIiEE", "tensorrt_llm::runtime::MPI_group_barrier::ranks"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModuleE", "tensorrt_llm::runtime::MedusaModule"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule13MedusaChoicesE", "tensorrt_llm::runtime::MedusaModule::MedusaChoices"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::MedusaModule::MedusaModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleEv", "tensorrt_llm::runtime::MedusaModule::MedusaModule"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::MedusaModule::MedusaModule::maxAcceptedTokens"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::MedusaModule::MedusaModule::maxDraftTokens"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule9TensorPtrE", "tensorrt_llm::runtime::MedusaModule::TensorPtr"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule16getMedusaChoicesEv", "tensorrt_llm::runtime::MedusaModule::getMedusaChoices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule21mDefaultMedusaChoicesE", "tensorrt_llm::runtime::MedusaModule::mDefaultMedusaChoices"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCountersE", "tensorrt_llm::runtime::MemoryCounters"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE", "tensorrt_llm::runtime::MemoryCounters::DiffType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters14MemoryCountersEv", "tensorrt_llm::runtime::MemoryCounters::MemoryCounters"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10SizeType32E", "tensorrt_llm::runtime::MemoryCounters::SizeType32"], [1, 3, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters8allocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8allocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate"], [1, 8, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters8allocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate::T"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8allocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate::memoryType"], [1, 4, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters8allocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8allocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate::size"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE10SizeType32i", "tensorrt_llm::runtime::MemoryCounters::bytesToString"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8DiffTypei", "tensorrt_llm::runtime::MemoryCounters::bytesToString"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE10SizeType32i", "tensorrt_llm::runtime::MemoryCounters::bytesToString::bytes"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8DiffTypei", "tensorrt_llm::runtime::MemoryCounters::bytesToString::bytes"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE10SizeType32i", "tensorrt_llm::runtime::MemoryCounters::bytesToString::precision"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8DiffTypei", "tensorrt_llm::runtime::MemoryCounters::bytesToString::precision"], [1, 3, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters10deallocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10deallocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate"], [1, 8, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters10deallocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate::T"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10deallocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate::memoryType"], [1, 4, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters10deallocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10deallocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate::size"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getCpuEv", "tensorrt_llm::runtime::MemoryCounters::getCpu"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getCpuDiffEv", "tensorrt_llm::runtime::MemoryCounters::getCpuDiff"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getGpuEv", "tensorrt_llm::runtime::MemoryCounters::getGpu"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getGpuDiffEv", "tensorrt_llm::runtime::MemoryCounters::getGpuDiff"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11getInstanceEv", "tensorrt_llm::runtime::MemoryCounters::getInstance"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters9getPinnedEv", "tensorrt_llm::runtime::MemoryCounters::getPinned"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters13getPinnedDiffEv", "tensorrt_llm::runtime::MemoryCounters::getPinnedDiff"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters13getPinnedPoolEv", "tensorrt_llm::runtime::MemoryCounters::getPinnedPool"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters17getPinnedPoolDiffEv", "tensorrt_llm::runtime::MemoryCounters::getPinnedPoolDiff"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getUVMEv", "tensorrt_llm::runtime::MemoryCounters::getUVM"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getUVMDiffEv", "tensorrt_llm::runtime::MemoryCounters::getUVMDiff"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mCpuE", "tensorrt_llm::runtime::MemoryCounters::mCpu"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mCpuDiffE", "tensorrt_llm::runtime::MemoryCounters::mCpuDiff"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mGpuE", "tensorrt_llm::runtime::MemoryCounters::mGpu"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mGpuDiffE", "tensorrt_llm::runtime::MemoryCounters::mGpuDiff"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters7mPinnedE", "tensorrt_llm::runtime::MemoryCounters::mPinned"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11mPinnedDiffE", "tensorrt_llm::runtime::MemoryCounters::mPinnedDiff"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11mPinnedPoolE", "tensorrt_llm::runtime::MemoryCounters::mPinnedPool"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters15mPinnedPoolDiffE", "tensorrt_llm::runtime::MemoryCounters::mPinnedPoolDiff"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mUVME", "tensorrt_llm::runtime::MemoryCounters::mUVM"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mUVMDiffE", "tensorrt_llm::runtime::MemoryCounters::mUVMDiff"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters8toStringEv", "tensorrt_llm::runtime::MemoryCounters::toString"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryTypeE", "tensorrt_llm::runtime::MemoryType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kCPUE", "tensorrt_llm::runtime::MemoryType::kCPU"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kGPUE", "tensorrt_llm::runtime::MemoryType::kGPU"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryType7kPINNEDE", "tensorrt_llm::runtime::MemoryType::kPINNED"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryType11kPINNEDPOOLE", "tensorrt_llm::runtime::MemoryType::kPINNEDPOOL"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kUVME", "tensorrt_llm::runtime::MemoryType::kUVM"], [1, 2, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime16MemoryTypeStringE", "tensorrt_llm::runtime::MemoryTypeString"], [1, 8, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime16MemoryTypeStringE", "tensorrt_llm::runtime::MemoryTypeString::T"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEEE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kCPU>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEE5valueE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kCPU>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEEE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kGPU>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEE5valueE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kGPU>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEEE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kPINNED>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEE5valueE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kPINNED>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType11kPINNEDPOOLEEE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kPINNEDPOOL>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType11kPINNEDPOOLEE5valueE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kPINNEDPOOL>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kUVMEEE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kUVM>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kUVMEE5valueE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kUVM>::value"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfigE", "tensorrt_llm::runtime::ModelConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheTypeE", "tensorrt_llm::runtime::ModelConfig::KVCacheType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType11kCONTINUOUSE", "tensorrt_llm::runtime::ModelConfig::KVCacheType::kCONTINUOUS"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType9kDISABLEDE", "tensorrt_llm::runtime::ModelConfig::KVCacheType::kDISABLED"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType6kPAGEDE", "tensorrt_llm::runtime::ModelConfig::KVCacheType::kPAGED"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21KVCacheTypeFromStringENSt6stringE", "tensorrt_llm::runtime::ModelConfig::KVCacheTypeFromString"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21KVCacheTypeFromStringENSt6stringE", "tensorrt_llm::runtime::ModelConfig::KVCacheTypeFromString::value"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerTypeE", "tensorrt_llm::runtime::ModelConfig::LayerType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType10kATTENTIONE", "tensorrt_llm::runtime::ModelConfig::LayerType::kATTENTION"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType7kLINEARE", "tensorrt_llm::runtime::ModelConfig::LayerType::kLINEAR"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType5kNOOPE", "tensorrt_llm::runtime::ModelConfig::LayerType::kNOOP"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType10kRECURRENTE", "tensorrt_llm::runtime::ModelConfig::LayerType::kRECURRENT"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsTypeE", "tensorrt_llm::runtime::ModelConfig::ManageWeightsType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsType9kDisabledE", "tensorrt_llm::runtime::ModelConfig::ManageWeightsType::kDisabled"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsType8kEnabledE", "tensorrt_llm::runtime::ModelConfig::ManageWeightsType::kEnabled"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::dtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::hiddenSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::nbAttentionLayers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::nbHeads"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::nbLayers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::nbRnnLayers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::vocabSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariantE", "tensorrt_llm::runtime::ModelConfig::ModelVariant"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant8kChatGlmE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kChatGlm"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant7kEncDecE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kEncDec"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant4kGlmE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kGlm"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant4kGptE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kGpt"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant6kMambaE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kMamba"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant15kRecurrentGemmaE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kRecurrentGemma"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfigE", "tensorrt_llm::runtime::ModelConfig::RnnConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig10convKernelE", "tensorrt_llm::runtime::ModelConfig::RnnConfig::convKernel"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig14rnnConvDimSizeE", "tensorrt_llm::runtime::ModelConfig::RnnConfig::rnnConvDimSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig11rnnHeadSizeE", "tensorrt_llm::runtime::ModelConfig::RnnConfig::rnnHeadSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig13rnnHiddenSizeE", "tensorrt_llm::runtime::ModelConfig::RnnConfig::rnnHiddenSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig9stateSizeE", "tensorrt_llm::runtime::ModelConfig::RnnConfig::stateSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20computeContextLogitsEb", "tensorrt_llm::runtime::ModelConfig::computeContextLogits"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20computeContextLogitsEv", "tensorrt_llm::runtime::ModelConfig::computeContextLogits"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20computeContextLogitsEb", "tensorrt_llm::runtime::ModelConfig::computeContextLogits::computeContextLogits"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23computeGenerationLogitsEb", "tensorrt_llm::runtime::ModelConfig::computeGenerationLogits"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig23computeGenerationLogitsEv", "tensorrt_llm::runtime::ModelConfig::computeGenerationLogits"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23computeGenerationLogitsEb", "tensorrt_llm::runtime::ModelConfig::computeGenerationLogits::computeGenerationLogits"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16countLocalLayersE9LayerType10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::countLocalLayers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16countLocalLayersE9LayerType10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::countLocalLayers::layerType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16countLocalLayersE9LayerType10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::countLocalLayers::pipelineParallelism"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16countLocalLayersE9LayerType10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::countLocalLayers::pipelineParallelismRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20countLowerRankLayersE9LayerType10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::countLowerRankLayers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20countLowerRankLayersE9LayerType10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::countLowerRankLayers::layerType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20countLowerRankLayersE9LayerType10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::countLowerRankLayers::pipelineParallelism"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20countLowerRankLayersE9LayerType10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::countLowerRankLayers::pipelineParallelismRank"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig32disableSeamlessLookaheadDecodingEv", "tensorrt_llm::runtime::ModelConfig::disableSeamlessLookaheadDecoding"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig31enableSeamlessLookaheadDecodingE10SizeType32", "tensorrt_llm::runtime::ModelConfig::enableSeamlessLookaheadDecoding"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig31enableSeamlessLookaheadDecodingE10SizeType32", "tensorrt_llm::runtime::ModelConfig::enableSeamlessLookaheadDecoding::maxDraftTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getContextFMHAEv", "tensorrt_llm::runtime::ModelConfig::getContextFMHA"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig11getDataTypeEv", "tensorrt_llm::runtime::ModelConfig::getDataType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getEncoderHiddenSizeEv", "tensorrt_llm::runtime::ModelConfig::getEncoderHiddenSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getFirstLocalLayerE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getFirstLocalLayer"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getFirstLocalLayerE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getFirstLocalLayer::pipelineParallelism"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getFirstLocalLayerE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getFirstLocalLayer::pipelineParallelismRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21getGemmAllReduceDtypeEv", "tensorrt_llm::runtime::ModelConfig::getGemmAllReduceDtype"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getHiddenSizeEv", "tensorrt_llm::runtime::ModelConfig::getHiddenSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getKVCacheTypeEv", "tensorrt_llm::runtime::ModelConfig::getKVCacheType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getKvDataTypeEv", "tensorrt_llm::runtime::ModelConfig::getKvDataType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getLayerTypesEv", "tensorrt_llm::runtime::ModelConfig::getLayerTypes"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getLogitsDtypeEv", "tensorrt_llm::runtime::ModelConfig::getLogitsDtype"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getLoraModulesEv", "tensorrt_llm::runtime::ModelConfig::getLoraModules"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getManageWeightsTypeEv", "tensorrt_llm::runtime::ModelConfig::getManageWeightsType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxBatchSizeEv", "tensorrt_llm::runtime::ModelConfig::getMaxBatchSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxBeamWidthEv", "tensorrt_llm::runtime::ModelConfig::getMaxBeamWidth"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig25getMaxDecodingDraftTokensEv", "tensorrt_llm::runtime::ModelConfig::getMaxDecodingDraftTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getMaxDecodingTokensEv", "tensorrt_llm::runtime::ModelConfig::getMaxDecodingTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16getMaxEncoderLenEv", "tensorrt_llm::runtime::ModelConfig::getMaxEncoderLen"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getMaxInputLenEv", "tensorrt_llm::runtime::ModelConfig::getMaxInputLen"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getMaxLoraRankEv", "tensorrt_llm::runtime::ModelConfig::getMaxLoraRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxNumTokensEv", "tensorrt_llm::runtime::ModelConfig::getMaxNumTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig24getMaxPositionEmbeddingsEv", "tensorrt_llm::runtime::ModelConfig::getMaxPositionEmbeddings"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig30getMaxPromptEmbeddingTableSizeEv", "tensorrt_llm::runtime::ModelConfig::getMaxPromptEmbeddingTableSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17getMaxSequenceLenEv", "tensorrt_llm::runtime::ModelConfig::getMaxSequenceLen"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16getMlpHiddenSizeEv", "tensorrt_llm::runtime::ModelConfig::getMlpHiddenSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getModelNameEv", "tensorrt_llm::runtime::ModelConfig::getModelName"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getModelVariantEv", "tensorrt_llm::runtime::ModelConfig::getModelVariant"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getNbAttentionLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbAttentionLayers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getNbAttentionLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbAttentionLayers::pipelineParallelism"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getNbAttentionLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbAttentionLayers::pipelineParallelismRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig10getNbHeadsEv", "tensorrt_llm::runtime::ModelConfig::getNbHeads"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getNbKvHeadsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbKvHeads"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getNbKvHeadsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbKvHeads::layerIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig11getNbLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbLayers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig11getNbLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbLayers::pipelineParallelism"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig11getNbLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbLayers::pipelineParallelismRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getNbRnnLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbRnnLayers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getNbRnnLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbRnnLayers::pipelineParallelism"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getNbRnnLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbRnnLayers::pipelineParallelismRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig27getNumKvHeadsForGivenLayersERKNSt6vectorI10SizeType32EEb", "tensorrt_llm::runtime::ModelConfig::getNumKvHeadsForGivenLayers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig27getNumKvHeadsForGivenLayersERKNSt6vectorI10SizeType32EEb", "tensorrt_llm::runtime::ModelConfig::getNumKvHeadsForGivenLayers::isCrossAttention"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig27getNumKvHeadsForGivenLayersERKNSt6vectorI10SizeType32EEb", "tensorrt_llm::runtime::ModelConfig::getNumKvHeadsForGivenLayers::layers"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21getNumKvHeadsPerLayerEv", "tensorrt_llm::runtime::ModelConfig::getNumKvHeadsPerLayer"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig31getNumKvHeadsPerLayerLocalRangeE10SizeType3210SizeType32b", "tensorrt_llm::runtime::ModelConfig::getNumKvHeadsPerLayerLocalRange"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig31getNumKvHeadsPerLayerLocalRangeE10SizeType3210SizeType32b", "tensorrt_llm::runtime::ModelConfig::getNumKvHeadsPerLayerLocalRange::isCrossAttention"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig31getNumKvHeadsPerLayerLocalRangeE10SizeType3210SizeType32b", "tensorrt_llm::runtime::ModelConfig::getNumKvHeadsPerLayerLocalRange::pipelineParallelism"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig31getNumKvHeadsPerLayerLocalRangeE10SizeType3210SizeType32b", "tensorrt_llm::runtime::ModelConfig::getNumKvHeadsPerLayerLocalRange::pipelineParallelismRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getNumLanguagesEv", "tensorrt_llm::runtime::ModelConfig::getNumLanguages"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig25getOptProfilesSplitPointsEv", "tensorrt_llm::runtime::ModelConfig::getOptProfilesSplitPoints"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig19getPagedContextFMHAEv", "tensorrt_llm::runtime::ModelConfig::getPagedContextFMHA"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getPpReduceScatterEv", "tensorrt_llm::runtime::ModelConfig::getPpReduceScatter"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getQuantModeEv", "tensorrt_llm::runtime::ModelConfig::getQuantMode"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getRnnConfigEv", "tensorrt_llm::runtime::ModelConfig::getRnnConfig"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21getRotaryEmbeddingDimEv", "tensorrt_llm::runtime::ModelConfig::getRotaryEmbeddingDim"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getSizePerHeadEv", "tensorrt_llm::runtime::ModelConfig::getSizePerHead"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig26getSpeculativeDecodingModeEv", "tensorrt_llm::runtime::ModelConfig::getSpeculativeDecodingMode"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig28getSpeculativeDecodingModuleEv", "tensorrt_llm::runtime::ModelConfig::getSpeculativeDecodingModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig31getSpeculativeDecodingModulePtrEv", "tensorrt_llm::runtime::ModelConfig::getSpeculativeDecodingModulePtr"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig31getSpeculativeDecodingModulePtrEv", "tensorrt_llm::runtime::ModelConfig::getSpeculativeDecodingModulePtr"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17getTokensPerBlockEv", "tensorrt_llm::runtime::ModelConfig::getTokensPerBlock"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getVocabSizeEv", "tensorrt_llm::runtime::ModelConfig::getVocabSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getVocabSizePaddedE10SizeType32", "tensorrt_llm::runtime::ModelConfig::getVocabSizePadded"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getVocabSizePaddedE10SizeType32", "tensorrt_llm::runtime::ModelConfig::getVocabSizePadded::worldSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12hasRnnConfigEv", "tensorrt_llm::runtime::ModelConfig::hasRnnConfig"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig28hasSpeculativeDecodingModuleEv", "tensorrt_llm::runtime::ModelConfig::hasSpeculativeDecodingModule"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig19isContinuousKVCacheEv", "tensorrt_llm::runtime::ModelConfig::isContinuousKVCache"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16isKVCacheEnabledEv", "tensorrt_llm::runtime::ModelConfig::isKVCacheEnabled"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12isMultiModalEv", "tensorrt_llm::runtime::ModelConfig::isMultiModal"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14isPagedKVCacheEv", "tensorrt_llm::runtime::ModelConfig::isPagedKVCache"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig10isRnnBasedEv", "tensorrt_llm::runtime::ModelConfig::isRnnBased"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18isTransformerBasedEv", "tensorrt_llm::runtime::ModelConfig::isTransformerBased"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig9isWhisperEv", "tensorrt_llm::runtime::ModelConfig::isWhisper"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig29kDEFAULT_NUM_TOKENS_PER_BLOCKE", "tensorrt_llm::runtime::ModelConfig::kDEFAULT_NUM_TOKENS_PER_BLOCK"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26kOPT_PROFILES_SPLIT_POINTSE", "tensorrt_llm::runtime::ModelConfig::kOPT_PROFILES_SPLIT_POINTS"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mComputeContextLogitsE", "tensorrt_llm::runtime::ModelConfig::mComputeContextLogits"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24mComputeGenerationLogitsE", "tensorrt_llm::runtime::ModelConfig::mComputeGenerationLogits"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mContextFMHAE", "tensorrt_llm::runtime::ModelConfig::mContextFMHA"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9mDataTypeE", "tensorrt_llm::runtime::ModelConfig::mDataType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mEncoderHiddenSizeE", "tensorrt_llm::runtime::ModelConfig::mEncoderHiddenSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig19mGemmAllReduceDtypeE", "tensorrt_llm::runtime::ModelConfig::mGemmAllReduceDtype"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mHiddenSizeE", "tensorrt_llm::runtime::ModelConfig::mHiddenSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mInputPackedE", "tensorrt_llm::runtime::ModelConfig::mInputPacked"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mKVCacheTypeE", "tensorrt_llm::runtime::ModelConfig::mKVCacheType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mLayerTypesE", "tensorrt_llm::runtime::ModelConfig::mLayerTypes"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mLogitsDtypeE", "tensorrt_llm::runtime::ModelConfig::mLogitsDtype"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mLoraModulesE", "tensorrt_llm::runtime::ModelConfig::mLoraModules"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mManageWeightsTypeE", "tensorrt_llm::runtime::ModelConfig::mManageWeightsType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxBatchSizeE", "tensorrt_llm::runtime::ModelConfig::mMaxBatchSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxBeamWidthE", "tensorrt_llm::runtime::ModelConfig::mMaxBeamWidth"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mMaxEncoderLenE", "tensorrt_llm::runtime::ModelConfig::mMaxEncoderLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mMaxInputLenE", "tensorrt_llm::runtime::ModelConfig::mMaxInputLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mMaxLoraRankE", "tensorrt_llm::runtime::ModelConfig::mMaxLoraRank"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxNumTokensE", "tensorrt_llm::runtime::ModelConfig::mMaxNumTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22mMaxPositionEmbeddingsE", "tensorrt_llm::runtime::ModelConfig::mMaxPositionEmbeddings"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28mMaxPromptEmbeddingTableSizeE", "tensorrt_llm::runtime::ModelConfig::mMaxPromptEmbeddingTableSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15mMaxSequenceLenE", "tensorrt_llm::runtime::ModelConfig::mMaxSequenceLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mMlpHiddenSizeE", "tensorrt_llm::runtime::ModelConfig::mMlpHiddenSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mModelNameE", "tensorrt_llm::runtime::ModelConfig::mModelName"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mModelVariantE", "tensorrt_llm::runtime::ModelConfig::mModelVariant"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mNbAttentionLayersE", "tensorrt_llm::runtime::ModelConfig::mNbAttentionLayers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig8mNbHeadsE", "tensorrt_llm::runtime::ModelConfig::mNbHeads"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9mNbLayersE", "tensorrt_llm::runtime::ModelConfig::mNbLayers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mNbRnnLayersE", "tensorrt_llm::runtime::ModelConfig::mNbRnnLayers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28mNumKvHeadsPerAttentionLayerE", "tensorrt_llm::runtime::ModelConfig::mNumKvHeadsPerAttentionLayer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig33mNumKvHeadsPerCrossAttentionLayerE", "tensorrt_llm::runtime::ModelConfig::mNumKvHeadsPerCrossAttentionLayer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mNumLanguagesE", "tensorrt_llm::runtime::ModelConfig::mNumLanguages"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17mPagedContextFMHAE", "tensorrt_llm::runtime::ModelConfig::mPagedContextFMHA"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mPagedStateE", "tensorrt_llm::runtime::ModelConfig::mPagedState"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16mPpReduceScatterE", "tensorrt_llm::runtime::ModelConfig::mPpReduceScatter"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mQuantModeE", "tensorrt_llm::runtime::ModelConfig::mQuantMode"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mRnnConfigE", "tensorrt_llm::runtime::ModelConfig::mRnnConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig19mRotaryEmbeddingDimE", "tensorrt_llm::runtime::ModelConfig::mRotaryEmbeddingDim"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mSizePerHeadE", "tensorrt_llm::runtime::ModelConfig::mSizePerHead"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20mSkipCrossAttnBlocksE", "tensorrt_llm::runtime::ModelConfig::mSkipCrossAttnBlocks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24mSpeculativeDecodingModeE", "tensorrt_llm::runtime::ModelConfig::mSpeculativeDecodingMode"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26mSpeculativeDecodingModuleE", "tensorrt_llm::runtime::ModelConfig::mSpeculativeDecodingModule"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15mTokensPerBlockE", "tensorrt_llm::runtime::ModelConfig::mTokensPerBlock"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mUseCrossAttentionE", "tensorrt_llm::runtime::ModelConfig::mUseCrossAttention"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23mUseGemmAllReducePluginE", "tensorrt_llm::runtime::ModelConfig::mUseGemmAllReducePlugin"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22mUseGptAttentionPluginE", "tensorrt_llm::runtime::ModelConfig::mUseGptAttentionPlugin"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mUseLoraPluginE", "tensorrt_llm::runtime::ModelConfig::mUseLoraPlugin"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mUseMambaConv1dPluginE", "tensorrt_llm::runtime::ModelConfig::mUseMambaConv1dPlugin"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9mUseMropeE", "tensorrt_llm::runtime::ModelConfig::mUseMrope"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mUsePositionEmbeddingE", "tensorrt_llm::runtime::ModelConfig::mUsePositionEmbedding"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mUseShapeInferenceE", "tensorrt_llm::runtime::ModelConfig::mUseShapeInference"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22mUseTokenTypeEmbeddingE", "tensorrt_llm::runtime::ModelConfig::mUseTokenTypeEmbedding"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mVocabSizeE", "tensorrt_llm::runtime::ModelConfig::mVocabSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig30resetSpeculativeDecodingModuleEv", "tensorrt_llm::runtime::ModelConfig::resetSpeculativeDecodingModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setContextFMHAEb", "tensorrt_llm::runtime::ModelConfig::setContextFMHA"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setContextFMHAEb", "tensorrt_llm::runtime::ModelConfig::setContextFMHA::contextFMHA"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setEncoderHiddenSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setEncoderHiddenSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setEncoderHiddenSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setEncoderHiddenSize::encoderHiddenSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setGemmAllReduceDtypeEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::setGemmAllReduceDtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setGemmAllReduceDtypeEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::setGemmAllReduceDtype::inputDtype"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setKVCacheTypeE11KVCacheType", "tensorrt_llm::runtime::ModelConfig::setKVCacheType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setKVCacheTypeE11KVCacheType", "tensorrt_llm::runtime::ModelConfig::setKVCacheType::kvCacheType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13setLayerTypesERKNSt6vectorI9LayerTypeEE", "tensorrt_llm::runtime::ModelConfig::setLayerTypes"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13setLayerTypesERKNSt6vectorI9LayerTypeEE", "tensorrt_llm::runtime::ModelConfig::setLayerTypes::layerTypes"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLogitsDtypeEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::setLogitsDtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLogitsDtypeEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::setLogitsDtype::inputDtype"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLoraModulesERKNSt6vectorI10LoraModuleEE", "tensorrt_llm::runtime::ModelConfig::setLoraModules"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLoraModulesERKNSt6vectorI10LoraModuleEE", "tensorrt_llm::runtime::ModelConfig::setLoraModules::loraModules"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setManageWeightsTypeEK17ManageWeightsType", "tensorrt_llm::runtime::ModelConfig::setManageWeightsType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setManageWeightsTypeEK17ManageWeightsType", "tensorrt_llm::runtime::ModelConfig::setManageWeightsType::manageWeightType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBatchSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBatchSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxBatchSize::maxBatchSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBeamWidthE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBeamWidthE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxBeamWidth::maxBeamWidth"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMaxEncoderLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxEncoderLen"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMaxEncoderLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxEncoderLen::maxEncoderLen"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxInputLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxInputLen"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxInputLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxInputLen::maxInputLen"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxLoraRankE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxLoraRank"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxLoraRankE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxLoraRank::maxLoraRank"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxNumTokensENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setMaxNumTokens"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxNumTokensENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setMaxNumTokens::maxNumTokens"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24setMaxPositionEmbeddingsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxPositionEmbeddings"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24setMaxPositionEmbeddingsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxPositionEmbeddings::maxPositionEmbeddings"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig30setMaxPromptEmbeddingTableSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxPromptEmbeddingTableSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig30setMaxPromptEmbeddingTableSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxPromptEmbeddingTableSize::maxPromptEmbeddingTableSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setMaxSequenceLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxSequenceLen"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setMaxSequenceLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxSequenceLen::maxSequenceLen"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMlpHiddenSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMlpHiddenSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMlpHiddenSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMlpHiddenSize::mlpHiddenSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setModelNameERKNSt6stringE", "tensorrt_llm::runtime::ModelConfig::setModelName"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setModelNameERKNSt6stringE", "tensorrt_llm::runtime::ModelConfig::setModelName::modelName"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setModelVariantE12ModelVariant", "tensorrt_llm::runtime::ModelConfig::setModelVariant"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setModelVariantE12ModelVariant", "tensorrt_llm::runtime::ModelConfig::setModelVariant::modelVariant"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setNbCrossKvHeadsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setNbCrossKvHeads"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setNbCrossKvHeadsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setNbCrossKvHeads::nbKvHeads"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setNbKvHeadsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setNbKvHeads"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setNbKvHeadsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setNbKvHeads::nbKvHeads"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26setNumKvHeadsPerCrossLayerERKNSt6vectorI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setNumKvHeadsPerCrossLayer"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26setNumKvHeadsPerCrossLayerERKNSt6vectorI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setNumKvHeadsPerCrossLayer::headsPerLayer"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setNumKvHeadsPerLayerERKNSt6vectorI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setNumKvHeadsPerLayer"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setNumKvHeadsPerLayerERKNSt6vectorI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setNumKvHeadsPerLayer::headsPerLayer"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setNumLanguagesENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setNumLanguages"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setNumLanguagesENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setNumLanguages::numLanguages"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig19setPagedContextFMHAEb", "tensorrt_llm::runtime::ModelConfig::setPagedContextFMHA"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig19setPagedContextFMHAEb", "tensorrt_llm::runtime::ModelConfig::setPagedContextFMHA::pagedContextFMHA"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18setPpReduceScatterEb", "tensorrt_llm::runtime::ModelConfig::setPpReduceScatter"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18setPpReduceScatterEb", "tensorrt_llm::runtime::ModelConfig::setPpReduceScatter::ppReduceScatter"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setQuantModeEN6common9QuantModeE", "tensorrt_llm::runtime::ModelConfig::setQuantMode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setQuantModeEN6common9QuantModeE", "tensorrt_llm::runtime::ModelConfig::setQuantMode::QuantMode"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setRnnConfigERK9RnnConfig", "tensorrt_llm::runtime::ModelConfig::setRnnConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setRnnConfigERK9RnnConfig", "tensorrt_llm::runtime::ModelConfig::setRnnConfig::rnnConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setRotaryEmbeddingDimE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setRotaryEmbeddingDim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setRotaryEmbeddingDimE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setRotaryEmbeddingDim::rotaryEmbeddingDim"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setSizePerHeadE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setSizePerHead"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setSizePerHeadE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setSizePerHead::sizePerHead"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22setSkipCrossAttnBlocksEb", "tensorrt_llm::runtime::ModelConfig::setSkipCrossAttnBlocks"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22setSkipCrossAttnBlocksEb", "tensorrt_llm::runtime::ModelConfig::setSkipCrossAttnBlocks::skipCrossAttnBlocks"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26setSpeculativeDecodingModeE23SpeculativeDecodingMode", "tensorrt_llm::runtime::ModelConfig::setSpeculativeDecodingMode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26setSpeculativeDecodingModeE23SpeculativeDecodingMode", "tensorrt_llm::runtime::ModelConfig::setSpeculativeDecodingMode::mode"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28setSpeculativeDecodingModuleERKNSt10shared_ptrI25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::ModelConfig::setSpeculativeDecodingModule"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28setSpeculativeDecodingModuleERKNSt10shared_ptrI25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::ModelConfig::setSpeculativeDecodingModule::speculativeDecodingModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setTokensPerBlockE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setTokensPerBlock"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setTokensPerBlockE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setTokensPerBlock::TokensPerBlock"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseCrossAttentionEb", "tensorrt_llm::runtime::ModelConfig::setUseCrossAttention"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseCrossAttentionEb", "tensorrt_llm::runtime::ModelConfig::setUseCrossAttention::useCrossAttention"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11setUseMropeEb", "tensorrt_llm::runtime::ModelConfig::setUseMrope"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11setUseMropeEb", "tensorrt_llm::runtime::ModelConfig::setUseMrope::useMrope"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23setUsePositionEmbeddingEb", "tensorrt_llm::runtime::ModelConfig::setUsePositionEmbedding"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23setUsePositionEmbeddingEb", "tensorrt_llm::runtime::ModelConfig::setUsePositionEmbedding::usePositionEmbedding"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseShapeInferenceEb", "tensorrt_llm::runtime::ModelConfig::setUseShapeInference"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseShapeInferenceEb", "tensorrt_llm::runtime::ModelConfig::setUseShapeInference::useShapeInference"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24setUseTokenTypeEmbeddingEb", "tensorrt_llm::runtime::ModelConfig::setUseTokenTypeEmbedding"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24setUseTokenTypeEmbeddingEb", "tensorrt_llm::runtime::ModelConfig::setUseTokenTypeEmbedding::useTokenTypeEmbedding"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig19skipCrossAttnBlocksEv", "tensorrt_llm::runtime::ModelConfig::skipCrossAttnBlocks"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig24supportsInflightBatchingEv", "tensorrt_llm::runtime::ModelConfig::supportsInflightBatching"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17useCrossAttentionEv", "tensorrt_llm::runtime::ModelConfig::useCrossAttention"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22useGemmAllReducePluginEb", "tensorrt_llm::runtime::ModelConfig::useGemmAllReducePlugin"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig22useGemmAllReducePluginEv", "tensorrt_llm::runtime::ModelConfig::useGemmAllReducePlugin"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22useGemmAllReducePluginEb", "tensorrt_llm::runtime::ModelConfig::useGemmAllReducePlugin::useGemmAllReducePlugin"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21useGptAttentionPluginEb", "tensorrt_llm::runtime::ModelConfig::useGptAttentionPlugin"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21useGptAttentionPluginEv", "tensorrt_llm::runtime::ModelConfig::useGptAttentionPlugin"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21useGptAttentionPluginEb", "tensorrt_llm::runtime::ModelConfig::useGptAttentionPlugin::useGptAttentionPlugin"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18useLanguageAdapterEv", "tensorrt_llm::runtime::ModelConfig::useLanguageAdapter"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13useLoraPluginEb", "tensorrt_llm::runtime::ModelConfig::useLoraPlugin"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13useLoraPluginEv", "tensorrt_llm::runtime::ModelConfig::useLoraPlugin"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13useLoraPluginEb", "tensorrt_llm::runtime::ModelConfig::useLoraPlugin::useLoraPlugin"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20useMambaConv1dPluginEb", "tensorrt_llm::runtime::ModelConfig::useMambaConv1dPlugin"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20useMambaConv1dPluginEv", "tensorrt_llm::runtime::ModelConfig::useMambaConv1dPlugin"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20useMambaConv1dPluginEb", "tensorrt_llm::runtime::ModelConfig::useMambaConv1dPlugin::useMambaConv1dPlugin"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig8useMropeEv", "tensorrt_llm::runtime::ModelConfig::useMrope"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14usePackedInputEb", "tensorrt_llm::runtime::ModelConfig::usePackedInput"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14usePackedInputEv", "tensorrt_llm::runtime::ModelConfig::usePackedInput"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14usePackedInputEb", "tensorrt_llm::runtime::ModelConfig::usePackedInput::inputPacked"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13usePagedStateEb", "tensorrt_llm::runtime::ModelConfig::usePagedState"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13usePagedStateEv", "tensorrt_llm::runtime::ModelConfig::usePagedState"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13usePagedStateEb", "tensorrt_llm::runtime::ModelConfig::usePagedState::pagedState"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20usePositionEmbeddingEv", "tensorrt_llm::runtime::ModelConfig::usePositionEmbedding"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15usePromptTuningEv", "tensorrt_llm::runtime::ModelConfig::usePromptTuning"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17useShapeInferenceEv", "tensorrt_llm::runtime::ModelConfig::useShapeInference"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21useTokenTypeEmbeddingEv", "tensorrt_llm::runtime::ModelConfig::useTokenTypeEmbedding"], [1, 1, 1, "_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE", "tensorrt_llm::runtime::PointerElementType"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE", "tensorrt_llm::runtime::PointerElementType::T"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParamsE", "tensorrt_llm::runtime::PromptTuningParams"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::PromptTuningParams::PromptTuningParams"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::PromptTuningParams::PromptTuningParams::embeddingTable"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::PromptTuningParams::PromptTuningParams::tasks"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::PromptTuningParams::PromptTuningParams::vocabSize"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams10SizeType32E", "tensorrt_llm::runtime::PromptTuningParams::SizeType32"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams9TensorPtrE", "tensorrt_llm::runtime::PromptTuningParams::TensorPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::batchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::numContextRequests"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::packedInput"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::reqBeamWidths"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::reqPromptLengths"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::tasksHost"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngineE", "tensorrt_llm::runtime::RawEngine"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type15AddressWithSizeE", "tensorrt_llm::runtime::RawEngine::AddressWithSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type8FilePathE", "tensorrt_llm::runtime::RawEngine::FilePath"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type10HostMemoryE", "tensorrt_llm::runtime::RawEngine::HostMemory"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineENSt10filesystem4pathE", "tensorrt_llm::runtime::RawEngine::RawEngine"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKN8nvinfer111IHostMemoryE", "tensorrt_llm::runtime::RawEngine::RawEngine"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKvNSt6size_tE", "tensorrt_llm::runtime::RawEngine::RawEngine"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKvNSt6size_tE", "tensorrt_llm::runtime::RawEngine::RawEngine::engineAddr"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKN8nvinfer111IHostMemoryE", "tensorrt_llm::runtime::RawEngine::RawEngine::engineBuffer"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineENSt10filesystem4pathE", "tensorrt_llm::runtime::RawEngine::RawEngine::enginePath"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKvNSt6size_tE", "tensorrt_llm::runtime::RawEngine::RawEngine::engineSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4TypeE", "tensorrt_llm::runtime::RawEngine::Type"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type15AddressWithSizeE", "tensorrt_llm::runtime::RawEngine::Type::AddressWithSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type8FilePathE", "tensorrt_llm::runtime::RawEngine::Type::FilePath"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type10HostMemoryE", "tensorrt_llm::runtime::RawEngine::Type::HostMemory"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine10getAddressEv", "tensorrt_llm::runtime::RawEngine::getAddress"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine13getHostMemoryEv", "tensorrt_llm::runtime::RawEngine::getHostMemory"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine23getManagedWeightsMapOptEv", "tensorrt_llm::runtime::RawEngine::getManagedWeightsMapOpt"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getPathEv", "tensorrt_llm::runtime::RawEngine::getPath"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine10getPathOptEv", "tensorrt_llm::runtime::RawEngine::getPathOpt"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getSizeEv", "tensorrt_llm::runtime::RawEngine::getSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getTypeEv", "tensorrt_llm::runtime::RawEngine::getType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEngineAddrE", "tensorrt_llm::runtime::RawEngine::mEngineAddr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine13mEngineBufferE", "tensorrt_llm::runtime::RawEngine::mEngineBuffer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEnginePathE", "tensorrt_llm::runtime::RawEngine::mEnginePath"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEngineSizeE", "tensorrt_llm::runtime::RawEngine::mEngineSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine18mManagedWeightsMapE", "tensorrt_llm::runtime::RawEngine::mManagedWeightsMap"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine5mTypeE", "tensorrt_llm::runtime::RawEngine::mType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine20setManagedWeightsMapENSt3mapINSt6stringEN12tensorrt_llm8executor6TensorEEE", "tensorrt_llm::runtime::RawEngine::setManagedWeightsMap"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine20setManagedWeightsMapENSt3mapINSt6stringEN12tensorrt_llm8executor6TensorEEE", "tensorrt_llm::runtime::RawEngine::setManagedWeightsMap::managedWeightsMap"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine7setPathENSt10filesystem4pathE", "tensorrt_llm::runtime::RawEngine::setPath"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine7setPathENSt10filesystem4pathE", "tensorrt_llm::runtime::RawEngine::setPath::enginePath"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11RequestTypeE", "tensorrt_llm::runtime::RequestType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11RequestType8kCONTEXTE", "tensorrt_llm::runtime::RequestType::kCONTEXT"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11RequestType11kGENERATIONE", "tensorrt_llm::runtime::RequestType::kGENERATION"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaultsE", "tensorrt_llm::runtime::RuntimeDefaults"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults15RuntimeDefaultsENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::RuntimeDefaults::RuntimeDefaults"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults15RuntimeDefaultsEv", "tensorrt_llm::runtime::RuntimeDefaults::RuntimeDefaults"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults15RuntimeDefaultsENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::RuntimeDefaults::RuntimeDefaults::maxAttentionWindowVec"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults15RuntimeDefaultsENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::RuntimeDefaults::RuntimeDefaults::sinkTokenLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults21maxAttentionWindowVecE", "tensorrt_llm::runtime::RuntimeDefaults::maxAttentionWindowVec"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults15sinkTokenLengthE", "tensorrt_llm::runtime::RuntimeDefaults::sinkTokenLength"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfigE", "tensorrt_llm::runtime::SamplingConfig"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE", "tensorrt_llm::runtime::SamplingConfig::FloatType"], [1, 1, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE", "tensorrt_llm::runtime::SamplingConfig::OptVec"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE", "tensorrt_llm::runtime::SamplingConfig::OptVec::T"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigE10SizeType32", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKN8executor14SamplingConfigERKNSt8optionalIN8executor25ExternalDraftTokensConfigEEE", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKNSt6vectorI14SamplingConfigEE", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigE10SizeType32", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig::beamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKNSt6vectorI14SamplingConfigEE", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig::configs"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKN8executor14SamplingConfigERKNSt8optionalIN8executor25ExternalDraftTokensConfigEEE", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig::externalDraftTokensConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKN8executor14SamplingConfigERKNSt8optionalIN8executor25ExternalDraftTokensConfigEEE", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig::samplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig23beamSearchDiversityRateE", "tensorrt_llm::runtime::SamplingConfig::beamSearchDiversityRate"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9beamWidthE", "tensorrt_llm::runtime::SamplingConfig::beamWidth"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14beamWidthArrayE", "tensorrt_llm::runtime::SamplingConfig::beamWidthArray"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig11cumLogProbsE", "tensorrt_llm::runtime::SamplingConfig::cumLogProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig24draftAcceptanceThresholdE", "tensorrt_llm::runtime::SamplingConfig::draftAcceptanceThreshold"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig13earlyStoppingE", "tensorrt_llm::runtime::SamplingConfig::earlyStopping"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig16frequencyPenaltyE", "tensorrt_llm::runtime::SamplingConfig::frequencyPenalty"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T", "tensorrt_llm::runtime::SamplingConfig::fuseValues"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T", "tensorrt_llm::runtime::SamplingConfig::fuseValues::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T", "tensorrt_llm::runtime::SamplingConfig::fuseValues::accessor"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T", "tensorrt_llm::runtime::SamplingConfig::fuseValues::configs"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T", "tensorrt_llm::runtime::SamplingConfig::fuseValues::defaultValue"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14SamplingConfig15getMaxBeamWidthEv", "tensorrt_llm::runtime::SamplingConfig::getMaxBeamWidth"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14SamplingConfig17getNumReturnBeamsEv", "tensorrt_llm::runtime::SamplingConfig::getNumReturnBeams"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig13lengthPenaltyE", "tensorrt_llm::runtime::SamplingConfig::lengthPenalty"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9minLengthE", "tensorrt_llm::runtime::SamplingConfig::minLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig4minPE", "tensorrt_llm::runtime::SamplingConfig::minP"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17noRepeatNgramSizeE", "tensorrt_llm::runtime::SamplingConfig::noRepeatNgramSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17normalizeLogProbsE", "tensorrt_llm::runtime::SamplingConfig::normalizeLogProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig18numReturnSequencesE", "tensorrt_llm::runtime::SamplingConfig::numReturnSequences"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14SamplingConfigeqERK14SamplingConfig", "tensorrt_llm::runtime::SamplingConfig::operator=="], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime14SamplingConfigeqERK14SamplingConfig", "tensorrt_llm::runtime::SamplingConfig::operator==::other"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig19originalTemperatureE", "tensorrt_llm::runtime::SamplingConfig::originalTemperature"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14outputLogProbsE", "tensorrt_llm::runtime::SamplingConfig::outputLogProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig15presencePenaltyE", "tensorrt_llm::runtime::SamplingConfig::presencePenalty"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig10randomSeedE", "tensorrt_llm::runtime::SamplingConfig::randomSeed"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17repetitionPenaltyE", "tensorrt_llm::runtime::SamplingConfig::repetitionPenalty"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig11temperatureE", "tensorrt_llm::runtime::SamplingConfig::temperature"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topKE", "tensorrt_llm::runtime::SamplingConfig::topK"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig15topKMedusaHeadsE", "tensorrt_llm::runtime::SamplingConfig::topKMedusaHeads"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topPE", "tensorrt_llm::runtime::SamplingConfig::topP"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9topPDecayE", "tensorrt_llm::runtime::SamplingConfig::topPDecay"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig7topPMinE", "tensorrt_llm::runtime::SamplingConfig::topPMin"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig12topPResetIdsE", "tensorrt_llm::runtime::SamplingConfig::topPResetIds"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig16useDefaultValuesEbRK6OptVecI1TE1T", "tensorrt_llm::runtime::SamplingConfig::useDefaultValues"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig16useDefaultValuesEbRK6OptVecI1TE1T", "tensorrt_llm::runtime::SamplingConfig::useDefaultValues::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig16useDefaultValuesEbRK6OptVecI1TE1T", "tensorrt_llm::runtime::SamplingConfig::useDefaultValues::defaultValue"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig16useDefaultValuesEbRK6OptVecI1TE1T", "tensorrt_llm::runtime::SamplingConfig::useDefaultValues::vec"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig8validateEv", "tensorrt_llm::runtime::SamplingConfig::validate"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec::max"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec::min"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec::name"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec::vec"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10SizeType32E", "tensorrt_llm::runtime::SizeType32"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10SizeType64E", "tensorrt_llm::runtime::SizeType64"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingModeE", "tensorrt_llm::runtime::SpeculativeDecodingMode"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode19DraftTokensExternalEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::DraftTokensExternal"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode5EagleEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::Eagle"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode19ExplicitDraftTokensEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::ExplicitDraftTokens"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode17LookaheadDecodingEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::LookaheadDecoding"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode6MedusaEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::Medusa"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode4NoneEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::None"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode23SpeculativeDecodingModeE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::SpeculativeDecodingMode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode23SpeculativeDecodingModeE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::SpeculativeDecodingMode::state"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode14UnderlyingTypeE", "tensorrt_llm::runtime::SpeculativeDecodingMode::UnderlyingType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9allBitSetE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::allBitSet"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9allBitSetE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::allBitSet::bits"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9anyBitSetE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::anyBitSet"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9anyBitSetE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::anyBitSet::bits"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode14hasDraftLogitsEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::hasDraftLogits"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21isDraftTokensExternalEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::isDraftTokensExternal"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode7isEagleEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::isEagle"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21isExplicitDraftTokensEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::isExplicitDraftTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19isLookaheadDecodingEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::isLookaheadDecoding"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode8isMedusaEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::isMedusa"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode6isNoneEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::isNone"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode20kDraftTokensExternalE", "tensorrt_llm::runtime::SpeculativeDecodingMode::kDraftTokensExternal"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode6kEagleE", "tensorrt_llm::runtime::SpeculativeDecodingMode::kEagle"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode20kExplicitDraftTokensE", "tensorrt_llm::runtime::SpeculativeDecodingMode::kExplicitDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode18kLookaheadDecodingE", "tensorrt_llm::runtime::SpeculativeDecodingMode::kLookaheadDecoding"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode7kMedusaE", "tensorrt_llm::runtime::SpeculativeDecodingMode::kMedusa"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode5kNoneE", "tensorrt_llm::runtime::SpeculativeDecodingMode::kNone"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode6mStateE", "tensorrt_llm::runtime::SpeculativeDecodingMode::mState"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode20needsDecoderPrologueEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::needsDecoderPrologue"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode18needsKVCacheRewindEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::needsKVCacheRewind"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingModeeqERK23SpeculativeDecodingMode", "tensorrt_llm::runtime::SpeculativeDecodingMode::operator=="], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingModeeqERK23SpeculativeDecodingMode", "tensorrt_llm::runtime::SpeculativeDecodingMode::operator==::other"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19predictsDraftTokensEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::predictsDraftTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21requiresAttentionMaskEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::requiresAttentionMask"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode18updatesPositionIdsEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::updatesPositionIds"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19variableDraftLengthEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::variableDraftLength"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleE", "tensorrt_llm::runtime::SpeculativeDecodingModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleERK25SpeculativeDecodingModule", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule::maxDecodingDraftTokens"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule::maxDraftPathLen"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule::maxNumPaths"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleERK25SpeculativeDecodingModule", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule::o"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule21computeNumPackedMasksEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::computeNumPackedMasks"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule25getMaxDecodingDraftTokensEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getMaxDecodingDraftTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule20getMaxDecodingTokensEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getMaxDecodingTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule18getMaxDraftPathLenEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getMaxDraftPathLen"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule14getMaxNumPathsEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getMaxNumPaths"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule13getMaxPathLenEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getMaxPathLen"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule17getNumPackedMasksEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getNumPackedMasks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule23mMaxDecodingDraftTokensE", "tensorrt_llm::runtime::SpeculativeDecodingModule::mMaxDecodingDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule16mMaxDraftPathLenE", "tensorrt_llm::runtime::SpeculativeDecodingModule::mMaxDraftPathLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule18mMaxNumPackedMasksE", "tensorrt_llm::runtime::SpeculativeDecodingModule::mMaxNumPackedMasks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule12mMaxNumPathsE", "tensorrt_llm::runtime::SpeculativeDecodingModule::mMaxNumPaths"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleaSERK25SpeculativeDecodingModule", "tensorrt_llm::runtime::SpeculativeDecodingModule::operator="], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleaSERK25SpeculativeDecodingModule", "tensorrt_llm::runtime::SpeculativeDecodingModule::operator=::o"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule18setMaxDraftPathLenE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxDraftPathLen"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule18setMaxDraftPathLenE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxDraftPathLen::maxDraftPathLen"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule17setMaxDraftTokensE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxDraftTokens"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule17setMaxDraftTokensE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxDraftTokens::maxDraftTokens"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule14setMaxNumPathsE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxNumPaths"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule14setMaxNumPathsE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxNumPaths::maxNumPaths"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleD0Ev", "tensorrt_llm::runtime::SpeculativeDecodingModule::~SpeculativeDecodingModule"], [1, 1, 1, "_CPPv4I0EN12tensorrt_llm7runtime12StringPtrMapE", "tensorrt_llm::runtime::StringPtrMap"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime12StringPtrMapE", "tensorrt_llm::runtime::StringPtrMap::T"], [1, 2, 1, "_CPPv4I0_bEN12tensorrt_llm7runtime11TRTDataTypeE", "tensorrt_llm::runtime::TRTDataType"], [1, 8, 1, "_CPPv4I0_bEN12tensorrt_llm7runtime11TRTDataTypeE", "tensorrt_llm::runtime::TRTDataType::T"], [1, 2, 1, "_CPPv4I0EN12tensorrt_llm7runtime11TRTDataTypeIP1TEE", "tensorrt_llm::runtime::TRTDataType<T*>"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime11TRTDataTypeIP1TEE", "tensorrt_llm::runtime::TRTDataType<T*>::T"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE15kUnderlyingTypeE", "tensorrt_llm::runtime::TRTDataType<T*>::kUnderlyingType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE5valueE", "tensorrt_llm::runtime::TRTDataType<T*>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIbEE", "tensorrt_llm::runtime::TRTDataType<bool>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIbE5valueE", "tensorrt_llm::runtime::TRTDataType<bool>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIfEE", "tensorrt_llm::runtime::TRTDataType<float>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIfE5valueE", "tensorrt_llm::runtime::TRTDataType<float>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeI4halfEE", "tensorrt_llm::runtime::TRTDataType<half>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeI4halfE5valueE", "tensorrt_llm::runtime::TRTDataType<half>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIN7kernels13FinishedStateEEE", "tensorrt_llm::runtime::TRTDataType<kernels::FinishedState>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIN7kernels13FinishedStateEE5valueE", "tensorrt_llm::runtime::TRTDataType<kernels::FinishedState>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIN7kernels12KVCacheIndexEEE", "tensorrt_llm::runtime::TRTDataType<kernels::KVCacheIndex>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIN7kernels12KVCacheIndexEE5valueE", "tensorrt_llm::runtime::TRTDataType<kernels::KVCacheIndex>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIN7runtime11RequestTypeEEE", "tensorrt_llm::runtime::TRTDataType<runtime::RequestType>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIN7runtime11RequestTypeEE5valueE", "tensorrt_llm::runtime::TRTDataType<runtime::RequestType>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEEE", "tensorrt_llm::runtime::TRTDataType<std::int32_t>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEE5valueE", "tensorrt_llm::runtime::TRTDataType<std::int32_t>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEEE", "tensorrt_llm::runtime::TRTDataType<std::int64_t>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEE5valueE", "tensorrt_llm::runtime::TRTDataType<std::int64_t>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEEE", "tensorrt_llm::runtime::TRTDataType<std::int8_t>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEE5valueE", "tensorrt_llm::runtime::TRTDataType<std::int8_t>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEEE", "tensorrt_llm::runtime::TRTDataType<std::uint32_t>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEE5valueE", "tensorrt_llm::runtime::TRTDataType<std::uint32_t>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEEE", "tensorrt_llm::runtime::TRTDataType<std::uint64_t>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEE5valueE", "tensorrt_llm::runtime::TRTDataType<std::uint64_t>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEEE", "tensorrt_llm::runtime::TRTDataType<std::uint8_t>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEE5valueE", "tensorrt_llm::runtime::TRTDataType<std::uint8_t>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIPvEE", "tensorrt_llm::runtime::TRTDataType<void*>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIPvE5valueE", "tensorrt_llm::runtime::TRTDataType<void*>::value"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLoggerE", "tensorrt_llm::runtime::TllmLogger"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger8getLevelEv", "tensorrt_llm::runtime::TllmLogger::getLevel"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger3logE8SeverityPKN8nvinfer19AsciiCharE", "tensorrt_llm::runtime::TllmLogger::log"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger3logE8SeverityPKN8nvinfer19AsciiCharE", "tensorrt_llm::runtime::TllmLogger::log::msg"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger3logE8SeverityPKN8nvinfer19AsciiCharE", "tensorrt_llm::runtime::TllmLogger::log::severity"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger8setLevelE8Severity", "tensorrt_llm::runtime::TllmLogger::setLevel"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger8setLevelE8Severity", "tensorrt_llm::runtime::TllmLogger::setLevel::level"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime16TokenExtraIdTypeE", "tensorrt_llm::runtime::TokenExtraIdType"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime11TokenIdTypeE", "tensorrt_llm::runtime::TokenIdType"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime11UniqueTokenE", "tensorrt_llm::runtime::UniqueToken"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11UniqueTokeneqERK11UniqueToken", "tensorrt_llm::runtime::UniqueToken::operator=="], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11UniqueTokeneqERK11UniqueToken", "tensorrt_llm::runtime::UniqueToken::operator==::other"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11UniqueToken12tokenExtraIdE", "tensorrt_llm::runtime::UniqueToken::tokenExtraId"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11UniqueToken7tokenIdE", "tensorrt_llm::runtime::UniqueToken::tokenId"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime16VecTokenExtraIdsE", "tensorrt_llm::runtime::VecTokenExtraIds"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime15VecUniqueTokensE", "tensorrt_llm::runtime::VecUniqueTokens"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfigE", "tensorrt_llm::runtime::WorldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::WorldConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::WorldConfig::contextParallelism"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::WorldConfig::deviceIds"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::WorldConfig::enableAttentionDP"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::WorldConfig::gpusPerNode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::WorldConfig::pipelineParallelism"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::WorldConfig::rank"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::WorldConfig::tensorParallelism"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig17enableAttentionDPEv", "tensorrt_llm::runtime::WorldConfig::enableAttentionDP"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig23getContextParallelGroupEv", "tensorrt_llm::runtime::WorldConfig::getContextParallelGroup"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getContextParallelRankEv", "tensorrt_llm::runtime::WorldConfig::getContextParallelRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig21getContextParallelismEv", "tensorrt_llm::runtime::WorldConfig::getContextParallelism"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig9getDeviceEv", "tensorrt_llm::runtime::WorldConfig::getDevice"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getDeviceOfE10SizeType32", "tensorrt_llm::runtime::WorldConfig::getDeviceOf"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getDeviceOfE10SizeType32", "tensorrt_llm::runtime::WorldConfig::getDeviceOf::rank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig15getGpusPerGroupEv", "tensorrt_llm::runtime::WorldConfig::getGpusPerGroup"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig14getGpusPerNodeEv", "tensorrt_llm::runtime::WorldConfig::getGpusPerNode"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getLastRankEv", "tensorrt_llm::runtime::WorldConfig::getLastRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig12getLocalRankEv", "tensorrt_llm::runtime::WorldConfig::getLocalRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getNodeRankEv", "tensorrt_llm::runtime::WorldConfig::getNodeRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig13getNodeRankOfE10SizeType32", "tensorrt_llm::runtime::WorldConfig::getNodeRankOf"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig13getNodeRankOfE10SizeType32", "tensorrt_llm::runtime::WorldConfig::getNodeRankOf::rank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig24getPipelineParallelGroupEv", "tensorrt_llm::runtime::WorldConfig::getPipelineParallelGroup"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig23getPipelineParallelRankEv", "tensorrt_llm::runtime::WorldConfig::getPipelineParallelRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getPipelineParallelismEv", "tensorrt_llm::runtime::WorldConfig::getPipelineParallelism"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getRankEv", "tensorrt_llm::runtime::WorldConfig::getRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getSizeEv", "tensorrt_llm::runtime::WorldConfig::getSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getTensorParallelGroupEv", "tensorrt_llm::runtime::WorldConfig::getTensorParallelGroup"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig21getTensorParallelRankEv", "tensorrt_llm::runtime::WorldConfig::getTensorParallelRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig20getTensorParallelismEv", "tensorrt_llm::runtime::WorldConfig::getTensorParallelism"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig17isContextParallelEv", "tensorrt_llm::runtime::WorldConfig::isContextParallel"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig26isFirstContextParallelRankEv", "tensorrt_llm::runtime::WorldConfig::isFirstContextParallelRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig27isFirstPipelineParallelRankEv", "tensorrt_llm::runtime::WorldConfig::isFirstPipelineParallelRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig25isFirstTensorParallelRankEv", "tensorrt_llm::runtime::WorldConfig::isFirstTensorParallelRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig26isLastPipelineParallelRankEv", "tensorrt_llm::runtime::WorldConfig::isLastPipelineParallelRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig18isPipelineParallelEv", "tensorrt_llm::runtime::WorldConfig::isPipelineParallel"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig16isTensorParallelEv", "tensorrt_llm::runtime::WorldConfig::isTensorParallel"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig19kDefaultGpusPerNodeE", "tensorrt_llm::runtime::WorldConfig::kDefaultGpusPerNode"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig19mContextParallelismE", "tensorrt_llm::runtime::WorldConfig::mContextParallelism"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig10mDeviceIdsE", "tensorrt_llm::runtime::WorldConfig::mDeviceIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig18mEnableAttentionDPE", "tensorrt_llm::runtime::WorldConfig::mEnableAttentionDP"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig12mGpusPerNodeE", "tensorrt_llm::runtime::WorldConfig::mGpusPerNode"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig20mPipelineParallelismE", "tensorrt_llm::runtime::WorldConfig::mPipelineParallelism"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig5mRankE", "tensorrt_llm::runtime::WorldConfig::mRank"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig18mTensorParallelismE", "tensorrt_llm::runtime::WorldConfig::mTensorParallelism"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::mpi"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::mpi::contextParallelism"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::mpi::deviceIds"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::mpi::enableAttentionDP"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::mpi::gpusPerNode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::mpi::pipelineParallelism"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::mpi::tensorParallelism"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig14validMpiConfigEv", "tensorrt_llm::runtime::WorldConfig::validMpiConfig"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEP1TR7IBuffer", "tensorrt_llm::runtime::bufferCast"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEPK1TRK7IBuffer", "tensorrt_llm::runtime::bufferCast"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEP1TR7IBuffer", "tensorrt_llm::runtime::bufferCast::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEPK1TRK7IBuffer", "tensorrt_llm::runtime::bufferCast::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEP1TR7IBuffer", "tensorrt_llm::runtime::bufferCast::buffer"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEPK1TRK7IBuffer", "tensorrt_llm::runtime::bufferCast::buffer"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7IBuffer9SharedPtrE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7ITensor9SharedPtrE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7IBuffer9SharedPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7ITensor9SharedPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7IBuffer14SharedConstPtrE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7ITensor14SharedConstPtrE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7IBuffer14SharedConstPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7ITensor14SharedConstPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7IBuffer9SharedPtrE", "tensorrt_llm::runtime::bufferCastOrNull::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7ITensor9SharedPtrE", "tensorrt_llm::runtime::bufferCastOrNull::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7IBuffer9SharedPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7ITensor9SharedPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7IBuffer14SharedConstPtrE", "tensorrt_llm::runtime::bufferCastOrNull::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7ITensor14SharedConstPtrE", "tensorrt_llm::runtime::bufferCastOrNull::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7IBuffer14SharedConstPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7ITensor14SharedConstPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7IBuffer9SharedPtrE", "tensorrt_llm::runtime::bufferCastOrNull::bufferPtr"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7IBuffer14SharedConstPtrE", "tensorrt_llm::runtime::bufferCastOrNull::bufferPtr"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7IBuffer9SharedPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::optionalBufferPtr"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7IBuffer14SharedConstPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::optionalBufferPtr"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7ITensor9SharedPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::optionalTensorPtr"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7ITensor14SharedConstPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::optionalTensorPtr"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7ITensor9SharedPtrE", "tensorrt_llm::runtime::bufferCastOrNull::tensorPtr"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7ITensor14SharedConstPtrE", "tensorrt_llm::runtime::bufferCastOrNull::tensorPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13canAccessPeerERK11WorldConfig", "tensorrt_llm::runtime::canAccessPeer"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13canAccessPeerERK11WorldConfig", "tensorrt_llm::runtime::canAccessPeer::worldConfig"], [1, 3, 1, "_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE", "tensorrt_llm::runtime::constPointerCast"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERKNSt10shared_ptrI1TEE", "tensorrt_llm::runtime::constPointerCast"], [1, 8, 1, "_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE", "tensorrt_llm::runtime::constPointerCast::D"], [1, 8, 1, "_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE", "tensorrt_llm::runtime::constPointerCast::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERKNSt10shared_ptrI1TEE", "tensorrt_llm::runtime::constPointerCast::T"], [1, 4, 1, "_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE", "tensorrt_llm::runtime::constPointerCast::ptr"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERKNSt10shared_ptrI1TEE", "tensorrt_llm::runtime::constPointerCast::ptr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7decoderE", "tensorrt_llm::runtime::decoder"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7decoderE", "tensorrt_llm::runtime::decoder"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffersE", "tensorrt_llm::runtime::decoder::BeamSearchBuffers"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers17BeamSearchBuffersERK13BufferManager", "tensorrt_llm::runtime::decoder::BeamSearchBuffers::BeamSearchBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers17BeamSearchBuffersERK13BufferManager", "tensorrt_llm::runtime::decoder::BeamSearchBuffers::BeamSearchBuffers::bufferManager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers15mCumLogProbsTmpE", "tensorrt_llm::runtime::decoder::BeamSearchBuffers::mCumLogProbsTmp"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers7mNumSMsE", "tensorrt_llm::runtime::decoder::BeamSearchBuffers::mNumSMs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers21mOutputBeamHypothesesE", "tensorrt_llm::runtime::decoder::BeamSearchBuffers::mOutputBeamHypotheses"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers7reshapeE10SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::BeamSearchBuffers::reshape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers7reshapeE10SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::BeamSearchBuffers::reshape::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers7reshapeE10SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::BeamSearchBuffers::reshape::maxSequenceLength"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderStateE", "tensorrt_llm::runtime::decoder::DecoderState"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState12DecoderStateEv", "tensorrt_llm::runtime::decoder::DecoderState::DecoderState"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState16DecodingInputPtrE", "tensorrt_llm::runtime::decoder::DecoderState::DecodingInputPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState17DecodingOutputPtrE", "tensorrt_llm::runtime::decoder::DecoderState::DecodingOutputPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState13LlmRequestPtrE", "tensorrt_llm::runtime::decoder::DecoderState::LlmRequestPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState13RequestVectorE", "tensorrt_llm::runtime::decoder::DecoderState::RequestVector"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState9TensorPtrE", "tensorrt_llm::runtime::decoder::DecoderState::TensorPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState16disableLookaheadERK13RequestVector", "tensorrt_llm::runtime::decoder::DecoderState::disableLookahead"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState16disableLookaheadERK13RequestVector", "tensorrt_llm::runtime::decoder::DecoderState::disableLookahead::genRequests"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState24getAcceptedLengthsCumSumEv", "tensorrt_llm::runtime::decoder::DecoderState::getAcceptedLengthsCumSum"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState22getAcceptedPackedPathsEv", "tensorrt_llm::runtime::decoder::DecoderState::getAcceptedPackedPaths"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState15getAllNewTokensEv", "tensorrt_llm::runtime::decoder::DecoderState::getAllNewTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState20getBeamSearchBuffersEv", "tensorrt_llm::runtime::decoder::DecoderState::getBeamSearchBuffers"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState24getCacheIndirectionInputEv", "tensorrt_llm::runtime::decoder::DecoderState::getCacheIndirectionInput"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState25getCacheIndirectionOutputEv", "tensorrt_llm::runtime::decoder::DecoderState::getCacheIndirectionOutput"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getCumLogProbsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getCumLogProbs"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getCumLogProbsEv", "tensorrt_llm::runtime::decoder::DecoderState::getCumLogProbs"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getCumLogProbsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getCumLogProbs::batchIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState15getEagleBuffersEv", "tensorrt_llm::runtime::decoder::DecoderState::getEagleBuffers"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState29getExplicitDraftTokensBuffersEv", "tensorrt_llm::runtime::decoder::DecoderState::getExplicitDraftTokensBuffers"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState16getFinishReasonsEv", "tensorrt_llm::runtime::decoder::DecoderState::getFinishReasons"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState16getFinishedStepsEv", "tensorrt_llm::runtime::decoder::DecoderState::getFinishedSteps"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getFinishedSumEv", "tensorrt_llm::runtime::decoder::DecoderState::getFinishedSum"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getGatheredIdsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getGatheredIds"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getGatheredIdsEv", "tensorrt_llm::runtime::decoder::DecoderState::getGatheredIds"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getGatheredIdsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getGatheredIds::batchIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getGenerationStepsEv", "tensorrt_llm::runtime::decoder::DecoderState::getGenerationSteps"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState6getIdsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getIds"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState6getIdsEv", "tensorrt_llm::runtime::decoder::DecoderState::getIds"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState6getIdsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getIds::batchIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState21getJointDecodingInputEv", "tensorrt_llm::runtime::decoder::DecoderState::getJointDecodingInput"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState22getJointDecodingOutputEv", "tensorrt_llm::runtime::decoder::DecoderState::getJointDecodingOutput"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState11getLogProbsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getLogProbs"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState11getLogProbsEv", "tensorrt_llm::runtime::decoder::DecoderState::getLogProbs"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState11getLogProbsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getLogProbs::batchIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState19getLookaheadBuffersEv", "tensorrt_llm::runtime::decoder::DecoderState::getLookaheadBuffers"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState15getMaxBatchSizeEv", "tensorrt_llm::runtime::decoder::DecoderState::getMaxBatchSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState15getMaxBeamWidthEv", "tensorrt_llm::runtime::decoder::DecoderState::getMaxBeamWidth"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState27getMaxDecodingDecoderTokensEv", "tensorrt_llm::runtime::decoder::DecoderState::getMaxDecodingDecoderTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getMaxDecodingEngineTokensEv", "tensorrt_llm::runtime::decoder::DecoderState::getMaxDecodingEngineTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState20getMaxSequenceLengthEv", "tensorrt_llm::runtime::decoder::DecoderState::getMaxSequenceLength"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getNextDraftTokensEv", "tensorrt_llm::runtime::decoder::DecoderState::getNextDraftTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState25getNextDraftTokensLengthsEv", "tensorrt_llm::runtime::decoder::DecoderState::getNextDraftTokensLengths"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getNumDecodingEngineTokensE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getNumDecodingEngineTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getNumDecodingEngineTokensEv", "tensorrt_llm::runtime::decoder::DecoderState::getNumDecodingEngineTokens"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getNumDecodingEngineTokensE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getNumDecodingEngineTokens::batchIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState12getParentIdsEv", "tensorrt_llm::runtime::decoder::DecoderState::getParentIds"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState25getPrevDraftTokensLengthsEv", "tensorrt_llm::runtime::decoder::DecoderState::getPrevDraftTokensLengths"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getSequenceLengthsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getSequenceLengths"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getSequenceLengthsEv", "tensorrt_llm::runtime::decoder::DecoderState::getSequenceLengths"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getSequenceLengthsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getSequenceLengths::batchIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getSpeculativeDecodingModeEv", "tensorrt_llm::runtime::decoder::DecoderState::getSpeculativeDecodingMode"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState18mBeamSearchBuffersE", "tensorrt_llm::runtime::decoder::DecoderState::mBeamSearchBuffers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14mFinishedStepsE", "tensorrt_llm::runtime::decoder::DecoderState::mFinishedSteps"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState19mJointDecodingInputE", "tensorrt_llm::runtime::decoder::DecoderState::mJointDecodingInput"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState20mJointDecodingOutputE", "tensorrt_llm::runtime::decoder::DecoderState::mJointDecodingOutput"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState13mMaxBatchSizeE", "tensorrt_llm::runtime::decoder::DecoderState::mMaxBatchSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState13mMaxBeamWidthE", "tensorrt_llm::runtime::decoder::DecoderState::mMaxBeamWidth"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState25mMaxDecodingDecoderTokensE", "tensorrt_llm::runtime::decoder::DecoderState::mMaxDecodingDecoderTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24mMaxDecodingEngineTokensE", "tensorrt_llm::runtime::decoder::DecoderState::mMaxDecodingEngineTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState18mMaxSequenceLengthE", "tensorrt_llm::runtime::decoder::DecoderState::mMaxSequenceLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24mNumDecodingEngineTokensE", "tensorrt_llm::runtime::decoder::DecoderState::mNumDecodingEngineTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24mSpeculativeDecodingModeE", "tensorrt_llm::runtime::decoder::DecoderState::mSpeculativeDecodingMode"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers::maxAttentionWindow"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers::maxSequenceLength"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers::sinkTokenLength"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers::worldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState30reshapeCacheIndirectionBuffersE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::reshapeCacheIndirectionBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState30reshapeCacheIndirectionBuffersE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::reshapeCacheIndirectionBuffers::maxAttentionWindow"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState30reshapeCacheIndirectionBuffersE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::reshapeCacheIndirectionBuffers::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState30reshapeCacheIndirectionBuffersE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::reshapeCacheIndirectionBuffers::maxBeamWidth"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState33reshapeSpeculativeDecodingBuffersERK23SpeculativeDecodingMode10SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeSpeculativeDecodingBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState33reshapeSpeculativeDecodingBuffersERK23SpeculativeDecodingMode10SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeSpeculativeDecodingBuffers::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState33reshapeSpeculativeDecodingBuffersERK23SpeculativeDecodingMode10SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeSpeculativeDecodingBuffers::maxTokensPerEngineStep"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState33reshapeSpeculativeDecodingBuffersERK23SpeculativeDecodingMode10SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeSpeculativeDecodingBuffers::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState33reshapeSpeculativeDecodingBuffersERK23SpeculativeDecodingMode10SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeSpeculativeDecodingBuffers::speculativeDecodingMode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState33reshapeSpeculativeDecodingBuffersERK23SpeculativeDecodingMode10SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeSpeculativeDecodingBuffers::worldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState18setGenerationStepsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::runtime::decoder::DecoderState::setGenerationSteps"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState18setGenerationStepsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::runtime::decoder::DecoderState::setGenerationSteps::generationSteps"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState26setNumDecodingEngineTokensE10SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::setNumDecodingEngineTokens"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState26setNumDecodingEngineTokensE10SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::setNumDecodingEngineTokens::batchIdx"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState26setNumDecodingEngineTokensE10SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::setNumDecodingEngineTokens::numTokens"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::dtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::maxAttentionWindow"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::maxSequenceLength"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::sinkTokenLength"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::worldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState12setupBuffersEN8nvinfer18DataTypeERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState12setupBuffersEN8nvinfer18DataTypeERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupBuffers::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState12setupBuffersEN8nvinfer18DataTypeERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupBuffers::dtype"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState21setupCacheIndirectionE10SizeType3210SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupCacheIndirection"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState21setupCacheIndirectionE10SizeType3210SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupCacheIndirection::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState21setupCacheIndirectionE10SizeType3210SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupCacheIndirection::maxAttentionWindow"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState21setupCacheIndirectionE10SizeType3210SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupCacheIndirection::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState21setupCacheIndirectionE10SizeType3210SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupCacheIndirection::maxBeamWidth"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState28setupCacheIndirectionBuffersERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupCacheIndirectionBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState28setupCacheIndirectionBuffersERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupCacheIndirectionBuffers::bufferManager"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24setupSpeculativeDecodingERK23SpeculativeDecodingMode10SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecoding"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24setupSpeculativeDecodingERK23SpeculativeDecodingMode10SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecoding::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24setupSpeculativeDecodingERK23SpeculativeDecodingMode10SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecoding::dtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24setupSpeculativeDecodingERK23SpeculativeDecodingMode10SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecoding::maxTokensPerEngineStep"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24setupSpeculativeDecodingERK23SpeculativeDecodingMode10SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecoding::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24setupSpeculativeDecodingERK23SpeculativeDecodingMode10SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecoding::speculativeDecodingMode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24setupSpeculativeDecodingERK23SpeculativeDecodingMode10SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecoding::worldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState31setupSpeculativeDecodingBuffersE23SpeculativeDecodingModeN8nvinfer18DataTypeERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecodingBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState31setupSpeculativeDecodingBuffersE23SpeculativeDecodingModeN8nvinfer18DataTypeERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecodingBuffers::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState31setupSpeculativeDecodingBuffersE23SpeculativeDecodingModeN8nvinfer18DataTypeERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecodingBuffers::dtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState31setupSpeculativeDecodingBuffersE23SpeculativeDecodingModeN8nvinfer18DataTypeERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecodingBuffers::speculativeDecodingMode"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batchE", "tensorrt_llm::runtime::decoder_batch"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batchE", "tensorrt_llm::runtime::decoder_batch"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5InputE", "tensorrt_llm::runtime::decoder_batch::Input"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI14TensorConstPtrEE", "tensorrt_llm::runtime::decoder_batch::Input::Input"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorINSt6vectorI14TensorConstPtrEEEE10SizeType32", "tensorrt_llm::runtime::decoder_batch::Input::Input"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI14TensorConstPtrEE", "tensorrt_llm::runtime::decoder_batch::Input::Input::logits"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorINSt6vectorI14TensorConstPtrEEEE10SizeType32", "tensorrt_llm::runtime::decoder_batch::Input::Input::logits"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorINSt6vectorI14TensorConstPtrEEEE10SizeType32", "tensorrt_llm::runtime::decoder_batch::Input::Input::maxDecoderSteps"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input14TensorConstPtrE", "tensorrt_llm::runtime::decoder_batch::Input::TensorConstPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input9TensorPtrE", "tensorrt_llm::runtime::decoder_batch::Input::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input10batchSlotsE", "tensorrt_llm::runtime::decoder_batch::Input::batchSlots"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input6logitsE", "tensorrt_llm::runtime::decoder_batch::Input::logits"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input15maxDecoderStepsE", "tensorrt_llm::runtime::decoder_batch::Input::maxDecoderSteps"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7RequestE", "tensorrt_llm::runtime::decoder_batch::Request"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9BufferPtrE", "tensorrt_llm::runtime::decoder_batch::Request::BufferPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14TensorConstPtr10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::decoder_batch::Request::Request"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14TensorConstPtr10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::decoder_batch::Request::Request::endId"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14TensorConstPtr10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::decoder_batch::Request::Request::ids"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14TensorConstPtr10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::decoder_batch::Request::Request::inputLen"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14TensorConstPtr10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::decoder_batch::Request::Request::maxNewTokens"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request14TensorConstPtrE", "tensorrt_llm::runtime::decoder_batch::Request::TensorConstPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9TensorPtrE", "tensorrt_llm::runtime::decoder_batch::Request::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request12badWordsListE", "tensorrt_llm::runtime::decoder_batch::Request::badWordsList"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11draftLogitsE", "tensorrt_llm::runtime::decoder_batch::Request::draftLogits"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11draftTokensE", "tensorrt_llm::runtime::decoder_batch::Request::draftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11eagleConfigE", "tensorrt_llm::runtime::decoder_batch::Request::eagleConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13embeddingBiasE", "tensorrt_llm::runtime::decoder_batch::Request::embeddingBias"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request5endIdE", "tensorrt_llm::runtime::decoder_batch::Request::endId"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request28generatedTokensPerEngineStepE", "tensorrt_llm::runtime::decoder_batch::Request::generatedTokensPerEngineStep"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request3idsE", "tensorrt_llm::runtime::decoder_batch::Request::ids"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request8inputLenE", "tensorrt_llm::runtime::decoder_batch::Request::inputLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request22lookaheadRuntimeConfigE", "tensorrt_llm::runtime::decoder_batch::Request::lookaheadRuntimeConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request12maxNewTokensE", "tensorrt_llm::runtime::decoder_batch::Request::maxNewTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11medusaPathsE", "tensorrt_llm::runtime::decoder_batch::Request::medusaPaths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13medusaTreeIdsE", "tensorrt_llm::runtime::decoder_batch::Request::medusaTreeIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13stopWordsListE", "tensorrt_llm::runtime::decoder_batch::Request::stopWordsList"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20getDefaultBatchSlotsEN7runtime10SizeType32E", "tensorrt_llm::runtime::getDefaultBatchSlots"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20getDefaultBatchSlotsEN7runtime10SizeType32E", "tensorrt_llm::runtime::getDefaultBatchSlots::batchSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime15ipcNvlsAllocateE6size_tNSt3setIiEE", "tensorrt_llm::runtime::ipcNvlsAllocate"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime15ipcNvlsAllocateE6size_tNSt3setIiEE", "tensorrt_llm::runtime::ipcNvlsAllocate::ranks"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime15ipcNvlsAllocateE6size_tNSt3setIiEE", "tensorrt_llm::runtime::ipcNvlsAllocate::size"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ipcNvlsFreeEP13IpcNvlsHandle", "tensorrt_llm::runtime::ipcNvlsFree"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ipcNvlsFreeEP13IpcNvlsHandle", "tensorrt_llm::runtime::ipcNvlsFree::handle"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime16ipcNvlsSupportedEv", "tensorrt_llm::runtime::ipcNvlsSupported"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20lamportInitializeAllEPvPvPv6size_t", "tensorrt_llm::runtime::lamportInitializeAll"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20lamportInitializeAllEPvPvPv6size_t", "tensorrt_llm::runtime::lamportInitializeAll::buffer_0"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20lamportInitializeAllEPvPvPv6size_t", "tensorrt_llm::runtime::lamportInitializeAll::buffer_1"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20lamportInitializeAllEPvPvPv6size_t", "tensorrt_llm::runtime::lamportInitializeAll::buffer_2"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20lamportInitializeAllEPvPvPv6size_t", "tensorrt_llm::runtime::lamportInitializeAll::size"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK10LoraModule", "tensorrt_llm::runtime::operator<<"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK26LoraCachePageManagerConfig", "tensorrt_llm::runtime::operator<<"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7IBuffer", "tensorrt_llm::runtime::operator<<"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7ITensor", "tensorrt_llm::runtime::operator<<"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN7ITensor5ShapeE", "tensorrt_llm::runtime::operator<<"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::operator<<"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7IBuffer", "tensorrt_llm::runtime::operator<<::buffer"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK26LoraCachePageManagerConfig", "tensorrt_llm::runtime::operator<<::c"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN7ITensor5ShapeE", "tensorrt_llm::runtime::operator<<::dims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK10LoraModule", "tensorrt_llm::runtime::operator<<::module"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK26LoraCachePageManagerConfig", "tensorrt_llm::runtime::operator<<::os"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::operator<<::os"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK10LoraModule", "tensorrt_llm::runtime::operator<<::output"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7IBuffer", "tensorrt_llm::runtime::operator<<::output"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7ITensor", "tensorrt_llm::runtime::operator<<::output"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN7ITensor5ShapeE", "tensorrt_llm::runtime::operator<<::output"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7ITensor", "tensorrt_llm::runtime::operator<<::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::operator<<::v"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9to_stringERK26LoraCachePageManagerConfig", "tensorrt_llm::runtime::to_string"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9to_stringERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::to_string"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9to_stringERK26LoraCachePageManagerConfig", "tensorrt_llm::runtime::to_string::c"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9to_stringERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::to_string::v"], [85, 9, 0, "-", "tensorrt_llm"]], "tensorrt_llm": [[80, 9, 0, "-", "functional"], [82, 9, 0, "-", "models"], [83, 9, 0, "-", "plugin"], [84, 9, 0, "-", "quantization"], [85, 9, 0, "-", "runtime"]], "tensorrt_llm.functional": [[80, 10, 1, "", "AllReduceFusionOp"], [80, 10, 1, "", "AllReduceParams"], [80, 10, 1, "", "AllReduceStrategy"], [80, 10, 1, "", "AttentionMaskType"], [80, 10, 1, "", "Conditional"], [80, 10, 1, "", "DimRange"], [80, 10, 1, "", "LayerNormPositionType"], [80, 10, 1, "", "LayerNormType"], [80, 10, 1, "", "MLPType"], [80, 10, 1, "", "MoEAllReduceParams"], [80, 10, 1, "", "PositionEmbeddingType"], [80, 10, 1, "", "RopeEmbeddingUtils"], [80, 10, 1, "", "RotaryScalingType"], [80, 10, 1, "", "SideStreamIDType"], [80, 10, 1, "", "SliceInputType"], [80, 10, 1, "", "Tensor"], [80, 14, 1, "", "abs"], [80, 14, 1, "", "activation"], [80, 14, 1, "", "add"], [80, 14, 1, "", "allgather"], [80, 14, 1, "", "allreduce"], [80, 14, 1, "", "arange"], [80, 14, 1, "", "argmax"], [80, 14, 1, "", "assertion"], [80, 14, 1, "", "avg_pool2d"], [80, 14, 1, "", "bert_attention"], [80, 14, 1, "", "broadcast_helper"], [80, 14, 1, "", "cast"], [80, 14, 1, "", "categorical_sample"], [80, 14, 1, "", "chunk"], [80, 14, 1, "", "clip"], [80, 14, 1, "", "concat"], [80, 14, 1, "", "constant"], [80, 14, 1, "", "constant_to_tensor_"], [80, 14, 1, "", "constants_to_tensors_"], [80, 14, 1, "", "conv1d"], [80, 14, 1, "", "conv2d"], [80, 14, 1, "", "conv3d"], [80, 14, 1, "", "conv_transpose2d"], [80, 14, 1, "", "cos"], [80, 14, 1, "", "cp_split_plugin"], [80, 14, 1, "", "create_allreduce_plugin"], [80, 14, 1, "", "cuda_stream_sync"], [80, 14, 1, "", "cumsum"], [80, 14, 1, "", "div"], [80, 14, 1, "", "dora_plugin"], [80, 14, 1, "", "einsum"], [80, 14, 1, "", "elementwise_binary"], [80, 14, 1, "", "embedding"], [80, 14, 1, "", "eq"], [80, 14, 1, "", "exp"], [80, 14, 1, "", "expand"], [80, 14, 1, "", "expand_dims"], [80, 14, 1, "", "expand_dims_like"], [80, 14, 1, "", "expand_mask"], [80, 14, 1, "", "flatten"], [80, 14, 1, "", "flip"], [80, 14, 1, "", "floordiv"], [80, 14, 1, "", "gather"], [80, 14, 1, "", "gather_last_token_logits"], [80, 14, 1, "", "gather_nd"], [80, 14, 1, "", "gegelu"], [80, 14, 1, "", "geglu"], [80, 14, 1, "", "gelu"], [80, 14, 1, "", "gemm_allreduce"], [80, 14, 1, "", "gemm_swiglu"], [80, 14, 1, "", "generate_alibi_biases"], [80, 14, 1, "", "generate_alibi_slopes"], [80, 14, 1, "", "generate_logn_scaling"], [80, 14, 1, "", "gpt_attention"], [80, 14, 1, "", "group_norm"], [80, 14, 1, "", "gt"], [80, 14, 1, "", "identity"], [80, 14, 1, "", "index_select"], [80, 14, 1, "", "int_clip"], [80, 14, 1, "", "interpolate"], [80, 14, 1, "", "is_gated_activation"], [80, 14, 1, "", "layer_norm"], [80, 14, 1, "", "log"], [80, 14, 1, "", "log_softmax"], [80, 14, 1, "", "lora_plugin"], [80, 14, 1, "", "low_latency_gemm"], [80, 14, 1, "", "low_latency_gemm_swiglu"], [80, 14, 1, "", "lt"], [80, 14, 1, "", "mamba_conv1d"], [80, 14, 1, "", "masked_scatter"], [80, 14, 1, "", "masked_select"], [80, 14, 1, "", "matmul"], [80, 14, 1, "", "max"], [80, 14, 1, "", "maximum"], [80, 14, 1, "", "mean"], [80, 14, 1, "", "meshgrid2d"], [80, 14, 1, "", "min"], [80, 14, 1, "", "minimum"], [80, 14, 1, "", "modulo"], [80, 14, 1, "", "mul"], [80, 14, 1, "", "non_gated_version"], [80, 14, 1, "", "nonzero"], [80, 14, 1, "", "not_op"], [80, 14, 1, "", "op_and"], [80, 14, 1, "", "op_or"], [80, 14, 1, "", "op_xor"], [80, 14, 1, "", "outer"], [80, 14, 1, "", "pad"], [80, 14, 1, "", "permute"], [80, 14, 1, "", "pow"], [80, 14, 1, "", "prod"], [80, 14, 1, "", "quick_gelu"], [80, 14, 1, "", "rand"], [80, 14, 1, "", "rearrange"], [80, 14, 1, "", "recv"], [80, 14, 1, "", "reduce"], [80, 14, 1, "", "reduce_scatter"], [80, 14, 1, "", "relu"], [80, 14, 1, "", "repeat"], [80, 14, 1, "", "repeat_interleave"], [80, 14, 1, "", "rg_lru"], [80, 14, 1, "", "rms_norm"], [80, 14, 1, "", "round"], [80, 14, 1, "", "scatter"], [80, 14, 1, "", "scatter_nd"], [80, 14, 1, "", "select"], [80, 14, 1, "", "selective_scan"], [80, 14, 1, "", "send"], [80, 14, 1, "", "shape"], [80, 14, 1, "", "sigmoid"], [80, 14, 1, "", "silu"], [80, 14, 1, "", "sin"], [80, 14, 1, "", "slice"], [80, 14, 1, "", "softmax"], [80, 14, 1, "", "softplus"], [80, 14, 1, "", "split"], [80, 14, 1, "", "sqrt"], [80, 14, 1, "", "squared_relu"], [80, 14, 1, "", "squeeze"], [80, 14, 1, "", "stack"], [80, 14, 1, "", "sub"], [80, 14, 1, "", "sum"], [80, 14, 1, "", "swiglu"], [80, 14, 1, "", "tanh"], [80, 14, 1, "", "topk"], [80, 14, 1, "", "transpose"], [80, 14, 1, "", "unary"], [80, 14, 1, "", "unbind"], [80, 14, 1, "", "unsqueeze"], [80, 14, 1, "", "view"], [80, 14, 1, "", "where"]], "tensorrt_llm.functional.AllReduceFusionOp": [[80, 11, 1, "", "LAST_PROCESS_FOR_UB"], [80, 11, 1, "", "MOE_FINALIZE_ALLREDUCE_RESIDUAL_RMS_NORM"], [80, 11, 1, "", "NONE"], [80, 11, 1, "", "RESIDUAL_RMS_NORM"], [80, 11, 1, "", "RESIDUAL_RMS_NORM_OUT_QUANT_FP8"], [80, 11, 1, "", "RESIDUAL_RMS_NORM_OUT_QUANT_NVFP4"], [80, 11, 1, "", "RESIDUAL_RMS_NORM_QUANT_FP8"], [80, 11, 1, "", "RESIDUAL_RMS_NORM_QUANT_NVFP4"], [80, 11, 1, "", "RESIDUAL_RMS_PREPOST_NORM"]], "tensorrt_llm.functional.AllReduceParams": [[80, 12, 1, "", "has_affine"], [80, 12, 1, "", "has_bias"], [80, 12, 1, "", "has_scale"], [80, 12, 1, "", "update_strategy"]], "tensorrt_llm.functional.AllReduceStrategy": [[80, 11, 1, "", "AUTO"], [80, 11, 1, "", "LOWPRECISION"], [80, 11, 1, "", "MIN_LATENCY"], [80, 11, 1, "", "MNNVL"], [80, 11, 1, "", "NCCL"], [80, 11, 1, "", "ONESHOT"], [80, 11, 1, "", "TWOSHOT"], [80, 11, 1, "", "UB"]], "tensorrt_llm.functional.AttentionMaskType": [[80, 11, 1, "", "bidirectional"], [80, 11, 1, "", "bidirectionalglm"], [80, 11, 1, "", "blocksparse"], [80, 11, 1, "", "causal"], [80, 11, 1, "", "custom_mask"], [80, 11, 1, "", "padding"], [80, 11, 1, "", "sliding_window_causal"]], "tensorrt_llm.functional.Conditional": [[80, 12, 1, "", "add_input"], [80, 12, 1, "", "add_output"]], "tensorrt_llm.functional.LayerNormPositionType": [[80, 11, 1, "", "post_layernorm"], [80, 11, 1, "", "pre_layernorm"]], "tensorrt_llm.functional.LayerNormType": [[80, 11, 1, "", "GroupNorm"], [80, 11, 1, "", "LayerNorm"], [80, 11, 1, "", "RmsNorm"]], "tensorrt_llm.functional.MLPType": [[80, 11, 1, "", "FusedGatedMLP"], [80, 11, 1, "", "GatedMLP"], [80, 11, 1, "", "MLP"]], "tensorrt_llm.functional.MoEAllReduceParams": [[80, 12, 1, "", "is_valid"]], "tensorrt_llm.functional.PositionEmbeddingType": [[80, 11, 1, "", "alibi"], [80, 11, 1, "", "alibi_with_scale"], [80, 11, 1, "", "chatglm"], [80, 12, 1, "", "choices"], [80, 11, 1, "", "deferred"], [80, 12, 1, "", "from_string"], [80, 12, 1, "", "is_alibi"], [80, 12, 1, "", "is_deferred"], [80, 12, 1, "", "is_mrope"], [80, 12, 1, "", "is_rope"], [80, 11, 1, "", "learned_absolute"], [80, 11, 1, "", "long_rope"], [80, 11, 1, "", "mrope"], [80, 11, 1, "", "relative"], [80, 11, 1, "", "rope_gpt_neox"], [80, 11, 1, "", "rope_gptj"], [80, 11, 1, "", "yarn"]], "tensorrt_llm.functional.RopeEmbeddingUtils": [[80, 12, 1, "", "apply_llama3_scaling"], [80, 12, 1, "", "apply_rotary_pos_emb"], [80, 12, 1, "", "apply_rotary_pos_emb_chatglm"], [80, 12, 1, "", "apply_rotary_pos_emb_cogvlm"], [80, 12, 1, "", "create_fake_weight"], [80, 12, 1, "", "create_sinusoidal_positions"], [80, 12, 1, "", "create_sinusoidal_positions_for_attention_plugin"], [80, 12, 1, "", "create_sinusoidal_positions_for_cogvlm_attention_plugin"], [80, 12, 1, "", "create_sinusoidal_positions_long_rope"], [80, 12, 1, "", "create_sinusoidal_positions_yarn"], [80, 12, 1, "", "rotate_every_two"], [80, 12, 1, "", "rotate_half"]], "tensorrt_llm.functional.RotaryScalingType": [[80, 11, 1, "", "dynamic"], [80, 12, 1, "", "from_string"], [80, 11, 1, "", "linear"], [80, 11, 1, "", "llama3"], [80, 11, 1, "", "longrope"], [80, 11, 1, "", "mrope"], [80, 11, 1, "", "none"], [80, 11, 1, "", "yarn"]], "tensorrt_llm.functional.SideStreamIDType": [[80, 11, 1, "", "disable"], [80, 11, 1, "", "moe"]], "tensorrt_llm.functional.SliceInputType": [[80, 11, 1, "", "axes"], [80, 11, 1, "", "data"], [80, 11, 1, "", "fill_value"], [80, 11, 1, "", "size"], [80, 11, 1, "", "start"], [80, 11, 1, "", "stride"]], "tensorrt_llm.functional.Tensor": [[80, 12, 1, "", "abs"], [80, 12, 1, "", "cast"], [80, 13, 1, "", "dtype"], [80, 12, 1, "", "flatten"], [80, 12, 1, "", "get_parent"], [80, 12, 1, "", "get_users"], [80, 12, 1, "", "is_dynamic"], [80, 12, 1, "", "is_trt_wrapper"], [80, 13, 1, "", "location"], [80, 12, 1, "", "log"], [80, 12, 1, "", "mark_output"], [80, 12, 1, "", "max"], [80, 12, 1, "", "mean"], [80, 13, 1, "", "name"], [80, 12, 1, "", "ndim"], [80, 13, 1, "", "network"], [80, 12, 1, "", "permute"], [80, 12, 1, "", "rank"], [80, 12, 1, "", "repeat"], [80, 12, 1, "", "replace_all_uses_with"], [80, 12, 1, "", "select"], [80, 13, 1, "", "shape"], [80, 12, 1, "", "size"], [80, 12, 1, "", "split"], [80, 12, 1, "", "sqrt"], [80, 12, 1, "", "squeeze"], [80, 12, 1, "", "transpose"], [80, 12, 1, "", "unbind"], [80, 12, 1, "", "unsqueeze"], [80, 12, 1, "", "view"]], "tensorrt_llm.layers": [[81, 9, 0, "-", "activation"], [81, 9, 0, "-", "attention"], [81, 9, 0, "-", "cast"], [81, 9, 0, "-", "conv"], [81, 9, 0, "-", "embedding"], [81, 9, 0, "-", "linear"], [81, 9, 0, "-", "mlp"], [81, 9, 0, "-", "normalization"], [81, 9, 0, "-", "pooling"]], "tensorrt_llm.layers.activation": [[81, 10, 1, "", "Mish"]], "tensorrt_llm.layers.activation.Mish": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.attention": [[81, 10, 1, "", "Attention"], [81, 10, 1, "", "AttentionMaskParams"], [81, 10, 1, "", "AttentionParams"], [81, 10, 1, "", "BertAttention"], [81, 10, 1, "", "BlockSparseAttnParams"], [81, 10, 1, "", "CogVLMAttention"], [81, 10, 1, "", "DeepseekV2Attention"], [81, 10, 1, "", "DiffusersAttention"], [81, 10, 1, "", "KeyValueCacheParams"], [81, 10, 1, "", "MropeParams"], [81, 10, 1, "", "SpecDecodingParams"], [81, 14, 1, "", "compute_relative_bias"], [81, 14, 1, "", "make_causal_mask"]], "tensorrt_llm.layers.attention.Attention": [[81, 12, 1, "", "create_attention_const_params"], [81, 12, 1, "", "fill_attention_params"], [81, 12, 1, "", "forward"], [81, 12, 1, "", "postprocess"], [81, 12, 1, "", "set_rel_attn_table"]], "tensorrt_llm.layers.attention.AttentionParams": [[81, 12, 1, "", "fill_attention_const_params_for_long_rope"], [81, 12, 1, "", "fill_attention_const_params_for_rope"], [81, 12, 1, "", "is_valid"], [81, 12, 1, "", "is_valid_cross_attn"]], "tensorrt_llm.layers.attention.BertAttention": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.attention.CogVLMAttention": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.attention.DeepseekV2Attention": [[81, 12, 1, "", "forward"], [81, 12, 1, "", "postprocess"], [81, 12, 1, "", "weight_loader"]], "tensorrt_llm.layers.attention.DiffusersAttention": [[81, 12, 1, "", "forward"], [81, 12, 1, "", "joint_attn_forward"]], "tensorrt_llm.layers.attention.KeyValueCacheParams": [[81, 12, 1, "", "fill_none_tensor_list"], [81, 12, 1, "", "get_first_past_key_value"], [81, 12, 1, "", "is_valid"]], "tensorrt_llm.layers.cast": [[81, 10, 1, "", "Cast"]], "tensorrt_llm.layers.cast.Cast": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.conv": [[81, 10, 1, "", "Conv1d"], [81, 10, 1, "", "Conv2d"], [81, 10, 1, "", "Conv3d"], [81, 10, 1, "", "ConvTranspose2d"]], "tensorrt_llm.layers.conv.Conv1d": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.conv.Conv2d": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.conv.Conv3d": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.conv.ConvTranspose2d": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.embedding": [[81, 10, 1, "", "CombinedTimestepLabelEmbeddings"], [81, 10, 1, "", "CombinedTimestepTextProjEmbeddings"], [81, 10, 1, "", "Embedding"], [81, 10, 1, "", "LabelEmbedding"], [81, 10, 1, "", "PixArtAlphaTextProjection"], [81, 10, 1, "", "PromptTuningEmbedding"], [81, 10, 1, "", "SD3PatchEmbed"], [81, 10, 1, "", "TimestepEmbedding"], [81, 10, 1, "", "Timesteps"], [81, 14, 1, "", "get_1d_sincos_pos_embed_from_grid"], [81, 14, 1, "", "get_2d_sincos_pos_embed"], [81, 14, 1, "", "get_2d_sincos_pos_embed_from_grid"], [81, 14, 1, "", "get_timestep_embedding"]], "tensorrt_llm.layers.embedding.CombinedTimestepLabelEmbeddings": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.embedding.CombinedTimestepTextProjEmbeddings": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.embedding.Embedding": [[81, 12, 1, "", "forward"], [81, 12, 1, "", "postprocess"], [81, 12, 1, "", "weight_loader"]], "tensorrt_llm.layers.embedding.LabelEmbedding": [[81, 12, 1, "", "forward"], [81, 12, 1, "", "token_drop"]], "tensorrt_llm.layers.embedding.PixArtAlphaTextProjection": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.embedding.PromptTuningEmbedding": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.embedding.SD3PatchEmbed": [[81, 12, 1, "", "cropped_pos_embed"], [81, 12, 1, "", "forward"]], "tensorrt_llm.layers.embedding.TimestepEmbedding": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.embedding.Timesteps": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.linear": [[81, 11, 1, "", "ColumnLinear"], [81, 10, 1, "", "Linear"], [81, 10, 1, "", "LinearBase"], [81, 10, 1, "", "RowLinear"]], "tensorrt_llm.layers.linear.Linear": [[81, 12, 1, "", "collect_and_bias"], [81, 12, 1, "", "postprocess"], [81, 12, 1, "", "tp_split_dim"]], "tensorrt_llm.layers.linear.LinearBase": [[81, 12, 1, "", "collect_and_bias"], [81, 12, 1, "", "forward"], [81, 12, 1, "", "get_weight"], [81, 12, 1, "", "multiply_and_lora"], [81, 12, 1, "", "multiply_collect"], [81, 12, 1, "", "tp_split_dim"], [81, 12, 1, "", "weight_loader"]], "tensorrt_llm.layers.linear.RowLinear": [[81, 12, 1, "", "collect_and_bias"], [81, 12, 1, "", "multiply_collect"], [81, 12, 1, "", "tp_split_dim"]], "tensorrt_llm.layers.mlp": [[81, 10, 1, "", "FusedGatedMLP"], [81, 10, 1, "", "GatedMLP"], [81, 10, 1, "", "LinearActivation"], [81, 10, 1, "", "LinearApproximateGELU"], [81, 10, 1, "", "LinearGEGLU"], [81, 10, 1, "", "LinearGELU"], [81, 10, 1, "", "LinearSwiGLU"], [81, 10, 1, "", "MLP"], [81, 14, 1, "", "fc_gate_dora"], [81, 14, 1, "", "fc_gate_lora"]], "tensorrt_llm.layers.mlp.FusedGatedMLP": [[81, 12, 1, "", "fc_gate"], [81, 12, 1, "", "fc_gate_plugin"], [81, 12, 1, "", "forward"]], "tensorrt_llm.layers.mlp.GatedMLP": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.mlp.LinearActivation": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.mlp.LinearApproximateGELU": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.mlp.LinearGEGLU": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.mlp.LinearGELU": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.mlp.LinearSwiGLU": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.mlp.MLP": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization": [[81, 10, 1, "", "AdaLayerNorm"], [81, 10, 1, "", "AdaLayerNormContinuous"], [81, 10, 1, "", "AdaLayerNormZero"], [81, 10, 1, "", "AdaLayerNormZeroSingle"], [81, 10, 1, "", "GroupNorm"], [81, 10, 1, "", "LayerNorm"], [81, 10, 1, "", "RmsNorm"], [81, 10, 1, "", "SD35AdaLayerNormZeroX"]], "tensorrt_llm.layers.normalization.AdaLayerNorm": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization.AdaLayerNormContinuous": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization.AdaLayerNormZero": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization.AdaLayerNormZeroSingle": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization.GroupNorm": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization.LayerNorm": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization.RmsNorm": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization.SD35AdaLayerNormZeroX": [[81, 12, 1, "", "forward"]], "tensorrt_llm.layers.pooling": [[81, 10, 1, "", "AvgPool2d"]], "tensorrt_llm.layers.pooling.AvgPool2d": [[81, 12, 1, "", "forward"]], "tensorrt_llm.llmapi": [[68, 10, 1, "", "BatchingType"], [68, 10, 1, "", "BuildCacheConfig"], [68, 10, 1, "", "BuildConfig"], [68, 10, 1, "", "CacheTransceiverConfig"], [68, 10, 1, "", "CalibConfig"], [68, 10, 1, "", "CapacitySchedulerPolicy"], [68, 10, 1, "", "CompletionOutput"], [68, 10, 1, "", "ContextChunkingPolicy"], [68, 10, 1, "", "CudaGraphConfig"], [68, 10, 1, "", "DisaggregatedParams"], [68, 10, 1, "", "DraftTargetDecodingConfig"], [68, 10, 1, "", "DynamicBatchConfig"], [68, 10, 1, "", "EagleDecodingConfig"], [68, 10, 1, "", "ExtendedRuntimePerfKnobConfig"], [68, 10, 1, "", "GuidedDecodingParams"], [68, 10, 1, "", "KvCacheConfig"], [68, 10, 1, "", "KvCacheRetentionConfig"], [68, 10, 1, "", "LLM"], [68, 11, 1, "", "LlmArgs"], [68, 10, 1, "", "LookaheadDecodingConfig"], [68, 10, 1, "", "MTPDecodingConfig"], [68, 10, 1, "", "MedusaDecodingConfig"], [68, 10, 1, "", "MpiCommSession"], [68, 10, 1, "", "NGramDecodingConfig"], [68, 10, 1, "", "QuantAlgo"], [68, 10, 1, "", "QuantConfig"], [68, 10, 1, "", "RequestError"], [68, 10, 1, "", "RequestOutput"], [68, 10, 1, "", "SamplingParams"], [68, 10, 1, "", "SchedulerConfig"], [68, 10, 1, "", "TorchCompileConfig"], [68, 10, 1, "", "TorchLlmArgs"], [68, 10, 1, "", "TrtLlmArgs"], [68, 10, 1, "", "UserProvidedDecodingConfig"]], "tensorrt_llm.llmapi.BatchingType": [[68, 11, 1, "", "INFLIGHT"], [68, 11, 1, "", "STATIC"]], "tensorrt_llm.llmapi.BuildCacheConfig": [[68, 12, 1, "", "__init__"], [68, 13, 1, "id7", "cache_root"], [68, 13, 1, "id8", "max_cache_storage_gb"], [68, 13, 1, "id9", "max_records"]], "tensorrt_llm.llmapi.BuildConfig": [[68, 12, 1, "", "__init__"], [68, 11, 1, "", "auto_parallel_config"], [68, 11, 1, "", "dry_run"], [68, 11, 1, "", "enable_debug_output"], [68, 11, 1, "", "force_num_profiles"], [68, 12, 1, "", "from_dict"], [68, 12, 1, "", "from_json_file"], [68, 11, 1, "", "gather_context_logits"], [68, 11, 1, "", "gather_generation_logits"], [68, 11, 1, "", "input_timing_cache"], [68, 11, 1, "", "kv_cache_type"], [68, 11, 1, "", "lora_config"], [68, 11, 1, "", "max_batch_size"], [68, 11, 1, "", "max_beam_width"], [68, 11, 1, "", "max_draft_len"], [68, 11, 1, "", "max_encoder_input_len"], [68, 11, 1, "", "max_input_len"], [68, 11, 1, "", "max_num_tokens"], [68, 11, 1, "", "max_prompt_embedding_table_size"], [68, 11, 1, "", "max_seq_len"], [68, 11, 1, "", "monitor_memory"], [68, 11, 1, "", "opt_batch_size"], [68, 11, 1, "", "opt_num_tokens"], [68, 11, 1, "", "output_timing_cache"], [68, 11, 1, "", "plugin_config"], [68, 11, 1, "", "profiling_verbosity"], [68, 11, 1, "", "speculative_decoding_mode"], [68, 11, 1, "", "strongly_typed"], [68, 12, 1, "", "to_dict"], [68, 12, 1, "", "update"], [68, 12, 1, "", "update_from_dict"], [68, 12, 1, "", "update_kv_cache_type"], [68, 11, 1, "", "use_mrope"], [68, 11, 1, "", "use_refit"], [68, 11, 1, "", "use_strip_plan"], [68, 11, 1, "", "visualize_network"], [68, 11, 1, "", "weight_sparsity"], [68, 11, 1, "", "weight_streaming"]], "tensorrt_llm.llmapi.CacheTransceiverConfig": [[68, 15, 1, "", "max_num_tokens"], [68, 11, 1, "", "model_config"]], "tensorrt_llm.llmapi.CalibConfig": [[68, 15, 1, "", "calib_batch_size"], [68, 15, 1, "", "calib_batches"], [68, 15, 1, "", "calib_dataset"], [68, 15, 1, "", "calib_max_seq_length"], [68, 15, 1, "", "device"], [68, 12, 1, "", "from_dict"], [68, 11, 1, "", "model_config"], [68, 15, 1, "", "random_seed"], [68, 12, 1, "", "to_dict"], [68, 15, 1, "", "tokenizer_max_seq_length"]], "tensorrt_llm.llmapi.CapacitySchedulerPolicy": [[68, 11, 1, "", "GUARANTEED_NO_EVICT"], [68, 11, 1, "", "MAX_UTILIZATION"], [68, 11, 1, "", "STATIC_BATCH"]], "tensorrt_llm.llmapi.CompletionOutput": [[68, 12, 1, "", "__init__"], [68, 11, 1, "", "cumulative_logprob"], [68, 11, 1, "", "disaggregated_params"], [68, 11, 1, "", "finish_reason"], [68, 11, 1, "", "generation_logits"], [68, 11, 1, "", "index"], [68, 13, 1, "id2", "length"], [68, 11, 1, "", "logprobs"], [68, 13, 1, "id3", "logprobs_diff"], [68, 11, 1, "", "prompt_logprobs"], [68, 11, 1, "", "request_perf_metrics"], [68, 11, 1, "", "stop_reason"], [68, 11, 1, "", "text"], [68, 13, 1, "id4", "text_diff"], [68, 11, 1, "", "token_ids"], [68, 13, 1, "id5", "token_ids_diff"]], "tensorrt_llm.llmapi.ContextChunkingPolicy": [[68, 11, 1, "", "EQUAL_PROGRESS"], [68, 11, 1, "", "FIRST_COME_FIRST_SERVED"]], "tensorrt_llm.llmapi.CudaGraphConfig": [[68, 15, 1, "", "batch_sizes"], [68, 15, 1, "", "max_batch_size"], [68, 11, 1, "", "model_config"], [68, 15, 1, "", "padding_enabled"], [68, 16, 1, "", "validate_cuda_graph_max_batch_size"]], "tensorrt_llm.llmapi.DisaggregatedParams": [[68, 12, 1, "", "__init__"], [68, 11, 1, "", "ctx_request_id"], [68, 11, 1, "", "draft_tokens"], [68, 11, 1, "", "first_gen_tokens"], [68, 12, 1, "", "get_context_phase_params"], [68, 12, 1, "", "get_request_type"], [68, 11, 1, "", "opaque_state"], [68, 11, 1, "", "request_type"]], "tensorrt_llm.llmapi.DraftTargetDecodingConfig": [[68, 11, 1, "", "decoding_type"], [68, 12, 1, "", "from_dict"], [68, 11, 1, "", "model_config"], [68, 12, 1, "", "supports_backend"]], "tensorrt_llm.llmapi.DynamicBatchConfig": [[68, 15, 1, "", "dynamic_batch_moving_average_window"], [68, 15, 1, "", "enable_batch_size_tuning"], [68, 15, 1, "", "enable_max_num_tokens_tuning"], [68, 11, 1, "", "model_config"]], "tensorrt_llm.llmapi.EagleDecodingConfig": [[68, 11, 1, "", "decoding_type"], [68, 15, 1, "", "dynamic_tree_max_topK"], [68, 15, 1, "", "eagle3_one_model"], [68, 15, 1, "", "eagle_choices"], [68, 12, 1, "", "from_dict"], [68, 12, 1, "", "get_draft_model_prompt"], [68, 15, 1, "", "greedy_sampling"], [68, 15, 1, "", "max_non_leaves_per_layer"], [68, 11, 1, "", "model_config"], [68, 15, 1, "", "num_eagle_layers"], [68, 15, 1, "", "posterior_threshold"], [68, 13, 1, "", "spec_dec_mode"], [68, 15, 1, "", "use_dynamic_tree"], [68, 12, 1, "", "validate"]], "tensorrt_llm.llmapi.ExtendedRuntimePerfKnobConfig": [[68, 15, 1, "", "cuda_graph_cache_size"], [68, 15, 1, "", "cuda_graph_mode"], [68, 15, 1, "", "enable_context_fmha_fp32_acc"], [68, 11, 1, "", "model_config"], [68, 15, 1, "", "multi_block_mode"]], "tensorrt_llm.llmapi.GuidedDecodingParams": [[68, 12, 1, "", "__init__"], [68, 11, 1, "", "grammar"], [68, 11, 1, "", "json"], [68, 11, 1, "", "json_object"], [68, 11, 1, "", "regex"], [68, 11, 1, "", "structural_tag"]], "tensorrt_llm.llmapi.KvCacheConfig": [[68, 15, 1, "", "copy_on_partial_reuse"], [68, 15, 1, "", "cross_kv_cache_fraction"], [68, 15, 1, "", "enable_block_reuse"], [68, 15, 1, "", "enable_partial_reuse"], [68, 15, 1, "", "event_buffer_max_size"], [68, 15, 1, "", "free_gpu_memory_fraction"], [68, 15, 1, "", "host_cache_size"], [68, 15, 1, "", "max_attention_window"], [68, 15, 1, "", "max_tokens"], [68, 11, 1, "", "model_config"], [68, 15, 1, "", "onboard_blocks"], [68, 15, 1, "", "secondary_offload_min_priority"], [68, 15, 1, "", "sink_token_length"], [68, 15, 1, "", "use_uvm"]], "tensorrt_llm.llmapi.KvCacheRetentionConfig": [[68, 10, 1, "", "TokenRangeRetentionConfig"], [68, 12, 1, "", "__init__"], [68, 13, 1, "", "decode_duration_ms"], [68, 13, 1, "", "decode_retention_priority"], [68, 13, 1, "", "directory"], [68, 13, 1, "", "token_range_retention_configs"], [68, 13, 1, "", "transfer_mode"]], "tensorrt_llm.llmapi.KvCacheRetentionConfig.TokenRangeRetentionConfig": [[68, 12, 1, "", "__init__"], [68, 13, 1, "", "duration_ms"], [68, 13, 1, "", "priority"], [68, 13, 1, "", "token_end"], [68, 13, 1, "", "token_start"]], "tensorrt_llm.llmapi.LLM": [[68, 12, 1, "", "generate"], [68, 12, 1, "", "generate_async"], [68, 12, 1, "", "get_kv_cache_events"], [68, 12, 1, "", "get_kv_cache_events_async"], [68, 12, 1, "", "get_stats"], [68, 12, 1, "", "get_stats_async"], [68, 13, 1, "id0", "llm_id"], [68, 12, 1, "", "shutdown"], [68, 13, 1, "id1", "tokenizer"]], "tensorrt_llm.llmapi.LookaheadDecodingConfig": [[68, 12, 1, "", "__init__"], [68, 12, 1, "", "calculate_speculative_resource"], [68, 11, 1, "", "decoding_type"], [68, 12, 1, "", "from_dict"], [68, 15, 1, "", "max_ngram_size"], [68, 15, 1, "", "max_verification_set_size"], [68, 15, 1, "", "max_window_size"], [68, 11, 1, "", "model_config"], [68, 12, 1, "", "supports_backend"], [68, 16, 1, "", "validate_positive_values"]], "tensorrt_llm.llmapi.MTPDecodingConfig": [[68, 15, 1, "", "BEGIN_THINKING_PHASE_TOKEN"], [68, 15, 1, "", "END_THINKING_PHASE_TOKEN"], [68, 11, 1, "", "decoding_type"], [68, 12, 1, "", "from_dict"], [68, 11, 1, "", "model_config"], [68, 15, 1, "", "num_nextn_predict_layers"], [68, 15, 1, "", "num_nextn_predict_layers_from_model_config"], [68, 15, 1, "", "relaxed_delta"], [68, 15, 1, "", "relaxed_topk"], [68, 13, 1, "", "spec_dec_mode"], [68, 12, 1, "", "supports_backend"], [68, 12, 1, "", "update_from_model_config"], [68, 15, 1, "", "use_mtp_vanilla"], [68, 15, 1, "", "use_relaxed_acceptance_for_thinking"]], "tensorrt_llm.llmapi.MedusaDecodingConfig": [[68, 11, 1, "", "decoding_type"], [68, 12, 1, "", "from_dict"], [68, 15, 1, "", "medusa_choices"], [68, 11, 1, "", "model_config"], [68, 15, 1, "", "num_medusa_heads"], [68, 12, 1, "", "supports_backend"]], "tensorrt_llm.llmapi.MpiCommSession": [[68, 12, 1, "", "__init__"], [68, 12, 1, "", "abort"], [68, 12, 1, "", "get_comm"], [68, 12, 1, "", "shutdown"], [68, 12, 1, "", "submit"], [68, 12, 1, "", "submit_sync"]], "tensorrt_llm.llmapi.NGramDecodingConfig": [[68, 11, 1, "", "decoding_type"], [68, 12, 1, "", "from_dict"], [68, 15, 1, "", "is_keep_all"], [68, 15, 1, "", "is_public_pool"], [68, 15, 1, "", "is_use_oldest"], [68, 15, 1, "", "max_matching_ngram_size"], [68, 11, 1, "", "model_config"], [68, 12, 1, "", "supports_backend"]], "tensorrt_llm.llmapi.QuantAlgo": [[68, 11, 1, "", "FP8"], [68, 11, 1, "", "FP8_BLOCK_SCALES"], [68, 11, 1, "", "FP8_PER_CHANNEL_PER_TOKEN"], [68, 11, 1, "", "INT8"], [68, 11, 1, "", "MIXED_PRECISION"], [68, 11, 1, "", "NO_QUANT"], [68, 11, 1, "", "NVFP4"], [68, 11, 1, "", "W4A16"], [68, 11, 1, "", "W4A16_AWQ"], [68, 11, 1, "", "W4A16_GPTQ"], [68, 11, 1, "", "W4A8_AWQ"], [68, 11, 1, "", "W4A8_MXFP4_FP8"], [68, 11, 1, "", "W4A8_QSERVE_PER_CHANNEL"], [68, 11, 1, "", "W4A8_QSERVE_PER_GROUP"], [68, 11, 1, "", "W8A16"], [68, 11, 1, "", "W8A16_GPTQ"], [68, 11, 1, "", "W8A8_SQ_PER_CHANNEL"], [68, 11, 1, "", "W8A8_SQ_PER_CHANNEL_PER_TENSOR_PLUGIN"], [68, 11, 1, "", "W8A8_SQ_PER_CHANNEL_PER_TOKEN_PLUGIN"], [68, 11, 1, "", "W8A8_SQ_PER_TENSOR_PER_TOKEN_PLUGIN"], [68, 11, 1, "", "W8A8_SQ_PER_TENSOR_PLUGIN"]], "tensorrt_llm.llmapi.QuantConfig": [[68, 12, 1, "", "__init__"], [68, 11, 1, "", "clamp_val"], [68, 11, 1, "", "exclude_modules"], [68, 12, 1, "", "from_dict"], [68, 11, 1, "", "group_size"], [68, 11, 1, "", "has_zero_point"], [68, 12, 1, "", "is_module_excluded_from_quantization"], [68, 11, 1, "", "kv_cache_quant_algo"], [68, 13, 1, "", "layer_quant_mode"], [68, 11, 1, "", "pre_quant_scale"], [68, 11, 1, "", "quant_algo"], [68, 13, 1, "", "quant_mode"], [68, 11, 1, "", "smoothquant_val"], [68, 12, 1, "", "to_dict"], [68, 11, 1, "", "use_meta_recipe"]], "tensorrt_llm.llmapi.RequestOutput": [[68, 12, 1, "", "__init__"], [68, 11, 1, "", "context_logits"], [68, 11, 1, "", "finished"], [68, 11, 1, "", "outputs"], [68, 13, 1, "id6", "prompt"], [68, 11, 1, "", "prompt_token_ids"], [68, 11, 1, "", "request_id"]], "tensorrt_llm.llmapi.SamplingParams": [[68, 12, 1, "", "__init__"], [68, 11, 1, "", "add_special_tokens"], [68, 11, 1, "", "additional_model_outputs"], [68, 11, 1, "", "apply_batched_logits_processor"], [68, 11, 1, "", "bad"], [68, 11, 1, "", "bad_token_ids"], [68, 11, 1, "", "beam_search_diversity_rate"], [68, 11, 1, "", "beam_width_array"], [68, 11, 1, "", "best_of"], [68, 11, 1, "", "detokenize"], [68, 11, 1, "", "early_stopping"], [68, 11, 1, "", "embedding_bias"], [68, 11, 1, "", "end_id"], [68, 11, 1, "", "exclude_input_from_output"], [68, 11, 1, "", "frequency_penalty"], [68, 11, 1, "", "guided_decoding"], [68, 11, 1, "", "ignore_eos"], [68, 11, 1, "", "include_stop_str_in_output"], [68, 11, 1, "", "length_penalty"], [68, 11, 1, "", "logits_processor"], [68, 11, 1, "", "logprobs"], [68, 11, 1, "", "lookahead_config"], [68, 11, 1, "", "max_tokens"], [68, 11, 1, "", "min_p"], [68, 11, 1, "", "min_tokens"], [68, 11, 1, "", "n"], [68, 11, 1, "", "no_repeat_ngram_size"], [68, 11, 1, "", "pad_id"], [68, 11, 1, "", "presence_penalty"], [68, 11, 1, "", "prompt_logprobs"], [68, 11, 1, "", "repetition_penalty"], [68, 11, 1, "", "return_context_logits"], [68, 11, 1, "", "return_encoder_output"], [68, 11, 1, "", "return_generation_logits"], [68, 11, 1, "", "return_perf_metrics"], [68, 11, 1, "", "seed"], [68, 11, 1, "", "skip_special_tokens"], [68, 11, 1, "", "spaces_between_special_tokens"], [68, 11, 1, "", "stop"], [68, 11, 1, "", "stop_token_ids"], [68, 11, 1, "", "temperature"], [68, 11, 1, "", "top_k"], [68, 11, 1, "", "top_p"], [68, 11, 1, "", "top_p_decay"], [68, 11, 1, "", "top_p_min"], [68, 11, 1, "", "top_p_reset_ids"], [68, 11, 1, "", "truncate_prompt_tokens"], [68, 11, 1, "", "use_beam_search"]], "tensorrt_llm.llmapi.SchedulerConfig": [[68, 15, 1, "", "capacity_scheduler_policy"], [68, 15, 1, "", "context_chunking_policy"], [68, 15, 1, "", "dynamic_batch_config"], [68, 11, 1, "", "model_config"]], "tensorrt_llm.llmapi.TorchCompileConfig": [[68, 15, 1, "", "enable_fullgraph"], [68, 15, 1, "", "enable_inductor"], [68, 15, 1, "", "enable_piecewise_cuda_graph"], [68, 15, 1, "", "enable_userbuffers"], [68, 11, 1, "", "model_config"]], "tensorrt_llm.llmapi.TorchLlmArgs": [[68, 15, 1, "", "allreduce_strategy"], [68, 15, 1, "", "attn_backend"], [68, 15, 1, "", "build_config"], [68, 16, 1, "", "convert_load_format"], [68, 15, 1, "", "cuda_graph_config"], [68, 11, 1, "", "decoding_config"], [68, 15, 1, "", "disable_overlap_scheduler"], [68, 15, 1, "", "enable_autotuner"], [68, 15, 1, "", "enable_iter_perf_stats"], [68, 15, 1, "", "enable_iter_req_stats"], [68, 15, 1, "", "enable_layerwise_nvtx_marker"], [68, 15, 1, "", "enable_min_latency"], [68, 15, 1, "", "enable_mixed_sampler"], [68, 15, 1, "", "enable_trtllm_sampler"], [68, 13, 1, "", "extra_resource_managers"], [68, 11, 1, "id18", "field_name"], [68, 15, 1, "", "force_dynamic_quantization"], [68, 15, 1, "", "garbage_collection_gen0_threshold"], [68, 12, 1, "", "get_pytorch_backend_config"], [68, 16, 1, "", "init_backend"], [68, 15, 1, "", "kv_cache_dtype"], [68, 15, 1, "", "load_format"], [68, 11, 1, "", "max_cpu_loras"], [68, 11, 1, "", "max_lora_rank"], [68, 11, 1, "", "max_loras"], [68, 11, 1, "", "model_config"], [68, 12, 1, "", "model_post_init"], [68, 15, 1, "", "moe_backend"], [68, 15, 1, "", "moe_load_balancer"], [68, 15, 1, "", "moe_max_num_tokens"], [68, 11, 1, "id16", "msg"], [68, 15, 1, "", "print_iter_log"], [68, 15, 1, "", "stream_interval"], [68, 15, 1, "", "torch_compile_config"], [68, 16, 1, "", "validate_cuda_graph_config"], [68, 16, 1, "", "validate_moe_load_balancer"], [68, 16, 1, "", "validate_stream_interval"], [68, 11, 1, "id17", "wrapped_property"]], "tensorrt_llm.llmapi.TrtLlmArgs": [[68, 11, 1, "", "auto_parallel"], [68, 13, 1, "", "auto_parallel_config"], [68, 11, 1, "", "auto_parallel_world_size"], [68, 15, 1, "", "build_config"], [68, 15, 1, "", "calib_config"], [68, 11, 1, "", "decoding_config"], [68, 15, 1, "", "embedding_parallel_mode"], [68, 15, 1, "", "enable_build_cache"], [68, 15, 1, "", "enable_prompt_adapter"], [68, 15, 1, "", "enable_tqdm"], [68, 15, 1, "", "extended_runtime_perf_knob_config"], [68, 15, 1, "", "fast_build"], [68, 11, 1, "id33", "field_name"], [68, 16, 1, "", "init_calib_config"], [68, 11, 1, "", "max_cpu_loras"], [68, 11, 1, "", "max_lora_rank"], [68, 11, 1, "", "max_loras"], [68, 15, 1, "", "max_prompt_adapter_token"], [68, 11, 1, "", "model_config"], [68, 12, 1, "", "model_post_init"], [68, 11, 1, "id31", "msg"], [68, 16, 1, "", "setup_embedding_parallel_mode"], [68, 16, 1, "", "validate_auto_parallel"], [68, 16, 1, "", "validate_enable_build_cache"], [68, 15, 1, "", "workspace"], [68, 11, 1, "id32", "wrapped_property"]], "tensorrt_llm.llmapi.UserProvidedDecodingConfig": [[68, 11, 1, "", "decoding_type"], [68, 15, 1, "", "drafter"], [68, 12, 1, "", "from_dict"], [68, 11, 1, "", "model_config"]], "tensorrt_llm.models": [[82, 10, 1, "", "BaichuanForCausalLM"], [82, 10, 1, "", "BertForQuestionAnswering"], [82, 10, 1, "", "BertForSequenceClassification"], [82, 10, 1, "", "BertModel"], [82, 10, 1, "", "BloomForCausalLM"], [82, 10, 1, "", "BloomModel"], [82, 10, 1, "", "CLIPVisionTransformer"], [82, 10, 1, "", "ChatGLMConfig"], [82, 10, 1, "", "ChatGLMForCausalLM"], [82, 10, 1, "", "ChatGLMModel"], [82, 10, 1, "", "CogVLMConfig"], [82, 10, 1, "", "CogVLMForCausalLM"], [82, 10, 1, "", "CohereForCausalLM"], [82, 10, 1, "", "DbrxConfig"], [82, 10, 1, "", "DbrxForCausalLM"], [82, 10, 1, "", "DecoderModel"], [82, 10, 1, "", "DeepseekForCausalLM"], [82, 10, 1, "", "DeepseekV2ForCausalLM"], [82, 10, 1, "", "DiT"], [82, 10, 1, "", "EagleForCausalLM"], [82, 10, 1, "", "EncoderModel"], [82, 10, 1, "", "FalconConfig"], [82, 10, 1, "", "FalconForCausalLM"], [82, 10, 1, "", "FalconModel"], [82, 10, 1, "", "GPTConfig"], [82, 10, 1, "", "GPTForCausalLM"], [82, 10, 1, "", "GPTJConfig"], [82, 10, 1, "", "GPTJForCausalLM"], [82, 10, 1, "", "GPTJModel"], [82, 10, 1, "", "GPTModel"], [82, 10, 1, "", "GPTNeoXForCausalLM"], [82, 10, 1, "", "GPTNeoXModel"], [82, 10, 1, "", "GemmaConfig"], [82, 10, 1, "", "GemmaForCausalLM"], [82, 10, 1, "", "LLaMAConfig"], [82, 10, 1, "", "LLaMAForCausalLM"], [82, 10, 1, "", "LLaMAModel"], [82, 10, 1, "", "LlavaNextVisionConfig"], [82, 10, 1, "", "LlavaNextVisionWrapper"], [82, 10, 1, "", "MLLaMAForCausalLM"], [82, 10, 1, "", "MPTForCausalLM"], [82, 10, 1, "", "MPTModel"], [82, 10, 1, "", "MambaForCausalLM"], [82, 10, 1, "", "MedusaConfig"], [82, 10, 1, "", "MedusaForCausalLm"], [82, 10, 1, "", "OPTForCausalLM"], [82, 10, 1, "", "OPTModel"], [82, 10, 1, "", "Phi3ForCausalLM"], [82, 10, 1, "", "Phi3Model"], [82, 10, 1, "", "PhiForCausalLM"], [82, 10, 1, "", "PhiModel"], [82, 10, 1, "", "PretrainedConfig"], [82, 10, 1, "", "PretrainedModel"], [82, 10, 1, "", "ReDrafterForLLaMALM"], [82, 10, 1, "", "ReDrafterForQWenLM"], [82, 10, 1, "", "RecurrentGemmaForCausalLM"], [82, 11, 1, "", "RobertaForQuestionAnswering"], [82, 11, 1, "", "RobertaForSequenceClassification"], [82, 11, 1, "", "RobertaModel"], [82, 10, 1, "", "SD3Transformer2DModel"], [82, 10, 1, "", "SpeculativeDecodingMode"], [82, 10, 1, "", "WhisperEncoder"]], "tensorrt_llm.models.BaichuanForCausalLM": [[82, 11, 1, "", "config_class"], [82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "quantize"]], "tensorrt_llm.models.BertForQuestionAnswering": [[82, 12, 1, "", "forward"]], "tensorrt_llm.models.BertForSequenceClassification": [[82, 12, 1, "", "forward"]], "tensorrt_llm.models.BertModel": [[82, 12, 1, "", "forward"]], "tensorrt_llm.models.BloomModel": [[82, 12, 1, "", "forward"]], "tensorrt_llm.models.CLIPVisionTransformer": [[82, 12, 1, "", "forward"]], "tensorrt_llm.models.ChatGLMConfig": [[82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "to_dict"]], "tensorrt_llm.models.ChatGLMForCausalLM": [[82, 11, 1, "", "config_class"], [82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "prepare_inputs"], [82, 12, 1, "", "quantize"]], "tensorrt_llm.models.ChatGLMModel": [[82, 12, 1, "", "forward"]], "tensorrt_llm.models.CogVLMConfig": [[82, 12, 1, "", "to_dict"]], "tensorrt_llm.models.CogVLMForCausalLM": [[82, 11, 1, "", "config_class"], [82, 12, 1, "", "default_plugin_config"], [82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "quantize"]], "tensorrt_llm.models.CohereForCausalLM": [[82, 11, 1, "", "config_class"], [82, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.DbrxConfig": [[82, 12, 1, "", "to_dict"]], "tensorrt_llm.models.DbrxForCausalLM": [[82, 11, 1, "", "config_class"]], "tensorrt_llm.models.DecoderModel": [[82, 12, 1, "", "check_config"], [82, 12, 1, "", "forward"], [82, 12, 1, "", "precompute_relative_attention_bias"], [82, 12, 1, "", "prepare_inputs"], [82, 12, 1, "", "use_lora"]], "tensorrt_llm.models.DeepseekForCausalLM": [[82, 11, 1, "", "config_class"], [82, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.DeepseekV2ForCausalLM": [[82, 11, 1, "", "config_class"], [82, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.DiT": [[82, 12, 1, "", "check_config"], [82, 12, 1, "", "forward"], [82, 12, 1, "", "forward_with_cfg"], [82, 12, 1, "", "forward_without_cfg"], [82, 12, 1, "", "prepare_inputs"], [82, 12, 1, "", "unpatchify"]], "tensorrt_llm.models.EagleForCausalLM": [[82, 11, 1, "", "config_class"], [82, 12, 1, "", "forward"], [82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "prepare_inputs"]], "tensorrt_llm.models.EncoderModel": [[82, 12, 1, "", "check_config"], [82, 12, 1, "", "forward"], [82, 12, 1, "", "precompute_relative_attention_bias"], [82, 12, 1, "", "prepare_inputs"], [82, 12, 1, "", "use_lora"], [82, 12, 1, "", "use_prompt_tuning"]], "tensorrt_llm.models.FalconConfig": [[82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "to_dict"]], "tensorrt_llm.models.FalconForCausalLM": [[82, 12, 1, "", "check_config"], [82, 11, 1, "", "config_class"], [82, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.FalconModel": [[82, 12, 1, "", "forward"]], "tensorrt_llm.models.GPTConfig": [[82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "from_nemo"], [82, 12, 1, "", "to_dict"]], "tensorrt_llm.models.GPTForCausalLM": [[82, 11, 1, "", "config_class"], [82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "from_nemo"], [82, 12, 1, "", "quantize"], [82, 12, 1, "", "use_lora"]], "tensorrt_llm.models.GPTJConfig": [[82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "to_dict"]], "tensorrt_llm.models.GPTJForCausalLM": [[82, 11, 1, "", "config_class"], [82, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.GPTJModel": [[82, 12, 1, "", "forward"]], "tensorrt_llm.models.GPTModel": [[82, 12, 1, "", "forward"]], "tensorrt_llm.models.GPTNeoXModel": [[82, 12, 1, "", "forward"]], "tensorrt_llm.models.GemmaConfig": [[82, 11, 1, "", "GEMMA2_ADDED_FIELDS"], [82, 11, 1, "", "GEMMA3_ADDED_FIELDS"], [82, 11, 1, "", "GEMMA_ADDED_FIELDS"], [82, 11, 1, "", "VERBATIM"], [82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "gemma2_config"], [82, 12, 1, "", "gemma3_config"], [82, 12, 1, "", "get_hf_config"], [82, 13, 1, "", "is_gemma_2"], [82, 13, 1, "", "is_gemma_3"], [82, 12, 1, "", "to_dict"]], "tensorrt_llm.models.GemmaForCausalLM": [[82, 11, 1, "", "NATIVE_QUANT_FLOW"], [82, 12, 1, "", "assert_valid_quant_algo"], [82, 11, 1, "", "config_class"], [82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "quantize"], [82, 12, 1, "", "use_lora"]], "tensorrt_llm.models.LLaMAConfig": [[82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "from_meta_ckpt"], [82, 12, 1, "", "to_dict"]], "tensorrt_llm.models.LLaMAForCausalLM": [[82, 11, 1, "", "config_class"], [82, 12, 1, "", "default_plugin_config"], [82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "from_meta_ckpt"], [82, 12, 1, "", "quantize"], [82, 12, 1, "", "use_lora"]], "tensorrt_llm.models.LLaMAModel": [[82, 12, 1, "", "forward"]], "tensorrt_llm.models.LlavaNextVisionConfig": [[82, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.LlavaNextVisionWrapper": [[82, 12, 1, "", "forward"], [82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "prepare_inputs"], [82, 12, 1, "", "save_checkpoint"]], "tensorrt_llm.models.MLLaMAForCausalLM": [[82, 11, 1, "", "config_class"], [82, 12, 1, "", "forward"], [82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "prepare_inputs"], [82, 12, 1, "", "use_lora"]], "tensorrt_llm.models.MPTForCausalLM": [[82, 12, 1, "", "check_config"]], "tensorrt_llm.models.MPTModel": [[82, 12, 1, "", "forward"]], "tensorrt_llm.models.MambaForCausalLM": [[82, 11, 1, "", "config_class"], [82, 12, 1, "", "forward"], [82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "prepare_inputs"]], "tensorrt_llm.models.MedusaConfig": [[82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "to_dict"]], "tensorrt_llm.models.MedusaForCausalLm": [[82, 11, 1, "", "config_class"], [82, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.OPTForCausalLM": [[82, 12, 1, "", "check_config"]], "tensorrt_llm.models.OPTModel": [[82, 12, 1, "", "forward"]], "tensorrt_llm.models.Phi3ForCausalLM": [[82, 11, 1, "", "config_class"], [82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "use_lora"]], "tensorrt_llm.models.Phi3Model": [[82, 12, 1, "", "forward"]], "tensorrt_llm.models.PhiForCausalLM": [[82, 12, 1, "", "check_config"], [82, 11, 1, "", "config_class"], [82, 12, 1, "", "from_hugging_face"], [82, 12, 1, "", "use_lora"]], "tensorrt_llm.models.PhiModel": [[82, 12, 1, "", "forward"]], "tensorrt_llm.models.PretrainedConfig": [[82, 12, 1, "", "create_runtime_defaults"], [82, 12, 1, "", "for_each_rank"], [82, 12, 1, "", "from_checkpoint"], [82, 12, 1, "", "from_dict"], [82, 12, 1, "", "from_json_file"], [82, 12, 1, "", "get_config_group"], [82, 12, 1, "", "has_config_group"], [82, 13, 1, "", "kv_dtype"], [82, 13, 1, "", "quant_algo"], [82, 13, 1, "", "quant_mode"], [82, 12, 1, "", "set_if_not_exist"], [82, 12, 1, "", "set_rank"], [82, 12, 1, "", "to_dict"], [82, 12, 1, "", "to_json_file"], [82, 12, 1, "", "to_layer_quant_config"]], "tensorrt_llm.models.PretrainedModel": [[82, 12, 1, "", "check_config"], [82, 12, 1, "", "from_checkpoint"], [82, 12, 1, "", "from_config"], [82, 12, 1, "", "load"], [82, 12, 1, "", "prepare_inputs"], [82, 12, 1, "", "quantize"], [82, 12, 1, "", "release"], [82, 12, 1, "", "save_checkpoint"]], "tensorrt_llm.models.RecurrentGemmaForCausalLM": [[82, 12, 1, "", "forward"], [82, 12, 1, "", "prepare_inputs"], [82, 12, 1, "", "prepare_recurrent_inputs"]], "tensorrt_llm.models.SD3Transformer2DModel": [[82, 13, 1, "", "attn_processors"], [82, 11, 1, "", "config_class"], [82, 12, 1, "", "disable_forward_chunking"], [82, 12, 1, "", "enable_forward_chunking"], [82, 12, 1, "", "forward"], [82, 12, 1, "", "from_pretrained"], [82, 12, 1, "", "fuse_qkv_projections"], [82, 12, 1, "", "load"], [82, 12, 1, "", "prepare_inputs"], [82, 12, 1, "", "set_attn_processor"], [82, 12, 1, "", "unfuse_qkv_projections"]], "tensorrt_llm.models.SpeculativeDecodingMode": [[82, 11, 1, "", "DRAFT_TOKENS_EXTERNAL"], [82, 11, 1, "", "EAGLE"], [82, 11, 1, "", "EXPLICIT_DRAFT_TOKENS"], [82, 11, 1, "", "LOOKAHEAD_DECODING"], [82, 11, 1, "", "MEDUSA"], [82, 11, 1, "", "NGRAM"], [82, 11, 1, "", "NONE"], [82, 11, 1, "", "USER_PROVIDED"], [82, 12, 1, "", "from_arguments"]], "tensorrt_llm.models.WhisperEncoder": [[82, 12, 1, "", "forward"], [82, 12, 1, "", "precompute_relative_attention_bias"], [82, 12, 1, "", "prepare_inputs"]], "tensorrt_llm.plugin": [[83, 10, 1, "", "PluginConfig"]], "tensorrt_llm.plugin.PluginConfig": [[83, 12, 1, "", "to_legacy_setting"]], "tensorrt_llm.quantization": [[84, 10, 1, "", "QuantAlgo"], [84, 10, 1, "", "QuantMode"], [84, 14, 1, "", "quantize_and_export"]], "tensorrt_llm.runtime": [[85, 10, 1, "", "ChatGLMGenerationSession"], [85, 10, 1, "", "EncDecModelRunner"], [85, 10, 1, "", "GenerationSequence"], [85, 10, 1, "", "GenerationSession"], [85, 10, 1, "", "KVCacheManager"], [85, 10, 1, "", "LogitsProcessor"], [85, 10, 1, "", "LogitsProcessorList"], [85, 10, 1, "", "ModelConfig"], [85, 10, 1, "", "ModelRunner"], [85, 10, 1, "", "ModelRunnerCpp"], [85, 10, 1, "", "MultimodalModelRunner"], [85, 10, 1, "", "QWenForCausalLMGenerationSession"], [85, 10, 1, "", "SamplingConfig"], [85, 10, 1, "", "Session"], [85, 10, 1, "", "StoppingCriteria"], [85, 10, 1, "", "StoppingCriteriaList"], [85, 10, 1, "", "TensorInfo"], [85, 14, 1, "", "decode_words_list"]], "tensorrt_llm.runtime.EncDecModelRunner": [[85, 12, 1, "", "encoder_run"], [85, 12, 1, "", "from_engine"], [85, 12, 1, "", "generate"], [85, 12, 1, "", "process_input"]], "tensorrt_llm.runtime.GenerationSequence": [[85, 12, 1, "", "get_batch_idx"], [85, 12, 1, "", "get_seq_idx"]], "tensorrt_llm.runtime.GenerationSession": [[85, 11, 1, "", "batch_size"], [85, 11, 1, "", "buffer_allocated"], [85, 13, 1, "", "context_mem_size"], [85, 13, 1, "", "conv_kernel"], [85, 13, 1, "", "cross_attention"], [85, 11, 1, "", "cuda_graph_mode"], [85, 12, 1, "", "cuda_stream_guard"], [85, 11, 1, "", "debug_mode"], [85, 11, 1, "", "debug_tensors_to_save"], [85, 12, 1, "", "decode"], [85, 12, 1, "", "decode_batch"], [85, 12, 1, "", "decode_regular"], [85, 12, 1, "", "decode_stream"], [85, 11, 1, "", "device"], [85, 13, 1, "", "dtype"], [85, 12, 1, "", "dump_debug_buffers"], [85, 12, 1, "", "early_stop_criteria"], [85, 13, 1, "", "engine_inspector"], [85, 12, 1, "", "filter_medusa_logits"], [85, 12, 1, "", "finalize_decoder"], [85, 12, 1, "", "find_best_medusa_path"], [85, 13, 1, "", "first_layer"], [85, 13, 1, "", "gather_context_logits"], [85, 13, 1, "", "gather_generation_logits"], [85, 13, 1, "", "gemm_allreduce_plugin"], [85, 12, 1, "", "get_next_medusa_tokens"], [85, 12, 1, "", "get_num_heads_kv"], [85, 12, 1, "", "handle_per_step"], [85, 13, 1, "", "has_position_embedding"], [85, 13, 1, "", "has_token_type_embedding"], [85, 13, 1, "", "head_size"], [85, 13, 1, "", "hidden_size"], [85, 13, 1, "", "is_medusa_mode"], [85, 13, 1, "", "is_redrafter_mode"], [85, 13, 1, "", "kv_cache_type"], [85, 13, 1, "", "last_layer"], [85, 12, 1, "", "locate_accepted_draft_tokens"], [85, 11, 1, "", "mapping"], [85, 13, 1, "", "max_draft_tokens"], [85, 13, 1, "", "max_prompt_embedding_table_size"], [85, 12, 1, "", "medusa_decode_and_verify"], [85, 11, 1, "", "medusa_paths"], [85, 11, 1, "", "medusa_position_offsets"], [85, 11, 1, "", "medusa_temperature"], [85, 11, 1, "", "medusa_topks"], [85, 11, 1, "", "medusa_tree_ids"], [85, 12, 1, "", "next_medusa_input_ids"], [85, 11, 1, "", "num_draft_tokens"], [85, 13, 1, "", "num_heads"], [85, 13, 1, "", "num_layers"], [85, 13, 1, "", "num_medusa_heads"], [85, 13, 1, "", "paged_kv_cache"], [85, 13, 1, "", "paged_state"], [85, 12, 1, "", "pp_communicate_final_output_ids"], [85, 12, 1, "", "pp_communicate_new_tokens"], [85, 12, 1, "", "process_logits_including_draft"], [85, 13, 1, "", "profiler"], [85, 13, 1, "", "quant_mode"], [85, 13, 1, "", "remove_input_padding"], [85, 12, 1, "", "reorder_kv_cache_for_beam_search"], [85, 13, 1, "", "rnn_conv_dim_size"], [85, 13, 1, "", "rnn_head_size"], [85, 13, 1, "", "rnn_hidden_size"], [85, 11, 1, "", "runtime"], [85, 12, 1, "", "setup"], [85, 13, 1, "", "state_dtype"], [85, 13, 1, "", "state_size"], [85, 13, 1, "", "tokens_per_block"], [85, 12, 1, "", "update_output_ids_by_offset"], [85, 13, 1, "", "use_gemm_allreduce_plugin"], [85, 13, 1, "", "use_gpt_attention_plugin"], [85, 13, 1, "", "use_kv_cache"], [85, 13, 1, "", "use_lora_plugin"], [85, 13, 1, "", "use_mamba_conv1d_plugin"], [85, 13, 1, "", "vocab_size"]], "tensorrt_llm.runtime.KVCacheManager": [[85, 12, 1, "", "add_sequence"], [85, 12, 1, "", "get_block_offsets"], [85, 12, 1, "", "step"]], "tensorrt_llm.runtime.ModelConfig": [[85, 11, 1, "", "conv_kernel"], [85, 11, 1, "", "cross_attention"], [85, 11, 1, "", "dtype"], [85, 11, 1, "", "gather_context_logits"], [85, 11, 1, "", "gather_generation_logits"], [85, 11, 1, "", "gemm_allreduce_plugin"], [85, 11, 1, "", "gpt_attention_plugin"], [85, 11, 1, "", "gpu_weights_percent"], [85, 11, 1, "", "has_position_embedding"], [85, 11, 1, "", "has_token_type_embedding"], [85, 11, 1, "", "head_size"], [85, 11, 1, "", "hidden_size"], [85, 11, 1, "", "kv_cache_type"], [85, 11, 1, "", "language_adapter_config"], [85, 11, 1, "", "layer_types"], [85, 11, 1, "", "lora_plugin"], [85, 11, 1, "", "lora_target_modules"], [85, 11, 1, "", "mamba_conv1d_plugin"], [85, 11, 1, "", "max_batch_size"], [85, 11, 1, "", "max_beam_width"], [85, 11, 1, "", "max_medusa_tokens"], [85, 11, 1, "", "max_prompt_embedding_table_size"], [85, 11, 1, "", "model_name"], [85, 11, 1, "", "num_heads"], [85, 11, 1, "", "num_kv_heads"], [85, 11, 1, "", "num_kv_heads_per_cross_attn_layer"], [85, 11, 1, "", "num_kv_heads_per_layer"], [85, 11, 1, "", "num_layers"], [85, 11, 1, "", "num_medusa_heads"], [85, 11, 1, "", "paged_state"], [85, 11, 1, "", "quant_mode"], [85, 11, 1, "", "redrafter_draft_len_per_beam"], [85, 11, 1, "", "redrafter_num_beams"], [85, 11, 1, "", "remove_input_padding"], [85, 11, 1, "", "rnn_conv_dim_size"], [85, 11, 1, "", "rnn_head_size"], [85, 11, 1, "", "rnn_hidden_size"], [85, 11, 1, "", "skip_cross_attn_blocks"], [85, 11, 1, "", "skip_cross_kv"], [85, 11, 1, "", "state_dtype"], [85, 11, 1, "", "state_size"], [85, 11, 1, "", "tokens_per_block"], [85, 11, 1, "", "trtllm_modules_to_hf_modules"], [85, 11, 1, "", "vocab_size"]], "tensorrt_llm.runtime.ModelRunner": [[85, 13, 1, "", "dtype"], [85, 12, 1, "", "from_dir"], [85, 12, 1, "", "from_engine"], [85, 13, 1, "", "gather_context_logits"], [85, 13, 1, "", "gather_generation_logits"], [85, 12, 1, "", "generate"], [85, 13, 1, "", "hidden_size"], [85, 13, 1, "", "mapping"], [85, 13, 1, "", "max_prompt_embedding_table_size"], [85, 13, 1, "", "max_sequence_length"], [85, 13, 1, "", "num_heads"], [85, 13, 1, "", "num_layers"], [85, 13, 1, "", "remove_input_padding"], [85, 12, 1, "", "serialize_engine"], [85, 13, 1, "", "use_lora_plugin"], [85, 13, 1, "", "vocab_size"], [85, 13, 1, "", "vocab_size_padded"]], "tensorrt_llm.runtime.ModelRunnerCpp": [[85, 13, 1, "", "dtype"], [85, 12, 1, "", "from_dir"], [85, 13, 1, "", "gather_context_logits"], [85, 13, 1, "", "gather_generation_logits"], [85, 12, 1, "", "generate"], [85, 13, 1, "", "hidden_size"], [85, 13, 1, "", "max_prompt_embedding_table_size"], [85, 13, 1, "", "max_sequence_length"], [85, 13, 1, "", "num_heads"], [85, 13, 1, "", "num_layers"], [85, 13, 1, "", "remove_input_padding"], [85, 13, 1, "", "vocab_size"], [85, 13, 1, "", "vocab_size_padded"]], "tensorrt_llm.runtime.MultimodalModelRunner": [[85, 13, 1, "", "audio_engine_dir"], [85, 13, 1, "", "cpp_e2e"], [85, 13, 1, "", "cpp_llm_only"], [85, 12, 1, "", "generate"], [85, 12, 1, "", "get_audio_features"], [85, 12, 1, "", "get_rope_index"], [85, 12, 1, "", "get_visual_features"], [85, 12, 1, "", "init_audio_encoder"], [85, 12, 1, "", "init_image_encoder"], [85, 12, 1, "", "init_llm"], [85, 12, 1, "", "init_processor"], [85, 12, 1, "", "init_tokenizer"], [85, 13, 1, "", "llm_engine_dir"], [85, 12, 1, "", "load_test_audio"], [85, 12, 1, "", "load_test_data"], [85, 12, 1, "", "prepare_position_ids_for_cogvlm"], [85, 12, 1, "", "preprocess"], [85, 12, 1, "", "ptuning_setup"], [85, 12, 1, "", "ptuning_setup_fuyu"], [85, 12, 1, "", "ptuning_setup_llava_next"], [85, 12, 1, "", "ptuning_setup_phi3"], [85, 12, 1, "", "ptuning_setup_pixtral"], [85, 13, 1, "", "python_e2e"], [85, 12, 1, "", "run"], [85, 12, 1, "", "setup_fake_prompts"], [85, 12, 1, "", "setup_fake_prompts_qwen2vl"], [85, 12, 1, "", "setup_fake_prompts_vila"], [85, 12, 1, "", "setup_inputs"], [85, 12, 1, "", "split_prompt_by_images"], [85, 12, 1, "", "tokenizer_image_token"], [85, 12, 1, "", "video_preprocess"], [85, 13, 1, "", "visual_engine_dir"]], "tensorrt_llm.runtime.QWenForCausalLMGenerationSession": [[85, 12, 1, "", "generate"]], "tensorrt_llm.runtime.SamplingConfig": [[85, 11, 1, "", "bad_words_list"], [85, 11, 1, "", "beam_search_diversity_rate"], [85, 11, 1, "", "early_stopping"], [85, 11, 1, "", "end_id"], [85, 11, 1, "", "frequency_penalty"], [85, 11, 1, "", "length_penalty"], [85, 11, 1, "", "max_attention_window_size"], [85, 11, 1, "", "max_new_tokens"], [85, 11, 1, "", "min_length"], [85, 11, 1, "", "min_p"], [85, 11, 1, "", "no_repeat_ngram_size"], [85, 11, 1, "", "num_beams"], [85, 11, 1, "", "num_return_sequences"], [85, 11, 1, "", "output_cum_log_probs"], [85, 11, 1, "", "output_log_probs"], [85, 11, 1, "", "output_sequence_lengths"], [85, 11, 1, "", "pad_id"], [85, 11, 1, "", "presence_penalty"], [85, 11, 1, "", "random_seed"], [85, 11, 1, "", "repetition_penalty"], [85, 11, 1, "", "return_dict"], [85, 11, 1, "", "sink_token_length"], [85, 11, 1, "", "stop_words_list"], [85, 11, 1, "", "temperature"], [85, 11, 1, "", "top_k"], [85, 11, 1, "", "top_p"], [85, 11, 1, "", "top_p_decay"], [85, 11, 1, "", "top_p_min"], [85, 11, 1, "", "top_p_reset_ids"], [85, 12, 1, "", "update"], [85, 11, 1, "", "use_beam_hyps"]], "tensorrt_llm.runtime.Session": [[85, 13, 1, "", "context"], [85, 13, 1, "", "context_mem_size"], [85, 13, 1, "", "engine"], [85, 12, 1, "", "from_engine"], [85, 12, 1, "", "from_serialized_engine"], [85, 12, 1, "", "infer_shapes"], [85, 12, 1, "", "run"], [85, 13, 1, "", "runtime"], [85, 12, 1, "", "set_shapes"]], "tensorrt_llm.runtime.TensorInfo": [[85, 11, 1, "", "dtype"], [85, 11, 1, "", "name"], [85, 12, 1, "", "numel"], [85, 11, 1, "", "shape"], [85, 12, 1, "", "squeeze"], [85, 12, 1, "", "view"]], "trtllm-serve-disaggregated": [[34, 17, 1, "cmdoption-trtllm-serve-disaggregated-c", "--config_file"], [34, 17, 1, "cmdoption-trtllm-serve-disaggregated-l", "--log_level"], [34, 17, 1, "cmdoption-trtllm-serve-disaggregated-m", "--metadata_server_config_file"], [34, 17, 1, "cmdoption-trtllm-serve-disaggregated-r", "--request_timeout"], [34, 17, 1, "cmdoption-trtllm-serve-disaggregated-t", "--server_start_timeout"], [34, 17, 1, "cmdoption-trtllm-serve-disaggregated-c", "-c"], [34, 17, 1, "cmdoption-trtllm-serve-disaggregated-l", "-l"], [34, 17, 1, "cmdoption-trtllm-serve-disaggregated-m", "-m"], [34, 17, 1, "cmdoption-trtllm-serve-disaggregated-r", "-r"], [34, 17, 1, "cmdoption-trtllm-serve-disaggregated-t", "-t"]], "trtllm-serve-disaggregated_mpi_worker": [[34, 17, 1, "cmdoption-trtllm-serve-disaggregated_mpi_worker-c", "--config_file"], [34, 17, 1, "cmdoption-trtllm-serve-disaggregated_mpi_worker-log_level", "--log_level"], [34, 17, 1, "cmdoption-trtllm-serve-disaggregated_mpi_worker-c", "-c"]], "trtllm-serve-serve": [[34, 17, 1, "cmdoption-trtllm-serve-serve-backend", "--backend"], [34, 17, 1, "cmdoption-trtllm-serve-serve-cluster_size", "--cluster_size"], [34, 17, 1, "cmdoption-trtllm-serve-serve-ep_size", "--ep_size"], [34, 17, 1, "cmdoption-trtllm-serve-serve-extra_llm_api_options", "--extra_llm_api_options"], [34, 17, 1, "cmdoption-trtllm-serve-serve-gpus_per_node", "--gpus_per_node"], [34, 17, 1, "cmdoption-trtllm-serve-serve-host", "--host"], [34, 17, 1, "cmdoption-trtllm-serve-serve-kv_cache_free_gpu_memory_fraction", "--kv_cache_free_gpu_memory_fraction"], [34, 17, 1, "cmdoption-trtllm-serve-serve-log_level", "--log_level"], [34, 17, 1, "cmdoption-trtllm-serve-serve-max_batch_size", "--max_batch_size"], [34, 17, 1, "cmdoption-trtllm-serve-serve-max_beam_width", "--max_beam_width"], [34, 17, 1, "cmdoption-trtllm-serve-serve-max_num_tokens", "--max_num_tokens"], [34, 17, 1, "cmdoption-trtllm-serve-serve-max_seq_len", "--max_seq_len"], [34, 17, 1, "cmdoption-trtllm-serve-serve-metadata_server_config_file", "--metadata_server_config_file"], [34, 17, 1, "cmdoption-trtllm-serve-serve-num_postprocess_workers", "--num_postprocess_workers"], [34, 17, 1, "cmdoption-trtllm-serve-serve-port", "--port"], [34, 17, 1, "cmdoption-trtllm-serve-serve-pp_size", "--pp_size"], [34, 17, 1, "cmdoption-trtllm-serve-serve-reasoning_parser", "--reasoning_parser"], [34, 17, 1, "cmdoption-trtllm-serve-serve-server_role", "--server_role"], [34, 17, 1, "cmdoption-trtllm-serve-serve-tokenizer", "--tokenizer"], [34, 17, 1, "cmdoption-trtllm-serve-serve-tp_size", "--tp_size"], [34, 17, 1, "cmdoption-trtllm-serve-serve-trust_remote_code", "--trust_remote_code"], [34, 17, 1, "cmdoption-trtllm-serve-serve-arg-MODEL", "MODEL"]]}, "objnames": {"0": ["c", "macro", "C macro"], "1": ["cpp", "type", "C++ type"], "2": ["cpp", "class", "C++ class"], "3": ["cpp", "function", "C++ function"], "4": ["cpp", "functionParam", "C++ function parameter"], "5": ["cpp", "member", "C++ member"], "6": ["cpp", "enum", "C++ enum"], "7": ["cpp", "enumerator", "C++ enumerator"], "8": ["cpp", "templateParam", "C++ template parameter"], "9": ["py", "module", "Python module"], "10": ["py", "class", "Python class"], "11": ["py", "attribute", "Python attribute"], "12": ["py", "method", "Python method"], "13": ["py", "property", "Python property"], "14": ["py", "function", "Python function"], "15": ["py", "pydantic_field", "Python field"], "16": ["py", "pydantic_validator", "Python validator"], "17": ["std", "cmdoption", "program option"]}, "objtypes": {"0": "c:macro", "1": "cpp:type", "2": "cpp:class", "3": "cpp:function", "4": "cpp:functionParam", "5": "cpp:member", "6": "cpp:enum", "7": "cpp:enumerator", "8": "cpp:templateParam", "9": "py:module", "10": "py:class", "11": "py:attribute", "12": "py:method", "13": "py:property", "14": "py:function", "15": "py:pydantic_field", "16": "py:pydantic_validator", "17": "std:cmdoption"}, "terms": {"": [0, 1, 2, 3, 4, 6, 7, 8, 13, 15, 16, 17, 18, 19, 20, 21, 22, 24, 25, 27, 28, 29, 30, 31, 32, 33, 35, 46, 47, 50, 51, 55, 63, 68, 69, 71, 73, 75, 76, 77, 78, 80, 81, 82, 85, 86, 87, 89, 90, 92, 93, 94, 96, 97, 98, 103], "0": [0, 1, 2, 3, 5, 6, 7, 9, 10, 13, 14, 16, 17, 18, 20, 21, 23, 24, 26, 27, 28, 29, 30, 31, 32, 33, 34, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 53, 54, 55, 56, 57, 59, 60, 62, 63, 64, 65, 67, 68, 69, 70, 71, 72, 73, 77, 78, 79, 80, 81, 82, 85, 86, 88, 89, 91, 92, 95, 96, 102, 104], "00": [17, 27, 52, 53, 54, 71, 72, 73, 92], "000": [21, 71], "0000": [71, 73], "0007503032684326172": 34, "0012": 71, "0017": 72, "003": 72, "0047": 92, "005": 72, "0070": 92, "0071": 92, "0096": 92, "00978": 90, "01": [26, 27, 52, 53, 54, 56, 71, 72, 89, 93], "0105": 21, "014": 24, "0158": 73, "016": 72, "0162": 75, "0165": 77, "017": 72, "02": [72, 93], "021": 72, "022": 72, "0235": 92, "0260": 92, "0273": 92, "028": 72, "0294": 92, "03": [77, 92, 93], "032": 27, "0339": 72, "03762": 80, "03961": 4, "03x": 28, "04": [65, 72, 93, 95, 100], "043": 72, "0449": 92, "045471": 30, "0461": 21, "0463": 72, "05": [72, 80, 81, 82, 91, 92, 93], "05100": 80, "0523": 92, "055": 72, "0554": 73, "0560": 92, "0563": 72, "06": [27, 71, 72, 80, 81], "0630": 92, "0669": 21, "0675": 21, "068": 72, "0682": 92, "0689e": 71, "07": [26, 27, 72, 93], "0704": 73, "0713": 92, "0723": 92, "0732": 92, "0772": 21, "0776": 92, "08": [27, 72, 77], "0804": 92, "081947": 30, "082": 72, "0838": [21, 72], "0881": 78, "089": 72, "09": [27, 92], "0903": 92, "0910": 92, "092": 72, "092314": 30, "092623": 30, "093256": 30, "09353": 10, "0964": 72, "09685": 10, "097": 72, "09f": [0, 1], "0b": 2, "0e": 6, "0f": [0, 6, 68], "0rc1": 71, "0rc3": [64, 86], "0u": 1, "0x": 23, "0x0000000000000000": 93, "1": [0, 1, 2, 3, 5, 6, 7, 9, 10, 13, 14, 16, 18, 20, 22, 23, 24, 25, 26, 27, 28, 29, 31, 33, 34, 37, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 55, 56, 57, 59, 60, 62, 64, 65, 68, 70, 71, 73, 74, 75, 77, 79, 80, 81, 82, 84, 85, 86, 87, 88, 91, 92, 94, 100, 101, 102, 103], "10": [0, 9, 10, 13, 21, 26, 27, 28, 30, 31, 34, 40, 42, 51, 56, 62, 65, 68, 71, 72, 73, 75, 78, 80, 89, 91, 92], "100": [0, 9, 12, 21, 30, 34, 42, 53, 70, 71, 73, 86], "1000": [0, 32, 70, 71, 72, 73], "10000": [80, 81, 82], "1003": 93, "100gb": 29, "101": 9, "101029": 30, "101978": 72, "102": [9, 23], "1024": [1, 6, 16, 21, 24, 26, 30, 32, 33, 40, 68, 71, 72, 73, 77, 80, 81, 92], "102415": 71, "103": [9, 30], "104": 93, "10438": 90, "1045": 92, "1047": 71, "1050": 92, "1051": 73, "1059": 71, "106563": 72, "1072": 92, "107501": 72, "10774": 0, "1079": 20, "108": 72, "1082": 92, "10858": 40, "109": 30, "10b": [80, 93], "10m": 23, "11": [0, 10, 13, 21, 24, 26, 30, 31, 62, 71, 72, 75, 80, 91, 92], "11023": 71, "110804": 72, "110b": 93, "111": [23, 27], "111302": 72, "111618": 72, "111668": 72, "1118": 93, "1123": 93, "1134": 89, "113420": 30, "1135": 92, "114": 30, "1141": 92, "114688": 21, "1148": 93, "11489": 21, "11490": 71, "115": 30, "1151": 21, "115378": 30, "115716": 72, "1160": [34, 41], "117": 72, "1178": 71, "1181": 93, "1183": 93, "119": [30, 71], "11943": 71, "11947": 40, "1196": 21, "119648": 30, "11b": [91, 93], "11x": 31, "12": [0, 10, 16, 23, 27, 30, 31, 32, 40, 62, 65, 71, 72, 75, 77, 80, 92, 100], "120": 30, "1212": 92, "121847": 71, "1219": 21, "122": 71, "1225": 80, "12288": 71, "123": [34, 42, 43], "1234": [68, 82], "1239": 93, "1242": 93, "1248": 93, "125": [30, 71], "1252": [20, 71], "1256": 93, "1257": 21, "125m": [13, 16], "126": 71, "1267": 93, "127": 80, "1272": 92, "128": [0, 1, 5, 9, 10, 14, 17, 21, 22, 23, 24, 25, 26, 27, 30, 34, 40, 42, 43, 53, 68, 71, 72, 82, 93], "1284": 93, "1287": 75, "128798": 68, "128799": 68, "128e": 32, "129": 30, "1290": 92, "1291504": 73, "1293": 20, "12945": 21, "129498": 21, "13": [5, 10, 25, 29, 30, 31, 62, 71, 72, 73, 80, 92], "1300": 46, "131072": [71, 73], "13195": 71, "132": [71, 72], "1323": 93, "1328": 93, "1329": 93, "133": 93, "13368": 71, "1337": 93, "1341": 21, "1343": 93, "1344": 93, "13525": 71, "13598": 71, "137": 71, "1378": 92, "138": 30, "139": 72, "1392": 93, "13b": 23, "14": [10, 16, 26, 30, 31, 62, 71, 72, 75, 77, 78, 92], "140g": 20, "141": 24, "1418": 71, "141gb": [22, 72], "142": [29, 30], "1424": 93, "1436": [21, 93], "1437": 92, "144": 75, "1446": 93, "1447": 93, "14480": 71, "1449": 93, "145": [77, 78], "1459": 92, "146": [77, 78], "1467": 93, "147": [73, 75, 77, 78], "1480": 93, "1486": 93, "149": [92, 93], "15": [10, 27, 30, 31, 32, 62, 71, 72, 78, 80, 92], "150": 70, "1500": 72, "15043": 40, "1514": 93, "152": [30, 71], "1529": 93, "1534": 93, "1535": 93, "1536": 21, "1537": 93, "1539": 93, "154": 27, "1552": 93, "1556": 92, "15585": 71, "1562": 93, "1564": [73, 77, 78], "158": 21, "1583": 93, "1584": 21, "1585": 73, "1589": 93, "1590": 93, "1597": 75, "15u": 29, "16": [0, 5, 10, 11, 13, 17, 21, 23, 26, 27, 30, 31, 34, 37, 39, 52, 53, 54, 62, 63, 71, 72, 73, 74, 80, 81, 82, 89, 90, 92], "160": [30, 93], "1607": 71, "161": [34, 41, 71], "162": 30, "1625": 75, "1626": 93, "163": 22, "1637": 93, "16384": [75, 77], "164": [27, 30], "1642": 93, "1650": 93, "1660": 93, "1669": 93, "167": [71, 72], "1672": 92, "1674": 93, "1675": 93, "167507": 30, "1676": 93, "168": 27, "16e": 91, "16x": [28, 89], "17": [0, 2, 10, 21, 30, 32, 62, 71, 72, 77, 92, 95], "1706": 80, "171": 30, "1721": 92, "1723": 93, "172321": 21, "17233": 21, "173": 27, "1732": 93, "17323": 90, "1738": 93, "174": 72, "1741966075": 86, "1742": 93, "17453": 33, "17453v3": 1, "1748018634": 32, "175": 72, "175b": 24, "176": 71, "1762": 93, "1799": 93, "17b": [32, 91], "18": [2, 10, 29, 30, 62, 69, 71, 72, 92], "180": [27, 89], "180000000": 0, "1806": 21, "180b": [26, 71], "1815": 93, "181540": 21, "182": 72, "1822": 40, "183": 72, "1834": 93, "184": 72, "185": [23, 71], "1851": 93, "18527": 40, "18563": 71, "1861": 78, "1866": 78, "187": 30, "1885": 73, "1886": 93, "1897": 93, "19": [2, 21, 30, 62, 72, 78, 92], "1909": 93, "191": 72, "192": [22, 30], "1926": 93, "1937": 93, "1939": 93, "1944": 77, "1950": 30, "1953": 93, "1959": 71, "1963": 30, "198": 27, "1985": 93, "1987": 93, "1993": 92, "1999": 93, "1_405b": 17, "1_70b": 17, "1b": [31, 34, 37, 39, 42, 44, 46, 47, 48, 49, 50, 51, 55, 57, 59, 65, 67, 86], "1d": [5, 80, 85], "1e": [16, 80, 81, 82], "1e20f": 1, "1g": 92, "1gb": 2, "1k": [21, 27, 28, 29], "1m": 78, "1st": [23, 80, 89], "1u": [0, 1], "1x": 27, "1xh200": 22, "1xtep": 31, "1ytic": 93, "2": [0, 1, 3, 5, 6, 7, 8, 9, 10, 11, 13, 14, 16, 17, 20, 22, 23, 24, 26, 27, 28, 29, 31, 34, 49, 50, 51, 52, 53, 54, 55, 62, 65, 68, 71, 72, 74, 75, 77, 78, 80, 82, 85, 87, 90, 91, 92, 94, 103], "20": [1, 6, 13, 14, 29, 30, 31, 34, 57, 59, 60, 71, 72, 73, 77, 80, 85, 92], "200": [24, 30, 32, 51, 68, 85], "2000": [29, 72], "20000": [68, 72], "200mb": 29, "2017": 77, "2018": 93, "202": 30, "2023": [22, 92], "2024": [27, 100], "2025": [21, 27, 71], "2028": 93, "203": 72, "2033": 78, "2039": 93, "204": [27, 72], "2040": 93, "2042": 21, "2044": [77, 78], "2045": 77, "2048": [16, 21, 22, 24, 25, 29, 33, 68, 71, 72, 73, 75, 76, 77, 78, 82, 85, 92, 93], "205": 30, "2056": 93, "206": 72, "20627": 40, "20685": 71, "2079": 92, "208": 72, "2081": [75, 77, 93], "2087": 93, "2089": 72, "209": [30, 72], "20b": 93, "21": [13, 21, 26, 27, 30, 72, 77, 92, 93], "2101": 4, "2102": 72, "2106": 10, "2107": 92, "210g": 20, "211": 27, "2113": 93, "212": 30, "2135": 93, "2152": 93, "2158": 72, "2168": 21, "2169": 93, "21747": 71, "2176": 72, "21764": 71, "2182": 93, "2191": 93, "22": [29, 30, 36, 72, 80, 92], "22000": 72, "22056": 71, "221": 71, "2210": 90, "2211": [80, 90], "2219": 93, "22213": 71, "2225": 92, "2232": 93, "224": 81, "2243": 93, "2263": 93, "227": 25, "2288": 93, "2294": 93, "22x": 28, "23": [30, 71, 72, 92, 93], "2305": 92, "2306": 90, "2309": [1, 33], "232": [25, 30], "234": 30, "2352": 93, "2357": 93, "236": 27, "2366": 93, "2370": 93, "2373": 93, "2379": 93, "2388": 93, "239": 27, "2397": 71, "24": [0, 30, 65, 71, 72, 92, 93, 95], "240": 72, "2401": 0, "2402": 10, "24189": 72, "2419": 93, "242": 72, "2425": 93, "243": 30, "2439": 93, "245": 27, "2458": 93, "246": 30, "2461": 77, "2466": 77, "2473": 93, "2474": [75, 77], "2484": 93, "2485": 93, "2487": 72, "249": 27, "24mib": 30, "25": [25, 27, 30, 31, 71, 72, 91, 93], "250": [21, 27, 30], "2500": 72, "25032": 71, "251": 30, "252u": 29, "253": [27, 72], "2552": 93, "256": [1, 21, 22, 25, 29, 30, 68, 71, 72, 80, 92, 93], "25603": 71, "2573": 93, "2581": [75, 77], "2590780": 71, "259840": 89, "26": [30, 71, 72, 75, 86], "260": 72, "2602": 40, "2628": [77, 78], "263": [22, 40], "2640": 78, "2649": 92, "2671": 21, "2677": 93, "26778": 71, "2679": 75, "2685": 93, "2691": 93, "27": [72, 93], "270": 72, "2712": 93, "274": [21, 93], "2742": 73, "275": 93, "2755": 21, "276": 72, "2766684": 21, "278": [40, 72], "2782": 93, "2787": 93, "2796": 93, "28": [27, 71, 72, 92], "2820": 92, "28390": 71, "287113": 71, "288": [30, 93], "29": [72, 89], "290": 30, "292": 72, "2939": 92, "294": 72, "297": 40, "29892": 40, "299": [27, 71], "29962": 40, "2998": 92, "2b": [20, 62, 71], "2cta": 29, "2d": [13, 80, 81, 90], "2k": [21, 27, 28, 29], "2m": 78, "2nd": 80, "2u": 1, "2x": [23, 24, 31], "2xdep": 31, "3": [0, 1, 3, 5, 7, 9, 10, 18, 22, 23, 24, 26, 27, 28, 29, 44, 47, 49, 55, 56, 62, 65, 67, 68, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 85, 86, 88, 92, 93, 96, 99, 101, 102], "30": [0, 13, 21, 27, 31, 32, 68, 72, 73, 75, 78, 80, 89], "300": [25, 30, 71], "3000": [71, 72], "30000": 72, "30065": 71, "3019": 71, "3021": 21, "3022": 71, "303": 24, "3031": 77, "304": 40, "3040": [73, 77, 78], "306": 40, "3072": 21, "30990": 71, "30b": 26, "30x": 26, "31": [11, 72, 73, 77, 78], "311": 72, "3132": 71, "315": [27, 72], "318": 72, "32": [1, 5, 9, 11, 21, 23, 24, 30, 31, 33, 40, 68, 71, 72, 73, 80, 81, 82, 85, 86, 89, 90, 92, 93], "3201": 73, "321": 71, "322": 40, "3276": [73, 77, 78], "32768": 80, "3291": 92, "32b": 93, "32k": 93, "32x": 26, "33": [72, 92], "332": 72, "3328": 92, "332826": 21, "3338": 73, "338": [27, 40], "3389": 75, "339447": 30, "339981": 30, "33x": 28, "34": [21, 30, 72], "340": [27, 72], "341": [24, 30], "3442": 92, "3445": 92, "3452": [71, 92], "3476": 21, "348gib": 30, "349": 24, "34b": 93, "35": [0, 68, 72], "3504": 30, "351": 72, "3555": 92, "357": 72, "36": [27, 30, 72, 74, 75], "36384": 21, "3671": 71, "367714": 30, "368": 27, "37": [30, 71], "370": 72, "371": 72, "374": 72, "375": 72, "3763": 27, "379": 72, "38": [71, 72], "381": 30, "384": [21, 72], "3863": 72, "387": 72, "387b12598a9e": 71, "3887": 92, "39": [27, 72], "3914": 72, "3936": 71, "3977": 92, "399": 72, "3_1": 91, "3_3": 91, "3b": [34, 38, 43, 58], "3d": [5, 80, 85], "3rd": 80, "3u": 1, "3x": [26, 27, 29], "4": [0, 1, 2, 7, 9, 10, 11, 13, 17, 20, 24, 26, 27, 28, 29, 30, 31, 34, 40, 52, 53, 54, 62, 68, 71, 72, 73, 75, 76, 77, 78, 79, 80, 82, 85, 86, 89, 90, 91, 92, 93, 94, 100], "40": [6, 72, 75, 80, 93], "400": [29, 30], "4000": 29, "403": 93, "405b": [71, 74], "4060": 89, "4066": 40, "408": 72, "408348": 30, "4089": 78, "4096": [22, 29, 40, 71, 72, 75, 80, 81, 85], "40b": 26, "40gb": 33, "40x": 26, "41": 72, "41020": 71, "411": 71, "4117e": 71, "4133": 78, "41375": 71, "414": 21, "41607": 71, "4168": 21, "4192": 92, "42": [30, 71, 72], "4224": 72, "4248": 75, "4265": 71, "427": [71, 72], "4280": 27, "43": [72, 86, 89], "43146": 21, "433": 72, "437": 72, "438": 72, "4384": 30, "44": [30, 72, 89], "4408": 40, "442": 72, "4439": 71, "4456": 72, "447": 72, "448": 72, "449": 93, "4493": [77, 78], "4495": 30, "4497": 72, "44x": 26, "45": [9, 30, 72, 91, 93], "450": 72, "45000000000": 9, "453": 72, "4548": 21, "4566": 72, "458676": 30, "459": 72, "46": 26, "4600": 29, "461014": 30, "462": 72, "463": 72, "464": 30, "4653": 40, "4656": 72, "466": 72, "4667": 72, "47": [26, 30, 75], "4701": 71, "471": 72, "472": 40, "475": 72, "477": 72, "478": 93, "47x": 26, "48": [30, 72, 75, 89, 93], "480gb": 30, "481": [23, 72], "482": 93, "488": 72, "49": [30, 72, 75], "491": 30, "49152": 21, "495": 72, "496": 11, "4963": 71, "4963654": 87, "498043": 30, "49b": 91, "4b": 93, "4bit": 22, "4gb": 29, "4u": 1, "4x": [22, 23, 24, 31], "5": [0, 1, 9, 10, 13, 14, 16, 22, 23, 24, 26, 27, 28, 29, 30, 31, 34, 38, 43, 46, 58, 68, 71, 72, 77, 80, 82, 85, 91, 92, 93, 102], "50": [0, 26, 30, 31, 46, 68, 71, 72, 93], "500": [27, 29, 72], "5000": 72, "500000": 82, "5007": 40, "500m": 26, "50272": 16, "505143404006958": 34, "5064": 72, "5073": 92, "50m": 30, "51": 72, "512": [1, 10, 14, 21, 24, 25, 68, 71, 72, 75, 77, 82], "5120": 21, "512mb": 2, "514": 72, "518": [40, 72], "51b": [91, 93], "51x": 26, "52": 30, "52269": 72, "524": 72, "525": 72, "526": [72, 93], "52667": 72, "529": 72, "529514": 30, "5299": 75, "53": [30, 71, 77, 78], "5305": 75, "531": 72, "535": 32, "537602": 30, "5393": 21, "54": [26, 72], "540": 71, "543": 72, "544": 72, "5443839": 21, "54576": 21, "5496": 75, "5497": 72, "55": [26, 71, 72], "5500": 72, "5510": 71, "5514": 71, "552": 32, "5530": 72, "554": 72, "557": 72, "559": 72, "56": [26, 30, 72], "560": 22, "562": [10, 14], "564": 30, "56401920000": 34, "564272": 30, "565": 72, "567": 72, "568": [71, 72], "57": [30, 71, 72], "570": 30, "571": 72, "572": 72, "5739": 21, "5742": [75, 77], "579": 72, "58": [27, 30, 72, 77], "580": 72, "5821": 72, "5830": 92, "5874": 92, "5877": 75, "5879": 92, "588": 72, "58x": 27, "59": [30, 71], "590": [40, 72], "5918": 92, "5957": 92, "5976": 75, "598": 72, "5980": 75, "5b": 93, "5th": [29, 80], "5u": 1, "5x": [23, 26, 27, 31], "6": [0, 1, 6, 9, 10, 13, 24, 26, 27, 28, 29, 30, 31, 34, 68, 72, 80, 85, 91, 92, 93], "60": [0, 30, 72], "600": 35, "6000": 71, "602": 72, "6049": 75, "6059": 71, "6064": 92, "608": 72, "61": 72, "610": 72, "6100": 21, "612328": 30, "6157": 92, "618": 72, "61954812": 88, "62": [27, 72, 77], "623219": 30, "6255": 92, "626": 40, "6299": 92, "63": [63, 71, 72, 77, 82, 89], "630": 72, "63266": 73, "63307": 73, "63308": 73, "63331": 73, "63374": 73, "634": 72, "63456": 73, "6345624": 73, "6372": 75, "6376": 21, "639": 93, "64": [0, 1, 5, 6, 16, 21, 23, 24, 30, 33, 34, 38, 43, 55, 58, 71, 72, 77, 80, 81, 82, 89, 93], "640": [22, 72], "640gb": 29, "6452": 78, "6475": 77, "649": 93, "64x": 27, "65": [65, 72], "65024": 92, "65100": 21, "651199": 30, "6523": 78, "653": 72, "654": 24, "6550": 75, "6554": 77, "656": 72, "657": 72, "659": 72, "6591": 71, "66": [27, 72], "661": 72, "6628": [77, 78], "6678": 89, "6684": 78, "6695": 89, "67": [26, 27, 30, 72], "671": 21, "67108864": [32, 63], "671b": 28, "673": 93, "675": 71, "6753e": 71, "6769": 77, "679": 23, "68": [26, 27, 72, 78], "682": 72, "6825": 71, "683": 72, "684": 27, "685": 72, "6852": [75, 77], "686": 72, "6862": 71, "6890": 92, "69": [26, 27, 30, 72, 78, 86], "6925": 71, "6938": 40, "695": 93, "696": 72, "697": 29, "6975": 75, "6976": [73, 77, 78], "698": 72, "6a": 22, "6b": [23, 71, 80, 93], "6x": [24, 31], "7": [0, 1, 9, 10, 22, 23, 26, 27, 28, 29, 30, 31, 62, 63, 65, 71, 72, 73, 80, 85, 92], "70": [0, 26, 30, 78, 89], "700": 35, "7000": 71, "701": 93, "7031": 75, "704": 72, "705": [29, 93], "706": 72, "7063": 71, "707": 72, "7072": 72, "709": 71, "7090": 92, "70b": [5, 20, 24, 26, 73, 75, 76, 77, 78, 79, 91, 93], "70g": 20, "71": [27, 71, 72], "711": 72, "712": 72, "7134": 92, "7136": 73, "714": 72, "7144": 92, "7168": [21, 27, 29], "717": 72, "717498": 30, "7187": 72, "7188": 21, "72": [30, 72, 74], "7206": 21, "722": 72, "727": 72, "728516": 30, "72b": [91, 93], "73": [27, 72], "732": 72, "734": 72, "736": 72, "737": 72, "7382": 72, "739": 93, "73x": 31, "74": [27, 72], "741": [72, 93], "742": 72, "745": 72, "7456": 21, "74561": 21, "747": 72, "7480": 73, "75": [26, 30, 32, 71, 93], "750": [24, 72], "7502": 73, "7520": 21, "755": 35, "7584": 21, "75903": 72, "76": 72, "7607": 77, "7621": 72, "7638": [73, 77, 78], "7657": 21, "767": 72, "768": [16, 81], "77": [30, 72], "772": 72, "7743": 73, "7770": 73, "78": [27, 72, 75], "780": 71, "7842": 75, "78509": 72, "7876": 77, "79": [71, 89], "7900": 92, "791": 30, "792": 30, "7933": 77, "794": [72, 93], "7949": 92, "7977": 75, "7a": 22, "7b": [10, 13, 14, 26, 34, 60, 71, 72, 86, 91, 93], "7x": [23, 27, 31], "8": [0, 1, 5, 9, 10, 11, 16, 17, 20, 21, 22, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 40, 41, 44, 47, 48, 49, 50, 51, 52, 53, 54, 62, 65, 68, 71, 72, 73, 74, 75, 79, 80, 81, 82, 86, 89, 90, 92, 94, 102], "80": [0, 6, 24, 27, 29, 63, 72, 93], "800": [22, 72, 93], "8000": [31, 32, 34, 37, 38, 39, 41, 42, 43, 57, 58, 59, 60, 86], "8001": 31, "8002": [31, 71], "8003": 31, "8004": 31, "8005": 72, "803": 22, "8048": 71, "80gb": [23, 26, 33, 72, 73, 75, 76], "81": [27, 30, 72, 75], "810": 72, "8140": 21, "8149": 92, "8179": 92, "819": 24, "8192": [33, 68, 71, 72, 73, 77, 80, 81, 92, 93], "82": [27, 72, 75], "820": 71, "8212": 1, "8218": 92, "822": 72, "8225": 75, "825": 93, "8259": 71, "83": 72, "8307": 78, "8351": 71, "838": 72, "84": [27, 72], "840": 72, "841": 72, "8441": 71, "85": [21, 26, 71, 72, 93], "850": 72, "851": 72, "854": 72, "86": [63, 72], "863": 71, "866": 72, "867": 72, "8672": 92, "87": [26, 30, 72], "8779": 92, "88": [72, 75, 78], "8804": 73, "880676": 30, "88226": 71, "8828": 92, "8841": 75, "89": [26, 27, 63, 72, 91], "893": 72, "8932": 71, "8958": 78, "896": [21, 72], "8a": 25, "8b": [44, 47, 56, 65, 67, 71, 86, 91, 101, 102], "8bit": 23, "8tb": 24, "8x": [29, 31, 32], "8x7b": [4, 71, 91, 93], "8xb200": [27, 32], "8xgpu": 29, "8xh100": 25, "8xh200": 22, "9": [0, 1, 10, 13, 20, 23, 27, 28, 30, 31, 62, 72, 75, 80, 88, 92], "90": [0, 12, 21, 30, 63, 68, 71, 72, 73, 75, 79, 89], "9007": 21, "9028": 92, "907": 23, "9087": 78, "91": 72, "910": 72, "9101": 72, "911": 72, "9115": 78, "912656": 21, "913": 72, "9184": 75, "9197": 21, "92": [27, 72], "920": 72, "9203": 75, "9214": 72, "924": 16, "925": 72, "9263": 21, "9274": 73, "93": [21, 30, 72], "935": 93, "9353e": 73, "9379": 21, "94": 72, "94022": 72, "941": [22, 25], "944": 72, "946": 22, "947": 72, "948": 30, "9494": 77, "95": [34, 41, 44, 47, 48, 49, 50, 51, 65, 72, 73, 79, 86], "9521": 92, "953": 72, "9537": 75, "954": 29, "955200": 30, "956": 72, "957": 72, "96": [22, 27, 29, 72, 75, 93], "960": 22, "9606": 29, "960gb": 30, "961": 72, "9613": 29, "9623": 77, "9629": 29, "963": 72, "9639": 72, "96583": 72, "967": 93, "9692": 92, "97": [29, 71, 72, 75], "970": 72, "976442": 30, "98": 72, "983": 93, "987": 93, "9898": 21, "99": [9, 27, 30, 35, 72], "990": 72, "991": 72, "992": 93, "9928": 78, "9938": 21, "9982": [77, 78], "9f": 0, "9x": [24, 25], "A": [0, 1, 2, 3, 5, 6, 8, 10, 13, 16, 17, 20, 21, 26, 27, 30, 32, 51, 52, 53, 54, 55, 67, 68, 70, 71, 72, 80, 85, 87, 93, 94, 96, 98], "AND": 80, "And": [13, 20, 28, 29, 30, 80, 81, 89], "As": [4, 5, 7, 10, 13, 17, 19, 28, 30, 31, 40, 63, 75, 78, 79, 80, 89, 90, 92, 98, 103], "At": [15, 29, 55, 75, 81, 89, 100], "Being": 87, "But": [5, 8, 30, 69], "By": [0, 1, 2, 6, 12, 13, 27, 29, 30, 31, 40, 63, 68, 71, 75, 78, 80, 88, 92, 98], "For": [0, 1, 2, 3, 5, 6, 7, 8, 9, 10, 12, 13, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 40, 44, 52, 53, 54, 61, 63, 67, 71, 72, 73, 74, 75, 77, 78, 79, 80, 85, 86, 87, 89, 92, 93, 94, 96, 97, 98, 103, 104], "If": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 16, 17, 18, 20, 26, 28, 30, 32, 33, 34, 35, 36, 51, 63, 64, 65, 67, 68, 69, 71, 73, 74, 75, 77, 78, 79, 80, 82, 85, 86, 88, 89, 91, 92, 93, 96, 98, 103, 104], "In": [0, 1, 7, 8, 11, 13, 17, 18, 20, 21, 23, 26, 27, 28, 29, 30, 31, 32, 36, 40, 55, 62, 63, 64, 71, 72, 73, 74, 75, 77, 78, 80, 86, 88, 89, 90, 91, 92, 93, 98, 102, 103, 104], "It": [0, 1, 3, 5, 6, 7, 10, 13, 15, 17, 18, 19, 21, 22, 25, 26, 27, 28, 29, 30, 33, 40, 51, 55, 63, 67, 68, 69, 71, 72, 75, 76, 77, 78, 79, 80, 86, 88, 90, 92, 94, 96, 97, 98, 104], "Its": [5, 80, 98], "NO": 99, "NOT": 80, "No": [0, 2, 9, 30, 55, 71, 73, 99], "Not": [1, 26, 46], "ON": [71, 75, 77, 78], "OR": 80, "Of": [27, 93], "On": [5, 9, 21, 30, 63, 65, 70, 74, 78, 80, 93], "One": [16, 17, 30, 77, 80, 92, 97, 99], "Or": [80, 85, 101], "That": [3, 5, 6, 9, 17, 69, 75, 80, 87], "The": [0, 1, 2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 26, 27, 28, 29, 31, 32, 33, 34, 40, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 62, 63, 65, 67, 68, 70, 71, 72, 73, 74, 75, 77, 78, 79, 80, 81, 82, 83, 85, 86, 87, 88, 89, 91, 92, 93, 94, 95, 96, 97, 98, 100, 101, 102, 103, 104], "Their": [29, 32], "Then": [10, 20, 28, 30, 34, 35, 67, 71, 73, 80, 96, 103], "There": [2, 5, 6, 7, 8, 9, 10, 16, 20, 24, 27, 28, 29, 30, 31, 40, 63, 65, 67, 80, 83, 86, 89, 90, 92, 93, 97, 98, 103, 104], "These": [13, 20, 22, 24, 25, 27, 29, 30, 31, 40, 71, 73, 74, 81, 83, 86, 88, 93], "To": [3, 5, 9, 10, 12, 13, 14, 17, 18, 19, 20, 21, 24, 27, 28, 30, 31, 32, 63, 67, 68, 69, 70, 71, 72, 75, 77, 78, 79, 80, 86, 87, 89, 90, 93, 95, 96, 98, 100, 103, 104], "Will": 0, "With": [5, 6, 13, 17, 30, 31, 35, 40, 62, 71], "_": [0, 3, 18, 83], "__all__": 96, "__call__": 51, "__init__": [7, 15, 17, 18, 51, 68, 71, 92, 93, 96, 98, 104], "__main__": [44, 46, 47, 48, 49, 50, 51, 55, 56, 65, 67, 73, 75, 78, 79, 86, 93, 96], "__name__": [44, 46, 47, 48, 49, 50, 51, 55, 56, 65, 73, 75, 78, 79, 86, 93, 96], "__post_init__": 93, "__repr__": 93, "__version__": [64, 86], "_capac": 1, "_context_logits_auto_en": 68, "_cpp_gen": 3, "_create_tensor": 17, "_explicitly_disable_gemm_plugin": 83, "_generation_logits_auto_en": 68, "_handl": 1, "_mark_output": 92, "_mpi_sess": 68, "_note": 5, "_path": 21, "_postproc_param": 68, "_postprocess_result": 68, "_return_log_prob": 68, "_run": 92, "_runtim": 85, "_static": 17, "_str_to_trt_dtype_dict": 80, "_tensorrt_engin": [44, 65, 86], "_torch": [68, 71, 93, 95, 96, 98, 101], "_torchllm": 68, "_unsign": 1, "_util": 80, "a10": 33, "a100": [6, 20, 33, 87], "a100x": 87, "a10g": 33, "a2": 93, "a30": 33, "a40": 33, "a8": 90, "a_": 80, "a_1": 80, "a_2": 80, "a_n": 80, "a_sf": 80, "aarch64": 91, "ab": [10, 33, 80, 90], "abbrevi": 34, "abc": 28, "abcd": 28, "abi": [63, 93], "abil": [69, 71], "abl": [5, 23, 27, 30, 65, 71, 77, 80, 93], "ablat": [28, 29], "abnorm": [30, 93], "abort": [68, 93], "about": [0, 1, 3, 20, 21, 22, 23, 25, 26, 29, 30, 31, 55, 62, 71, 73, 75, 76, 78, 80, 86, 89, 92, 93], "abov": [10, 11, 17, 20, 21, 26, 29, 30, 31, 32, 40, 63, 65, 71, 72, 73, 75, 78, 88, 89], "absenc": [6, 31], "absorb": 27, "abstract": [78, 81], "ac": 93, "acc": 80, "acceler": [5, 11, 13, 23, 24, 25, 26, 30, 33, 69], "accept": [0, 1, 13, 21, 30, 32, 40, 47, 48, 49, 50, 63, 67, 68, 73, 75, 80, 85, 86, 87, 91, 93, 98], "accept_length": 85, "acceptancelength": 0, "acceptancer": 0, "acceptancethreshold": 0, "acceptedlen": 1, "acceptedlengthscumsum": 1, "acceptedpath": 1, "acceptedpathid": 1, "acceptedtoken": 1, "acceptedtokenslen": 1, "access": [3, 30, 32, 36, 46, 68, 71, 73, 80, 86, 88, 93], "accessor": 1, "accommod": [4, 31, 97, 103], "accomplish": 74, "accord": [5, 18, 32, 80, 81, 98], "accordingli": 18, "account": [17, 21, 31, 35, 52, 53, 54, 63], "accumul": [0, 5, 6, 30, 33, 51, 68, 80, 85, 86], "accur": [22, 28, 46, 71, 73, 93], "accuraci": [21, 22, 27, 29, 33, 75, 79, 80, 90, 93], "achiev": [2, 13, 21, 22, 26, 27, 29, 30, 31, 63, 72, 73, 75, 77, 79, 96], "across": [2, 4, 5, 6, 7, 17, 18, 24, 27, 30, 31, 32, 34, 72, 74, 75, 77, 78, 80, 85, 87, 94], "act": [27, 30, 31], "act_fn": 81, "act_typ": [17, 80], "activ": [0, 1, 5, 7, 17, 22, 23, 26, 27, 29, 30, 31, 33, 74, 80, 90, 91, 93, 104], "activation_scaling_factor": 16, "activationtyp": [17, 80], "active_request": 104, "actual": [7, 8, 13, 21, 26, 27, 28, 30, 32, 33, 75, 77, 78, 79, 93, 94, 103], "ad": [1, 5, 6, 7, 9, 13, 14, 20, 21, 28, 29, 31, 36, 62, 70, 74, 77, 78, 80, 82, 85, 93, 95, 97], "ada": [5, 26, 63, 69, 75, 91, 93], "adalayernorm": 81, "adalayernormcontinu": 81, "adalayernormzero": 81, "adalayernormzerosingl": 81, "adapt": [0, 10, 28, 30, 45, 68, 80, 81, 93, 96], "adapter_s": 10, "adapters": 1, "add": [1, 3, 5, 7, 10, 15, 16, 17, 20, 28, 35, 36, 63, 67, 68, 71, 73, 75, 78, 80, 85, 87, 88, 92, 93, 96, 103], "add_activ": 17, "add_bias_linear": 82, "add_generation_prompt": 27, "add_input": 80, "add_output": 80, "add_padding_request": 103, "add_prefix_spac": 51, "add_qkv_bia": 82, "add_rmsnorm": 27, "add_sequ": 85, "add_special_token": [27, 51, 68, 85, 93], "addcumlogprob": 93, "added_kv_proj_dim": 81, "added_proj_bia": 81, "addit": [0, 5, 6, 10, 13, 17, 20, 24, 28, 29, 30, 31, 34, 40, 46, 63, 68, 71, 72, 74, 75, 77, 80, 81, 90, 91, 92, 93, 98, 103], "addition": [71, 73, 75, 78, 96, 98], "additional_model_output": 68, "additional_opt": 54, "additionalmodeloutput": [0, 3, 68], "additionaloutput": [0, 3], "addr": 0, "address": [1, 18, 21, 26, 27, 29, 30, 67, 78, 89, 93], "addresswiths": 1, "adequ": 81, "adher": 46, "adjust": [30, 31, 32, 51, 52, 68, 71, 73, 89, 104], "admin": 65, "adopt": [6, 20, 30], "advanc": [13, 17, 25, 27, 28, 29, 30, 31, 33, 47, 48, 50, 67, 80, 93, 98], "advantag": [6, 30, 31, 69], "advers": [22, 33], "advertis": 71, "affect": [11, 20, 21, 33, 73, 75, 77, 78, 89], "affin": 81, "aforement": [30, 88], "after": [0, 1, 3, 5, 7, 8, 9, 10, 13, 17, 18, 27, 28, 29, 30, 32, 33, 34, 35, 63, 67, 68, 71, 75, 77, 78, 79, 80, 81, 83, 86, 87, 88, 89, 93, 94, 98, 104], "again": [17, 30, 73, 75, 78, 92], "against": [63, 71], "agent": 24, "agentdesc": 0, "agentnam": 0, "agentst": 0, "aggreg": [29, 30, 31], "aggress": [16, 28, 75, 79], "agre": [67, 86], "agreement": 67, "ahead": [0, 5, 13, 32], "ai": [21, 23, 27, 30, 32, 34, 41, 44, 47, 48, 49, 50, 51, 56, 65, 69, 70, 73, 79, 80, 86, 91, 93], "aidc": 93, "aim": [4, 16, 21, 27, 30, 69, 71, 73, 75, 93], "ainsli": 22, "air": 93, "aka": 80, "akhoroshev": 93, "al": 22, "albeit": 13, "alessionetti": 93, "algo": 56, "algorithm": [0, 5, 6, 13, 16, 17, 20, 26, 27, 28, 29, 30, 56, 68, 71, 75, 80, 93], "alia": [68, 81, 82], "alibi": 80, "alibi_bias_max": [80, 81], "alibi_scal": 80, "alibi_slop": 80, "alibi_with_scal": 80, "align": [71, 93, 104], "align_corn": 80, "all": [0, 1, 3, 4, 5, 6, 7, 8, 10, 13, 17, 18, 20, 21, 24, 27, 28, 29, 30, 31, 32, 52, 53, 54, 55, 63, 64, 65, 68, 69, 71, 72, 73, 74, 75, 77, 78, 79, 80, 81, 83, 85, 86, 87, 89, 90, 91, 92, 93, 94, 98, 103, 104], "all2al": 30, "all_reduce_param": [80, 81], "allbitset": [0, 1], "allgath": [17, 29, 33, 78, 80, 93], "allgeneratedtoken": 0, "alllayersdrafttokenid": 1, "alllayersdrafttokenidspredecessor": 1, "alllayersscor": 1, "alloc": [0, 1, 2, 5, 8, 9, 32, 34, 40, 68, 79, 80, 85, 89, 92, 93, 94, 97, 98, 103, 104], "allocateipcmemori": 1, "allocnewblock": 0, "allocnewblocksperrequest": 0, "alloctotalblock": 0, "alloctotalblocksperrequest": 0, "allot": 0, "allottedtimem": [0, 93], "allow": [0, 1, 2, 3, 5, 6, 9, 13, 16, 22, 25, 29, 30, 31, 33, 67, 68, 69, 70, 71, 72, 73, 74, 75, 77, 78, 80, 83, 88, 92, 93, 97, 100, 104], "allreduc": [17, 27, 29, 33, 68, 78, 80, 93], "allreduce_gemm": 12, "allreduce_strategi": [11, 68], "allreducebuff": 1, "allreducefusionkernel": 27, "allreducefusionop": 80, "allreduceparam": [80, 81], "allreducestrategi": [11, 80], "almost": [17, 29, 30, 75, 77, 89], "alon": 4, "along": [5, 13, 19, 28, 63, 80, 93], "alongsid": 30, "alpaca": 10, "alpha": [68, 80, 81, 93], "alphabet": 80, "alreadi": [0, 5, 7, 9, 19, 21, 27, 28, 29, 30, 31, 68, 75, 77, 79, 80, 93, 96, 103], "also": [0, 3, 5, 7, 13, 16, 17, 18, 19, 20, 21, 24, 25, 26, 27, 28, 29, 30, 31, 33, 34, 40, 51, 63, 64, 65, 67, 68, 71, 72, 73, 74, 75, 76, 77, 80, 81, 86, 87, 88, 89, 90, 93, 96, 97, 98, 103], "altair": 93, "alter": [3, 7], "altern": [3, 12, 27, 44, 63, 65, 71, 86, 96, 97], "although": [7, 17, 31, 71, 75, 78], "alwai": [0, 1, 3, 5, 6, 9, 16, 17, 20, 29, 30, 68, 77, 78, 80, 92], "always_share_across_beam": 85, "am": [47, 48, 50, 73, 79, 85], "ambigu": 1, "amd": 93, "amen": [0, 3, 68], "among": [31, 36, 80], "amongst": 80, "amount": [0, 9, 17, 29, 30, 33, 68, 71, 77, 79, 85, 89, 92], "amper": [23, 63, 69, 91, 93], "an": [0, 1, 2, 3, 5, 6, 7, 9, 10, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 24, 26, 27, 28, 29, 30, 31, 33, 34, 40, 46, 47, 48, 49, 50, 51, 63, 65, 67, 68, 69, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 85, 86, 87, 88, 89, 90, 92, 93, 96, 97, 98, 103, 104], "analog": 88, "analys": 30, "analysi": [7, 27, 28, 29, 30, 31, 32, 62, 89], "analysispatternmanag": 7, "analyt": 23, "analyz": [7, 51, 73], "ani": [0, 1, 2, 3, 7, 8, 13, 18, 20, 21, 28, 29, 30, 34, 63, 68, 69, 71, 72, 77, 78, 79, 80, 82, 85, 87, 88, 92, 96, 97, 98], "announc": [21, 22, 23, 25], "anoth": [0, 1, 5, 7, 10, 20, 23, 27, 28, 29, 30, 31, 32, 34, 77, 80, 86, 92, 98, 104], "answer": [28, 46, 51], "antialia": 80, "anybitset": [0, 1], "anymor": 30, "anyth": [55, 72], "aotman": 93, "apart": 40, "api": [2, 6, 9, 13, 15, 16, 17, 19, 21, 28, 29, 30, 31, 32, 40, 41, 44, 45, 53, 54, 62, 63, 69, 70, 71, 72, 75, 76, 78, 79, 80, 89, 92, 95, 96], "api_kei": [34, 57, 58, 59, 60], "app": [63, 93], "appar": 69, "appear": [0, 5, 6, 65, 68, 80, 87, 92, 93], "append": [28, 70, 80, 104], "append_paged_kv_cach": 98, "appl": 93, "appli": [0, 3, 5, 7, 10, 13, 16, 17, 18, 27, 28, 29, 30, 33, 63, 68, 69, 71, 80, 81, 85, 88, 90, 93, 98], "applic": [9, 13, 23, 26, 27, 29, 30, 31, 32, 34, 37, 38, 39, 65, 67, 69, 70, 86, 88, 92, 93, 94, 104], "apply_batched_logits_processor": 68, "apply_chat_templ": [27, 46], "apply_llama3_sc": 80, "apply_query_key_layer_sc": [81, 82], "apply_residual_connection_post_layernorm": 82, "apply_rotary_pos_emb": 80, "apply_rotary_pos_emb_chatglm": 80, "apply_rotary_pos_emb_cogvlm": 80, "apply_silu": 80, "applybiasropeupdatekvcach": 93, "applyrop": 27, "appreci": 29, "approach": [0, 4, 7, 9, 11, 13, 27, 28, 29, 30, 31, 71, 79, 86], "appropri": [26, 31, 40, 87, 92], "approxim": [29, 30, 63, 81], "apt": [21, 35, 63, 65], "ar": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 37, 38, 46, 47, 48, 50, 51, 52, 53, 54, 55, 57, 58, 63, 64, 65, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 85, 86, 87, 88, 89, 90, 92, 93, 94, 96, 97, 98, 101, 102, 103, 104], "arang": 80, "arbitrag": 71, "arbitrari": [18, 93], "arbitrary_types_allow": 68, "architectur": [2, 4, 6, 9, 16, 23, 28, 29, 30, 31, 63, 69, 82, 85, 91, 93, 95], "arctic": [91, 93], "area": [29, 30], "aresult": 40, "arg": [0, 7, 20, 34, 68, 81, 82, 85, 93], "arglist": 7, "argmax": 80, "argument": [2, 3, 21, 34, 40, 56, 63, 68, 71, 74, 80, 87, 89, 93, 94, 98], "aris": 63, "arithmet": 17, "arm": 87, "around": [1, 16, 20, 69, 73, 78], "arrai": [0, 1, 68, 80, 85, 87], "arrayview": [0, 1], "arriv": [0, 4], "arrivaltim": 0, "arrow": 80, "art": [21, 27, 30, 31], "articl": [5, 13, 27, 28], "artifact": [63, 88], "artifici": [32, 69], "arxiv": [0, 1, 4, 10, 33, 80, 90], "as_dtyp": 80, "as_lay": 7, "as_shap": 80, "ascii": 80, "asciichar": 1, "ask": [55, 92], "aspect": 5, "assembl": [17, 19], "assert": [7, 60, 80, 92, 93, 104], "assert_valid_quant_algo": 82, "assign": [0, 20, 30, 71, 81, 83, 96], "assist": [6, 32, 34, 37, 38, 46, 57, 58, 67, 86], "assistant_model": 6, "associ": [1, 3, 4, 10, 29, 31, 63, 73, 80, 88], "asssembl": 13, "assum": [1, 3, 9, 10, 13, 14, 21, 28, 29, 30, 68, 71, 80, 85], "assumpt": [13, 31, 33], "assur": 30, "async": [40, 48, 49, 68, 71, 85], "asynchron": [1, 3, 30, 40, 45, 68], "asynchroni": 30, "asyncio": [48, 49], "asyncllmengin": 93, "atom": 1, "attach": [21, 86], "attempt": [0, 2, 72, 73, 75, 88, 94], "attend": 79, "attent": [0, 1, 2, 6, 8, 9, 10, 13, 15, 17, 18, 21, 22, 30, 31, 33, 62, 68, 80, 85, 86, 89, 92, 93, 94, 95, 96, 99, 103], "attention_backend": [96, 98], "attention_head_s": [80, 81], "attention_mask": [80, 81, 82, 85, 98], "attention_mask_param": 82, "attention_mask_typ": 81, "attention_multipli": 82, "attention_output": 92, "attention_output_orig_quant_scal": 80, "attention_output_sf_scal": 80, "attention_packed_mask": [80, 81], "attention_param": [81, 82], "attention_qk_half_accumul": 93, "attention_window_s": 8, "attentionconfig": 0, "attentionheads": 1, "attentionmask": 98, "attentionmaskparam": 81, "attentionmasktyp": [80, 81], "attentionmetadata": 96, "attentionparam": [81, 82], "attentiontyp": 0, "attn_backend": [68, 98], "attn_bia": 82, "attn_dens": [10, 33], "attn_forward_funcnam": 81, "attn_k": [10, 33, 71], "attn_logit_softcap": 82, "attn_logit_softcapping_scal": 80, "attn_metadata": 96, "attn_processor": 82, "attn_q": [10, 33, 71], "attn_qkv": [10, 33], "attn_v": [10, 33, 71], "attribut": [0, 1, 3, 7, 18, 20, 68, 85], "audienc": 51, "audio": [85, 93], "audio_engine_dir": 85, "audio_featur": 85, "audio_path": 85, "authent": [67, 73, 86], "authorized_kei": [35, 36], "auto": [0, 1, 3, 5, 6, 11, 14, 17, 30, 68, 71, 78, 80, 82, 83, 84, 88, 93], "auto_deploi": 93, "auto_parallel": [33, 68, 93], "auto_parallel_config": 68, "auto_parallel_world_s": 68, "auto_quantize_bit": 84, "autoawq": 93, "autodeploi": 93, "autogptq": 93, "autom": [31, 46, 51, 93], "automat": [0, 3, 7, 11, 17, 18, 27, 30, 34, 40, 67, 69, 71, 73, 80, 87, 89, 90, 93], "autonom": 32, "autoparallelconfig": 68, "autopp": 93, "autoq": 93, "autoregress": [0, 13, 98, 103], "autotoken": 40, "autotun": [68, 93], "aux": 89, "auxiliari": 13, "avaiable_block": 104, "avail": [0, 1, 3, 7, 9, 12, 17, 22, 24, 30, 31, 34, 40, 47, 48, 50, 63, 64, 69, 71, 77, 78, 79, 85, 86, 88, 89, 90, 93, 95, 98, 102, 103], "averag": [0, 13, 21, 28, 30, 31, 68, 71, 72, 73, 75, 77, 78], "avg": [71, 73, 80], "avg_pool2d": 80, "avgnumdecodedtokensperit": 0, "avgpool2d": 81, "avoid": [1, 2, 20, 27, 28, 29, 30, 63, 67, 85, 89, 93], "awai": [68, 77, 78], "await": [0, 3, 40, 48, 49], "awaitcontextrespons": 0, "awaitgenerationrespons": 0, "awaitrespons": [0, 3], "awar": [5, 22, 31, 92], "awq": [26, 40, 62, 91, 93], "awq_block_s": 84, "ax": 80, "axi": [25, 30, 80], "b": [1, 2, 7, 10, 17, 22, 23, 24, 25, 70, 80, 82, 85, 87, 93], "b200": [28, 29, 30, 32, 72, 93], "b6261862419c33d6ce2313aff1e7116067d6037d": 21, "b_sf": 80, "back": [0, 9, 11, 13, 30, 65, 72, 93], "backbon": 69, "backend": [0, 3, 13, 17, 19, 21, 28, 29, 30, 32, 34, 41, 45, 46, 62, 67, 68, 70, 71, 72, 86, 87, 93, 97, 101, 102, 103, 104], "backend_token": [0, 3], "backendagentdesc": 0, "background": 30, "backlog": 87, "backu": [0, 3, 68], "backward": 20, "bad": [0, 3, 68, 93, 102], "bad_token_id": 68, "bad_words_data": 85, "bad_words_list": 85, "badword": 0, "badwordslen": 1, "badwordslist": 1, "badwordsptr": 1, "baichuan": [90, 91, 93], "baichuan2": 91, "baichuanconfig": 82, "baichuanforcausallm": 82, "balanc": [4, 6, 13, 17, 29, 31, 68, 77, 79], "band": 46, "bandwidth": [6, 17, 22, 23, 24, 26, 29, 30, 46], "bangbang": 23, "bantoken": 0, "banword": 0, "bar": 68, "bare": [93, 95], "barissglc": 55, "bart": [91, 93], "base": [0, 1, 3, 9, 10, 11, 13, 15, 18, 19, 20, 21, 22, 23, 26, 27, 29, 30, 31, 33, 48, 49, 51, 63, 68, 69, 71, 77, 79, 80, 81, 82, 83, 84, 85, 88, 89, 91, 93, 94, 95, 96, 97, 103, 104], "base64": 58, "base_model": 10, "base_s": 81, "base_url": [34, 57, 58, 59, 60], "baseagentconfig": 0, "basekvcachemanag": 0, "baselin": [26, 27, 28, 29, 73, 77, 78, 98], "baseline_fp8_engin": 75, "basellmarg": 68, "basemodel": 68, "baseresourcemanag": [97, 103], "basetransferag": 0, "bash": [17, 34, 36, 37, 38, 39, 41, 42, 43, 52, 53, 54, 70, 86], "basi": 31, "basic": [15, 70, 80], "basic_string_view": 0, "batch": [0, 1, 6, 9, 10, 11, 13, 14, 17, 19, 21, 23, 24, 26, 27, 28, 29, 30, 32, 33, 34, 62, 66, 68, 71, 72, 73, 75, 76, 78, 79, 80, 81, 85, 86, 89, 92, 93, 94, 96, 97, 98, 100, 103, 104], "batch_beam_s": [5, 80], "batch_dim": 80, "batch_idx": 85, "batch_input_id": 85, "batch_manag": [0, 1, 103], "batch_schedul": 93, "batch_siz": [5, 7, 14, 16, 21, 22, 25, 68, 72, 80, 81, 84, 85, 89, 98], "batchdon": 1, "batched_logits_processor": 68, "batchedlogitsprocessor": 68, "batchidx": 1, "batchindex": 1, "batching_typ": 68, "batchingtyp": [0, 68], "batchsiz": [0, 1, 6, 23], "batchsizelimit": 0, "batchsizet": 0, "batchslot": 1, "batchslotshostcopi": 1, "bc": 80, "beam": [0, 1, 6, 13, 19, 25, 33, 34, 40, 62, 68, 80, 85, 89, 92, 93], "beam_search_diversity_r": [68, 85], "beam_width": [5, 6, 40, 80, 85, 93], "beam_width_arrai": 68, "beamhypothes": 1, "beamsearch": 0, "beamsearchbuff": 1, "beamsearchdiversityr": [0, 1, 6], "beamsiz": 0, "beamtoken": [0, 3], "beamwidth": [0, 1, 2, 3, 6, 68, 93], "beamwidtharrai": [0, 1, 6], "becam": 0, "becaus": [0, 3, 9, 26, 27, 28, 29, 30, 33, 40, 55, 64, 67, 71, 72, 73, 74, 75, 77, 79, 80, 86, 89], "becom": [5, 6, 7, 9, 10, 17, 18, 26, 27, 29, 30, 69], "been": [0, 3, 4, 5, 20, 21, 23, 24, 27, 29, 30, 36, 55, 63, 64, 65, 68, 71, 75, 77, 80, 86, 92, 93], "befor": [0, 1, 2, 3, 5, 7, 9, 10, 11, 16, 17, 18, 27, 28, 30, 32, 51, 52, 53, 54, 62, 63, 65, 67, 68, 69, 70, 74, 75, 77, 79, 80, 82, 85, 89, 92, 93, 96, 97, 98, 103, 104], "beforehand": 73, "begin": [13, 69, 74, 93, 96], "begin_thinking_phase_token": 68, "behav": [0, 68, 89], "behavior": [2, 5, 72, 77, 80, 85, 88, 89, 93], "behaviour": [0, 30, 80], "behind": [23, 29], "being": [0, 5, 9, 17, 20, 29, 32, 55, 68, 77, 92, 93, 94, 98], "believ": [30, 71], "belong": 77, "below": [0, 5, 6, 7, 8, 10, 21, 24, 25, 26, 28, 29, 30, 31, 32, 35, 36, 63, 71, 72, 75, 77, 78, 86, 87, 92], "bench": [21, 28, 30, 45, 55, 71, 72, 76, 93], "benchmark": [27, 28, 30, 31, 32, 53, 62, 63, 70, 75, 76, 78, 86, 93], "benchmark_2nod": 34, "benefici": [29, 31, 71, 77, 78], "benefit": [7, 9, 11, 24, 26, 28, 29, 30, 31, 33, 51, 69, 77, 93], "bert": [33, 80, 90, 91, 93], "bert_attent": 80, "bert_attention_plugin": 33, "bert_context_fmha_fp32_acc": 33, "bertattent": 81, "bertattentionplugin": 80, "bertbas": 82, "bertforquestionansw": 82, "bertforsequenceclassif": [82, 91], "bertmodel": 82, "besid": 97, "best": [5, 17, 27, 28, 29, 30, 31, 62, 68, 70, 71, 74, 76, 77, 86, 93], "best_of": [68, 93], "best_path": 85, "best_path_len": 85, "best_path_length": 85, "best_perf_practice_on_deepseek": [27, 93], "bestpathindic": 1, "bestpathlength": 1, "beta": [34, 80], "beta_fast": 80, "beta_slow": 80, "better": [0, 2, 5, 6, 9, 11, 18, 20, 25, 27, 28, 29, 30, 31, 33, 51, 52, 53, 54, 68, 72, 74, 75, 78, 79, 93, 100], "between": [0, 2, 5, 6, 8, 9, 12, 13, 17, 18, 20, 27, 28, 29, 30, 31, 34, 38, 58, 68, 70, 72, 74, 78, 79, 80, 81, 89, 92, 93, 96], "beyond": [1, 23, 75], "bf16": [1, 5, 11, 18, 20, 21, 27, 29, 32, 62, 75, 78, 91, 93], "bfloat16": [5, 17, 33, 71, 73, 83, 90, 91, 93], "bhuvanesh09": 93, "bi": 5, "bia": [0, 3, 16, 17, 29, 68, 80, 81, 82, 93], "bias": [16, 80], "bidirect": [80, 81], "bidirectionalglm": 80, "big": 51, "bigger": 9, "biggest": 9, "billion": 21, "bin": [16, 17, 18, 21, 34, 37, 38, 39, 41, 42, 43, 52, 53, 54, 70, 92, 93], "binari": [13, 17, 70, 80], "bind": [30, 62, 68, 79, 85, 89, 93, 97, 103, 104], "bindcapacityschedul": 104, "bindf": 88, "bit": [0, 1, 5, 23, 30, 55, 80, 90], "bitmask": 93, "bl": [13, 31], "black": 7, "blackwel": [2, 21, 28, 30, 62, 65, 74, 75, 91, 93], "blip": [90, 93], "blip2": [90, 91, 93], "blob": 27, "block": [0, 1, 2, 5, 6, 9, 17, 29, 30, 31, 33, 40, 62, 67, 68, 77, 80, 85, 89, 93, 103], "block_controlnet_hidden_st": 82, "block_num": 80, "block_siz": [80, 81, 85], "block_sparse_block_s": 80, "block_sparse_homo_head_pattern": 80, "block_sparse_num_local_block": 80, "block_sparse_param": 81, "block_sparse_vertical_strid": 80, "blockhash": 0, "blockidx": 1, "blockptr": 1, "blocksiz": 0, "blockspars": 80, "blocksparseattnparam": 81, "blog": [21, 22, 25, 26, 27, 28, 29, 30, 31, 93, 100], "bloodeagle40234": 93, "bloom": [6, 18, 90, 91, 93], "bloom_dict": 18, "bloomforcausallm": 82, "bloommodel": 82, "bm": 1, "bmm": 17, "board": 78, "bodi": 17, "book": 55, "bool": [0, 1, 7, 14, 16, 51, 68, 80, 81, 82, 83, 85, 98], "boolean": [1, 3, 10, 80, 82, 83], "boost": [21, 27, 29, 30, 32, 51, 75, 77, 78], "boost_factor": 51, "boost_val": 51, "born": [15, 17, 92], "borrow": [40, 71], "bos_token": 51, "bos_token_ad": 51, "bos_token_id": [51, 85], "bot": 87, "both": [0, 2, 4, 5, 7, 8, 10, 13, 17, 18, 21, 23, 26, 27, 28, 29, 30, 31, 32, 33, 44, 68, 71, 72, 74, 77, 79, 80, 81, 87, 89, 90, 93, 97, 98], "bottleneck": [4, 11, 21, 26, 30, 74, 77], "bottom": 36, "bound": [0, 6, 15, 17, 24, 27, 28, 29, 68, 71, 80, 85, 89], "boundari": [6, 17, 29, 30, 68, 80, 82, 84, 89], "box": [7, 21], "bpru": 93, "brahma": 71, "branch": [13, 22, 25, 30, 32, 68], "breadth": 13, "break": [13, 27, 30, 71, 78, 93, 104], "breakdown": [70, 71, 72, 73], "breviti": 21, "bridg": 30, "brief": [82, 85, 87, 98], "briefli": [34, 38, 58], "brife": 0, "bright": 51, "bring": [26, 27, 28, 29, 30, 96], "broad": 67, "broadcast": [3, 27, 80], "broadcast_help": 80, "broader": [5, 67, 93], "broadli": 29, "broken": [69, 77, 93], "brought": 30, "bsz": 81, "bu": 63, "budget": [14, 77], "buffer": [0, 1, 2, 3, 8, 9, 30, 33, 34, 62, 68, 80, 93, 103], "buffer_0": 1, "buffer_1": 1, "buffer_2": 1, "buffer_alloc": 85, "buffercast": 1, "buffercastornul": 1, "bufferdatatyp": 1, "buffermanag": 89, "buffermanagertest": 1, "bufferptr": 1, "bufferrang": 1, "buffers": 1, "bufferview": 0, "bug": [29, 87, 93], "build": [2, 3, 5, 6, 7, 9, 10, 12, 13, 14, 15, 17, 19, 55, 62, 68, 69, 70, 74, 75, 76, 77, 79, 82, 83, 86, 88, 89, 92, 93], "build_config": [20, 33, 40, 55, 68, 75, 77, 78, 82], "build_dir": 63, "build_engin": 17, "build_flags_multiple_profil": 78, "build_serialized_network": 17, "build_wheel": [12, 21, 63, 70], "buildcacheconfig": 68, "buildconfig": [14, 20, 40, 55, 68, 75, 77, 78, 93], "builder": [14, 17, 20, 68, 93], "builder_force_num_profil": 93, "builder_opt": 93, "built": [3, 6, 9, 17, 20, 29, 31, 33, 62, 63, 65, 67, 71, 72, 73, 78, 79, 80, 86, 88, 89, 92, 93], "bulk": 30, "bump": 1, "bumptaskinprogress": 1, "burden": 74, "busi": [0, 31, 51], "button": 93, "buvnswrn": 93, "bw": 93, "bypass": [31, 88], "byt5": [91, 93], "byte": [0, 1, 11, 68, 85], "bytestostr": 1, "c": [0, 1, 2, 5, 7, 13, 17, 19, 21, 28, 29, 31, 32, 34, 35, 36, 40, 52, 53, 54, 62, 68, 69, 70, 77, 80, 82, 86, 93, 97, 99, 102, 103, 104], "c2c": 30, "c4dep4_g1dep4": 31, "cach": [0, 1, 2, 3, 6, 10, 17, 20, 26, 27, 28, 29, 32, 33, 34, 40, 62, 66, 68, 69, 71, 72, 73, 77, 80, 85, 86, 88, 90, 93, 95, 96, 97, 98, 99, 104], "cache_indir": 85, "cache_indir_t": 80, "cache_indirect": [5, 80, 81, 85, 92], "cache_root": 68, "cache_transceiver_config": 68, "cachehitr": 0, "cacheindirect": 1, "cachelevel": 0, "cachelevelupd": 0, "caches": 0, "cachest": 0, "cachetransceiv": 0, "cachetransceiverconfig": [0, 68], "cachetyp": 103, "cachevalu": 1, "calcul": [0, 22, 23, 25, 28, 29, 30, 31, 68, 71, 79, 80, 85, 89, 93], "calculate_speculative_resourc": 68, "calculatespeculativeresourc": 0, "calculatespeculativeresourcetupl": 0, "calib_batch": [68, 75, 82], "calib_batch_s": [68, 75, 82], "calib_config": [68, 75], "calib_dataset": [68, 82, 84], "calib_max_seq_length": [68, 75, 82, 84], "calib_s": [71, 84], "calibconfig": [68, 75], "calibr": [18, 26, 29, 30, 33, 68, 75, 93], "call": [0, 1, 3, 4, 5, 6, 7, 12, 17, 18, 20, 28, 29, 30, 31, 40, 51, 68, 70, 73, 75, 80, 82, 84, 85, 86, 89, 93, 94, 96, 97, 98, 103], "callabl": [18, 68, 82], "callback": [3, 68], "campaign": 51, "can": [0, 1, 2, 3, 4, 5, 6, 7, 8, 11, 12, 13, 14, 17, 18, 19, 20, 21, 22, 23, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 40, 44, 51, 52, 53, 54, 55, 56, 62, 63, 64, 65, 67, 68, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 82, 83, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 101, 103, 104], "canaccessp": 1, "cancel": [0, 3, 68, 71, 93], "cancelrequest": [0, 3], "candid": [0, 6, 11, 13, 17, 27, 28, 68], "canenqueu": 0, "canenqueuerequest": 0, "cannot": [1, 6, 17, 18, 27, 29, 30, 31, 67, 68, 77, 78, 79, 80, 89, 92, 93, 104], "cap": 73, "capabl": [22, 27, 30, 31, 46, 63, 69, 70, 75], "capac": [0, 1, 22, 24, 26, 30, 68, 104], "capacitor_schedul": 104, "capacity_scheduler_polici": [68, 79], "capacityschedul": [97, 103, 104], "capacityschedulerpolici": [0, 68, 79, 93], "capit": [44, 47, 48, 49, 50, 56, 65, 73, 79, 86], "caption": 81, "captur": [28, 29, 30, 68, 98], "card": 55, "care": [30, 31], "carefulli": [21, 30], "case": [0, 1, 2, 5, 6, 8, 9, 10, 13, 21, 23, 26, 27, 28, 29, 30, 31, 33, 40, 67, 71, 72, 73, 75, 76, 78, 80, 88, 90, 93], "cast": [29, 80], "cast_to_dtyp": 80, "castsiz": 1, "cat": [21, 28, 30, 34, 53], "catalog": [63, 64, 86], "categor": [13, 29, 80], "categori": 83, "categorical_sampl": 80, "caus": [2, 3, 18, 20, 30, 33, 68, 78, 92, 93], "causal": [28, 80, 81, 98], "cautiou": 20, "caveat": 75, "cd": [15, 16, 21, 28, 32, 63, 71, 86, 92, 101], "ceil": [1, 82], "ceil_mod": [80, 81], "ceildiv": 1, "center": [23, 24, 31], "central": 83, "certain": [2, 7, 16, 30, 31, 65, 69, 80], "cg": 82, "chain": [28, 51], "challeng": [27, 30, 31, 69], "chanc": [9, 30, 33, 79], "chang": [2, 5, 6, 8, 9, 10, 18, 20, 21, 22, 24, 25, 28, 29, 30, 56, 63, 68, 69, 71, 78, 80, 82, 85, 87, 89, 92, 94, 95, 103], "channel": [30, 33, 80, 90, 93], "char": [0, 1], "characterist": 31, "charg": [6, 17, 98], "chart": 23, "chat": [13, 24, 31, 32, 39, 42, 44, 46, 47, 48, 49, 50, 51, 55, 59, 61, 65, 67, 86, 93], "chatbot": 55, "chatcmpl": [32, 86], "chatglm": [80, 90, 91, 93], "chatglm2": [91, 93], "chatglm3": [82, 91, 93], "chatglm_vers": 82, "chatglmconfig": 82, "chatglmforcausallm": 82, "chatglmgenerationsess": 85, "chatglmmodel": 82, "check": [2, 3, 30, 32, 44, 63, 65, 68, 72, 74, 75, 77, 78, 80, 85, 86, 88, 89, 92, 93, 96, 100], "check_accuraci": 16, "check_config": 82, "check_gpt_mem_usag": 89, "checkbeamsearchdiversityr": 0, "checkbeamwidth": 0, "checkbeamwidtharrai": 0, "checkearlystop": 0, "checklengthpenalti": 0, "checkminp": 0, "checkmintoken": 0, "checknorepeatngrams": 0, "checknumreturnsequ": 0, "checkpoint": [15, 18, 19, 20, 21, 27, 28, 29, 32, 33, 34, 47, 62, 67, 68, 71, 73, 75, 84, 85, 86, 90, 92, 93, 96], "checkpoint_dir": [10, 14, 15, 16, 17, 20, 33, 71, 86, 92], "checkposteriorvalu": 0, "checkremotedesc": 0, "checkrepetitionpenalti": 0, "checktemperatur": 0, "checktopk": 0, "checktopp": 0, "checktoppdecai": 0, "checktoppmin": 0, "checktoppresetid": 0, "chef": 92, "chmod": 35, "choic": [0, 13, 26, 28, 30, 32, 33, 56, 71, 74, 80, 85, 86, 98], "choos": [17, 20, 27, 29, 30, 31, 75, 80, 93], "chose": 30, "chosen": [29, 89, 102, 104], "chrome": 70, "chrono": 0, "chunk": [0, 8, 29, 33, 62, 66, 68, 78, 80, 85, 89, 93, 99], "chunk_dim": 81, "chunk_length": 93, "chunk_scan": 80, "chunk_siz": [80, 82], "chunkedcontextnexttoken": 1, "chunkedcontextnexttokenshost": 1, "ci": [1, 62, 88], "circular": 5, "citi": 86, "ckpt": [71, 86], "ckpt_dir": [17, 20, 82], "ckpt_llama_3": 17, "cl": [15, 20], "claim": [1, 18], "claimpag": 1, "claimpageswithevict": 1, "clamp": [68, 93], "clamp_val": 68, "class": [0, 1, 5, 6, 7, 8, 14, 15, 17, 18, 20, 26, 33, 40, 51, 63, 67, 68, 74, 75, 78, 80, 81, 82, 83, 84, 85, 92, 93, 96, 97, 98, 102, 104], "class_dropout_prob": 81, "class_label": 81, "classic": [17, 30, 62], "classifi": [81, 82], "classmethod": [15, 20, 68, 81, 82, 85], "classvar": 68, "clean": [21, 30, 63, 70, 92], "clear": [30, 77, 85], "clearli": [30, 79], "cli": [16, 21, 40, 62, 71, 74, 75, 77, 78, 86], "click": [35, 36, 56], "client": [0, 3, 31, 34, 61, 72, 94], "client_id": 51, "clientid": 0, "clip": 80, "clip_before_cast": 80, "clip_qkv": [81, 82], "clip_vision_model": 82, "clipvisiontransform": 82, "clock": 27, "clone": [10, 21, 63, 67, 73, 86, 92, 101], "clone_input": 7, "close": [5, 20, 21, 30, 31, 33, 78, 89], "closur": 80, "cloud": [23, 35, 36], "cls_token": 81, "cluster": [6, 17, 27, 30, 32, 33, 34, 65, 68, 93], "cluster_info": 93, "cluster_kei": [33, 93], "cluster_s": 34, "cmake": [63, 93], "cnn_dailymail": [68, 82], "co": [0, 10, 21, 28, 29, 30, 34, 38, 58, 67, 80, 81, 86, 92], "coast": 86, "code": [5, 7, 8, 11, 12, 13, 17, 20, 26, 27, 29, 32, 34, 40, 52, 53, 54, 62, 67, 68, 69, 70, 71, 80, 88, 90, 91, 92, 93, 96, 103, 104], "codebas": [8, 96], "codellama": 93, "codepath": 93, "codeqwen": 93, "coderham": 93, "cogvlm": [91, 93], "cogvlmattent": 81, "cogvlmconfig": 82, "cogvlmforcausallm": 82, "coher": [6, 93], "cohereconfig": 82, "cohereforcausallm": 82, "cold": 30, "collabor": [6, 27, 29, 30, 31, 80], "collect": [1, 7, 11, 13, 17, 27, 29, 31, 68, 72, 80, 96], "collect_and_bia": 81, "collector": 30, "color": [55, 77], "column": [10, 80, 90], "columnlinear": [10, 15, 81], "com": [17, 20, 21, 27, 32, 51, 63, 80, 86, 87, 88, 92, 93, 101], "combin": [0, 7, 13, 24, 27, 28, 29, 30, 31, 32, 33, 52, 53, 54, 71, 72, 75, 77, 81, 82, 88, 93, 95, 98, 104], "combinedtimesteplabelembed": 81, "combinedtimesteptextprojembed": 81, "come": [6, 10, 23, 30, 31, 73, 74, 77, 79, 89, 92], "comm": 68, "comma": [80, 85], "command": [9, 10, 12, 15, 16, 17, 20, 21, 31, 32, 34, 35, 36, 52, 53, 54, 56, 63, 64, 70, 71, 73, 78, 83, 86, 87, 88, 89, 92, 93, 101], "commandr": 93, "comment": [87, 93], "commit": [21, 29, 32, 87, 88], "commmod": 0, "common": [0, 5, 8, 9, 13, 21, 29, 30, 44, 67, 68, 80, 88, 89, 103], "commonli": [7, 27, 34, 93], "commstat": 0, "commtyp": 0, "commun": [0, 6, 11, 17, 29, 31, 33, 67, 69, 75, 80, 91, 93], "communicationmod": 0, "communicationtyp": 0, "compani": [32, 51], "compar": [1, 2, 18, 21, 23, 24, 26, 28, 29, 30, 31, 75, 77, 78, 79, 80, 98], "comparison": [6, 23, 27, 28, 71], "compat": [13, 20, 28, 30, 31, 32, 34, 63, 78, 81, 86, 91, 93, 96], "compbin": 10, "compet": 30, "compil": [6, 11, 12, 19, 32, 62, 65, 68, 69, 70, 71, 80, 92], "complet": [0, 1, 3, 6, 8, 9, 13, 30, 32, 37, 38, 40, 57, 58, 61, 63, 68, 69, 71, 72, 73, 77, 78, 86, 93, 100, 103, 104], "complete_sent": 51, "completion_token": [32, 86], "completionoutput": [40, 68], "complex": [7, 8, 13, 17, 27, 30, 51, 86], "compli": 34, "complic": [28, 29, 30, 96], "compon": [3, 5, 17, 19, 26, 27, 28, 29, 30, 62, 90, 97], "compos": [0, 6, 30, 62, 71], "comprehens": [21, 34, 69], "compress": [22, 29], "compris": [26, 31], "comput": [0, 1, 4, 5, 6, 9, 13, 17, 22, 23, 24, 26, 27, 28, 29, 30, 31, 32, 33, 47, 48, 50, 51, 68, 70, 71, 74, 75, 79, 80, 89, 92, 93, 96, 97, 98, 100, 103], "compute_relative_bia": 81, "computecontextlogit": 1, "computegenerationlogit": 1, "computenumpackedmask": 1, "concat": [15, 27, 80], "concat_kvcach": 27, "concaten": [5, 10, 18, 27, 80, 96], "concept": [17, 31, 71, 76, 93, 103], "conceptu": 1, "concern": [17, 30, 89], "conclud": 30, "conclus": 76, "concret": [30, 96], "concurr": [1, 2, 13, 21, 23, 27, 28, 29, 30, 31, 71, 93, 94, 100], "concurrency_list": 94, "cond_proj_dim": 81, "conda": 93, "condit": [0, 1, 3, 6, 7, 13, 30, 31, 71, 80, 81, 87, 93], "condition": [80, 88], "conditioning_embed": 81, "conditioning_embedding_dim": 81, "conduct": [5, 31, 71], "config": [0, 1, 5, 9, 10, 14, 15, 18, 20, 21, 22, 28, 29, 32, 34, 41, 68, 71, 77, 81, 82, 83, 85, 92, 93, 94, 96, 103], "config_class": 82, "config_dir": 82, "config_fil": [34, 68, 82, 94], "configdict": 68, "configur": [0, 1, 2, 4, 5, 8, 12, 13, 18, 19, 21, 24, 31, 32, 33, 34, 46, 55, 62, 63, 65, 68, 71, 72, 73, 76, 77, 79, 82, 85, 87, 89, 92, 93, 94, 98, 100], "configuration_llama": 96, "configuration_mymodel": 96, "configuration_util": 96, "conform": 68, "congest": 30, "conjunct": 77, "connect": [0, 11, 17, 30, 32, 73, 74, 76], "connectioninfo": 0, "connectioninfotyp": 0, "connectionmanag": 0, "connectremoteag": 0, "consecut": 6, "consequ": [26, 74, 78], "conserv": [0, 79, 87], "consid": [0, 1, 10, 13, 21, 26, 30, 31, 32, 55, 68, 72, 77, 80, 96, 104], "consider": [20, 26, 30, 31, 40], "consist": [7, 20, 23, 27, 68, 69, 71, 73, 80, 90, 92, 98], "consol": 35, "consolid": [13, 30], "const": [0, 1, 3], "const_iter": 1, "constant": [1, 5, 30, 80, 89], "constant_to_tensor_": 80, "constantli": [47, 48, 50], "constants_to_tensors_": 80, "constantthreshold": 1, "constexpr": [0, 1], "constitut": 31, "constpointercast": 1, "constrain": [6, 26], "constraint": [0, 5, 6, 26, 30, 31, 80], "construct": [0, 1, 3, 13, 17, 31, 71, 80, 93, 98], "constructor": [0, 14, 55, 67, 86, 98], "consult": [13, 63, 70], "consum": [0, 7, 29, 30, 68, 80, 87], "consumpt": [5, 23, 28, 33], "contact": 80, "contain": [0, 1, 3, 5, 6, 7, 8, 10, 11, 16, 17, 18, 19, 20, 27, 30, 32, 33, 34, 36, 52, 53, 54, 62, 65, 68, 69, 71, 72, 80, 82, 85, 87, 90, 91, 93, 94, 95, 97, 98], "container_id": [32, 86], "container_imag": [52, 53, 54], "container_img": 34, "content": [1, 10, 20, 32, 34, 35, 37, 38, 39, 46, 57, 58, 62, 68, 80, 86, 88, 89, 93], "context": [0, 2, 4, 9, 26, 28, 29, 30, 31, 33, 62, 66, 68, 71, 76, 80, 85, 89, 92, 93, 94, 98, 102, 103, 104], "context_chunking_polici": [68, 79], "context_fmha": [10, 33], "context_fmha_fp32_acc": 93, "context_fmha_typ": [5, 89], "context_init": 104, "context_len": [85, 98], "context_length": [80, 81, 85, 92], "context_logit": [68, 85], "context_mem_s": 85, "context_onli": 68, "context_parallel_s": 68, "context_phas": 5, "context_pre_onli": 81, "context_request": 104, "context_serv": 31, "contextchunkingpolici": [0, 68, 79, 93], "contextexecutor": 2, "contextfmha": 1, "contextidx": 0, "contextlogit": 0, "contextmanag": 67, "contextparallel": 1, "contextphaseparam": [0, 68], "contextpositionid": 1, "contextprefillposit": 0, "contextrequest": 1, "contigu": [2, 8, 74, 80, 93], "continu": [1, 3, 5, 13, 24, 26, 31, 33, 62, 63, 68, 69, 75, 77, 85, 104], "contract": 71, "contrast": [6, 13, 98], "contrib": 22, "contribut": [20, 28, 29, 30, 71, 80, 93], "contributor": [27, 30, 31, 89], "control": [0, 2, 5, 6, 7, 12, 32, 40, 45, 68, 70, 71, 73, 79, 80, 81, 85, 90, 93], "conv": 80, "conv1d": [33, 80, 81], "conv2d": [80, 81], "conv3d": [80, 81], "conv_bia": 80, "conv_kernel": 85, "conv_stat": 82, "conv_state_or_ptr": 80, "conv_transpose2d": 80, "conv_weight": 80, "conveni": [1, 15, 20, 63], "convent": [20, 80], "convers": [1, 18, 25, 26, 31, 55, 62, 86, 93], "convert": [0, 1, 10, 14, 15, 16, 17, 18, 20, 30, 51, 69, 71, 73, 75, 86, 92, 93, 98], "convert_and_load_weights_into_trtllm_llama": 20, "convert_checkpoint": [10, 14, 15, 16, 17, 20, 73, 74, 86, 92, 93], "convert_coneckpoint": 4, "convert_hf_mpt_legaci": 93, "convert_load_format": 68, "convert_util": 93, "convert_weights_from_custom_training_checkpoint": 20, "convkernel": 1, "convolut": [0, 85], "convtranspose2d": 81, "coordin": [13, 30, 62, 80], "copi": [0, 1, 2, 9, 13, 30, 33, 36, 68, 75, 80, 89, 93, 98], "copy_on_partial_reus": 68, "copyfrom": 1, "copyonpartialreus": 0, "copytask": 1, "copytaskmappag": 1, "copyto": 0, "copytocpu": 0, "copytogpu": 0, "copytomanag": 0, "copytopag": 1, "copytopin": 0, "copytopooledpin": 0, "core": [6, 7, 10, 14, 17, 20, 22, 23, 25, 29, 63, 68, 71, 74, 86, 92, 93, 94, 97], "corner": 29, "coroutin": [48, 49, 68], "correct": [3, 5, 10, 13, 28, 93], "correctli": [9, 80, 93, 96], "correspond": [0, 1, 4, 5, 7, 8, 10, 13, 18, 20, 28, 30, 31, 34, 64, 68, 70, 78, 80, 81, 85, 86, 87, 90, 92, 93, 96], "correspondingli": 30, "corrupt": 30, "cost": [9, 17, 27, 28, 29, 30, 51, 71, 74, 89, 93], "costli": 27, "could": [0, 7, 8, 9, 16, 30, 47, 48, 49, 50, 68, 73, 89, 92, 93], "couldn": 77, "count": [0, 1, 6, 30, 34, 42, 43, 51, 67, 71, 86], "count_include_pad": [80, 81], "countlocallay": 1, "countlowerranklay": 1, "cours": 13, "cover": [21, 30, 75, 76, 78, 87], "coverag": [30, 68], "cp312": 63, "cp_config": 68, "cp_group": [80, 81], "cp_rank": [80, 81], "cp_size": [80, 81, 84, 93], "cp_split_plugin": 80, "cpp": [3, 5, 6, 12, 17, 21, 29, 34, 53, 62, 63, 70, 71, 72, 73, 92, 93], "cpp_e2e": 85, "cpp_extens": 65, "cpp_llm_onli": 85, "cpp_onli": 63, "cpu": [0, 1, 8, 9, 10, 14, 17, 27, 28, 30, 33, 34, 65, 68, 80, 89, 92, 93, 98, 100], "cpumemusag": [0, 68], "crash": 93, "creat": [1, 3, 7, 8, 9, 13, 14, 15, 17, 19, 20, 27, 32, 34, 35, 40, 47, 48, 49, 50, 51, 57, 58, 59, 60, 63, 68, 69, 71, 72, 73, 77, 78, 80, 81, 82, 85, 86, 88, 89, 93, 94, 96, 97, 98, 104], "create_allreduce_plugin": 80, "create_attention_const_param": 81, "create_builder_config": 14, "create_cuda_graph_metadata": 98, "create_execution_context": 85, "create_fake_weight": 80, "create_network": 17, "create_pytorch_model_based_executor": [103, 104], "create_runtime_default": 82, "create_sinusoidal_posit": 80, "create_sinusoidal_positions_for_attention_plugin": 80, "create_sinusoidal_positions_for_cogvlm_attention_plugin": 80, "create_sinusoidal_positions_long_rop": 80, "create_sinusoidal_positions_yarn": 80, "createloramodul": 1, "creation": [1, 68, 80, 89], "creativ": 6, "criteria": [85, 100], "critic": [27, 30, 31, 71, 92], "crop": 81, "cropped_pos_emb": 81, "cross": [0, 10, 11, 27, 28, 30, 68, 80, 85, 93], "cross_attent": [81, 85], "cross_attention_dim": 81, "cross_attention_mask": [81, 85], "cross_attention_mask_for_context": 85, "cross_attention_mask_for_gen": 85, "cross_attention_norm": 81, "cross_attention_norm_num_group": 81, "cross_attention_packed_mask": 81, "cross_attn_dens": [10, 33], "cross_attn_k": [10, 33], "cross_attn_q": [10, 33], "cross_attn_qkv": [10, 33], "cross_attn_v": [10, 33], "cross_kv": 80, "cross_kv_cache_block_offset": [81, 85], "cross_kv_cache_fract": [68, 85], "cross_kv_cache_gen": [81, 82], "cross_kv_length": 80, "cross_kv_reus": [81, 82], "crossattentionmask": 0, "crosskvcachefract": [0, 93], "crosskvcachestat": 0, "crucial": [13, 17, 26, 97], "ctor": 80, "ctx": [0, 21, 31], "ctx1dep4": 31, "ctx_batch_siz": 94, "ctx_enable_attention_dp": 94, "ctx_gpu": 94, "ctx_max_num_token": 94, "ctx_param": 31, "ctx_request_id": 68, "ctx_tp_size": 94, "ctxenginepath": 0, "ctxexecutorconfig": 0, "ctxreqrat": 31, "cu": [17, 27], "cu12": 93, "cu128": 65, "cuassert": 92, "cubla": 29, "cublaslt": [33, 78], "cublasltmatmul": 29, "cublasscaledmm": 29, "cuda": [0, 1, 2, 5, 11, 17, 21, 28, 29, 30, 32, 51, 63, 65, 68, 70, 71, 82, 85, 89, 92, 93, 98, 99, 103], "cuda_arch": 63, "cuda_architectur": [12, 21, 63], "cuda_graph_batch_s": 68, "cuda_graph_cache_s": 68, "cuda_graph_config": [21, 28, 29, 30, 68, 72], "cuda_graph_inst": 92, "cuda_graph_mod": [68, 85, 92], "cuda_hom": 65, "cuda_launch_block": 92, "cuda_stream": 92, "cuda_stream_guard": 85, "cuda_stream_sync": 80, "cudadevicegetstreampriorityrang": 1, "cudaevent_t": 1, "cudaeventdisabletim": 1, "cudagraph": 93, "cudagraphcaches": 0, "cudagraphconfig": 68, "cudagraphlaunch": 92, "cudagraphmod": 0, "cudamalloc": [1, 2], "cudamallocasync": [1, 2], "cudamempool": 1, "cudamempoolptr": 1, "cudaprofilerapi": 70, "cudart": 92, "cudastream": 0, "cudastream_t": 1, "cudastreamcreatewithflag": 1, "cudastreamnonblock": 1, "cudastreamptr": [0, 1], "cudeviceptr": 1, "cudnn": 93, "cufil": 0, "cumemgenericallocationhandl": 1, "cumlogprob": [0, 1], "cumlogprobscba": 1, "cumsum": [80, 93], "cumsumgenerationlength": 1, "cumsumlastdim": 80, "cumsumlength": 1, "cumul": [0, 1, 68, 80], "cumulative_logprob": [40, 68], "curand": 93, "curl": [32, 34, 61, 86], "currenc": 71, "current": [0, 1, 2, 3, 5, 10, 13, 21, 26, 27, 28, 29, 30, 31, 33, 40, 46, 55, 63, 64, 68, 71, 75, 77, 78, 79, 80, 85, 86, 88, 89, 91, 93, 95, 97, 98, 103, 104], "current_image_tag": 88, "current_stream": 92, "currentexpandindic": 1, "curv": [25, 31], "custom": [6, 17, 20, 22, 27, 28, 30, 31, 33, 44, 51, 63, 67, 69, 75, 78, 80, 85, 88, 93, 97, 98], "custom_all_reduc": 93, "custom_mask": 80, "customallreduc": 93, "customized_key_dict": 18, "customized_preprocess": 18, "customizedmodulea": 18, "customizedmoduleb": 18, "cutlass": [12, 29, 68, 93], "cutlass_kernel": 12, "cxx11": 63, "cyclic": [62, 80, 85], "d": [1, 10, 12, 32, 34, 35, 37, 38, 39, 52, 53, 54, 55, 71, 80, 81, 86, 92, 93], "d0": 27, "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b": 71, "d_": 28, "d_6": 28, "dangl": 7, "data": [0, 1, 2, 5, 6, 8, 11, 17, 18, 22, 23, 24, 25, 26, 27, 30, 31, 33, 51, 58, 68, 71, 72, 73, 80, 82, 88, 91, 92, 93, 96, 99], "data_path": 53, "data_typ": [14, 16], "datacontext": 0, "dataset": [27, 28, 29, 32, 34, 38, 53, 58, 68, 70, 75, 93], "dataset_fil": 72, "dataset_path": 71, "datatyp": [0, 1, 6, 17, 80, 85, 90, 92], "datatypetrait": 1, "date": 20, "datetim": 68, "db": 87, "dbrx": [90, 91, 93], "dbrxconfig": 82, "dbrxforcausallm": 82, "dconv": 80, "de": 1, "deactiv": 40, "dead": 93, "deal": [5, 7, 92], "dealloc": [1, 8, 104], "debug": [0, 8, 30, 33, 34, 62, 63, 85, 89, 93], "debug_buff": 92, "debug_mod": [85, 92], "debug_tensors_to_sav": 85, "debugconfig": 0, "debuginputtensor": 0, "debugoutputtensor": 0, "debugtensor": 0, "debugtensornam": 0, "debugtensorsmaxiter": 0, "debugtensorsperiter": 0, "dec": [33, 85, 93], "decai": [0, 6, 68], "decid": [5, 16, 30, 62, 71, 76, 77, 90, 97, 104], "decilmforcausallm": 91, "decis": [30, 55, 80], "declar": [1, 6, 7, 20, 97, 103], "decltyp": [0, 1], "decod": [0, 1, 2, 5, 6, 15, 20, 27, 29, 30, 31, 32, 34, 45, 62, 67, 68, 71, 80, 82, 85, 91, 93, 96, 99, 100, 102, 103], "decode_batch": 85, "decode_duration_m": 68, "decode_regular": 85, "decode_retention_prior": 68, "decode_stream": 85, "decode_words_list": 85, "decode_wrapp": 98, "decodedurationm": 0, "decoder_batch": 1, "decoder_input_id": [82, 85], "decoder_language_adapter_rout": 85, "decoder_lay": 96, "decoder_start_token_id": 33, "decoderbuff": 1, "decoderenginebuff": 0, "decoderetentionprior": 0, "decoderjsonconfigstr": 0, "decoderlay": 96, "decoderlayerlist": 15, "decoderlookaheadbuff": 1, "decodermaskedmultiheadattent": 5, "decodermodel": [0, 82, 96], "decodermodelforcausallm": [15, 20, 82, 96], "decodermodelpath": 0, "decoderst": 93, "decoderxqarunn": 5, "decoding_config": 68, "decoding_typ": [21, 28, 32, 68], "decodingbaseconfig": 68, "decodingconfig": [0, 1], "decodinginputptr": 1, "decodingit": 0, "decodinglayerworkspac": 1, "decodingmod": [0, 1, 93], "decodingoutputptr": 1, "decompos": [5, 30], "decor": 96, "decoupl": [12, 27, 30, 31, 89], "decreas": [22, 23, 75], "dedic": [27, 29, 30, 31, 92], "deduc": [30, 33, 34, 93], "deep": [17, 23, 24, 32, 70, 80, 93], "deepep": 30, "deeper": 28, "deepgemm": 21, "deeplearn": [17, 80, 92], "deepli": 30, "deepseek": [30, 34, 56, 61, 70, 72, 91, 93], "deepseek_v1": 93, "deepseek_v2": 93, "deepseek_v3": [27, 93], "deepseekforcausallm": 82, "deepseekv1config": 82, "deepseekv2": 80, "deepseekv2attent": 81, "deepseekv2config": 82, "deepseekv2forcausallm": 82, "deepseekv3forcausallm": 91, "deepseekv3routingimpl": 29, "deepspe": 16, "def": [7, 15, 17, 18, 20, 44, 46, 47, 48, 49, 50, 51, 55, 56, 65, 73, 75, 78, 79, 86, 92, 96, 104], "default": [0, 1, 2, 3, 4, 5, 6, 9, 12, 16, 18, 20, 28, 29, 33, 34, 35, 40, 51, 56, 62, 63, 64, 68, 70, 72, 75, 76, 77, 78, 79, 80, 82, 85, 86, 87, 88, 89, 90, 92, 93, 96, 98, 100], "default_net": 80, "default_plugin_config": 82, "default_trtnet": 17, "defaultvalu": 1, "defer": 80, "defin": [0, 1, 3, 5, 7, 13, 16, 17, 18, 19, 20, 21, 24, 30, 33, 69, 71, 78, 80, 81, 87, 88, 90, 93, 94, 96, 98], "definit": [3, 5, 8, 19, 20, 27, 62, 69, 80, 92], "deftruth": 93, "degrad": [0, 2, 33, 75], "degre": [30, 47, 48, 50, 72, 75, 78, 88], "delai": [30, 31, 72, 93], "deleg": [80, 98], "delet": [0, 1, 30, 83, 92], "deliv": [21, 22, 25, 27, 28, 72], "delta": [0, 27, 28, 80, 81], "delta_bia": 80, "delta_softplu": 80, "delv": 29, "demand": [27, 29, 30, 31, 51], "demo": [27, 34, 38, 58], "demonstr": [3, 18, 23, 27, 30, 31, 67, 73, 75, 77, 78], "denois": 81, "denot": 13, "dens": [4, 5, 10, 16, 18, 80], "dense_4h_to_h": 18, "dense_bia": 81, "dense_h_to_4h": 18, "densiti": 26, "dep": 63, "dep4": 31, "dep8": 31, "depend": [0, 2, 3, 5, 6, 7, 12, 13, 16, 24, 30, 31, 32, 34, 65, 68, 72, 73, 75, 78, 80, 89, 92, 93, 103], "deploi": [13, 16, 30, 34, 62, 65, 69], "deplot": [91, 93], "deploy": [26, 27, 30, 31, 32, 67, 69, 71, 75, 86, 93], "deprec": [12, 33, 68, 69, 71, 93], "deprecationwarn": 71, "depriorit": 12, "depriv": 7, "depth": 13, "dequ": [0, 1], "dequant": [5, 11, 62, 80], "deregistermemori": 0, "deriv": [17, 18, 80, 89, 97], "desc": 0, "descendli": 6, "describ": [0, 5, 6, 8, 9, 10, 13, 15, 17, 18, 19, 21, 25, 30, 31, 34, 36, 38, 58, 63, 65, 71, 72, 78, 80, 87, 90, 92, 98], "descript": [0, 1, 6, 10, 34, 62, 71, 72, 78, 80, 98], "descriptor": 68, "deseri": [0, 20], "deserializeadditionalmodeloutput": 0, "deserializeadditionaloutput": 0, "deserializeagentst": 0, "deserializebool": 0, "deserializecachest": 0, "deserializecachetransceiverconfig": 0, "deserializecommst": 0, "deserializecontextphaseparam": 0, "deserializedatatransceiverst": 0, "deserializedebugconfig": 0, "deserializedecodingconfig": 0, "deserializedecodingmod": 0, "deserializedisservingrequeststat": 0, "deserializedynamicbatchconfig": 0, "deserializeeagleconfig": 0, "deserializeexecutorconfig": 0, "deserializeextendedruntimeperfknobconfig": 0, "deserializeexternaldrafttokensconfig": 0, "deserializeguideddecodingconfig": 0, "deserializeguideddecodingparam": 0, "deserializeinflightbatchingstat": 0, "deserializeiterationstat": 0, "deserializeiterationstatsvec": 0, "deserializekvcacheconfig": 0, "deserializekvcacheretentionconfig": 0, "deserializekvcachestat": 0, "deserializelookaheaddecodingconfig": 0, "deserializeloraconfig": 0, "deserializemodeltyp": 0, "deserializemropeconfig": 0, "deserializemultimodalinput": 0, "deserializeorchestratorconfig": 0, "deserializeoutputconfig": 0, "deserializeparallelconfig": 0, "deserializepeftcacheconfig": 0, "deserializeprompttuningconfig": 0, "deserializerequest": 0, "deserializerequestperfmetr": 0, "deserializerequeststag": 0, "deserializerequeststat": 0, "deserializerequeststatsperiter": 0, "deserializerequeststatsperiterationvec": 0, "deserializerespons": 0, "deserializeresult": 0, "deserializesamplingconfig": 0, "deserializeschedulerconfig": 0, "deserializesocketst": 0, "deserializespecdecfastlogitsinfo": 0, "deserializespecdecodingstat": 0, "deserializespeculativedecodingconfig": 0, "deserializestaticbatchingstat": 0, "deserializestr": 0, "deserializetensor": 0, "deserializetimepoint": 0, "deserializetokenrangeretentionconfig": 0, "design": [1, 11, 13, 17, 18, 20, 21, 26, 27, 28, 29, 31, 67, 73, 86, 97, 98, 103], "desir": [3, 72, 80, 86, 88, 98, 102], "destin": [52, 53, 54], "destroi": [1, 89], "destroyipcmemori": 1, "destructor": 1, "detach": 32, "detail": [0, 3, 5, 11, 13, 15, 17, 21, 27, 29, 30, 31, 33, 34, 40, 44, 46, 62, 71, 72, 73, 75, 79, 80, 82, 86, 87, 88, 89, 92, 93, 97, 98, 103], "detect": [0, 3, 30, 34, 68, 80, 88, 93], "detect_format": 18, "determin": [0, 1, 5, 6, 10, 20, 28, 30, 31, 68, 74, 75, 79, 80, 82, 90, 94, 97, 103, 104], "determinenumpag": 1, "determinist": [78, 93], "detoken": [68, 93, 97], "detokenizedgenerationresultbas": 68, "dev": [30, 32, 62, 65, 93], "dev_container_imag": 88, "devcontain": 88, "devel": [35, 36, 63], "develop": [15, 16, 17, 20, 27, 28, 30, 31, 32, 35, 47, 48, 50, 62, 63, 65, 69, 73, 80, 87, 88, 91, 93, 96], "deviat": [30, 72], "devic": [0, 1, 2, 30, 31, 51, 68, 75, 80, 82, 84, 85, 92], "device_id": 85, "device_map": 84, "device_memory_size_v2": 89, "device_num_expert": 80, "device_request_typ": 82, "deviceallocationnvl": 1, "devicecach": 1, "devicecacheperc": 0, "deviceid": [0, 1, 2], "dgx": [6, 17, 21, 29, 87], "di": [28, 30, 31], "diagon": 80, "diagram": [13, 29, 31], "diamond": [27, 29], "dict": [15, 18, 20, 68, 80, 82, 85, 93, 96, 103], "dict_kei": 92, "dictat": 77, "dictionari": [16, 18, 68, 81], "didn": 77, "differ": [0, 1, 2, 4, 5, 6, 8, 9, 11, 15, 16, 17, 18, 20, 21, 26, 28, 29, 30, 31, 33, 34, 38, 58, 63, 68, 69, 71, 73, 75, 77, 78, 80, 82, 85, 89, 90, 93, 94, 98, 102], "differenti": 80, "difftyp": 1, "diffus": [34, 38, 58, 81, 93], "diffusersattent": 81, "digit": 69, "dilat": [80, 81], "dim": [0, 1, 80, 81, 82, 85, 92], "dim0": 80, "dim1": 80, "dim_head": 81, "dim_in": 81, "dim_out": 81, "dim_rang": 80, "dimems": 1, "dimens": [0, 1, 5, 6, 10, 29, 30, 80, 81, 82, 89, 92, 93, 96], "dimension": 80, "diminish": 30, "dimrang": 80, "dimtype64": [0, 1], "dir": [40, 63, 71], "direct": [0, 2, 11, 20, 31, 65, 92], "directli": [0, 2, 6, 7, 13, 17, 20, 28, 29, 30, 31, 36, 40, 63, 67, 71, 78, 79, 80, 86, 93, 94, 98, 104], "directori": [0, 3, 15, 16, 17, 18, 20, 30, 33, 52, 53, 54, 63, 67, 68, 71, 72, 73, 82, 85, 86, 93, 94, 96], "disabl": [0, 1, 5, 6, 9, 14, 18, 30, 33, 68, 71, 75, 78, 79, 80, 83, 85, 88, 89, 93, 100], "disable_forward_chunk": 82, "disable_kv_cach": 85, "disable_overlap_schedul": [29, 46, 56, 68, 100], "disable_weight_only_quant_plugin": 82, "disable_xqa": 5, "disablelookahead": 1, "disablelookaheaddecod": 1, "disableseamlesslookaheaddecod": 1, "disadvantag": [20, 74], "disagg_config": 31, "disagg_executor": 0, "disaggexecutororchestr": 0, "disaggreg": [0, 62, 68, 93, 99], "disaggregated_mpi_work": 94, "disaggregated_param": 68, "disaggregatedparam": 68, "disaggserverbenchmark": 93, "discard": 75, "disclaim": [28, 73, 75, 77, 78], "disclosur": 93, "disconnect": 93, "discourag": [0, 6, 51, 68], "discov": [17, 65], "discoveri": 88, "discrep": [31, 63, 96], "discuss": [5, 28, 30, 73, 75, 78, 79, 93], "disk": [3, 20, 63], "dispatch": [0, 4, 20, 27, 30, 31, 40], "displai": [30, 68], "disservingrequeststat": 0, "disservingstat": 0, "dist": [21, 53, 65, 70, 71, 72, 73], "distanc": [5, 80], "distil": 93, "distinct": [8, 10, 13, 27, 31, 80], "distinguish": 9, "distribut": [1, 4, 5, 6, 17, 27, 30, 45, 52, 67, 71, 80, 85, 89, 94], "distserv": 2, "dit": [82, 93], "div": 80, "dive": [28, 69, 70], "divers": [0, 6, 70], "diversity_penalti": 6, "divid": [18, 28, 30, 80, 93], "divup": 80, "dl": 26, "dlsym": 0, "do": [1, 2, 7, 18, 20, 21, 26, 27, 28, 29, 30, 31, 40, 62, 65, 68, 73, 75, 78, 80, 86, 87, 92, 96, 98], "do_cross_attent": [80, 81], "do_layer_norm_befor": 16, "do_sampl": 6, "doc": [1, 17, 21, 25, 27, 30, 36, 75, 78, 80, 92, 93], "docker": [21, 52, 53, 54, 62, 86, 92, 93], "docker_run_arg": 21, "dockerfil": [35, 63], "document": [0, 2, 5, 6, 8, 9, 10, 13, 15, 16, 17, 19, 20, 23, 24, 26, 28, 30, 31, 34, 37, 38, 39, 40, 41, 42, 43, 46, 57, 58, 59, 60, 63, 64, 65, 66, 70, 72, 73, 79, 80, 86, 89, 90, 92, 97, 98], "doe": [0, 2, 5, 6, 10, 13, 20, 21, 22, 29, 30, 33, 60, 64, 68, 71, 72, 78, 80, 85, 86, 88, 89, 91, 93, 96, 104], "doesn": [1, 5, 27, 35, 40, 56, 71, 77, 78], "dollar": 71, "domain": [11, 30], "domin": [27, 30, 93], "don": [13, 20, 29, 30, 35, 74, 78, 80], "done": [1, 9, 17, 21, 29, 30, 31, 32, 69, 71, 75, 77, 80, 83, 96], "dongjiyingdji": 93, "dora": [33, 80, 81], "dora_plugin": [10, 33, 80], "dot": [18, 27, 80], "doubl": [0, 23, 76, 78, 92], "down": [0, 3, 10, 22, 28, 29, 30, 55, 69, 74, 80, 85], "down_proj": 18, "download": [19, 52, 53, 54, 55, 56, 63, 65, 67, 71, 73, 86, 92, 93], "downscale_freq_shift": 81, "downsid": 78, "downstream": 90, "dp": [21, 22, 25, 27, 29, 31, 93, 94], "dp8": [27, 29], "dprank": 0, "dpsize": 0, "dq": 62, "draft": [0, 1, 27, 28, 32, 33, 62, 68, 82, 85, 93], "draft_len": 82, "draft_path": 85, "draft_target": [56, 68], "draft_target_model": 13, "draft_token": [68, 82], "draft_tokens_extern": [33, 82], "draftacceptancethreshold": 1, "draftbuff": 1, "drafter": [13, 68], "draftindic": 1, "draftlen": 1, "draftlogit": 1, "draftoverhead": 0, "draftparticipantid": 0, "draftpath": 1, "draftpathshost": 1, "draftprob": 1, "draftrequestid": 0, "drafttargetdecodingconfig": 68, "drafttoken": [0, 1], "drafttokenid": 1, "drafttokensextern": 1, "dram": [0, 17, 68], "drastic": 29, "dreamgenx": 93, "drive": [17, 51, 71], "driven": [30, 69], "driver": [30, 89, 93], "drop": [21, 28, 29, 75, 77, 79], "dropout": 81, "dropout_prob": 81, "dry_run": [33, 68, 93], "dst": 1, "dstate": 80, "dstdesc": 0, "dsttype": 1, "dt_proj": 80, "dt_rank": 80, "dtype": [1, 7, 10, 14, 15, 16, 17, 20, 68, 71, 73, 74, 80, 81, 82, 83, 84, 85, 92, 93, 103], "dual": 63, "due": [0, 12, 13, 20, 21, 24, 27, 29, 30, 32, 63, 71, 73, 77, 79, 85, 87, 88, 93, 98, 102], "dummi": [68, 73, 93], "dump": [0, 3, 30, 63, 68], "dump_debug_buff": 85, "duplic": [29, 93], "duplicate_data": 80, "durat": [0, 30, 73], "duration_m": 68, "durationm": 0, "dure": [0, 1, 5, 6, 7, 11, 12, 13, 14, 17, 25, 27, 28, 29, 30, 31, 33, 63, 68, 70, 71, 78, 79, 85, 87, 89, 92, 98, 103], "dynam": [0, 27, 28, 30, 31, 33, 68, 71, 80, 82, 85, 89, 93, 104], "dynamic_batch_config": 68, "dynamic_batch_moving_average_window": 68, "dynamic_quant_bf16tonvfp4": 27, "dynamic_tree_max_topk": 68, "dynamicbatchconfig": [0, 68], "dynamicbatchmovingaveragewindow": 0, "dynamicbatchsizeconfig": 0, "dynamicdecodelay": 1, "dynamicqu": 27, "dynamictreemaxtopk": 0, "dynamictreemaxtopkhost": 1, "dynamo": 67, "dynlibload": 0, "e": [0, 2, 3, 5, 8, 9, 10, 11, 18, 28, 29, 32, 34, 35, 52, 53, 54, 63, 64, 67, 68, 70, 71, 80, 83, 85, 86, 88, 90, 92, 93, 94, 96, 100], "e2": [29, 31, 62], "e4m3": [11, 23], "e5m2": 23, "e752184d1181494c940579c007ab2c5f": 32, "each": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 16, 17, 21, 27, 28, 29, 30, 31, 33, 34, 40, 51, 52, 53, 54, 68, 71, 72, 73, 74, 77, 78, 79, 80, 81, 83, 85, 87, 89, 90, 92, 93, 94, 97, 98, 103, 104], "eager": [29, 69, 93], "eagl": [0, 1, 32, 33, 62, 68, 82, 85, 93, 99, 102], "eagle3": [56, 68], "eagle3_one_model": [56, 68], "eagle_choic": [68, 85], "eagle_dynamic_tree_max_top_k": 85, "eagle_posterior_threshold": 85, "eagle_temperatur": 82, "eagle_use_dynamic_tre": 85, "eaglechoic": [0, 1], "eagleconfig": [0, 1, 82], "eagledecodingconfig": [56, 68], "eagleforcausallm": 82, "eagleinput": 1, "eaglenetctxcontextlengthshost": 1, "eaglenetctxpastkeyvaluelengthshost": 1, "eaglenetctxrequesttypeshost": 1, "eaglenetgencontextlengthshost": 1, "eaglenetgenpastkeyvaluelengthshost": 1, "eaglenetgenrequesttypeshost": 1, "ealge2": 28, "earli": [85, 92, 93], "earlier": [0, 16, 75, 92], "early_stop": [6, 68, 85, 93], "early_stop_criteria": 85, "earlystop": [0, 1, 6], "eas": [19, 30, 31, 69, 72], "easi": [26, 30, 67, 73], "easier": [17, 20, 21, 28, 30, 71], "easili": [18, 19, 21, 27, 30, 69, 80, 86], "east": [15, 17, 92], "eastern": 86, "ebnf": [0, 3, 68], "echo": [32, 34, 35, 36, 53, 54], "ecosystem": 67, "eddi": 93, "edg": 23, "edit": [13, 63, 88], "ef648e7489c040679d87ed12db5d3214": 86, "effect": [0, 2, 6, 11, 13, 27, 28, 29, 33, 51, 65, 68, 75, 77, 78], "effici": [4, 5, 6, 9, 13, 17, 19, 27, 28, 29, 30, 31, 33, 34, 38, 47, 48, 50, 58, 87, 89, 91, 95, 97, 98, 103], "effort": [13, 16, 28, 29, 30, 31, 75, 93], "eg": 72, "eight": [21, 22], "einop": 80, "einstein": 80, "einsum": 80, "einsum_eq": 80, "either": [0, 1, 3, 19, 27, 29, 67, 68, 80, 87, 89, 92, 93], "element": [0, 1, 5, 6, 10, 11, 30, 68, 80, 81, 87, 90], "element_typ": 1, "elementwis": [7, 80], "elementwise_affin": 81, "elementwise_binari": 80, "elementwise_sub": 7, "elementwise_sum": 7, "elementwiseoper": [7, 80], "eleutherai": 71, "elif": [56, 104], "elimin": [2, 13, 27, 29, 33, 69, 71, 75, 77, 93], "ellipsi": 80, "els": [0, 17, 18, 20, 40, 51, 56, 80, 92, 104], "emb": [17, 58, 81], "embark": 69, "embed": [0, 9, 15, 28, 33, 68, 71, 80, 85, 93, 96, 98], "embed_dim": 81, "embed_posit": 81, "embed_positions_for_gpt_attent": 81, "embed_positions_for_gpt_attention_loc": 81, "embed_positions_loc": 81, "embed_token": [18, 96], "embedding_bia": 68, "embedding_dim": 81, "embedding_multipli": 82, "embedding_parallel_mod": 68, "embedding_scal": 82, "embedding_sharding_dim": [16, 82], "embeddingbia": [0, 1], "embeddingt": [0, 1], "emerg": [26, 27, 30], "emit": 68, "emphasi": 16, "empir": 30, "emploi": [13, 30, 31, 97, 104], "employe": 51, "empow": 27, "empti": [0, 1, 13, 40, 80, 93, 104], "emptybuff": 1, "emptygenslot": 0, "emptytensor": 1, "emul": [80, 93], "en": 93, "enabl": [0, 2, 3, 5, 6, 7, 10, 11, 12, 13, 14, 17, 18, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 36, 40, 44, 49, 50, 51, 62, 63, 65, 68, 71, 73, 77, 79, 80, 81, 82, 83, 85, 86, 88, 90, 92, 93, 94, 96, 98, 100, 102, 103], "enable_allreduc": 80, "enable_attention_dp": [21, 30, 32, 34, 53, 68], "enable_autotun": 68, "enable_batch_size_tun": 68, "enable_block_reus": [32, 34, 68], "enable_build_cach": [68, 93], "enable_chunked_context": [85, 93], "enable_chunked_prefil": [68, 93], "enable_context_fmha_fp32_acc": [68, 85], "enable_debug_output": [33, 68, 92], "enable_forward_chunk": 82, "enable_fp8": 11, "enable_fullgraph": 68, "enable_if_t": 1, "enable_inductor": 68, "enable_iter_perf_stat": [34, 68], "enable_iter_req_stat": 68, "enable_kv_cache_reus": 9, "enable_layerwise_nvtx_mark": 68, "enable_lora": [55, 68], "enable_max_num_tokens_tun": [68, 93], "enable_min_lat": 68, "enable_mixed_sampl": 68, "enable_multi_devic": 93, "enable_overlap_schedul": 34, "enable_partial_reus": 68, "enable_pdl": 94, "enable_piecewise_cuda_graph": 68, "enable_prompt_adapt": [68, 93], "enable_qkv": 81, "enable_tqdm": 68, "enable_trt_overlap": 93, "enable_trtllm_sampl": [68, 102], "enable_ucx": 93, "enable_userbuff": 68, "enable_xqa": 93, "enableattentiondp": [0, 1], "enablebatchsizetun": 0, "enableblockreus": [0, 9], "enablechunkedcontext": 0, "enablecontextfmhafp32acc": 0, "enabled_with_fp32_acc": 5, "enablelookaheaddecod": 1, "enablemaxnumtokenstun": 0, "enablepartialreus": 0, "enableseamlesslookaheaddecod": [0, 1], "enabletrtoverlap": 0, "enc": [33, 85, 93], "enc_dec": 6, "encapsul": [5, 6, 17, 80], "encdecmodelrunn": 85, "encod": [0, 5, 6, 23, 27, 33, 51, 68, 80, 85, 90, 91, 93], "encode_base64_content_from_url": 58, "encoded_vocab": [0, 3], "encodedvocab": [0, 3], "encoder_hidden_st": [81, 82], "encoder_input_featur": 85, "encoder_input_id": 85, "encoder_input_len_rang": 93, "encoder_input_length": [80, 81, 85], "encoder_language_adapter_rout": 85, "encoder_max_input_length": [81, 85], "encoder_output": [81, 82, 85], "encoder_output_length": 85, "encoder_run": 85, "encoderenginebuff": 0, "encoderhiddens": 1, "encoderinputfeatur": 0, "encoderinputtokenid": 0, "encoderjsonconfigstr": 0, "encoderlen": 0, "encodermodel": [0, 82], "encodermodelpath": 0, "encoderoutput": 0, "encoderoutputlength": 0, "encount": [18, 21, 32, 65, 92], "encourag": [0, 6, 20, 30, 51, 68], "end": [0, 1, 5, 6, 17, 28, 33, 51, 68, 69, 71, 75, 78, 79, 80, 86, 93, 103], "end_dim": 80, "end_id": [68, 85, 93], "end_thinking_phase_token": 68, "end_token": [0, 68], "endeavor": [27, 30, 31], "endid": [0, 1], "endpoint": [32, 42, 43, 68, 86, 93, 94], "endswith": 18, "enforc": [73, 80], "engin": [0, 1, 2, 3, 5, 6, 7, 10, 13, 14, 19, 20, 25, 27, 28, 29, 30, 31, 33, 34, 40, 55, 62, 65, 72, 74, 75, 77, 78, 79, 80, 82, 85, 89, 92, 93, 99], "engine_buff": 85, "engine_dir": [14, 15, 16, 17, 20, 71, 73, 85, 86, 92], "engine_inspector": 85, "engine_llama_3": 17, "engine_nam": 85, "engine_output": 33, "engineaddr": 1, "enginebuff": [0, 1], "enginefilenam": 1, "engineinput": 1, "engineoutput": 1, "enginepath": 1, "engines": 1, "enhanc": [4, 6, 13, 21, 27, 28, 29, 30, 31, 51, 69, 79, 89, 95, 98], "enjoi": [36, 47, 48, 50], "enough": [5, 9, 21, 28, 77, 89, 97, 104], "enqueu": [0, 3, 17, 85, 89, 93], "enqueuecontext": 0, "enqueuegener": 0, "enqueuerequest": [0, 3], "ensembl": 31, "ensur": [3, 4, 7, 12, 20, 28, 30, 32, 63, 68, 71, 77, 83, 96, 103], "enter": [7, 35, 63, 72, 77, 103], "enterpris": 46, "entir": [0, 3, 10, 17, 22, 27, 30, 69, 71, 72, 80, 89, 103], "entri": [0, 10, 44, 50, 63, 65, 71, 80, 86, 87, 93, 94], "entrypoint": [35, 67, 73], "enum": [0, 1], "enumer": [0, 1, 49, 51], "env": [34, 37, 38, 39, 41, 42, 43, 71, 88], "envelop": 30, "environ": [6, 11, 13, 21, 27, 30, 31, 34, 38, 52, 53, 54, 58, 60, 62, 63, 65, 70, 71, 73, 75, 77, 78, 92, 93, 94, 95, 98], "environment": 18, "eo": [6, 51, 68], "eof": [21, 28, 30, 34, 53], "eos_id": 30, "eos_token": 51, "eos_token_id": [3, 51, 85], "ep": [4, 21, 27, 28, 31, 34, 71, 80, 81], "ep2": 27, "ep2tp4": 27, "ep32": 30, "ep4": 30, "ep4tp2": 27, "ep8": [29, 30], "ep8tp8": 27, "ep_load_balanc": 30, "ep_siz": [30, 32, 34, 41], "epsilon": [0, 80], "eq": 80, "equal": [0, 1, 3, 4, 29, 30, 33, 40, 74, 80, 81, 89], "equal_progress": [68, 79], "equat": [25, 80], "equip": [2, 19], "equival": [27, 29, 75, 80, 86, 96], "equvili": 33, "erenup": 93, "err": [52, 53, 54], "error": [0, 2, 3, 10, 20, 29, 32, 33, 34, 62, 63, 65, 68, 73, 77, 88, 89, 93], "errorcod": 67, "errormsg": 0, "especi": [7, 28, 30, 31, 33, 47, 48, 50, 74, 77, 103], "essenti": [13, 30, 71], "establish": [29, 30, 31], "estim": [30, 71, 93, 104], "et": 22, "etc": [0, 1, 13, 30, 67, 68, 70, 71, 75, 78, 85, 89, 92, 96], "ethnzhng": 93, "eval": 46, "evalu": [11, 21, 23, 24, 29, 31, 62, 93], "even": [2, 5, 6, 17, 20, 26, 27, 30, 31, 33, 73, 77, 80, 88, 89], "evenli": [4, 27], "event": [0, 1, 62, 68], "event_buffer_max_s": 68, "eventbuffermaxs": 0, "eventid": 0, "eventptr": 1, "eventu": 12, "ever": [0, 78], "everi": [0, 3, 18, 27, 29, 30, 31, 51, 71, 73, 74, 80, 85, 87], "everyon": 28, "everyth": 17, "evict": [0, 1, 8, 9, 10, 28, 69, 71, 73, 77], "evolv": [5, 20, 27, 69, 90, 103], "ex": [53, 54], "exact": [5, 21, 89], "exactli": 87, "exam": 27, "examin": [13, 30], "exampl": [0, 2, 5, 6, 7, 9, 12, 13, 14, 15, 19, 20, 22, 24, 26, 28, 30, 31, 34, 40, 46, 52, 62, 63, 64, 68, 72, 73, 74, 75, 76, 77, 78, 79, 80, 85, 86, 88, 89, 90, 91, 92, 93, 95, 96, 98, 101, 102, 104], "exaon": [18, 91, 93], "exc": 49, "exce": [0, 2, 68, 79, 80], "exceed": [0, 89], "except": [0, 3, 5, 6, 20, 27, 28, 30, 33, 51, 74, 80, 92, 93], "excess": [5, 30], "exchang": 68, "excit": [47, 48, 49, 50], "exclud": [1, 68, 75, 80, 93], "exclude_input_from_output": 68, "exclude_modul": [16, 68, 93], "excludeinputfromoutput": 0, "exclus": [1, 6, 90, 93], "exec": [70, 86], "execut": [0, 3, 6, 10, 13, 17, 19, 20, 27, 29, 30, 31, 62, 68, 69, 70, 71, 77, 79, 80, 85, 86, 87, 88, 89, 94, 97, 104], "executor": [1, 2, 9, 13, 14, 19, 31, 40, 55, 62, 68, 69, 71, 79, 85, 89, 93, 97], "executor_config": 103, "executorconfig": [0, 3, 14], "executorexamplefastlogit": 93, "exhaust": [0, 19, 31], "exist": [1, 6, 9, 10, 13, 18, 20, 27, 29, 30, 33, 60, 63, 68, 71, 85, 88, 93, 98], "exit": [30, 72, 85], "exp": 80, "expand": [0, 24, 26, 28, 80, 85, 93], "expand_dim": 80, "expand_dims_lik": 80, "expand_mask": 80, "expand_shap": 80, "expanded_idx_to_permuted_idx": 80, "expans": 80, "expect": [0, 5, 6, 11, 15, 17, 18, 20, 24, 28, 30, 31, 32, 33, 40, 52, 53, 54, 62, 68, 71, 73, 76, 80, 92, 93], "expens": [3, 13, 31, 69, 74, 75, 79], "experi": [12, 13, 25, 26, 27, 29, 30, 31, 51, 67, 69, 70, 71, 92, 94], "experiment": [5, 6, 13, 18, 28, 34, 52, 53, 54, 62, 71, 90, 93, 95], "expert": [10, 21, 34, 50, 62, 68, 78, 93], "expert_scale_factor": 80, "expert_statist": 30, "expert_statistic_eplb": 30, "expert_statistic_iter_rang": 30, "expert_statistic_path": 30, "expertid": 30, "expertis": [27, 29, 30, 31], "expir": 0, "explain": [6, 17, 19, 29, 77, 80, 87, 89, 90, 97, 98], "explan": [21, 29, 78, 85, 87, 89], "explicit": [0, 1, 13, 30, 80, 93], "explicit_draft_token": [13, 33, 82], "explicitdrafttoken": [0, 1], "explicitdrafttokensdtyp": 1, "explicitdrafttokensinput": 1, "explicitdrafttokensmodul": 1, "expliciteosstop": 0, "explicitli": [1, 2, 7, 13, 17, 18, 29, 30, 33, 34, 40, 68, 93], "explor": [13, 27, 29, 30, 69], "expon": 23, "exponenti": [13, 31], "export": [2, 16, 20, 21, 27, 28, 30, 33, 34, 42, 43, 52, 53, 54, 71, 84, 85, 92, 93], "export_fmt": 101, "expos": [0, 6, 17, 32, 36, 63, 75, 86, 93], "express": [0, 3, 68, 80], "extend": [0, 3, 9, 17, 27, 28, 29, 30, 67, 68, 78, 80, 93], "extended_runtime_perf_knob_config": [68, 93], "extendedruntimeperfknobconfig": [0, 68], "extens": [16, 19, 31, 65, 69, 71, 87, 93], "extern": [0, 7, 8, 18, 85, 89], "external_checkpoint_dir": 18, "external_kei": 18, "external_weight": 18, "externaldrafttoken": 0, "externaldrafttokensconfig": [0, 1], "externaldrafttokensinput": 1, "externalstream": 51, "extra": [0, 2, 5, 9, 13, 16, 21, 27, 28, 33, 34, 41, 65, 68, 71, 72, 74, 75, 85, 87, 93, 100], "extra_arg": 53, "extra_bodi": 60, "extra_id": 9, "extra_llm_api_opt": [21, 28, 30, 32, 34, 41, 53, 71, 72], "extra_llm_api_options_eplb": 30, "extra_resource_manag": 68, "extra_token": 81, "extract": [0, 3, 30, 63, 70, 76, 80, 85], "extrapol": 80, "extrem": [17, 27, 30, 75, 77, 78], "f": [0, 5, 6, 32, 35, 44, 46, 47, 48, 49, 50, 51, 55, 56, 60, 65, 68, 70, 73, 79, 80, 86, 92], "face": [3, 10, 14, 19, 20, 30, 40, 68, 71, 82, 86, 93], "facilit": [7, 13, 30, 31, 86], "fact": [69, 71, 78], "factor": [26, 29, 30, 51, 74, 75, 80, 81, 89, 90], "factori": [20, 68, 85, 93], "factual": 6, "fail": [30, 32, 68, 85, 88, 89, 92, 104], "failur": [18, 30, 93], "fairli": 17, "fairseq": [91, 93], "fake": [9, 93], "fakebuff": 1, "falcon": [16, 26, 71, 90, 91, 93], "falconconfig": 82, "falconforcausallm": 82, "falconmodel": 82, "fall": [11, 65, 72, 93], "fallback": 18, "fals": [0, 1, 3, 5, 6, 7, 9, 16, 27, 29, 32, 33, 34, 46, 51, 53, 68, 80, 81, 82, 83, 84, 85, 93, 94], "false_output_valu": 80, "false_valu": 80, "famili": [5, 18, 30, 87, 91, 93], "familiar": [6, 17, 67, 73, 74, 76, 86], "famou": 6, "faq": 62, "far": [0, 3, 28], "fast": [0, 5, 8, 13, 30, 32, 68, 71, 74, 93], "fast_build": [33, 68, 93], "fastapi": 93, "fastapi_serv": 93, "faster": [5, 20, 23, 24, 28, 29, 33, 72, 73, 80], "fastlogit": 0, "fault": [30, 93], "favor": 93, "favorit": 55, "fc": [16, 17, 18, 92], "fc_gate": 81, "fc_gate_dora": 81, "fc_gate_lora": 81, "fc_gate_plugin": 81, "featur": [0, 2, 3, 5, 7, 8, 10, 11, 13, 16, 17, 18, 20, 26, 27, 28, 29, 30, 31, 33, 52, 53, 54, 62, 63, 67, 71, 75, 77, 78, 79, 80, 83, 85, 86, 87, 88, 91, 96, 98, 102], "feature_dim": 85, "februari": 29, "fed": [72, 82], "feed": 80, "feedback": [30, 93], "feedforward": 4, "feel": 55, "fetch": [0, 28, 34, 97], "few": [9, 17, 20, 26, 28, 29, 30, 65, 77], "fewer": [5, 13, 22, 98], "ffn": [4, 27], "ffn_hidden_s": 81, "fhma": 93, "field": [0, 6, 11, 16, 20, 34, 36, 40, 68, 69, 71, 75, 82, 83, 90, 93, 98], "field_nam": 68, "fifo": 30, "figur": [27, 28, 30, 31], "file": [0, 3, 4, 5, 7, 9, 16, 17, 18, 20, 21, 28, 30, 32, 33, 34, 42, 43, 70, 71, 72, 85, 86, 87, 88, 93, 96], "filepath": 1, "filesystem": [0, 1], "fill": [18, 36, 80, 98], "fill_attention_const_params_for_long_rop": 81, "fill_attention_const_params_for_rop": 81, "fill_attention_param": 81, "fill_none_tensor_list": 81, "fill_valu": 80, "fillemptyfieldsfromruntimedefault": 0, "filloper": 80, "filltaskstensor": 1, "filter_medusa_logit": 85, "final": [0, 1, 10, 27, 28, 30, 31, 33, 34, 35, 40, 80, 104], "final_logit_softcap": 82, "final_output_id": 85, "finalize_decod": 85, "find": [21, 29, 30, 31, 62, 75, 80, 92, 93], "find_best_medusa_path": 85, "fine": [13, 21, 29, 30, 71, 78, 81], "finer": 7, "finetun": 27, "finish": [0, 1, 3, 6, 8, 20, 28, 30, 40, 68, 69, 71, 85, 97, 103], "finish_reason": [32, 68, 86, 93], "finishedst": 1, "finishedsum": 1, "finishreason": [0, 1, 93], "first": [0, 1, 3, 5, 6, 7, 9, 10, 13, 19, 24, 26, 28, 29, 30, 31, 32, 33, 34, 35, 63, 67, 68, 71, 72, 73, 75, 77, 78, 79, 80, 89, 92, 93, 96, 98, 103, 104], "first_come_first_serv": [68, 79], "first_gen_token": 68, "first_lay": 85, "firstgentoken": 0, "firstit": 0, "firstli": [29, 30, 35, 77, 89], "firstscheduledtim": 0, "firsttokentim": 0, "fit": [1, 5, 22, 23, 68, 74, 75, 104], "fitting_request": 104, "fix": [8, 10, 13, 28, 29, 31, 71, 89], "fjosw": 93, "flag": [0, 1, 3, 5, 10, 20, 25, 30, 34, 40, 62, 71, 75, 76, 77, 79, 80, 89, 93], "flags_siz": 1, "flan": [90, 91], "flash": [5, 17], "flashattent": [5, 17, 86], "flashinf": 98, "flashinferattent": 98, "flashmla": [28, 93], "flatten": [1, 10, 25, 30, 80, 81], "flattenedinouts": 1, "flattenn": 1, "flayer": 7, "flayerinfomemo": 7, "flexibl": [13, 20, 27, 30, 40, 63, 67], "flight": [1, 19, 62, 71, 77, 79, 86, 89, 93], "flip": 80, "flip_sin_to_co": 81, "float": [0, 1, 6, 14, 16, 17, 23, 51, 68, 79, 80, 81, 82, 85, 90], "float16": [7, 10, 14, 15, 16, 20, 33, 74, 80, 82, 83, 86, 92], "float2": 80, "float32": [0, 16, 33, 80, 81, 82, 83], "floattensor": 96, "floattyp": [0, 1], "floor_div": 80, "floordiv": 80, "flop": 29, "flow": [7, 20, 27, 29, 31, 73, 74, 75, 77, 78, 93, 97, 104], "fly": [5, 80, 90], "fmha": [0, 33, 68, 80, 85, 89, 93], "fmt_dim": 1, "focu": [7, 26, 27, 30, 51, 70], "focus": [13, 71, 75, 76, 93], "fold": 89, "folder": [0, 3, 6, 20, 73, 88, 90, 91, 93], "folder_trt_llm": 17, "follow": [3, 6, 7, 10, 12, 13, 15, 16, 17, 18, 20, 21, 26, 27, 28, 29, 30, 32, 33, 34, 36, 40, 48, 49, 52, 53, 54, 63, 65, 67, 71, 72, 73, 74, 75, 76, 77, 78, 80, 86, 87, 88, 90, 91, 93, 94, 96, 98, 101, 102, 103], "footprint": [5, 22, 29, 89], "for_each_rank": 82, "forbid": 68, "forc": [0, 5, 27, 30, 31, 68, 71, 88], "force_drop_id": 81, "force_dynamic_quant": 68, "force_multi_block_mod": 71, "force_nccl_all_reduce_strategi": 93, "force_num_profil": 68, "force_words_id": 6, "forecast": 13, "fork": 70, "form": [0, 3, 5, 13, 31, 68, 80, 86], "format": [0, 3, 11, 16, 18, 20, 23, 26, 28, 29, 32, 43, 62, 63, 68, 69, 73, 75, 85, 86, 89, 92, 93, 98], "former": [17, 26], "formula": [29, 31, 80], "forth": 30, "forthcom": 32, "forum": 93, "forward": [0, 1, 7, 13, 15, 17, 28, 30, 31, 79, 80, 81, 82, 92, 93, 96, 97, 98, 103, 104], "forward_loop": 71, "forward_with_cfg": 82, "forward_without_cfg": 82, "forwardasync": 1, "forwarddispatch": 1, "forwardsync": 1, "found": [3, 4, 5, 6, 7, 13, 17, 19, 21, 23, 30, 51, 63, 65, 71, 73, 75, 78, 88, 90, 104], "foundat": 28, "four": [3, 7, 13, 16, 27, 28, 81], "fourth": 3, "fp": [90, 93], "fp16": [5, 10, 11, 14, 16, 18, 22, 23, 26, 33, 62, 71, 75, 78, 80, 86, 91, 92, 93], "fp32": [0, 5, 27, 29, 33, 62, 68, 80, 85, 86, 91, 92, 93], "fp4": [21, 28, 29, 30, 33, 56, 67, 93], "fp4_gemm": 12, "fp8": [11, 20, 22, 24, 25, 26, 27, 28, 29, 30, 32, 33, 44, 47, 62, 65, 67, 68, 71, 76, 78, 80, 83, 86, 89, 91, 93, 98, 101, 102], "fp8_block_scal": 68, "fp8_blockscale_gemm": 93, "fp8_inputs_overrid": 80, "fp8_kv_cach": [5, 90], "fp8_per_channel_per_token": 68, "fp8_qdq": 90, "fp8_rowwise_gemm_plugin": 33, "fp_valu": 5, "fpa_intb": 93, "frac": 31, "fraction": [0, 31, 34, 68, 80, 81, 85, 94], "framework": [13, 15, 16, 19, 20, 69, 80, 93], "franc": [15, 17, 44, 47, 48, 49, 50, 56, 65, 73, 79, 86, 92], "free": [0, 1, 8, 10, 17, 18, 29, 30, 34, 51, 69, 77, 81, 82, 85, 89, 103], "free_gpu_memory_fract": [34, 40, 68, 79, 93], "free_resourc": [97, 103], "freed": 71, "freedom": 20, "freegpumemoryfract": [0, 89, 93], "freenumblock": 0, "freez": 29, "french": 86, "freq": 80, "frequenc": [71, 81], "frequency_penalti": [68, 85, 93], "frequencypenalti": [0, 1, 6], "frequent": [9, 68, 92], "friend": [0, 1, 71], "friendli": [30, 80], "from": [0, 1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 24, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 40, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 62, 64, 65, 68, 69, 71, 72, 73, 74, 75, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 88, 89, 92, 93, 94, 96, 97, 98, 100, 101, 102, 103, 104], "from_argu": 82, "from_checkpoint": [20, 82], "from_config": 82, "from_dict": [68, 82], "from_dir": 85, "from_engin": 85, "from_hugging_fac": [15, 18, 20, 82], "from_jax": 20, "from_json_fil": [68, 82], "from_kera": 20, "from_meta_ckpt": [20, 82], "from_nemo": [20, 82], "from_pretrain": 82, "from_prun": 82, "from_serialized_engin": 85, "from_str": 80, "fromfil": 17, "fruit": 29, "full": [0, 4, 5, 6, 9, 10, 13, 23, 24, 28, 29, 30, 31, 34, 51, 68, 69, 70, 71, 74, 80, 85, 86, 87, 89, 92], "full_stop_token": 51, "fulli": [29, 44, 87, 93], "funcnam": 0, "function": [0, 1, 3, 5, 14, 15, 17, 19, 20, 27, 28, 30, 67, 68, 69, 70, 78, 82, 83, 85, 89, 90, 91, 92, 93, 103, 104], "functiont": 0, "further": [3, 4, 5, 13, 17, 22, 26, 28, 29, 30, 31, 32, 33, 71, 75, 78, 98], "furthermor": [13, 27, 30, 31, 75], "fuse": [5, 13, 17, 27, 29, 33, 78, 80, 86, 93, 96, 98], "fuse_a": [27, 29], "fuse_fp4_qu": 33, "fuse_qkv_project": 82, "fuseattentionwithbiaspass": 7, "fused_gate_up_dora": 81, "fused_gate_up_lora": 81, "fused_mo": 68, "fusedgatedmlp": [80, 81], "fusevalu": 1, "fusion": [7, 29, 33, 62, 69, 77, 89, 90, 93, 98], "fusion_op": 80, "futur": [2, 5, 6, 8, 12, 13, 18, 20, 26, 30, 33, 44, 46, 47, 48, 49, 50, 51, 56, 63, 65, 68, 69, 71, 73, 79, 80, 86, 89, 90, 93, 95], "fuyu": [91, 93], "g": [3, 8, 11, 18, 28, 29, 34, 52, 53, 54, 64, 68, 71, 77, 85, 86, 88, 94, 96, 100], "g1": 77, "g2": 77, "gain": [30, 74, 77], "game": 32, "gamma": 80, "gap": 31, "garbag": 68, "garbage_collection_gen0_threshold": 68, "gate": [10, 18, 33, 73, 80, 93], "gate_a": 80, "gate_a_bia": 80, "gate_bia": 80, "gate_proj": 18, "gate_x": 80, "gate_x_bia": 80, "gatedmlp": [80, 81], "gather": [0, 1, 33, 48, 49, 68, 80, 85], "gather_all_token_logit": [33, 93], "gather_context_logit": [33, 68, 82, 85], "gather_dim": [17, 80], "gather_generation_logit": [33, 68, 82, 85], "gather_last_token_logit": 80, "gather_nd": 80, "gather_output": 81, "gathercontext": [0, 93], "gatheredid": 1, "gatherel": 80, "gathergenerationlogit": 0, "gathermod": 80, "gathertre": 1, "gatherv2": 80, "gb": [2, 24, 29, 63, 68, 71], "gb200": [29, 31, 93], "gcc": 63, "gd": 0, "gdrdma": 2, "geforc": 93, "gegelu": 80, "gegelu_limit": 81, "geglu": 80, "gelu": [80, 82], "gelu_pytorch_tanh": 93, "gelu_tanh": 81, "gemm": [7, 29, 30, 33, 77, 80, 86, 89, 93], "gemm_allreduc": 80, "gemm_allreduce_plugin": [33, 85], "gemm_fc1": 27, "gemm_plugin": [10, 14, 16, 17, 33, 71, 75, 78, 81, 86], "gemm_swiglu": 80, "gemm_swiglu_plugin": [33, 75, 83], "gemma": [20, 90, 91, 93], "gemma2": 91, "gemma2_added_field": 82, "gemma2_config": 82, "gemma3": 93, "gemma3_added_field": 82, "gemma3_config": 82, "gemma_added_field": 82, "gemma_config_kwarg": 82, "gemmaconfig": 82, "gemmaforcausallm": 82, "gen": [31, 68, 93], "gen2dep4": 31, "gen4": 31, "gen8": 31, "gen_batch_s": 94, "gen_enable_attention_dp": 94, "gen_gpu_memory_fract": 94, "gen_max_num_token": 94, "gen_tp_siz": 94, "genai": [26, 34, 61], "genattent": 27, "genenginepath": 0, "gener": [0, 1, 3, 6, 9, 13, 16, 17, 18, 20, 21, 22, 23, 25, 27, 28, 29, 31, 33, 44, 45, 56, 62, 64, 65, 67, 68, 69, 70, 71, 72, 73, 74, 76, 77, 78, 79, 80, 82, 85, 86, 88, 89, 91, 92, 93, 94, 96, 97, 98, 101, 102, 103, 104], "generate_alibi_bias": 80, "generate_alibi_slop": 80, "generate_async": [40, 48, 49, 68, 93], "generate_eplb_config": 30, "generate_logn_sc": 80, "generate_tllm_weight": 18, "generated_text": [44, 55, 65, 73, 79, 86], "generatedtokensperenginestep": 1, "generation_complet": 104, "generation_in_progress": 104, "generation_logit": [68, 85], "generation_onli": 68, "generation_phas": 5, "generation_request": 104, "generation_serv": 31, "generation_to_complet": 104, "generationexecutor": [2, 93], "generationlength": 1, "generationlengthsdevic": 1, "generationlengthshost": 1, "generationlengthshostcopi": 1, "generationlogit": 0, "generationmixin": 82, "generationresult": 68, "generationsequ": 85, "generationsess": [5, 85, 89], "generationstep": 1, "genericprompttuningparam": 1, "genert": 2, "genexecutorconfig": 0, "genidx": 0, "genlengthlogitsprocessor": 51, "genlenthlogitsprocesor": 51, "genreqr": 31, "genrequest": 1, "get": [0, 1, 3, 5, 7, 10, 14, 18, 25, 28, 29, 30, 32, 34, 35, 36, 40, 60, 63, 65, 68, 69, 70, 73, 75, 80, 85, 86, 92, 93, 101, 104], "get_1d_sincos_pos_embed_from_grid": 81, "get_2d_sincos_pos_emb": 81, "get_2d_sincos_pos_embed_from_grid": 81, "get_audio_featur": 85, "get_batch_cache_indic": 103, "get_batch_idx": 85, "get_block_offset": 85, "get_buff": 103, "get_comm": 68, "get_config_group": 82, "get_context_phase_param": 68, "get_draft_model_prompt": 68, "get_first_past_key_valu": 81, "get_hf_config": 82, "get_input": 7, "get_kv_cache_ev": 68, "get_kv_cache_events_async": 68, "get_max_resource_count": [103, 104], "get_needed_resource_to_complet": [103, 104], "get_next_medusa_token": 85, "get_num_free_block": 103, "get_num_heads_kv": 85, "get_output": [7, 17], "get_par": [7, 80], "get_pytorch_backend_config": 68, "get_request_typ": 68, "get_rope_index": 85, "get_seq_idx": 85, "get_shap": 18, "get_slic": 18, "get_stat": [68, 93], "get_stats_async": 68, "get_timestep_embed": 81, "get_us": [7, 80], "get_visual_featur": 85, "get_vocab": [0, 3], "get_weight": 81, "getacceptancethreshold": 0, "getacceptedlengthscumsum": 1, "getacceptedpackedpath": 1, "getadditionalmodeloutput": 0, "getadditionaloutputnam": 0, "getaddr": 0, "getaddress": 1, "getagentst": 0, "getallnewtoken": 1, "getallottedtimem": 0, "getattentionconfig": 0, "getattr": 51, "getbackend": 0, "getbackendagentdesc": 0, "getbadword": 0, "getbatchingtyp": 0, "getbatchsizet": 0, "getbeamsearchbuff": 1, "getbeamsearchdiversityr": 0, "getbeamwidth": 0, "getbeamwidtharrai": 0, "getbuffermanag": 1, "getcacheindirectioninput": 1, "getcacheindirectionoutput": 1, "getcachest": 0, "getcachetransceiverconfig": 0, "getcapac": 1, "getcapacityschedulerpolici": 0, "getclientid": 0, "getcommptr": 1, "getcommst": 0, "getcommunicationmod": 0, "getcommunicationtyp": 0, "getconfig": 0, "getconnect": 0, "getconnectioninfo": 0, "getcontextchunkingpolici": 0, "getcontextexecutor": 0, "getcontextfmha": 1, "getcontextparallel": 1, "getcontextparallelgroup": 1, "getcontextparallelrank": 1, "getcontextphaseparam": 0, "getcopyonpartialreus": 0, "getcpu": 1, "getcpudiff": 1, "getcrossattentionmask": 0, "getcrosskvcachefract": 0, "getcudagraphcaches": 0, "getcudagraphmod": 0, "getcumlogprob": 1, "getdata": 0, "getdatatyp": [0, 1], "getdatatypenam": 1, "getdebugconfig": 0, "getdebuginputtensor": 0, "getdebugoutputtensor": 0, "getdebugtensornam": 0, "getdebugtensorsmaxiter": 0, "getdecodedurationm": 0, "getdecoderetentionprior": 0, "getdecoderstream": 1, "getdecodingconfig": 0, "getdecodingmod": 0, "getdefaultbatchslot": 1, "getdefaulteaglechoic": 1, "getdesc": 0, "getdevic": 1, "getdevicecacheperc": 0, "getdeviceid": 0, "getdeviceof": 1, "getdimens": 1, "getdirectori": 0, "getdrafttoken": 0, "getdstdesc": 0, "getdynamicbatchconfig": 0, "getdynamicbatchmovingaveragewindow": 0, "getdynamictreemaxtopk": 0, "geteaglebuff": 1, "geteaglechoic": 0, "geteagleconfig": 0, "getearlystop": 0, "getembeddingbia": 0, "getembeddingt": 0, "getenablebatchsizetun": 0, "getenableblockreus": 0, "getenablechunkedcontext": 0, "getenablecontextfmhafp32acc": 0, "getenablemaxnumtokenstun": 0, "getenablepartialreus": 0, "getenabletrtoverlap": 0, "getencodedvocab": 0, "getencoderhiddens": 1, "getencoderinputfeatur": 0, "getencoderinputtokenid": 0, "getencoderoutputlength": 0, "getendid": 0, "geterrormsg": 0, "geteventbuffermaxs": 0, "getexecutionconfig": 1, "getexplicitdrafttokensbuff": 1, "getextendedruntimeperfknobconfig": 0, "getexternaldrafttokensconfig": 0, "getfastlogit": 0, "getfinishedstep": 1, "getfinishedsum": 1, "getfinishreason": 1, "getfirstgentoken": 0, "getfirstlocallay": 1, "getfreegpumemoryfract": 0, "getfrequencypenalti": 0, "getfunctionpoint": 0, "getgatheredid": 1, "getgathergenerationlogit": 0, "getgemmallreducedtyp": 1, "getgenerationstep": 1, "getgenexecutor": 0, "getgpu": 1, "getgpudiff": 1, "getgpuspergroup": 1, "getgpuspernod": 1, "getgpuweightsperc": [0, 14], "getguid": 0, "getguideddecodingconfig": 0, "getguideddecodingparam": 0, "getguidetyp": 0, "gethandl": 0, "gethiddens": 1, "gethostcaches": 0, "gethostmemori": 1, "getid": 1, "getinittozero": 1, "getinputtokenextraid": 0, "getinputtokenid": 0, "getinst": [0, 1], "getipcunicastpoint": 1, "getisorchestr": 0, "getiterstatsmaxiter": 0, "getjointdecodinginput": 1, "getjointdecodingoutput": 1, "getkvcacheconfig": 0, "getkvcacheconfigref": 0, "getkvcacheeventmanag": 0, "getkvcacheretentionconfig": 0, "getkvcachetyp": 1, "getkvdatatyp": 1, "getlanguageadapteruid": 0, "getlastrank": 1, "getlatestdebugtensor": 0, "getlatestev": 0, "getlatestiterationstat": [0, 3], "getlatestrequeststat": 0, "getlayertyp": 1, "getlen": 0, "getlengthpenalti": 0, "getlevel": 1, "getlocalagentdesc": 0, "getlocalrank": 1, "getlogit": 0, "getlogitsdtyp": 1, "getlogitspostprocessor": 0, "getlogitspostprocessorconfig": 0, "getlogitspostprocessornam": 0, "getlogprob": 1, "getlookaheadbuff": 1, "getlookaheadconfig": 0, "getlookaheaddecodingconfig": 0, "getlookaheaddecodingmaxnumrequest": 0, "getloraconfig": 0, "getloramodul": 1, "getloraprefetchdir": 0, "getmanagedweightsmapopt": 1, "getmanageweightstyp": 1, "getmaxadapters": 0, "getmaxattentionwindowvec": 0, "getmaxbatchs": [0, 1], "getmaxbeamwidth": [0, 1], "getmaxdecodingdecodertoken": 1, "getmaxdecodingdrafttoken": 1, "getmaxdecodingenginetoken": 1, "getmaxdecodingtoken": 1, "getmaxdraftpathlen": 1, "getmaxencoderlen": 1, "getmaxinputlen": 1, "getmaxlorarank": 1, "getmaxnonleafnodesperlay": 1, "getmaxnumpath": 1, "getmaxnumtoken": [0, 1], "getmaxpagesperblock": 1, "getmaxpagesperblockdevic": 0, "getmaxpagesperblockhost": 0, "getmaxpathlen": 1, "getmaxpositionembed": 1, "getmaxpromptembeddingtables": 1, "getmaxqueues": 0, "getmaxseqidlemicrosecond": 0, "getmaxsequencelen": 1, "getmaxsequencelength": 1, "getmaxtoken": 0, "getmedusachoic": [0, 1], "getmemorytyp": [0, 1], "getmemorytypenam": 1, "getminp": 0, "getmintoken": 0, "getmlphiddens": 1, "getmodelconfig": [0, 1], "getmodelconfigmut": 1, "getmodelnam": 1, "getmodelvari": 1, "getmpist": 0, "getmropeconfig": 0, "getmropepositiondelta": 0, "getmroperotarycossin": 0, "getmultiblockmod": 0, "getmulticastpoint": 1, "getmultimodalembed": 0, "getmultimodalhash": 0, "getmultimodalinput": 0, "getmultimodallength": 0, "getmultimodalposit": 0, "getnam": [0, 1], "getnbattentionlay": 1, "getnbhead": 1, "getnbkvhead": 1, "getnblay": 1, "getnbrnnlay": 1, "getnextdrafttoken": 1, "getnextdrafttokenslength": 1, "getngrams": 0, "getnoderank": 1, "getnoderankof": 1, "getnorepeatngrams": 0, "getnormalizelogprob": 0, "getnotifiedsyncmessag": 0, "getnumcopystream": [0, 1], "getnumdecodingenginetoken": 1, "getnumdevicemodulelay": 0, "getnumensurework": 0, "getnumhostmodulelay": 0, "getnumkvheadsforgivenlay": 1, "getnumkvheadsperlay": 1, "getnumkvheadsperlayerlocalrang": 1, "getnumlanguag": 1, "getnumnod": 0, "getnumpackedmask": 1, "getnumpag": 1, "getnumputwork": 0, "getnumresponsesreadi": 0, "getnumreturnbeam": [0, 1], "getnumreturnsequ": 0, "getnumtransformerlay": 1, "getonboardblock": 0, "getop": 0, "getoptimaladapters": 0, "getoptprofilessplitpoint": 1, "getorchestratorconfig": 0, "getorchleadercomm": 0, "getoutputconfig": 0, "getpadid": 0, "getpagedcontextfmha": 1, "getpageptr": 1, "getpagewidth": 1, "getparallelconfig": 0, "getparentid": 1, "getparticipantid": 0, "getpath": 1, "getpathopt": 1, "getpeftcacheconfig": 0, "getperblockretentionprioritydur": 0, "getpin": 1, "getpinneddiff": 1, "getpinnedpool": 1, "getpinnedpooldiff": 1, "getpipelineparallel": 1, "getpipelineparallelgroup": 1, "getpipelineparallelrank": 1, "getpositionid": 0, "getposteriorthreshold": 0, "getppreducescatt": 1, "getprecis": 1, "getpresencepenalti": 0, "getprevdrafttokenslength": 1, "getprior": 0, "getprocessorbatch": 0, "getprocessormap": 0, "getprompttableoffload": 0, "getprompttuningconfig": 0, "getquantmod": 1, "getrank": 1, "getrecvpollperiodm": 0, "getremotenam": 0, "getrepetitionpenalti": 0, "getrepl": 0, "getreqid": 0, "getrequestid": 0, "getrequeststatsmaxiter": 0, "getrequesttyp": 0, "getresult": [0, 3], "getreturnallgeneratedtoken": 0, "getrnnconfig": 1, "getrotaryembeddingdim": 1, "getruntimedefault": 1, "getruntimetyp": 0, "getsamplingconfig": [0, 1], "getschedulerconfig": 0, "getschedulerconfigref": 0, "getse": 0, "getsecondaryoffloadminprior": 0, "getselfidx": 0, "getsequencelength": 1, "getserializedst": 0, "getshap": [0, 1], "getsinktokenlength": 0, "getsiz": [0, 1], "getsizeinbit": 1, "getsizeinbyt": [0, 1], "getsizeperhead": 1, "getskipcrossattnblock": 0, "getslotsperpag": 1, "getsocketst": 0, "getspawnprocess": 0, "getspecdecconfig": 0, "getspeculativedecodingmod": 1, "getspeculativedecodingmodul": 1, "getspeculativedecodingmoduleptr": 1, "getsrcdesc": 0, "getstat": 0, "getstatu": 1, "getstoptokenid": 0, "getstopword": 0, "getstream": [0, 1], "getsyncmessag": 0, "gettag": 0, "gettaskid": 0, "gettemperatur": 0, "gettensorparallel": 1, "gettensorparallelgroup": 1, "gettensorparallelrank": 1, "getter": 6, "gettoken": 0, "gettokenizerstr": 0, "gettokenrangeretentionconfig": 0, "gettokensperblock": 1, "gettopk": 0, "gettopp": 0, "gettoppdecai": 0, "gettoppmin": 0, "gettoppresetid": 0, "gettotalnumpag": 1, "gettransfermod": 0, "gettyp": [0, 1], "getunderlyingdecod": 1, "getunicastpoint": 1, "getusegpudirectstorag": 0, "getuseuvm": 0, "getuvm": 1, "getuvmdiff": 1, "getverificationsets": 0, "getvers": 1, "getvocabs": 1, "getvocabsizepad": 1, "getweight": 0, "getwindows": 0, "getworkerexecutablepath": 0, "getworlds": 1, "gh200": [87, 93], "ghz": 46, "gib": [9, 89], "gid": [0, 88], "gigabyt": 24, "git": [10, 21, 32, 63, 67, 86, 88, 92, 101], "github": [20, 21, 27, 30, 32, 51, 63, 64, 69, 86, 93, 101], "give": [3, 28, 29, 69, 75, 77, 82, 102], "given": [0, 1, 3, 6, 10, 18, 20, 21, 24, 30, 68, 70, 76, 77, 80, 81, 82, 84, 85, 89, 90, 93, 103], "givyboi": 55, "glm": [80, 91, 93], "glm4": 93, "global": [0, 5, 8, 17, 27, 29, 93], "global_max_input_length": 85, "global_max_output_length": 85, "globalrequestid": 0, "glossari": [22, 25], "gm": 92, "gnu": 63, "go": [5, 6, 74, 93], "goal": [30, 79], "goe": [28, 67, 71], "good": [3, 17, 21, 29, 30, 71, 74, 77, 78], "got": [0, 46, 47, 48, 49, 50, 51, 55, 67, 71, 92], "gpqa": [27, 29], "gpt": [1, 5, 13, 17, 19, 23, 26, 33, 62, 71, 80, 87, 89, 90, 91, 92, 93], "gpt2": [82, 92], "gpt3": 24, "gpt_attent": [5, 7, 25, 80, 86, 93], "gpt_attention_plugin": [10, 17, 33, 71, 81, 85, 92, 93], "gpt_attention_plugin_remove_pad": 7, "gpt_variant": [82, 93], "gptattent": 7, "gptattentionpluginremovepaddingrewritepass": 7, "gptconfig": 82, "gptdecod": 6, "gptdecoderbatch": 93, "gptdecoderptr": 1, "gptforcausallm": 82, "gptj": 82, "gptjconfig": 82, "gptjforcausallm": 82, "gptjmodel": 82, "gptlmheadmodel": 92, "gptmanag": 93, "gptmanagerbenchmark": [9, 63, 93], "gptmodel": 82, "gptmodelconfig": 93, "gptneoxforcausallm": 82, "gptneoxmodel": 82, "gptq": [26, 62, 91, 93], "gptsession": 93, "gptsessionbenchmark": 93, "gpu": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11, 13, 16, 19, 20, 23, 24, 25, 26, 28, 31, 32, 33, 34, 40, 52, 53, 54, 62, 63, 65, 67, 68, 72, 73, 74, 75, 78, 80, 82, 85, 86, 87, 91, 92, 93, 94, 97, 98, 100], "gpu_typ": 87, "gpu_weights_perc": [14, 85], "gpudirect": 0, "gpumemusag": [0, 34], "gpus_per_nod": [33, 34, 68], "gpuspernod": [1, 6], "gpusync": 1, "gpuweightsperc": [0, 14], "gqa": [5, 8, 22, 25, 33, 80, 93, 98], "grace": [9, 30, 65, 91], "gradient": 23, "gradual": [12, 20], "grain": [7, 30], "gram": 13, "grammar": [0, 3, 68], "granit": [91, 93], "graph": [0, 17, 21, 28, 29, 30, 62, 68, 70, 71, 80, 85, 86, 89, 92, 93, 98, 99, 103], "graph_rewrit": 7, "graphic": 32, "gratitud": 28, "gre": 34, "great": [22, 30, 32], "greater": [0, 2, 5, 25, 26, 27, 30, 33, 80], "greatli": [9, 20, 28, 75, 78], "greedi": [0, 6, 97], "greedy_sampl": 68, "greedysampl": 0, "greedysamplinghost": 1, "grid": [17, 75, 77, 80, 81], "grid_search_engin": 73, "grid_siz": 81, "grok": [91, 93], "groovi": 87, "ground": 70, "groundbreak": 69, "group": [0, 3, 4, 6, 8, 17, 22, 29, 30, 62, 68, 80, 81, 90, 93, 98], "group_cl": 82, "group_norm": 80, "group_siz": [16, 68, 80], "groupedrmsnorm": 27, "groupgemm": [29, 30], "groupnorm": [80, 81], "grow": [1, 13, 31, 77], "gsm8k": 29, "gt": 80, "gtc": [21, 27], "guarante": [0, 6, 9, 20, 30, 71, 72, 73, 75, 79], "guaranteed_no_evict": [0, 68, 71, 79], "guaranteednoevictschedul": 104, "guard": 73, "guid": [0, 17, 21, 26, 32, 45, 62, 67, 68, 69, 70, 72, 73, 74, 75, 78, 80, 92, 93, 98, 99], "guidanc": [13, 34, 78, 81, 82], "guided_decod": [46, 68], "guided_decoding_backend": [46, 68], "guideddecodingbackend": 0, "guideddecodingconfig": [0, 3], "guideddecodingparam": [0, 3, 46, 68], "guidelin": [2, 74], "guidetyp": [0, 3], "gw": 7, "h": [3, 5, 13, 18, 28, 32, 33, 34, 37, 38, 39, 73, 80, 82, 86, 93], "h0": 28, "h1": 80, "h100": [20, 26, 32, 33, 69, 72, 73, 75, 76, 77, 87, 93], "h20": 33, "h200": [23, 33, 72, 93], "ha": [0, 1, 3, 5, 9, 10, 11, 16, 17, 18, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 33, 36, 51, 63, 64, 68, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 85, 86, 89, 90, 92, 93, 97, 103, 104], "habitu": 87, "had": [20, 21, 29, 75, 77], "half": [0, 1, 17, 29, 73, 80], "halv": [23, 80], "hand": [9, 13, 19, 74, 87], "handl": [0, 1, 2, 4, 8, 18, 20, 22, 27, 31, 73, 75, 77, 78, 79, 80, 81, 96, 97], "handle_per_step": 85, "hang": [0, 30, 67, 92, 93], "happen": [3, 6, 9, 17, 30, 65, 89, 92], "happi": 85, "har": 29, "hard": [5, 68], "harder": 6, "hardwar": [8, 26, 29, 32, 40, 62, 63, 87, 93], "has_affin": 80, "has_bia": 80, "has_config_group": 82, "has_position_embed": 85, "has_scal": 80, "has_token_type_embed": 85, "has_zero_point": [16, 68], "hascontextawaitthread": 0, "hasdraftlogit": 1, "haserror": [0, 3], "hasgenawaitthread": 0, "hash": [0, 68], "hasresult": 0, "hasrnnconfig": 1, "hasspeculativedecodingmodul": 1, "hattizai": 93, "have": [0, 1, 3, 4, 5, 6, 9, 10, 12, 13, 16, 17, 18, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32, 33, 35, 52, 53, 54, 55, 56, 65, 67, 68, 69, 70, 71, 73, 74, 75, 76, 77, 78, 79, 80, 85, 86, 89, 91, 92, 93, 96], "hbm3": 72, "hbm3e": 24, "head": [1, 6, 8, 13, 17, 22, 28, 29, 33, 62, 71, 80, 81, 93, 98], "head_dim": [98, 103], "head_siz": [5, 80, 82, 85, 93], "header": 2, "headsiz": 80, "headsperlay": 1, "health": [32, 34, 55, 94], "healthi": 94, "heat": 6, "heavi": [78, 87], "heavier": 74, "heavili": 30, "height": [43, 81, 85], "hello": [44, 47, 48, 49, 50, 52, 55, 65, 73, 79, 86, 101, 102], "help": [2, 3, 5, 7, 17, 27, 28, 30, 31, 33, 34, 37, 38, 46, 51, 56, 57, 58, 63, 68, 70, 71, 72, 73, 76, 77, 78, 79, 80, 86, 93, 97], "helper": [1, 80], "henc": 96, "here": [3, 7, 10, 14, 15, 16, 17, 18, 20, 21, 23, 24, 28, 29, 30, 34, 36, 40, 44, 46, 51, 63, 65, 68, 70, 73, 74, 75, 77, 78, 80, 85, 86, 89, 90, 92, 95, 98, 103, 104], "heterogen": 2, "heurist": [5, 29, 71, 80, 88, 93], "hf": [6, 10, 14, 18, 33, 34, 47, 48, 49, 50, 52, 53, 54, 60, 71, 72, 73, 85, 91, 92, 101], "hf_config_or_dir": 82, "hf_home": 88, "hf_lora_convert": 10, "hf_model": [71, 82], "hf_model_dir": [14, 15, 16, 20, 82], "hf_model_nam": 71, "hf_model_or_dir": 82, "hf_quant_config": 71, "hf_token": 71, "hfconfigordir": 82, "hgx": 24, "hi": 10, "hidden": [0, 3, 4, 5, 6, 10, 13, 27, 28, 68, 80, 81, 93], "hidden_act": [16, 81, 82], "hidden_dim": [0, 5, 80], "hidden_dim_per_head": [5, 80], "hidden_dtyp": 81, "hidden_s": [0, 7, 16, 18, 80, 81, 82, 85, 96, 98], "hidden_size_in": 10, "hidden_size_out": 10, "hidden_size_per_head": 80, "hidden_st": [15, 80, 81, 82, 85, 92, 96], "hidden_states_for_emb": 82, "hiddens": [0, 1, 6], "hide": [27, 29], "hierarch": 16, "hierarchi": [20, 62, 80], "high": [3, 13, 15, 17, 20, 22, 26, 27, 28, 29, 31, 32, 67, 71, 79, 80, 89, 93], "higher": [0, 1, 5, 6, 9, 10, 13, 18, 22, 23, 25, 29, 30, 31, 69, 72, 79, 89, 93, 96], "highest": [6, 7, 23, 24], "highli": [13, 17, 29, 30, 70, 75], "highlight": [23, 26, 75, 77], "hin": 28, "hint": [71, 80], "histori": 29, "hit": [0, 29, 68, 72, 77, 78, 93], "hk": 13, "ho": 10, "hoc": [20, 85], "hold": [0, 1, 3, 4, 7, 8, 9, 10, 13, 30, 68, 74, 81, 89, 97], "home": [21, 71, 88], "home_dir": 88, "homo_head_pattern": 81, "homogen": 2, "hood": 67, "hope": [27, 30, 31], "hopper": [5, 9, 22, 23, 26, 28, 29, 30, 33, 62, 63, 65, 69, 75, 91, 93], "horizont": [29, 33], "host": [1, 10, 29, 31, 32, 34, 36, 41, 54, 62, 63, 65, 68, 78, 80, 93], "host_cache_s": 68, "host_context_length": [80, 81, 82, 85, 92], "host_context_progress": [80, 81, 92], "host_cross_kv_cache_block_offset": [81, 85], "host_cross_kv_cache_pool_map": 81, "host_cross_kv_cache_pool_point": 81, "host_kv_cache_block_offset": [80, 81, 85, 92], "host_kv_cache_block_point": 92, "host_kv_cache_pool_map": [80, 81, 92], "host_kv_cache_pool_point": [80, 81, 92], "host_max_attention_window_s": [80, 81, 92], "host_past_key_value_length": [80, 81, 92], "host_request_typ": [80, 81, 82, 92], "host_runtime_perf_knob": [80, 81, 92], "host_sink_token_length": [80, 81, 92], "hostcaches": [0, 9], "hostmemori": 1, "hostnam": [31, 34], "hot": 30, "hottest": 30, "hour": 73, "hous": [30, 74], "how": [0, 2, 3, 13, 15, 17, 18, 20, 30, 31, 33, 36, 44, 52, 62, 68, 70, 73, 75, 76, 78, 80, 86, 87, 89, 90, 92, 95, 97, 98], "howev": [2, 3, 5, 13, 20, 21, 22, 27, 28, 29, 30, 34, 71, 74, 75, 77, 78, 79, 89, 93, 96, 97], "hpc": 23, "html": [1, 17, 80, 92], "http": [0, 1, 4, 10, 17, 20, 21, 27, 32, 33, 34, 37, 38, 39, 51, 57, 58, 59, 60, 63, 65, 67, 80, 86, 87, 88, 90, 92, 93, 100, 101], "http_code": 32, "hub": [19, 32, 55, 68, 71, 86, 93, 101], "hug": [3, 10, 14, 19, 20, 40, 68, 71, 82, 86, 93], "huggingfac": [0, 10, 15, 16, 18, 20, 21, 34, 38, 55, 58, 67, 71, 72, 73, 86, 88, 91, 92, 93, 96], "huggingface_exampl": 101, "huggingface_hub": 55, "huggingface_model_card": 101, "human": [27, 71], "hundr": 30, "hurt": [29, 30, 78], "hw": [27, 29, 30], "hybrid": [4, 93], "hyper": 16, "hypothesi": 13, "i": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 36, 37, 39, 40, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 59, 63, 64, 65, 67, 68, 69, 71, 72, 73, 75, 76, 77, 78, 79, 80, 81, 82, 83, 85, 86, 87, 88, 90, 91, 92, 93, 94, 95, 96, 97, 98, 101, 102, 103, 104], "ia3": 5, "iactivationlay": 17, "ib": 87, "ibrahimamin1": 93, "ibufferptr": 1, "iconstantlay": 80, "icudaengin": [85, 89], "id": [0, 1, 3, 9, 28, 30, 32, 40, 49, 51, 67, 68, 71, 72, 80, 81, 85, 86, 98, 103], "idea": [10, 29, 30, 78], "ideal": [7, 30, 31, 75, 77, 93], "ident": [3, 9, 29, 33, 80, 102], "identifi": [0, 6, 10, 13, 17, 30, 31, 71, 77, 80], "idl": [0, 100], "idtyp": [0, 3], "idx": 85, "ieee": 90, "ieinsumlay": 80, "ielementwiselay": 80, "iexecutioncontext": [85, 89], "ifb": [13, 31, 93], "ifilllay": 80, "igatherlay": 80, "ignor": [33, 68, 71, 80, 85, 88], "ignore_eo": [68, 93], "igptdecod": 1, "ihostmemori": [1, 17, 85], "ii": [5, 80], "ij": 80, "ijk": 80, "ijl": 80, "ik": 80, "ikl": 80, "ilay": [7, 17], "illustr": [7, 13, 19, 27, 28, 30, 31], "ilogg": 1, "ilooplay": 80, "imag": [34, 38, 43, 52, 53, 54, 58, 62, 65, 71, 81, 85, 93], "image64": 58, "image_grid_thw": 85, "image_patches_indic": 85, "image_path": 85, "image_s": 82, "image_tag": [64, 86], "image_token_index": 85, "image_url": [34, 38, 58], "imatrixmultiplylay": 80, "imb": 30, "imbal": [30, 77], "imbalanc": 30, "immedi": [5, 13, 69, 73, 92], "immut": 1, "impact": [11, 13, 22, 26, 27, 28, 29, 30, 34, 55, 74, 75, 77, 78, 79], "imped": [26, 30], "impl": [0, 104], "implement": [2, 3, 5, 6, 8, 12, 13, 16, 17, 19, 20, 22, 29, 31, 32, 51, 62, 69, 80, 81, 82, 86, 90, 91, 92, 93, 96, 97, 103, 104], "implicit": [1, 5, 13, 80], "implicitli": 1, "import": [11, 13, 18, 20, 22, 26, 28, 29, 32, 34, 40, 44, 46, 47, 48, 49, 50, 51, 55, 56, 57, 58, 59, 60, 62, 65, 73, 75, 77, 78, 79, 86, 87, 91, 93, 95, 96, 97, 101, 102, 103], "importantli": [30, 88], "impos": 26, "improv": [5, 9, 11, 17, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 33, 47, 48, 50, 51, 62, 69, 71, 72, 73, 75, 76, 77, 78, 93, 95, 98, 100], "in_channel": 81, "in_featur": [16, 17, 81], "in_hidden_s": 80, "in_len": 7, "in_point": 80, "in_progress": 85, "includ": [0, 1, 3, 5, 6, 9, 10, 12, 13, 16, 17, 18, 19, 22, 23, 25, 28, 29, 30, 31, 33, 34, 40, 46, 63, 65, 67, 68, 69, 71, 75, 78, 80, 86, 87, 90, 92, 93, 94, 97, 98, 103, 104], "include_stop_str_in_output": 68, "inclus": 80, "incompat": [33, 93, 95], "incorpor": [0, 27, 30, 69, 93], "incorrect": [9, 13, 93], "increas": [0, 5, 9, 13, 17, 21, 23, 24, 27, 28, 29, 30, 31, 33, 51, 70, 71, 73, 75, 78, 79, 80, 87, 93, 104], "incred": 69, "increment": [30, 63, 93], "incur": [17, 27, 31], "inde": 89, "independ": [0, 1, 2, 3, 13, 31, 80], "index": [0, 1, 3, 8, 13, 18, 27, 32, 40, 62, 65, 68, 80, 85, 86, 87, 93, 98], "index_select": 80, "indic": [0, 1, 3, 5, 6, 13, 16, 31, 68, 79, 80, 81, 85, 89, 103], "indim": 1, "indimfirst": 1, "indirect": 1, "individu": [27, 30, 31, 87, 93], "indivis": 93, "inductor": 68, "industri": 71, "ineffici": [5, 27], "inetworkdefinit": [7, 17, 80], "inevit": 17, "infeas": 3, "infer": [0, 2, 6, 10, 13, 17, 19, 20, 21, 22, 23, 24, 27, 29, 33, 38, 44, 58, 62, 65, 67, 70, 72, 73, 74, 75, 76, 78, 79, 80, 85, 90, 92, 93, 97], "infer_shap": 85, "inferencerequest": 93, "infin": 36, "infinit": [17, 71, 72], "inflat": 27, "inflight": [0, 5, 10, 13, 34, 66, 68, 71, 76, 77, 80, 93, 98, 104], "inflight_request_id": 104, "inflightbatch": 0, "inflightbatchingstat": [0, 34], "influenc": [27, 78], "info": [0, 30, 33, 34, 71, 89, 92], "inform": [0, 1, 2, 3, 5, 6, 8, 13, 16, 17, 22, 25, 27, 28, 30, 31, 34, 62, 63, 65, 69, 71, 73, 91, 92, 93], "infti": 6, "inher": 30, "inherit": [18, 20, 80, 96, 97, 103, 104], "init": [1, 21, 29, 32, 63, 93], "init_audio_encod": 85, "init_backend": 68, "init_build_config": 68, "init_calib_config": 68, "init_image_encod": 85, "init_llm": 85, "init_processor": 85, "init_token": 85, "initi": [1, 13, 18, 27, 30, 31, 32, 68, 71, 75, 77, 78, 88, 89, 92, 93, 96, 98, 104], "initial_global_assign": 30, "initialis": 68, "initializecommand": 88, "initializer_list": [0, 1], "initmemorypool": 89, "inittozero": 1, "inlin": [0, 1], "inner": 80, "inner_layernorm": [81, 82], "innov": [29, 30, 32], "inp": 80, "inpaint": [34, 38, 58], "inprogress": 1, "input": [0, 1, 3, 6, 7, 9, 10, 11, 13, 17, 18, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 33, 34, 40, 42, 43, 53, 58, 62, 68, 70, 71, 72, 73, 74, 76, 78, 79, 80, 81, 82, 85, 89, 91, 92, 93, 94, 96, 97, 98, 104], "input_1": 80, "input_1_": 80, "input_audio": 85, "input_featur": 82, "input_fil": 93, "input_id": [9, 15, 27, 71, 80, 82, 85, 92, 96], "input_imag": 85, "input_layernorm": [15, 16, 18, 96], "input_length": [80, 81, 82, 85], "input_list": 80, "input_n": 80, "input_n_": 80, "input_text": [15, 17, 85, 86], "input_timing_cach": [33, 68], "input_token": 68, "input_token_extra_id": 85, "inputbuff": 1, "inputdesc": 17, "inputdtyp": 1, "inputgentokenshost": 1, "inputlen": 1, "inputpack": [1, 6], "inputs_emb": 96, "inputtokenextraid": 0, "inputtokenid": 0, "insert": [7, 17, 30, 71, 80], "insertinputtensor": 1, "insid": [1, 13, 18, 20, 21, 28, 29, 63, 80, 86, 89, 98], "insight": [27, 30, 31], "insiz": 1, "inspect": [33, 70, 89], "inspir": 28, "instabl": 2, "instal": [20, 32, 34, 35, 52, 53, 54, 63, 67, 73, 93, 96], "instanc": [0, 2, 3, 6, 7, 8, 13, 17, 27, 30, 31, 40, 51, 67, 68, 85, 89, 93, 98], "instance_idx": 92, "instanti": [73, 79, 103], "instead": [7, 9, 13, 17, 20, 21, 22, 30, 40, 63, 65, 68, 78, 79, 80, 87, 89, 93], "instruct": [13, 21, 29, 31, 32, 34, 38, 43, 44, 47, 56, 58, 63, 64, 65, 71, 72, 73, 74, 78, 79, 86, 91, 93, 96, 101, 102], "instrument": 29, "int": [0, 1, 6, 15, 16, 17, 20, 49, 51, 68, 77, 80, 81, 82, 85, 96, 98, 103, 104], "int32": [1, 5, 33, 80, 83, 92], "int32_t": [0, 1, 80], "int4": [18, 20, 26, 30, 33, 40, 62, 91, 93], "int4_weight": 90, "int64": [1, 6, 80, 92], "int64_t": [0, 1], "int8": [1, 16, 18, 20, 26, 30, 33, 62, 68, 75, 80, 89, 91, 93], "int8_kv_cach": [5, 90, 93], "int8_t": [0, 1], "int8_weight": 90, "int8awq": 75, "int_clip": 80, "integ": [5, 68, 71, 80, 90, 93], "integr": [13, 30, 31, 62, 67, 93, 97, 98, 103, 104], "intellig": [32, 69], "intend": [63, 88, 89], "intens": [29, 30], "intent": 73, "intention": 20, "intenum": 80, "inter": [2, 30, 73, 74, 75, 77, 78, 92, 93], "inter_layernorm": 82, "inter_s": 18, "interact": [3, 13, 30, 31, 69, 86, 92], "interchang": 8, "interconect": 74, "interconnect": [6, 73, 74, 75, 77, 78], "interest": [30, 71], "interfac": [17, 20, 67, 73, 85, 93, 96, 97], "interfer": [30, 31, 92], "interleav": [5, 17, 29], "intermedi": [5, 17, 29, 92], "intermediate_s": [16, 82], "intern": [1, 3, 5, 8, 12, 20, 21, 27, 29, 73, 76, 88, 89, 92, 103], "internal_cutlass_kernel": 12, "internal_error": [33, 34], "internlm": [90, 91, 93], "internlm2": [90, 91, 93], "internvl2": 93, "interpol": 80, "interpolation_scal": 81, "interpret": [3, 63, 77], "intersect": 2, "intertwin": 78, "interv": 68, "intflag": [82, 84], "intpsplitdim": 1, "intra": 74, "introduc": [20, 21, 23, 27, 28, 30, 31, 36, 90, 93, 100], "introduct": [76, 86, 93], "inttensor": [85, 96], "intuit": [29, 69, 76], "inv": 80, "inv_freq": 80, "invalid": [30, 56, 92, 93], "invalidateremoteag": 0, "inventori": 71, "invers": 5, "invest": 71, "investig": [21, 93], "invoc": 93, "invok": [0, 3, 7, 30, 67, 87, 92, 104], "invokequant": 17, "involv": [0, 1, 13, 17, 26, 28, 29, 31, 81, 97, 98, 103], "io": [5, 32, 35, 36, 89, 93], "ip": [0, 93], "ipc": [32, 63], "ipc_uc_handl": 1, "ipc_uc_ptr": 1, "ipc_uc_va": 1, "ipcmemori": 1, "ipcnvl": 1, "ipcnvlsalloc": 1, "ipcnvlsfre": 1, "ipcnvlshandl": 1, "ipcnvlssupport": 1, "ipluginv3lay": 80, "ireducelay": 80, "irrespect": [0, 6, 68], "is_alibi": 80, "is_caus": 81, "is_const_v": 1, "is_cuda_graph": 98, "is_cutlass_min_lat": 80, "is_def": 80, "is_dora": 10, "is_dynam": 80, "is_enc_dec": 85, "is_expert": 81, "is_gated_activ": 80, "is_gemma_2": 82, "is_gemma_3": 82, "is_keep_al": [56, 68], "is_loc": 81, "is_medusa_mod": 85, "is_mla_en": 80, "is_mla_enabled_flag": 80, "is_module_excluded_from_quant": 68, "is_mrop": 80, "is_network_input": 80, "is_orchestrator_mod": 85, "is_public_pool": [56, 68], "is_qkv": 81, "is_redrafter_mod": 85, "is_rop": 80, "is_trt_wrapp": 80, "is_use_oldest": [56, 68], "is_valid": [80, 81], "is_valid_cross_attn": 81, "isagentst": 0, "isauto": 0, "isbeamsearch": 0, "iscomplet": 0, "iscontextparallel": 1, "iscontinuouskvcach": 1, "iscrossattent": 1, "isdon": 1, "isdora": 1, "isdrafttokensextern": 1, "iseagl": [0, 1], "iselectlay": 80, "isexplicitdrafttoken": [0, 1], "isexternaldrafttoken": 0, "isfin": [0, 3], "isfirstcontextparallelrank": 1, "isfirstpipelineparallelrank": 1, "isfirsttensorparallelrank": 1, "isgreedysampl": 0, "ishufflelay": 80, "iskvcacheen": 1, "isl": [0, 22, 23, 24, 25, 27, 28, 29, 30, 71, 72, 78, 94], "isl8192": 31, "islastpipelineparallelrank": 1, "isleg": 0, "islicelay": 80, "isload": 1, "islookahead": 0, "islookaheaddecod": 1, "ismedusa": [0, 1], "ismpist": 0, "ismultimod": 1, "isn": [30, 92], "isnon": 1, "isoftmaxlay": 80, "isorchestr": 0, "ispagedkvcach": 1, "isparticip": [0, 93], "ispipelineparallel": 1, "ispoint": 1, "isrnnbas": 1, "issequencefin": [0, 3], "issocketst": 0, "issu": [5, 17, 20, 28, 30, 32, 55, 62, 63, 65, 67, 71, 72, 73, 80, 88, 92], "istensorparallel": 1, "isthreadsaf": 0, "istopk": 0, "istopkandtopp": 0, "istopkortopp": 0, "istopp": 0, "istransformerbas": 1, "istream": [0, 1], "isunsign": 1, "isusebantoken": 0, "isusebanword": 0, "isuseexpliciteosstop": 0, "isusefrequencypenalti": 0, "isusemaxlengthstop": 0, "isuseminlength": 0, "isuseminp": 0, "isusenorepeatngrams": 0, "isuseoccurrencepenalti": 0, "isusepenalti": 0, "isusepresencepenalti": 0, "isuserepetitionpenalti": 0, "isusestopcriteria": 0, "isusestopword": 0, "isusetemperatur": 0, "isusevariablebeamwidthsearch": 0, "iswhisp": 1, "ite": 85, "item": [0, 3, 29, 85], "itensor": [0, 80], "itensorbind": 1, "itensorptr": 1, "iter": [0, 1, 3, 5, 13, 18, 27, 28, 30, 34, 68, 69, 71, 73, 77, 78, 79, 85, 93, 94], "iter_stats_max_iter": 68, "iterationresult": 68, "iterationstat": 0, "iterationtyp": 0, "iterlatencym": [0, 34], "iterlatencymillisec": 93, "iterstat": 0, "iterstatsmaxiter": 0, "iterstatsvec": 0, "ith": 80, "itl": [30, 75, 78, 93], "its": [0, 1, 3, 5, 6, 7, 8, 14, 16, 17, 18, 20, 22, 24, 27, 28, 30, 31, 46, 67, 69, 71, 74, 76, 77, 78, 80, 87, 89, 97, 98, 104], "itself": [3, 29, 30, 85], "itsuji": 71, "iunarylay": 80, "j": [5, 6, 23, 26, 28, 52, 53, 54, 71, 80, 90, 91, 93], "jacobi": 13, "jai": 93, "jamesthez": 93, "janpetrov": 93, "japanes": [10, 71], "jax": [16, 20], "jenkin": [62, 88], "ji": 80, "jit": [21, 65, 93], "jj": 80, "jk": 80, "jl749": 93, "job": [17, 53, 54, 87, 94], "join": 31, "joint": 29, "joint_attention_kwarg": 82, "joint_attn_forward": 81, "journei": [27, 69], "jpg": 71, "json": [0, 1, 3, 16, 30, 32, 34, 37, 38, 39, 42, 43, 46, 68, 70, 71, 86, 88, 93], "json_object": 68, "jsonconfigstr": 0, "jsonl": 71, "jsonseri": 0, "judgement": 30, "just": [0, 1, 13, 28, 29, 30, 51, 52, 53, 54, 55, 63, 65, 71, 73, 79, 85, 89], "justic": 55, "k": [1, 5, 6, 10, 13, 19, 27, 28, 29, 68, 80, 90, 92, 93, 96, 98, 102], "k_b_proj_tran": 80, "k_dim": 80, "k_proj": [18, 71, 96], "kattent": 1, "kattn_dens": 1, "kattn_k": 1, "kattn_q": 1, "kattn_qkv": 1, "kattn_v": 1, "kauto": 0, "kbatchedpostprocessornam": [0, 3], "kbeamsearch": 0, "kbf16": 0, "kblk": 0, "kbool": [0, 1], "kbyte_typ": 1, "kc_cache_retention_config": 93, "kcancel": 0, "kchatglm": 1, "kcontext": 1, "kcontext_in_progress": 0, "kcontinu": 1, "kcpu": [0, 1], "kcpu_pin": 0, "kcpu_pinnedpool": 0, "kcross_attn_dens": 1, "kcross_attn_k": 1, "kcross_attn_q": 1, "kcross_attn_qkv": 1, "kcross_attn_v": 1, "kdatatyp": 1, "kdecoder_onli": [0, 14], "kdefault": 0, "kdefault_num_tokens_per_block": 1, "kdefaultbatchsizet": 0, "kdefaultdynamicbatchmovingaveragewindow": 0, "kdefaultgpumemfract": 0, "kdefaultgpuspernod": 1, "kdefaultiterstatsmaxiter": 0, "kdefaultlookaheaddecodingngram": 0, "kdefaultlookaheaddecodingverificationset": 0, "kdefaultlookaheaddecodingwindow": 0, "kdefaultmaxadapters": 0, "kdefaultmaxpagesperblockdevic": 0, "kdefaultmaxpagesperblockhost": 0, "kdefaultmaxseqidlemicrosecond": 0, "kdefaultoptimaladapters": 0, "kdefaultprior": 0, "kdefaultrequeststatsmaxiter": 0, "kdefaultretentionprior": 0, "kdisabl": 1, "kdrafttokensextern": 1, "kdram": 0, "kdynamicpostprocessornameprefix": 0, "keagl": [0, 1], "kebnf_grammar": [0, 3], "keep": [0, 5, 6, 12, 20, 27, 29, 30, 68, 72, 79, 80, 87, 93], "keepdim": 80, "kei": [0, 3, 9, 17, 22, 26, 28, 29, 30, 62, 71, 72, 77, 82, 85, 92, 97, 98, 103], "kenabl": 1, "kencdec": 1, "kencoder_decod": 0, "kencoder_in_progress": 0, "kencoder_onli": 0, "kend_id": 0, "kept": [5, 20, 30, 68, 80], "kequal_progress": 0, "kera": 20, "kernel": [1, 5, 9, 12, 17, 22, 28, 29, 31, 33, 65, 69, 70, 75, 78, 80, 85, 86, 89, 92, 93], "kernel_s": [80, 81], "kexplicitdrafttoken": [0, 1], "kexternaldrafttoken": 0, "key_length": [80, 81], "keyvaluecacheparam": [81, 82], "keyword": [18, 68, 80, 89], "kfile": 0, "kfirst_come_first_serv": 0, "kfloat": [1, 17], "kfp16": 0, "kfp32": [0, 68], "kfp8": 0, "kgener": 1, "kgeneration_complet": 0, "kgeneration_in_progress": 0, "kglm": 1, "kgpt": 1, "kgpu": [0, 1], "kguaranteed_no_evict": 0, "khalf": 1, "kick": 87, "kill": [32, 94], "kind": [4, 5, 7, 27, 30, 104], "kinflight": 0, "kint32": [0, 1], "kint64": [0, 1], "kint8": [0, 1], "kinvalid": 1, "kispoint": 1, "kisunsign": 1, "kj": 80, "kjson": [0, 3], "kjson_schema": [0, 3], "kleader": 0, "klength": 0, "klinear": 1, "kllguidanc": 0, "klookahead": 0, "klookaheaddecod": 1, "kmamba": 1, "kmax_util": 0, "kmaxretentionprior": 0, "kmedusa": [0, 1], "kminretentionprior": 0, "kmla": 0, "kmlp_4h_to_h": 1, "kmlp_gate": 1, "kmlp_gate_up": 1, "kmlp_h_to_4h": 1, "kmlp_router": 1, "kmoe_4h_to_h": 1, "kmoe_gat": 1, "kmoe_h_to_4h": 1, "kmoe_rout": 1, "kmpi": 0, "knegativeinfin": 1, "knob": [0, 68, 79, 80], "knone": 1, "knoop": 1, "knot_finish": 0, "know": [6, 70, 79, 80], "knowledg": 62, "known": [5, 12, 13, 17, 28, 30, 62, 65, 80, 87, 91], "knumflag": 0, "kobj": 0, "kopt_profiles_split_point": 1, "korchestr": 0, "kosmo": [91, 93], "kpage": 1, "kpin": 1, "kpinnedpool": 1, "kqueu": 0, "kread": 0, "krecurr": 1, "krecurrentgemma": 1, "kregex": [0, 3], "kstatic": 0, "kstatic_batch": 0, "kstop_word": 0, "kstructural_tag": 0, "ktimed_out": 0, "ktopk": 0, "ktopktopp": 0, "ktopp": 0, "ktrtpointertyp": 1, "kubernet": 31, "kuint8": [0, 1], "kunderlyingtyp": 1, "kunish": 10, "kunknown": 0, "kunsign": 1, "kusebantoken": 0, "kusebanword": 0, "kuseexpliciteosstop": 0, "kusefrequencypenalti": 0, "kusemaxlengthstop": 0, "kuseminlength": 0, "kuseminp": 0, "kusenorepeatngrams": 0, "kuseoccurrencepenalti": 0, "kusepenalti": 0, "kusepresencepenalti": 0, "kuserepetitionpenalti": 0, "kusestandardstopcriteria": 0, "kusestopword": 0, "kusetemperatur": 0, "kusevariablebeamwidthsearch": 0, "kuvm": [0, 1], "kv": [0, 1, 2, 3, 10, 17, 20, 22, 26, 28, 29, 32, 33, 34, 40, 62, 66, 68, 69, 71, 72, 73, 77, 80, 85, 86, 93, 95, 96, 97, 98, 99, 104], "kv_b_proj": 80, "kv_cach": 0, "kv_cache_block_offset": [80, 81, 85, 92], "kv_cache_block_point": 92, "kv_cache_config": [34, 40, 68, 79, 103], "kv_cache_dtyp": [21, 68, 71, 75, 84, 103], "kv_cache_enable_block_reus": [85, 93], "kv_cache_free_gpu_mem_fract": [21, 30, 72, 79], "kv_cache_free_gpu_memory_fract": [31, 32, 34, 41, 85, 93], "kv_cache_host_memory_byt": 9, "kv_cache_manag": [0, 93, 97, 98, 103, 104], "kv_cache_param": [81, 82, 98], "kv_cache_quant_algo": [16, 68, 71, 75], "kv_cache_quant_mod": [5, 80], "kv_cache_retention_config": 68, "kv_cache_scaling_factor": [5, 16], "kv_cache_typ": [17, 33, 68, 85, 93], "kv_dtype": 82, "kv_head": 81, "kv_host_cache_byt": 9, "kv_lora_rank": [80, 81], "kv_orig_quant_scal": 80, "kv_quant_orig_scal": 80, "kvalue_status_load": 1, "kvalue_status_miss": 1, "kvalue_status_process": 1, "kvcach": [0, 27, 93], "kvcacheblock": 8, "kvcacheblockpool": 8, "kvcacheconfig": [0, 5, 9, 40, 68, 79, 89], "kvcachecreateddata": [0, 68], "kvcacheev": 0, "kvcacheeventdata": 0, "kvcacheeventdiff": 0, "kvcacheeventmanag": [0, 62], "kvcachehitr": 0, "kvcachehitrateperrequest": 0, "kvcacheindex": 1, "kvcachemanag": [0, 5, 9, 85, 98, 103], "kvcachemetr": 0, "kvcacheparam": 98, "kvcacheremoveddata": [0, 68], "kvcacheretentionconfig": [0, 68], "kvcaches": 0, "kvcachestat": [0, 34], "kvcachestoredblockdata": 0, "kvcachestoreddata": [0, 68], "kvcachetransferend": 0, "kvcachetransferm": 0, "kvcachetransfermod": [0, 68], "kvcachetransferstart": 0, "kvcachetyp": [1, 68, 85], "kvcachetypefromstr": 1, "kvcacheupdateddata": [0, 68], "kvfactor": 0, "kvheadnum": 80, "kvram": 0, "kwarg": [18, 20, 68, 80, 81, 82, 85, 93, 96], "kwrite": 0, "kxgrammar": 0, "l": [13, 34, 52, 53, 54, 71, 91], "l0_a100": 87, "l0_mergerequest": 87, "l0_sanity_check": 87, "l0_test": 87, "l2": 33, "l20": 33, "l304": 27, "l345": 27, "l4": 33, "l40": 33, "l440": 27, "l506": 27, "l546": 27, "l823": 27, "lab": 71, "label": [7, 80, 81, 82], "labelembed": 81, "lack": [0, 1], "lai": 28, "lambda": [0, 3], "lamportinitializeal": 1, "languag": [0, 6, 13, 17, 19, 22, 27, 30, 31, 69, 70, 80, 90, 91, 93, 97, 100], "language_adapt": [85, 93], "language_adapter_config": 85, "language_adapter_rout": [82, 85], "language_adapter_uid": 85, "language_model": 18, "languageadapterconfig": 85, "languageadapteruid": 0, "larg": [5, 9, 11, 13, 17, 19, 20, 21, 22, 26, 27, 29, 31, 32, 33, 34, 38, 58, 68, 69, 70, 71, 74, 75, 77, 78, 80, 89, 91, 92, 93, 97, 100], "larger": [0, 2, 5, 6, 9, 13, 14, 21, 23, 24, 26, 29, 31, 68, 71, 72, 80, 85, 89, 93], "largest": [6, 22, 23, 24, 80], "last": [0, 1, 3, 5, 10, 11, 13, 15, 27, 28, 30, 32, 51, 68, 77, 79, 80, 82], "last_lay": 85, "last_process_for_ub": 80, "last_token_id": [80, 82, 92], "last_token_ids_for_logit": 82, "last_tokens_id": 80, "lastdraftindic": 1, "lastdraftlen": 1, "lastdraftpath": 1, "lastdrafttoken": 1, "lastgenerationlength": 1, "lastit": 0, "lastpositionidsbas": 1, "lasttokentim": 0, "late": 55, "latenc": [0, 5, 9, 13, 23, 24, 26, 28, 29, 30, 31, 33, 62, 68, 72, 77, 78, 79, 80, 93], "latent": [29, 81, 82], "later": [0, 1, 6, 10, 13, 17, 20, 24, 32, 75, 78, 85, 89, 92, 95], "latest": [0, 17, 21, 29, 32, 35, 63, 86, 93], "latter": [3, 26, 88, 93], "launch": [9, 17, 29, 30, 31, 34, 52, 53, 54, 62, 65, 67, 73, 92, 93, 94, 95, 100], "launch_llama_3": 17, "layer": [0, 1, 2, 4, 5, 6, 7, 8, 10, 13, 15, 16, 17, 18, 28, 30, 31, 33, 68, 74, 80, 85, 86, 89, 90, 92, 93, 96, 98, 103], "layer1": 10, "layer_idx": [10, 15, 80, 85, 96, 98], "layer_names_onli": [33, 68], "layer_norm": [80, 81], "layer_quant_mod": 68, "layer_typ": 85, "layer_updates_per_it": 30, "layerid": [1, 10], "layeridx": 1, "layernorm": [15, 33, 78, 80, 81, 93], "layernorm_shar": 81, "layernorm_typ": 81, "layernormpositiontyp": 80, "layernormtyp": [80, 81], "layertyp": [1, 7], "layerwis": 68, "layout": [77, 93], "lead": [7, 9, 13, 17, 30, 31, 33, 55, 63, 71, 72, 73, 75, 77, 78], "leader": [0, 32, 85], "learn": [23, 24, 26, 30, 32, 47, 48, 50, 75, 80, 86], "learned_absolut": [16, 80, 81, 82], "least": [0, 3, 5, 20, 21, 30, 34, 55, 77, 85], "leav": [31, 77, 78, 79], "left": [31, 68, 72, 77, 79, 80], "legaci": [18, 79, 83, 93], "len": [0, 1, 51, 71, 80, 85, 104], "length": [0, 1, 5, 9, 21, 22, 23, 24, 25, 26, 27, 28, 29, 31, 33, 34, 51, 68, 71, 72, 73, 76, 78, 79, 80, 85, 89, 92, 93, 94, 98, 103], "length_penalti": [6, 68, 85], "lengthlengthpenalti": 6, "lengthpenalti": [0, 1, 6], "less": [0, 3, 5, 6, 17, 23, 28, 30, 68, 72, 80], "let": [7, 15, 16, 18, 27, 30, 35, 40, 69, 71, 77, 80], "letter": 80, "level": [0, 1, 3, 5, 8, 10, 12, 15, 16, 18, 20, 28, 29, 31, 33, 34, 67, 70, 71, 89, 93, 94, 96], "leverag": [13, 22, 27, 28, 30, 31, 32, 75, 86], "lf": [10, 21, 32, 63, 67], "lfz941": 93, "lh": 1, "lib": [20, 65, 71], "libnam": 0, "libnvinfer_plugin_tensorrt_llm": 63, "libopenmpi": 65, "librari": [12, 17, 19, 30, 31, 63, 67, 69, 92, 93, 98], "libtensorrt_llm": 63, "licens": [67, 86], "life": 55, "lifecycl": 8, "lightweight": [5, 30], "like": [0, 3, 5, 6, 7, 9, 13, 16, 17, 19, 20, 26, 27, 28, 29, 30, 31, 32, 33, 40, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 64, 68, 69, 71, 73, 74, 75, 77, 78, 79, 80, 86, 87, 88, 89, 90, 92, 93, 95, 96, 97, 103], "likelihood": [4, 9, 13, 51], "limit": [0, 2, 3, 5, 6, 7, 17, 20, 26, 27, 28, 29, 30, 31, 32, 40, 65, 67, 68, 69, 73, 77, 79, 80, 83, 85, 89, 91, 98], "lin": 22, "line": [9, 21, 26, 31, 51, 71, 73, 75, 78, 87, 88, 89, 93, 103, 104], "linear": [1, 10, 13, 15, 16, 17, 29, 80, 89, 90, 93, 96, 98], "linearactiv": 81, "linearapproximategelu": 81, "linearbas": 81, "lineargeglu": 81, "lineargelu": 81, "linearli": 89, "linearswiglu": 81, "link": [9, 21, 27, 35, 36, 87, 93], "linspac": 80, "linux": [62, 86, 88, 91, 93], "linux_x86_64": 63, "list": [0, 1, 3, 5, 6, 7, 16, 17, 18, 19, 28, 30, 40, 51, 63, 66, 68, 69, 71, 72, 73, 80, 81, 82, 85, 87, 88, 91, 92, 93, 94, 98, 103, 104], "list_siz": 81, "liter": 68, "littl": [28, 30, 78], "live": [87, 89], "livecodebench": 27, "lkm2835": 93, "ll": [26, 28, 34], "ll128": 30, "llama": [6, 10, 13, 14, 18, 20, 23, 24, 26, 32, 33, 44, 47, 56, 60, 65, 67, 73, 74, 76, 77, 79, 82, 86, 90, 91, 93, 95, 96, 101, 102], "llama2": [5, 10, 22, 23, 93], "llama3": [56, 80], "llama4": [30, 68], "llama4forconditionalgener": 91, "llama_13b": 24, "llama_70b": 24, "llama_7b": [10, 14], "llama_7b_with_lora_qkv": 10, "llama_model_path": 40, "llamaconfig": [82, 96], "llamaforcausallm": [18, 20, 82, 91], "llamamodel": 82, "llava": [18, 90, 91, 93], "llava_dict": 18, "llavallamamodel": 91, "llavanextforconditionalgener": 91, "llavanextvisionconfig": 82, "llavanextvisionwrapp": 82, "llguidanc": [0, 68], "llm": [0, 2, 3, 5, 6, 7, 8, 9, 10, 11, 15, 17, 22, 25, 27, 29, 33, 34, 37, 38, 39, 41, 42, 43, 46, 47, 48, 49, 51, 53, 54, 55, 56, 57, 58, 59, 60, 64, 65, 66, 68, 70, 72, 74, 75, 76, 78, 79, 80, 82, 84, 85, 87, 88, 90, 92, 94, 95, 96, 97, 98, 101, 102, 103, 104], "llm_arg": [68, 72], "llm_engine_dir": 85, "llm_id": 68, "llm_inference_distribut": 67, "llm_mgmn_": 93, "llm_models_root": 60, "llm_option": 72, "llm_ptq": 101, "llmapi": [3, 30, 34, 40, 46, 52, 53, 54, 55, 56, 68, 72, 75, 93], "llmarg": [11, 68, 72, 93], "llmrequest": [1, 103, 104], "llmrequestptr": 1, "llmrequestst": 104, "lm": 13, "lm_head": [15, 18, 71, 93], "lmm": [6, 71], "lmsy": 100, "ln_emb": 18, "ln_f": [15, 18], "load": [0, 1, 10, 15, 16, 17, 20, 25, 27, 29, 31, 32, 33, 65, 67, 68, 71, 72, 73, 78, 79, 82, 84, 85, 86, 89, 93], "load_format": 68, "load_model_on_cpu": 82, "load_tensor": 18, "load_test_audio": 85, "load_test_data": 85, "load_weight": 96, "loaded_weight": 81, "loader": 93, "loadformat": 68, "loadinprogress": 1, "loadremoteag": 0, "loadweight": 1, "local": [16, 17, 21, 27, 30, 33, 47, 48, 49, 50, 52, 53, 54, 56, 63, 64, 65, 68, 71, 72, 75, 88, 93, 103], "local_build": 88, "local_in_featur": 81, "local_layer_idx": 81, "local_model": [52, 53, 54], "local_out_featur": 81, "local_path_to_model": 67, "local_us": [21, 63, 86], "localhost": [31, 32, 34, 37, 38, 39, 41, 42, 43, 57, 58, 59, 60, 86], "localinadapters": 1, "localindim": 1, "localinouts": 1, "localins": 1, "localoutadapters": 1, "localoutdim": 1, "localouts": 1, "localreduct": 27, "localscaless": 1, "localtotals": 1, "locat": [6, 7, 17, 29, 30, 63, 71, 72, 80, 86, 87, 92, 98], "locate_accepted_draft_token": 85, "lock": [30, 71], "lockstep": 0, "log": [0, 1, 5, 8, 33, 34, 35, 52, 53, 54, 68, 71, 80, 86, 89, 93, 94, 102], "log_level": [33, 34], "log_path": 94, "log_softmax": 80, "logic": [3, 8, 18, 20, 31, 51, 81, 82, 88, 93, 96, 97, 104], "login": [35, 86], "logit": [0, 1, 6, 13, 27, 28, 45, 68, 71, 80, 85, 92, 93, 99, 102], "logits_dtyp": [16, 33, 82], "logits_processor": [51, 68, 85], "logits_processor_map": 85, "logits_processor_nam": 85, "logitspostprocessor": 0, "logitspostprocessorbatch": [0, 3], "logitspostprocessorconfig": [0, 3, 93], "logitspostprocessormap": 0, "logitspostprocessornam": 0, "logitsprocessor": [51, 68, 85, 93], "logitsprocessorlist": 85, "logitsvec": 1, "logn": [80, 93], "logn_scal": 80, "logprob": [0, 1, 32, 40, 68, 86], "logprobs_diff": 68, "logprobscba": 1, "logprobstil": 1, "london": 92, "long": [5, 26, 30, 31, 33, 70, 71, 73, 74, 75, 77, 78, 89, 93], "long_mscal": [80, 81], "long_rop": 80, "long_rope_embed_posit": 81, "long_rope_embed_positions_for_gpt_attent": 81, "long_rope_rotary_cos_sin": 80, "long_rope_rotary_inv_freq": [80, 81], "longer": [0, 6, 9, 27, 29, 30, 32, 68, 72, 77, 80, 104], "longest": [2, 28, 77, 80], "longrop": 80, "longtensor": [51, 85], "look": [0, 3, 20, 25, 30, 63, 69, 71, 93], "lookahead": [0, 1, 62, 68, 93], "lookahead_config": [68, 85], "lookahead_decod": [33, 82], "lookaheadalgoconfig": 1, "lookaheadconfig": 0, "lookaheaddecod": 1, "lookaheaddecodingbuff": 1, "lookaheaddecodingconfig": [0, 1, 68], "lookaheadinput": 1, "lookaheadoutput": 1, "lookaheadprompt": 1, "lookaheadruntimebuff": 1, "lookaheadruntimeconfig": 1, "lookup": [62, 80, 81, 93], "lookup_plugin": 80, "loop": [0, 3, 6, 17, 18, 68, 79, 94], "lopuhin": 93, "lora": [0, 1, 3, 45, 61, 62, 66, 68, 80, 81, 82, 85, 93], "lora_0": 71, "lora_ckpt_sourc": [33, 85], "lora_config": [55, 68, 71, 82], "lora_dir": [10, 33, 55, 71, 85], "lora_dir1": 55, "lora_dir2": 55, "lora_dir3": 55, "lora_hidden_st": 81, "lora_int_id": [60, 71], "lora_layer_param": 81, "lora_manag": [55, 68, 85, 93], "lora_nam": [60, 71], "lora_param": 82, "lora_path": [60, 71], "lora_plugin": [10, 33, 80, 85], "lora_rank": [10, 80], "lora_request": [55, 60, 68, 71], "lora_runtime_param": 81, "lora_target_modul": [10, 33, 71, 82, 85], "lora_task_uid": 85, "lora_uid": 85, "lora_weights_point": 80, "loracachefullexcept": 1, "loracachepagemanag": 1, "loraconfig": [0, 10, 55, 68, 82, 93], "loraexpectedexcept": 1, "loraid": 0, "loramanag": 85, "loramodulenam": 1, "loraparam": 82, "loraprefetchdir": 0, "lorarequest": [55, 68], "loraruntimeparam": 81, "lorataskidtyp": [0, 1], "loraweight": 10, "loss": [26, 75], "lot": [5, 9, 17, 19, 28], "loudspeak": 24, "love": 32, "lovelac": [69, 91, 93], "low": [5, 15, 20, 21, 26, 27, 28, 29, 30, 31, 33, 62, 80, 93], "low_latency_gemm": [12, 80], "low_latency_gemm_plugin": [33, 71, 75, 81], "low_latency_gemm_swiglu": 80, "low_latency_gemm_swiglu_plugin": [33, 75, 83], "low_rank": 80, "lower": [0, 1, 2, 6, 7, 9, 10, 25, 26, 29, 31, 68, 72, 75, 80, 89], "lowprecis": [11, 68, 80], "loyalti": 51, "lpddr5x": 30, "lru": [1, 9, 80], "lt": 80, "lunch": 30, "luotuo": [10, 60], "m": [0, 21, 23, 27, 30, 31, 34, 42, 43, 46, 55, 71, 72, 73, 75, 77, 78, 80, 89, 90], "macceptancethreshold": 0, "machin": [9, 21, 26, 32, 93, 94], "macro": 12, "madditionalmodeloutput": 0, "maddr": 0, "made": [64, 69, 93, 104], "magentnam": 0, "magic": 30, "mahmoudashraf97": 93, "mai": [0, 1, 2, 3, 5, 6, 9, 10, 11, 12, 13, 16, 17, 18, 20, 21, 27, 28, 30, 31, 32, 33, 35, 52, 53, 54, 63, 67, 70, 71, 72, 73, 78, 79, 80, 81, 83, 88, 89, 92, 93, 96, 97, 98, 103], "main": [3, 6, 8, 22, 25, 27, 28, 30, 32, 34, 38, 40, 44, 46, 47, 48, 49, 50, 51, 55, 56, 58, 65, 67, 68, 70, 73, 75, 78, 79, 80, 86, 89, 92, 94, 96], "mainli": [28, 30], "mainstream": 31, "maintain": [10, 12, 22, 23, 26, 30, 71, 75, 90], "major": [20, 27, 69, 72, 89], "make": [1, 2, 5, 7, 10, 12, 17, 20, 21, 26, 27, 28, 30, 32, 35, 36, 55, 62, 63, 67, 69, 71, 73, 79, 80, 86, 92, 93], "make_causal_mask": 81, "make_env": 88, "makeshap": 1, "maketransferag": 0, "mallotedtim": 0, "mallreducecommptr": 1, "mamba": [33, 80, 90, 91, 93], "mamba1": 80, "mamba2": [80, 93], "mamba_conv1d": 80, "mamba_conv1d_plugin": [33, 85], "mamba_vers": 80, "mambaconfig": 82, "mambaforcausallm": 82, "manag": [0, 1, 2, 5, 13, 17, 29, 30, 31, 33, 40, 51, 62, 65, 67, 73, 79, 83, 85, 86, 89, 93, 95, 97, 98], "managedweight": 0, "managedweightsmap": 1, "manageweightstyp": 1, "manageweighttyp": 1, "mandatori": [1, 3, 16], "mani": [0, 5, 8, 9, 13, 17, 20, 28, 29, 30, 32, 33, 36, 68, 72, 75, 77, 79, 80, 91, 92], "manipul": 7, "manner": [7, 30], "mantissa": 23, "manual": [29, 30, 40, 65, 67, 68, 85, 92], "manufactur": 71, "map": [0, 1, 3, 5, 7, 11, 15, 16, 17, 18, 20, 27, 30, 31, 32, 72, 80, 81, 82, 85, 86, 87, 103], "mard1no": 93, "margin": [71, 77], "mark": [1, 7, 77, 80, 87, 92], "mark_as_remov": 7, "mark_output": [3, 80], "markalldon": 1, "markdon": 1, "marker": [68, 87], "market": 51, "marks101": 93, "marktaskdon": 1, "mask": [0, 1, 5, 13, 27, 28, 80, 81, 82, 85, 98], "mask_typ": 80, "masked_scatt": 80, "masked_scatter_": 80, "masked_select": [80, 93], "massiv": 21, "master": [74, 75, 76], "mat2": 80, "match": [0, 4, 7, 13, 28, 31, 62, 68, 71, 80, 81, 85, 86, 87, 92, 93], "match_and_rewrit": 7, "materi": 3, "math": [27, 29, 91], "matichon": 93, "matmul": [5, 17, 33, 75, 80, 90], "matric": 4, "matrix": [5, 17, 25, 29, 62, 69, 71, 74, 80, 86, 95, 98], "mattentionconfig": 0, "mattentiontyp": 0, "matter": 9, "matur": 34, "max": [0, 1, 10, 22, 23, 24, 29, 30, 62, 68, 73, 75, 76, 78, 80, 85, 89, 92, 94, 98], "max_all_reduce_block": 1, "max_attention_window": [68, 79, 93], "max_attention_window_s": [5, 79, 80, 85], "max_attn_valu": 81, "max_batch_s": [5, 10, 14, 16, 17, 20, 21, 28, 32, 33, 34, 40, 41, 68, 71, 75, 77, 78, 80, 82, 85, 89, 92, 93, 103], "max_beam_width": [3, 5, 33, 34, 40, 68, 80, 82, 85, 89], "max_block": [80, 104], "max_blocks_per_seq": 85, "max_blocks_per_sequ": 80, "max_boost_slid": 71, "max_cache_storage_gb": 68, "max_context_length": [80, 81, 85, 89], "max_cpu_lora": 68, "max_decoder_input_len": 82, "max_decoder_seq_len": 33, "max_dist": [5, 80, 81], "max_draft_len": [32, 33, 56, 68, 82, 84], "max_draft_token": 85, "max_encoder_input_len": [33, 68, 82], "max_gen_token": 82, "max_input_len": [10, 14, 16, 17, 33, 68, 71, 82, 85, 89], "max_input_length": [80, 81, 82, 85], "max_kv_seqlen": 80, "max_lora": 68, "max_lora_rank": [10, 33, 55, 68, 71], "max_low_rank": 80, "max_matching_ngram_s": [56, 68], "max_medusa_token": 85, "max_multimodal_len": 33, "max_new_token": [85, 89], "max_ngram_s": 68, "max_non_leaves_per_lay": 68, "max_num_request": [98, 103, 104], "max_num_token": [21, 33, 34, 40, 41, 68, 71, 75, 77, 78, 82, 89, 93, 98], "max_output_len": [17, 85, 86, 92, 93], "max_period": 81, "max_position_embed": [16, 80, 81, 82], "max_position_embedding_len": 80, "max_power_limit": 71, "max_prompt_adapter_token": 68, "max_prompt_embedding_table_s": [33, 68, 85, 93], "max_record": 68, "max_seq_len": [10, 14, 16, 17, 32, 33, 34, 68, 71, 79, 80, 81, 82, 85, 89, 93, 103], "max_seqlen": [5, 80], "max_seqlen_for_logn_sc": 81, "max_sequence_length": [5, 85], "max_token": [32, 34, 37, 38, 39, 46, 51, 56, 57, 58, 59, 60, 68, 79, 86], "max_token_count": 51, "max_tokens_in_paged_kv_cach": [79, 85, 93], "max_util": [0, 68, 79], "max_verification_set_s": 68, "max_window_s": 68, "maxaccepteddrafttokensperstep": 1, "maxacceptedtoken": 1, "maxadapters": 0, "maxattentionwindow": 1, "maxattentionwindowvec": [0, 1], "maxbadwordslen": 1, "maxbatchs": [0, 1, 6], "maxbatchsizeruntim": 0, "maxbatchsizeruntimeupperbound": 0, "maxbatchsizestat": 0, "maxbatchsizetunerrecommend": 0, "maxbeamwidth": [0, 1, 3, 93], "maxdecoderstep": 1, "maxdecodingdrafttoken": 1, "maxdecodingtoken": [0, 1], "maxdraftpathlen": [0, 1], "maxdrafttoken": [0, 1], "maxencoderlen": 1, "maxgenerationlength": 1, "maxgenlengthdevic": 1, "maxgenlengthhost": 1, "maxgentoken": 1, "maxim": [0, 22, 24, 27, 29, 71, 79, 100], "maximum": [0, 1, 2, 3, 5, 6, 21, 24, 30, 33, 34, 68, 71, 72, 75, 80, 81, 85, 89, 92, 93, 103], "maxinputlen": [1, 6], "maxinputlength": 1, "maxlength": 1, "maxlengthstop": 0, "maxlorarank": 1, "maxmedusahead": 1, "maxnewtoken": [1, 93], "maxnonleafnodesperlay": 1, "maxnumactiverequest": 0, "maxnumblock": 0, "maxnumpath": 1, "maxnumsequ": [1, 93], "maxnumtoken": [0, 1], "maxnumtokensruntim": 0, "maxnumtokensstat": 0, "maxnumtokenstunerrecommend": 0, "maxoutputlength": 3, "maxpagesperblock": 1, "maxpagesperblockdevic": 0, "maxpagesperblockhost": 0, "maxpathdraftlen": 1, "maxpathlen": [0, 1], "maxpositionembed": [0, 1], "maxpromptembeddingtables": 1, "maxqueues": 0, "maxseqidlemicrosecond": 0, "maxseqlen": 1, "maxsequencelen": [1, 6], "maxsequencelength": 1, "maxstopwordslen": 1, "maxtoken": [0, 89, 93], "maxtokensperenginestep": 1, "maxtokensperstep": 1, "mb": [68, 89], "mbackend": 0, "mbackendagentdesc": 0, "mbart": [91, 93], "mbatchingtyp": 0, "mbatchsizet": 0, "mbeamsearchbuff": 1, "mbeamsearchdiversityr": 0, "mbeamwidth": 0, "mbeamwidtharrai": 0, "mbp": 46, "mbuffer": 1, "mbuffermanag": 1, "mc_handl": 1, "mc_ptr": 1, "mc_va": 1, "mcachemap": 1, "mcachemutex": 1, "mcachepagemanag": 1, "mcachest": 0, "mcachetransceiverconfig": 0, "mcapacityschedulerpolici": 0, "mcommmod": 0, "mcommptr": 1, "mcommstat": 0, "mcommtyp": 0, "mcomputecontextlogit": 1, "mcomputegenerationlogit": 1, "mconfig": [0, 1], "mconnectioninfo": 0, "mcontextchunkingpolici": 0, "mcontextfmha": 1, "mcontextparallel": 1, "mcopyonpartialreus": 0, "mcpu": 1, "mcpudiff": 1, "mcrosskvcachefract": 0, "mcudagraphcaches": 0, "mcudagraphmod": 0, "mcumlogprobstmp": 1, "md": [13, 15, 27, 80, 86, 93, 97], "mdatatyp": [0, 1], "mdebugconfig": 0, "mdebuginputtensor": 0, "mdebugoutputtensor": 0, "mdebugtensornam": 0, "mdebugtensorsmaxiter": 0, "mdecod": 1, "mdecodedurationm": 0, "mdecoderetentionprior": 0, "mdecoderstream": 1, "mdecodingconfig": 0, "mdecodinglayerworkspac": 1, "mdecodingmod": [0, 1], "mdefaulteaglechoic": 1, "mdefaultmedusachoic": 1, "mdefaultposteriorthreshold": 1, "mdesc": 0, "mdevic": 1, "mdevicebuffermanag": 1, "mdevicecacheperc": 0, "mdeviceid": [0, 1], "mdirectori": 0, "mdllmutex": 0, "mdogreedysampl": 1, "mdonetask": 1, "mdprank": 0, "mdpsize": 0, "mdrafttoken": 0, "mdstdesc": 0, "mdynamicbatchconfig": 0, "mdynamicbatchmovingaveragewindow": 0, "mdynamicdecodelay": 1, "mdynamictreemaxtopk": 0, "me": [34, 38, 55, 58, 86], "meaglechoic": 0, "meagleconfig": 0, "mean": [1, 4, 5, 6, 9, 13, 16, 18, 20, 21, 23, 24, 28, 29, 30, 31, 34, 42, 43, 53, 55, 68, 70, 71, 72, 73, 74, 79, 80, 83, 85, 89], "meaning": [1, 21, 29, 75, 78], "meant": [68, 76, 94], "mearlystop": 0, "measur": [0, 22, 24, 25, 26, 28, 29, 30, 62, 71, 73, 93], "mechan": [3, 17, 30, 31, 88, 103, 104], "media": [71, 93], "media_path": 71, "medium": [26, 92, 93], "medusa": [0, 1, 33, 62, 68, 80, 82, 85, 93], "medusa_choic": [13, 68, 71, 85], "medusa_decode_and_verifi": 85, "medusa_hidden_act": 84, "medusa_logit": 85, "medusa_model_dir": 84, "medusa_output_token": 85, "medusa_path": 85, "medusa_position_offset": 85, "medusa_temperatur": [13, 85], "medusa_topk": 85, "medusa_tree_id": 85, "medusachoic": [0, 1], "medusaconfig": 82, "medusacurtokensperstep": 1, "medusadecodingconfig": 68, "medusaforcausallm": 82, "medusainput": 1, "medusalogit": 1, "medusapath": 1, "medusatargettokensperstep": 1, "medusatreeid": 1, "meet": [26, 30, 31, 80], "membeddingt": 0, "member": [0, 1, 6, 7, 14, 17, 80], "memlock": [32, 63, 92], "memori": [0, 1, 2, 4, 5, 6, 8, 10, 17, 18, 20, 22, 23, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 40, 62, 68, 71, 72, 73, 77, 78, 80, 85, 92, 93, 94, 98, 103], "memorydesc": 0, "memorypoolfre": [1, 89], "memorypoolreserv": [1, 89], "memorypooltrimto": 1, "memorypoolus": 1, "memorytyp": [0, 1], "memorytypestr": 1, "memtyp": 1, "memusagechang": 89, "menableattentiondp": [0, 1], "menablebatchsizetun": 0, "menableblockreus": 0, "menablechunkedcontext": 0, "menablecontextfmhafp32acc": 0, "menablemaxnumtokenstun": 0, "menablepartialreus": 0, "menabletrtoverlap": 0, "mencodedvocab": 0, "mencoderhiddens": 1, "mengineaddr": 1, "menginebuff": 1, "menginepath": 1, "mengines": 1, "mental": 55, "mention": [6, 20, 21, 40, 75], "menu": [35, 36], "merg": [27, 30, 80, 88], "meshgrid": 80, "meshgrid2d": 80, "messag": [11, 27, 32, 34, 37, 38, 57, 58, 65, 68, 72, 80, 86, 89, 93], "met": [0, 1, 3, 13], "meta": [20, 56, 67, 68, 71, 72, 73, 79, 86, 91], "meta_ckpt_dir": 82, "metadata": [8, 31, 34, 71, 96, 98], "metadata_server_config_fil": 34, "metal": [93, 95], "meth": 67, "method": [0, 1, 3, 5, 6, 12, 13, 14, 16, 17, 20, 22, 28, 29, 30, 31, 40, 51, 65, 68, 71, 85, 88, 90, 92, 93, 96, 97, 103, 104], "metric": [0, 29, 30, 31, 68, 70, 71, 72, 73, 75, 77, 78, 93], "mevent": 1, "meventbuffermaxs": 0, "mexecutionconfig": 1, "mextendedruntimeperfknobconfig": 0, "mfastlogit": 0, "mfinishedstep": 1, "mfirstgentoken": 0, "mflagptr": 1, "mfreegpumemoryfract": 0, "mfreepageid": 1, "mfrequencypenalti": 0, "mfuntowicz": 93, "mgathergenerationlogit": 0, "mgemmallreducedtyp": 1, "mgmn": 30, "mgpu": 1, "mgpudiff": 1, "mgpuspernod": 1, "mgpuweightsperc": 0, "mgreedysampl": 0, "mguid": 0, "mguideddecodingconfig": 0, "mguidetyp": 0, "mh": 13, "mh1": 13, "mha": [5, 8, 22, 29, 33, 80, 85, 98], "mhandler": 0, "mhiddens": 1, "mhostcaches": 0, "mi": 90, "mib": 89, "micro": [0, 89], "microbatchid": 0, "microbatchschedul": [97, 104], "microsecond": 0, "microsoft": 16, "middl": 70, "might": [0, 3, 17, 20, 21, 26, 30, 33, 63, 69, 71, 73, 74, 78, 85, 89, 92, 93, 103], "migrat": [20, 83, 93], "million": 71, "millisecond": 0, "millisecondstyp": 0, "mimpl": 0, "min": [0, 1, 6, 23, 27, 28, 29, 68, 71, 73, 78, 80, 92], "min_lat": 80, "min_length": [6, 85], "min_p": [0, 6, 68, 85], "min_token": 68, "mind": [26, 67, 79], "mindim": 1, "mindimfirst": 1, "mini": 93, "minim": [27, 30, 31, 77, 86], "minimum": [0, 5, 6, 68, 71, 72, 75, 80, 85, 89], "minitron": [91, 93], "minittozero": 1, "minlat": [11, 68], "minlength": [1, 6, 93], "minnormedscorescba": 1, "minor": 93, "minp": [0, 1, 6], "minprogresstask": 1, "minputpack": 1, "minputtokenextraid": 0, "mintoken": [0, 93], "mintpsplitdim": 1, "minut": [0, 26, 32, 73], "mip": 0, "mipcmemoryhandl": 1, "mirco": 0, "mish": 81, "mismatch": [20, 92], "misorchestr": 0, "mispagefre": 1, "miss": [0, 7, 71, 93], "missedblock": 0, "missedblocksperrequest": 0, "mission": [27, 30, 31], "mistral": [4, 71, 75, 78, 90, 91, 93], "mistralai": [71, 91], "mistralforcausallm": 91, "misus": 93, "miterstatsmaxiter": 0, "mitig": [20, 27, 30], "mix": [2, 29, 74, 78, 93], "mixed_precis": 68, "mixer": 93, "mixtral": [4, 10, 71, 75, 78, 90, 91, 93], "mixtralforcausallm": 91, "mixtur": [29, 30, 62, 78, 93], "mjointdecodinginput": 1, "mjointdecodingoutput": 1, "mkdir": 35, "mkvcacheconfig": 0, "mkvcachetyp": 1, "mkvfactor": 0, "ml": [80, 93], "mla": [27, 28, 80, 93], "mlayertyp": 1, "mlen": 0, "mlengthpenalti": 0, "mllama": [91, 93], "mllamaconfig": 82, "mllamaforcausallm": 82, "mllamaforconditionalgener": 91, "mlogit": 0, "mlogitsdtyp": 1, "mlogitspostprocessorconfig": 0, "mlookaheaddecodingconfig": 0, "mlookaheaddecodingmaxnumrequest": 0, "mloramodul": 1, "mloraprefetchdir": 0, "mlp": [10, 15, 17, 18, 33, 80, 92, 93, 96], "mlp_4h_to_h": [10, 33], "mlp_bia": 82, "mlp_gate": [10, 33], "mlp_gate_up": [10, 33], "mlp_h_to_4h": [10, 33], "mlp_output": 92, "mlp_router": [10, 33], "mlphiddens": 1, "mlptype": 80, "mm": 93, "mm_data": 71, "mm_embedding_offload": 85, "mma": [29, 80], "mmanag": 1, "mmanagedweightsmap": 1, "mmanageweightstyp": 1, "mmaxadapters": 0, "mmaxattentionwindow": 0, "mmaxattentionwindowvec": 0, "mmaxbatchs": [0, 1], "mmaxbeamwidth": [0, 1], "mmaxdecodingdecodertoken": 1, "mmaxdecodingdrafttoken": 1, "mmaxdecodingenginetoken": 1, "mmaxdraftpathlen": 1, "mmaxencoderlen": 1, "mmaxinputlen": 1, "mmaxlorarank": 1, "mmaxnonleafnodesperlay": 1, "mmaxnumpackedmask": 1, "mmaxnumpath": 1, "mmaxnumtoken": [0, 1], "mmaxpagesperblock": 1, "mmaxpagesperblockdevic": 0, "mmaxpagesperblockhost": 0, "mmaxpositionembed": 1, "mmaxpromptembeddingtables": 1, "mmaxqueues": 0, "mmaxseqidlemicrosecond": 0, "mmaxsequencelen": 1, "mmaxsequencelength": 1, "mmaxtoken": 0, "mmedusachoic": 0, "mmemorytyp": 1, "mmha": [80, 93], "mminp": 0, "mmintoken": 0, "mmlphiddens": 1, "mmlu": [26, 27, 93], "mmlu_llmapi": 93, "mmmu": 71, "mmodelconfig": [0, 1], "mmodelnam": 1, "mmodelvari": 1, "mmoduleidtomodul": 1, "mmropepositiondelta": 0, "mmroperotarycossin": 0, "mmultiblockmod": 0, "mmultimodalhash": 0, "mmultimodallength": 0, "mmultimodalposit": 0, "mname": [0, 1], "mnbattentionlay": 1, "mnbhead": 1, "mnbkvheadsperlay": 0, "mnblayer": 1, "mnbrnnlayer": 1, "mngramsiz": 0, "mnnvl": [11, 30, 68, 80], "mnorepeatngrams": 0, "mnormalizelogprob": 0, "mnumcopystream": [0, 1], "mnumdecodingenginetoken": 1, "mnumdevicemodulelay": 0, "mnumensurework": 0, "mnumhostmodulelay": 0, "mnumkvheadsperattentionlay": 1, "mnumkvheadspercrossattentionlay": 1, "mnumlanguag": 1, "mnumnod": 0, "mnumputwork": 0, "mnumreturnbeam": 0, "mnumreturnsequ": 0, "mnumsm": 1, "mnumtransformerslay": 1, "modal": 90, "mode": [0, 1, 4, 5, 7, 17, 18, 29, 32, 33, 34, 46, 52, 53, 54, 68, 79, 80, 81, 85, 88, 89, 90, 93, 96], "model": [0, 1, 2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 20, 22, 23, 24, 25, 26, 29, 30, 31, 32, 33, 34, 37, 38, 39, 40, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 62, 65, 68, 69, 70, 73, 76, 79, 80, 81, 83, 84, 85, 89, 90, 94, 95, 98, 99, 100, 101, 102, 103, 104], "model_architectur": 68, "model_cl": 81, "model_cls_fil": 33, "model_cls_nam": 33, "model_config": [33, 68, 85, 96], "model_dir": [10, 14, 15, 16, 17, 18, 20, 28, 52, 71, 74, 82, 84, 86, 92], "model_engin": 103, "model_nam": [30, 53, 72, 85, 94], "model_path": [14, 30, 53, 70, 71], "model_post_init": 68, "model_qu": 71, "model_weights_load": [18, 93], "modelconfig": [0, 6, 85, 93, 96], "modelengin": [97, 103], "modelidtomodel": 1, "modeling_deepseekv3": [27, 29], "modeling_llama": 96, "modeling_mymodel": 96, "modeling_opt": 96, "modeling_util": [68, 96], "modelnam": 1, "modelopt": [16, 20, 65, 71, 72, 84, 93], "modelopt_cuda_ext": 65, "modelpath": 0, "modelrunn": [16, 85, 93], "modelrunnercpp": [85, 93], "modelrunnermixin": 85, "modeltyp": [0, 14], "modelvari": 1, "modelweightsformat": 18, "modelweightsload": [18, 93], "moder": 31, "modern": 85, "modif": [7, 17], "modifi": [3, 7, 63, 71, 75, 78, 79, 92, 93, 94], "modul": [0, 1, 5, 6, 15, 16, 17, 18, 27, 30, 31, 33, 62, 63, 68, 78, 80, 81, 82, 84, 85, 92, 93, 96], "modular": [30, 67, 69], "modularli": 31, "module1": 27, "module10": 27, "module11": 27, "module12": 27, "module13": 27, "module2": 27, "module3": 27, "module4": 27, "module5": 27, "module6": 27, "module7": 27, "module8": 27, "module9": 27, "module_id": 10, "moduleid": [1, 10], "moduleidtomodel": 1, "modulelist": 96, "moduletyp": 1, "modulo": 80, "moe": [10, 18, 27, 28, 30, 33, 50, 62, 68, 78, 80, 82, 93], "moe_4h_to_h": [10, 33], "moe_backend": [21, 28, 68], "moe_cluster_parallel_s": 68, "moe_ep_s": 4, "moe_expert_parallel_s": [50, 68], "moe_finalize_allreduce_residual_rms_norm": 80, "moe_gat": [10, 33], "moe_gemm": 12, "moe_h_to_4h": [10, 33], "moe_load_balanc": [30, 68], "moe_max_num_token": 68, "moe_plugin": 33, "moe_rout": [10, 33], "moe_shared_": 30, "moe_tensor_parallel_s": [50, 68], "moe_tp_siz": 4, "moeallreduceparam": 80, "moeconfig": 82, "moeloadbalancerconfig": 68, "moetopk": 93, "moment": 3, "monboardblock": 0, "monitor": [8, 31, 33], "monitor_memori": [33, 68], "monolith": 5, "monost": 0, "month": 71, "mop": 0, "mopenipc": 1, "moptimaladapters": 0, "morchestratorconfig": 0, "morchleadercomm": 0, "more": [0, 1, 2, 3, 4, 5, 6, 7, 8, 13, 15, 16, 17, 22, 23, 24, 26, 27, 28, 29, 30, 31, 33, 34, 40, 44, 51, 63, 67, 68, 69, 71, 72, 73, 75, 77, 78, 79, 80, 86, 87, 88, 89, 92, 93, 94, 96, 98, 102, 104], "most": [0, 1, 6, 8, 13, 17, 20, 22, 23, 24, 26, 27, 29, 31, 47, 48, 50, 68, 70, 76, 78, 79, 80, 86, 87, 88, 89, 92, 93, 102], "mostli": 30, "mount": [34, 52, 53, 54, 62, 63], "mount_dest": [52, 53, 54], "mount_dir": [52, 53, 54], "moutdim": 1, "moutdimfirst": 1, "moutputbeamhypothes": 1, "mouttpsplitdim": 1, "move": [0, 1, 8, 20, 30, 68, 69, 80, 92, 93], "movement": [8, 17], "mownsev": 1, "mownsstream": 1, "mp4": [34, 38, 58], "mpageblock": 1, "mpagedcontextfmha": 1, "mpagedst": 1, "mpagemanagerconfig": 1, "mpagesmutex": 1, "mpagewidth": 1, "mparallelconfig": 0, "mparticipantid": 0, "mpeftcacheconfig": 0, "mpi": [0, 1, 6, 17, 19, 20, 31, 33, 34, 52, 53, 54, 65, 68, 70, 71, 73, 80, 92, 93, 94], "mpi4pi": [67, 73, 92, 93], "mpi_abort": 67, "mpi_barri": 20, "mpi_comm_world": [6, 67], "mpi_group_barri": 1, "mpicomm": 0, "mpicommsess": 68, "mpin": 1, "mpinneddiff": 1, "mpinnedpool": 1, "mpinnedpooldiff": 1, "mpipelineparallel": [0, 1], "mpirun": [16, 17, 67, 73, 92, 93], "mpisess": 68, "mpistat": 0, "mpointer": 1, "mpool": 1, "mport": 0, "mposteriorthreshold": 0, "mppreducescatt": 1, "mprecis": 1, "mpresencepenalti": 0, "mprocessorbatch": 0, "mprocessormap": 0, "mprompttableoffload": 0, "mpt": [26, 90, 91, 93], "mptforcausallm": 82, "mptmodel": 82, "mqa": [5, 8, 22, 25, 27, 33, 80, 93, 98], "mquantmod": 1, "mrank": [0, 1], "mrecvpollperiodm": 0, "mremotenam": 0, "mrepetitionpenalti": 0, "mreplic": 0, "mreqid": 0, "mrequeststatsmaxiter": 0, "mrnnconfig": 1, "mrope": [0, 80], "mrope_param": [81, 85], "mrope_position_delta": [80, 81, 85], "mrope_rotary_cos_sin": [80, 81], "mrope_rotary_cos_sin_s": 82, "mropeconfig": 0, "mropeparam": [81, 85], "mropepositiondelta": 0, "mroperoratysinco": 0, "mrotaryembeddingdim": 1, "mruntimedefault": 1, "mruntimestream": 1, "msamplingconfig": 1, "mscale": 80, "mscale_all_dim": 80, "mschedulerconfig": 0, "msecondaryofflineminprior": [0, 68], "msecondaryoffloadminprior": 0, "mseed": 0, "mselfidx": 0, "msg": [0, 1, 27, 68], "msinktokenlength": 0, "msizeperhead": [0, 1], "mskipcrossattnblock": 1, "msl": 1, "mslotsperpag": 1, "mspawnprocess": 0, "mspeculativedecodingconfig": 0, "mspeculativedecodingmod": 1, "mspeculativedecodingmodul": 1, "msrcdesc": 0, "mstate": [0, 1], "mstoptokenid": 0, "mstream": 1, "msyncmessag": 0, "mt5": 91, "mtag": 0, "mtaskid": 0, "mtemperatur": 0, "mtensor": 0, "mtensorparallel": [0, 1], "mtoken": 0, "mtokenizerstr": 0, "mtokenrangeretentionconfig": 0, "mtokensperblock": [0, 1], "mtopk": 0, "mtopp": 0, "mtoppdecai": 0, "mtoppmin": 0, "mtoppresetid": 0, "mtotalnumpag": 1, "mtp": [21, 30, 31, 56, 68, 93, 99, 102], "mtp3": 31, "mtp3_autoregress": 27, "mtp3_top1": 27, "mtp3_top10": 27, "mtp3_top15": 27, "mtp3_vanilla": 27, "mtpdecodingconfig": [56, 68], "mtprank": 1, "mtransfermod": 0, "mtrimpool": 1, "mtype": [0, 1], "much": [9, 17, 28, 30, 70, 72, 77, 89], "mul": 80, "multi": [0, 2, 3, 4, 6, 9, 10, 13, 16, 19, 20, 22, 28, 29, 30, 33, 38, 52, 53, 54, 58, 62, 63, 67, 68, 73, 80, 82, 89, 90, 93, 98], "multi_block_mod": [5, 68, 85, 93], "multi_round": 94, "multiblockmod": 0, "multidimension": 80, "multihead": [17, 22], "multimod": [0, 33, 61, 67, 71, 85, 91, 93], "multimodalembed": 0, "multimodalhash": 0, "multimodalinput": 0, "multimodallength": 0, "multimodalmodelrunn": 85, "multimodalposit": 0, "multinod": 74, "multinomi": 6, "multipl": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 13, 17, 18, 27, 28, 29, 30, 31, 32, 33, 45, 68, 69, 73, 74, 75, 77, 80, 81, 85, 86, 87, 92, 93, 94, 98], "multiple_profil": [33, 71, 75, 78, 93], "multipli": [5, 18, 29, 80], "multiply_and_lora": 81, "multiply_collect": 81, "multiprocessor": 17, "munsign": 1, "musecrossattent": 1, "musedynamictre": 0, "musegemmallreduceplugin": 1, "musegptattentionplugin": 1, "musegpudirectstorag": 0, "museloraplugin": 1, "musemambaconv1dplugin": 1, "musemrop": 1, "musepositionembed": 1, "museshapeinfer": 1, "musetokentypeembed": 1, "museuvm": 0, "must": [0, 1, 2, 3, 4, 5, 6, 9, 10, 13, 17, 19, 30, 31, 33, 34, 36, 46, 65, 68, 75, 80, 81, 83, 85, 90, 92], "mutabl": [0, 1], "mutablepageptr": 1, "mutex": [0, 1], "mutual": [6, 90], "muvm": 1, "muvmdiff": 1, "mverificationsets": 0, "mversion": 1, "mvocabs": 1, "mvocabsizepad": 1, "mweight": 0, "mwindows": 0, "mworkerexecutablepath": 0, "mworldconfig": 1, "my": [1, 44, 47, 48, 49, 50, 65, 71, 86, 101, 102], "my_faster_on": 40, "my_model": 15, "my_profile_export": [34, 42, 43], "myattent": 96, "myconfig": 96, "mydecoderlay": [15, 96], "mymodel": [15, 96], "mymodelforcausallm": [15, 96], "n": [1, 2, 5, 10, 13, 16, 17, 28, 29, 32, 34, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 67, 68, 71, 73, 77, 80, 81, 82, 89, 90, 92, 93, 100], "n1": [32, 51], "n2": [32, 51], "n3": 51, "n4": 51, "n_worker": 68, "na": [71, 93], "naiv": 78, "naivepatternrewriter_replaceaddwithsub": 7, "name": [0, 1, 3, 6, 7, 10, 12, 16, 17, 34, 35, 44, 47, 48, 49, 50, 53, 56, 62, 65, 67, 68, 71, 72, 73, 80, 82, 83, 84, 85, 86, 92, 93, 94, 96, 101, 102], "named_network_output": 92, "named_paramet": 18, "namespac": [0, 1, 67, 82], "nanoflow": 100, "nation": 71, "nationwid": 71, "nativ": [20, 23, 29, 30, 67, 93, 96], "native_quant_flow": 82, "natur": [20, 29, 30, 34, 38, 58, 73], "naur": [0, 3, 68], "nbattentionlay": [0, 1], "nbdim": 1, "nbhead": 1, "nbkvhead": [0, 1], "nbkvheadperlay": 0, "nblayer": 1, "nbrnnlayer": 1, "nccl": [11, 17, 27, 30, 33, 68, 80, 92, 93], "nccl_p2p_level": 93, "nccl_plugin": 33, "ncclplugin": 17, "ncclrecv": [30, 80], "ncclsend": [30, 80], "ncuda_graph_config": 32, "nd": [71, 80], "ndarrai": [80, 81, 85], "ndim": 80, "nearest": [29, 68, 80], "nearli": [7, 23, 29], "necess": 13, "necessari": [1, 4, 13, 27, 29, 30, 55, 75, 80, 88, 93, 102, 103], "necessarili": [1, 17, 89], "necessit": 30, "need": [1, 2, 3, 5, 6, 7, 9, 13, 14, 15, 16, 17, 18, 19, 20, 21, 27, 28, 29, 30, 31, 32, 34, 35, 40, 44, 46, 50, 52, 53, 54, 55, 63, 65, 67, 68, 69, 71, 72, 73, 74, 75, 77, 78, 79, 80, 82, 83, 85, 86, 87, 89, 92, 93, 94, 96, 97, 98, 103, 104], "needed_block": 104, "needsdecoderprologu": 1, "needskvcacherewind": 1, "neg": [1, 51, 68, 79, 80], "neglig": [9, 26, 77], "neither": [3, 80, 89], "nemo": [16, 19, 33, 69, 73, 85, 90, 91, 93], "nemo_ckpt_dir": 82, "nemo_prompt_convert": 85, "nemotron": [91, 93], "nemotron_na": 93, "nemotronforcausallm": 91, "nemotronna": [91, 93], "nemotronnasforcausallm": 91, "nenable_autotun": 32, "nenable_min_lat": 32, "neox": [5, 6, 90, 91, 93], "nest": 7, "net": [9, 68, 92], "net_guard": 7, "network": [3, 4, 5, 7, 11, 17, 19, 20, 29, 30, 33, 46, 80, 86, 89, 90, 92, 93], "neural": [4, 7, 17, 86, 93], "neva": [91, 93], "never": [7, 71, 79], "nevertheless": 30, "new": [0, 1, 3, 5, 6, 7, 9, 10, 13, 14, 20, 23, 24, 27, 28, 30, 34, 35, 37, 39, 47, 48, 49, 50, 51, 57, 59, 62, 63, 67, 68, 69, 77, 78, 80, 85, 86, 93, 95, 97, 103], "new_decoder_architectur": [16, 82], "new_generated_id": 85, "new_input": 7, "new_line_token": 51, "new_out": 7, "new_shap": 80, "new_tensor": 80, "new_token": 85, "new_workflow": 93, "newactiverequestsqueuelatencym": [0, 34], "newer": [91, 93], "newest": [24, 68], "newli": [0, 28, 30, 68, 77], "newsiz": 1, "newtoken": 1, "newtokensstep": 1, "newtokensvec": 1, "newvalu": 0, "next": [1, 10, 13, 17, 20, 23, 28, 30, 62, 63, 69, 74, 75, 77, 78, 79, 85, 89, 91, 93, 100], "next_logit": 85, "next_medusa_input_id": 85, "next_medusa_logit": 85, "next_step_buff": 85, "next_step_tensor": 85, "nextdraftindic": 1, "nextdraftlen": 1, "nextdraftpath": 1, "nextdraftprob": 1, "nextdrafttoken": 1, "nextdrafttokenslen": 1, "nextflattoken": 1, "nextgenerationlength": 1, "nextn": 28, "nextpositionoffset": 1, "ngc": [62, 63, 65, 86, 88, 93, 95], "ngoanpv": 93, "ngram": [0, 6, 56, 68, 82], "ngramdecodingconfig": [56, 68], "ngramsiz": 0, "ngroup": 80, "nhead": 80, "nhere": 46, "ni": [46, 90], "nic": 30, "nice": 30, "nine": 86, "nixl": 31, "nj": 49, "njane": [47, 48, 49, 50], "njason": 55, "nkv_cache_config": 32, "nmh": 85, "nmt": [85, 91, 93], "nn": [80, 96], "no_quant": 68, "no_repeat_ngram_s": [6, 68, 85], "no_schedule_after_st": 104, "no_schedule_until_st": 104, "noauxtckernel": 27, "node": [0, 2, 6, 11, 19, 28, 29, 30, 31, 32, 33, 52, 53, 54, 62, 67, 68, 70, 73, 74, 80, 85, 90, 92, 93, 94], "noexcept": [0, 1], "nomin": 49, "non": [0, 2, 5, 8, 14, 17, 20, 26, 27, 28, 29, 30, 33, 68, 80, 92, 93], "non_block": 51, "non_gated_vers": 80, "none": [1, 6, 7, 15, 18, 20, 33, 34, 40, 51, 55, 56, 68, 71, 73, 77, 80, 81, 82, 83, 84, 85, 92, 93, 96, 98], "nonetyp": [68, 85], "nonzero": 80, "nor": [30, 89], "norepeatngrams": [0, 1, 6], "norm": [18, 21, 29, 53, 70, 71, 72, 73, 80, 93, 96], "norm_before_bmm1": [81, 82], "norm_elementwise_affin": 81, "norm_ep": 81, "norm_epsilon": [16, 82], "norm_factor": 5, "norm_num_group": 81, "norm_pre_residual_weight": 80, "norm_quant_fus": 33, "norm_typ": 81, "norm_weight": 80, "normal": [0, 6, 9, 10, 14, 26, 27, 28, 29, 30, 68, 71, 80, 89, 93], "normalize_log_prob": 68, "normalize_weight": 10, "normalized_shap": [80, 81], "normalizelogprob": [0, 1], "normedscorescba": 1, "north": [15, 17, 92], "northeastern": 86, "not_op": 80, "notabl": 26, "notat": 28, "note": [1, 2, 7, 9, 10, 11, 12, 13, 17, 21, 24, 26, 27, 28, 29, 30, 32, 33, 36, 40, 52, 53, 54, 62, 63, 67, 68, 71, 72, 75, 77, 79, 80, 83, 85, 87, 89, 90, 91, 92, 95, 96, 103], "notic": 55, "notifysyncmessag": 0, "notimplementederror": 20, "nougat": [90, 91, 93], "now": [6, 12, 13, 16, 18, 22, 27, 28, 30, 69, 71, 77, 83, 86, 89, 93], "np": 80, "npy": 85, "npytorch_backend_config": 34, "nsight": 62, "nspeculative_config": 32, "nsy": [70, 94], "ntask": [17, 34, 52, 53, 54], "null": [1, 16, 32, 71, 86], "nullopt": [0, 1], "nullptr": [0, 1], "num": [0, 1, 21, 53, 62, 68, 70, 71, 72, 73, 75, 76, 78], "num_attention_head": [16, 80, 81, 82], "num_aud_token": 85, "num_beam": [6, 85], "num_beam_group": 6, "num_block": [85, 103], "num_bucket": [80, 81], "num_channel": [81, 82], "num_class": 81, "num_context": 98, "num_ctx_serv": 94, "num_ctx_token": 98, "num_draft_token": [0, 80, 85], "num_eagle_lay": 68, "num_embed": 81, "num_experts_per_tok": 4, "num_extra_kv_token": 68, "num_gen_serv": 94, "num_gener": 98, "num_group": [80, 81], "num_head": [5, 18, 80, 85, 98], "num_hidden_lay": [16, 82, 96, 103], "num_imag": 85, "num_img_token": 85, "num_inst": 31, "num_key_value_head": [16, 82, 103], "num_kv_head": [8, 80, 81, 85, 98, 103], "num_kv_heads_origin": 80, "num_kv_heads_per_cross_attn_lay": 85, "num_kv_heads_per_lay": 85, "num_lay": [80, 81, 85, 103], "num_ln_in_parallel_attn": 82, "num_local_block": 81, "num_local_expert": 4, "num_lora_module_lay": 10, "num_lora_modules_lay": 10, "num_medusa_head": [68, 82, 84, 85], "num_medusa_lay": [82, 84], "num_multimodal_token": 0, "num_nextn_predict_lay": [21, 28, 56, 68], "num_nextn_predict_layers_from_model_config": 68, "num_orig_po": 80, "num_po": 80, "num_postprocess_work": [34, 68], "num_profil": 82, "num_q_head": 27, "num_request": [21, 28, 71, 72], "num_return_sequ": [85, 93], "num_sampl": 70, "num_slot": 30, "num_task": 81, "num_token": [5, 27, 80, 98], "num_tokens_per_block": [80, 103], "num_tokens_per_task": 81, "num_video": 85, "numa": [11, 30], "numacceptedtoken": 0, "numactiverequest": 0, "numactl": 30, "numattentionhead": 1, "numavailablepag": 1, "numbeamscba": 1, "number": [0, 1, 2, 3, 4, 5, 6, 8, 13, 17, 21, 25, 27, 28, 29, 30, 31, 32, 33, 34, 52, 53, 54, 68, 71, 72, 73, 74, 75, 77, 78, 79, 80, 81, 85, 87, 89, 90, 92, 93, 94, 96, 98, 103], "numblockspercachelevel": 0, "numcompletedrequest": 0, "numcontextrequest": [0, 1], "numcopystream": [0, 1], "numctxgpu": 31, "numctxsequ": 1, "numctxtoken": 0, "numdevicemodulelay": 0, "numdrafttoken": [0, 1], "numdrafttokenshost": 1, "numeaglelay": 1, "numel": 85, "numensurework": 0, "numer": [6, 11, 27, 62, 71, 86, 91, 94], "numexpert": 1, "numgeneratedtoken": 0, "numgengpu": 31, "numgenrequest": 0, "numgensequ": 1, "numgentoken": [0, 1], "numhead": 6, "numhostmodulelay": 0, "numkvattentionhead": 1, "numkvhead": 6, "numlanguag": 1, "numlay": 6, "nummissedblock": 0, "numnewactiverequest": 0, "numnewallocatedblock": 0, "numnewtokenscumsum": 93, "numnod": [0, 93], "numpag": 1, "numpausedrequest": 0, "numpi": [10, 80, 85], "numputwork": 0, "numqueuedrequest": [0, 93], "numrequestswithdrafttoken": 0, "numreturnbeam": 0, "numreturnsequ": [0, 1, 3], "numreusedblock": 0, "numscheduledrequest": 0, "numsequ": 1, "numslot": 1, "numtoken": 1, "numtotalallocatedblock": 0, "numtransformerslay": 1, "nvbugspro": 87, "nvcc": 21, "nvcr": 93, "nvfp4": [27, 30, 33, 62, 68, 71, 93, 101], "nvidia": [16, 17, 19, 20, 21, 22, 23, 24, 26, 28, 30, 31, 32, 33, 35, 37, 38, 39, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 62, 63, 64, 65, 67, 69, 71, 72, 73, 78, 80, 86, 87, 88, 89, 91, 92, 93, 101, 102], "nvila": [91, 93], "nvinfer1": [0, 1], "nvl": [1, 33, 93], "nvl36": 74, "nvl72": [29, 74], "nvlink": [2, 6, 11, 30, 31, 73, 74, 76, 93], "nvswitch": [17, 27], "nvtx": 68, "nyou": 46, "n\u7b54\u6848": 60, "o": [0, 1, 7, 10, 20, 25, 27, 29, 32, 52, 53, 54, 60, 70, 92], "o_proj": 18, "oai": [34, 38, 58], "obei": 92, "object": [0, 1, 3, 9, 15, 17, 18, 20, 32, 40, 46, 51, 68, 80, 81, 82, 83, 85, 86, 89, 97, 102], "observ": [29, 31, 72], "obtain": [19, 31, 64, 72, 80], "obviou": [21, 29], "occas": 92, "occasion": 93, "occup": [5, 89, 100], "occupi": [26, 29, 30, 89], "occur": [6, 9, 31, 103, 104], "off": [9, 12, 29, 31, 70, 75, 77, 78, 87, 89, 93], "offer": [17, 19, 26, 27, 31, 69, 88, 98], "offic": 46, "officenetsecur": 46, "offici": [5, 21, 28, 71], "offlin": [15, 24, 29, 44, 71, 72, 93], "offload": [0, 8, 14, 30, 33, 62, 68, 93], "offset": [1, 80, 85, 90, 93], "offsetdim": 1, "ofitensor": 0, "often": [0, 3, 8, 13, 22, 26, 27, 30, 31, 68, 74, 75, 80], "ok": 92, "old": [7, 10, 28, 92], "older": [9, 20, 63, 91], "oldest": [10, 68], "oldvalu": 0, "omit": [1, 3, 20, 64, 80, 86], "ompi": [65, 92], "onboard": [0, 9, 68, 89], "onboard_block": 68, "onboardblock": 0, "onc": [0, 3, 5, 6, 7, 17, 19, 28, 30, 31, 32, 63, 65, 67, 68, 75, 80, 87, 89], "one": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 11, 13, 16, 17, 18, 20, 22, 27, 28, 29, 31, 33, 34, 35, 55, 68, 71, 73, 74, 75, 78, 79, 80, 81, 83, 85, 88, 89, 92, 93, 94, 96, 100, 104], "ones": [0, 10], "oneshot": [11, 27, 68, 80], "oneshotallreduc": 27, "oneshotar": 27, "onevis": [91, 93], "ongo": [20, 30], "onli": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 12, 13, 14, 15, 17, 18, 20, 21, 26, 28, 29, 30, 31, 33, 34, 40, 51, 62, 65, 67, 68, 71, 72, 73, 74, 75, 77, 78, 79, 80, 81, 83, 85, 87, 89, 91, 93, 97, 104], "onlin": [19, 24, 44], "only_cross_attent": 81, "onnx": [33, 80], "onnx__gathernd": 80, "onto": 6, "oom": [21, 22, 25, 29, 89], "ootb": [29, 93], "op": [0, 1, 7, 29, 68, 80, 93], "op_and": 80, "op_or": 80, "op_xor": 80, "opaqu": 7, "opaque_st": 68, "open": [6, 12, 22, 27, 29, 30, 69, 70, 86, 92, 93], "openai": [31, 32, 34, 61, 86, 93], "openipc": 1, "openmpi": 93, "opensora": 93, "openssh": 35, "oper": [0, 1, 3, 5, 6, 7, 11, 13, 16, 17, 18, 27, 29, 30, 31, 33, 68, 71, 74, 75, 78, 80, 86, 89, 91, 93, 97, 98, 103], "opportun": 71, "opposit": 51, "opt": [3, 16, 26, 29, 35, 80, 90, 91, 92, 93], "opt_batch_s": [68, 82], "opt_num_token": [33, 68, 82], "optforcausallm": [16, 82], "optim": [1, 3, 6, 7, 8, 11, 12, 13, 17, 19, 20, 22, 23, 24, 25, 26, 30, 32, 33, 47, 51, 63, 69, 71, 72, 74, 75, 76, 80, 86, 89, 91, 92, 93, 95, 97, 98, 100, 101, 103], "optimaladapters": [0, 1], "option": [0, 1, 3, 6, 7, 8, 11, 12, 13, 15, 20, 23, 28, 33, 34, 40, 51, 53, 55, 56, 62, 64, 65, 68, 70, 71, 72, 73, 74, 76, 77, 80, 83, 85, 86, 87, 88, 89, 92, 93, 94, 96, 98, 102, 103], "optionalbufferptr": 1, "optionaltensorptr": 1, "optmodel": 82, "optvec": 1, "orchestr": [0, 13, 30, 31, 92, 93, 94], "orchestratorconfig": 0, "orchleadercomm": 0, "order": [0, 2, 5, 8, 18, 22, 68, 71, 72, 75, 79, 80, 81, 86, 88, 89, 94, 102], "org": [0, 1, 4, 10, 33, 65, 80, 90, 100], "organ": [8, 69, 87, 103], "orient": [29, 30, 31], "origin": [0, 5, 7, 10, 11, 28, 29, 30, 51, 80, 93, 96], "original_max_position_embed": [80, 81], "originaltemperatur": 1, "oserror": 93, "osl": [22, 23, 24, 25, 27, 28, 29, 30, 71, 72, 78, 94], "osl256": 31, "oss": 12, "ostream": [0, 1], "other": [0, 1, 2, 3, 4, 5, 6, 9, 11, 12, 13, 17, 18, 20, 22, 27, 28, 29, 30, 31, 32, 33, 40, 52, 53, 54, 63, 67, 68, 69, 72, 73, 74, 75, 77, 78, 79, 80, 83, 87, 89, 92, 93, 98, 104], "other_audio_input": 85, "other_decoder_input": 85, "other_vision_input": 85, "othercach": 1, "otherwis": [0, 1, 3, 5, 6, 40, 68, 71, 80, 85, 92, 98], "our": [21, 26, 27, 28, 29, 30, 46, 47, 48, 50, 71, 72, 75, 77, 78, 80, 91, 92, 93, 96], "out": [0, 1, 2, 10, 20, 22, 23, 24, 25, 27, 28, 29, 30, 32, 44, 52, 53, 54, 67, 70, 72, 75, 77, 78, 80, 86, 88, 89, 93], "out_bia": 81, "out_channel": 81, "out_context_dim": 81, "out_dim": 81, "out_fatur": 16, "out_featur": [16, 17, 81], "out_hidden_s": 80, "out_of_tree_exampl": 96, "out_point": 80, "out_tp": [22, 25], "outdim": 1, "outdimfirst": 1, "outer": 80, "outlin": 70, "outperform": 31, "output": [0, 1, 5, 6, 7, 9, 10, 13, 17, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 33, 34, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 53, 55, 56, 65, 68, 70, 72, 73, 74, 75, 76, 78, 79, 80, 81, 85, 86, 92, 93, 94, 97, 98, 104], "output_ctx0": 31, "output_ctx1": 31, "output_cum_log_prob": 85, "output_dim": 81, "output_dir": [10, 14, 15, 16, 17, 20, 33, 71, 74, 82, 84, 86, 92], "output_dtyp": [80, 81], "output_gen0": 31, "output_gen1": 31, "output_generation_logit": 85, "output_id": 85, "output_log_prob": 85, "output_multiplier_scal": 82, "output_pad": [80, 81], "output_path": 30, "output_s": 81, "output_seqlen": [22, 25], "output_sequence_length": 85, "output_timing_cach": [33, 68], "output_token": 71, "outputbuff": 1, "outputconfig": [0, 3, 40, 93], "outputidscba": 1, "outputlen": 0, "outputlogprob": 1, "outputtokenid": [0, 3], "outsid": [13, 19, 20, 86, 98], "outsiz": 1, "outstand": 28, "outtpsplitdim": 1, "outweigh": 74, "over": [0, 1, 9, 13, 18, 21, 23, 24, 26, 27, 29, 31, 32, 36, 68, 70, 71, 74, 77, 78, 80, 93], "overal": [3, 5, 9, 11, 13, 21, 28, 29, 30, 31, 69, 74, 75, 77, 78, 79, 96], "overcom": [5, 17, 27], "overflow": 1, "overhead": [0, 3, 17, 27, 28, 29, 31, 68, 74, 93, 98, 100], "overiew": 71, "overlap": [0, 2, 13, 21, 27, 28, 29, 30, 68, 93, 95, 99, 104], "overlap_schedul": 56, "overload": [0, 1], "overrid": [1, 18, 20, 40, 62, 68, 80, 85], "overridden": [63, 88], "override_field": 82, "overshadow": 74, "oversubscrib": [67, 73], "overus": 87, "overview": [2, 3, 8, 21, 26, 30, 62, 63, 70, 71, 73, 95, 97], "overwhelm": 55, "overwrit": [5, 34], "own": [0, 1, 9, 13, 16, 17, 18, 19, 20, 21, 28, 30, 32, 40, 63, 96], "ownership": 0, "ownsev": 1, "ownsstream": 1, "p": [0, 6, 13, 19, 32, 35, 51, 52, 53, 54, 68, 82, 85, 93, 102], "p2p": [30, 80], "p50": [71, 72], "p90": [71, 72, 73], "p95": [71, 72, 73], "p99": [71, 72, 73], "p_max": 0, "p_x": 0, "pack": [0, 1, 6, 33, 62, 79, 80, 82, 89, 96], "packag": [3, 63, 65, 71, 73, 92, 93], "packed_length": 82, "packedinput": 1, "packedmask": 1, "packedmaskhost": 1, "packedmaskhostcopi": 1, "packedmasksdevic": 1, "packedpositionid": 1, "pad": [0, 1, 6, 7, 10, 29, 33, 34, 62, 68, 69, 80, 81, 85, 89, 93], "pad_id": [68, 85], "pad_lda": 81, "pad_ldc": 81, "pad_token_id": 85, "padding_2d": 80, "padding_back": 80, "padding_bottom": 80, "padding_en": [21, 29, 68, 72], "padding_front": 80, "padding_left": 80, "padding_mod": 81, "padding_right": 80, "padding_top": 80, "padid": 0, "page": [1, 2, 6, 9, 17, 24, 33, 62, 71, 73, 75, 80, 86, 87, 89, 93, 98], "paged_context_fmha": [75, 93], "paged_kv_cach": [10, 33, 71, 85], "paged_st": [33, 85], "pagedcontextfmha": 1, "pagedkvcach": 6, "pagedst": 1, "pageid": 1, "pageidx": 1, "pagemanagerconfig": 1, "pageptr": 1, "pagewidth": 1, "paid": 30, "pair": [0, 1, 22, 28, 68, 75, 78, 80], "paper": [2, 10, 13, 23, 28, 29, 31, 90, 98], "par": [77, 78], "parallel": [0, 1, 2, 3, 5, 6, 13, 16, 17, 21, 22, 24, 25, 28, 31, 32, 34, 50, 62, 67, 68, 72, 75, 76, 80, 81, 82, 89, 93, 94, 96, 99, 104], "parallel_attent": [16, 82], "parallelconfig": [0, 93], "param": [0, 1, 18, 47, 48, 49, 50, 68, 80, 81, 85], "paramet": [0, 1, 3, 4, 5, 8, 9, 10, 13, 14, 16, 17, 18, 20, 21, 29, 31, 32, 33, 34, 51, 52, 68, 71, 74, 75, 76, 79, 80, 81, 82, 85, 87, 88, 89, 93, 94, 98, 102], "parametr": 85, "parent": [0, 1, 18, 20, 71], "parenthash": 0, "parentid": 1, "pareto": 31, "pari": [47, 48, 49, 50], "pars": [1, 68], "parser": [34, 61, 68], "part": [1, 3, 4, 7, 17, 18, 20, 29, 62, 63, 67, 68, 69, 72, 77, 78, 79, 80, 85, 87, 89], "part2": 93, "parti": 93, "partial": [0, 4, 9, 17, 27, 68, 74], "particip": [0, 80, 93], "participantid": [0, 2], "particular": [0, 3, 76, 77, 78, 86, 88], "particularli": [27, 29, 30, 31, 63, 78, 103], "partit": [5, 10, 17, 52, 53, 54], "pass": [0, 1, 3, 5, 7, 9, 10, 13, 17, 18, 30, 40, 51, 55, 67, 68, 70, 71, 73, 75, 77, 78, 80, 81, 82, 85, 87, 89, 93, 96, 97, 98, 101, 102, 104], "past": [0, 5, 28, 30, 31], "past_key_valu": [80, 81], "past_key_value_length": 81, "past_key_values_length": 81, "past_kv_length": 85, "past_sequence_length": 85, "patch": [81, 85], "patch_siz": [81, 82], "path": [0, 1, 3, 5, 12, 13, 16, 18, 21, 28, 30, 32, 33, 34, 40, 47, 48, 49, 50, 52, 53, 54, 56, 60, 63, 67, 68, 70, 71, 72, 73, 75, 80, 85, 88, 93, 94], "path_to_llama_from_hf": 97, "pathlib": [60, 68], "pathlik": 82, "pathorn": 93, "pathsoffset": 1, "pattern": [4, 27, 29, 30, 62, 68, 80, 93], "patternanalyz": 7, "patternrewrit": 7, "paus": [0, 30, 79, 104], "paused_request": 104, "pcie": [11, 30, 33], "pd": 30, "pdf": [0, 4, 10], "pdl": [27, 93], "peak": [0, 21, 22, 23, 27, 72], "peer": 30, "peft": 68, "peft_cache_config": [40, 68], "peftcacheconfig": [0, 68], "peftcachemanag": [0, 93], "penal": [0, 6, 68], "penalti": [93, 102], "penalty_alpha": 6, "pend": 104, "pending_request": 104, "per": [0, 1, 3, 5, 6, 8, 11, 13, 17, 20, 21, 22, 24, 25, 27, 28, 29, 30, 31, 32, 33, 34, 52, 53, 54, 68, 71, 72, 73, 74, 75, 80, 81, 89, 90, 93], "per_channel": 90, "per_group": 90, "per_token": 90, "per_token_scal": 80, "perceiv": 23, "percent": [0, 14], "percentag": [10, 14, 71, 72, 73], "percentil": [71, 93], "perf": [0, 21, 29, 31, 34, 61, 68, 80, 93], "perf_best_practic": 93, "perfect": [30, 31], "perfectli": 30, "perform": [0, 1, 2, 3, 5, 6, 7, 10, 12, 17, 18, 19, 20, 22, 24, 25, 28, 29, 33, 34, 40, 63, 67, 68, 69, 71, 72, 74, 77, 79, 80, 85, 86, 91, 93, 96, 98, 103], "performantli": 22, "period": 30, "permut": 80, "persimmon": 93, "persist": 26, "person": [35, 51, 55], "phase": [0, 2, 7, 13, 22, 25, 27, 28, 29, 30, 31, 33, 62, 71, 76, 77, 78, 79, 80, 89, 93, 94, 98, 103], "phi": [80, 90, 91, 93], "phi3config": 82, "phi3forcausallm": 82, "phi3model": 82, "phiconfig": 82, "phiforcausallm": 82, "phimodel": 82, "physic": [80, 89], "pick": 77, "pickl": 93, "piec": [30, 77], "piecewis": 68, "pin": [0, 1, 9], "ping": 93, "pinnedmemusag": 0, "pinnedpool": 1, "pip": [21, 34, 62, 63, 86, 93], "pip3": 65, "pipelin": [0, 1, 3, 6, 17, 22, 25, 33, 34, 50, 62, 68, 71, 72, 76, 89, 93, 104], "pipeline_parallel_s": [50, 68, 74, 75], "pipelineparallel": [0, 1, 6], "pipelineparallelismrank": 1, "pitfal": [9, 20], "pixart": 81, "pixartalphatextproject": 81, "pixel_valu": 82, "pl": [65, 71], "place": [1, 30, 33, 65, 80, 93, 96], "placemen": 30, "placement": [27, 30], "plai": 77, "plan": [3, 5, 27, 30, 31, 63], "planner": 93, "platform": [30, 35, 36, 47, 48, 50, 63, 69, 71, 93, 95], "pleas": [2, 5, 7, 11, 13, 15, 22, 24, 25, 26, 27, 29, 30, 31, 32, 36, 40, 46, 63, 64, 65, 67, 71, 72, 74, 76, 80, 92, 93, 95, 104], "plot": 31, "plu": [11, 30, 31, 85], "plugin": [5, 6, 7, 14, 16, 62, 63, 68, 77, 80, 82, 86, 89, 90, 92, 93], "plugin_config": [68, 75, 78, 80, 82], "plugin_namespac": 7, "plugin_typ": 7, "plugin_v2": 7, "plugin_v2_gemm_0": 92, "pluginconfig": [68, 83], "pluginconfigmeta": 83, "pluginfield": 93, "pluginv2build": 92, "pm": [21, 27, 71], "pmi": 92, "pmi2_init": 92, "pmix": [17, 34, 52, 53, 54, 92], "png": [34, 38, 43, 58], "po": 81, "point": [1, 5, 17, 19, 23, 26, 30, 31, 44, 46, 50, 65, 68, 72, 74, 79, 80, 86, 90, 92, 93, 94], "pointer": [0, 1, 6, 18, 30, 80, 85, 93], "pointerelementtyp": 1, "polar": 91, "polici": [0, 1, 30, 68, 71, 73, 89], "poll": [0, 34], "polyhedr": 17, "pong": 93, "pool": [0, 1, 5, 29, 30, 31, 62, 68, 80, 85, 103, 104], "pooled_project": [81, 82], "pooled_projection_dim": 81, "pooledpin": 0, "poor": 2, "popd": 92, "popfirstgentoken": 0, "popul": [1, 5, 17, 80], "popular": [5, 16, 20, 26, 28, 36, 67], "port": [0, 31, 32, 34, 36, 41, 86], "portfolio": 24, "portion": [4, 74, 80, 89], "pos_emb_typ": 80, "pos_embd_param": 98, "pos_embed_max_s": 81, "pos_embed_typ": 81, "pose": 78, "posit": [0, 1, 13, 27, 28, 68, 71, 80, 81, 85, 93, 98], "position_embed": [80, 81], "position_embedding_typ": [5, 16, 80, 81, 82], "position_encoding_2d": 82, "position_id": [82, 85, 92, 96, 98], "positionalembeddingparam": 98, "positionembeddingtyp": [5, 80, 81, 82], "positionid": [0, 1], "positionidsbas": 1, "positionidsdevic": 1, "positionidshost": 1, "positionidshostcopi": 1, "positionoffset": 1, "positionoffsetsdevic": 1, "positionoffsetshost": 1, "positionoffsetshostcopi": 1, "posix": 0, "posix_debug_fallback": 0, "possibl": [3, 5, 6, 9, 13, 17, 21, 28, 29, 30, 31, 33, 40, 63, 65, 68, 69, 70, 71, 72, 75, 77, 79, 80, 88, 89, 92, 93, 97], "possibli": [1, 8, 80], "post": [0, 16, 23, 26, 27, 28, 29, 30, 31, 69, 70, 80, 86, 93, 99], "post_act_fn": 81, "post_attention_layernorm": [18, 96], "post_input_id": 85, "post_layernorm": [15, 16, 18, 80, 92], "post_merg": 87, "post_pad": 80, "post_prompt": 85, "post_strid": 80, "posterior_threshold": 68, "posterioralpha": 1, "posterioralphahost": 1, "posteriorthreshold": [0, 1], "posteriorthresholdhost": 1, "postprocess": [34, 68, 81], "postprocess_tokenizer_dir": 68, "postprocessor": [0, 68], "postprocparam": 68, "potenti": [0, 1, 8, 13, 29, 30, 33, 70, 71, 75, 96], "pow": 80, "power": [9, 17, 24, 26, 27, 29, 30, 51, 69, 77, 93], "pp": [0, 2, 6, 10, 22, 25, 31, 34, 71, 73, 80, 93], "pp2": [31, 71], "pp_communicate_final_output_id": 85, "pp_communicate_new_token": 85, "pp_reduce_scatt": [33, 78], "pp_size": [16, 17, 34, 41, 71, 72, 74, 84, 93], "ppreducescatt": 1, "pr": [27, 30], "practic": [5, 8, 17, 23, 24, 27, 29, 30, 31, 62, 86, 89, 93], "pre": [0, 1, 3, 5, 16, 19, 30, 31, 62, 63, 65, 68, 69, 71, 80, 86, 87, 88, 89, 93, 98], "pre_input_id": 85, "pre_layernorm": 80, "pre_merg": 87, "pre_onli": 81, "pre_pad": 80, "pre_prompt": 85, "pre_quant_scal": [16, 68], "pre_strid": 80, "prebuilt": [63, 86], "preced": [17, 80], "precis": [1, 6, 18, 21, 22, 26, 30, 33, 62, 71, 75, 78, 83, 86, 89, 91, 93], "precompute_relative_attention_bia": 82, "precomputed_relative_attent": 81, "predefin": [13, 96, 98], "predict": [1, 5, 13, 27, 28, 30, 93], "predictor": 13, "predictsdrafttoken": 1, "prefer": [12, 26, 63], "prefer_managed_weight": 81, "prefer_plugin": 80, "prefetch": 27, "prefil": [0, 29, 30, 31, 68, 76, 99], "prefix": [3, 13, 16, 28, 67, 73, 80, 83, 87, 92], "prefix_token_ad": 51, "preliminari": [22, 24, 25, 30], "preload": 18, "premis": 28, "prepar": [0, 2, 27, 28, 30, 53, 62, 70, 77, 80, 82, 90, 93, 98, 102], "prepare_dataset": [21, 53, 70, 71, 72, 73], "prepare_input": [82, 89], "prepare_position_ids_for_cogvlm": 85, "prepare_recurrent_input": 82, "prepare_resourc": [97, 103], "prepend": 92, "preprocess": [18, 85, 90], "preprocess_weights_hook": 82, "preprocessor": [31, 71], "preqrequisit": 65, "prequant_scaling_factor": 16, "prerequisit": [62, 65], "presenc": [6, 17], "presence_penalti": [68, 85, 93], "presencepenalti": [0, 1, 6], "present": [0, 30, 31, 68, 71, 77, 78, 90, 93], "preserv": 75, "presid": [73, 79], "pressur": 30, "pretrain": 19, "pretrained_config": 96, "pretrained_model_name_or_path": 82, "pretrainedconfig": [15, 20, 68, 82, 83, 96], "pretrainedmodel": [20, 82, 89], "pretrainedtoken": 51, "pretrainedtokenizerbas": 68, "prevdrafttokenslen": 1, "prevent": [27, 29, 62, 67], "preview": 93, "previou": [1, 3, 4, 12, 13, 20, 21, 23, 28, 30, 64, 71, 73, 74, 75, 77, 78, 79, 86, 93], "previous": [1, 12, 22, 75, 77, 79, 93], "prevscor": 1, "prewritten": 86, "price": 71, "primari": [0, 1, 8, 26, 30, 89, 104], "primarili": 98, "primit": [17, 29, 30, 69, 86], "principl": 30, "print": [1, 5, 34, 40, 44, 46, 47, 48, 49, 50, 51, 55, 56, 57, 58, 59, 60, 65, 68, 71, 72, 73, 79, 86, 89, 92], "print_iter_log": [21, 53, 68], "prior": [3, 33, 63, 65], "priorit": [26, 77, 79], "prioriti": [0, 1, 8, 9, 18, 68], "prioritytyp": 0, "priorityupd": 0, "privat": [0, 1, 6, 32, 68], "privileg": 7, "prm": 91, "pro": 27, "prob": [80, 102], "probabilist": 81, "probabl": [0, 1, 6, 9, 13, 27, 28, 68, 80, 85, 93], "probil": 1, "problem": [5, 21, 29, 92], "proc": 18, "proccessed_weight": 18, "proccessed_zero": 18, "proce": 31, "procedur": 21, "proceed": 17, "process": [0, 1, 2, 3, 5, 6, 8, 11, 13, 16, 17, 20, 21, 27, 28, 29, 30, 31, 32, 33, 44, 46, 50, 51, 52, 53, 54, 65, 67, 68, 69, 70, 71, 72, 73, 74, 77, 78, 79, 80, 85, 86, 88, 92, 93, 94, 96, 97, 98, 104], "process_input": 85, "process_logits_including_draft": 85, "processor": [0, 5, 31, 45, 68, 82, 85, 93, 99], "processorbatch": 0, "processormap": 0, "prod": 80, "produc": [0, 1, 3, 7, 17, 40, 71, 73, 75, 77, 78, 80, 93], "product": [4, 5, 13, 17, 24, 30, 31, 51, 69, 77, 78, 79, 80, 86, 98], "profession": 32, "profil": [2, 33, 34, 42, 43, 62, 75, 77, 80, 85, 89, 92, 93, 94], "profiling_verbos": [33, 68], "profit": [13, 71], "program": [2, 20, 44, 47, 48, 50, 65, 67, 79, 86, 92], "progress": [1, 27, 68, 71, 80], "proj": [16, 18, 92], "project": [5, 10, 29, 63, 80, 81, 96, 103], "projector_hidden_act": 82, "prologu": [52, 53, 54], "promin": 13, "promis": [13, 20, 28, 31], "prompt": [0, 3, 6, 9, 15, 21, 31, 33, 34, 39, 40, 44, 46, 47, 48, 49, 50, 51, 52, 55, 56, 59, 60, 62, 65, 68, 71, 73, 77, 78, 79, 81, 85, 86, 93, 98, 102], "prompt_adapter_request": [68, 93], "prompt_embedding_t": [81, 82, 85], "prompt_embedding_table_s": 82, "prompt_id": 51, "prompt_len": 98, "prompt_logprob": 68, "prompt_lookup": [13, 93], "prompt_lookup_num_token": 6, "prompt_tabl": 85, "prompt_task": [82, 85], "prompt_token": [32, 86], "prompt_token_id": [40, 68], "prompt_vocab_s": [82, 85], "promptadapterrequest": 68, "promptinput": [68, 93], "promptlen": 0, "promptli": 31, "prompttableoffload": 0, "prompttuningconfig": 0, "prompttuningembed": 81, "prompttuningen": 1, "pronounc": [13, 30], "proof": 103, "propag": [9, 93], "proper": [2, 71], "properli": [18, 30, 32, 77, 79], "properti": [3, 46, 68, 80, 82, 83, 85, 88], "proport": 5, "propos": [0, 27], "protect": [1, 44, 50, 65, 67, 86], "protocol": [0, 31, 34, 46], "proud": [27, 30, 31], "prove": [13, 29], "provid": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 12, 13, 15, 16, 19, 20, 21, 22, 23, 26, 27, 29, 30, 31, 32, 33, 34, 35, 40, 46, 51, 63, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 80, 85, 88, 89, 91, 92, 93, 96, 97, 98], "proxy_dispatch_result_thread": 71, "prune": [7, 13, 80], "pseudo": [5, 80, 90], "pth": [18, 93], "ptq": [26, 75, 93], "ptr": 1, "ptr_idx": 18, "ptrdiff_t": 1, "ptune": 87, "ptuning_setup": 85, "ptuning_setup_fuyu": 85, "ptuning_setup_llava_next": 85, "ptuning_setup_phi3": 85, "ptuning_setup_pixtr": 85, "ptuningconfig": 0, "public": [0, 1, 26, 36], "publish": [21, 22, 25, 64, 71, 72, 86, 93], "pull": [19, 21, 32, 63, 86, 87, 93], "puneeshkhanna": 93, "purchas": 71, "pure": 85, "purpos": [5, 8, 29, 30, 31, 63, 73, 75, 77, 78], "pursu": [47, 48, 50], "push": [29, 30, 35], "pushd": 92, "put": [1, 16, 27, 52, 53, 54, 65, 67, 69, 77], "pwd": [21, 63], "py": [3, 4, 5, 7, 10, 12, 13, 14, 15, 16, 17, 18, 20, 21, 27, 28, 29, 30, 52, 53, 63, 65, 67, 70, 71, 72, 73, 74, 75, 80, 83, 85, 86, 87, 88, 92, 93, 96, 97, 103, 104], "py3": 93, "py_executor_cr": 104, "pybind": 93, "pybind11_object": 68, "pybindmirror": 68, "pydant": [68, 93], "pydantic_cor": 68, "pyexecutor": [93, 103, 104], "pynvml": 93, "pypi": [63, 86, 93], "pytest": 87, "python": [1, 5, 6, 7, 10, 13, 15, 17, 19, 20, 21, 28, 29, 31, 34, 40, 48, 49, 62, 65, 67, 68, 70, 71, 72, 73, 74, 86, 90, 93, 94, 96, 97, 103, 104], "python3": [10, 12, 14, 16, 21, 52, 53, 63, 65, 70, 71, 86, 92], "python_bind": 21, "python_e2": 85, "python_plugin": 93, "pythonpath": [21, 53, 54], "pytorch": [7, 13, 16, 19, 21, 28, 29, 30, 31, 32, 34, 41, 45, 62, 63, 65, 67, 68, 72, 80, 87, 93, 97, 98, 101, 102, 103, 104], "pytorch_backend_config": 34, "pytorch_extra_arg": 53, "pytorch_model": 92, "pytorch_model_engin": 97, "pytorch_model_registri": 103, "pytorchconfig": [68, 98], "pytorchmodelengin": [97, 103], "pzzzzz5142": 93, "q": [2, 5, 6, 10, 22, 27, 29, 62, 71, 80, 92, 96, 98], "q_b_proj": 80, "q_dim": 80, "q_lora_rank": [80, 81], "q_proj": [18, 71, 96], "q_scale": [5, 80, 81, 82], "qa": 13, "qformat": [71, 84], "qgmma": 93, "qingquansong": 93, "qk_layernorm": [81, 82], "qk_nope_head_dim": [80, 81], "qk_norm": 81, "qk_rope_head_dim": [80, 81], "qkv": [7, 10, 16, 18, 62, 80, 92, 93, 98], "qkv_bia": [80, 93], "qkv_dim": 80, "qkv_proj": 96, "qo_indptr": 98, "qpi": 11, "qserv": 93, "quadrat": [5, 89], "qualifi": 87, "qualiti": [28, 30, 75, 78], "qualnam": [68, 80, 82, 84], "quant": [20, 68, 71, 80, 93, 101], "quant_algo": [16, 18, 20, 40, 68, 71, 75, 82], "quant_config": [20, 40, 68, 75, 82, 98], "quant_medusa_head": 84, "quant_mod": [20, 68, 81, 82, 85], "quantalgo": [40, 68, 75, 82, 84], "quantconfig": [20, 40, 68, 75, 82, 93, 98], "quanticonfig": 20, "quantiz": [5, 6, 11, 17, 18, 21, 22, 23, 27, 29, 33, 47, 62, 65, 66, 67, 68, 69, 72, 73, 76, 80, 81, 82, 85, 86, 91, 93, 95, 96, 98], "quantizaton": 71, "quantize_and_export": 84, "quantize_kwarg": 82, "quantize_lm_head": [84, 93], "quantized_valu": 5, "quantizedkernel": 17, "quantizetensorplugin": 17, "quantmod": [1, 5, 6, 62, 68, 80, 81, 82, 84, 85], "quantmodewrapp": [68, 80], "queri": [3, 6, 8, 13, 17, 22, 29, 31, 32, 34, 62, 71, 80, 89, 98, 103], "query_dim": 81, "query_key_valu": 18, "query_length": 81, "query_pre_attn_scalar": 82, "question": [30, 55, 71, 89, 92], "queu": [0, 72, 77], "queue": [0, 68, 69, 87, 97], "quick": [5, 62, 69, 71, 73, 98], "quick_gelu": 80, "quicker": 74, "quickli": [20, 86], "quickstart": [67, 73], "quickstart_advanc": [28, 52], "quit": [7, 67], "qweight": 18, "qwen": [18, 34, 43, 71, 80, 82, 90, 91, 93], "qwen1": [91, 93], "qwen2": [10, 34, 38, 43, 58, 71, 91, 93], "qwen2_5_vlforconditionalgener": 91, "qwen2_audio_7b_instruct": 87, "qwen2audio": 93, "qwen2forcausallm": 91, "qwen2forprocessrewardmodel": 91, "qwen2forrewardmodel": 91, "qwen2forsequenceclassif": 93, "qwen2vl": 93, "qwen2vlforconditionalgener": 91, "qwen3": 30, "qwenforcausallm": [18, 82], "qwenforcausallmgenerationsess": 85, "qwenvl": 93, "qwq": 91, "qychen": 10, "qzero": 18, "r": [1, 10, 34, 44, 46, 47, 48, 49, 50, 51, 55, 65, 73, 79, 80, 86, 92, 93], "r1": [30, 34, 56, 61, 72, 93], "r1_in_tensorrt": [27, 93], "race": 93, "radix": 103, "rais": [20, 51, 56, 68, 73, 92, 93], "rand": [71, 80], "rand_data": 80, "rand_data_valid": 82, "random": [0, 6, 34, 42, 43, 68, 72, 80, 93], "random_se": [68, 82, 85], "randomdatasampl": 1, "randomdatavalid": 1, "randomli": [71, 72], "randomse": [1, 6, 93], "randomseedtyp": 0, "rang": [0, 6, 9, 13, 31, 32, 51, 67, 70, 71, 78, 80, 82, 89, 90, 91, 92, 96], "rank": [0, 1, 2, 3, 4, 6, 10, 20, 21, 29, 30, 33, 67, 71, 80, 82, 85, 89, 92, 93], "rank0": 16, "rank1": 16, "rapid": [13, 72, 86], "rate": [0, 21, 27, 28, 29, 31, 34, 42, 43, 71, 72, 73, 93], "rather": [5, 7, 13, 29, 30, 65, 69, 94], "ratio": [29, 30, 31], "ration": 31, "rational": 29, "raw": 34, "raw_audio": 85, "raw_imag": 85, "rdma": [2, 31], "re": [21, 26, 30, 32, 68, 69, 93, 98], "reach": [0, 5, 16, 31, 67, 71, 75, 79], "reachabl": 88, "react": 30, "read": [0, 2, 3, 5, 13, 15, 17, 18, 21, 27, 28, 30, 33, 55, 68, 71, 93, 94], "read_config_from_the_custom_training_checkpoint": 20, "readabl": 71, "reader": 80, "readi": [0, 32, 86, 94], "readm": [13, 34, 67, 73, 93], "real": [7, 12, 21, 27, 30, 63, 73, 75, 77, 78, 80, 92], "realiti": 77, "realiz": [9, 13], "rearrang": 80, "reason": [0, 5, 6, 17, 20, 27, 28, 30, 32, 34, 61, 68, 71, 74, 77, 78, 80, 87, 92], "reasoning_pars": [34, 41, 68], "rebalanc": 30, "rebuild": [78, 80, 88, 92], "receiv": [0, 1, 2, 3, 4, 11, 13, 30, 31, 75, 80, 93], "recent": [1, 4, 5, 12, 23, 27, 88], "recept": 31, "recip": [27, 29, 34, 68, 90], "reclaim": 0, "recogn": [13, 27, 30, 31, 71, 96], "recommend": [2, 5, 6, 13, 15, 18, 19, 21, 23, 26, 29, 30, 31, 34, 51, 63, 68, 71, 76, 77, 79, 92, 93, 96, 98], "recompute_scale_factor": 80, "reconfigur": [3, 65], "reconstruct": [5, 80], "record": [1, 7, 21, 27, 28, 30, 68], "recored": 0, "recreat": 19, "recurr": 13, "recurrentgemma": [90, 91, 93], "recurrentgemmaforcausallm": 82, "recurs": [21, 32, 63, 67], "recv": [0, 17, 30, 80], "recvconnect": 0, "recvpollperiodm": 0, "recycl": [5, 103], "redesign": 93, "redirect": [7, 68], "redistribut": 30, "redraft": [62, 80, 82, 85, 93], "redrafter_draft_len_per_beam": 85, "redrafter_num_beam": 85, "redrafterforllamalm": 82, "redrafterforqwenlm": 82, "redraftermixin": 82, "reduc": [2, 3, 4, 5, 9, 11, 13, 17, 21, 22, 25, 27, 28, 29, 30, 31, 32, 33, 51, 63, 67, 68, 69, 70, 71, 72, 73, 74, 77, 79, 80, 87, 89, 92, 93, 98, 100], "reduce_fus": [33, 71, 75, 78], "reduce_scatt": 80, "reduceoper": 80, "reducescatt": [33, 78, 93], "reduct": [11, 13, 27, 79, 80], "redund": [13, 27, 30], "refactor": [20, 21, 93], "refer": [0, 1, 2, 3, 5, 6, 7, 8, 10, 13, 17, 19, 20, 21, 30, 31, 32, 34, 36, 37, 38, 39, 40, 41, 42, 43, 44, 51, 57, 58, 59, 60, 63, 64, 67, 69, 71, 72, 73, 74, 75, 76, 78, 80, 86, 91, 93, 96, 98], "referenc": 75, "reference_wrapp": [0, 3], "refin": 93, "refit": [17, 33, 93], "refit_engin": 17, "reflect": 77, "refresh": [21, 71], "regard": 80, "regardless": 92, "regex": [3, 68], "region": 70, "regist": [30, 35, 62, 92, 93, 96], "register_auto_model": 96, "register_network_output": 92, "registerdesc": 0, "registermemori": 0, "regress": [5, 6, 17], "regular": [0, 3, 5, 27, 68, 80], "reinforc": 76, "reject": [0, 28], "rel": [9, 22, 30, 77, 79, 80, 93], "rel_attn_t": 81, "relat": [2, 4, 8, 18, 62, 64, 69, 70, 80, 83, 89, 92, 93, 95, 96, 103], "relationship": 89, "relative_attent": [80, 81], "relative_attention_bia": 80, "relax": [5, 30], "relaxed_delta": [27, 28, 56, 68], "relaxed_topk": [27, 28, 56, 68], "releas": [1, 5, 6, 8, 20, 22, 25, 26, 30, 31, 62, 63, 69, 80, 82, 86, 89, 90, 91], "release_build": [32, 63], "release_run": [63, 86], "releasepag": 1, "releasest": 0, "relev": [6, 63, 88, 103], "reli": [2, 5, 7, 20, 30, 31, 67, 70, 90], "reload": [3, 30], "relu": [16, 17, 80, 92], "remain": [0, 7, 9, 13, 14, 27, 30, 63, 72, 73, 75, 77, 78, 80, 87, 89, 93], "remaind": 75, "remark": [27, 28], "rememb": 30, "remind": [5, 98], "remot": [30, 68], "remotenam": 0, "remov": [0, 1, 5, 6, 7, 8, 17, 18, 21, 28, 31, 33, 34, 63, 68, 69, 75, 80, 87, 89, 93, 96], "remove_const_t": 1, "remove_cv_t": 0, "remove_duplicated_kv_head": 82, "remove_input_pad": [5, 10, 33, 80, 81, 85], "remove_pointer_t": 1, "remove_reference_t": 1, "remove_sequ": 103, "renam": 93, "reopen": 88, "reorder": [80, 81], "reorder_kv_cache_for_beam_search": 85, "rep": 70, "repeat": [0, 5, 28, 29, 68, 80], "repeat_interleav": 80, "repeatedli": 13, "repetit": [0, 6, 51, 68, 80], "repetition_penalti": [6, 68, 85, 93], "repetitionpenalti": [0, 1, 6], "replac": [1, 4, 7, 17, 18, 20, 21, 29, 32, 71, 73, 75, 79, 80, 89, 96], "replace_add_with_sub": 7, "replace_all_uses_with": [7, 80], "replace_input_with": 7, "replace_output_uses_with": 7, "replace_outputs_uses_with": 7, "replai": 30, "replic": [0, 3, 27, 30, 80], "replit": [90, 91, 93], "repo": [20, 69, 73, 92], "repo_id": 55, "report": [8, 28, 29, 30, 32, 70, 71, 72, 89, 93], "report_load_statist": 30, "reportpluginerror": 92, "repositori": [13, 19, 21, 35, 63, 67, 86, 88], "repres": [0, 1, 2, 8, 12, 13, 21, 22, 26, 27, 30, 46, 55, 68, 71, 77, 80, 85, 104], "represent": [7, 17], "reproduc": [62, 71, 93], "req": [21, 71, 72, 73, 75, 77, 78], "req_id": 51, "req_stat": 104, "reqbeamwidth": 1, "reqid": 0, "reqpromptlength": 1, "request": [0, 2, 5, 6, 9, 10, 17, 21, 23, 25, 28, 29, 30, 31, 33, 34, 42, 43, 53, 68, 69, 70, 71, 72, 73, 75, 77, 78, 79, 80, 86, 87, 89, 93, 97, 98, 103, 104], "request_id": [40, 68, 98], "request_perf_metr": 68, "request_stats_max_iter": 68, "request_timeout": 34, "request_typ": 68, "request_type_context_and_gener": 0, "request_type_context_onli": 0, "request_type_generation_onli": 0, "requesterror": 68, "requestid": [0, 2, 3], "requestidtyp": 0, "requestlist": 104, "requestoutput": [40, 68, 93], "requestperfmetr": [0, 68], "requestschedul": 104, "requeststag": 0, "requeststat": 0, "requeststatsmaxiter": 0, "requeststatsperit": 0, "requeststatsperiter": 0, "requeststatsvec": 0, "requesttoken": 3, "requesttyp": [0, 1, 68], "requesttypesdevic": 1, "requestvector": 1, "requir": [0, 2, 5, 6, 9, 10, 13, 17, 18, 20, 21, 22, 26, 27, 29, 30, 31, 33, 34, 46, 55, 63, 65, 67, 68, 71, 72, 73, 74, 75, 78, 80, 81, 86, 87, 88, 89, 91, 92, 93, 103], "require_ln_f": 82, "requiresattentionmask": 1, "rerun": 78, "rescale_output_factor": 81, "research": [5, 28, 30, 36, 47, 48, 50, 90], "reserv": [0, 1, 34, 68, 79, 85, 89, 104], "reserved_block": 104, "reset": [0, 1, 6, 68, 71, 85], "resetspeculativedecodingmodul": 1, "reshap": [1, 80], "reshapebuff": 1, "reshapecacheindirectionbuff": 1, "reshapespeculativedecodingbuff": 1, "resid": [10, 30], "residu": [80, 92], "residual_connect": 81, "residual_mlp": 82, "residual_multipli": 82, "residual_rms_norm": 80, "residual_rms_norm_out_quant_fp8": 80, "residual_rms_norm_out_quant_nvfp4": 80, "residual_rms_norm_quant_fp8": 80, "residual_rms_norm_quant_nvfp4": 80, "residual_rms_prepost_norm": 80, "residualadd": [33, 78, 93], "resiz": 1, "resolv": [31, 34, 38, 58, 92], "resourc": [0, 2, 5, 20, 27, 29, 31, 87, 94, 97, 103, 104], "respect": [4, 31, 32, 40, 79, 80, 85, 88, 89, 90, 96, 104], "respond": 94, "respons": [0, 2, 8, 31, 34, 40, 56, 57, 58, 59, 60, 68, 71, 80, 94, 97, 100], "responsewithid": 0, "rest": [1, 5, 31, 75], "restart": 0, "restrict": [0, 3, 6, 63, 68, 80, 87, 102], "result": [0, 1, 4, 5, 11, 13, 17, 22, 23, 24, 26, 28, 29, 30, 31, 33, 40, 62, 63, 68, 71, 74, 75, 76, 77, 78, 80, 81, 87, 93, 96, 98, 102, 104], "retail": 71, "retain": [22, 24, 28], "retent": [0, 68], "retentionprior": 0, "retentionpriorityanddur": 0, "rethink": 13, "retri": 87, "retriev": [1, 18, 31, 68, 72, 80], "return": [0, 1, 3, 7, 10, 13, 15, 17, 18, 20, 31, 32, 40, 51, 68, 71, 77, 80, 81, 82, 85, 89, 92, 93, 103, 104], "return_all_generated_token": 85, "return_context_logit": 68, "return_dict": 85, "return_encoder_output": [68, 85], "return_generation_logit": 68, "return_perf_metr": 68, "returnallgeneratedtoken": [0, 3], "returncontextlogit": 0, "returnencoderoutput": 0, "returngenerationlogit": 0, "returnlogprob": 0, "returnperfmetr": 0, "reus": [0, 2, 3, 8, 28, 33, 62, 66, 68, 80, 85, 87, 88, 89, 93, 96, 99, 103], "reusabl": [8, 9, 30], "reusedblock": 0, "reusedblocksperrequest": 0, "reveal": [27, 29], "revers": 80, "revert": 80, "review": [30, 71], "revis": 68, "revolution": 69, "rewind": [28, 93], "rewrit": [62, 80, 93, 96], "rewritepatternmanag": 7, "rewrt": 92, "rf": 92, "rg_lru": 80, "rgc": 71, "rh": [0, 1], "rich": 16, "right": [31, 69, 75, 80, 92], "rigor": 71, "risk": [2, 17, 75, 79], "rm": [63, 80, 91, 92, 96], "rms_norm": [27, 80, 96], "rmsnorm": [10, 27, 80, 81, 82, 93, 96], "rnn": [33, 93], "rnn_conv_dim_s": 85, "rnn_head_siz": 85, "rnn_hidden_s": 85, "rnn_state": 82, "rnnconfig": 1, "rnnconvdims": 1, "rnnheadsiz": 1, "rnnhiddens": 1, "ro": [21, 88], "roberta": [91, 93], "robertaforquestionansw": 82, "robertaforsequenceclassif": 82, "robertamodel": 82, "robin": 31, "robust": [27, 30, 93], "rock": 80, "roi": 51, "role": [17, 31, 32, 34, 37, 38, 46, 57, 58, 77, 86], "roll": 62, "rooflin": 29, "root": [16, 21, 35, 63, 65, 67, 68, 73, 80, 86], "root_lay": 7, "rootless": 88, "rope": [27, 29, 80, 85, 93, 98], "rope_gpt_neox": [5, 80, 82], "rope_gptj": [5, 80], "rope_local_base_freq": 82, "rope_scaling_config": 80, "rope_scaling_long_factor": 81, "rope_scaling_long_mscal": 81, "rope_scaling_short_factor": 81, "rope_scaling_short_mscal": 81, "ropeembeddingutil": 80, "rotari": [0, 27, 80, 85, 96, 98], "rotary_bas": 82, "rotary_cos_sin": 80, "rotary_dim": 82, "rotary_embed": 96, "rotary_embedding_bas": [80, 81], "rotary_embedding_base_loc": 81, "rotary_embedding_beta_fast": 81, "rotary_embedding_beta_slow": 81, "rotary_embedding_dim": [5, 80, 82], "rotary_embedding_long_m_scal": 80, "rotary_embedding_max_posit": 80, "rotary_embedding_mscal": 81, "rotary_embedding_mscale_all_dim": 81, "rotary_embedding_origin_max_posit": 81, "rotary_embedding_original_max_posit": 80, "rotary_embedding_percentag": 81, "rotary_embedding_sc": 81, "rotary_embedding_scal": 80, "rotary_embedding_scale_typ": 80, "rotary_embedding_short_m_scal": 80, "rotary_inv_freq": [80, 81], "rotary_inv_freq_loc": 81, "rotary_pct": 82, "rotary_sc": [81, 82], "rotaryembed": 96, "rotaryembeddingdim": [0, 1], "rotaryscalingtyp": 80, "rotate_every_two": 80, "rotate_half": 80, "round": [31, 68, 80, 94], "round_robin": 31, "rout": [2, 29, 30, 31], "router": [4, 10, 29, 30, 31, 93], "router_gemm": 27, "routin": [7, 30], "routingkernel": 27, "row": [10, 77, 80, 90, 93], "rowlinear": [10, 81], "rowwis": 68, "rr": 93, "rslora": 93, "rst": 3, "rtx": 93, "rubric": 80, "rule": [5, 74, 92], "run": [0, 1, 2, 3, 5, 6, 9, 12, 13, 15, 16, 17, 22, 26, 27, 29, 31, 32, 33, 34, 35, 36, 45, 48, 49, 62, 63, 65, 67, 68, 69, 74, 75, 77, 78, 79, 80, 85, 87, 88, 89, 90, 92, 93, 94, 96, 97, 98, 100, 103], "run_dtm_pld": 13, "run_eagle3": 56, "run_mtp": 56, "run_ngram": 56, "runner": [0, 16, 85], "runningleon": 93, "runpod": 35, "runtim": [0, 3, 5, 13, 14, 19, 27, 28, 30, 31, 33, 34, 51, 55, 62, 67, 68, 69, 70, 71, 73, 76, 77, 80, 81, 82, 86, 92, 93, 96, 98, 104], "runtime_config": 40, "runtime_default": 82, "runtime_error": 1, "runtime_rank": 85, "runtimedefault": [0, 82], "runtimedefaultsin": 82, "runtimeerror": [67, 68, 92], "runtimetensor": 85, "s0": 5, "s1": 5, "s2": 5, "sacrif": 27, "sad": 85, "saeyoonoh": 93, "safe": [1, 7, 29, 78], "safer": 80, "safetensor": [16, 18, 92, 93], "sage_attn": 80, "sage_attn_k_block_s": 80, "sage_attn_k_quant_s": 80, "sage_attn_q_block_s": 80, "sage_attn_q_quant_s": 80, "sage_attn_v_block_s": 80, "sage_attn_v_quant_s": 80, "sageattent": 80, "sai": [30, 70, 73, 77], "said": 75, "sake": 77, "sale": [51, 71], "same": [0, 1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 13, 14, 17, 20, 23, 28, 29, 30, 31, 33, 52, 53, 54, 63, 67, 68, 71, 72, 75, 78, 79, 80, 81, 83, 85, 87, 89, 93], "sampl": [0, 1, 3, 5, 17, 19, 21, 27, 28, 47, 48, 49, 50, 51, 55, 62, 66, 68, 70, 71, 72, 80, 81, 85, 93, 95, 100], "sample_proj_bia": 81, "sample_weight_strip": 93, "samplemod": 80, "sampler": [68, 99], "sampling_config": 85, "sampling_param": [40, 44, 46, 47, 48, 49, 50, 51, 65, 68, 73, 79, 86, 93, 102], "samplingconfig": [0, 3, 6, 40, 85, 93], "samplingparam": [40, 44, 46, 47, 48, 49, 50, 51, 56, 65, 68, 73, 79, 86, 93, 102], "saniti": [65, 74, 75, 78], "santacod": [90, 91], "satfinit": 90, "satisfi": [6, 18, 30, 31, 93], "satur": 30, "save": [5, 9, 13, 20, 21, 28, 29, 30, 33, 35, 70, 71, 75, 78, 79, 89, 93], "save_checkpoint": [20, 82], "save_config": [20, 82], "saw": [75, 86], "sbatch": [17, 52, 53, 54, 94], "sbsa": [93, 95], "scaffold": [93, 96], "scalabl": 30, "scalar": [6, 11, 80], "scalartyp": 93, "scale": [0, 6, 10, 18, 29, 31, 33, 68, 75, 80, 81, 90, 93], "scale_d0": 80, "scale_d1": 80, "scale_factor": 80, "scale_output": 80, "scale_qk": 81, "scale_typ": 80, "scaling_factor": 80, "scaling_long_factor": 80, "scaling_short_factor": 80, "scalingvecpoint": 1, "scanreducetempstorag": 1, "scanreducetempstoragebyt": 1, "scantempstorag": 1, "scantempstoragebyt": 1, "scarc": 87, "scatter": [7, 30, 80], "scatter_nd": 80, "scenario": [5, 11, 13, 16, 21, 24, 26, 27, 29, 30, 31, 33, 36, 71, 72, 73, 75, 77, 78, 93], "scfg": 85, "schedul": [0, 2, 3, 9, 10, 21, 28, 29, 30, 33, 34, 68, 71, 73, 78, 89, 93, 95, 99], "schedule_request": 104, "scheduled_request": 104, "scheduler_config": [68, 79], "schedulerconfig": [0, 68, 79, 93], "schedulerpolici": 93, "schema": [0, 3, 46, 68, 71], "scheme": 0, "scicod": 27, "scienc": [47, 48, 50], "scope": [19, 28, 93], "score": [6, 29], "scout": 91, "scratch": [30, 71, 73, 74, 78, 88], "script": [10, 12, 15, 17, 20, 21, 30, 31, 35, 52, 53, 54, 63, 67, 70, 71, 72, 73, 83, 88, 90, 92, 93, 96, 101], "sd3": 81, "sd35adalayernormzerox": 81, "sd3patchemb": 81, "sd3transformer2dmodel": 82, "sd3transformer2dmodelconfig": 82, "sdxl": 93, "seamless": 93, "seamlessli": 67, "search": [0, 1, 3, 6, 13, 19, 25, 33, 34, 40, 62, 68, 75, 77, 80, 87, 93, 97], "seashor": [34, 38, 58], "sec": [21, 23, 31, 71, 72, 73, 75, 77, 78], "second": [1, 3, 6, 9, 10, 13, 21, 22, 24, 25, 27, 30, 31, 32, 68, 77, 80], "secondari": [0, 8, 68, 89], "secondary_offload_min_prior": 68, "secondaryoffloadminprior": 0, "secondli": 77, "section": [3, 6, 17, 18, 20, 21, 28, 29, 30, 34, 63, 69, 71, 73, 75, 76, 77, 78, 80, 86, 87, 88, 91, 93, 98], "section_s": 80, "secur": [46, 93], "securityprotocol": 46, "see": [0, 1, 5, 6, 8, 13, 17, 18, 21, 22, 24, 25, 26, 28, 29, 30, 34, 35, 36, 38, 44, 58, 63, 64, 65, 71, 72, 73, 75, 77, 78, 79, 80, 81, 82, 86, 87, 88, 89, 90, 92, 93, 103], "seed": [0, 6, 34, 42, 43, 68, 84, 93], "seem": [9, 55, 71, 74], "seen": [13, 21, 30, 71], "segment": 93, "select": [0, 4, 6, 19, 26, 27, 29, 31, 33, 62, 71, 78, 80, 85, 87, 89, 97, 104], "selectcontextid": 0, "selectgenidx": 0, "selective_scan": 80, "self": [0, 5, 7, 15, 17, 18, 51, 68, 71, 80, 82, 85, 92, 96, 103, 104], "self_attent": 18, "self_attention_mask": 81, "self_attention_packed_mask": 81, "self_attn": [18, 96], "selfidx": 0, "sell": 71, "semicolon": 63, "send": [0, 2, 17, 27, 30, 31, 34, 73, 74, 80, 86, 93], "sens": 75, "sensit": [27, 30, 75], "sent": [0, 13, 29, 30, 31, 34, 68], "sentenc": [0, 6, 51, 68, 86], "separ": [11, 13, 30, 31, 33, 63, 68, 71, 80, 85, 87, 94, 98], "separate_match_rewrit": 7, "seq": [1, 5, 71, 80], "seq_idx": 85, "seq_len": [72, 80, 81, 98], "seq_length": 80, "seq_lens_cuda": 98, "seqlen": [0, 80], "seqslot": 1, "sequenc": [0, 1, 3, 5, 6, 7, 8, 9, 13, 17, 21, 22, 23, 24, 25, 27, 28, 29, 30, 31, 51, 68, 69, 71, 72, 73, 76, 79, 80, 81, 85, 89, 93, 94, 98, 103], "sequence_length": [80, 81, 85, 92], "sequence_length_buff": 85, "sequence_limit_length": 85, "sequenceindex": [0, 3], "sequencelengthscba": 1, "sequencelimitlength": 1, "sequenti": [0, 2, 13, 28, 89], "seri": 93, "serial": [33, 80, 82, 85], "serializ": 68, "serialize_engin": 85, "serializeds": 0, "serializedst": 0, "serv": [0, 2, 3, 5, 8, 13, 17, 19, 25, 26, 30, 32, 37, 38, 39, 41, 42, 43, 45, 57, 58, 59, 60, 62, 68, 78, 93, 94, 97, 98, 99, 100], "server": [0, 9, 13, 17, 19, 23, 30, 35, 37, 38, 39, 41, 42, 43, 57, 58, 59, 60, 62, 93, 94], "server_rol": 34, "server_start_timeout": 34, "servic": [19, 31, 51, 62, 88], "session": [5, 67, 71, 85], "set": [0, 1, 2, 3, 4, 5, 6, 7, 8, 11, 12, 13, 14, 16, 18, 19, 20, 21, 27, 29, 30, 31, 32, 33, 34, 40, 46, 52, 53, 54, 63, 65, 68, 69, 70, 72, 73, 75, 77, 78, 79, 80, 81, 82, 83, 85, 86, 87, 88, 89, 92, 93, 94, 100, 104], "set_attn_processor": 82, "set_default_max_input_len": 68, "set_from_opt": 1, "set_if_not_exist": 82, "set_input_shap": 85, "set_rank": 82, "set_rel_attn_t": 81, "set_runtime_knobs_from_build_config": 68, "set_shap": 85, "setadditionalmodeloutput": [0, 3], "setallottedtimem": 0, "setbackend": 0, "setbadword": 0, "setbatchingtyp": 0, "setbeamsearchdiversityr": 0, "setbeamwidth": 0, "setbeamwidtharrai": 0, "setbitto": 0, "setcachest": 0, "setcachetransceiverconfig": 0, "setclientid": 0, "setcommst": 0, "setcommunicationmod": 0, "setcommunicationtyp": 0, "setcontextfmha": 1, "setcontextphaseparam": 0, "setcopyonpartialreus": 0, "setcrossattentionmask": 0, "setcrosskvcachefract": 0, "setcudagraphcaches": 0, "setcudagraphmod": 0, "setdatatyp": 1, "setdebugconfig": 0, "setdebuginputtensor": 0, "setdebugoutputtensor": 0, "setdebugtensornam": 0, "setdebugtensorsmaxiter": 0, "setdecodingconfig": 0, "setdecodingmod": 0, "setdeviceid": 0, "seteagleconfig": 0, "setearlystop": 0, "setembeddingbia": 0, "setenableblockreus": 0, "setenablechunkedcontext": 0, "setenablecontextfmhafp32acc": 0, "setenablepartialreus": 0, "setenabletrtoverlap": 0, "setencodedvocab": 0, "setencoderhiddens": 1, "setencoderinputfeatur": 0, "setencoderinputtokenid": 0, "setencoderoutputlength": 0, "setendid": 0, "seteventbuffermaxs": 0, "setexecutionconfig": 1, "setextendedruntimeperfknobconfig": 0, "setexternaldrafttokensconfig": 0, "setfreegpumemoryfract": 0, "setfrequencypenalti": 0, "setfrom": 0, "setfrominput": 1, "setgathergenerationlogit": 0, "setgemmallreducedtyp": 1, "setgenerationstep": 1, "setgpuweightsperc": [0, 14], "setguideddecodingconfig": 0, "setguideddecodingparam": 0, "sethostcaches": 0, "setinittozero": 1, "setisorchestr": 0, "setiterstatsmaxiter": 0, "setkvcacheconfig": 0, "setkvcacheretentionconfig": 0, "setkvcachetyp": 1, "setlanguageadapteruid": 0, "setlayertyp": 1, "setlengthpenalti": 0, "setlevel": 1, "setlogitsdtyp": 1, "setlogitspostprocessor": 0, "setlogitspostprocessorconfig": 0, "setlogitspostprocessornam": 0, "setlookaheadconfig": 0, "setlookaheaddecodingconfig": 0, "setloraconfig": 0, "setloramodul": 1, "setmanagedweightsmap": 1, "setmanageweightstyp": 1, "setmaxattentionwindowvec": 0, "setmaxbatchs": [0, 1], "setmaxbeamwidth": [0, 1], "setmaxdraftpathlen": 1, "setmaxdrafttoken": 1, "setmaxencoderlen": 1, "setmaxinputlen": 1, "setmaxlorarank": 1, "setmaxnumpath": 1, "setmaxnumtoken": [0, 1], "setmaxpagesperblock": 1, "setmaxpositionembed": 1, "setmaxpromptembeddingtables": 1, "setmaxqueues": 0, "setmaxseqidlemicrosecond": 0, "setmaxsequencelen": 1, "setmaxtoken": 0, "setmedusachoic": 0, "setmem": 1, "setmemorytyp": 1, "setminp": 0, "setmintoken": 0, "setmlphiddens": 1, "setmodelnam": 1, "setmodelvari": 1, "setmropeconfig": 0, "setmultiblockmod": 0, "setmultimodalembed": 0, "setmultimodalinput": 0, "setnbcrosskvhead": 1, "setnbkvhead": 1, "setnorepeatngrams": 0, "setnormalizelogprob": 0, "setnumcopystream": 1, "setnumdecodingenginetoken": 1, "setnumkvheadspercrosslay": 1, "setnumkvheadsperlay": 1, "setnumlanguag": 1, "setnumnod": 0, "setnumreturnsequ": 0, "setonboardblock": 0, "setorchestratorconfig": 0, "setorchleadercomm": 0, "setoutputconfig": 0, "setpadid": 0, "setpagedcontextfmha": 1, "setpagewidth": 1, "setparallelconfig": 0, "setparticipantid": 0, "setpath": 1, "setpeftcacheconfig": 0, "setpositionid": 0, "setppreducescatt": 1, "setpresencepenalti": 0, "setprior": 0, "setprocessorbatch": 0, "setprocessormap": 0, "setprompttableoffload": 0, "setprompttuningconfig": 0, "setquantmod": 1, "setrecvpollperiodm": 0, "setrepetitionpenalti": 0, "setrepl": [0, 3], "setrequeststatsmaxiter": 0, "setrequesttyp": 0, "setreturnallgeneratedtoken": 0, "setrnnconfig": 1, "setrotaryembeddingdim": 1, "setsamplingconfig": 0, "setschedulerconfig": 0, "setse": 0, "setsecondaryoffloadminprior": 0, "setsinktokenlength": 0, "setsizeperhead": 1, "setskipcrossattnblock": [0, 1], "setslotsperpag": 1, "setspawnprocess": 0, "setspecdecconfig": 0, "setspeculativedecodingmod": 1, "setspeculativedecodingmodul": 1, "setstoptokenid": 0, "setstopword": 0, "setstream": 0, "settemperatur": 0, "setter": [0, 6], "settokenizerstr": 0, "settokensperblock": 1, "settopk": 0, "settopp": 0, "settoppdecai": 0, "settoppmin": 0, "settoppresetid": 0, "settotalnumpag": 1, "setup": [1, 5, 31, 33, 46, 52, 53, 54, 65, 67, 74, 75, 85, 86, 89, 93], "setup_embedding_parallel_mod": 68, "setup_fake_prompt": 85, "setup_fake_prompts_qwen2vl": 85, "setup_fake_prompts_vila": 85, "setup_input": 85, "setupbuff": 1, "setupcacheindirect": 1, "setupcacheindirectionbuff": 1, "setupspeculativedecod": 1, "setupspeculativedecodingbuff": 1, "setuptool": 65, "setusecrossattent": 1, "setusegpudirectstorag": 0, "setusemrop": 1, "setusepositionembed": 1, "setuseshapeinfer": 1, "setusetokentypeembed": 1, "setuseuvm": 0, "setworkerexecutablepath": 0, "setzero": [0, 1], "seve": 68, "sever": [0, 1, 2, 5, 7, 13, 16, 30, 31, 32, 40, 75, 76, 77, 78, 80, 89, 92, 98], "sft": 55, "sglang": [30, 100], "sh": [17, 32, 35, 88, 93, 101], "shah": 93, "shall": [20, 89], "shape": [0, 1, 5, 7, 10, 16, 17, 27, 29, 68, 78, 80, 82, 85, 89, 90, 92, 93, 98, 103], "shape_cast_dtyp": 80, "shapeequ": 1, "shard": [18, 27, 62, 71, 76, 80, 81, 87], "shard_map": 18, "sharding_along_vocab": 68, "sharding_dim": [80, 81], "share": [1, 3, 5, 7, 8, 9, 10, 13, 20, 21, 26, 27, 28, 29, 30, 31, 32, 33, 63, 74, 75, 80, 81, 93], "share_embed": 93, "share_weight": 81, "shared_embedding_t": 93, "shared_expert_output": 80, "shared_fc1": 29, "shared_fc2": 29, "shared_ptr": [0, 1], "sharedconstptr": 1, "sharedptr": 1, "shelf": 93, "shell": [64, 86, 88, 94], "sherlock113": 93, "shift": [11, 28, 30], "ship": 20, "shm": [30, 92], "short": [5, 30, 71, 75, 77], "short_mscal": [80, 81], "shorter": [5, 51, 72], "shot": 93, "should": [0, 1, 3, 7, 9, 10, 11, 20, 21, 29, 30, 40, 46, 52, 53, 54, 55, 63, 68, 71, 72, 73, 74, 78, 79, 80, 81, 83, 85, 86, 87, 89, 93, 96, 98, 103, 104], "should_stop": 85, "shouldus": 5, "show": [2, 3, 17, 23, 27, 28, 29, 30, 31, 34, 44, 72, 73, 77, 78, 86, 87, 89, 91, 95], "showcas": [75, 78, 86], "shown": [11, 24, 28, 30, 31, 34, 63, 71, 73, 75, 77, 78, 80], "shrunk": 80, "shuffl": 80, "shutdown": [0, 67, 68], "si": 5, "sibl": 17, "side": [3, 30, 80], "side_stream_id": 80, "sidestreamidtyp": 80, "sigh": 55, "sigmoid": [17, 80], "signal": 0, "signatur": [7, 80], "signifi": 77, "signific": [3, 5, 8, 24, 28, 29, 30, 55, 74, 75, 77, 78], "significantli": [26, 27, 28, 29, 30, 31, 73, 74, 75, 77, 78, 89, 98, 100], "silicon": 29, "silu": [17, 80, 81], "similar": [0, 5, 6, 7, 13, 21, 22, 24, 28, 30, 40, 70, 71, 79, 80, 97, 104], "similarli": 13, "simpl": [7, 8, 13, 17, 30, 32, 44, 63, 67, 69, 72, 86, 95], "simpler": [13, 30], "simpleschedul": 104, "simplest": [64, 80], "simpli": [5, 13, 67, 69, 71, 72, 77, 86, 92, 96], "simplic": 20, "simplifi": [5, 20, 67, 71, 77, 80, 93], "simultan": [13, 77], "sin": [0, 80, 81], "sinc": [0, 1, 4, 5, 7, 9, 13, 14, 20, 21, 28, 29, 30, 35, 40, 51, 63, 68, 71, 73, 74, 75, 77, 78, 80, 82, 89, 97, 103, 104], "sincer": 29, "sinco": 81, "singl": [0, 1, 2, 3, 4, 5, 6, 8, 13, 15, 17, 20, 21, 24, 25, 27, 28, 29, 30, 31, 32, 33, 34, 38, 58, 67, 68, 70, 71, 75, 78, 80, 82, 86, 89, 90, 93, 94, 96, 97, 98, 103], "singleton": [7, 80], "sink": [0, 1, 5, 68, 85], "sink_token_len": 85, "sink_token_length": [5, 68, 85], "sinktokenlength": [0, 1], "sinusoid": 81, "sit": [20, 55], "situaiton": 72, "situat": [13, 55, 62, 73, 77], "six": 28, "size": [0, 1, 2, 5, 6, 8, 9, 10, 11, 13, 14, 21, 23, 24, 26, 27, 28, 29, 30, 33, 34, 40, 52, 53, 54, 62, 68, 70, 71, 72, 73, 74, 75, 76, 78, 80, 81, 82, 85, 92, 93, 94, 98, 104], "size_t": [0, 1], "size_typ": [0, 1], "sizeof": 1, "sizeperhead": [0, 1], "sizetype32": [0, 1], "sizetype64": [0, 1], "skip": [0, 1, 7, 18, 21, 36, 63, 68, 80, 87, 104], "skip_attn": [80, 81], "skip_cross_attn_block": [82, 85], "skip_cross_kv": [81, 85], "skip_encod": 85, "skip_special_token": [68, 93], "skip_tokenizer_init": [40, 68], "skipcrossattnblock": [0, 1], "sku": [73, 75, 77, 78], "skywork": [90, 91, 93], "sleep": 36, "slice": [1, 4, 18, 80, 93], "slice_shap": 18, "sliceinputtyp": 80, "slicen": 1, "slide": [0, 8, 62, 79, 80, 85, 93, 99], "slider": [21, 27, 71], "sliding_window": 82, "sliding_window_caus": 80, "sliding_window_pattern": 82, "slight": [21, 28, 29, 75, 77, 78], "slightli": [0, 2, 10, 11, 34, 75, 78], "slope": [5, 80], "slot": [0, 1, 30, 93], "slot_map": [80, 82], "slotid": 30, "slotidx": 1, "slotsperpag": 1, "slow": [3, 9, 68, 69, 74], "slower": [8, 20, 29, 74], "slowest": 5, "slurm": [17, 30, 65, 67, 92, 93], "slurm_job_nodelist": 94, "slurm_tasks_per_nod": 94, "sm": [91, 93], "sm120": 93, "sm80": [91, 93], "sm86": [91, 93], "sm89": [91, 93], "sm90": [91, 93], "small": [5, 9, 11, 13, 17, 26, 27, 28, 29, 30, 51, 73, 75, 77, 78, 80, 89, 92, 93], "smaller": [1, 13, 21, 28, 33, 70, 71, 74, 77, 78, 79, 80, 89, 93], "smallest": [0, 1, 8, 80], "smart": [31, 80], "smaug": [91, 93], "smi": [21, 27, 32, 71, 89], "smile": 55, "smith": [47, 48, 49, 50], "smooth": [20, 68, 93], "smoother": 21, "smoothquant": [7, 26, 62, 93], "smoothquant_v": 68, "snapshot": 71, "snapshot_download": 55, "snip": 71, "snippet": [71, 93, 104], "snshrivas10": 55, "so": [0, 3, 5, 7, 10, 13, 19, 20, 21, 27, 28, 29, 30, 35, 40, 63, 68, 71, 74, 75, 77, 78, 79, 80, 81, 82, 87, 89, 91, 93, 96, 103], "socketst": 0, "softmax": [5, 17, 28, 29, 80, 98], "softplu": 80, "softwar": [3, 5, 17, 29, 30, 62, 69, 93], "sol": 31, "solid": 76, "solut": [19, 30, 67, 92, 97], "some": [0, 2, 3, 4, 5, 6, 7, 9, 13, 14, 16, 17, 20, 21, 27, 28, 29, 30, 31, 33, 34, 36, 51, 55, 65, 67, 68, 69, 72, 75, 76, 78, 79, 80, 83, 86, 87, 88, 89, 92, 93, 96, 97, 104], "some_uri": 88, "someth": [17, 40], "sometim": [30, 31, 71, 87], "song": 71, "soon": [0, 22, 23, 24, 25, 26, 30, 40], "sora": [34, 38, 58], "sort": [0, 1, 3, 6, 80], "sota": 93, "sourc": [12, 15, 16, 18, 20, 21, 22, 25, 27, 29, 30, 33, 34, 37, 38, 39, 41, 42, 43, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 62, 64, 68, 69, 80, 81, 82, 83, 84, 85, 86, 88, 93], "source_dir": 88, "source_root": [52, 53, 54], "sourcetaskvalu": 1, "soyer": [15, 17, 92], "space": [10, 30, 31, 63, 68, 77, 89, 94, 103], "spaces_between_special_token": [68, 93], "span": [20, 27, 28, 30, 31], "spars": [13, 29, 80, 93], "sparse_fc1": 29, "sparse_fc2": 29, "sparsiti": [30, 33], "spatial_norm_dim": 81, "spawn": [44, 50, 65, 67, 73, 86, 92], "spawnprocess": 0, "spec": [30, 33], "spec_config": 56, "spec_dec_mod": 68, "spec_decode_algo": 28, "spec_decode_nextn": 28, "spec_decoding_generation_length": [80, 81, 82], "spec_decoding_is_generation_length_vari": [80, 81, 82], "spec_decoding_max_generation_length": [80, 81], "spec_decoding_packed_mask": [80, 81, 82], "spec_decoding_param": [81, 82], "spec_decoding_position_offset": [80, 81, 82], "spec_decoding_us": [80, 81], "specdec": 0, "specdecconfig": 0, "specdecfastlogitsinfo": 0, "specdecodinggenerationlength": 1, "specdecodinggenerationlengthshost": 1, "specdecodingpackedmask": 1, "specdecodingparam": 81, "specdecodingpositionoffset": 1, "specdecodingstat": 0, "special": [2, 5, 10, 17, 18, 22, 28, 33, 68, 93], "specif": [0, 1, 4, 6, 7, 8, 10, 11, 12, 13, 16, 20, 23, 26, 27, 29, 30, 31, 32, 34, 51, 63, 65, 67, 71, 74, 75, 78, 80, 86, 87, 93, 96, 97], "specifi": [0, 1, 2, 3, 5, 6, 7, 8, 10, 13, 18, 20, 21, 30, 33, 34, 40, 46, 51, 55, 63, 67, 68, 70, 71, 72, 74, 75, 77, 79, 80, 82, 83, 85, 86, 87, 89, 92, 93, 94, 98], "specul": [0, 1, 3, 27, 30, 31, 32, 45, 62, 66, 67, 68, 71, 73, 80, 82, 93, 102], "speculative_config": [21, 27, 28, 56, 68], "speculative_decod": 93, "speculative_decoding_draft_tokens_extern": 82, "speculative_decoding_mod": [33, 68, 71], "speculative_model_dir": [32, 56, 68], "speculativedecod": 0, "speculativedecodingconfig": 0, "speculativedecodingfastlogitsinfo": 0, "speculativedecodingmetr": 0, "speculativedecodingmod": [68, 82, 93], "speculativedecodingmodul": 93, "speculativedecodingoutput": 1, "speed": [17, 23, 27, 28, 29, 30, 32, 33, 71, 72, 78, 93], "speedup": [21, 23, 25, 26, 27, 29, 31, 32], "spent": 0, "spirit": 30, "split": [1, 4, 5, 10, 17, 68, 71, 74, 75, 80, 89, 93], "split_input_id": 85, "split_prompt_by_imag": 85, "split_siz": 80, "split_size_or_sect": 80, "splittransposecpu": 1, "splittransposecpuinn": 1, "splitwis": 2, "spot": [30, 77], "sq": [26, 90, 93], "sqrt": [5, 80], "squar": [77, 80], "squared_relu": 80, "squeez": [1, 80, 85], "src": [1, 17, 80], "src_seq_len": 80, "srcdesc": 0, "srctype": 1, "srun": [17, 34, 52, 53, 54, 65, 92, 94], "ssd": 32, "ssh": 88, "sshd": 35, "ssid": 46, "ssm": 80, "ssm_state": 82, "stabil": [12, 27, 30], "stabl": [5, 18, 30, 33, 73, 77, 78, 80, 93], "stack": [18, 27, 32, 63, 80], "stackoverflow": 88, "stage": [0, 5, 7, 13, 28, 31, 32, 62, 72, 89, 93, 98], "stage_list": 87, "stai": [23, 26, 30, 74, 78], "stall": 30, "stand": 17, "standalon": 20, "standard": [13, 17, 19, 22, 30, 32, 72, 80], "starcod": [91, 93], "starcoder1": 90, "starcoder2": [90, 93], "starrickliu": 93, "start": [0, 3, 5, 7, 9, 21, 28, 30, 33, 35, 36, 37, 38, 39, 41, 42, 43, 54, 55, 57, 58, 59, 60, 63, 68, 69, 71, 72, 73, 74, 77, 79, 80, 82, 84, 85, 87, 88, 89, 93, 94], "start_dim": 80, "startup": 92, "stat": [0, 68, 93], "state": [0, 1, 3, 4, 5, 7, 8, 9, 13, 21, 27, 28, 30, 31, 33, 68, 71, 72, 73, 77, 79, 80, 86, 93, 104], "state_dtyp": 85, "state_or_ptr": 80, "state_s": 85, "statement": 67, "stateptr": 0, "states": 1, "static": [0, 1, 3, 12, 13, 29, 33, 68, 80, 81, 82, 85, 93], "static_batch": [68, 79], "static_cast": 90, "staticbatchingstat": 0, "statist": [0, 3, 13, 32, 34, 68, 71, 93], "statu": [30, 92], "std": [0, 1, 3, 30], "stddev": [34, 42, 43], "stdev": [21, 53, 70, 71, 72, 73], "stdit": 93, "stdout": [21, 53, 70, 71, 72, 73], "steadi": 72, "steady_clock": 0, "step": [0, 1, 5, 6, 7, 9, 13, 16, 17, 19, 20, 22, 27, 28, 36, 62, 65, 68, 69, 71, 72, 73, 80, 85, 92, 97, 98, 100, 103, 104], "still": [5, 18, 20, 21, 27, 28, 29, 30, 31, 69, 71, 73, 75, 80, 85, 89, 93], "stop": [0, 1, 3, 6, 7, 13, 30, 51, 68, 71, 77, 85, 86, 93, 100, 102], "stop_reason": [32, 68, 86, 93], "stop_token_id": [3, 68], "stop_words_data": 85, "stop_words_list": 85, "stopping_criteria": 85, "stoppingcriteria": [85, 93], "stoppingcriterialist": 85, "stoptokenid": [0, 3], "stopword": [0, 6], "stopwordslen": 1, "stopwordslist": 1, "stopwordsptr": 1, "storag": [0, 8, 10, 32, 67, 68], "store": [0, 1, 5, 8, 9, 10, 17, 23, 27, 28, 30, 32, 68, 71, 79, 80, 82, 89, 90, 94, 96, 98, 103], "stori": 55, "str": [16, 20, 48, 49, 51, 56, 60, 68, 80, 81, 82, 85], "straight": 63, "straightforward": 28, "strategi": [0, 11, 13, 21, 26, 28, 30, 31, 40, 62, 67, 68, 71, 76, 80, 82, 89, 93], "stream": [0, 1, 2, 3, 17, 29, 30, 33, 34, 40, 42, 43, 45, 51, 68, 70, 80, 85, 89, 92, 93, 94], "stream_interv": 68, "stream_ptr": 51, "streaming_llm": 93, "streamingllm": [33, 62, 93], "streamlin": [67, 71, 86], "streamptr": [0, 1, 3], "street": 55, "strenum": [68, 84], "strict": [27, 28, 30], "strict_bound": 80, "strict_dtyp": [80, 81], "stricter": 27, "strictli": 71, "stride": [1, 80, 81], "strike": [13, 30], "string": [0, 1, 3, 16, 46, 68, 71, 80, 85], "string_valu": 9, "string_view": 1, "stringptrmap": 1, "stringvec": 0, "strip": [33, 93], "strip_plan": 33, "strong": 30, "strongli": 75, "strongly_typ": [68, 93], "struct": [0, 1, 8], "structur": [0, 4, 7, 8, 13, 29, 68, 71, 80, 89, 93], "structural_tag": 68, "struggl": 55, "student": [47, 48, 50], "studi": [29, 73, 75, 76, 78], "studio": 88, "style": [5, 13, 27, 93], "sub": [16, 20, 30, 80], "sub_fil": 94, "subclass": [1, 20, 51, 96], "subcommad": 71, "subcommand": [72, 93], "subdirectori": [71, 94], "subgraph": [7, 80], "subject": [2, 22, 24, 25, 26, 80, 86, 95], "submiss": 71, "submit": [10, 68, 71], "submit_sync": 68, "submittransferrequest": 0, "submodul": [21, 32, 63, 96], "suboptim": 17, "subscript": 80, "subsequ": [9, 10, 13, 28, 63, 73, 87], "subset": [0, 3, 6, 17, 20, 28, 68, 71, 80, 102], "substanti": [9, 13, 27, 29, 31], "substitut": 88, "subsystem": 93, "subtract": 7, "succe": [89, 93], "succeed": 85, "success": [3, 23, 27, 72, 87], "successfulli": [13, 36, 75], "sudo": [21, 27, 65, 71], "suffer": [27, 30], "suffici": [74, 75], "suggest": [5, 26, 30, 51, 55, 75], "suit": [5, 30, 31, 71, 72], "suitabl": [30, 31, 88], "sum": [1, 7, 15, 80, 103], "sum_of_token": 80, "summar": [5, 13, 14, 15, 16, 24, 26, 30, 71, 72, 79, 89], "summari": [8, 13, 30, 62], "summat": 80, "sunjiabin17": 93, "super": [7, 15, 18, 20, 91, 92, 96, 104], "superchip": 91, "supplementari": 81, "suppli": [10, 19, 51], "support": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 16, 19, 20, 22, 23, 24, 25, 26, 27, 29, 30, 33, 34, 35, 40, 46, 52, 53, 54, 55, 62, 65, 66, 67, 68, 72, 73, 75, 77, 78, 79, 80, 81, 83, 86, 87, 88, 92, 93, 95, 96, 97, 98, 101, 102, 103, 104], "supports_backend": 68, "supportsinflightbatch": 1, "suppos": 96, "sure": [2, 20, 21, 28, 30, 32, 36, 63, 67, 71, 79, 80, 93], "surpass": 5, "surround": [5, 93], "swa": 8, "swap": [8, 30], "sweep": [17, 23, 31, 77, 94], "sweet": 77, "swept": 24, "swiftli": 30, "swiglu": [33, 80, 93], "switch": [4, 9, 11, 12, 23, 26, 27, 29, 31, 63, 79, 89, 93], "sxm": [23, 33, 73, 75, 76], "sy": 93, "symbol": 0, "sync": 85, "synchron": [1, 3, 17, 30, 68, 92, 93], "syncmessag": 0, "syntax": [80, 86], "synthet": [21, 34, 42, 43, 71, 72], "synthetic_128_128": 71, "synthetic_2048_2048": 73, "synthetic_2048_2048_1000": 73, "synthetic_lora_data": 71, "system": [8, 9, 17, 21, 23, 28, 29, 30, 32, 34, 37, 38, 46, 52, 53, 54, 57, 58, 62, 63, 65, 72, 74, 86, 87, 91, 93, 95, 100], "systemat": [27, 30, 31], "t": [0, 1, 5, 13, 17, 20, 27, 29, 30, 34, 35, 40, 51, 52, 53, 54, 56, 65, 68, 70, 71, 74, 77, 78, 80, 82, 85, 92], "t5": [5, 6, 90, 91, 93], "t_": 28, "t_2": 28, "t_5": 28, "tabl": [0, 6, 9, 23, 26, 33, 71, 72, 80, 81, 85, 91, 92, 93], "tackl": 29, "tactic": [29, 33], "tag": [0, 35, 63, 65, 68, 87, 88], "tailor": [26, 75, 78], "take": [0, 1, 2, 5, 6, 7, 9, 11, 16, 20, 28, 30, 31, 32, 55, 68, 69, 71, 73, 74, 77, 80, 81, 94, 103], "taken": [18, 22, 23, 30, 80], "talk": [30, 55], "tanh": [80, 81], "target": [0, 18, 21, 29, 30, 31, 33, 40, 51, 62, 63, 71, 78, 79, 93], "target_isl": 71, "target_osl": 71, "targetcach": 1, "targetpageid": 1, "targetprob": 1, "targettaskvalu": 1, "tarot": 55, "task": [0, 1, 9, 10, 13, 15, 16, 30, 48, 49, 51, 52, 53, 54, 68, 71, 81, 85, 90, 93, 100, 103], "task_id": [10, 71], "task_vocab_s": 81, "taskid": [0, 1], "taskidtyp": 1, "tasklayermoduleconfig": 1, "tasklayermoduleconfigbind": 1, "tasklayermoduleconfiglistptr": 1, "taskshost": 1, "taskvalu": 1, "taskvalueptr": 1, "taslid": 1, "tayef": 93, "tconstptr": 1, "tcp": 36, "team": [16, 20, 27, 28, 29, 30, 31, 36, 87, 91, 93], "tech": [28, 30, 31, 93], "technic": [8, 28, 29, 30, 62], "techniqu": [5, 7, 13, 17, 22, 27, 28, 29, 30, 31, 69, 74, 75, 76, 79, 90, 93], "technologi": [27, 32, 47, 48, 50, 51], "tekit_2025": 71, "tell": [34, 38, 55, 58, 78, 86], "temb": 81, "temp": 85, "temperatur": [0, 1, 6, 32, 34, 37, 38, 39, 40, 44, 47, 48, 49, 50, 51, 65, 68, 71, 73, 79, 85, 86, 93, 102], "templat": [0, 1, 17, 18, 87], "tempor": 85, "temporari": 2, "ten": [13, 26, 28, 30], "tend": 79, "tensor": [1, 6, 11, 16, 17, 18, 21, 22, 23, 24, 25, 27, 28, 29, 30, 32, 34, 50, 51, 62, 68, 71, 72, 75, 76, 78, 80, 81, 82, 85, 90, 92, 93, 94, 96, 98], "tensor_dict": 85, "tensor_input": 7, "tensor_parallel_s": [50, 52, 53, 54, 68, 73, 74, 75, 78, 79], "tensor_shap": 18, "tensorconstptr": 1, "tensorinfo": 85, "tensorloc": 80, "tensormap": 1, "tensorparallel": [0, 1, 6], "tensorptr": [0, 1], "tensorrt": [1, 3, 5, 6, 7, 8, 11, 14, 15, 22, 25, 27, 29, 33, 34, 37, 38, 39, 40, 41, 42, 43, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 64, 65, 66, 67, 70, 72, 75, 76, 78, 79, 80, 85, 87, 88, 90, 92, 94, 95, 96, 97, 98, 101, 103, 104], "tensorrt_llm": [0, 1, 3, 5, 6, 7, 10, 12, 14, 15, 17, 18, 20, 21, 32, 34, 35, 36, 40, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 63, 64, 65, 68, 71, 72, 73, 75, 78, 79, 80, 81, 82, 83, 84, 85, 86, 88, 92, 93, 95, 96, 97, 98, 101, 102, 103], "tensorrt_llm_gpt": 17, "tensorrt_llm_rouge1_threshold": 16, "tensorrtllm_backend": [10, 86, 93], "tensortrt": 63, "tep4": 31, "term": [17, 30, 31, 67, 79, 80, 86, 87], "termin": [0, 9, 36, 72, 86, 93], "test": [5, 26, 27, 28, 31, 34, 38, 58, 62, 63, 65, 71, 72, 73, 75, 76, 77, 78, 79, 91, 93, 94, 103], "test_gpt_ib_ptun": 87, "test_graph_rewrit": 7, "test_list": 87, "test_llm_openai_triton_1gpu": 87, "test_llm_qwen2audio_single_gpu": 87, "test_openai": 87, "test_qwen2audio": 87, "test_triton": 87, "test_trt_llm": [14, 15, 16], "texec": 0, "text": [0, 3, 5, 6, 9, 31, 33, 34, 38, 40, 44, 45, 50, 56, 58, 65, 68, 69, 71, 72, 73, 79, 85, 86, 91, 92, 93], "text_diff": 68, "text_hidden_s": 82, "text_to_token": 51, "textattack": 91, "textprompt": 68, "tg_group": 80, "tgt": [17, 80], "tgt_len": [80, 81], "tgt_seq_len": 80, "th": [1, 16, 28, 80], "than": [0, 1, 2, 3, 5, 6, 7, 9, 13, 17, 21, 22, 23, 24, 26, 27, 28, 29, 30, 31, 33, 63, 68, 69, 71, 72, 73, 74, 75, 77, 79, 80, 85, 89, 92, 93, 98], "thank": [28, 30, 93], "thecodewrangl": 93, "thei": [0, 1, 3, 5, 6, 10, 17, 18, 20, 27, 28, 29, 30, 63, 68, 71, 73, 75, 77, 78, 79, 80, 82, 87, 88, 90, 93], "them": [0, 3, 4, 7, 13, 14, 21, 27, 28, 29, 30, 31, 52, 53, 54, 68, 69, 70, 71, 74, 76, 77, 79, 80, 85, 89, 96], "themselv": 87, "theoret": [30, 89], "theori": 79, "therebi": [2, 79], "therefor": [6, 14, 20, 72, 80, 92, 102, 103], "thermal": 71, "theta": 80, "thi": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 20, 21, 22, 23, 24, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 40, 44, 46, 51, 52, 53, 54, 55, 56, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 85, 86, 87, 88, 89, 90, 92, 93, 94, 95, 96, 97, 98, 100, 102, 103, 104], "thin": 20, "thing": [6, 31, 36, 47, 48, 50, 77, 78], "think": [27, 28, 29, 76], "third": [3, 31, 93], "thorough": 30, "those": [3, 5, 6, 16, 17, 19, 21, 27, 28, 29, 30, 33, 34, 70, 72, 73, 78, 80, 81, 87, 90], "though": [20, 28, 30, 31, 77, 89], "thread": [0, 1, 5, 11, 30, 40, 67, 71, 85], "three": [3, 16, 26, 27, 29, 31, 79, 80, 90, 96, 97, 98], "threshold": [0, 27, 28, 68, 80, 85], "throttl": 71, "through": [0, 5, 6, 7, 11, 12, 13, 17, 18, 19, 21, 27, 30, 31, 32, 33, 34, 63, 69, 71, 73, 74, 75, 77, 78, 81, 86, 93, 94], "throughout": [73, 76], "throughput": [0, 3, 5, 22, 23, 24, 28, 30, 31, 32, 53, 62, 70, 75, 77, 78, 79, 93, 98, 100], "throw": [0, 1, 68], "thu": [9, 20, 21, 27, 29, 30, 63, 80, 88, 89], "thumb": [5, 74, 92], "ti": [5, 28], "tiiuae": 71, "tile": 29, "time": [0, 1, 2, 3, 5, 9, 10, 11, 13, 14, 17, 21, 24, 26, 27, 28, 29, 30, 31, 33, 47, 48, 49, 50, 55, 62, 63, 68, 69, 70, 71, 72, 73, 75, 76, 77, 79, 80, 85, 92, 93, 100, 103], "time_embed_dim": 81, "time_encod": 85, "time_point": 0, "timedelta": 68, "timedout": 0, "timelin": [16, 31], "timeout": [0, 30, 34, 40, 68, 93], "timepoint": 0, "timestamp": 0, "timestep": [81, 82], "timestepembed": 81, "timingmetr": 0, "tini": 55, "tinyllama": [31, 34, 37, 39, 42, 44, 46, 47, 48, 49, 50, 51, 55, 57, 59, 65, 67, 86], "tip": 62, "titl": [34, 46], "tle": 14, "tllm": 99, "tllm_checkpoint_16gpu_tp8_pp2": 74, "tllm_ckpt_dir": 15, "tllm_engine_dir": 15, "tllm_kei": [18, 81], "tllm_llmapi_build_cach": 93, "tllm_llmapi_enable_nvtx": 70, "tllm_log_level": 92, "tllm_nvtx_debug": 70, "tllm_override_layer_num": 93, "tllm_profile_record_gc": 70, "tllm_profile_start_stop": 70, "tllm_to_externel_key_dict": 18, "tllm_torch_profile_trac": 70, "tllm_trace_model_forward": 93, "tllm_weight": 18, "tllmruntim": [1, 6, 92], "tlntin": 93, "tmp": [10, 14, 53, 70, 71, 74], "tmp9so41y3r": 71, "tmpowsrb_f4": 71, "tmpxhdvasex": 71, "to_arrai": 80, "to_dict": [68, 82], "to_json_fil": 82, "to_layer_quant_config": 82, "to_legacy_set": 83, "to_str": [0, 1, 3], "to_trt": 82, "tobyt": 1, "todo": [1, 80], "togeth": [3, 5, 6, 10, 17, 19, 22, 27, 31, 32, 33, 85, 90, 93, 94], "toggl": 70, "toi": 77, "toitensor": 0, "tojsonstr": 0, "tok": [22, 24, 25, 31, 78], "token": [0, 1, 3, 4, 5, 6, 8, 9, 13, 17, 21, 22, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 42, 43, 46, 51, 53, 62, 68, 70, 71, 72, 73, 75, 76, 78, 80, 81, 85, 86, 89, 90, 93, 94, 96, 97, 98], "token_count": 51, "token_drop": 81, "token_end": 68, "token_id": [40, 68], "token_ids_diff": 68, "token_range_retention_config": 68, "token_start": 68, "token_type_id": [82, 85], "tokenend": 0, "tokenextraid": 1, "tokenextraidtyp": 1, "tokenid": 1, "tokenidtyp": [0, 1], "tokenization_utils_bas": 68, "tokenizer_dir": [15, 17, 86, 92], "tokenizer_image_token": 85, "tokenizer_max_seq_length": [68, 75, 82, 84], "tokenizer_mod": 68, "tokenizer_revis": 68, "tokenizer_str": [0, 3], "tokenizerbas": 68, "tokenizerstr": [0, 3], "tokenlogprob": 68, "tokenrangeretentionconfig": [0, 68], "tokenrangeretentionprior": 0, "tokens_per_block": [8, 9, 33, 85, 93, 103], "tokensperblock": [0, 1, 6], "tokensperstep": 1, "tokensprompt": 68, "tokenstart": 0, "tokyo": [34, 38, 58], "toler": [26, 30], "tomodulenam": 1, "tomoduletyp": 1, "tonylek": 93, "too": [3, 5, 21, 29, 30, 73, 77, 92], "took": 73, "tool": [2, 16, 21, 29, 30, 62, 71, 88, 93], "tool_cal": [32, 86], "toolkit": [19, 20, 26, 27, 32, 65, 97], "top": [0, 5, 6, 13, 17, 19, 28, 29, 30, 31, 68, 80, 87, 93, 102], "top1": 27, "top_k": [6, 68, 85, 93, 102], "top_p": [6, 44, 47, 48, 49, 50, 51, 65, 68, 73, 79, 85, 86, 102], "top_p_decai": [68, 85], "top_p_min": [68, 85], "top_p_reset_id": [68, 85], "topenkoff": 93, "topic": [30, 78], "topk": [0, 1, 4, 6, 13, 27, 29, 80, 93], "topk_logit": 3, "topklastdim": 80, "topklogit": 3, "topkmedusahead": 1, "topktopp": [0, 6], "topmodelmixin": [20, 82], "topn": 27, "topologi": 30, "topp": [0, 1, 6, 93], "toppdecai": [0, 1, 6], "toppmin": [0, 1, 6, 68], "toppresetid": [0, 1, 6], "torch": [5, 18, 51, 63, 65, 68, 71, 80, 85, 92, 96, 99], "torch_compile_config": 68, "torchaudio": 65, "torchcompileconfig": 68, "torchllm": 68, "torchllmarg": 68, "torchvis": 65, "tostr": [0, 1], "total": [0, 1, 4, 5, 6, 13, 16, 18, 21, 28, 30, 31, 33, 34, 71, 72, 73, 74, 87, 89, 103], "total_lat": [22, 25], "total_token": [32, 86], "totalaccepteddrafttoken": 0, "totaldrafttoken": 0, "totalgentoken": 1, "totalnumpag": 1, "totensor": 0, "touch": [35, 96], "toward": [30, 100], "tp": [0, 2, 4, 6, 10, 17, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 34, 53, 71, 72, 73, 80, 93], "tp1": [22, 23, 24], "tp2": [31, 71], "tp4": 27, "tp4ep2": 27, "tp8": [24, 27, 29], "tp8ep2": 27, "tp_1_pp_1": 71, "tp_dim": [18, 81], "tp_group": [80, 81], "tp_rank": [18, 80, 81], "tp_size": [4, 10, 16, 17, 18, 20, 32, 34, 41, 52, 54, 71, 72, 74, 80, 81, 84, 93], "tp_split_dim": 81, "tpot": [25, 31, 72], "tprank": 1, "tpsize": 1, "tqdm": [18, 68, 93], "trace": [20, 30, 33, 34, 70, 92], "track": [5, 8, 30, 68, 80, 88], "trade": [9, 29], "tradeoff": [26, 27, 28, 75], "tradit": 0, "traffic": [30, 31], "train": [13, 15, 16, 17, 19, 20, 23, 26, 28, 71, 80, 92, 96], "trait": 93, "transa": 80, "transb": 80, "transceiv": [0, 68], "transfer": [0, 2, 17, 29, 30, 31, 68, 93], "transfer_mod": 68, "transferdesc": 0, "transfermod": 0, "transferop": 0, "transferrequest": 0, "transferstatu": 0, "transform": [0, 4, 5, 13, 15, 16, 17, 18, 33, 34, 40, 51, 68, 82, 86, 89, 91, 92, 93, 96, 97, 103], "translat": [79, 88, 93], "transmiss": [2, 11, 31], "transmit": [2, 11], "transpar": 30, "transpos": [1, 16, 80], "transposit": 80, "travers": 17, "treat": [5, 27, 80], "tree": [0, 64, 71, 85, 86, 92, 103], "tri": [29, 104], "tricki": 82, "trigger": [5, 7, 17, 30, 33, 40, 62, 67, 68], "trigger_completion_at_end": 80, "trim": 1, "trimpool": 1, "triton": [9, 10, 13, 17, 19, 62, 69, 87, 93], "triton_serv": 87, "tritonserv": 93, "trivial": 17, "troubleshoot": [62, 93], "trt": [0, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 17, 18, 23, 35, 71, 77, 80, 82, 84, 85, 89, 92, 93, 98], "trt_ckpt": [10, 14, 16, 92], "trt_engin": [10, 14, 16, 92], "trt_llm_data": 88, "trt_llm_disable_load_weights_in_parallel": 32, "trt_root": 21, "trt_tensor": [17, 80], "trtdatatyp": 1, "trtgptmodel": 89, "trtgptmodeloptionalparam": 93, "trtgptmodelv1": 93, "trtllm": [9, 10, 14, 15, 16, 17, 20, 21, 28, 30, 32, 37, 38, 39, 40, 41, 42, 43, 45, 52, 57, 58, 59, 60, 62, 68, 71, 72, 75, 76, 77, 78, 88, 89, 92, 93, 94], "trtllm_dg_jit_use_nvcc": 21, "trtllm_disable_kv_cache_transfer_overlap": 2, "trtllm_disable_unified_convert": 18, "trtllm_enable_kvcache_receive_parallel": 2, "trtllm_enable_mmha_multi_block_debug": 71, "trtllm_enable_pdl": [21, 27, 28, 32, 71], "trtllm_force_xqa": 5, "trtllm_kvcache_send_max_concurrency_num": 2, "trtllm_kvcache_transfer_buffer_s": 2, "trtllm_kvcache_transfer_use_async_buff": 2, "trtllm_mmha_blocks_per_sequ": 71, "trtllm_mmha_kernel_block_s": 71, "trtllm_model": 18, "trtllm_modules_to_hf_modul": [71, 85], "trtllm_parallel_cache_send": 2, "trtllm_pdl_overlap_ratio": 71, "trtllm_precompiled_loc": 63, "trtllm_prefetch_ratio": 71, "trtllm_request_kv_cache_concurr": 2, "trtllm_serv": 34, "trtllm_try_zcopy_for_kvcache_transf": 2, "trtllm_use_precompil": 63, "trtllm_use_ucx_kvcach": 2, "trtllmarg": 68, "trtllmattent": 98, "trtlmmdatatyp": 0, "true": [0, 1, 3, 6, 7, 9, 13, 16, 21, 27, 28, 29, 30, 32, 34, 40, 46, 49, 51, 53, 55, 56, 68, 70, 71, 72, 75, 78, 80, 81, 82, 83, 85, 89, 92, 93, 94, 100, 102], "true_output_valu": 80, "true_valu": 80, "truncat": [68, 93], "truncate_prompt_token": [68, 93], "trust": [29, 68], "trust_remote_cod": [32, 34, 68, 93], "try": [0, 1, 3, 15, 20, 30, 32, 55, 64, 67, 72, 75, 77, 78, 79, 86, 89, 92, 95, 101], "tsuji": 71, "ttensor": 1, "ttft": [31, 72, 75, 77, 78, 79, 93], "ttim": 93, "ttl": 27, "tunabl": 76, "tune": [0, 2, 3, 13, 23, 26, 27, 29, 30, 31, 33, 62, 68, 71, 72, 75, 78, 81, 82, 85, 86, 89, 93], "tuner": 0, "tupl": [0, 1, 80, 81, 85, 104], "turn": [5, 6, 9, 13, 29, 31, 63, 75, 85, 89, 93], "turnaround": 87, "tushar": 93, "tweak": 79, "twice": 17, "two": [0, 3, 4, 5, 6, 7, 9, 10, 11, 13, 14, 16, 17, 20, 23, 27, 28, 29, 30, 31, 33, 34, 38, 58, 63, 67, 71, 73, 75, 77, 79, 80, 81, 83, 86, 87, 93, 97, 99, 102, 103, 104], "twofold": 13, "twoshot": [11, 68, 80], "txt": [20, 21, 53, 70, 71, 73, 86, 87, 93], "type": [1, 2, 3, 5, 6, 7, 10, 16, 17, 23, 26, 29, 31, 32, 33, 34, 37, 38, 39, 42, 43, 46, 51, 56, 58, 68, 71, 75, 78, 80, 82, 84, 85, 86, 87, 90, 91, 92, 93, 96, 97, 98, 103], "typedef": [0, 1], "typenam": [0, 1, 17], "typetrait": 0, "typic": [0, 2, 7, 15, 17, 20, 26, 28, 29, 30, 31, 34, 67, 74, 75, 78, 79, 83, 85, 89, 93, 96], "typo": 93, "u": [1, 7, 29, 30, 31, 35, 47, 48, 49, 50, 71, 72, 93], "ub": [11, 68, 80], "ub_oneshot": 71, "ub_tp_siz": 71, "ubuntu": [65, 93, 95], "uc_handl": 1, "uc_ptr": 1, "uc_va": 1, "ucx": [2, 31, 93], "ucx_cuda_copy_async_mem_typ": 2, "ucx_cuda_copy_dmabuf": 2, "ucx_info": 2, "ucx_memtype_cach": 2, "ucx_rndv_frag_mem_typ": 2, "ucx_rndv_pipeline_error_handl": 2, "uid": [0, 85, 88], "uint16_t": 0, "uint32": 1, "uint32_t": [0, 1, 80], "uint64": [1, 9], "uint64_t": [0, 1], "uint8": 1, "uint8_t": [0, 1], "uintptr_t": [0, 1], "uk": 29, "uk_bgemm": 27, "ulimit": [32, 63, 92], "ultim": 74, "ulyss": 93, "unabl": [65, 77], "unaccept": 75, "unari": 80, "unaryoper": 80, "unbind": 80, "uncas": 91, "uncertainti": 13, "unchang": [13, 30, 78, 80, 87], "uncom": 88, "uncommon": 17, "undefin": 80, "under": [0, 26, 31, 33, 63, 67, 68, 71, 72, 87, 92, 93], "underli": [0, 1, 7, 13, 30, 31], "underlying_type_t": 1, "underlyingtyp": [0, 1], "underscor": 75, "understand": [30, 62, 63, 70, 87], "understood": [68, 77], "underutil": 13, "underwai": 31, "uneven": 93, "unevenli": 27, "unexpect": [92, 93], "unfinish": 0, "unfus": 80, "unfuse_qkv_project": 82, "ungath": 1, "unguid": 46, "unif": 93, "unifi": [16, 20, 26, 93], "uniform": [71, 72, 80], "uniniti": 98, "union": [68, 80], "uniqu": [0, 5, 6, 8, 10, 13, 16, 33, 68, 71], "unique_ptr": [0, 1], "uniqueconstptr": 1, "uniqueptr": 1, "uniquetoken": 1, "unit": [1, 8, 18, 29, 32, 62, 63, 71, 73, 79, 86], "unittest": 87, "univers": [47, 48, 50], "unless": [0, 40, 68, 74, 78, 79], "unlik": [9, 13, 28], "unlock": [30, 69], "unnecessari": [7, 93, 96, 104], "unneed": [5, 27], "unordered_map": [0, 1, 3], "unpatchifi": 82, "unschedul": 77, "unset": [30, 79], "unsign": 1, "unspecifi": [33, 34, 80], "unsqueez": [1, 80], "unstabl": 20, "unsupport": [87, 93], "untest": 99, "until": [0, 1, 3, 6, 9, 13, 30], "untouch": 80, "unus": [0, 71], "up": [0, 5, 6, 10, 13, 21, 23, 24, 27, 28, 29, 30, 31, 32, 33, 46, 51, 68, 71, 77, 78, 86, 93, 94, 103], "up_proj": 18, "upcast": 80, "upcast_attent": 81, "upcast_softmax": 81, "upcom": [26, 103], "updat": [0, 8, 13, 17, 18, 20, 21, 24, 28, 29, 30, 32, 33, 35, 63, 68, 80, 85, 92, 100, 103], "update_from_dict": 68, "update_from_model_config": 68, "update_key_map": 18, "update_kv_cache_typ": 68, "update_output_ids_by_offset": 85, "update_resourc": [97, 103], "update_strategi": 80, "updatenumreturnbeam": 0, "updatespositionid": 1, "upgrad": [65, 86], "uplift": [75, 77, 78], "upon": [13, 32, 72, 78, 92, 93], "upper": [56, 71, 80, 89], "uq_qr_gemm": 27, "url": [31, 34, 38, 42, 43, 58, 63, 65, 93], "us": [0, 1, 2, 3, 4, 5, 6, 8, 9, 11, 12, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 33, 34, 35, 36, 40, 44, 45, 46, 49, 52, 53, 54, 55, 62, 63, 64, 65, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 80, 81, 82, 83, 85, 86, 87, 90, 92, 93, 94, 95, 96, 97, 98, 102, 103, 104], "usabl": 95, "usag": [0, 2, 5, 7, 8, 17, 20, 22, 25, 29, 31, 32, 33, 34, 44, 62, 64, 67, 68, 71, 78, 79, 80, 86, 93, 94, 98], "use_beam_hyp": 85, "use_beam_search": [68, 93], "use_cach": [80, 81, 82], "use_context_fmha_for_gener": 93, "use_custom_all_reduc": 93, "use_diff_of_squar": 80, "use_dynamic_tre": 68, "use_embedding_shar": 93, "use_fp32_acc": 80, "use_fp8": 81, "use_fp8_context_fmha": [5, 33, 71, 93], "use_fused_mlp": [33, 71, 93], "use_gemm_allreduce_plugin": 85, "use_gpt_attention_plugin": 85, "use_gpu_direct_storag": 85, "use_implicit_relative_attent": 81, "use_kv_cach": [81, 85], "use_logn_sc": 81, "use_lora": 82, "use_lora_plugin": 85, "use_mamba_conv1d_plugin": 85, "use_meta_recip": 68, "use_modelopt_quant": 20, "use_mrop": 68, "use_mtp_vanilla": 68, "use_one_more_block": 85, "use_paged_context_fmha": [5, 9, 33, 71, 75, 78], "use_parallel_embed": [16, 17, 82], "use_preload": 82, "use_prompt_tun": [82, 93], "use_py_sess": 92, "use_refit": 68, "use_relaxed_acceptance_for_think": [27, 28, 56, 68], "use_runtime_default": 85, "use_safetensors_load": 82, "use_strip_plan": 68, "use_tqdm": 68, "use_uvm": 68, "use_variable_beam_width_search": 85, "usebantoken": 0, "usebanword": 0, "usecrossattent": 1, "usedefaultvalu": 1, "usednumblock": 0, "usedraftlogit": 1, "usedraftlogitshost": 1, "usedynamictre": 0, "usedynamictreehost": 1, "useexpliciteosstop": 0, "usefrequencypenalti": 0, "usegemmallreduceplugin": 1, "usegptattentionplugin": [1, 6], "usegpudirectstorag": 0, "uselanguageadapt": 1, "useloraplugin": 1, "usemambaconv1dplugin": 1, "usemaxlengthstop": 0, "useminlen": 0, "useminlength": 0, "useminp": 0, "usemrop": 1, "usenorepeatngrams": 0, "useoccurrencepenalti": 0, "usepackedinput": 1, "usepagedst": 1, "usepenalti": 0, "usepositionembed": 1, "usepresencepenalti": 0, "useprogthread": 0, "useprompttun": 1, "user": [0, 2, 3, 5, 6, 7, 9, 10, 11, 12, 17, 18, 19, 20, 21, 25, 26, 27, 28, 29, 30, 31, 32, 34, 35, 37, 38, 46, 57, 58, 63, 67, 68, 70, 71, 72, 77, 78, 79, 80, 82, 86, 88, 89, 90, 92, 93, 94], "user_buff": [33, 75], "user_provid": [68, 82], "userandomacceptancethreshold": 1, "userbuff": [68, 93], "userepetitionpenalti": 0, "usernam": 32, "userprovideddecodingconfig": 68, "userwarn": 65, "useshapeinfer": 1, "usespecdecod": 1, "usestopword": 0, "usetemp": 0, "usetemperatur": 0, "usetokentypeembed": 1, "useuvm": 0, "usevariablebeamwidthsearch": 0, "using_oss_cutlass_": 12, "using_oss_cutlass_low_latency_gemm": 12, "using_oss_cutlass_moe_gemm": 12, "usr": [16, 21, 34, 37, 38, 39, 41, 42, 43, 65, 71], "usual": [17, 20, 28, 65, 68, 72, 73, 78, 80, 103], "util": [0, 1, 2, 5, 6, 13, 17, 21, 22, 27, 29, 30, 31, 32, 33, 44, 65, 69, 70, 71, 75, 78, 79, 89, 93, 98, 100], "uv": 29, "uv_gemm": 27, "uvm": [0, 1, 68], "v": [1, 2, 5, 6, 10, 21, 22, 23, 26, 27, 29, 32, 62, 80, 85, 88, 90, 91, 92, 96, 98], "v0": [10, 22, 23, 24, 25, 69, 71, 72, 91, 93, 100], "v1": [31, 32, 34, 37, 38, 39, 42, 44, 46, 47, 48, 49, 50, 51, 55, 57, 58, 59, 60, 65, 67, 86, 91, 93], "v10": 93, "v100": 93, "v12": 93, "v2": [26, 29, 90, 93], "v3": [28, 30, 34, 70, 90, 91, 93], "v9": 24, "v_dim": 80, "v_head_dim": [80, 81], "v_proj": [18, 71, 96], "valid": [0, 1, 3, 13, 28, 30, 68, 72, 80, 85], "validate_and_init_token": 68, "validate_auto_parallel": 68, "validate_build_config_remain": 68, "validate_build_config_with_runtime_param": 68, "validate_cuda_graph_config": 68, "validate_cuda_graph_max_batch_s": 68, "validate_enable_build_cach": 68, "validate_lora_config_consist": 68, "validate_model_format_misc": 68, "validate_moe_load_balanc": 68, "validate_parallel_config": 68, "validate_positive_valu": 68, "validate_speculative_config": 68, "validate_stream_interv": 68, "validatevec": 1, "validationerror": 68, "validmpiconfig": 1, "valu": [0, 1, 2, 5, 6, 8, 9, 10, 11, 14, 16, 17, 18, 21, 22, 23, 28, 29, 31, 33, 34, 40, 51, 68, 71, 73, 75, 77, 79, 80, 82, 83, 84, 85, 87, 89, 90, 92, 93, 98, 103, 104], "valuabl": [27, 30, 31], "value_typ": 0, "valueerror": 56, "valuestatu": 1, "vanilla": [5, 98], "vanillaattent": 98, "var": 80, "vari": [24, 30, 31, 32, 77, 78, 103], "variabl": [0, 1, 6, 8, 18, 21, 24, 27, 30, 31, 52, 53, 54, 62, 65, 68, 70, 71, 88, 92, 93, 94], "variabledraftlength": 1, "varianc": [29, 75, 77, 78, 80], "variant": [0, 3, 5, 20, 22, 28, 29, 80, 86, 93, 98], "varieti": [71, 73, 93], "variou": [5, 13, 19, 30, 31, 63, 67, 71, 75, 77, 88, 93, 94], "varnam": 1, "vartyp": 1, "vboost": [21, 27, 71], "vbw": 93, "ve": [27, 55], "vec": [0, 1], "vec2": 80, "veclogprob": 0, "vectoken": 0, "vectokenextraid": [0, 1], "vector": [0, 1, 3, 5, 6, 8, 10, 29, 80], "vecuniquetoken": [0, 1], "vehicl": 32, "verbatim": 82, "verbos": [33, 34, 71], "veri": [5, 16, 17, 19, 26, 28, 30, 32, 73, 74, 75, 93], "verif": [0, 13, 28, 68], "verifi": [13, 28, 32, 62, 78, 80, 87, 93], "verificationsets": 0, "versa": [9, 29], "version": [0, 1, 2, 5, 6, 16, 18, 20, 21, 27, 29, 30, 34, 40, 63, 64, 65, 71, 73, 80, 86, 88, 92, 93, 95], "vertic": 80, "vertical_strid": 81, "vgqa": 8, "via": [0, 11, 12, 13, 27, 30, 31, 52, 53, 54, 55, 62, 63, 71, 75, 76, 78, 79, 80, 86, 87, 93, 94, 95], "vice": [9, 29], "vicuna": 13, "video": [34, 38, 58, 71, 85, 91, 93], "video_grid_thw": 85, "video_path": 85, "video_preprocess": 85, "video_url": [34, 38, 58], "view": [1, 28, 30, 32, 80, 85], "vila": [34, 38, 58, 90, 91, 93], "vinyl": 71, "violat": 93, "virtual": [0, 1, 81], "vision": [85, 90, 91, 93], "vision_grid_thw": 85, "vision_length": 80, "vision_model_typ": 82, "vision_start": 80, "vision_token_mask": 81, "visit": [13, 27, 93], "visual": [32, 77, 88, 93], "visual_engine_dir": 85, "visual_featur": 85, "visualize_network": [33, 68, 93], "vit": 93, "vital": [7, 26], "vl": [34, 38, 43, 58, 71, 91, 93], "vlm": [91, 93], "vocab": [80, 85], "vocab_embed": [15, 18], "vocab_s": [0, 16, 18, 68, 81, 82, 85, 96], "vocab_size_pad": 85, "vocabs": [1, 6], "vocabsizepad": [0, 1], "vocabulari": [0, 1, 6, 9, 13, 72, 81, 85], "void": [0, 1, 3, 17], "volta": 93, "volum": [1, 11, 62, 63, 71], "volumenonneg": 1, "vonjackustc": 93, "vswa": 8, "vulner": 93, "vultureprim": 93, "w": [1, 21, 25, 27, 29, 32, 34, 80, 82, 90, 91, 93], "w1": 80, "w4a": [90, 93], "w4a16": [16, 26, 62, 68, 82], "w4a16_awq": [16, 20, 40, 68], "w4a16_gptq": [16, 68], "w4a8": [26, 93], "w4a8_awq": [16, 20, 68], "w4a8_mxfp4_fp8": 68, "w4a8_qserve_per_channel": 68, "w4a8_qserve_per_group": 68, "w4aint8": 93, "w8a": 90, "w8a16": [16, 26, 62, 68, 82], "w8a16_gptq": 68, "w8a8": [23, 26, 62], "w8a8_sq_per_channel": [16, 68], "w8a8_sq_per_channel_per_tensor_plugin": [68, 82], "w8a8_sq_per_channel_per_token_plugin": [68, 82], "w8a8_sq_per_tensor_per_token_plugin": [68, 82], "w8a8_sq_per_tensor_plugin": [68, 82], "wa": [0, 1, 3, 5, 6, 16, 28, 29, 30, 64, 65, 67, 71, 72, 73, 75, 77, 78, 79, 81, 86, 90, 92, 93, 96, 104], "wai": [2, 5, 6, 7, 11, 19, 27, 28, 29, 30, 31, 50, 51, 64, 67, 69, 71, 73, 75, 80, 86, 89, 93], "wait": [0, 1, 3, 20, 29, 30, 40, 68, 69, 71, 80, 94, 100], "waiv": 62, "walk": [32, 34, 38, 55, 58, 73, 74, 75], "wang1120": 93, "wangkuiyi": 93, "want": [5, 13, 20, 27, 28, 30, 32, 36, 63, 65, 70, 71, 75, 77, 79, 80, 92, 93, 96], "war": 1, "warm": 103, "warmup": [21, 30, 70, 71, 73, 93, 98, 103], "warn": [5, 33, 34, 51, 68, 71, 72, 89], "warp": [11, 93], "wast": [29, 87], "watch": 78, "wdkv": 27, "wdq": 27, "we": [1, 2, 4, 6, 7, 10, 11, 12, 13, 14, 16, 20, 21, 25, 26, 27, 28, 29, 30, 31, 32, 34, 35, 36, 47, 48, 50, 55, 63, 65, 70, 71, 72, 73, 74, 75, 77, 78, 80, 85, 86, 92, 93, 96], "web": [19, 36], "weig": 80, "weight": [0, 1, 4, 10, 20, 22, 23, 26, 27, 28, 30, 32, 33, 34, 50, 62, 68, 69, 72, 73, 74, 75, 80, 81, 82, 85, 86, 93], "weight_index": 80, "weight_load": 81, "weight_only_groupwise_quant_matmul": 90, "weight_only_precis": 93, "weight_spars": [33, 68], "weight_stream": [14, 33, 68], "weightonlygroupwisequantmatmulplugin": 90, "weights_dict": 20, "weights_scaling_factor": [16, 18], "weightsinpoint": 1, "weightsoutpoint": 1, "welcom": 30, "well": [2, 5, 6, 17, 19, 23, 30, 40, 70, 77, 78, 90, 91, 102], "were": [0, 1, 12, 13, 16, 20, 22, 26, 29, 31, 72, 74, 77, 93], "weren": 65, "wget": 92, "what": [2, 3, 29, 30, 34, 38, 55, 56, 58, 62, 63, 68, 70, 71, 73, 75, 77, 78, 87], "whatev": 1, "wheel": [63, 65, 86, 93], "when": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11, 13, 17, 18, 20, 21, 25, 26, 28, 29, 30, 31, 32, 33, 35, 40, 51, 62, 63, 65, 68, 70, 71, 73, 75, 77, 78, 79, 80, 81, 82, 85, 86, 87, 88, 89, 90, 92, 93, 96, 98, 102, 103], "whenev": 1, "where": [0, 1, 2, 5, 6, 8, 9, 11, 12, 13, 16, 17, 22, 26, 27, 28, 29, 30, 31, 34, 37, 39, 40, 55, 57, 59, 68, 71, 72, 75, 77, 79, 80, 85, 86, 90, 93, 104], "wherea": [0, 16, 31, 77], "whether": [0, 1, 2, 3, 5, 10, 30, 31, 33, 68, 74, 75, 78, 80, 81, 85, 97, 98], "which": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 13, 16, 17, 18, 20, 22, 26, 27, 28, 29, 30, 31, 32, 33, 34, 51, 63, 65, 67, 68, 70, 71, 73, 75, 77, 78, 79, 80, 82, 83, 85, 86, 87, 88, 89, 90, 93, 94, 97, 98, 101, 102, 104], "while": [0, 1, 4, 7, 8, 9, 11, 12, 13, 17, 20, 21, 22, 23, 25, 26, 27, 28, 29, 30, 31, 32, 65, 67, 69, 71, 73, 74, 75, 76, 77, 78, 79, 80, 87, 89, 90, 93, 98], "whisper": [90, 91, 93], "whisperencod": 82, "whl": [21, 63, 65], "who": [28, 67], "whole": [1, 68, 69, 80], "whose": [2, 9, 16, 27, 30, 31, 81, 87], "why": [0, 2, 17, 29, 32, 68, 75, 77, 78, 80, 87, 89], "wide": [0, 4, 28, 32, 68, 73], "width": [0, 1, 5, 6, 43, 68, 81, 85, 89, 93], "wildcard": 87, "win": 68, "window": [0, 1, 8, 13, 33, 62, 68, 71, 80, 85, 93, 99], "window_s": 5, "windows": 0, "wip": [27, 99], "wireless": 46, "wirelessaccesspoint": 46, "wise": [7, 30, 68, 80, 93], "wish": 9, "with_ssh": 35, "within": [2, 5, 8, 11, 13, 17, 29, 30, 68, 71, 74, 75, 77, 78, 80, 86, 94, 103], "without": [0, 1, 3, 5, 11, 13, 17, 18, 21, 26, 27, 30, 31, 33, 40, 51, 69, 71, 75, 78, 80, 82, 87, 93, 96, 98, 100], "wkr": 27, "wo": [18, 27, 93], "wo_gemm": 27, "won": [65, 74], "word": [0, 3, 5, 6, 68, 80, 85, 93, 102], "word_dict": 85, "word_embed": 18, "word_embeddings_layernorm": 18, "work": [5, 6, 7, 8, 11, 13, 17, 20, 21, 30, 40, 52, 53, 54, 56, 63, 64, 65, 69, 72, 76, 80, 85, 86, 90, 92, 93, 94, 96], "work_dir": 94, "workaround": [18, 21, 93], "workdir": [34, 52, 53, 54, 63], "worker": [17, 31, 33, 34, 68, 71, 89, 93, 94], "workerexecutablepath": 0, "workflow": [5, 6, 15, 16, 21, 28, 30, 31, 40, 62, 67, 72, 73, 75, 76, 80, 86, 92, 93], "workload": [4, 11, 17, 29, 30, 31, 32, 33, 70, 71, 73, 75, 76, 77, 78], "workspac": [1, 30, 33, 34, 68, 71, 80, 88, 89, 93], "workstat": 23, "world": [0, 7, 21, 28, 30, 33, 52, 53, 54, 69, 71, 73, 74, 75, 80], "world_config": 85, "world_siz": [16, 20, 80, 93], "worldconfig": [0, 6, 85], "worldsiz": 1, "wors": [13, 33, 75], "worst": [30, 77, 78], "worth": [5, 8, 75, 78], "would": [0, 7, 13, 28, 30, 71, 73, 75, 77, 79, 80, 96], "wpa2": 46, "wqr": 27, "wrap": [0, 1, 17, 33, 67, 73, 80, 83, 85, 93], "wrapped_properti": 68, "wrapper": [1, 7, 20, 30, 98], "write": [0, 1, 9, 18, 27, 30, 33, 62, 80, 92], "written": [17, 71, 80], "wrong": [13, 93], "wsl": 93, "wuk": 27, "wuq": 27, "wuv": 27, "www": 93, "x": [0, 1, 3, 6, 10, 14, 30, 34, 63, 64, 71, 80, 81, 82, 86, 90, 93], "x86": 9, "x86_64": 91, "xcomposer2": 93, "xgrammar": [0, 3, 46, 68, 93], "xl": 93, "xml": 3, "xor": 80, "xqa": 93, "xxx": [18, 20, 92], "xxx_plugin": 83, "xy": 80, "y": [2, 3, 21, 25, 30, 35, 63, 64, 65, 71, 80, 82, 86, 90], "y_bia": 80, "yaml": [30, 31, 32, 34, 71, 72, 87, 94], "yarn": 80, "ye": [2, 80, 89, 99], "yeah": 55, "yelp": 91, "yen": 71, "yet": [0, 6, 20, 21, 23, 27, 30, 64, 80, 86, 102, 104], "yield": [9, 29, 40, 75, 77], "yiyixu": [34, 38, 58], "yml": [21, 28, 34, 41, 71, 72, 87, 88], "york": [34, 37, 39, 57, 59, 86], "you": [3, 4, 5, 6, 7, 9, 10, 12, 13, 16, 17, 19, 20, 21, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 40, 46, 52, 53, 54, 55, 56, 57, 58, 62, 63, 64, 65, 67, 68, 71, 72, 74, 75, 76, 77, 78, 79, 80, 85, 86, 87, 89, 92, 93, 94, 95, 96, 98, 101], "your": [9, 10, 11, 13, 19, 20, 21, 26, 28, 30, 33, 35, 36, 40, 55, 63, 65, 67, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 86, 87, 92, 96, 98, 103], "your_data_path": [21, 28], "your_dockerhub_usernam": [35, 36], "your_model_dir": 28, "your_model_path": [21, 30], "your_public_kei": 36, "your_work_path": 21, "yourself": 101, "yuhuili": 56, "yyi": 92, "z": [63, 64, 80, 86], "zars19": 93, "zero": [0, 1, 3, 18, 67, 68, 80, 81, 90, 92, 100], "zero_is_placehold": 80, "zjli2013": 93, "zoo": [51, 93], "zoom": 30, "\u7f8e\u56fd\u7684\u9996\u90fd\u5728\u54ea\u91cc": 60}, "titles": ["Executor", "Runtime", "Disaggregated-Service (Experimental)", "Executor API", "Expert Parallelism in TensorRT-LLM", "Multi-Head, Multi-Query, and Group-Query Attention", "C++ GPT Runtime", "Graph Rewriting Module", "KV Cache Management: Pools, Blocks, and Events", "KV cache reuse", "Run gpt-2b + LoRA using Executor / cpp runtime", "Low-Precision-AllReduce", "<no title>", "Speculative Sampling", "Running With Weight Streaming to Reduce GPU Memory Consumption", "Adding a Model", "TensorRT-LLM Checkpoint", "Model Definition", "TensorRT-LLM Model Weights Loader", "TensorRT-LLM Architecture", "TensorRT-LLM Build Workflow", "How to get best performance on DeepSeek-R1 in TensorRT-LLM", "Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100", "H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token", "H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM", "New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget", "Speed up inference with SOTA quantization techniques in TRT-LLM", "Pushing Latency Boundaries: Optimizing DeepSeek-R1 Performance on NVIDIA B200 GPUs", "DeepSeek R1 MTP Implementation and Optimization", "Optimizing DeepSeek R1 Throughput on NVIDIA Blackwell GPUs: A Deep Dive for Developers", "Scaling Expert Parallelism in TensorRT-LLM (Part 1: Design and Implementation of Large-scale EP)", "Disaggregated Serving in TensorRT-LLM", "How to launch Llama4 Maverick + Eagle3 TensorRT-LLM server", "trtllm-build", "trtllm-serve", "Build the TensorRT-LLM Docker Image", "Develop TensorRT-LLM on Runpod", "Curl Chat Client", "Curl Chat Client For Multimodal", "Curl Completion Client", "LLM Common Customizations", "Deepseek R1 Reasoning Parser", "Genai Perf Client", "Genai Perf Client For Multimodal", "LLM Examples Introduction", "LLM Examples", "Generate text with guided decoding", "Generate text", "Generate text asynchronously", "Generate text in streaming", "Distributed LLM Generation", "Control generated text using logits processor", "Run LLM-API with pytorch backend on Slurm", "Run trtllm-bench with pytorch backend on Slurm", "Run trtllm-serve with pytorch backend on Slurm", "Generate text with multiple LoRA adapters", "Speculative Decoding", "OpenAI Chat Client", "OpenAI Chat Client for Multimodal", "OpenAI Completion Client", "Openai Completion Client For Lora", "Online Serving Examples", "Welcome to TensorRT-LLM\u2019s Documentation!", "Building from Source Code on Linux", "Pre-built release container images on NGC", "Installing on Linux via pip", "Key Features", "LLM API Introduction", "API Reference", "Overview", "Performance Analysis", "TensorRT-LLM Benchmarking", "Overview", "Benchmarking Default Performance", "Deciding Model Sharding Strategy", "FP8 Quantization", "Performance Tuning Guide", "Tuning Max Batch Size and Max Num Tokens", "Useful Build-Time Flags", "Useful Runtime Options", "Functionals", "Layers", "Models", "Plugin", "Quantization", "Runtime", "Quick Start Guide", "Continuous Integration Overview", "Using Dev Containers", "Memory Usage of TensorRT-LLM", "Numerical Precision", "Support Matrix", "Troubleshooting", "Release Notes", "Disaggregated Inference Benchmark Scripts", "PyTorch Backend", "Adding a New Model in PyTorch Backend", "Architecture Ovewiew", "Attention", "Feature Combination Matrix", "Overlap Scheduler", "Quantization", "Sampling", "KV Cache Manager", "Scheduler"], "titleterms": {"": [5, 23, 26, 62], "0": 93, "000": [23, 24], "0528": 21, "1": [15, 17, 21, 30, 32, 63, 67, 72, 89, 93], "10": [23, 93], "100m": 23, "1024": 31, "11": 93, "12": [24, 93], "1200": 31, "13": 93, "13b": 24, "14": 93, "15": 93, "16": 93, "17": 93, "18": 93, "180b": 22, "19": 93, "2": [15, 21, 25, 30, 32, 63, 67, 89, 93], "256": 31, "2b": 10, "3": [15, 17, 21, 30, 31, 32, 71, 72, 89, 91], "4": [15, 21, 23, 32], "405b": [17, 72], "4096": 31, "4400": 31, "4x": 25, "5": [21, 32], "6": [21, 22, 32], "6x": 23, "7": [32, 93], "70b": [17, 22, 25, 71, 72], "7x": 22, "8": 93, "8192": 31, "8b": 72, "9": 93, "A": 29, "As": 3, "For": [38, 43, 60], "In": [3, 5, 69], "It": 100, "Not": [21, 89], "One": [27, 63], "The": [3, 30, 90], "To": 73, "With": [14, 69], "a100": [22, 23], "about": [13, 34, 69, 74], "absorb": 29, "accept": [27, 28], "access": 35, "account": 36, "accuraci": [11, 26, 28], "achiev": [23, 24, 28], "acknowledg": [27, 28, 29, 30, 31], "activ": [81, 89], "ad": [15, 96], "adapt": [55, 71], "addit": 3, "adp": 29, "advanc": [62, 63], "algorithm": 11, "alibi": 5, "allreduc": 11, "altern": 32, "an": 8, "analysi": 70, "announc": 93, "api": [3, 7, 14, 20, 34, 52, 67, 68, 73, 86, 93, 97], "arbitrari": 3, "architectur": [19, 27, 62, 97], "argument": 33, "artifact": 32, "asynchron": 48, "asyncio": 40, "attent": [5, 16, 27, 28, 29, 69, 77, 78, 79, 81, 98], "attentionbackend": 98, "attentionmetadata": 98, "auto": 33, "autoregress": 27, "avoid": [73, 87], "awq": [16, 22, 90], "b200": [21, 27], "backend": [27, 31, 52, 53, 54, 91, 95, 96, 98], "background": [27, 28], "balanc": [27, 30], "base": [28, 40], "baselin": 75, "basic": [28, 45], "batch": [3, 5, 69, 77], "beam": [3, 5], "befor": [71, 73], "begin": 73, "behavior": 71, "bench": [53, 70, 73], "benchmark": [21, 26, 34, 71, 72, 73, 94], "best": [21, 26, 87], "bf16": 90, "bia": 5, "bind": [3, 17, 63], "blackwel": [29, 90], "block": 8, "blockmanag": 8, "boost": 71, "boundari": 27, "budget": 25, "buffer": [5, 75, 89], "buffermanag": 1, "build": [16, 20, 21, 32, 33, 35, 36, 40, 63, 71, 73, 78], "built": 64, "c": [3, 6, 30, 63, 89], "cach": [5, 8, 9, 16, 21, 31, 75, 79, 89, 103], "cachecommun": 0, "can": [9, 69], "capac": 79, "case": 77, "cast": 81, "caveat": 71, "chang": [14, 77, 93], "chat": [34, 37, 38, 57, 58], "checkpoint": 16, "choos": 26, "chunk": [5, 21, 77, 79], "ci": 87, "class": 3, "classic": 7, "cli": [20, 73], "client": [37, 38, 39, 42, 43, 57, 58, 59, 60], "clock": [21, 71], "clone": 32, "close": [22, 25], "code": 63, "collect": [30, 70], "combin": [21, 99], "come": 26, "command": 72, "common": [1, 40, 69], "commun": [27, 30, 74], "compil": [17, 21, 63, 86], "complet": [34, 39, 59, 60], "compon": [6, 95], "compos": 88, "conclus": [75, 77, 78], "config": [16, 33], "configur": [3, 6, 10, 27, 30, 36, 40, 75, 78, 88, 96], "connect": 36, "consider": 11, "consumpt": 14, "contain": [21, 35, 63, 64, 86, 88], "content": [21, 27, 28, 29, 30, 76, 87, 96], "context": [3, 5, 21, 77, 78, 79], "contigu": 5, "continu": 87, "control": [3, 51], "conv": 81, "convers": [15, 20], "coordin": 70, "core": [30, 96], "cpp": 10, "creat": 36, "cross": 5, "cuda": 27, "cudaev": 1, "cudastream": 1, "curl": [37, 38, 39], "custom": [18, 40, 45, 103, 104], "cutlass": 27, "cyclic": 5, "data": 29, "dataset": [21, 30, 31, 71, 72, 73], "datatransceiverst": 0, "debug": [2, 70, 92], "decid": 74, "decod": [3, 13, 28, 33, 46, 56, 89, 97], "decoderst": 1, "decodinginput": 1, "decodingoutput": 1, "decor": 7, "deep": 29, "deepseek": [21, 27, 28, 29, 31, 41], "default": [21, 27, 71, 73], "definit": [17, 86, 87, 96], "dens": 27, "depend": 27, "deploi": 86, "dequant": 90, "descript": [70, 94], "design": 30, "detail": [10, 90], "dev": 88, "develop": [29, 36, 95], "diagram": 27, "differ": 3, "disabl": [40, 87], "disaggr_torch": 94, "disaggreg": [2, 31, 34, 94], "disaggregated_mpi_work": 34, "disaggserverutil": 0, "distribut": 50, "dive": 29, "do": 69, "docker": [32, 35, 36, 63, 88], "dockerhub": [35, 36], "document": [62, 93], "dora": 10, "download": [21, 32], "dq": 90, "draft": 13, "dynamo": 31, "e2": [30, 92], "eagl": [13, 28], "eagle3": [28, 32], "eaglebuff": 1, "eaglemodul": 1, "effect": 30, "embed": [5, 81], "enabl": [4, 9, 21, 35, 70, 75, 78], "endpoint": 34, "engin": [16, 17, 71, 73, 86, 97], "enhanc": 93, "environ": 2, "ep": [29, 30], "eplb": 30, "error": 92, "etp": 27, "evalu": [16, 28, 30], "event": 8, "everyth": 27, "exampl": [3, 10, 16, 17, 18, 44, 45, 61, 67, 70, 71, 87], "except": 89, "exchang": 31, "execut": 92, "executor": [0, 3, 10], "expand": 30, "expect": [9, 21], "experiment": 2, "expert": [4, 27, 29, 30], "explicitdrafttokensbuff": 1, "explor": 21, "extens": 30, "face": 67, "factor": [5, 16], "fail": 87, "falcon": 22, "faq": [2, 89], "fast": 87, "faster": 22, "featur": [21, 66, 70, 93, 95, 99], "file": [63, 94], "find": 87, "first": 23, "fix": 93, "flag": [78, 90], "flayerinfo": 7, "flight": [3, 5, 69], "flow": 71, "fmha": 5, "format": [10, 21], "fp16": [21, 90], "fp32": 90, "fp4": 72, "fp8": [5, 16, 21, 23, 69, 72, 75, 90], "fraction": 79, "free": 79, "from": [63, 67], "full": 63, "fulli": 18, "function": [7, 18, 80], "fuse_a_gemm": 27, "fusion": [17, 27, 75, 78], "futur": [27, 28, 29, 31, 40], "garbag": 70, "gate": 75, "gb200": 30, "gc": 70, "gemm": [27, 75, 78], "gen_yaml": 94, "genai": [42, 43], "gener": [2, 5, 30, 40, 46, 47, 48, 49, 50, 51, 55], "get": [21, 62], "gil": 70, "gpt": [6, 10], "gptdecod": 1, "gptdecoderbatch": 1, "gptjsonconfig": 1, "gptq": 90, "gpu": [14, 17, 21, 22, 27, 29, 30, 69, 71, 79, 89], "graph": [7, 27], "group": [5, 27], "gsm8k": 30, "guid": [3, 46, 76, 86, 95, 96], "h": [0, 1], "h100": [23, 24], "h200": [21, 22, 24, 25], "ha": 23, "hardwar": 91, "hbm": 24, "head": 5, "header": 63, "hierarchi": 8, "high": [7, 30], "hopper": [21, 90], "host": [9, 30], "how": [4, 9, 21, 27, 28, 29, 32, 71, 74, 77, 100], "hub": 67, "hug": 67, "i": [23, 74, 89], "ibuff": 1, "id": 10, "igptdecoderbatch": 1, "imag": [32, 35, 36, 63, 64, 86, 88], "implement": [15, 27, 28, 30, 98], "import": 5, "improv": 13, "increas": 25, "indic": 62, "infer": [3, 26, 28, 30, 31, 34, 69, 86, 89, 94], "inform": [7, 70, 86], "infrastructur": 93, "input": [5, 67], "instal": [21, 62, 65, 86, 92], "int4": [22, 90], "int8": [5, 90], "integr": 87, "interfac": [30, 103], "intern": 6, "introduct": [29, 30, 44, 67, 96, 103, 104], "ipcnvlsmemori": 1, "ipcutil": 1, "isl": [21, 31], "issu": [21, 89, 93, 95], "itensor": 1, "iter": 70, "jenkin": 87, "kei": [18, 27, 36, 66, 74, 93, 95], "kernel": [25, 27, 30], "knowledg": 76, "known": [63, 89, 93, 95], "kv": [5, 8, 9, 16, 21, 31, 75, 79, 89, 103], "kvcacheeventmanag": 8, "kvcachemanag": 97, "larg": 30, "latenc": [21, 25, 27, 71, 73, 75], "latest": [24, 69], "launch": [27, 32, 70], "layer": [27, 29, 81], "layernorm": 16, "layout": [18, 31], "level": [7, 27, 30, 97], "limit": [13, 63, 71, 93], "linear": 81, "link": 63, "linux": [63, 65], "llama": [17, 22, 25, 71, 72, 75, 78], "llama2": 24, "llama4": 32, "llm": [4, 13, 16, 18, 19, 20, 21, 23, 24, 26, 28, 30, 31, 32, 35, 36, 40, 44, 45, 50, 52, 62, 63, 67, 69, 71, 73, 77, 86, 89, 91, 93], "load": [18, 30, 96], "loader": 18, "local": 67, "log": 32, "logic": 30, "logit": [3, 33, 51], "lookahead": 13, "lookaheadbuff": 1, "lookaheadmodul": 1, "lookup": 13, "lora": [10, 33, 55, 60, 71], "loracach": [1, 10], "loracachepagemanagerconfig": 1, "loramodul": 1, "low": [11, 71, 75], "machin": [30, 31], "make": 16, "manag": [7, 8, 71, 103], "map": [10, 71], "mark": 3, "marker": 70, "match": 17, "matrix": [90, 91, 99], "maverick": 32, "max": [21, 71, 77, 79], "maximum": 79, "measur": [31, 72], "medusa": [13, 71], "medusamodul": 1, "memori": [9, 14, 21, 24, 79, 89], "memorycount": 1, "merg": 87, "method": [7, 26], "methodologi": 31, "metric": 34, "min": 21, "miscellan": 30, "mix": 27, "mixtur": 4, "mla": [21, 29], "mlp": [16, 75, 81], "mlperf": 23, "modal": [71, 91], "mode": 71, "model": [6, 13, 15, 17, 18, 19, 21, 27, 28, 67, 71, 72, 74, 75, 78, 82, 86, 91, 92, 93, 96, 97], "modelconfig": 1, "modul": [7, 10, 28, 29], "moe": [4, 29], "moe_backend": 27, "monitor": 32, "more": [21, 25, 70], "motiv": [30, 31], "mount": 88, "mqa": 29, "mtp": [27, 28], "multi": [5, 17, 27, 31, 34, 69, 71, 91], "multimod": [34, 38, 43, 58], "multipl": [55, 78], "name": [18, 33, 87], "nativ": [18, 69], "nearli": 24, "network": 71, "new": [15, 25, 96, 98], "next": [26, 86], "ngc": [32, 64], "node": [17, 34, 69], "non": 71, "norm": [75, 78], "normal": 81, "note": [3, 5, 93], "nsight": 70, "num": 77, "numer": 90, "nvfp4": 90, "nvidia": [27, 29, 70], "nvtx": 70, "o": 89, "observ": 30, "obtain": 3, "offlin": 30, "offload": 9, "one": 30, "onli": [27, 63, 70, 90], "onlin": [30, 61], "openai": [57, 58, 59, 60], "optim": [5, 27, 28, 29, 31, 78], "option": [21, 32, 63, 75, 78, 79], "osl": [21, 31], "other": 71, "out": [21, 96], "output": [3, 71], "over": [22, 30], "overlap": [31, 100], "overrid": 88, "overview": [6, 16, 18, 20, 69, 72, 87, 94], "ovewiew": 97, "own": 104, "p": 9, "pack": 5, "pad": 5, "page": [5, 8, 69, 77, 78, 79], "parallel": [4, 10, 27, 29, 30, 33, 71, 74, 78], "paramet": 6, "parser": 41, "part": [15, 30], "pattern": [7, 17], "perf": [42, 43], "perform": [9, 11, 13, 21, 23, 26, 27, 30, 31, 32, 62, 70, 73, 75, 76, 78], "persist": 71, "phase": 5, "pip": 65, "pipelin": [74, 78, 87], "pitfal": 73, "plugin": [17, 33, 75, 78, 83], "pod": 36, "polici": 79, "pool": [8, 81, 89], "posit": 5, "post": [3, 87], "postprocess": 18, "power": 71, "practic": [26, 87], "pre": 64, "precis": [11, 27, 29, 90], "prepar": [16, 21, 32, 36, 71, 72, 73], "prerequisit": [21, 32, 63, 76, 86, 96], "prevent": 9, "processor": [3, 51], "profil": [27, 70, 78], "programmat": 27, "prompt": 13, "prompttuningparam": 1, "provid": 25, "push": [27, 32], "py": 94, "pyexecutor": 97, "python": [3, 30, 63, 89], "pytorch": [52, 53, 54, 70, 71, 91, 95, 96], "q": 90, "qkv": 5, "quantiz": [16, 20, 26, 40, 71, 75, 84, 90, 101], "quantmod": 90, "queri": 5, "quick": [67, 86, 95], "quickstart": 71, "qwen": 31, "r1": [21, 27, 28, 29, 31, 41], "rab": 5, "rank": 16, "rawengin": 1, "re": 27, "reason": 41, "recommend": [75, 78, 89], "record_signatur": 7, "redraft": 13, "reduc": [14, 75, 78], "refer": [15, 62, 68, 100], "regist": 15, "registr": 96, "registri": 32, "rel": 5, "relat": [7, 86], "relax": [27, 28], "releas": [32, 64, 93], "repositori": 32, "reproduc": [21, 27, 29, 30, 31, 72], "request": [1, 3, 32], "requir": [7, 11], "resourcemanag": 97, "respons": 3, "result": [3, 21, 70, 72, 73], "retriev": 7, "reus": 9, "revisit": 77, "rewrit": 7, "right": 26, "roll": 5, "rope": 5, "rotari": 5, "router": 27, "routergemm": 27, "run": [10, 14, 21, 28, 30, 52, 53, 54, 70, 71, 72, 73, 86], "run_benchmark": 94, "runpod": 36, "runtim": [1, 6, 10, 17, 29, 40, 63, 79, 85, 89], "runtimedefault": 1, "same": 25, "sampl": [6, 13, 32, 40, 102], "samplingconfig": 1, "save": 73, "scale": [5, 16, 30], "scatter": 78, "schedul": [77, 79, 97, 100, 104], "script": 94, "search": 5, "sec": 24, "select": 88, "send": 3, "serial": 0, "serv": [31, 34, 54, 61, 70, 86], "server": [3, 31, 32, 34, 86], "servic": 2, "set": [71, 74], "sh": 94, "shard": 74, "shoot": 18, "singl": 22, "situat": 9, "size": [77, 79, 89], "slide": 5, "slurm": [34, 45, 52, 53, 54, 94], "smart": 27, "smoothquant": 90, "softwar": 91, "sota": 26, "sourc": 63, "spars": 27, "specif": 70, "specul": [13, 28, 33, 56], "speculativedecodingmod": 1, "speculativedecodingmodul": 1, "speed": 26, "speedup": 28, "ssh": [35, 36], "stage": 87, "start": [32, 34, 62, 67, 86, 95], "start_work": 94, "statist": 30, "step": [15, 21, 30, 31, 32, 63, 86, 96], "stop": 32, "strategi": [27, 29, 74], "stream": [14, 27, 49], "streamingllm": 5, "structur": 3, "studi": [28, 30, 31, 77], "style": 40, "subcommand": 71, "submit": 94, "summari": [71, 75, 78], "support": [17, 18, 21, 28, 31, 63, 69, 71, 90, 91], "swiglu": 75, "syntax": 34, "synthet": 31, "system": [27, 70], "tabl": [21, 27, 28, 29, 30, 62, 76, 87, 96], "tag": [32, 64, 86], "target": 13, "technic": 90, "techniqu": 26, "templat": 36, "tensor": [0, 3, 4, 5, 7, 10, 74, 89], "tensorrt": [4, 13, 16, 17, 18, 19, 20, 21, 23, 24, 26, 28, 30, 31, 32, 35, 36, 62, 63, 69, 71, 73, 77, 86, 89, 91, 93], "test": [32, 87, 92], "text": [46, 47, 48, 49, 51, 55], "think": 74, "thought": 30, "throughput": [21, 25, 29, 71, 72, 73], "time": [78, 89], "tip": [32, 67, 73, 92], "tllmlogger": 1, "tok": 23, "token": [23, 24, 40, 77, 79], "tool": 20, "top": 97, "topic": 63, "topologi": 11, "tradeoff": 100, "transferag": 0, "transform": 31, "translat": [18, 30, 31], "tree": [13, 28, 96], "trigger": [8, 87], "triton": [3, 31, 86], "troubl": 18, "troubleshoot": [2, 32, 67, 73, 92], "trt": 26, "trtllm": [27, 31, 33, 34, 53, 54, 70, 73, 86], "tune": [9, 21, 32, 76, 77], "type": [0, 8], "understand": [77, 89], "unit": [87, 92], "unnecessari": 87, "up": [22, 25, 26], "updat": 93, "upload": [35, 36], "us": [7, 10, 13, 32, 51, 67, 78, 79, 88, 89], "usag": [11, 87, 89, 100], "user": 75, "v": [4, 24], "valid": 71, "vanilla": 28, "variabl": [2, 72], "verif": 27, "verifi": 15, "via": [65, 73], "visual": 70, "volum": 88, "w4a16": 90, "w8a16": 90, "w8a8": 90, "wai": 32, "waiv": 87, "weekli": 32, "weight": [14, 15, 16, 17, 18, 19, 29, 89, 90, 96], "welcom": 62, "what": [8, 23, 26, 69], "when": [7, 27], "width": 3, "window": [5, 69, 79], "windowblockmanag": 8, "wip": 21, "within": 25, "without": 63, "work": [27, 28, 29, 31, 71, 100], "workflow": [7, 18, 20, 70, 71, 94], "workload": 27, "world": 6, "worldconfig": 1, "write": 15, "xqa": [5, 25], "you": [69, 73], "your": [32, 104]}}) \ No newline at end of file +Search.setIndex({"alltitles": {"1. Download TensorRT-LLM": [[21, "download-tensorrt-llm"]], "1. Using a Model from the Hugging Face Hub": [[70, "using-a-model-from-the-hugging-face-hub"]], "1. Weights size": [[92, "weights-size"]], "2. Activation size": [[92, "activation-size"]], "2. Download the DeepSeek R1 models": [[21, "download-the-deepseek-r1-models"]], "2. Using a Local Hugging Face Model": [[70, "using-a-local-hugging-face-model"]], "3. Build and run TensorRT-LLM container": [[21, "build-and-run-tensorrt-llm-container"]], "3. I/O tensors": [[92, "i-o-tensors"]], "3.1 Runtime and decoder buffers except KV cache tensor": [[92, "runtime-and-decoder-buffers-except-kv-cache-tensor"]], "3.2 KV cache tensor": [[92, "kv-cache-tensor"]], "4. Compile and Install TensorRT-LLM": [[21, "compile-and-install-tensorrt-llm"]], "5. Optional: Tune GPU clocks": [[21, "optional-tune-gpu-clocks"]], "6. Dataset preparation": [[21, "dataset-preparation"]], "@record_signature to Decorate Functionals Requiring FLayerInfo": [[7, "record-signature-to-decorate-functionals-requiring-flayerinfo"]], "ALiBi": [[5, "alibi"]], "API": [[3, "api"]], "API Changes": [[14, "api-changes"], [96, "api-changes"], [96, "id9"], [96, "id14"], [96, "id19"], [96, "id24"], [96, "id31"], [96, "id36"], [96, "id42"], [96, "id48"], [96, "id54"]], "API Reference": [[71, null]], "AWQ Quantization Scaling Factors": [[16, "awq-quantization-scaling-factors"]], "About": [[35, "about"]], "About Speculative Sampling": [[13, "about-speculative-sampling"]], "About TensorRT-LLM": [[72, "about-tensorrt-llm"]], "Accuracy": [[26, "accuracy"]], "Accuracy studies for Relaxed Acceptance": [[28, "accuracy-studies-for-relaxed-acceptance"]], "Achieving speedup with MTP speculative decoding": [[28, "achieving-speedup-with-mtp-speculative-decoding"]], "Acknowledgement": [[30, "acknowledgement"], [31, "acknowledgement"]], "Acknowledgment": [[27, "acknowledgment"], [28, "acknowledgment"], [29, "acknowledgment"]], "Activation": [[84, "module-tensorrt_llm.layers.activation"]], "Adding a Model": [[15, null]], "Adding a New Model in PyTorch Backend": [[99, null]], "Advanced": [[65, null]], "Advanced topics": [[66, "advanced-topics"]], "Algorithm": [[11, "algorithm"]], "Announcements": [[96, "announcements"], [96, "id52"]], "Architecture": [[65, null]], "Architecture Ovewiew": [[100, null]], "Asyncio-Based Generation": [[41, "asyncio-based-generation"]], "Attention": [[84, "module-tensorrt_llm.layers.attention"], [101, null]], "Attention Backends": [[101, "attention-backends"]], "Attention Kernel": [[27, "attention-kernel"]], "Attention Weights": [[16, "attention-weights"]], "Attention for MTP": [[28, "attention-for-mtp"]], "Auto parallel arguments": [[34, "tensorrt_llm.commands.build-parse_arguments-auto-parallel-arguments"]], "Autoregressive MTP Layers": [[27, "autoregressive-mtp-layers"]], "Avoiding unnecessary --disable-fail-fast usage": [[90, "avoiding-unnecessary-disable-fail-fast-usage"]], "B200 max-throughput for R1 with FP16 KV cache": [[21, "b200-max-throughput-for-r1-with-fp16-kv-cache"]], "B200 max-throughput for R1-0528 with FP8 KV cache": [[21, "b200-max-throughput-for-r1-0528-with-fp8-kv-cache"]], "B200 min-latency": [[21, "b200-min-latency"]], "Background": [[27, "background"], [28, "background"]], "Basic Implementation": [[28, "basic-implementation"]], "Basics": [[46, "basics"]], "Beam-Search": [[5, "beam-search"]], "Before Benchmarking": [[74, "before-benchmarking"]], "Before You Begin: TensorRT-LLM LLM-API": [[76, "before-you-begin-tensorrt-llm-llm-api"]], "Benchmark": [[21, "benchmark"], [21, "id1"], [26, "benchmark"], [35, "benchmark"]], "Benchmarking Default Performance": [[76, null]], "Benchmarking a non-Medusa Low Latency Engine": [[74, "benchmarking-a-non-medusa-low-latency-engine"]], "Benchmarking with LoRA Adapters in PyTorch workflow": [[74, "benchmarking-with-lora-adapters-in-pytorch-workflow"]], "Benchmarking with trtllm-bench": [[76, "benchmarking-with-trtllm-bench"]], "Best practices to choose the right quantization methods": [[26, "best-practices-to-choose-the-right-quantization-methods"]], "Block": [[8, "block"]], "Boost settings": [[74, "boost-settings"]], "Build APIs": [[20, "build-apis"]], "Build Checkpoint into TensorRT Engine": [[16, "build-checkpoint-into-tensorrt-engine"]], "Build Configuration": [[41, "build-configuration"]], "Build TensorRT-LLM": [[66, "build-tensorrt-llm"]], "Build the TensorRT-LLM Docker Image": [[36, null]], "Build the TensorRT-LLM Docker Image and Upload to DockerHub": [[36, "build-the-tensorrt-llm-docker-image-and-upload-to-dockerhub"], [37, "build-the-tensorrt-llm-docker-image-and-upload-to-dockerhub"]], "Building a Benchmark Engine": [[74, "building-a-benchmark-engine"]], "Building a Medusa Low-Latency Engine": [[74, "building-a-medusa-low-latency-engine"]], "Building a TensorRT-LLM Docker Image": [[66, "building-a-tensorrt-llm-docker-image"]], "Building and Saving Engines via CLI": [[76, "building-and-saving-engines-via-cli"]], "Building and Saving the Engine": [[76, "building-and-saving-the-engine"]], "Building from Source Code on Linux": [[66, null]], "Building the Python Bindings for the C++ Runtime": [[66, "building-the-python-bindings-for-the-c-runtime"]], "C++ Executor API Example": [[3, "c-executor-api-example"]], "C++ GPT Runtime": [[6, null]], "C++ extension": [[30, "c-extension"]], "C++ runtime": [[92, "c-runtime"], [92, "id1"]], "CI pipelines": [[90, "ci-pipelines"]], "CLI Tools": [[20, "cli-tools"]], "CUDA Graph & Programmatic Dependent Launch": [[27, "cuda-graph-programmatic-dependent-launch"]], "CUTLASS Backend (default backend)": [[27, "cutlass-backend-default-backend"]], "Cache Layout Transformation": [[31, "cache-layout-transformation"]], "Capacity Scheduler Policy": [[82, "capacity-scheduler-policy"]], "Cast": [[84, "module-tensorrt_llm.layers.cast"]], "Chat API": [[35, "chat-api"]], "Chunked Context": [[5, "chunked-context"]], "Classical Workflow": [[7, "classical-workflow"]], "Closing": [[22, "closing"], [25, "closing"]], "Collect PyTorch profiler results": [[73, "collect-pytorch-profiler-results"]], "Command Overview": [[75, "command-overview"]], "Common LLM Support": [[72, "common-llm-support"]], "Communication Kernel": [[27, "communication-kernel"]], "Compilation": [[17, "compilation"]], "Compile the Model into a TensorRT Engine": [[89, "compile-the-model-into-a-tensorrt-engine"]], "Completions API": [[35, "completions-api"], [35, "id1"]], "Conclusion": [[78, "conclusion"], [80, "conclusion"], [81, "conclusion"]], "Config": [[16, "config"]], "Configure SSH Key": [[37, "configure-ssh-key"]], "Configure The Executor": [[3, "configure-the-executor"]], "Connect to the Pod": [[37, "connect-to-the-pod"]], "Container image selection": [[91, "container-image-selection"]], "Container image tags": [[67, null], [89, null]], "Context Chunking Policy": [[82, "context-chunking-policy"]], "Context Phase": [[5, "context-phase"]], "Context and Generation Phases": [[5, "context-and-generation-phases"]], "Contiguous KV Cache": [[5, "contiguous-kv-cache"]], "Continuous Integration Overview": [[90, null]], "Control generated text using logits processor": [[52, null]], "Controlling output with Logits Post-Processor": [[3, "controlling-output-with-logits-post-processor"]], "Conv": [[84, "module-tensorrt_llm.layers.conv"]], "Conversion APIs": [[20, "conversion-apis"]], "Coordinating with NVIDIA Nsight Systems Launch": [[73, "coordinating-with-nvidia-nsight-systems-launch"]], "Coordinating with PyTorch profiler (PyTorch workflow only)": [[73, "coordinating-with-pytorch-profiler-pytorch-workflow-only"]], "Core Models": [[99, "core-models"]], "Core implementations of the GPU logic": [[30, "core-implementations-of-the-gpu-logic"]], "Core implementations of the host logic": [[30, "core-implementations-of-the-host-logic"]], "Create a Pod Template": [[37, "create-a-pod-template"]], "Create a Runpod account": [[37, "create-a-runpod-account"]], "Cross Attention": [[5, "cross-attention"]], "Curl Chat Client": [[38, null]], "Curl Chat Client For Multimodal": [[39, null]], "Curl Completion Client": [[40, null]], "Customization": [[46, "customization"]], "Customize KV Cache Manager": [[106, "customize-kv-cache-manager"]], "Customize Your Own Scheduler": [[107, "customize-your-own-scheduler"]], "Data Parallel for Attention module (ADP)": [[29, "data-parallel-for-attention-module-adp"]], "Debug Execution Errors": [[95, "debug-execution-errors"]], "Debug on E2E Models": [[95, "debug-on-e2e-models"]], "Debug on Unit Tests": [[95, "debug-on-unit-tests"]], "Debugging FAQs": [[2, "debugging-faqs"]], "Deciding Model Sharding Strategy": [[77, null]], "Decoder": [[100, "decoder"]], "DeepSeek R1": [[31, "deepseek-r1"]], "DeepSeek R1 MTP Implementation and Optimization": [[28, null]], "Deepseek R1 Reasoning Parser": [[42, null]], "Default Build Behavior": [[74, "default-build-behavior"]], "Dense GEMM optimization": [[27, "dense-gemm-optimization"]], "Deploy with Triton Inference Server": [[89, "deploy-with-triton-inference-server"]], "Deploy with trtllm-serve": [[89, "deploy-with-trtllm-serve"]], "Develop TensorRT-LLM on Runpod": [[37, null]], "Developer Guide": [[98, "developer-guide"]], "Disable Tokenizer": [[41, "disable-tokenizer"]], "Disaggregated Inference Benchmark Scripts": [[97, null]], "Disaggregated Serving": [[13, "disaggregated-serving"]], "Disaggregated Serving in TensorRT-LLM": [[31, null], [31, "id1"]], "Disaggregated-Service (Experimental)": [[2, null]], "Distributed LLM Generation": [[51, null]], "DoRA": [[10, "dora"]], "Documentation": [[96, "documentation"], [96, "id28"]], "Download Artifacts": [[32, "download-artifacts"]], "Draft-Target-Model": [[13, "draft-target-model"]], "Dynamo": [[31, "dynamo"]], "E2E evaluation": [[30, "e2e-evaluation"]], "EAGLE": [[13, "eagle"]], "EP Load Balancer": [[30, "ep-load-balancer"]], "EP communication kernels": [[30, "ep-communication-kernels"]], "EP communication kernels implementation": [[30, "ep-communication-kernels-implementation"]], "Eagle3 support": [[28, "eagle3-support"]], "Embedding": [[84, "module-tensorrt_llm.layers.embedding"]], "Enable GIL information in NVTX markers": [[73, "enable-gil-information-in-nvtx-markers"]], "Enable garbage collection (GC) NVTX markers": [[73, "enable-garbage-collection-gc-nvtx-markers"]], "Enable kv cache reuse for p-tuning": [[9, "enable-kv-cache-reuse-for-p-tuning"]], "Enable more NVTX markers for debugging": [[73, "enable-more-nvtx-markers-for-debugging"]], "Enable ssh access to the container": [[36, "enable-ssh-access-to-the-container"]], "Enabling GEMM + SwiGLU Fusion": [[78, "enabling-gemm-swiglu-fusion"]], "Enabling GEMM Plugin": [[81, "enabling-gemm-plugin"]], "Enabling Low Latency GEMM plugin": [[78, "enabling-low-latency-gemm-plugin"]], "Enabling Paged Context Attention": [[81, "enabling-paged-context-attention"]], "Enabling Quantization": [[78, "enabling-quantization"]], "Enabling Quantized KV Cache": [[78, "enabling-quantized-kv-cache"]], "Enabling Reduce Norm Fusion Plugin": [[81, "enabling-reduce-norm-fusion-plugin"]], "Enabling Reduce Norm Fusion with User Buffers": [[78, "enabling-reduce-norm-fusion-with-user-buffers"]], "Enabling building with multiple profiles": [[81, "enabling-building-with-multiple-profiles"]], "Environment Variables": [[2, "environment-variables"]], "Evaluation": [[28, "evaluation"]], "Events in KVCacheEventManager": [[8, "events-in-kvcacheeventmanager"]], "Everything in One Diagram": [[27, "everything-in-one-diagram"]], "Example": [[16, "example"]], "Example LoRA tensors": [[10, "example-lora-tensors"]], "Example of Build Subcommand Output:": [[74, "example-of-build-subcommand-output"]], "Examples": [[17, "examples"], [18, "examples"], [73, "examples"]], "Executor": [[0, null]], "Executor API": [[3, null]], "Expanded thoughts": [[30, "expanded-thoughts"]], "Expected Result Format": [[21, "expected-result-format"], [21, "id2"], [21, "id3"], [21, "id4"]], "Expected Results": [[21, "expected-results"]], "Expert Parallelism in TensorRT-LLM": [[4, null]], "Expert parallel for MoE (EP)": [[29, "expert-parallel-for-moe-ep"]], "Exploring more ISL/OSL combinations": [[21, "exploring-more-isl-osl-combinations"]], "FAQ": [[92, "faq"]], "FLayerInfo for Retrieving High-Level Information for a Functional": [[7, "flayerinfo-for-retrieving-high-level-information-for-a-functional"]], "FP32, FP16 and BF16": [[93, "fp32-fp16-and-bf16"]], "FP4 Models:": [[75, "fp4-models"]], "FP8 (Hopper)": [[93, "fp8-hopper"]], "FP8 Context FMHA": [[5, "fp8-context-fmha"]], "FP8 Models:": [[75, "fp8-models"]], "FP8 Quantization": [[78, null]], "FP8 Quantization Scaling Factors": [[16, "fp8-quantization-scaling-factors"]], "FP8 Support": [[72, "fp8-support"]], "FP8 \u201cBaseline\u201d Performance": [[78, "fp8-baseline-performance"]], "Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100": [[22, null]], "Falcon-180B on a single H200 with INT4 AWQ": [[22, "falcon-180b-on-a-single-h200-with-int4-awq"]], "Feature Combination Matrix": [[102, null]], "Feature Descriptions": [[73, "feature-descriptions"]], "Features": [[98, "features"]], "File Descriptions": [[97, "file-descriptions"]], "Finding the stage for a test": [[90, "finding-the-stage-for-a-test"]], "Fixed Issues": [[96, "fixed-issues"], [96, "id11"], [96, "id15"], [96, "id21"], [96, "id26"], [96, "id33"], [96, "id38"], [96, "id44"], [96, "id50"], [96, "id56"], [96, "id61"]], "Fully customized": [[18, "fully-customized"]], "Functionals": [[83, null]], "Fuse_A_GEMM": [[27, "fuse-a-gemm"]], "Future Work": [[31, "future-work"]], "Future Works": [[27, "future-works"], [28, "future-works"], [29, "future-works"]], "Future-Style Generation": [[41, "future-style-generation"]], "GEMM + SwiGLU Fusion in Gated-MLP": [[78, "gemm-swiglu-fusion-in-gated-mlp"]], "GEMM Plugin": [[81, "gemm-plugin"]], "GPTQ and AWQ (W4A16)": [[93, "gptq-and-awq-w4a16"]], "GPU Clock Management": [[74, "gpu-clock-management"]], "Genai Perf Client": [[43, null]], "Genai Perf Client For Multimodal": [[44, null]], "General FAQs": [[2, "general-faqs"]], "Generate text": [[48, null]], "Generate text asynchronously": [[49, null]], "Generate text in streaming": [[50, null]], "Generate text with guided decoding": [[47, null]], "Generate text with multiple LoRA adapters": [[56, null]], "Generation": [[41, "generation"]], "Generation Phase": [[5, "generation-phase"]], "Getting Started": [[65, null]], "Graph Rewriting APIs": [[7, "graph-rewriting-apis"]], "Graph Rewriting Module": [[7, null]], "Grouped GEMM": [[27, "grouped-gemm"]], "H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token": [[23, null]], "H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM": [[24, null]], "H200 max-throughput": [[21, "h200-max-throughput"]], "H200 min-latency": [[21, "h200-min-latency"]], "H200 vs H100": [[24, "h200-vs-h100"]], "Hardware": [[94, "hardware"]], "Hierarchy: Pool, Block, and Page": [[8, "hierarchy-pool-block-and-page"]], "High-level design introduction": [[30, "high-level-design-introduction"]], "How It Works": [[103, "how-it-works"]], "How the Benchmarker Works": [[74, "how-the-benchmarker-works"]], "How to Enable": [[4, "how-to-enable"]], "How to Think about Model Sharding: Communication is Key": [[77, "how-to-think-about-model-sharding-communication-is-key"]], "How to change Max Batch Size": [[80, "how-to-change-max-batch-size"]], "How to change Max Num Tokens": [[80, "how-to-change-max-num-tokens"]], "How to enable kv cache reuse": [[9, "how-to-enable-kv-cache-reuse"]], "How to get best performance on DeepSeek-R1 in TensorRT-LLM": [[21, null]], "How to launch Llama4 Maverick + Eagle3 TensorRT-LLM server": [[32, null]], "How to reproduce": [[27, "how-to-reproduce"], [29, "how-to-reproduce"]], "How to run DeepSeek models with MTP": [[28, "how-to-run-deepseek-models-with-mtp"]], "How to run the DeepSeek-R1 model with Relaxed Acceptance": [[28, "how-to-run-the-deepseek-r1-model-with-relaxed-acceptance"]], "How to set Tensor Parallelism and Pipeline Parallelism": [[77, "how-to-set-tensor-parallelism-and-pipeline-parallelism"]], "INT4 and INT8 Weight-Only (W4A16 and W8A16)": [[93, "int4-and-int8-weight-only-w4a16-and-w8a16"]], "INT8 SmoothQuant (W8A8)": [[93, "int8-smoothquant-w8a8"]], "INT8/FP8 KV Caches": [[5, "int8-fp8-kv-caches"]], "ISL 4096 - OSL 1024 (Machine Translation Dataset)": [[31, "isl-4096-osl-1024-machine-translation-dataset"]], "ISL 4400 - OSL 1200 (Machine Translation Dataset)": [[31, "isl-4400-osl-1200-machine-translation-dataset"]], "ISL 8192 - OSL 1024 (Machine Translation Dataset)": [[31, "isl-8192-osl-1024-machine-translation-dataset"]], "ISL 8192 - OSL 256 (Synthetic Dataset)": [[31, "isl-8192-osl-256-synthetic-dataset"]], "Implement AttentionBackend": [[101, "implement-attentionbackend"]], "Implement AttentionMetadata": [[101, "implement-attentionmetadata"]], "Implement a New Attention Backend": [[101, "implement-a-new-attention-backend"]], "Implementation Configuration": [[27, "implementation-configuration"]], "Important Note": [[5, "important-note"]], "In-Flight Batching and Paged Attention": [[72, "in-flight-batching-and-paged-attention"]], "In-flight Batching": [[5, "in-flight-batching"]], "In-flight Batching with the Triton Inference Server": [[3, "in-flight-batching-with-the-triton-inference-server"]], "Indices and tables": [[65, "indices-and-tables"]], "Inference Endpoints": [[35, "inference-endpoints"]], "Infrastructure Changes": [[96, "infrastructure-changes"], [96, "id4"], [96, "id7"], [96, "id12"], [96, "id16"], [96, "id22"], [96, "id27"], [96, "id34"], [96, "id39"], [96, "id45"]], "Infrastructure changes": [[96, "id51"]], "Input QKV tensor": [[5, "input-qkv-tensor"]], "Installation": [[65, null], [89, "installation"]], "Installation Errors": [[95, "installation-errors"]], "Installing on Linux via pip": [[68, null]], "Interfaces": [[106, "interfaces"]], "Internal Components": [[6, "internal-components"]], "Introduction": [[29, "introduction"], [99, "introduction"]], "Jenkins stage names": [[90, "jenkins-stage-names"]], "KV Cache": [[5, "kv-cache"]], "KV Cache Exchange": [[31, "kv-cache-exchange"]], "KV Cache Management: Pools, Blocks, and Events": [[8, null]], "KV Cache Manager": [[106, null]], "KV Cache Manager Introduction": [[106, "kv-cache-manager-introduction"]], "KV Cache Pool Management": [[8, "kv-cache-pool-management"]], "KV Cache Quantization Scaling Factors": [[16, "kv-cache-quantization-scaling-factors"]], "KV cache reuse": [[9, null]], "KVCacheManager": [[100, "kvcachemanager"]], "Kernel Level optimizations": [[27, "kernel-level-optimizations"]], "Kernel fusion": [[27, "kernel-fusion"]], "Key Components": [[98, "key-components"]], "Key Features": [[69, null]], "Key Features and Enhancements": [[96, "key-features-and-enhancements"], [96, "id2"], [96, "id3"], [96, "id5"], [96, "id8"], [96, "id13"], [96, "id18"], [96, "id23"], [96, "id30"], [96, "id35"], [96, "id41"], [96, "id47"], [96, "id53"], [96, "id57"], [96, "id59"]], "Key Optimizations": [[27, "key-optimizations"]], "Known Issues": [[92, "known-issues"], [96, "known-issues"], [96, "id6"], [96, "id10"], [96, "id17"], [96, "id29"], [96, "id40"], [96, "id46"], [96, "id62"], [98, "known-issues"]], "Known Limitations": [[66, "known-limitations"]], "LLM API": [[89, "llm-api"]], "LLM API Introduction": [[70, null]], "LLM Common Customizations": [[41, null]], "LLM Examples": [[46, null]], "LLM Examples Introduction": [[45, null]], "LLM Models": [[94, "llm-models"]], "Latest GPU Support": [[72, "latest-gpu-support"]], "Latest HBM Memory": [[24, "latest-hbm-memory"]], "Launching the server": [[32, "launching-the-server"]], "LayerNorm Weights": [[16, "layernorm-weights"]], "Layers": [[84, null]], "Limitations": [[13, "limitations"], [96, "limitations"]], "Limitations and Caveats": [[74, "limitations-and-caveats"]], "Linear": [[84, "module-tensorrt_llm.layers.linear"]], "Linking with the TensorRT-LLM C++ Runtime": [[66, "linking-with-the-tensorrt-llm-c-runtime"]], "Llama 3.1 405B": [[17, "llama-3-1-405b"]], "Llama 3.1 405B FP4": [[75, "llama-3-1-405b-fp4"]], "Llama 3.1 405B FP8": [[75, "llama-3-1-405b-fp8"]], "Llama 3.1 70B": [[17, "llama-3-1-70b"]], "Llama 3.1 70B FP8": [[75, "llama-3-1-70b-fp8"]], "Llama 3.1 8B FP8": [[75, "llama-3-1-8b-fp8"]], "Llama 3.3 70B FP4": [[75, "llama-3-3-70b-fp4"]], "Llama-70B on H200 up to 2.4x increased throughput with XQA within same latency budget": [[25, "llama-70b-on-h200-up-to-2-4x-increased-throughput-with-xqa-within-same-latency-budget"]], "Llama-70B on H200 up to 6.7x A100": [[22, "llama-70b-on-h200-up-to-6-7x-a100"]], "LoRA Module id mapping": [[10, "lora-module-id-mapping"]], "LoRA arguments": [[34, "tensorrt_llm.commands.build-parse_arguments-lora-arguments"]], "LoRA tensor format details": [[10, "lora-tensor-format-details"]], "LoRA with tensor parallel": [[10, "lora-with-tensor-parallel"]], "Loading function": [[18, "loading-function"]], "Logits arguments": [[34, "tensorrt_llm.commands.build-parse_arguments-logits-arguments"]], "Lookahead Decoding": [[13, "lookahead-decoding"]], "LoraCache configuration": [[10, "loracache-configuration"]], "Low Latency Benchmark": [[74, "low-latency-benchmark"]], "Low Latency GEMM Plugin": [[78, "low-latency-gemm-plugin"]], "Low Latency TensorRT-LLM Engine for Llama-3 70B": [[74, "low-latency-tensorrt-llm-engine-for-llama-3-70b"]], "Low-Precision-AllReduce": [[11, null]], "MLA Layers Optimizations": [[29, "mla-layers-optimizations"]], "MLP": [[84, "module-tensorrt_llm.layers.mlp"]], "MLP Weights": [[16, "mlp-weights"]], "MLPerf on H100 with FP8": [[23, "mlperf-on-h100-with-fp8"]], "MTP": [[27, "mtp"]], "MTP Eagle": [[28, "mtp-eagle"]], "MTP Modules": [[28, "mtp-modules"]], "MTP Vanilla": [[28, "mtp-vanilla"]], "MTP for inference": [[28, "mtp-for-inference"]], "MTP implementation in TensorRT-LLM": [[28, "mtp-implementation-in-tensorrt-llm"]], "MTP optimization - Relaxed Acceptance": [[28, "mtp-optimization-relaxed-acceptance"]], "Make Evaluation": [[16, "make-evaluation"]], "Mark Tensors As Output": [[3, "mark-tensors-as-output"]], "Max Throughput Benchmark": [[74, "max-throughput-benchmark"]], "Max Tokens in Paged KV Cache and KV Cache Free GPU Memory Fraction": [[82, "max-tokens-in-paged-kv-cache-and-kv-cache-free-gpu-memory-fraction"]], "Maximum Attention Window Size": [[82, "maximum-attention-window-size"]], "Measurement Methodology": [[31, "measurement-methodology"]], "Medusa": [[13, "medusa"]], "Medusa Tree": [[13, "medusa-tree"]], "Memory Usage of TensorRT-LLM": [[92, null]], "Memory pool": [[92, "memory-pool"]], "Metrics Endpoint": [[35, "metrics-endpoint"]], "Miscellaneous": [[30, "miscellaneous"]], "Mixed ETP": [[27, "mixed-etp"]], "Mixture of Experts (MoE)": [[4, "mixture-of-experts-moe"]], "MoE Layers Optimizations": [[29, "moe-layers-optimizations"]], "Model Architecture": [[27, "model-architecture"]], "Model Configuration": [[6, "model-configuration"], [99, "model-configuration"]], "Model Definition": [[17, null], [99, "model-definition"]], "Model Definition API": [[89, "model-definition-api"]], "Model Engine": [[17, "model-engine"], [100, "model-engine"]], "Model Input": [[70, "model-input"]], "Model Registration": [[99, "model-registration"]], "Model Updates": [[96, "model-updates"], [96, "id20"], [96, "id25"], [96, "id32"], [96, "id37"], [96, "id43"], [96, "id49"], [96, "id55"], [96, "id58"], [96, "id60"]], "Model Weights": [[19, "model-weights"]], "Models": [[85, null]], "Models (PyTorch Backend)": [[94, "models-pytorch-backend"]], "Models (TensorRT Backend)": [[94, "models-tensorrt-backend"]], "Models with customized key names": [[18, "models-with-customized-key-names"]], "Models with customized weight layout": [[18, "models-with-customized-weight-layout"]], "Motivation": [[31, "motivation"]], "Motivation for large-scale EP": [[30, "motivation-for-large-scale-ep"]], "Motivation of EP communication kernels for GB200": [[30, "motivation-of-ep-communication-kernels-for-gb200"]], "Multi-GPU Multi-Node Inference": [[72, "multi-gpu-multi-node-inference"]], "Multi-GPU and Multi-Node Support": [[17, "multi-gpu-and-multi-node-support"]], "Multi-Head, Multi-Query, and Group-Query Attention": [[5, null]], "Multi-Modal Models 3": [[94, "multi-modal-models"]], "Multi-backend Support": [[31, "multi-backend-support"]], "Multi-node Serving with Slurm": [[35, "multi-node-serving-with-slurm"]], "Multi-streams": [[27, "multi-streams"]], "Multimodal Serving": [[35, "multimodal-serving"]], "Multiple Profiles": [[81, "multiple-profiles"]], "NGram": [[13, "ngram"]], "NVFP4 (Blackwell)": [[93, "nvfp4-blackwell"]], "Named Arguments": [[34, "tensorrt_llm.commands.build-parse_arguments-named-arguments"]], "Native Windows Support": [[72, "native-windows-support"]], "Natively supported models": [[18, "natively-supported-models"]], "New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget": [[25, null]], "Next Steps": [[89, "next-steps"]], "Normalization": [[84, "module-tensorrt_llm.layers.normalization"]], "Not supported: MLA chunked context support on Hopper": [[21, "not-supported-mla-chunked-context-support-on-hopper"]], "Note on context outputs": [[3, "note-on-context-outputs"]], "Numerical Precision": [[93, null]], "Observation over GSM8K dataset": [[30, "observation-over-gsm8k-dataset"]], "Observations over one machine translation dataset": [[30, "observations-over-one-machine-translation-dataset"]], "Obtaining Arbitrary Output Tensors": [[3, "obtaining-arbitrary-output-tensors"]], "Offline EP Load Balancer": [[30, "offline-ep-load-balancer"], [30, "id1"]], "Offloading to host memory": [[9, "offloading-to-host-memory"]], "Online EP Load Balancer": [[30, "online-ep-load-balancer"], [30, "id2"]], "Online Serving Examples": [[64, null]], "Only collect specific iterations": [[73, "only-collect-specific-iterations"]], "OpenAI Chat Client": [[60, null]], "OpenAI Chat Client for Multimodal": [[61, null]], "OpenAI Completion Client": [[62, null]], "Openai Completion Client For Lora": [[63, null]], "Optimizing DeepSeek R1 Throughput on NVIDIA Blackwell GPUs: A Deep Dive for Developers": [[29, null]], "Option 1. Use weekly release NGC docker image": [[32, "option-1-use-weekly-release-ngc-docker-image"]], "Option 1: Build TensorRT-LLM in One Step": [[66, "option-1-build-tensorrt-llm-in-one-step"]], "Option 1: Full Build with C++ Compilation": [[66, "option-1-full-build-with-c-compilation"]], "Option 2. Build TensorRT-LLM Docker image (Alternative way)": [[32, "option-2-build-tensorrt-llm-docker-image-alternative-way"]], "Option 2: Container for building TensorRT-LLM Step-by-Step": [[66, "option-2-container-for-building-tensorrt-llm-step-by-step"]], "Option 2: Python-Only Build without C++ Compilation": [[66, "option-2-python-only-build-without-c-compilation"]], "Other Build Modes": [[74, "other-build-modes"]], "Out of memory issues": [[21, "out-of-memory-issues"]], "Out-of-Tree Models": [[99, "out-of-tree-models"]], "Overlap Optimization": [[31, "overlap-optimization"]], "Overlap Scheduler": [[103, null]], "Overriding Docker Compose configuration": [[91, "overriding-docker-compose-configuration"]], "Overview": [[6, "overview"], [16, "overview"], [18, "overview"], [20, "overview"], [72, null], [75, null], [97, "overview"]], "Padded and Packed Tensors": [[5, "padded-and-packed-tensors"]], "Page": [[8, "page"]], "Paged Context Attention": [[81, "paged-context-attention"]], "Paged KV Cache": [[5, "paged-kv-cache"]], "Parallel strategy": [[29, "parallel-strategy"]], "Parallelism Mapping Support": [[74, "parallelism-mapping-support"]], "Parallelism Strategy": [[27, "parallelism-strategy"]], "Pattern and Pattern Manager": [[7, "pattern-and-pattern-manager"]], "Pattern-Matching and Fusion": [[17, "pattern-matching-and-fusion"]], "Performance": [[26, "performance"], [65, null], [81, "performance"]], "Performance Analysis": [[73, null]], "Performance Improvements": [[13, "performance-improvements"]], "Performance Studies": [[31, "performance-studies"]], "Performance Tuning": [[32, "performance-tuning"]], "Performance Tuning Guide": [[79, null]], "Performance and Accuracy Considerations": [[11, "performance-and-accuracy-considerations"]], "Performance expectations": [[9, "performance-expectations"]], "Performance study": [[30, "performance-study"]], "Performance with GEMM + SwiGLU Fusion": [[78, "performance-with-gemm-swiglu-fusion"]], "Performance with GEMM Plugin": [[81, "performance-with-gemm-plugin"]], "Performance with Low Latency GEMM plugin": [[78, "performance-with-low-latency-gemm-plugin"]], "Performance with Quantized KV Cache": [[78, "performance-with-quantized-kv-cache"]], "Performance with Reduce Norm Fusion": [[81, "performance-with-reduce-norm-fusion"]], "Performance with Reduce Norm Fusion + User Buffers:": [[78, "performance-with-reduce-norm-fusion-user-buffers"]], "Performance with multiple profiles": [[81, "performance-with-multiple-profiles"]], "Persistence mode": [[74, "persistence-mode"]], "Pipeline Parallel Reduce Scatter Optimization": [[81, "pipeline-parallel-reduce-scatter-optimization"]], "Plugin": [[86, null]], "Plugin config arguments": [[34, "tensorrt_llm.commands.build-parse_arguments-plugin-config-arguments"]], "Plugins": [[17, "plugins"]], "Pool": [[8, "pool"]], "Pooling": [[84, "module-tensorrt_llm.layers.pooling"]], "Postprocessing functions": [[18, "postprocessing-functions"]], "Pre-built release container images on NGC": [[67, null]], "Precision Strategy": [[27, "precision-strategy"]], "Precision strategy": [[29, "precision-strategy"]], "Prepare": [[37, "prepare"]], "Prepare Dataset": [[76, "prepare-dataset"]], "Prepare the TensorRT-LLM Checkpoint": [[16, "prepare-the-tensorrt-llm-checkpoint"]], "Preparing a Dataset": [[74, "preparing-a-dataset"], [75, "preparing-a-dataset"]], "Prerequisite Knowledge": [[79, "prerequisite-knowledge"]], "Prerequisites": [[32, "prerequisites"], [66, "prerequisites"], [89, "prerequisites"], [99, "prerequisites"]], "Prerequisites: Install TensorRT-LLM and download models": [[21, "prerequisites-install-tensorrt-llm-and-download-models"]], "Profiling specific iterations on a trtllm-bench/trtllm-serve run": [[73, "profiling-specific-iterations-on-a-trtllm-bench-trtllm-serve-run"]], "Pushing Latency Boundaries: Optimizing DeepSeek-R1 Performance on NVIDIA B200 GPUs": [[27, null]], "PyExecutor": [[100, "pyexecutor"]], "PyTorch Backend": [[98, null]], "Python Bindings for the Executor API": [[3, "python-bindings-for-the-executor-api"]], "Python Interface": [[30, "python-interface"]], "Python runtime (Not recommended to be used)": [[92, "python-runtime-not-recommended-to-be-used"]], "Quantization": [[41, "quantization"], [87, null], [104, null]], "Quantization APIs": [[20, "quantization-apis"]], "Quantization and Dequantization (Q/DQ)": [[93, "quantization-and-dequantization-q-dq"]], "Quantization in TensorRT-LLM": [[26, "quantization-in-tensorrt-llm"]], "Quantization in the PyTorch Flow": [[74, "quantization-in-the-pytorch-flow"]], "Quantized KV-Cache": [[78, "quantized-kv-cache"]], "Quick Start": [[98, "quick-start"]], "Quick Start Example": [[70, "quick-start-example"]], "Quick Start Guide": [[89, null]], "Quickstart": [[74, "quickstart"]], "Qwen 3": [[31, "qwen-3"]], "Rank Weights": [[16, "rank-weights"]], "Re-balanced the sparse experts": [[27, "re-balanced-the-sparse-experts"]], "ReDrafter": [[13, "redrafter"]], "Reduce Norm Fusion Plugin for Llama models:": [[81, "reduce-norm-fusion-plugin-for-llama-models"]], "Reduce Norm Fusion with User Buffers for Llama Models": [[78, "reduce-norm-fusion-with-user-buffers-for-llama-models"]], "Reference": [[15, "reference"], [65, null]], "References": [[103, "references"]], "Related Information": [[89, "related-information"]], "Relative Attention Bias (RAB)": [[5, "relative-attention-bias-rab"]], "Relax Acceptance Verification": [[27, "relax-acceptance-verification"]], "Relaxed Acceptance": [[28, "relaxed-acceptance"]], "Release Notes": [[96, null]], "Reproducing Benchmarked Results": [[75, "reproducing-benchmarked-results"]], "Reproducing Steps": [[31, "reproducing-steps"]], "Reproducing steps": [[21, "reproducing-steps"], [30, "reproducing-steps"]], "Request Additional Output": [[3, "request-additional-output"]], "ResourceManager": [[100, "resourcemanager"]], "Results": [[76, "results"]], "Revisiting Paged Context Attention and Context Chunking": [[80, "revisiting-paged-context-attention-and-context-chunking"]], "Rotary Positional Embedding (RoPE)": [[5, "rotary-positional-embedding-rope"]], "RouterGEMM": [[27, "routergemm"]], "Run LLM-API with pytorch backend on Slurm": [[53, null]], "Run gpt-2b + LoRA using Executor / cpp runtime": [[10, null]], "Run the Model": [[89, "run-the-model"]], "Run trtllm-bench with pytorch backend on Slurm": [[54, null]], "Run trtllm-serve with pytorch backend on Slurm": [[55, null]], "Running Throughput and Latency Benchmarks": [[76, "running-throughput-and-latency-benchmarks"]], "Running With Weight Streaming to Reduce GPU Memory Consumption": [[14, null]], "Running multi-modal models in the PyTorch Workflow": [[74, "running-multi-modal-models-in-the-pytorch-workflow"]], "Running the Benchmark": [[75, "running-the-benchmark"]], "Running with the PyTorch Workflow": [[74, "running-with-the-pytorch-workflow"]], "Runtime": [[1, null], [17, "runtime"], [88, null]], "Runtime Configuration Examples": [[57, null]], "Runtime Customization": [[41, "runtime-customization"]], "Runtime Optimizations": [[29, "runtime-optimizations"]], "Sampling": [[41, "sampling"], [105, null]], "Sampling Parameters": [[6, "sampling-parameters"]], "Sampling Techniques Showcase": [[58, null]], "Scaling Expert Parallelism in TensorRT-LLM (Part 1: Design and Implementation of Large-scale EP)": [[30, null]], "Scaling factor(s)": [[5, "scaling-factor-s"]], "Scheduler": [[100, "scheduler"], [107, null]], "Scheduler Introduction": [[107, "scheduler-introduction"]], "Sending Requests with Different Beam Widths": [[3, "sending-requests-with-different-beam-widths"]], "Set power limits": [[74, "set-power-limits"]], "Situations that can prevent kv cache reuse": [[9, "situations-that-can-prevent-kv-cache-reuse"]], "Sliding Window Attention, Cyclic (Rolling Buffer) KV Cache": [[5, "sliding-window-attention-cyclic-rolling-buffer-kv-cache"]], "Slurm": [[46, "slurm"]], "Smart Router": [[27, "smart-router"]], "Software": [[94, "software"]], "Sparse Experts as GEMMs (only works when moe_backend=CUTLASS)": [[27, "sparse-experts-as-gemms-only-works-when-moe-backend-cutlass"]], "Speculative Decoding": [[59, null]], "Speculative Sampling": [[13, null]], "Speculative decoding arguments": [[34, "tensorrt_llm.commands.build-parse_arguments-speculative-decoding-arguments"]], "Speed up inference with SOTA quantization techniques in TRT-LLM": [[26, null]], "Starting a Server": [[35, "starting-a-server"]], "Step 1. Write Modeling Part": [[15, "step-1-write-modeling-part"]], "Step 1: Clone the repository": [[32, "step-1-clone-the-repository"]], "Step 1: Run inference and collect statistics": [[30, "step-1-run-inference-and-collect-statistics"]], "Step 2. Implement Weight Conversion": [[15, "step-2-implement-weight-conversion"]], "Step 2: Generate the EPLB configuration": [[30, "step-2-generate-the-eplb-configuration"]], "Step 2: Prepare the TensorRT-LLM release Docker image": [[32, "step-2-prepare-the-tensorrt-llm-release-docker-image"]], "Step 3. Register New Model": [[15, "step-3-register-new-model"]], "Step 3: (Optional) Tag and push the Docker image to your registry": [[32, "step-3-optional-tag-and-push-the-docker-image-to-your-registry"]], "Step 3: Run inference with the EPLB configuration": [[30, "step-3-run-inference-with-the-eplb-configuration"]], "Step 4. Verify New Model": [[15, "step-4-verify-new-model"]], "Step 4: Start the TensorRT-LLM server": [[32, "step-4-start-the-tensorrt-llm-server"]], "Step 5: Test the server with a sample request": [[32, "step-5-test-the-server-with-a-sample-request"]], "Step 6: (Optional) Monitor server logs": [[32, "step-6-optional-monitor-server-logs"]], "Step 7: (Optional) Stop the server": [[32, "step-7-optional-stop-the-server"]], "Step-by-Step Guide": [[99, "step-by-step-guide"]], "StreamingLLM": [[5, "streamingllm"]], "Structured output with guided decoding": [[3, "structured-output-with-guided-decoding"]], "Summary": [[74, "summary"]], "Summary of Configuration Option Recommendations:": [[78, "summary-of-configuration-option-recommendations"], [81, "summary-of-configuration-option-recommendations"]], "Support Matrix": [[94, null]], "Support matrix": [[93, "support-matrix"]], "Supported C++ Header Files": [[66, "supported-c-header-files"]], "Supported Quantization Modes": [[74, "supported-quantization-modes"]], "Syntax": [[35, "syntax"]], "System Level optimizations": [[27, "system-level-optimizations"]], "TRTLLM Backend": [[27, "trtllm-backend"]], "Table of Contents": [[21, "table-of-contents"], [27, "table-of-contents"], [28, "table-of-contents"], [29, "table-of-contents"], [30, "table-of-contents"], [79, "table-of-contents"], [90, "table-of-contents"], [99, "table-of-contents"]], "Technical Detail: The QuantMode Flags": [[93, "technical-detail-the-quantmode-flags"]], "Tensor Parallel vs Expert Parallel": [[4, "tensor-parallel-vs-expert-parallel"]], "Tensor-Related Methods": [[7, "tensor-related-methods"]], "TensorRT Compiler": [[17, "tensorrt-compiler"]], "TensorRT-LLM Architecture": [[19, null]], "TensorRT-LLM Benchmarking": [[74, null]], "TensorRT-LLM Build Workflow": [[20, null]], "TensorRT-LLM Checkpoint": [[16, null]], "TensorRT-LLM Model Weights Loader": [[18, null]], "TensorRT-LLM Release 0.10.0": [[96, "tensorrt-llm-release-0-10-0"]], "TensorRT-LLM Release 0.11.0": [[96, "tensorrt-llm-release-0-11-0"]], "TensorRT-LLM Release 0.12.0": [[96, "tensorrt-llm-release-0-12-0"]], "TensorRT-LLM Release 0.13.0": [[96, "tensorrt-llm-release-0-13-0"]], "TensorRT-LLM Release 0.14.0": [[96, "tensorrt-llm-release-0-14-0"]], "TensorRT-LLM Release 0.15.0": [[96, "tensorrt-llm-release-0-15-0"]], "TensorRT-LLM Release 0.16.0": [[96, "tensorrt-llm-release-0-16-0"]], "TensorRT-LLM Release 0.17.0": [[96, "tensorrt-llm-release-0-17-0"]], "TensorRT-LLM Release 0.18.0": [[96, "tensorrt-llm-release-0-18-0"]], "TensorRT-LLM Release 0.18.1": [[96, "tensorrt-llm-release-0-18-1"]], "TensorRT-LLM Release 0.18.2": [[96, "tensorrt-llm-release-0-18-2"]], "TensorRT-LLM Release 0.19.0": [[96, "tensorrt-llm-release-0-19-0"]], "TensorRT-LLM Release 0.7.1": [[96, "tensorrt-llm-release-0-7-1"]], "TensorRT-LLM Release 0.8.0": [[96, "tensorrt-llm-release-0-8-0"]], "TensorRT-LLM Release 0.9.0": [[96, "tensorrt-llm-release-0-9-0"]], "Test definitions": [[90, "test-definitions"]], "The Executor Class": [[3, "the-executor-class"]], "The Request Class": [[3, "the-request-class"]], "The Response Class": [[3, "the-response-class"]], "The Result Class": [[3, "the-result-class"]], "The effect of EP Load Balancer": [[30, "the-effect-of-ep-load-balancer"], [30, "id3"]], "Throughput Benchmarking": [[74, "throughput-benchmarking"]], "Throughput Measurements": [[75, "throughput-measurements"]], "Tips": [[95, "tips"]], "Tips and Troubleshooting": [[70, "tips-and-troubleshooting"]], "Tokenizer Customization": [[41, "tokenizer-customization"]], "Top Level API": [[100, "top-level-api"]], "Topology Requirements": [[11, "topology-requirements"]], "Tradeoff": [[103, "tradeoff"]], "Translator": [[18, "translator"]], "Tree-based speculative decoding support": [[28, "tree-based-speculative-decoding-support"]], "Triggering CI Best Practices": [[90, "triggering-ci-best-practices"]], "Triggering Post-merge tests": [[90, "triggering-post-merge-tests"]], "Triton Inference Server": [[31, "triton-inference-server"]], "Trouble shooting": [[18, "trouble-shooting"]], "Troubleshooting": [[95, null]], "Troubleshooting Tips": [[32, "troubleshooting-tips"]], "Troubleshooting Tips and Pitfalls To Avoid": [[76, "troubleshooting-tips-and-pitfalls-to-avoid"]], "Troubleshooting and FAQ": [[2, "troubleshooting-and-faq"]], "Tuning Case Study": [[80, "tuning-case-study"], [80, "id2"]], "Tuning Max Batch Size": [[80, "tuning-max-batch-size"]], "Tuning Max Batch Size and Max Num Tokens": [[80, null]], "Tuning Max Num Tokens": [[80, "tuning-max-num-tokens"]], "Types of Events": [[8, "types-of-events"]], "Understand inference time GPU memory usage": [[92, "understand-inference-time-gpu-memory-usage"]], "Understanding the TensorRT-LLM scheduler": [[80, "understanding-the-tensorrt-llm-scheduler"]], "Unit tests": [[90, "unit-tests"]], "Upload the Docker Image to DockerHub": [[36, "upload-the-docker-image-to-dockerhub"]], "Usage": [[11, "usage"], [103, "usage"]], "Useful Build-Time Flags": [[81, null]], "Useful Runtime Options": [[82, null]], "Using Dev Containers": [[91, null]], "Using Medusa with TensorRT-LLM": [[13, "using-medusa-with-tensorrt-llm"]], "Using test_to_stage_mapping.py": [[90, "using-test-to-stage-mapping-py"]], "Validated Networks for Benchmarking": [[74, "validated-networks-for-benchmarking"]], "Variables": [[75, "variables"]], "Visualize the PyTorch profiler results": [[73, "visualize-the-pytorch-profiler-results"]], "Volume Mounts": [[91, "volume-mounts"]], "WIP: Enable more features by default": [[21, "wip-enable-more-features-by-default"]], "Waiving tests": [[90, "waiving-tests"]], "Weight Bindings": [[17, "weight-bindings"]], "Weight Loading": [[99, "weight-loading"]], "Weights absorb and MQA": [[29, "weights-absorb-and-mqa"]], "Welcome to TensorRT-LLM\u2019s Documentation!": [[65, null]], "What Can You Do With TensorRT-LLM?": [[72, "what-can-you-do-with-tensorrt-llm"]], "What Triggers an Event?": [[8, "what-triggers-an-event"]], "What is H100 FP8?": [[23, "what-is-h100-fp8"]], "What\u2019s coming next": [[26, "whats-coming-next"]], "When to Use Graph Rewriting?": [[7, "when-to-use-graph-rewriting"]], "WindowBlockManager/BlockManager": [[8, "windowblockmanager-blockmanager"]], "Workflow": [[18, "workflow"], [74, "workflow"], [97, "workflow"]], "Workload Profile": [[27, "workload-profile"]], "World Configuration": [[6, "world-configuration"]], "XQA Optimization": [[5, "xqa-optimization"]], "bufferManager.h": [[1, "buffermanager-h"]], "build": [[33, "trtllm-bench-build"]], "cacheCommunicator.h": [[0, "cachecommunicator-h"]], "common.h": [[1, "common-h"]], "cudaEvent.h": [[1, "cudaevent-h"]], "cudaStream.h": [[1, "cudastream-h"]], "dataTransceiverState.h": [[0, "datatransceiverstate-h"]], "dataset": [[33, "dataset"]], "decoderState.h": [[1, "decoderstate-h"]], "decodingInput.h": [[1, "decodinginput-h"]], "decodingOutput.h": [[1, "decodingoutput-h"]], "disaggServerUtil.h": [[0, "disaggserverutil-h"]], "disaggr_torch.slurm": [[97, "disaggr-torch-slurm"]], "disaggregated": [[35, "trtllm-serve-disaggregated"]], "disaggregated_mpi_worker": [[35, "trtllm-serve-disaggregated-mpi-worker"]], "eagleBuffers.h": [[1, "eaglebuffers-h"]], "eagleModule.h": [[1, "eaglemodule-h"]], "executor.h": [[0, "executor-h"]], "explicitDraftTokensBuffers.h": [[1, "explicitdrafttokensbuffers-h"]], "gen_yaml.py": [[97, "gen-yaml-py"]], "gptDecoder.h": [[1, "gptdecoder-h"]], "gptDecoderBatched.h": [[1, "gptdecoderbatched-h"]], "gptJsonConfig.h": [[1, "gptjsonconfig-h"]], "iBuffer.h": [[1, "ibuffer-h"]], "iGptDecoderBatched.h": [[1, "igptdecoderbatched-h"]], "iTensor.h": [[1, "itensor-h"]], "ipcNvlsMemory.h": [[1, "ipcnvlsmemory-h"]], "ipcUtils.h": [[1, "ipcutils-h"]], "latency": [[33, "trtllm-bench-latency"]], "lookaheadBuffers.h": [[1, "lookaheadbuffers-h"]], "lookaheadModule.h": [[1, "lookaheadmodule-h"]], "loraCache.h": [[1, "loracache-h"]], "loraCachePageManagerConfig.h": [[1, "loracachepagemanagerconfig-h"]], "loraModule.h": [[1, "loramodule-h"]], "medusaModule.h": [[1, "medusamodule-h"]], "memoryCounters.h": [[1, "memorycounters-h"]], "modelConfig.h": [[1, "modelconfig-h"]], "prepare_dataset": [[33, "prepare-dataset"]], "prepare_dataset.py": [[33, "prepare-dataset-py"]], "promptTuningParams.h": [[1, "prompttuningparams-h"]], "rawEngine.h": [[1, "rawengine-h"]], "request.h": [[1, "request-h"]], "run_benchmark.sh": [[97, "run-benchmark-sh"]], "runtimeDefaults.h": [[1, "runtimedefaults-h"]], "samplingConfig.h": [[1, "samplingconfig-h"]], "serialization.h": [[0, "serialization-h"]], "serve": [[35, "trtllm-serve-serve"]], "speculativeDecodingMode.h": [[1, "speculativedecodingmode-h"]], "speculativeDecodingModule.h": [[1, "speculativedecodingmodule-h"]], "start_worker.sh": [[97, "start-worker-sh"]], "submit.sh": [[97, "submit-sh"]], "tensor.h": [[0, "tensor-h"]], "throughput": [[33, "trtllm-bench-throughput"]], "tllmLogger.h": [[1, "tllmlogger-h"]], "token_norm_dist": [[33, "token-norm-dist"]], "token_unif_dist": [[33, "token-unif-dist"]], "transferAgent.h": [[0, "transferagent-h"]], "trtllm-bench": [[33, null], [33, "trtllm-bench"]], "trtllm-build": [[34, null]], "trtllm-serve": [[31, "trtllm-serve"], [35, null], [35, "trtllm-serve"]], "types.h": [[0, "types-h"]], "worldConfig.h": [[1, "worldconfig-h"]]}, "docnames": ["_cpp_gen/executor", "_cpp_gen/runtime", "advanced/disaggregated-service", "advanced/executor", "advanced/expert-parallelism", "advanced/gpt-attention", "advanced/gpt-runtime", "advanced/graph-rewriting", "advanced/kv-cache-management", "advanced/kv-cache-reuse", "advanced/lora", "advanced/lowprecision-pcie-allreduce", "advanced/open-sourced-cutlass-kernels", "advanced/speculative-decoding", "advanced/weight-streaming", "architecture/add-model", "architecture/checkpoint", "architecture/core-concepts", "architecture/model-weights-loader", "architecture/overview", "architecture/workflow", "blogs/Best_perf_practice_on_DeepSeek-R1_in_TensorRT-LLM", "blogs/Falcon180B-H200", "blogs/H100vsA100", "blogs/H200launch", "blogs/XQA-kernel", "blogs/quantization-in-TRT-LLM", "blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs", "blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization", "blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs", "blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM", "blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM", "blogs/tech_blog/blog6_Llama4_maverick_eagle_guide", "commands/trtllm-bench", "commands/trtllm-build", "commands/trtllm-serve", "dev-on-cloud/build-image-to-dockerhub", "dev-on-cloud/dev-on-runpod", "examples/curl_chat_client", "examples/curl_chat_client_for_multimodal", "examples/curl_completion_client", "examples/customization", "examples/deepseek_r1_reasoning_parser", "examples/genai_perf_client", "examples/genai_perf_client_for_multimodal", "examples/index", "examples/llm_api_examples", "examples/llm_guided_decoding", "examples/llm_inference", "examples/llm_inference_async", "examples/llm_inference_async_streaming", "examples/llm_inference_distributed", "examples/llm_logits_processor", "examples/llm_mgmn_llm_distributed", "examples/llm_mgmn_trtllm_bench", "examples/llm_mgmn_trtllm_serve", "examples/llm_multilora", "examples/llm_runtime", "examples/llm_sampling", "examples/llm_speculative_decoding", "examples/openai_chat_client", "examples/openai_chat_client_for_multimodal", "examples/openai_completion_client", "examples/openai_completion_client_for_lora", "examples/trtllm_serve_examples", "index", "installation/build-from-source-linux", "installation/containers", "installation/linux", "key-features", "llm-api/index", "llm-api/reference", "overview", "performance/perf-analysis", "performance/perf-benchmarking", "performance/perf-overview", "performance/performance-tuning-guide/benchmarking-default-performance", "performance/performance-tuning-guide/deciding-model-sharding-strategy", "performance/performance-tuning-guide/fp8-quantization", "performance/performance-tuning-guide/index", "performance/performance-tuning-guide/tuning-max-batch-size-and-max-num-tokens", "performance/performance-tuning-guide/useful-build-time-flags", "performance/performance-tuning-guide/useful-runtime-flags", "python-api/tensorrt_llm.functional", "python-api/tensorrt_llm.layers", "python-api/tensorrt_llm.models", "python-api/tensorrt_llm.plugin", "python-api/tensorrt_llm.quantization", "python-api/tensorrt_llm.runtime", "quick-start-guide", "reference/ci-overview", "reference/dev-containers", "reference/memory", "reference/precision", "reference/support-matrix", "reference/troubleshooting", "release-notes", "scripts/disaggregated/README", "torch", "torch/adding_new_model", "torch/arch_overview", "torch/attention", "torch/features/feature_combination_matrix", "torch/features/overlap_scheduler", "torch/features/quantization", "torch/features/sampling", "torch/kv_cache_manager", "torch/scheduler"], "envversion": {"sphinx": 62, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.todo": 2, "sphinx.ext.viewcode": 1}, "filenames": ["_cpp_gen/executor.rst", "_cpp_gen/runtime.rst", "advanced/disaggregated-service.md", "advanced/executor.md", "advanced/expert-parallelism.md", "advanced/gpt-attention.md", "advanced/gpt-runtime.md", "advanced/graph-rewriting.md", "advanced/kv-cache-management.md", "advanced/kv-cache-reuse.md", "advanced/lora.md", "advanced/lowprecision-pcie-allreduce.md", "advanced/open-sourced-cutlass-kernels.md", "advanced/speculative-decoding.md", "advanced/weight-streaming.md", "architecture/add-model.md", "architecture/checkpoint.md", "architecture/core-concepts.md", "architecture/model-weights-loader.md", "architecture/overview.md", "architecture/workflow.md", "blogs/Best_perf_practice_on_DeepSeek-R1_in_TensorRT-LLM.md", "blogs/Falcon180B-H200.md", "blogs/H100vsA100.md", "blogs/H200launch.md", "blogs/XQA-kernel.md", "blogs/quantization-in-TRT-LLM.md", "blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.md", "blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.md", "blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.md", "blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.md", "blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.md", "blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.md", "commands/trtllm-bench.rst", "commands/trtllm-build.rst", "commands/trtllm-serve.rst", "dev-on-cloud/build-image-to-dockerhub.md", "dev-on-cloud/dev-on-runpod.md", "examples/curl_chat_client.rst", "examples/curl_chat_client_for_multimodal.rst", "examples/curl_completion_client.rst", "examples/customization.md", "examples/deepseek_r1_reasoning_parser.rst", "examples/genai_perf_client.rst", "examples/genai_perf_client_for_multimodal.rst", "examples/index.rst", "examples/llm_api_examples.rst", "examples/llm_guided_decoding.rst", "examples/llm_inference.rst", "examples/llm_inference_async.rst", "examples/llm_inference_async_streaming.rst", "examples/llm_inference_distributed.rst", "examples/llm_logits_processor.rst", "examples/llm_mgmn_llm_distributed.rst", "examples/llm_mgmn_trtllm_bench.rst", "examples/llm_mgmn_trtllm_serve.rst", "examples/llm_multilora.rst", "examples/llm_runtime.rst", "examples/llm_sampling.rst", "examples/llm_speculative_decoding.rst", "examples/openai_chat_client.rst", "examples/openai_chat_client_for_multimodal.rst", "examples/openai_completion_client.rst", "examples/openai_completion_client_for_lora.rst", "examples/trtllm_serve_examples.rst", "index.rst", "installation/build-from-source-linux.md", "installation/containers.md", "installation/linux.md", "key-features.md", "llm-api/index.md", "llm-api/reference.rst", "overview.md", "performance/perf-analysis.md", "performance/perf-benchmarking.md", "performance/perf-overview.md", "performance/performance-tuning-guide/benchmarking-default-performance.md", "performance/performance-tuning-guide/deciding-model-sharding-strategy.md", "performance/performance-tuning-guide/fp8-quantization.md", "performance/performance-tuning-guide/index.rst", "performance/performance-tuning-guide/tuning-max-batch-size-and-max-num-tokens.md", "performance/performance-tuning-guide/useful-build-time-flags.md", "performance/performance-tuning-guide/useful-runtime-flags.md", "python-api/tensorrt_llm.functional.rst", "python-api/tensorrt_llm.layers.rst", "python-api/tensorrt_llm.models.rst", "python-api/tensorrt_llm.plugin.rst", "python-api/tensorrt_llm.quantization.rst", "python-api/tensorrt_llm.runtime.rst", "quick-start-guide.md", "reference/ci-overview.md", "reference/dev-containers.md", "reference/memory.md", "reference/precision.md", "reference/support-matrix.md", "reference/troubleshooting.md", "release-notes.md", "scripts/disaggregated/README.md", "torch.md", "torch/adding_new_model.md", "torch/arch_overview.md", "torch/attention.md", "torch/features/feature_combination_matrix.md", "torch/features/overlap_scheduler.md", "torch/features/quantization.md", "torch/features/sampling.md", "torch/kv_cache_manager.md", "torch/scheduler.md"], "indexentries": {"--backend": [[33, "cmdoption-trtllm-bench-latency-backend", false], [33, "cmdoption-trtllm-bench-throughput-backend", false], [35, "cmdoption-trtllm-serve-serve-backend", false]], "--beam_width": [[33, "cmdoption-trtllm-bench-latency-beam_width", false], [33, "cmdoption-trtllm-bench-throughput-beam_width", false]], "--cluster_size": [[33, "cmdoption-trtllm-bench-throughput-cluster_size", false], [35, "cmdoption-trtllm-serve-serve-cluster_size", false]], "--concurrency": [[33, "cmdoption-trtllm-bench-latency-concurrency", false], [33, "cmdoption-trtllm-bench-throughput-concurrency", false]], "--config_file": [[35, "cmdoption-trtllm-serve-disaggregated-c", false], [35, "cmdoption-trtllm-serve-disaggregated_mpi_worker-c", false]], "--dataset": [[33, "cmdoption-trtllm-bench-build-dataset", false], [33, "cmdoption-trtllm-bench-latency-dataset", false], [33, "cmdoption-trtllm-bench-throughput-dataset", false]], "--enable_chunked_context": [[33, "cmdoption-trtllm-bench-throughput-enable_chunked_context", false]], "--engine_dir": [[33, "cmdoption-trtllm-bench-latency-engine_dir", false], [33, "cmdoption-trtllm-bench-throughput-engine_dir", false]], "--eos_id": [[33, "cmdoption-trtllm-bench-throughput-eos_id", false]], "--ep": [[33, "cmdoption-trtllm-bench-latency-ep", false], [33, "cmdoption-trtllm-bench-throughput-ep", false]], "--ep_size": [[35, "cmdoption-trtllm-serve-serve-ep_size", false]], "--extra_llm_api_options": [[33, "cmdoption-trtllm-bench-throughput-extra_llm_api_options", false], [35, "cmdoption-trtllm-serve-serve-extra_llm_api_options", false]], "--gpus_per_node": [[35, "cmdoption-trtllm-serve-serve-gpus_per_node", false]], "--host": [[35, "cmdoption-trtllm-serve-serve-host", false]], "--iteration_log": [[33, "cmdoption-trtllm-bench-latency-iteration_log", false], [33, "cmdoption-trtllm-bench-throughput-iteration_log", false]], "--kv_cache_free_gpu_mem_fraction": [[33, "cmdoption-trtllm-bench-latency-kv_cache_free_gpu_mem_fraction", false], [33, "cmdoption-trtllm-bench-throughput-kv_cache_free_gpu_mem_fraction", false]], "--kv_cache_free_gpu_memory_fraction": [[35, "cmdoption-trtllm-serve-serve-kv_cache_free_gpu_memory_fraction", false]], "--log_level": [[33, "cmdoption-trtllm-bench-log_level", false], [35, "cmdoption-trtllm-serve-disaggregated-l", false], [35, "cmdoption-trtllm-serve-disaggregated_mpi_worker-log_level", false], [35, "cmdoption-trtllm-serve-serve-log_level", false]], "--max_batch_size": [[33, "cmdoption-trtllm-bench-build-max_batch_size", false], [33, "cmdoption-trtllm-bench-throughput-max_batch_size", false], [35, "cmdoption-trtllm-serve-serve-max_batch_size", false]], "--max_beam_width": [[35, "cmdoption-trtllm-serve-serve-max_beam_width", false]], "--max_input_len": [[33, "cmdoption-trtllm-bench-latency-max_input_len", false], [33, "cmdoption-trtllm-bench-throughput-max_input_len", false]], "--max_num_tokens": [[33, "cmdoption-trtllm-bench-build-max_num_tokens", false], [33, "cmdoption-trtllm-bench-throughput-max_num_tokens", false], [35, "cmdoption-trtllm-serve-serve-max_num_tokens", false]], "--max_seq_len": [[33, "cmdoption-trtllm-bench-build-max_seq_len", false], [33, "cmdoption-trtllm-bench-latency-max_seq_len", false], [33, "cmdoption-trtllm-bench-throughput-max_seq_len", false], [35, "cmdoption-trtllm-serve-serve-max_seq_len", false]], "--medusa_choices": [[33, "cmdoption-trtllm-bench-latency-medusa_choices", false]], "--metadata_server_config_file": [[35, "cmdoption-trtllm-serve-disaggregated-m", false], [35, "cmdoption-trtllm-serve-serve-metadata_server_config_file", false]], "--modality": [[33, "cmdoption-trtllm-bench-latency-modality", false], [33, "cmdoption-trtllm-bench-throughput-modality", false]], "--model": [[33, "cmdoption-trtllm-bench-m", false]], "--model_path": [[33, "cmdoption-trtllm-bench-model_path", false]], "--no_weights_loading": [[33, "cmdoption-trtllm-bench-build-no_weights_loading", false]], "--num_postprocess_workers": [[35, "cmdoption-trtllm-serve-serve-num_postprocess_workers", false]], "--num_requests": [[33, "cmdoption-trtllm-bench-latency-num_requests", false], [33, "cmdoption-trtllm-bench-throughput-num_requests", false]], "--output_json": [[33, "cmdoption-trtllm-bench-throughput-output_json", false]], "--port": [[35, "cmdoption-trtllm-serve-serve-port", false]], "--pp": [[33, "cmdoption-trtllm-bench-latency-pp", false], [33, "cmdoption-trtllm-bench-throughput-pp", false]], "--pp_size": [[33, "cmdoption-trtllm-bench-build-pp", false], [35, "cmdoption-trtllm-serve-serve-pp_size", false]], "--quantization": [[33, "cmdoption-trtllm-bench-build-q", false]], "--reasoning_parser": [[35, "cmdoption-trtllm-serve-serve-reasoning_parser", false]], "--report_json": [[33, "cmdoption-trtllm-bench-latency-report_json", false], [33, "cmdoption-trtllm-bench-throughput-report_json", false]], "--request_json": [[33, "cmdoption-trtllm-bench-throughput-request_json", false]], "--request_timeout": [[35, "cmdoption-trtllm-serve-disaggregated-r", false]], "--scheduler_policy": [[33, "cmdoption-trtllm-bench-throughput-scheduler_policy", false]], "--server_role": [[35, "cmdoption-trtllm-serve-serve-server_role", false]], "--server_start_timeout": [[35, "cmdoption-trtllm-serve-disaggregated-t", false]], "--streaming": [[33, "cmdoption-trtllm-bench-throughput-streaming", false]], "--target_input_len": [[33, "cmdoption-trtllm-bench-build-target_input_len", false], [33, "cmdoption-trtllm-bench-throughput-target_input_len", false]], "--target_output_len": [[33, "cmdoption-trtllm-bench-build-target_output_len", false], [33, "cmdoption-trtllm-bench-throughput-target_output_len", false]], "--tokenizer": [[35, "cmdoption-trtllm-serve-serve-tokenizer", false]], "--tp": [[33, "cmdoption-trtllm-bench-latency-tp", false], [33, "cmdoption-trtllm-bench-throughput-tp", false]], "--tp_size": [[33, "cmdoption-trtllm-bench-build-tp", false], [35, "cmdoption-trtllm-serve-serve-tp_size", false]], "--trust_remote_code": [[33, "cmdoption-trtllm-bench-build-trust_remote_code", false], [35, "cmdoption-trtllm-serve-serve-trust_remote_code", false]], "--warmup": [[33, "cmdoption-trtllm-bench-latency-warmup", false], [33, "cmdoption-trtllm-bench-throughput-warmup", false]], "--workspace": [[33, "cmdoption-trtllm-bench-w", false]], "-c": [[35, "cmdoption-trtllm-serve-disaggregated-c", false], [35, "cmdoption-trtllm-serve-disaggregated_mpi_worker-c", false]], "-l": [[35, "cmdoption-trtllm-serve-disaggregated-l", false]], "-m": [[33, "cmdoption-trtllm-bench-m", false], [35, "cmdoption-trtllm-serve-disaggregated-m", false]], "-pp": [[33, "cmdoption-trtllm-bench-build-pp", false]], "-q": [[33, "cmdoption-trtllm-bench-build-q", false]], "-r": [[35, "cmdoption-trtllm-serve-disaggregated-r", false]], "-t": [[35, "cmdoption-trtllm-serve-disaggregated-t", false]], "-tp": [[33, "cmdoption-trtllm-bench-build-tp", false]], "-w": [[33, "cmdoption-trtllm-bench-w", false]], "__init__() (tensorrt_llm.llmapi.buildcacheconfig method)": [[71, "tensorrt_llm.llmapi.BuildCacheConfig.__init__", false]], "__init__() (tensorrt_llm.llmapi.buildconfig method)": [[71, "tensorrt_llm.llmapi.BuildConfig.__init__", false]], "__init__() (tensorrt_llm.llmapi.completionoutput method)": [[71, "tensorrt_llm.llmapi.CompletionOutput.__init__", false]], "__init__() (tensorrt_llm.llmapi.disaggregatedparams method)": [[71, "tensorrt_llm.llmapi.DisaggregatedParams.__init__", false]], "__init__() (tensorrt_llm.llmapi.guideddecodingparams method)": [[71, "tensorrt_llm.llmapi.GuidedDecodingParams.__init__", false]], "__init__() (tensorrt_llm.llmapi.kvcacheretentionconfig method)": [[71, "tensorrt_llm.llmapi.KvCacheRetentionConfig.__init__", false]], "__init__() (tensorrt_llm.llmapi.kvcacheretentionconfig.tokenrangeretentionconfig method)": [[71, "tensorrt_llm.llmapi.KvCacheRetentionConfig.TokenRangeRetentionConfig.__init__", false]], "__init__() (tensorrt_llm.llmapi.lookaheaddecodingconfig method)": [[71, "tensorrt_llm.llmapi.LookaheadDecodingConfig.__init__", false]], "__init__() (tensorrt_llm.llmapi.mpicommsession method)": [[71, "tensorrt_llm.llmapi.MpiCommSession.__init__", false]], "__init__() (tensorrt_llm.llmapi.quantconfig method)": [[71, "tensorrt_llm.llmapi.QuantConfig.__init__", false]], "__init__() (tensorrt_llm.llmapi.requestoutput method)": [[71, "tensorrt_llm.llmapi.RequestOutput.__init__", false]], "__init__() (tensorrt_llm.llmapi.samplingparams method)": [[71, "tensorrt_llm.llmapi.SamplingParams.__init__", false]], "abort() (tensorrt_llm.llmapi.mpicommsession method)": [[71, "tensorrt_llm.llmapi.MpiCommSession.abort", false]], "abs() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.abs", false]], "abs() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.abs", false]], "activation() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.activation", false]], "adalayernorm (class in tensorrt_llm.layers.normalization)": [[84, "tensorrt_llm.layers.normalization.AdaLayerNorm", false]], "adalayernormcontinuous (class in tensorrt_llm.layers.normalization)": [[84, "tensorrt_llm.layers.normalization.AdaLayerNormContinuous", false]], "adalayernormzero (class in tensorrt_llm.layers.normalization)": [[84, "tensorrt_llm.layers.normalization.AdaLayerNormZero", false]], "adalayernormzerosingle (class in tensorrt_llm.layers.normalization)": [[84, "tensorrt_llm.layers.normalization.AdaLayerNormZeroSingle", false]], "add() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.add", false]], "add_input() (tensorrt_llm.functional.conditional method)": [[83, "tensorrt_llm.functional.Conditional.add_input", false]], "add_output() (tensorrt_llm.functional.conditional method)": [[83, "tensorrt_llm.functional.Conditional.add_output", false]], "add_sequence() (tensorrt_llm.runtime.kvcachemanager method)": [[88, "tensorrt_llm.runtime.KVCacheManager.add_sequence", false]], "add_special_tokens (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.add_special_tokens", false]], "additional_model_outputs (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.additional_model_outputs", false]], "alibi (tensorrt_llm.functional.positionembeddingtype attribute)": [[83, "tensorrt_llm.functional.PositionEmbeddingType.alibi", false]], "alibi_with_scale (tensorrt_llm.functional.positionembeddingtype attribute)": [[83, "tensorrt_llm.functional.PositionEmbeddingType.alibi_with_scale", false]], "allgather() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.allgather", false]], "allreduce() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.allreduce", false]], "allreduce_strategy (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.allreduce_strategy", false]], "allreducefusionop (class in tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.AllReduceFusionOp", false]], "allreduceparams (class in tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.AllReduceParams", false]], "allreducestrategy (class in tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.AllReduceStrategy", false]], "apply_batched_logits_processor (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.apply_batched_logits_processor", false]], "apply_llama3_scaling() (tensorrt_llm.functional.ropeembeddingutils static method)": [[83, "tensorrt_llm.functional.RopeEmbeddingUtils.apply_llama3_scaling", false]], "apply_rotary_pos_emb() (tensorrt_llm.functional.ropeembeddingutils static method)": [[83, "tensorrt_llm.functional.RopeEmbeddingUtils.apply_rotary_pos_emb", false]], "apply_rotary_pos_emb_chatglm() (tensorrt_llm.functional.ropeembeddingutils static method)": [[83, "tensorrt_llm.functional.RopeEmbeddingUtils.apply_rotary_pos_emb_chatglm", false]], "apply_rotary_pos_emb_cogvlm() (tensorrt_llm.functional.ropeembeddingutils static method)": [[83, "tensorrt_llm.functional.RopeEmbeddingUtils.apply_rotary_pos_emb_cogvlm", false]], "arange() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.arange", false]], "argmax() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.argmax", false]], "assert_valid_quant_algo() (tensorrt_llm.models.gemmaforcausallm class method)": [[85, "tensorrt_llm.models.GemmaForCausalLM.assert_valid_quant_algo", false]], "assertion() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.assertion", false]], "attention (class in tensorrt_llm.layers.attention)": [[84, "tensorrt_llm.layers.attention.Attention", false]], "attentionmaskparams (class in tensorrt_llm.layers.attention)": [[84, "tensorrt_llm.layers.attention.AttentionMaskParams", false]], "attentionmasktype (class in tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.AttentionMaskType", false]], "attentionparams (class in tensorrt_llm.layers.attention)": [[84, "tensorrt_llm.layers.attention.AttentionParams", false]], "attn_backend (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.attn_backend", false]], "attn_processors (tensorrt_llm.models.sd3transformer2dmodel property)": [[85, "tensorrt_llm.models.SD3Transformer2DModel.attn_processors", false]], "audio_engine_dir (tensorrt_llm.runtime.multimodalmodelrunner property)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.audio_engine_dir", false]], "auto (tensorrt_llm.functional.allreducestrategy attribute)": [[83, "tensorrt_llm.functional.AllReduceStrategy.AUTO", false]], "auto_parallel (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.auto_parallel", false]], "auto_parallel_config (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.auto_parallel_config", false]], "auto_parallel_config (tensorrt_llm.llmapi.trtllmargs property)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.auto_parallel_config", false]], "auto_parallel_world_size (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.auto_parallel_world_size", false]], "avg_pool2d() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.avg_pool2d", false]], "avgpool2d (class in tensorrt_llm.layers.pooling)": [[84, "tensorrt_llm.layers.pooling.AvgPool2d", false]], "axes (tensorrt_llm.functional.sliceinputtype attribute)": [[83, "tensorrt_llm.functional.SliceInputType.axes", false]], "backend (tensorrt_llm.llmapi.cachetransceiverconfig attribute)": [[71, "tensorrt_llm.llmapi.CacheTransceiverConfig.backend", false]], "backend (tensorrt_llm.llmapi.moeconfig attribute)": [[71, "tensorrt_llm.llmapi.MoeConfig.backend", false]], "bad (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.bad", false]], "bad_token_ids (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.bad_token_ids", false]], "bad_words_list (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.bad_words_list", false]], "baichuanforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.BaichuanForCausalLM", false]], "batch_size (tensorrt_llm.runtime.generationsession attribute)": [[88, "tensorrt_llm.runtime.GenerationSession.batch_size", false]], "batch_sizes (tensorrt_llm.llmapi.cudagraphconfig attribute)": [[71, "tensorrt_llm.llmapi.CudaGraphConfig.batch_sizes", false]], "batchingtype (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.BatchingType", false]], "beam_search_diversity_rate (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.beam_search_diversity_rate", false]], "beam_search_diversity_rate (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.beam_search_diversity_rate", false]], "beam_width_array (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.beam_width_array", false]], "begin_thinking_phase_token (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.MTPDecodingConfig.BEGIN_THINKING_PHASE_TOKEN", false]], "bert_attention() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.bert_attention", false]], "bertattention (class in tensorrt_llm.layers.attention)": [[84, "tensorrt_llm.layers.attention.BertAttention", false]], "bertforquestionanswering (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.BertForQuestionAnswering", false]], "bertforsequenceclassification (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.BertForSequenceClassification", false]], "bertmodel (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.BertModel", false]], "best_of (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.best_of", false]], "bidirectional (tensorrt_llm.functional.attentionmasktype attribute)": [[83, "tensorrt_llm.functional.AttentionMaskType.bidirectional", false]], "bidirectionalglm (tensorrt_llm.functional.attentionmasktype attribute)": [[83, "tensorrt_llm.functional.AttentionMaskType.bidirectionalglm", false]], "blocksparse (tensorrt_llm.functional.attentionmasktype attribute)": [[83, "tensorrt_llm.functional.AttentionMaskType.blocksparse", false]], "blocksparseattnparams (class in tensorrt_llm.layers.attention)": [[84, "tensorrt_llm.layers.attention.BlockSparseAttnParams", false]], "bloomforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.BloomForCausalLM", false]], "bloommodel (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.BloomModel", false]], "broadcast_helper() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.broadcast_helper", false]], "buffer_allocated (tensorrt_llm.runtime.generationsession attribute)": [[88, "tensorrt_llm.runtime.GenerationSession.buffer_allocated", false]], "build_config (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.build_config", false]], "build_config (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.build_config", false]], "buildcacheconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.BuildCacheConfig", false]], "buildconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.BuildConfig", false]], "cache_root (tensorrt_llm.llmapi.buildcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildCacheConfig.cache_root", false]], "cache_root (tensorrt_llm.llmapi.buildcacheconfig property)": [[71, "id7", false]], "cachetransceiverconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.CacheTransceiverConfig", false]], "calculate_speculative_resource() (tensorrt_llm.llmapi.lookaheaddecodingconfig method)": [[71, "tensorrt_llm.llmapi.LookaheadDecodingConfig.calculate_speculative_resource", false]], "calib_batch_size (tensorrt_llm.llmapi.calibconfig attribute)": [[71, "tensorrt_llm.llmapi.CalibConfig.calib_batch_size", false]], "calib_batches (tensorrt_llm.llmapi.calibconfig attribute)": [[71, "tensorrt_llm.llmapi.CalibConfig.calib_batches", false]], "calib_config (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.calib_config", false]], "calib_dataset (tensorrt_llm.llmapi.calibconfig attribute)": [[71, "tensorrt_llm.llmapi.CalibConfig.calib_dataset", false]], "calib_max_seq_length (tensorrt_llm.llmapi.calibconfig attribute)": [[71, "tensorrt_llm.llmapi.CalibConfig.calib_max_seq_length", false]], "calibconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.CalibConfig", false]], "capacity_scheduler_policy (tensorrt_llm.llmapi.schedulerconfig attribute)": [[71, "tensorrt_llm.llmapi.SchedulerConfig.capacity_scheduler_policy", false]], "capacityschedulerpolicy (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.CapacitySchedulerPolicy", false]], "cast (class in tensorrt_llm.layers.cast)": [[84, "tensorrt_llm.layers.cast.Cast", false]], "cast() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.cast", false]], "cast() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.cast", false]], "categorical_sample() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.categorical_sample", false]], "causal (tensorrt_llm.functional.attentionmasktype attribute)": [[83, "tensorrt_llm.functional.AttentionMaskType.causal", false]], "chatglm (tensorrt_llm.functional.positionembeddingtype attribute)": [[83, "tensorrt_llm.functional.PositionEmbeddingType.chatglm", false]], "chatglmconfig (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.ChatGLMConfig", false]], "chatglmforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.ChatGLMForCausalLM", false]], "chatglmgenerationsession (class in tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.ChatGLMGenerationSession", false]], "chatglmmodel (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.ChatGLMModel", false]], "check_config() (tensorrt_llm.models.decodermodel method)": [[85, "tensorrt_llm.models.DecoderModel.check_config", false]], "check_config() (tensorrt_llm.models.dit method)": [[85, "tensorrt_llm.models.DiT.check_config", false]], "check_config() (tensorrt_llm.models.encodermodel method)": [[85, "tensorrt_llm.models.EncoderModel.check_config", false]], "check_config() (tensorrt_llm.models.falconforcausallm method)": [[85, "tensorrt_llm.models.FalconForCausalLM.check_config", false]], "check_config() (tensorrt_llm.models.mptforcausallm method)": [[85, "tensorrt_llm.models.MPTForCausalLM.check_config", false]], "check_config() (tensorrt_llm.models.optforcausallm method)": [[85, "tensorrt_llm.models.OPTForCausalLM.check_config", false]], "check_config() (tensorrt_llm.models.phiforcausallm method)": [[85, "tensorrt_llm.models.PhiForCausalLM.check_config", false]], "check_config() (tensorrt_llm.models.pretrainedmodel method)": [[85, "tensorrt_llm.models.PretrainedModel.check_config", false]], "checkpoint_format (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.checkpoint_format", false]], "checkpoint_loader (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.checkpoint_loader", false]], "choices() (tensorrt_llm.functional.positionembeddingtype static method)": [[83, "tensorrt_llm.functional.PositionEmbeddingType.choices", false]], "chunk() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.chunk", false]], "clamp_val (tensorrt_llm.llmapi.quantconfig attribute)": [[71, "tensorrt_llm.llmapi.QuantConfig.clamp_val", false]], "clip() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.clip", false]], "clipvisiontransformer (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.CLIPVisionTransformer", false]], "cogvlmattention (class in tensorrt_llm.layers.attention)": [[84, "tensorrt_llm.layers.attention.CogVLMAttention", false]], "cogvlmconfig (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.CogVLMConfig", false]], "cogvlmforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.CogVLMForCausalLM", false]], "cohereforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.CohereForCausalLM", false]], "collect_and_bias() (tensorrt_llm.layers.linear.linear method)": [[84, "tensorrt_llm.layers.linear.Linear.collect_and_bias", false]], "collect_and_bias() (tensorrt_llm.layers.linear.linearbase method)": [[84, "tensorrt_llm.layers.linear.LinearBase.collect_and_bias", false]], "collect_and_bias() (tensorrt_llm.layers.linear.rowlinear method)": [[84, "tensorrt_llm.layers.linear.RowLinear.collect_and_bias", false]], "columnlinear (in module tensorrt_llm.layers.linear)": [[84, "tensorrt_llm.layers.linear.ColumnLinear", false]], "combinedtimesteplabelembeddings (class in tensorrt_llm.layers.embedding)": [[84, "tensorrt_llm.layers.embedding.CombinedTimestepLabelEmbeddings", false]], "combinedtimesteptextprojembeddings (class in tensorrt_llm.layers.embedding)": [[84, "tensorrt_llm.layers.embedding.CombinedTimestepTextProjEmbeddings", false]], "completionoutput (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.CompletionOutput", false]], "compute_relative_bias() (in module tensorrt_llm.layers.attention)": [[84, "tensorrt_llm.layers.attention.compute_relative_bias", false]], "concat() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.concat", false]], "conditional (class in tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.Conditional", false]], "config_class (tensorrt_llm.models.baichuanforcausallm attribute)": [[85, "tensorrt_llm.models.BaichuanForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.chatglmforcausallm attribute)": [[85, "tensorrt_llm.models.ChatGLMForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.cogvlmforcausallm attribute)": [[85, "tensorrt_llm.models.CogVLMForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.cohereforcausallm attribute)": [[85, "tensorrt_llm.models.CohereForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.dbrxforcausallm attribute)": [[85, "tensorrt_llm.models.DbrxForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.deepseekforcausallm attribute)": [[85, "tensorrt_llm.models.DeepseekForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.deepseekv2forcausallm attribute)": [[85, "tensorrt_llm.models.DeepseekV2ForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.eagleforcausallm attribute)": [[85, "tensorrt_llm.models.EagleForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.falconforcausallm attribute)": [[85, "tensorrt_llm.models.FalconForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.gemmaforcausallm attribute)": [[85, "tensorrt_llm.models.GemmaForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.gptforcausallm attribute)": [[85, "tensorrt_llm.models.GPTForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.gptjforcausallm attribute)": [[85, "tensorrt_llm.models.GPTJForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.llamaforcausallm attribute)": [[85, "tensorrt_llm.models.LLaMAForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.mambaforcausallm attribute)": [[85, "tensorrt_llm.models.MambaForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.medusaforcausallm attribute)": [[85, "tensorrt_llm.models.MedusaForCausalLm.config_class", false]], "config_class (tensorrt_llm.models.mllamaforcausallm attribute)": [[85, "tensorrt_llm.models.MLLaMAForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.phi3forcausallm attribute)": [[85, "tensorrt_llm.models.Phi3ForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.phiforcausallm attribute)": [[85, "tensorrt_llm.models.PhiForCausalLM.config_class", false]], "config_class (tensorrt_llm.models.sd3transformer2dmodel attribute)": [[85, "tensorrt_llm.models.SD3Transformer2DModel.config_class", false]], "constant() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.constant", false]], "constant_to_tensor_() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.constant_to_tensor_", false]], "constants_to_tensors_() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.constants_to_tensors_", false]], "context (tensorrt_llm.runtime.session property)": [[88, "tensorrt_llm.runtime.Session.context", false]], "context_chunking_policy (tensorrt_llm.llmapi.schedulerconfig attribute)": [[71, "tensorrt_llm.llmapi.SchedulerConfig.context_chunking_policy", false]], "context_logits (tensorrt_llm.llmapi.requestoutput attribute)": [[71, "tensorrt_llm.llmapi.RequestOutput.context_logits", false]], "context_mem_size (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.context_mem_size", false]], "context_mem_size (tensorrt_llm.runtime.session property)": [[88, "tensorrt_llm.runtime.Session.context_mem_size", false]], "contextchunkingpolicy (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.ContextChunkingPolicy", false]], "conv1d (class in tensorrt_llm.layers.conv)": [[84, "tensorrt_llm.layers.conv.Conv1d", false]], "conv1d() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.conv1d", false]], "conv2d (class in tensorrt_llm.layers.conv)": [[84, "tensorrt_llm.layers.conv.Conv2d", false]], "conv2d() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.conv2d", false]], "conv3d (class in tensorrt_llm.layers.conv)": [[84, "tensorrt_llm.layers.conv.Conv3d", false]], "conv3d() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.conv3d", false]], "conv_kernel (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.conv_kernel", false]], "conv_kernel (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.conv_kernel", false]], "conv_transpose2d() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.conv_transpose2d", false]], "convert_load_format() (tensorrt_llm.llmapi.torchllmargs class method)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.convert_load_format", false]], "convtranspose2d (class in tensorrt_llm.layers.conv)": [[84, "tensorrt_llm.layers.conv.ConvTranspose2d", false]], "copy_on_partial_reuse (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.KvCacheConfig.copy_on_partial_reuse", false]], "cos() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.cos", false]], "cp_split_plugin() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.cp_split_plugin", false]], "cpp_e2e (tensorrt_llm.runtime.multimodalmodelrunner property)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.cpp_e2e", false]], "cpp_llm_only (tensorrt_llm.runtime.multimodalmodelrunner property)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.cpp_llm_only", false]], "create_allreduce_plugin() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.create_allreduce_plugin", false]], "create_attention_const_params() (tensorrt_llm.layers.attention.attention static method)": [[84, "tensorrt_llm.layers.attention.Attention.create_attention_const_params", false]], "create_fake_weight() (tensorrt_llm.functional.ropeembeddingutils static method)": [[83, "tensorrt_llm.functional.RopeEmbeddingUtils.create_fake_weight", false]], "create_runtime_defaults() (tensorrt_llm.models.pretrainedconfig static method)": [[85, "tensorrt_llm.models.PretrainedConfig.create_runtime_defaults", false]], "create_sinusoidal_positions() (tensorrt_llm.functional.ropeembeddingutils static method)": [[83, "tensorrt_llm.functional.RopeEmbeddingUtils.create_sinusoidal_positions", false]], "create_sinusoidal_positions_for_attention_plugin() (tensorrt_llm.functional.ropeembeddingutils static method)": [[83, "tensorrt_llm.functional.RopeEmbeddingUtils.create_sinusoidal_positions_for_attention_plugin", false]], "create_sinusoidal_positions_for_cogvlm_attention_plugin() (tensorrt_llm.functional.ropeembeddingutils static method)": [[83, "tensorrt_llm.functional.RopeEmbeddingUtils.create_sinusoidal_positions_for_cogvlm_attention_plugin", false]], "create_sinusoidal_positions_long_rope() (tensorrt_llm.functional.ropeembeddingutils method)": [[83, "tensorrt_llm.functional.RopeEmbeddingUtils.create_sinusoidal_positions_long_rope", false]], "create_sinusoidal_positions_long_rope_for_attention_plugin() (tensorrt_llm.functional.ropeembeddingutils static method)": [[83, "tensorrt_llm.functional.RopeEmbeddingUtils.create_sinusoidal_positions_long_rope_for_attention_plugin", false]], "create_sinusoidal_positions_yarn() (tensorrt_llm.functional.ropeembeddingutils static method)": [[83, "tensorrt_llm.functional.RopeEmbeddingUtils.create_sinusoidal_positions_yarn", false]], "cropped_pos_embed() (tensorrt_llm.layers.embedding.sd3patchembed method)": [[84, "tensorrt_llm.layers.embedding.SD3PatchEmbed.cropped_pos_embed", false]], "cross_attention (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.cross_attention", false]], "cross_attention (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.cross_attention", false]], "cross_kv_cache_fraction (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.KvCacheConfig.cross_kv_cache_fraction", false]], "ctx_request_id (tensorrt_llm.llmapi.disaggregatedparams attribute)": [[71, "tensorrt_llm.llmapi.DisaggregatedParams.ctx_request_id", false]], "cuda_graph_cache_size (tensorrt_llm.llmapi.extendedruntimeperfknobconfig attribute)": [[71, "tensorrt_llm.llmapi.ExtendedRuntimePerfKnobConfig.cuda_graph_cache_size", false]], "cuda_graph_config (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.cuda_graph_config", false]], "cuda_graph_mode (tensorrt_llm.llmapi.extendedruntimeperfknobconfig attribute)": [[71, "tensorrt_llm.llmapi.ExtendedRuntimePerfKnobConfig.cuda_graph_mode", false]], "cuda_graph_mode (tensorrt_llm.runtime.generationsession attribute)": [[88, "tensorrt_llm.runtime.GenerationSession.cuda_graph_mode", false]], "cuda_stream_guard() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.cuda_stream_guard", false]], "cuda_stream_sync() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.cuda_stream_sync", false]], "cudagraphconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.CudaGraphConfig", false]], "cumsum() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.cumsum", false]], "cumulative_logprob (tensorrt_llm.llmapi.completionoutput attribute)": [[71, "tensorrt_llm.llmapi.CompletionOutput.cumulative_logprob", false]], "custom_mask (tensorrt_llm.functional.attentionmasktype attribute)": [[83, "tensorrt_llm.functional.AttentionMaskType.custom_mask", false]], "data (tensorrt_llm.functional.sliceinputtype attribute)": [[83, "tensorrt_llm.functional.SliceInputType.data", false]], "dbrxconfig (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.DbrxConfig", false]], "dbrxforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.DbrxForCausalLM", false]], "debug_mode (tensorrt_llm.runtime.generationsession attribute)": [[88, "tensorrt_llm.runtime.GenerationSession.debug_mode", false]], "debug_tensors_to_save (tensorrt_llm.runtime.generationsession attribute)": [[88, "tensorrt_llm.runtime.GenerationSession.debug_tensors_to_save", false]], "decode() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.decode", false]], "decode_batch() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.decode_batch", false]], "decode_duration_ms (tensorrt_llm.llmapi.kvcacheretentionconfig property)": [[71, "tensorrt_llm.llmapi.KvCacheRetentionConfig.decode_duration_ms", false]], "decode_regular() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.decode_regular", false]], "decode_retention_priority (tensorrt_llm.llmapi.kvcacheretentionconfig property)": [[71, "tensorrt_llm.llmapi.KvCacheRetentionConfig.decode_retention_priority", false]], "decode_stream() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.decode_stream", false]], "decode_words_list() (in module tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.decode_words_list", false]], "decodermodel (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.DecoderModel", false]], "decoding_config (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.decoding_config", false]], "decoding_config (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.decoding_config", false]], "decoding_type (tensorrt_llm.llmapi.drafttargetdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.DraftTargetDecodingConfig.decoding_type", false]], "decoding_type (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.EagleDecodingConfig.decoding_type", false]], "decoding_type (tensorrt_llm.llmapi.lookaheaddecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.LookaheadDecodingConfig.decoding_type", false]], "decoding_type (tensorrt_llm.llmapi.medusadecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.MedusaDecodingConfig.decoding_type", false]], "decoding_type (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.MTPDecodingConfig.decoding_type", false]], "decoding_type (tensorrt_llm.llmapi.ngramdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.NGramDecodingConfig.decoding_type", false]], "decoding_type (tensorrt_llm.llmapi.userprovideddecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.UserProvidedDecodingConfig.decoding_type", false]], "deepseekforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.DeepseekForCausalLM", false]], "deepseekv2attention (class in tensorrt_llm.layers.attention)": [[84, "tensorrt_llm.layers.attention.DeepseekV2Attention", false]], "deepseekv2forcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.DeepseekV2ForCausalLM", false]], "default_plugin_config() (tensorrt_llm.models.cogvlmforcausallm method)": [[85, "tensorrt_llm.models.CogVLMForCausalLM.default_plugin_config", false]], "default_plugin_config() (tensorrt_llm.models.llamaforcausallm method)": [[85, "tensorrt_llm.models.LLaMAForCausalLM.default_plugin_config", false]], "deferred (tensorrt_llm.functional.positionembeddingtype attribute)": [[83, "tensorrt_llm.functional.PositionEmbeddingType.deferred", false]], "detokenize (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.detokenize", false]], "device (tensorrt_llm.llmapi.calibconfig attribute)": [[71, "tensorrt_llm.llmapi.CalibConfig.device", false]], "device (tensorrt_llm.runtime.generationsession attribute)": [[88, "tensorrt_llm.runtime.GenerationSession.device", false]], "diffusersattention (class in tensorrt_llm.layers.attention)": [[84, "tensorrt_llm.layers.attention.DiffusersAttention", false]], "dimrange (class in tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.DimRange", false]], "directory (tensorrt_llm.llmapi.kvcacheretentionconfig property)": [[71, "tensorrt_llm.llmapi.KvCacheRetentionConfig.directory", false]], "disable (tensorrt_llm.functional.sidestreamidtype attribute)": [[83, "tensorrt_llm.functional.SideStreamIDType.disable", false]], "disable_forward_chunking() (tensorrt_llm.models.sd3transformer2dmodel method)": [[85, "tensorrt_llm.models.SD3Transformer2DModel.disable_forward_chunking", false]], "disable_overlap_scheduler (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.disable_overlap_scheduler", false]], "disaggregated_params (tensorrt_llm.llmapi.completionoutput attribute)": [[71, "tensorrt_llm.llmapi.CompletionOutput.disaggregated_params", false]], "disaggregatedparams (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.DisaggregatedParams", false]], "dit (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.DiT", false]], "div() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.div", false]], "dora_plugin() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.dora_plugin", false]], "draft_tokens (tensorrt_llm.llmapi.disaggregatedparams attribute)": [[71, "tensorrt_llm.llmapi.DisaggregatedParams.draft_tokens", false]], "draft_tokens_external (tensorrt_llm.models.speculativedecodingmode attribute)": [[85, "tensorrt_llm.models.SpeculativeDecodingMode.DRAFT_TOKENS_EXTERNAL", false]], "drafter (tensorrt_llm.llmapi.userprovideddecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.UserProvidedDecodingConfig.drafter", false]], "drafttargetdecodingconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.DraftTargetDecodingConfig", false]], "dry_run (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.dry_run", false]], "dtype (tensorrt_llm.functional.tensor property)": [[83, "tensorrt_llm.functional.Tensor.dtype", false]], "dtype (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.KvCacheConfig.dtype", false]], "dtype (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.dtype", false]], "dtype (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.dtype", false]], "dtype (tensorrt_llm.runtime.modelrunner property)": [[88, "tensorrt_llm.runtime.ModelRunner.dtype", false]], "dtype (tensorrt_llm.runtime.modelrunnercpp property)": [[88, "tensorrt_llm.runtime.ModelRunnerCpp.dtype", false]], "dtype (tensorrt_llm.runtime.tensorinfo attribute)": [[88, "tensorrt_llm.runtime.TensorInfo.dtype", false]], "dump_debug_buffers() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.dump_debug_buffers", false]], "duration_ms (tensorrt_llm.llmapi.kvcacheretentionconfig.tokenrangeretentionconfig property)": [[71, "tensorrt_llm.llmapi.KvCacheRetentionConfig.TokenRangeRetentionConfig.duration_ms", false]], "dynamic (tensorrt_llm.functional.rotaryscalingtype attribute)": [[83, "tensorrt_llm.functional.RotaryScalingType.dynamic", false]], "dynamic_batch_config (tensorrt_llm.llmapi.schedulerconfig attribute)": [[71, "tensorrt_llm.llmapi.SchedulerConfig.dynamic_batch_config", false]], "dynamic_batch_moving_average_window (tensorrt_llm.llmapi.dynamicbatchconfig attribute)": [[71, "tensorrt_llm.llmapi.DynamicBatchConfig.dynamic_batch_moving_average_window", false]], "dynamic_tree_max_topk (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.EagleDecodingConfig.dynamic_tree_max_topK", false]], "dynamicbatchconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.DynamicBatchConfig", false]], "eagle (tensorrt_llm.models.speculativedecodingmode attribute)": [[85, "tensorrt_llm.models.SpeculativeDecodingMode.EAGLE", false]], "eagle3_one_model (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.EagleDecodingConfig.eagle3_one_model", false]], "eagle_choices (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.EagleDecodingConfig.eagle_choices", false]], "eagledecodingconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.EagleDecodingConfig", false]], "eagleforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.EagleForCausalLM", false]], "early_stop_criteria() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.early_stop_criteria", false]], "early_stopping (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.early_stopping", false]], "early_stopping (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.early_stopping", false]], "einsum() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.einsum", false]], "elementwise_binary() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.elementwise_binary", false]], "embedding (class in tensorrt_llm.layers.embedding)": [[84, "tensorrt_llm.layers.embedding.Embedding", false]], "embedding() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.embedding", false]], "embedding_bias (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.embedding_bias", false]], "embedding_parallel_mode (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.embedding_parallel_mode", false]], "enable_autotuner (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.enable_autotuner", false]], "enable_batch_size_tuning (tensorrt_llm.llmapi.dynamicbatchconfig attribute)": [[71, "tensorrt_llm.llmapi.DynamicBatchConfig.enable_batch_size_tuning", false]], "enable_block_reuse (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.KvCacheConfig.enable_block_reuse", false]], "enable_build_cache (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.enable_build_cache", false]], "enable_context_fmha_fp32_acc (tensorrt_llm.llmapi.extendedruntimeperfknobconfig attribute)": [[71, "tensorrt_llm.llmapi.ExtendedRuntimePerfKnobConfig.enable_context_fmha_fp32_acc", false]], "enable_debug_output (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.enable_debug_output", false]], "enable_forward_chunking() (tensorrt_llm.models.sd3transformer2dmodel method)": [[85, "tensorrt_llm.models.SD3Transformer2DModel.enable_forward_chunking", false]], "enable_fullgraph (tensorrt_llm.llmapi.torchcompileconfig attribute)": [[71, "tensorrt_llm.llmapi.TorchCompileConfig.enable_fullgraph", false]], "enable_inductor (tensorrt_llm.llmapi.torchcompileconfig attribute)": [[71, "tensorrt_llm.llmapi.TorchCompileConfig.enable_inductor", false]], "enable_iter_perf_stats (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.enable_iter_perf_stats", false]], "enable_iter_req_stats (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.enable_iter_req_stats", false]], "enable_layerwise_nvtx_marker (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.enable_layerwise_nvtx_marker", false]], "enable_max_num_tokens_tuning (tensorrt_llm.llmapi.dynamicbatchconfig attribute)": [[71, "tensorrt_llm.llmapi.DynamicBatchConfig.enable_max_num_tokens_tuning", false]], "enable_min_latency (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.enable_min_latency", false]], "enable_mixed_sampler (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.enable_mixed_sampler", false]], "enable_padding (tensorrt_llm.llmapi.cudagraphconfig attribute)": [[71, "tensorrt_llm.llmapi.CudaGraphConfig.enable_padding", false]], "enable_partial_reuse (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.KvCacheConfig.enable_partial_reuse", false]], "enable_piecewise_cuda_graph (tensorrt_llm.llmapi.torchcompileconfig attribute)": [[71, "tensorrt_llm.llmapi.TorchCompileConfig.enable_piecewise_cuda_graph", false]], "enable_prompt_adapter (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.enable_prompt_adapter", false]], "enable_tqdm (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.enable_tqdm", false]], "enable_trtllm_sampler (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.enable_trtllm_sampler", false]], "enable_userbuffers (tensorrt_llm.llmapi.torchcompileconfig attribute)": [[71, "tensorrt_llm.llmapi.TorchCompileConfig.enable_userbuffers", false]], "encdecmodelrunner (class in tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.EncDecModelRunner", false]], "encoder_run() (tensorrt_llm.runtime.encdecmodelrunner method)": [[88, "tensorrt_llm.runtime.EncDecModelRunner.encoder_run", false]], "encodermodel (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.EncoderModel", false]], "end_id (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.end_id", false]], "end_id (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.end_id", false]], "end_thinking_phase_token (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.MTPDecodingConfig.END_THINKING_PHASE_TOKEN", false]], "engine (tensorrt_llm.runtime.session property)": [[88, "tensorrt_llm.runtime.Session.engine", false]], "engine_inspector (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.engine_inspector", false]], "eq() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.eq", false]], "equal_progress (tensorrt_llm.llmapi.contextchunkingpolicy attribute)": [[71, "tensorrt_llm.llmapi.ContextChunkingPolicy.EQUAL_PROGRESS", false]], "event_buffer_max_size (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.KvCacheConfig.event_buffer_max_size", false]], "exclude_input_from_output (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.exclude_input_from_output", false]], "exclude_modules (tensorrt_llm.llmapi.quantconfig attribute)": [[71, "tensorrt_llm.llmapi.QuantConfig.exclude_modules", false]], "exp() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.exp", false]], "expand() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.expand", false]], "expand_dims() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.expand_dims", false]], "expand_dims_like() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.expand_dims_like", false]], "expand_mask() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.expand_mask", false]], "explicit_draft_tokens (tensorrt_llm.models.speculativedecodingmode attribute)": [[85, "tensorrt_llm.models.SpeculativeDecodingMode.EXPLICIT_DRAFT_TOKENS", false]], "extended_runtime_perf_knob_config (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.extended_runtime_perf_knob_config", false]], "extendedruntimeperfknobconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.ExtendedRuntimePerfKnobConfig", false]], "extra_resource_managers (tensorrt_llm.llmapi.torchllmargs property)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.extra_resource_managers", false]], "falconconfig (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.FalconConfig", false]], "falconforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.FalconForCausalLM", false]], "falconmodel (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.FalconModel", false]], "fast_build (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.fast_build", false]], "fc_gate() (tensorrt_llm.layers.mlp.fusedgatedmlp method)": [[84, "tensorrt_llm.layers.mlp.FusedGatedMLP.fc_gate", false]], "fc_gate_dora() (in module tensorrt_llm.layers.mlp)": [[84, "tensorrt_llm.layers.mlp.fc_gate_dora", false]], "fc_gate_lora() (in module tensorrt_llm.layers.mlp)": [[84, "tensorrt_llm.layers.mlp.fc_gate_lora", false]], "fc_gate_plugin() (tensorrt_llm.layers.mlp.fusedgatedmlp method)": [[84, "tensorrt_llm.layers.mlp.FusedGatedMLP.fc_gate_plugin", false]], "field_name (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "id12", false], [71, "id15", false], [71, "id18", false], [71, "tensorrt_llm.llmapi.TorchLlmArgs.field_name", false]], "field_name (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "id21", false], [71, "id24", false], [71, "id27", false], [71, "id30", false], [71, "id33", false], [71, "tensorrt_llm.llmapi.TrtLlmArgs.field_name", false]], "fill_attention_const_params_for_long_rope() (tensorrt_llm.layers.attention.attentionparams method)": [[84, "tensorrt_llm.layers.attention.AttentionParams.fill_attention_const_params_for_long_rope", false]], "fill_attention_const_params_for_rope() (tensorrt_llm.layers.attention.attentionparams method)": [[84, "tensorrt_llm.layers.attention.AttentionParams.fill_attention_const_params_for_rope", false]], "fill_attention_params() (tensorrt_llm.layers.attention.attention static method)": [[84, "tensorrt_llm.layers.attention.Attention.fill_attention_params", false]], "fill_none_tensor_list() (tensorrt_llm.layers.attention.keyvaluecacheparams method)": [[84, "tensorrt_llm.layers.attention.KeyValueCacheParams.fill_none_tensor_list", false]], "fill_value (tensorrt_llm.functional.sliceinputtype attribute)": [[83, "tensorrt_llm.functional.SliceInputType.fill_value", false]], "filter_medusa_logits() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.filter_medusa_logits", false]], "finalize_decoder() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.finalize_decoder", false]], "find_best_medusa_path() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.find_best_medusa_path", false]], "finish_reason (tensorrt_llm.llmapi.completionoutput attribute)": [[71, "tensorrt_llm.llmapi.CompletionOutput.finish_reason", false]], "finished (tensorrt_llm.llmapi.requestoutput attribute)": [[71, "tensorrt_llm.llmapi.RequestOutput.finished", false]], "first_come_first_served (tensorrt_llm.llmapi.contextchunkingpolicy attribute)": [[71, "tensorrt_llm.llmapi.ContextChunkingPolicy.FIRST_COME_FIRST_SERVED", false]], "first_gen_tokens (tensorrt_llm.llmapi.disaggregatedparams attribute)": [[71, "tensorrt_llm.llmapi.DisaggregatedParams.first_gen_tokens", false]], "first_layer (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.first_layer", false]], "flatten() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.flatten", false]], "flatten() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.flatten", false]], "flip() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.flip", false]], "floordiv() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.floordiv", false]], "fmt_dim (c macro)": [[1, "c.FMT_DIM", false]], "for_each_rank() (tensorrt_llm.models.pretrainedconfig method)": [[85, "tensorrt_llm.models.PretrainedConfig.for_each_rank", false]], "force_dynamic_quantization (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.force_dynamic_quantization", false]], "force_num_profiles (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.force_num_profiles", false]], "forward() (tensorrt_llm.layers.activation.mish method)": [[84, "tensorrt_llm.layers.activation.Mish.forward", false]], "forward() (tensorrt_llm.layers.attention.attention method)": [[84, "tensorrt_llm.layers.attention.Attention.forward", false]], "forward() (tensorrt_llm.layers.attention.bertattention method)": [[84, "tensorrt_llm.layers.attention.BertAttention.forward", false]], "forward() (tensorrt_llm.layers.attention.cogvlmattention method)": [[84, "tensorrt_llm.layers.attention.CogVLMAttention.forward", false]], "forward() (tensorrt_llm.layers.attention.deepseekv2attention method)": [[84, "tensorrt_llm.layers.attention.DeepseekV2Attention.forward", false]], "forward() (tensorrt_llm.layers.attention.diffusersattention method)": [[84, "tensorrt_llm.layers.attention.DiffusersAttention.forward", false]], "forward() (tensorrt_llm.layers.cast.cast method)": [[84, "tensorrt_llm.layers.cast.Cast.forward", false]], "forward() (tensorrt_llm.layers.conv.conv1d method)": [[84, "tensorrt_llm.layers.conv.Conv1d.forward", false]], "forward() (tensorrt_llm.layers.conv.conv2d method)": [[84, "tensorrt_llm.layers.conv.Conv2d.forward", false]], "forward() (tensorrt_llm.layers.conv.conv3d method)": [[84, "tensorrt_llm.layers.conv.Conv3d.forward", false]], "forward() (tensorrt_llm.layers.conv.convtranspose2d method)": [[84, "tensorrt_llm.layers.conv.ConvTranspose2d.forward", false]], "forward() (tensorrt_llm.layers.embedding.combinedtimesteplabelembeddings method)": [[84, "tensorrt_llm.layers.embedding.CombinedTimestepLabelEmbeddings.forward", false]], "forward() (tensorrt_llm.layers.embedding.combinedtimesteptextprojembeddings method)": [[84, "tensorrt_llm.layers.embedding.CombinedTimestepTextProjEmbeddings.forward", false]], "forward() (tensorrt_llm.layers.embedding.embedding method)": [[84, "tensorrt_llm.layers.embedding.Embedding.forward", false]], "forward() (tensorrt_llm.layers.embedding.labelembedding method)": [[84, "tensorrt_llm.layers.embedding.LabelEmbedding.forward", false]], "forward() (tensorrt_llm.layers.embedding.pixartalphatextprojection method)": [[84, "tensorrt_llm.layers.embedding.PixArtAlphaTextProjection.forward", false]], "forward() (tensorrt_llm.layers.embedding.prompttuningembedding method)": [[84, "tensorrt_llm.layers.embedding.PromptTuningEmbedding.forward", false]], "forward() (tensorrt_llm.layers.embedding.sd3patchembed method)": [[84, "tensorrt_llm.layers.embedding.SD3PatchEmbed.forward", false]], "forward() (tensorrt_llm.layers.embedding.timestepembedding method)": [[84, "tensorrt_llm.layers.embedding.TimestepEmbedding.forward", false]], "forward() (tensorrt_llm.layers.embedding.timesteps method)": [[84, "tensorrt_llm.layers.embedding.Timesteps.forward", false]], "forward() (tensorrt_llm.layers.linear.linearbase method)": [[84, "tensorrt_llm.layers.linear.LinearBase.forward", false]], "forward() (tensorrt_llm.layers.mlp.fusedgatedmlp method)": [[84, "tensorrt_llm.layers.mlp.FusedGatedMLP.forward", false]], "forward() (tensorrt_llm.layers.mlp.gatedmlp method)": [[84, "tensorrt_llm.layers.mlp.GatedMLP.forward", false]], "forward() (tensorrt_llm.layers.mlp.linearactivation method)": [[84, "tensorrt_llm.layers.mlp.LinearActivation.forward", false]], "forward() (tensorrt_llm.layers.mlp.linearapproximategelu method)": [[84, "tensorrt_llm.layers.mlp.LinearApproximateGELU.forward", false]], "forward() (tensorrt_llm.layers.mlp.lineargeglu method)": [[84, "tensorrt_llm.layers.mlp.LinearGEGLU.forward", false]], "forward() (tensorrt_llm.layers.mlp.lineargelu method)": [[84, "tensorrt_llm.layers.mlp.LinearGELU.forward", false]], "forward() (tensorrt_llm.layers.mlp.linearswiglu method)": [[84, "tensorrt_llm.layers.mlp.LinearSwiGLU.forward", false]], "forward() (tensorrt_llm.layers.mlp.mlp method)": [[84, "tensorrt_llm.layers.mlp.MLP.forward", false]], "forward() (tensorrt_llm.layers.normalization.adalayernorm method)": [[84, "tensorrt_llm.layers.normalization.AdaLayerNorm.forward", false]], "forward() (tensorrt_llm.layers.normalization.adalayernormcontinuous method)": [[84, "tensorrt_llm.layers.normalization.AdaLayerNormContinuous.forward", false]], "forward() (tensorrt_llm.layers.normalization.adalayernormzero method)": [[84, "tensorrt_llm.layers.normalization.AdaLayerNormZero.forward", false]], "forward() (tensorrt_llm.layers.normalization.adalayernormzerosingle method)": [[84, "tensorrt_llm.layers.normalization.AdaLayerNormZeroSingle.forward", false]], "forward() (tensorrt_llm.layers.normalization.groupnorm method)": [[84, "tensorrt_llm.layers.normalization.GroupNorm.forward", false]], "forward() (tensorrt_llm.layers.normalization.layernorm method)": [[84, "tensorrt_llm.layers.normalization.LayerNorm.forward", false]], "forward() (tensorrt_llm.layers.normalization.rmsnorm method)": [[84, "tensorrt_llm.layers.normalization.RmsNorm.forward", false]], "forward() (tensorrt_llm.layers.normalization.sd35adalayernormzerox method)": [[84, "tensorrt_llm.layers.normalization.SD35AdaLayerNormZeroX.forward", false]], "forward() (tensorrt_llm.layers.pooling.avgpool2d method)": [[84, "tensorrt_llm.layers.pooling.AvgPool2d.forward", false]], "forward() (tensorrt_llm.models.bertforquestionanswering method)": [[85, "tensorrt_llm.models.BertForQuestionAnswering.forward", false]], "forward() (tensorrt_llm.models.bertforsequenceclassification method)": [[85, "tensorrt_llm.models.BertForSequenceClassification.forward", false]], "forward() (tensorrt_llm.models.bertmodel method)": [[85, "tensorrt_llm.models.BertModel.forward", false]], "forward() (tensorrt_llm.models.bloommodel method)": [[85, "tensorrt_llm.models.BloomModel.forward", false]], "forward() (tensorrt_llm.models.chatglmmodel method)": [[85, "tensorrt_llm.models.ChatGLMModel.forward", false]], "forward() (tensorrt_llm.models.clipvisiontransformer method)": [[85, "tensorrt_llm.models.CLIPVisionTransformer.forward", false]], "forward() (tensorrt_llm.models.decodermodel method)": [[85, "tensorrt_llm.models.DecoderModel.forward", false]], "forward() (tensorrt_llm.models.dit method)": [[85, "tensorrt_llm.models.DiT.forward", false]], "forward() (tensorrt_llm.models.eagleforcausallm method)": [[85, "tensorrt_llm.models.EagleForCausalLM.forward", false]], "forward() (tensorrt_llm.models.encodermodel method)": [[85, "tensorrt_llm.models.EncoderModel.forward", false]], "forward() (tensorrt_llm.models.falconmodel method)": [[85, "tensorrt_llm.models.FalconModel.forward", false]], "forward() (tensorrt_llm.models.gptjmodel method)": [[85, "tensorrt_llm.models.GPTJModel.forward", false]], "forward() (tensorrt_llm.models.gptmodel method)": [[85, "tensorrt_llm.models.GPTModel.forward", false]], "forward() (tensorrt_llm.models.gptneoxmodel method)": [[85, "tensorrt_llm.models.GPTNeoXModel.forward", false]], "forward() (tensorrt_llm.models.llamamodel method)": [[85, "tensorrt_llm.models.LLaMAModel.forward", false]], "forward() (tensorrt_llm.models.llavanextvisionwrapper method)": [[85, "tensorrt_llm.models.LlavaNextVisionWrapper.forward", false]], "forward() (tensorrt_llm.models.mambaforcausallm method)": [[85, "tensorrt_llm.models.MambaForCausalLM.forward", false]], "forward() (tensorrt_llm.models.mllamaforcausallm method)": [[85, "tensorrt_llm.models.MLLaMAForCausalLM.forward", false]], "forward() (tensorrt_llm.models.mptmodel method)": [[85, "tensorrt_llm.models.MPTModel.forward", false]], "forward() (tensorrt_llm.models.optmodel method)": [[85, "tensorrt_llm.models.OPTModel.forward", false]], "forward() (tensorrt_llm.models.phi3model method)": [[85, "tensorrt_llm.models.Phi3Model.forward", false]], "forward() (tensorrt_llm.models.phimodel method)": [[85, "tensorrt_llm.models.PhiModel.forward", false]], "forward() (tensorrt_llm.models.recurrentgemmaforcausallm method)": [[85, "tensorrt_llm.models.RecurrentGemmaForCausalLM.forward", false]], "forward() (tensorrt_llm.models.sd3transformer2dmodel method)": [[85, "tensorrt_llm.models.SD3Transformer2DModel.forward", false]], "forward() (tensorrt_llm.models.whisperencoder method)": [[85, "tensorrt_llm.models.WhisperEncoder.forward", false]], "forward_with_cfg() (tensorrt_llm.models.dit method)": [[85, "tensorrt_llm.models.DiT.forward_with_cfg", false]], "forward_without_cfg() (tensorrt_llm.models.dit method)": [[85, "tensorrt_llm.models.DiT.forward_without_cfg", false]], "fp8 (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.FP8", false]], "fp8_block_scales (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.FP8_BLOCK_SCALES", false]], "fp8_per_channel_per_token (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.FP8_PER_CHANNEL_PER_TOKEN", false]], "free_gpu_memory_fraction (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.KvCacheConfig.free_gpu_memory_fraction", false]], "frequency_penalty (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.frequency_penalty", false]], "frequency_penalty (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.frequency_penalty", false]], "from_arguments() (tensorrt_llm.models.speculativedecodingmode static method)": [[85, "tensorrt_llm.models.SpeculativeDecodingMode.from_arguments", false]], "from_checkpoint() (tensorrt_llm.models.pretrainedconfig class method)": [[85, "tensorrt_llm.models.PretrainedConfig.from_checkpoint", false]], "from_checkpoint() (tensorrt_llm.models.pretrainedmodel class method)": [[85, "tensorrt_llm.models.PretrainedModel.from_checkpoint", false]], "from_config() (tensorrt_llm.models.pretrainedmodel class method)": [[85, "tensorrt_llm.models.PretrainedModel.from_config", false]], "from_dict() (tensorrt_llm.llmapi.buildconfig class method)": [[71, "tensorrt_llm.llmapi.BuildConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.calibconfig class method)": [[71, "tensorrt_llm.llmapi.CalibConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.drafttargetdecodingconfig class method)": [[71, "tensorrt_llm.llmapi.DraftTargetDecodingConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.eagledecodingconfig class method)": [[71, "tensorrt_llm.llmapi.EagleDecodingConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.lookaheaddecodingconfig class method)": [[71, "tensorrt_llm.llmapi.LookaheadDecodingConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.medusadecodingconfig class method)": [[71, "tensorrt_llm.llmapi.MedusaDecodingConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.moeconfig class method)": [[71, "tensorrt_llm.llmapi.MoeConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.mtpdecodingconfig class method)": [[71, "tensorrt_llm.llmapi.MTPDecodingConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.ngramdecodingconfig class method)": [[71, "tensorrt_llm.llmapi.NGramDecodingConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.quantconfig class method)": [[71, "tensorrt_llm.llmapi.QuantConfig.from_dict", false]], "from_dict() (tensorrt_llm.llmapi.userprovideddecodingconfig class method)": [[71, "tensorrt_llm.llmapi.UserProvidedDecodingConfig.from_dict", false]], "from_dict() (tensorrt_llm.models.pretrainedconfig class method)": [[85, "tensorrt_llm.models.PretrainedConfig.from_dict", false]], "from_dir() (tensorrt_llm.runtime.modelrunner class method)": [[88, "tensorrt_llm.runtime.ModelRunner.from_dir", false]], "from_dir() (tensorrt_llm.runtime.modelrunnercpp class method)": [[88, "tensorrt_llm.runtime.ModelRunnerCpp.from_dir", false]], "from_engine() (tensorrt_llm.runtime.encdecmodelrunner class method)": [[88, "tensorrt_llm.runtime.EncDecModelRunner.from_engine", false]], "from_engine() (tensorrt_llm.runtime.modelrunner class method)": [[88, "tensorrt_llm.runtime.ModelRunner.from_engine", false]], "from_engine() (tensorrt_llm.runtime.session static method)": [[88, "tensorrt_llm.runtime.Session.from_engine", false]], "from_hugging_face() (tensorrt_llm.models.baichuanforcausallm class method)": [[85, "tensorrt_llm.models.BaichuanForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.chatglmconfig class method)": [[85, "tensorrt_llm.models.ChatGLMConfig.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.chatglmforcausallm class method)": [[85, "tensorrt_llm.models.ChatGLMForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.cogvlmforcausallm class method)": [[85, "tensorrt_llm.models.CogVLMForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.cohereforcausallm class method)": [[85, "tensorrt_llm.models.CohereForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.deepseekforcausallm class method)": [[85, "tensorrt_llm.models.DeepseekForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.deepseekv2forcausallm class method)": [[85, "tensorrt_llm.models.DeepseekV2ForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.eagleforcausallm class method)": [[85, "tensorrt_llm.models.EagleForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.falconconfig class method)": [[85, "tensorrt_llm.models.FalconConfig.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.falconforcausallm class method)": [[85, "tensorrt_llm.models.FalconForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.gemmaconfig class method)": [[85, "tensorrt_llm.models.GemmaConfig.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.gemmaforcausallm class method)": [[85, "tensorrt_llm.models.GemmaForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.gptconfig class method)": [[85, "tensorrt_llm.models.GPTConfig.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.gptforcausallm class method)": [[85, "tensorrt_llm.models.GPTForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.gptjconfig class method)": [[85, "tensorrt_llm.models.GPTJConfig.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.gptjforcausallm class method)": [[85, "tensorrt_llm.models.GPTJForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.llamaconfig class method)": [[85, "tensorrt_llm.models.LLaMAConfig.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.llamaforcausallm class method)": [[85, "tensorrt_llm.models.LLaMAForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.llavanextvisionconfig class method)": [[85, "tensorrt_llm.models.LlavaNextVisionConfig.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.llavanextvisionwrapper class method)": [[85, "tensorrt_llm.models.LlavaNextVisionWrapper.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.mambaforcausallm class method)": [[85, "tensorrt_llm.models.MambaForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.medusaconfig class method)": [[85, "tensorrt_llm.models.MedusaConfig.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.medusaforcausallm class method)": [[85, "tensorrt_llm.models.MedusaForCausalLm.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.mllamaforcausallm class method)": [[85, "tensorrt_llm.models.MLLaMAForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.phi3forcausallm class method)": [[85, "tensorrt_llm.models.Phi3ForCausalLM.from_hugging_face", false]], "from_hugging_face() (tensorrt_llm.models.phiforcausallm class method)": [[85, "tensorrt_llm.models.PhiForCausalLM.from_hugging_face", false]], "from_json_file() (tensorrt_llm.llmapi.buildconfig class method)": [[71, "tensorrt_llm.llmapi.BuildConfig.from_json_file", false]], "from_json_file() (tensorrt_llm.models.pretrainedconfig class method)": [[85, "tensorrt_llm.models.PretrainedConfig.from_json_file", false]], "from_meta_ckpt() (tensorrt_llm.models.llamaconfig class method)": [[85, "tensorrt_llm.models.LLaMAConfig.from_meta_ckpt", false]], "from_meta_ckpt() (tensorrt_llm.models.llamaforcausallm class method)": [[85, "tensorrt_llm.models.LLaMAForCausalLM.from_meta_ckpt", false]], "from_nemo() (tensorrt_llm.models.gptconfig class method)": [[85, "tensorrt_llm.models.GPTConfig.from_nemo", false]], "from_nemo() (tensorrt_llm.models.gptforcausallm class method)": [[85, "tensorrt_llm.models.GPTForCausalLM.from_nemo", false]], "from_pretrained() (tensorrt_llm.models.sd3transformer2dmodel class method)": [[85, "tensorrt_llm.models.SD3Transformer2DModel.from_pretrained", false]], "from_serialized_engine() (tensorrt_llm.runtime.session static method)": [[88, "tensorrt_llm.runtime.Session.from_serialized_engine", false]], "from_string() (tensorrt_llm.functional.positionembeddingtype static method)": [[83, "tensorrt_llm.functional.PositionEmbeddingType.from_string", false]], "from_string() (tensorrt_llm.functional.rotaryscalingtype static method)": [[83, "tensorrt_llm.functional.RotaryScalingType.from_string", false]], "fuse_qkv_projections() (tensorrt_llm.models.sd3transformer2dmodel method)": [[85, "tensorrt_llm.models.SD3Transformer2DModel.fuse_qkv_projections", false]], "fusedgatedmlp (class in tensorrt_llm.layers.mlp)": [[84, "tensorrt_llm.layers.mlp.FusedGatedMLP", false]], "fusedgatedmlp (tensorrt_llm.functional.mlptype attribute)": [[83, "tensorrt_llm.functional.MLPType.FusedGatedMLP", false]], "garbage_collection_gen0_threshold (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.garbage_collection_gen0_threshold", false]], "gatedmlp (class in tensorrt_llm.layers.mlp)": [[84, "tensorrt_llm.layers.mlp.GatedMLP", false]], "gatedmlp (tensorrt_llm.functional.mlptype attribute)": [[83, "tensorrt_llm.functional.MLPType.GatedMLP", false]], "gather() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.gather", false]], "gather_context_logits (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.gather_context_logits", false]], "gather_context_logits (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.gather_context_logits", false]], "gather_context_logits (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.gather_context_logits", false]], "gather_context_logits (tensorrt_llm.runtime.modelrunner property)": [[88, "tensorrt_llm.runtime.ModelRunner.gather_context_logits", false]], "gather_context_logits (tensorrt_llm.runtime.modelrunnercpp property)": [[88, "tensorrt_llm.runtime.ModelRunnerCpp.gather_context_logits", false]], "gather_generation_logits (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.gather_generation_logits", false]], "gather_generation_logits (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.gather_generation_logits", false]], "gather_generation_logits (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.gather_generation_logits", false]], "gather_generation_logits (tensorrt_llm.runtime.modelrunner property)": [[88, "tensorrt_llm.runtime.ModelRunner.gather_generation_logits", false]], "gather_generation_logits (tensorrt_llm.runtime.modelrunnercpp property)": [[88, "tensorrt_llm.runtime.ModelRunnerCpp.gather_generation_logits", false]], "gather_last_token_logits() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.gather_last_token_logits", false]], "gather_nd() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.gather_nd", false]], "gegelu() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.gegelu", false]], "geglu() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.geglu", false]], "gelu() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.gelu", false]], "gemm_allreduce() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.gemm_allreduce", false]], "gemm_allreduce_plugin (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.gemm_allreduce_plugin", false]], "gemm_allreduce_plugin (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.gemm_allreduce_plugin", false]], "gemm_swiglu() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.gemm_swiglu", false]], "gemma2_added_fields (tensorrt_llm.models.gemmaconfig attribute)": [[85, "tensorrt_llm.models.GemmaConfig.GEMMA2_ADDED_FIELDS", false]], "gemma2_config() (tensorrt_llm.models.gemmaconfig method)": [[85, "tensorrt_llm.models.GemmaConfig.gemma2_config", false]], "gemma3_added_fields (tensorrt_llm.models.gemmaconfig attribute)": [[85, "tensorrt_llm.models.GemmaConfig.GEMMA3_ADDED_FIELDS", false]], "gemma3_config() (tensorrt_llm.models.gemmaconfig method)": [[85, "tensorrt_llm.models.GemmaConfig.gemma3_config", false]], "gemma_added_fields (tensorrt_llm.models.gemmaconfig attribute)": [[85, "tensorrt_llm.models.GemmaConfig.GEMMA_ADDED_FIELDS", false]], "gemmaconfig (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.GemmaConfig", false]], "gemmaforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.GemmaForCausalLM", false]], "generate() (tensorrt_llm.llmapi.llm method)": [[71, "tensorrt_llm.llmapi.LLM.generate", false]], "generate() (tensorrt_llm.runtime.encdecmodelrunner method)": [[88, "tensorrt_llm.runtime.EncDecModelRunner.generate", false]], "generate() (tensorrt_llm.runtime.modelrunner method)": [[88, "tensorrt_llm.runtime.ModelRunner.generate", false]], "generate() (tensorrt_llm.runtime.modelrunnercpp method)": [[88, "tensorrt_llm.runtime.ModelRunnerCpp.generate", false]], "generate() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.generate", false]], "generate() (tensorrt_llm.runtime.qwenforcausallmgenerationsession method)": [[88, "tensorrt_llm.runtime.QWenForCausalLMGenerationSession.generate", false]], "generate_alibi_biases() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.generate_alibi_biases", false]], "generate_alibi_slopes() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.generate_alibi_slopes", false]], "generate_async() (tensorrt_llm.llmapi.llm method)": [[71, "tensorrt_llm.llmapi.LLM.generate_async", false]], "generate_logn_scaling() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.generate_logn_scaling", false]], "generation_logits (tensorrt_llm.llmapi.completionoutput attribute)": [[71, "tensorrt_llm.llmapi.CompletionOutput.generation_logits", false]], "generationsequence (class in tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.GenerationSequence", false]], "generationsession (class in tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.GenerationSession", false]], "get_1d_sincos_pos_embed_from_grid() (in module tensorrt_llm.layers.embedding)": [[84, "tensorrt_llm.layers.embedding.get_1d_sincos_pos_embed_from_grid", false]], "get_2d_sincos_pos_embed() (in module tensorrt_llm.layers.embedding)": [[84, "tensorrt_llm.layers.embedding.get_2d_sincos_pos_embed", false]], "get_2d_sincos_pos_embed_from_grid() (in module tensorrt_llm.layers.embedding)": [[84, "tensorrt_llm.layers.embedding.get_2d_sincos_pos_embed_from_grid", false]], "get_audio_features() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.get_audio_features", false]], "get_batch_idx() (tensorrt_llm.runtime.generationsequence method)": [[88, "tensorrt_llm.runtime.GenerationSequence.get_batch_idx", false]], "get_block_offsets() (tensorrt_llm.runtime.kvcachemanager method)": [[88, "tensorrt_llm.runtime.KVCacheManager.get_block_offsets", false]], "get_build_config_defaults() (tensorrt_llm.llmapi.buildconfig class method)": [[71, "tensorrt_llm.llmapi.BuildConfig.get_build_config_defaults", false]], "get_comm() (tensorrt_llm.llmapi.mpicommsession method)": [[71, "tensorrt_llm.llmapi.MpiCommSession.get_comm", false]], "get_config_group() (tensorrt_llm.models.pretrainedconfig method)": [[85, "tensorrt_llm.models.PretrainedConfig.get_config_group", false]], "get_context_phase_params() (tensorrt_llm.llmapi.disaggregatedparams method)": [[71, "tensorrt_llm.llmapi.DisaggregatedParams.get_context_phase_params", false]], "get_draft_model_prompt() (tensorrt_llm.llmapi.eagledecodingconfig method)": [[71, "tensorrt_llm.llmapi.EagleDecodingConfig.get_draft_model_prompt", false]], "get_first_past_key_value() (tensorrt_llm.layers.attention.keyvaluecacheparams method)": [[84, "tensorrt_llm.layers.attention.KeyValueCacheParams.get_first_past_key_value", false]], "get_hf_config() (tensorrt_llm.models.gemmaconfig static method)": [[85, "tensorrt_llm.models.GemmaConfig.get_hf_config", false]], "get_kv_cache_events() (tensorrt_llm.llmapi.llm method)": [[71, "tensorrt_llm.llmapi.LLM.get_kv_cache_events", false]], "get_kv_cache_events_async() (tensorrt_llm.llmapi.llm method)": [[71, "tensorrt_llm.llmapi.LLM.get_kv_cache_events_async", false]], "get_next_medusa_tokens() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.get_next_medusa_tokens", false]], "get_num_heads_kv() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.get_num_heads_kv", false]], "get_parent() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.get_parent", false]], "get_pytorch_backend_config() (tensorrt_llm.llmapi.torchllmargs method)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.get_pytorch_backend_config", false]], "get_request_type() (tensorrt_llm.llmapi.disaggregatedparams method)": [[71, "tensorrt_llm.llmapi.DisaggregatedParams.get_request_type", false]], "get_rope_index() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.get_rope_index", false]], "get_seq_idx() (tensorrt_llm.runtime.generationsequence method)": [[88, "tensorrt_llm.runtime.GenerationSequence.get_seq_idx", false]], "get_stats() (tensorrt_llm.llmapi.llm method)": [[71, "tensorrt_llm.llmapi.LLM.get_stats", false]], "get_stats_async() (tensorrt_llm.llmapi.llm method)": [[71, "tensorrt_llm.llmapi.LLM.get_stats_async", false]], "get_timestep_embedding() (in module tensorrt_llm.layers.embedding)": [[84, "tensorrt_llm.layers.embedding.get_timestep_embedding", false]], "get_users() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.get_users", false]], "get_visual_features() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.get_visual_features", false]], "get_weight() (tensorrt_llm.layers.linear.linearbase method)": [[84, "tensorrt_llm.layers.linear.LinearBase.get_weight", false]], "gpt_attention() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.gpt_attention", false]], "gpt_attention_plugin (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.gpt_attention_plugin", false]], "gptconfig (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.GPTConfig", false]], "gptforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.GPTForCausalLM", false]], "gptjconfig (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.GPTJConfig", false]], "gptjforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.GPTJForCausalLM", false]], "gptjmodel (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.GPTJModel", false]], "gptmodel (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.GPTModel", false]], "gptneoxforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.GPTNeoXForCausalLM", false]], "gptneoxmodel (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.GPTNeoXModel", false]], "gpu_weights_percent (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.gpu_weights_percent", false]], "grammar (tensorrt_llm.llmapi.guideddecodingparams attribute)": [[71, "tensorrt_llm.llmapi.GuidedDecodingParams.grammar", false]], "greedy_sampling (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.EagleDecodingConfig.greedy_sampling", false]], "group_norm() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.group_norm", false]], "group_size (tensorrt_llm.llmapi.quantconfig attribute)": [[71, "tensorrt_llm.llmapi.QuantConfig.group_size", false]], "groupnorm (class in tensorrt_llm.layers.normalization)": [[84, "tensorrt_llm.layers.normalization.GroupNorm", false]], "groupnorm (tensorrt_llm.functional.layernormtype attribute)": [[83, "tensorrt_llm.functional.LayerNormType.GroupNorm", false]], "gt() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.gt", false]], "guaranteed_no_evict (tensorrt_llm.llmapi.capacityschedulerpolicy attribute)": [[71, "tensorrt_llm.llmapi.CapacitySchedulerPolicy.GUARANTEED_NO_EVICT", false]], "guided_decoding (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.guided_decoding", false]], "guideddecodingparams (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.GuidedDecodingParams", false]], "handle_per_step() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.handle_per_step", false]], "has_affine() (tensorrt_llm.functional.allreduceparams method)": [[83, "tensorrt_llm.functional.AllReduceParams.has_affine", false]], "has_bias() (tensorrt_llm.functional.allreduceparams method)": [[83, "tensorrt_llm.functional.AllReduceParams.has_bias", false]], "has_config_group() (tensorrt_llm.models.pretrainedconfig method)": [[85, "tensorrt_llm.models.PretrainedConfig.has_config_group", false]], "has_position_embedding (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.has_position_embedding", false]], "has_position_embedding (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.has_position_embedding", false]], "has_scale() (tensorrt_llm.functional.allreduceparams method)": [[83, "tensorrt_llm.functional.AllReduceParams.has_scale", false]], "has_token_type_embedding (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.has_token_type_embedding", false]], "has_token_type_embedding (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.has_token_type_embedding", false]], "has_zero_point (tensorrt_llm.llmapi.quantconfig attribute)": [[71, "tensorrt_llm.llmapi.QuantConfig.has_zero_point", false]], "head_size (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.head_size", false]], "head_size (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.head_size", false]], "hidden_size (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.hidden_size", false]], "hidden_size (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.hidden_size", false]], "hidden_size (tensorrt_llm.runtime.modelrunner property)": [[88, "tensorrt_llm.runtime.ModelRunner.hidden_size", false]], "hidden_size (tensorrt_llm.runtime.modelrunnercpp property)": [[88, "tensorrt_llm.runtime.ModelRunnerCpp.hidden_size", false]], "host_cache_size (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.KvCacheConfig.host_cache_size", false]], "identity() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.identity", false]], "ignore_eos (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.ignore_eos", false]], "include_stop_str_in_output (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.include_stop_str_in_output", false]], "index (tensorrt_llm.llmapi.completionoutput attribute)": [[71, "tensorrt_llm.llmapi.CompletionOutput.index", false]], "index_select() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.index_select", false]], "infer_shapes() (tensorrt_llm.runtime.session method)": [[88, "tensorrt_llm.runtime.Session.infer_shapes", false]], "inflight (tensorrt_llm.llmapi.batchingtype attribute)": [[71, "tensorrt_llm.llmapi.BatchingType.INFLIGHT", false]], "init_audio_encoder() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.init_audio_encoder", false]], "init_backend() (tensorrt_llm.llmapi.torchllmargs class method)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.init_backend", false]], "init_calib_config() (tensorrt_llm.llmapi.trtllmargs class method)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.init_calib_config", false]], "init_image_encoder() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.init_image_encoder", false]], "init_llm() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.init_llm", false]], "init_processor() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.init_processor", false]], "init_tokenizer() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.init_tokenizer", false]], "input_timing_cache (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.input_timing_cache", false]], "int8 (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.INT8", false]], "int_clip() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.int_clip", false]], "interpolate() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.interpolate", false]], "is_alibi() (tensorrt_llm.functional.positionembeddingtype method)": [[83, "tensorrt_llm.functional.PositionEmbeddingType.is_alibi", false]], "is_deferred() (tensorrt_llm.functional.positionembeddingtype method)": [[83, "tensorrt_llm.functional.PositionEmbeddingType.is_deferred", false]], "is_dynamic() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.is_dynamic", false]], "is_gated_activation() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.is_gated_activation", false]], "is_gemma_2 (tensorrt_llm.models.gemmaconfig property)": [[85, "tensorrt_llm.models.GemmaConfig.is_gemma_2", false]], "is_gemma_3 (tensorrt_llm.models.gemmaconfig property)": [[85, "tensorrt_llm.models.GemmaConfig.is_gemma_3", false]], "is_keep_all (tensorrt_llm.llmapi.ngramdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.NGramDecodingConfig.is_keep_all", false]], "is_medusa_mode (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.is_medusa_mode", false]], "is_module_excluded_from_quantization() (tensorrt_llm.llmapi.quantconfig method)": [[71, "tensorrt_llm.llmapi.QuantConfig.is_module_excluded_from_quantization", false]], "is_mrope() (tensorrt_llm.functional.positionembeddingtype method)": [[83, "tensorrt_llm.functional.PositionEmbeddingType.is_mrope", false]], "is_public_pool (tensorrt_llm.llmapi.ngramdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.NGramDecodingConfig.is_public_pool", false]], "is_redrafter_mode (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.is_redrafter_mode", false]], "is_rope() (tensorrt_llm.functional.positionembeddingtype method)": [[83, "tensorrt_llm.functional.PositionEmbeddingType.is_rope", false]], "is_trt_wrapper() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.is_trt_wrapper", false]], "is_use_oldest (tensorrt_llm.llmapi.ngramdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.NGramDecodingConfig.is_use_oldest", false]], "is_valid() (tensorrt_llm.functional.moeallreduceparams method)": [[83, "tensorrt_llm.functional.MoEAllReduceParams.is_valid", false]], "is_valid() (tensorrt_llm.layers.attention.attentionparams method)": [[84, "tensorrt_llm.layers.attention.AttentionParams.is_valid", false]], "is_valid() (tensorrt_llm.layers.attention.keyvaluecacheparams method)": [[84, "tensorrt_llm.layers.attention.KeyValueCacheParams.is_valid", false]], "is_valid_cross_attn() (tensorrt_llm.layers.attention.attentionparams method)": [[84, "tensorrt_llm.layers.attention.AttentionParams.is_valid_cross_attn", false]], "joint_attn_forward() (tensorrt_llm.layers.attention.diffusersattention method)": [[84, "tensorrt_llm.layers.attention.DiffusersAttention.joint_attn_forward", false]], "json (tensorrt_llm.llmapi.guideddecodingparams attribute)": [[71, "tensorrt_llm.llmapi.GuidedDecodingParams.json", false]], "json_object (tensorrt_llm.llmapi.guideddecodingparams attribute)": [[71, "tensorrt_llm.llmapi.GuidedDecodingParams.json_object", false]], "keyvaluecacheparams (class in tensorrt_llm.layers.attention)": [[84, "tensorrt_llm.layers.attention.KeyValueCacheParams", false]], "kv_cache_quant_algo (tensorrt_llm.llmapi.quantconfig attribute)": [[71, "tensorrt_llm.llmapi.QuantConfig.kv_cache_quant_algo", false]], "kv_cache_type (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.kv_cache_type", false]], "kv_cache_type (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.kv_cache_type", false]], "kv_cache_type (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.kv_cache_type", false]], "kv_dtype (tensorrt_llm.models.pretrainedconfig property)": [[85, "tensorrt_llm.models.PretrainedConfig.kv_dtype", false]], "kvcacheconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.KvCacheConfig", false]], "kvcachemanager (class in tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.KVCacheManager", false]], "kvcacheretentionconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.KvCacheRetentionConfig", false]], "kvcacheretentionconfig.tokenrangeretentionconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.KvCacheRetentionConfig.TokenRangeRetentionConfig", false]], "labelembedding (class in tensorrt_llm.layers.embedding)": [[84, "tensorrt_llm.layers.embedding.LabelEmbedding", false]], "language_adapter_config (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.language_adapter_config", false]], "last_layer (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.last_layer", false]], "last_process_for_ub (tensorrt_llm.functional.allreducefusionop attribute)": [[83, "tensorrt_llm.functional.AllReduceFusionOp.LAST_PROCESS_FOR_UB", false]], "layer_norm() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.layer_norm", false]], "layer_quant_mode (tensorrt_llm.llmapi.quantconfig property)": [[71, "tensorrt_llm.llmapi.QuantConfig.layer_quant_mode", false]], "layer_types (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.layer_types", false]], "layernorm (class in tensorrt_llm.layers.normalization)": [[84, "tensorrt_llm.layers.normalization.LayerNorm", false]], "layernorm (tensorrt_llm.functional.layernormtype attribute)": [[83, "tensorrt_llm.functional.LayerNormType.LayerNorm", false]], "layernormpositiontype (class in tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.LayerNormPositionType", false]], "layernormtype (class in tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.LayerNormType", false]], "learned_absolute (tensorrt_llm.functional.positionembeddingtype attribute)": [[83, "tensorrt_llm.functional.PositionEmbeddingType.learned_absolute", false]], "length (tensorrt_llm.llmapi.completionoutput attribute)": [[71, "tensorrt_llm.llmapi.CompletionOutput.length", false]], "length (tensorrt_llm.llmapi.completionoutput property)": [[71, "id2", false]], "length_penalty (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.length_penalty", false]], "length_penalty (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.length_penalty", false]], "linear (class in tensorrt_llm.layers.linear)": [[84, "tensorrt_llm.layers.linear.Linear", false]], "linear (tensorrt_llm.functional.rotaryscalingtype attribute)": [[83, "tensorrt_llm.functional.RotaryScalingType.linear", false]], "linearactivation (class in tensorrt_llm.layers.mlp)": [[84, "tensorrt_llm.layers.mlp.LinearActivation", false]], "linearapproximategelu (class in tensorrt_llm.layers.mlp)": [[84, "tensorrt_llm.layers.mlp.LinearApproximateGELU", false]], "linearbase (class in tensorrt_llm.layers.linear)": [[84, "tensorrt_llm.layers.linear.LinearBase", false]], "lineargeglu (class in tensorrt_llm.layers.mlp)": [[84, "tensorrt_llm.layers.mlp.LinearGEGLU", false]], "lineargelu (class in tensorrt_llm.layers.mlp)": [[84, "tensorrt_llm.layers.mlp.LinearGELU", false]], "linearswiglu (class in tensorrt_llm.layers.mlp)": [[84, "tensorrt_llm.layers.mlp.LinearSwiGLU", false]], "llama3 (tensorrt_llm.functional.rotaryscalingtype attribute)": [[83, "tensorrt_llm.functional.RotaryScalingType.llama3", false]], "llamaconfig (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.LLaMAConfig", false]], "llamaforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.LLaMAForCausalLM", false]], "llamamodel (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.LLaMAModel", false]], "llavanextvisionconfig (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.LlavaNextVisionConfig", false]], "llavanextvisionwrapper (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.LlavaNextVisionWrapper", false]], "llm (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.LLM", false]], "llm_engine_dir (tensorrt_llm.runtime.multimodalmodelrunner property)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.llm_engine_dir", false]], "llm_id (tensorrt_llm.llmapi.llm attribute)": [[71, "tensorrt_llm.llmapi.LLM.llm_id", false]], "llm_id (tensorrt_llm.llmapi.llm property)": [[71, "id0", false]], "llmargs (in module tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.LlmArgs", false]], "load() (tensorrt_llm.models.pretrainedmodel method)": [[85, "tensorrt_llm.models.PretrainedModel.load", false]], "load() (tensorrt_llm.models.sd3transformer2dmodel method)": [[85, "tensorrt_llm.models.SD3Transformer2DModel.load", false]], "load_balancer (tensorrt_llm.llmapi.moeconfig attribute)": [[71, "tensorrt_llm.llmapi.MoeConfig.load_balancer", false]], "load_format (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.load_format", false]], "load_test_audio() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.load_test_audio", false]], "load_test_data() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.load_test_data", false]], "locate_accepted_draft_tokens() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.locate_accepted_draft_tokens", false]], "location (tensorrt_llm.functional.tensor property)": [[83, "tensorrt_llm.functional.Tensor.location", false]], "log() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.log", false]], "log() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.log", false]], "log_softmax() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.log_softmax", false]], "logits_processor (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.logits_processor", false]], "logitsprocessor (class in tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.LogitsProcessor", false]], "logitsprocessorlist (class in tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.LogitsProcessorList", false]], "logprobs (tensorrt_llm.llmapi.completionoutput attribute)": [[71, "tensorrt_llm.llmapi.CompletionOutput.logprobs", false]], "logprobs (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.logprobs", false]], "logprobs_diff (tensorrt_llm.llmapi.completionoutput attribute)": [[71, "tensorrt_llm.llmapi.CompletionOutput.logprobs_diff", false]], "logprobs_diff (tensorrt_llm.llmapi.completionoutput property)": [[71, "id3", false]], "long_rope (tensorrt_llm.functional.positionembeddingtype attribute)": [[83, "tensorrt_llm.functional.PositionEmbeddingType.long_rope", false]], "longrope (tensorrt_llm.functional.rotaryscalingtype attribute)": [[83, "tensorrt_llm.functional.RotaryScalingType.longrope", false]], "lookahead_config (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.lookahead_config", false]], "lookahead_decoding (tensorrt_llm.models.speculativedecodingmode attribute)": [[85, "tensorrt_llm.models.SpeculativeDecodingMode.LOOKAHEAD_DECODING", false]], "lookaheaddecodingconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.LookaheadDecodingConfig", false]], "lora_config (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.lora_config", false]], "lora_plugin (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.lora_plugin", false]], "lora_plugin() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.lora_plugin", false]], "lora_target_modules (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.lora_target_modules", false]], "low_latency_gemm() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.low_latency_gemm", false]], "low_latency_gemm_swiglu() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.low_latency_gemm_swiglu", false]], "lowprecision (tensorrt_llm.functional.allreducestrategy attribute)": [[83, "tensorrt_llm.functional.AllReduceStrategy.LOWPRECISION", false]], "lt() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.lt", false]], "make_causal_mask() (in module tensorrt_llm.layers.attention)": [[84, "tensorrt_llm.layers.attention.make_causal_mask", false]], "mamba_conv1d() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.mamba_conv1d", false]], "mamba_conv1d_plugin (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.mamba_conv1d_plugin", false]], "mambaforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.MambaForCausalLM", false]], "mapping (tensorrt_llm.runtime.generationsession attribute)": [[88, "tensorrt_llm.runtime.GenerationSession.mapping", false]], "mapping (tensorrt_llm.runtime.modelrunner property)": [[88, "tensorrt_llm.runtime.ModelRunner.mapping", false]], "mark_output() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.mark_output", false]], "masked_scatter() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.masked_scatter", false]], "masked_select() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.masked_select", false]], "matmul() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.matmul", false]], "max() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.max", false]], "max() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.max", false]], "max_attention_window (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.KvCacheConfig.max_attention_window", false]], "max_attention_window_size (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.max_attention_window_size", false]], "max_batch_size (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.max_batch_size", false]], "max_batch_size (tensorrt_llm.llmapi.cudagraphconfig attribute)": [[71, "tensorrt_llm.llmapi.CudaGraphConfig.max_batch_size", false]], "max_batch_size (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.max_batch_size", false]], "max_beam_width (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.max_beam_width", false]], "max_beam_width (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.max_beam_width", false]], "max_cache_storage_gb (tensorrt_llm.llmapi.buildcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildCacheConfig.max_cache_storage_gb", false]], "max_cache_storage_gb (tensorrt_llm.llmapi.buildcacheconfig property)": [[71, "id8", false]], "max_cpu_loras (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.max_cpu_loras", false]], "max_cpu_loras (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.max_cpu_loras", false]], "max_draft_len (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.max_draft_len", false]], "max_draft_tokens (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.max_draft_tokens", false]], "max_encoder_input_len (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.max_encoder_input_len", false]], "max_input_len (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.max_input_len", false]], "max_lora_rank (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.max_lora_rank", false]], "max_lora_rank (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.max_lora_rank", false]], "max_loras (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.max_loras", false]], "max_loras (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.max_loras", false]], "max_matching_ngram_size (tensorrt_llm.llmapi.ngramdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.NGramDecodingConfig.max_matching_ngram_size", false]], "max_medusa_tokens (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.max_medusa_tokens", false]], "max_new_tokens (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.max_new_tokens", false]], "max_ngram_size (tensorrt_llm.llmapi.lookaheaddecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.LookaheadDecodingConfig.max_ngram_size", false]], "max_non_leaves_per_layer (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.EagleDecodingConfig.max_non_leaves_per_layer", false]], "max_num_tokens (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.max_num_tokens", false]], "max_num_tokens (tensorrt_llm.llmapi.moeconfig attribute)": [[71, "tensorrt_llm.llmapi.MoeConfig.max_num_tokens", false]], "max_prompt_adapter_token (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.max_prompt_adapter_token", false]], "max_prompt_embedding_table_size (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.max_prompt_embedding_table_size", false]], "max_prompt_embedding_table_size (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.max_prompt_embedding_table_size", false]], "max_prompt_embedding_table_size (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.max_prompt_embedding_table_size", false]], "max_prompt_embedding_table_size (tensorrt_llm.runtime.modelrunner property)": [[88, "tensorrt_llm.runtime.ModelRunner.max_prompt_embedding_table_size", false]], "max_prompt_embedding_table_size (tensorrt_llm.runtime.modelrunnercpp property)": [[88, "tensorrt_llm.runtime.ModelRunnerCpp.max_prompt_embedding_table_size", false]], "max_records (tensorrt_llm.llmapi.buildcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildCacheConfig.max_records", false]], "max_records (tensorrt_llm.llmapi.buildcacheconfig property)": [[71, "id9", false]], "max_seq_len (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.max_seq_len", false]], "max_sequence_length (tensorrt_llm.runtime.modelrunner property)": [[88, "tensorrt_llm.runtime.ModelRunner.max_sequence_length", false]], "max_sequence_length (tensorrt_llm.runtime.modelrunnercpp property)": [[88, "tensorrt_llm.runtime.ModelRunnerCpp.max_sequence_length", false]], "max_tokens (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.KvCacheConfig.max_tokens", false]], "max_tokens (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.max_tokens", false]], "max_tokens_in_buffer (tensorrt_llm.llmapi.cachetransceiverconfig attribute)": [[71, "tensorrt_llm.llmapi.CacheTransceiverConfig.max_tokens_in_buffer", false]], "max_utilization (tensorrt_llm.llmapi.capacityschedulerpolicy attribute)": [[71, "tensorrt_llm.llmapi.CapacitySchedulerPolicy.MAX_UTILIZATION", false]], "max_verification_set_size (tensorrt_llm.llmapi.lookaheaddecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.LookaheadDecodingConfig.max_verification_set_size", false]], "max_window_size (tensorrt_llm.llmapi.lookaheaddecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.LookaheadDecodingConfig.max_window_size", false]], "maximum() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.maximum", false]], "mean() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.mean", false]], "mean() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.mean", false]], "medusa (tensorrt_llm.models.speculativedecodingmode attribute)": [[85, "tensorrt_llm.models.SpeculativeDecodingMode.MEDUSA", false]], "medusa_choices (tensorrt_llm.llmapi.medusadecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.MedusaDecodingConfig.medusa_choices", false]], "medusa_decode_and_verify() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.medusa_decode_and_verify", false]], "medusa_paths (tensorrt_llm.runtime.generationsession attribute)": [[88, "tensorrt_llm.runtime.GenerationSession.medusa_paths", false]], "medusa_position_offsets (tensorrt_llm.runtime.generationsession attribute)": [[88, "tensorrt_llm.runtime.GenerationSession.medusa_position_offsets", false]], "medusa_temperature (tensorrt_llm.runtime.generationsession attribute)": [[88, "tensorrt_llm.runtime.GenerationSession.medusa_temperature", false]], "medusa_topks (tensorrt_llm.runtime.generationsession attribute)": [[88, "tensorrt_llm.runtime.GenerationSession.medusa_topks", false]], "medusa_tree_ids (tensorrt_llm.runtime.generationsession attribute)": [[88, "tensorrt_llm.runtime.GenerationSession.medusa_tree_ids", false]], "medusaconfig (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.MedusaConfig", false]], "medusadecodingconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.MedusaDecodingConfig", false]], "medusaforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.MedusaForCausalLm", false]], "meshgrid2d() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.meshgrid2d", false]], "min() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.min", false]], "min_latency (tensorrt_llm.functional.allreducestrategy attribute)": [[83, "tensorrt_llm.functional.AllReduceStrategy.MIN_LATENCY", false]], "min_length (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.min_length", false]], "min_p (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.min_p", false]], "min_p (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.min_p", false]], "min_tokens (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.min_tokens", false]], "minimum() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.minimum", false]], "mish (class in tensorrt_llm.layers.activation)": [[84, "tensorrt_llm.layers.activation.Mish", false]], "mixed_precision (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.MIXED_PRECISION", false]], "mllamaforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.MLLaMAForCausalLM", false]], "mlp (class in tensorrt_llm.layers.mlp)": [[84, "tensorrt_llm.layers.mlp.MLP", false]], "mlp (tensorrt_llm.functional.mlptype attribute)": [[83, "tensorrt_llm.functional.MLPType.MLP", false]], "mlptype (class in tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.MLPType", false]], "mnnvl (tensorrt_llm.functional.allreducestrategy attribute)": [[83, "tensorrt_llm.functional.AllReduceStrategy.MNNVL", false]], "model": [[35, "cmdoption-trtllm-serve-serve-arg-MODEL", false]], "model_config (tensorrt_llm.llmapi.cachetransceiverconfig attribute)": [[71, "tensorrt_llm.llmapi.CacheTransceiverConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.calibconfig attribute)": [[71, "tensorrt_llm.llmapi.CalibConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.cudagraphconfig attribute)": [[71, "tensorrt_llm.llmapi.CudaGraphConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.drafttargetdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.DraftTargetDecodingConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.dynamicbatchconfig attribute)": [[71, "tensorrt_llm.llmapi.DynamicBatchConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.EagleDecodingConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.extendedruntimeperfknobconfig attribute)": [[71, "tensorrt_llm.llmapi.ExtendedRuntimePerfKnobConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.KvCacheConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.lookaheaddecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.LookaheadDecodingConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.medusadecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.MedusaDecodingConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.moeconfig attribute)": [[71, "tensorrt_llm.llmapi.MoeConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.MTPDecodingConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.ngramdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.NGramDecodingConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.schedulerconfig attribute)": [[71, "tensorrt_llm.llmapi.SchedulerConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.torchcompileconfig attribute)": [[71, "tensorrt_llm.llmapi.TorchCompileConfig.model_config", false]], "model_config (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.model_config", false]], "model_config (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.model_config", false]], "model_config (tensorrt_llm.llmapi.userprovideddecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.UserProvidedDecodingConfig.model_config", false]], "model_name (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.model_name", false]], "model_post_init() (tensorrt_llm.llmapi.torchllmargs method)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.model_post_init", false]], "model_post_init() (tensorrt_llm.llmapi.trtllmargs method)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.model_post_init", false]], "modelconfig (class in tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.ModelConfig", false]], "modelrunner (class in tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.ModelRunner", false]], "modelrunnercpp (class in tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.ModelRunnerCpp", false]], "module": [[83, "module-tensorrt_llm", false], [83, "module-tensorrt_llm.functional", false], [84, "module-tensorrt_llm", false], [84, "module-tensorrt_llm.layers.activation", false], [84, "module-tensorrt_llm.layers.attention", false], [84, "module-tensorrt_llm.layers.cast", false], [84, "module-tensorrt_llm.layers.conv", false], [84, "module-tensorrt_llm.layers.embedding", false], [84, "module-tensorrt_llm.layers.linear", false], [84, "module-tensorrt_llm.layers.mlp", false], [84, "module-tensorrt_llm.layers.normalization", false], [84, "module-tensorrt_llm.layers.pooling", false], [85, "module-tensorrt_llm", false], [85, "module-tensorrt_llm.models", false], [86, "module-tensorrt_llm", false], [86, "module-tensorrt_llm.plugin", false], [87, "module-tensorrt_llm", false], [87, "module-tensorrt_llm.quantization", false], [88, "module-tensorrt_llm", false], [88, "module-tensorrt_llm.runtime", false]], "modulo() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.modulo", false]], "moe (tensorrt_llm.functional.sidestreamidtype attribute)": [[83, "tensorrt_llm.functional.SideStreamIDType.moe", false]], "moe_config (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.moe_config", false]], "moe_finalize_allreduce_residual_rms_norm (tensorrt_llm.functional.allreducefusionop attribute)": [[83, "tensorrt_llm.functional.AllReduceFusionOp.MOE_FINALIZE_ALLREDUCE_RESIDUAL_RMS_NORM", false]], "moeallreduceparams (class in tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.MoEAllReduceParams", false]], "moeconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.MoeConfig", false]], "monitor_memory (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.monitor_memory", false]], "mpicommsession (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.MpiCommSession", false]], "mptforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.MPTForCausalLM", false]], "mptmodel (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.MPTModel", false]], "mrope (tensorrt_llm.functional.positionembeddingtype attribute)": [[83, "tensorrt_llm.functional.PositionEmbeddingType.mrope", false]], "mrope (tensorrt_llm.functional.rotaryscalingtype attribute)": [[83, "tensorrt_llm.functional.RotaryScalingType.mrope", false]], "mropeparams (class in tensorrt_llm.layers.attention)": [[84, "tensorrt_llm.layers.attention.MropeParams", false]], "msg (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "id10", false], [71, "id13", false], [71, "id16", false], [71, "tensorrt_llm.llmapi.TorchLlmArgs.msg", false]], "msg (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "id19", false], [71, "id22", false], [71, "id25", false], [71, "id28", false], [71, "id31", false], [71, "tensorrt_llm.llmapi.TrtLlmArgs.msg", false]], "mtpdecodingconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.MTPDecodingConfig", false]], "mul() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.mul", false]], "multi_block_mode (tensorrt_llm.llmapi.extendedruntimeperfknobconfig attribute)": [[71, "tensorrt_llm.llmapi.ExtendedRuntimePerfKnobConfig.multi_block_mode", false]], "multimodalmodelrunner (class in tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner", false]], "multiply_and_lora() (tensorrt_llm.layers.linear.linearbase method)": [[84, "tensorrt_llm.layers.linear.LinearBase.multiply_and_lora", false]], "multiply_collect() (tensorrt_llm.layers.linear.linearbase method)": [[84, "tensorrt_llm.layers.linear.LinearBase.multiply_collect", false]], "multiply_collect() (tensorrt_llm.layers.linear.rowlinear method)": [[84, "tensorrt_llm.layers.linear.RowLinear.multiply_collect", false]], "n (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.n", false]], "name (tensorrt_llm.functional.tensor property)": [[83, "tensorrt_llm.functional.Tensor.name", false]], "name (tensorrt_llm.runtime.tensorinfo attribute)": [[88, "tensorrt_llm.runtime.TensorInfo.name", false]], "native_quant_flow (tensorrt_llm.models.gemmaforcausallm attribute)": [[85, "tensorrt_llm.models.GemmaForCausalLM.NATIVE_QUANT_FLOW", false]], "nccl (tensorrt_llm.functional.allreducestrategy attribute)": [[83, "tensorrt_llm.functional.AllReduceStrategy.NCCL", false]], "ndim() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.ndim", false]], "network (tensorrt_llm.functional.tensor property)": [[83, "tensorrt_llm.functional.Tensor.network", false]], "next_medusa_input_ids() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.next_medusa_input_ids", false]], "ngram (tensorrt_llm.models.speculativedecodingmode attribute)": [[85, "tensorrt_llm.models.SpeculativeDecodingMode.NGRAM", false]], "ngramdecodingconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.NGramDecodingConfig", false]], "no_quant (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.NO_QUANT", false]], "no_repeat_ngram_size (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.no_repeat_ngram_size", false]], "no_repeat_ngram_size (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.no_repeat_ngram_size", false]], "non_gated_version() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.non_gated_version", false]], "none (tensorrt_llm.functional.allreducefusionop attribute)": [[83, "tensorrt_llm.functional.AllReduceFusionOp.NONE", false]], "none (tensorrt_llm.functional.rotaryscalingtype attribute)": [[83, "tensorrt_llm.functional.RotaryScalingType.none", false]], "none (tensorrt_llm.models.speculativedecodingmode attribute)": [[85, "tensorrt_llm.models.SpeculativeDecodingMode.NONE", false]], "nonzero() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.nonzero", false]], "not_op() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.not_op", false]], "num_beams (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.num_beams", false]], "num_draft_tokens (tensorrt_llm.runtime.generationsession attribute)": [[88, "tensorrt_llm.runtime.GenerationSession.num_draft_tokens", false]], "num_eagle_layers (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.EagleDecodingConfig.num_eagle_layers", false]], "num_heads (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.num_heads", false]], "num_heads (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.num_heads", false]], "num_heads (tensorrt_llm.runtime.modelrunner property)": [[88, "tensorrt_llm.runtime.ModelRunner.num_heads", false]], "num_heads (tensorrt_llm.runtime.modelrunnercpp property)": [[88, "tensorrt_llm.runtime.ModelRunnerCpp.num_heads", false]], "num_kv_heads (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.num_kv_heads", false]], "num_kv_heads_per_cross_attn_layer (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.num_kv_heads_per_cross_attn_layer", false]], "num_kv_heads_per_layer (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.num_kv_heads_per_layer", false]], "num_layers (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.num_layers", false]], "num_layers (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.num_layers", false]], "num_layers (tensorrt_llm.runtime.modelrunner property)": [[88, "tensorrt_llm.runtime.ModelRunner.num_layers", false]], "num_layers (tensorrt_llm.runtime.modelrunnercpp property)": [[88, "tensorrt_llm.runtime.ModelRunnerCpp.num_layers", false]], "num_medusa_heads (tensorrt_llm.llmapi.medusadecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.MedusaDecodingConfig.num_medusa_heads", false]], "num_medusa_heads (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.num_medusa_heads", false]], "num_medusa_heads (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.num_medusa_heads", false]], "num_nextn_predict_layers (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.MTPDecodingConfig.num_nextn_predict_layers", false]], "num_nextn_predict_layers_from_model_config (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.MTPDecodingConfig.num_nextn_predict_layers_from_model_config", false]], "num_return_sequences (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.num_return_sequences", false]], "numel() (tensorrt_llm.runtime.tensorinfo method)": [[88, "tensorrt_llm.runtime.TensorInfo.numel", false]], "nvfp4 (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.NVFP4", false]], "nvinfer1 (c++ type)": [[1, "_CPPv48nvinfer1", false]], "onboard_blocks (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.KvCacheConfig.onboard_blocks", false]], "oneshot (tensorrt_llm.functional.allreducestrategy attribute)": [[83, "tensorrt_llm.functional.AllReduceStrategy.ONESHOT", false]], "op_and() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.op_and", false]], "op_or() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.op_or", false]], "op_xor() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.op_xor", false]], "opaque_state (tensorrt_llm.llmapi.disaggregatedparams attribute)": [[71, "tensorrt_llm.llmapi.DisaggregatedParams.opaque_state", false]], "opt_batch_size (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.opt_batch_size", false]], "opt_num_tokens (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.opt_num_tokens", false]], "optforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.OPTForCausalLM", false]], "optmodel (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.OPTModel", false]], "outer() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.outer", false]], "output_cum_log_probs (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.output_cum_log_probs", false]], "output_log_probs (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.output_log_probs", false]], "output_sequence_lengths (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.output_sequence_lengths", false]], "output_timing_cache (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.output_timing_cache", false]], "outputs (tensorrt_llm.llmapi.requestoutput attribute)": [[71, "tensorrt_llm.llmapi.RequestOutput.outputs", false]], "pad() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.pad", false]], "pad_id (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.pad_id", false]], "pad_id (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.pad_id", false]], "padding (tensorrt_llm.functional.attentionmasktype attribute)": [[83, "tensorrt_llm.functional.AttentionMaskType.padding", false]], "paged_kv_cache (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.paged_kv_cache", false]], "paged_state (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.paged_state", false]], "paged_state (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.paged_state", false]], "permute() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.permute", false]], "permute() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.permute", false]], "phi3forcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.Phi3ForCausalLM", false]], "phi3model (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.Phi3Model", false]], "phiforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.PhiForCausalLM", false]], "phimodel (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.PhiModel", false]], "pixartalphatextprojection (class in tensorrt_llm.layers.embedding)": [[84, "tensorrt_llm.layers.embedding.PixArtAlphaTextProjection", false]], "plugin_config (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.plugin_config", false]], "pluginconfig (class in tensorrt_llm.plugin)": [[86, "tensorrt_llm.plugin.PluginConfig", false]], "positionembeddingtype (class in tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.PositionEmbeddingType", false]], "post_layernorm (tensorrt_llm.functional.layernormpositiontype attribute)": [[83, "tensorrt_llm.functional.LayerNormPositionType.post_layernorm", false]], "posterior_threshold (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.EagleDecodingConfig.posterior_threshold", false]], "postprocess() (tensorrt_llm.layers.attention.attention method)": [[84, "tensorrt_llm.layers.attention.Attention.postprocess", false]], "postprocess() (tensorrt_llm.layers.attention.deepseekv2attention method)": [[84, "tensorrt_llm.layers.attention.DeepseekV2Attention.postprocess", false]], "postprocess() (tensorrt_llm.layers.embedding.embedding method)": [[84, "tensorrt_llm.layers.embedding.Embedding.postprocess", false]], "postprocess() (tensorrt_llm.layers.linear.linear method)": [[84, "tensorrt_llm.layers.linear.Linear.postprocess", false]], "pow() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.pow", false]], "pp_communicate_final_output_ids() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.pp_communicate_final_output_ids", false]], "pp_communicate_new_tokens() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.pp_communicate_new_tokens", false]], "pre_layernorm (tensorrt_llm.functional.layernormpositiontype attribute)": [[83, "tensorrt_llm.functional.LayerNormPositionType.pre_layernorm", false]], "pre_quant_scale (tensorrt_llm.llmapi.quantconfig attribute)": [[71, "tensorrt_llm.llmapi.QuantConfig.pre_quant_scale", false]], "precompute_relative_attention_bias() (tensorrt_llm.models.decodermodel method)": [[85, "tensorrt_llm.models.DecoderModel.precompute_relative_attention_bias", false]], "precompute_relative_attention_bias() (tensorrt_llm.models.encodermodel method)": [[85, "tensorrt_llm.models.EncoderModel.precompute_relative_attention_bias", false]], "precompute_relative_attention_bias() (tensorrt_llm.models.whisperencoder method)": [[85, "tensorrt_llm.models.WhisperEncoder.precompute_relative_attention_bias", false]], "prepare_inputs() (tensorrt_llm.models.chatglmforcausallm method)": [[85, "tensorrt_llm.models.ChatGLMForCausalLM.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.decodermodel method)": [[85, "tensorrt_llm.models.DecoderModel.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.dit method)": [[85, "tensorrt_llm.models.DiT.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.eagleforcausallm method)": [[85, "tensorrt_llm.models.EagleForCausalLM.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.encodermodel method)": [[85, "tensorrt_llm.models.EncoderModel.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.llavanextvisionwrapper method)": [[85, "tensorrt_llm.models.LlavaNextVisionWrapper.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.mambaforcausallm method)": [[85, "tensorrt_llm.models.MambaForCausalLM.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.mllamaforcausallm method)": [[85, "tensorrt_llm.models.MLLaMAForCausalLM.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.pretrainedmodel method)": [[85, "tensorrt_llm.models.PretrainedModel.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.recurrentgemmaforcausallm method)": [[85, "tensorrt_llm.models.RecurrentGemmaForCausalLM.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.sd3transformer2dmodel method)": [[85, "tensorrt_llm.models.SD3Transformer2DModel.prepare_inputs", false]], "prepare_inputs() (tensorrt_llm.models.whisperencoder method)": [[85, "tensorrt_llm.models.WhisperEncoder.prepare_inputs", false]], "prepare_position_ids_for_cogvlm() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.prepare_position_ids_for_cogvlm", false]], "prepare_recurrent_inputs() (tensorrt_llm.models.recurrentgemmaforcausallm method)": [[85, "tensorrt_llm.models.RecurrentGemmaForCausalLM.prepare_recurrent_inputs", false]], "preprocess() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.preprocess", false]], "presence_penalty (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.presence_penalty", false]], "presence_penalty (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.presence_penalty", false]], "pretrainedconfig (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.PretrainedConfig", false]], "pretrainedmodel (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.PretrainedModel", false]], "print_iter_log (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.print_iter_log", false]], "priority (tensorrt_llm.llmapi.kvcacheretentionconfig.tokenrangeretentionconfig property)": [[71, "tensorrt_llm.llmapi.KvCacheRetentionConfig.TokenRangeRetentionConfig.priority", false]], "process_input() (tensorrt_llm.runtime.encdecmodelrunner method)": [[88, "tensorrt_llm.runtime.EncDecModelRunner.process_input", false]], "process_logits_including_draft() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.process_logits_including_draft", false]], "prod() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.prod", false]], "profiler (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.profiler", false]], "profiling_verbosity (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.profiling_verbosity", false]], "prompt (tensorrt_llm.llmapi.requestoutput attribute)": [[71, "tensorrt_llm.llmapi.RequestOutput.prompt", false]], "prompt (tensorrt_llm.llmapi.requestoutput property)": [[71, "id6", false]], "prompt_logprobs (tensorrt_llm.llmapi.completionoutput attribute)": [[71, "tensorrt_llm.llmapi.CompletionOutput.prompt_logprobs", false]], "prompt_logprobs (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.prompt_logprobs", false]], "prompt_token_ids (tensorrt_llm.llmapi.requestoutput attribute)": [[71, "tensorrt_llm.llmapi.RequestOutput.prompt_token_ids", false]], "prompttuningembedding (class in tensorrt_llm.layers.embedding)": [[84, "tensorrt_llm.layers.embedding.PromptTuningEmbedding", false]], "ptuning_setup() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.ptuning_setup", false]], "ptuning_setup_fuyu() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.ptuning_setup_fuyu", false]], "ptuning_setup_llava_next() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.ptuning_setup_llava_next", false]], "ptuning_setup_phi3() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.ptuning_setup_phi3", false]], "ptuning_setup_pixtral() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.ptuning_setup_pixtral", false]], "python_e2e (tensorrt_llm.runtime.multimodalmodelrunner property)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.python_e2e", false]], "quant_algo (tensorrt_llm.llmapi.quantconfig attribute)": [[71, "tensorrt_llm.llmapi.QuantConfig.quant_algo", false]], "quant_algo (tensorrt_llm.models.pretrainedconfig property)": [[85, "tensorrt_llm.models.PretrainedConfig.quant_algo", false]], "quant_config (tensorrt_llm.llmapi.torchllmargs property)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.quant_config", false]], "quant_config (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.quant_config", false]], "quant_mode (tensorrt_llm.llmapi.quantconfig property)": [[71, "tensorrt_llm.llmapi.QuantConfig.quant_mode", false]], "quant_mode (tensorrt_llm.models.pretrainedconfig property)": [[85, "tensorrt_llm.models.PretrainedConfig.quant_mode", false]], "quant_mode (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.quant_mode", false]], "quant_mode (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.quant_mode", false]], "quantalgo (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.QuantAlgo", false]], "quantalgo (class in tensorrt_llm.quantization)": [[87, "tensorrt_llm.quantization.QuantAlgo", false]], "quantconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.QuantConfig", false]], "quantize() (tensorrt_llm.models.baichuanforcausallm class method)": [[85, "tensorrt_llm.models.BaichuanForCausalLM.quantize", false]], "quantize() (tensorrt_llm.models.chatglmforcausallm class method)": [[85, "tensorrt_llm.models.ChatGLMForCausalLM.quantize", false]], "quantize() (tensorrt_llm.models.cogvlmforcausallm class method)": [[85, "tensorrt_llm.models.CogVLMForCausalLM.quantize", false]], "quantize() (tensorrt_llm.models.gemmaforcausallm class method)": [[85, "tensorrt_llm.models.GemmaForCausalLM.quantize", false]], "quantize() (tensorrt_llm.models.gptforcausallm class method)": [[85, "tensorrt_llm.models.GPTForCausalLM.quantize", false]], "quantize() (tensorrt_llm.models.llamaforcausallm class method)": [[85, "tensorrt_llm.models.LLaMAForCausalLM.quantize", false]], "quantize() (tensorrt_llm.models.pretrainedmodel class method)": [[85, "tensorrt_llm.models.PretrainedModel.quantize", false]], "quantize_and_export() (in module tensorrt_llm.quantization)": [[87, "tensorrt_llm.quantization.quantize_and_export", false]], "quantmode (class in tensorrt_llm.quantization)": [[87, "tensorrt_llm.quantization.QuantMode", false]], "quick_gelu() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.quick_gelu", false]], "qwenforcausallmgenerationsession (class in tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.QWenForCausalLMGenerationSession", false]], "rand() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.rand", false]], "random_seed (tensorrt_llm.llmapi.calibconfig attribute)": [[71, "tensorrt_llm.llmapi.CalibConfig.random_seed", false]], "random_seed (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.random_seed", false]], "rank() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.rank", false]], "rearrange() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.rearrange", false]], "recurrentgemmaforcausallm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.RecurrentGemmaForCausalLM", false]], "recv() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.recv", false]], "redrafter_draft_len_per_beam (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.redrafter_draft_len_per_beam", false]], "redrafter_num_beams (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.redrafter_num_beams", false]], "redrafterforllamalm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.ReDrafterForLLaMALM", false]], "redrafterforqwenlm (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.ReDrafterForQWenLM", false]], "reduce() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.reduce", false]], "reduce_scatter() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.reduce_scatter", false]], "regex (tensorrt_llm.llmapi.guideddecodingparams attribute)": [[71, "tensorrt_llm.llmapi.GuidedDecodingParams.regex", false]], "relative (tensorrt_llm.functional.positionembeddingtype attribute)": [[83, "tensorrt_llm.functional.PositionEmbeddingType.relative", false]], "relaxed_delta (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.MTPDecodingConfig.relaxed_delta", false]], "relaxed_topk (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.MTPDecodingConfig.relaxed_topk", false]], "release() (tensorrt_llm.models.pretrainedmodel method)": [[85, "tensorrt_llm.models.PretrainedModel.release", false]], "relu() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.relu", false]], "remove_input_padding (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.remove_input_padding", false]], "remove_input_padding (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.remove_input_padding", false]], "remove_input_padding (tensorrt_llm.runtime.modelrunner property)": [[88, "tensorrt_llm.runtime.ModelRunner.remove_input_padding", false]], "remove_input_padding (tensorrt_llm.runtime.modelrunnercpp property)": [[88, "tensorrt_llm.runtime.ModelRunnerCpp.remove_input_padding", false]], "reorder_kv_cache_for_beam_search() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.reorder_kv_cache_for_beam_search", false]], "repeat() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.repeat", false]], "repeat() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.repeat", false]], "repeat_interleave() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.repeat_interleave", false]], "repetition_penalty (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.repetition_penalty", false]], "repetition_penalty (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.repetition_penalty", false]], "replace_all_uses_with() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.replace_all_uses_with", false]], "request_id (tensorrt_llm.llmapi.requestoutput attribute)": [[71, "tensorrt_llm.llmapi.RequestOutput.request_id", false]], "request_perf_metrics (tensorrt_llm.llmapi.completionoutput attribute)": [[71, "tensorrt_llm.llmapi.CompletionOutput.request_perf_metrics", false]], "request_type (tensorrt_llm.llmapi.disaggregatedparams attribute)": [[71, "tensorrt_llm.llmapi.DisaggregatedParams.request_type", false]], "requesterror (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.RequestError", false]], "requestoutput (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.RequestOutput", false]], "residual_rms_norm (tensorrt_llm.functional.allreducefusionop attribute)": [[83, "tensorrt_llm.functional.AllReduceFusionOp.RESIDUAL_RMS_NORM", false]], "residual_rms_norm_out_quant_fp8 (tensorrt_llm.functional.allreducefusionop attribute)": [[83, "tensorrt_llm.functional.AllReduceFusionOp.RESIDUAL_RMS_NORM_OUT_QUANT_FP8", false]], "residual_rms_norm_out_quant_nvfp4 (tensorrt_llm.functional.allreducefusionop attribute)": [[83, "tensorrt_llm.functional.AllReduceFusionOp.RESIDUAL_RMS_NORM_OUT_QUANT_NVFP4", false]], "residual_rms_norm_quant_fp8 (tensorrt_llm.functional.allreducefusionop attribute)": [[83, "tensorrt_llm.functional.AllReduceFusionOp.RESIDUAL_RMS_NORM_QUANT_FP8", false]], "residual_rms_norm_quant_nvfp4 (tensorrt_llm.functional.allreducefusionop attribute)": [[83, "tensorrt_llm.functional.AllReduceFusionOp.RESIDUAL_RMS_NORM_QUANT_NVFP4", false]], "residual_rms_prepost_norm (tensorrt_llm.functional.allreducefusionop attribute)": [[83, "tensorrt_llm.functional.AllReduceFusionOp.RESIDUAL_RMS_PREPOST_NORM", false]], "resource_manager (tensorrt_llm.llmapi.userprovideddecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.UserProvidedDecodingConfig.resource_manager", false]], "return_context_logits (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.return_context_logits", false]], "return_dict (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.return_dict", false]], "return_encoder_output (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.return_encoder_output", false]], "return_generation_logits (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.return_generation_logits", false]], "return_perf_metrics (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.return_perf_metrics", false]], "rg_lru() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.rg_lru", false]], "rms_norm() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.rms_norm", false]], "rmsnorm (class in tensorrt_llm.layers.normalization)": [[84, "tensorrt_llm.layers.normalization.RmsNorm", false]], "rmsnorm (tensorrt_llm.functional.layernormtype attribute)": [[83, "tensorrt_llm.functional.LayerNormType.RmsNorm", false]], "rnn_conv_dim_size (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.rnn_conv_dim_size", false]], "rnn_conv_dim_size (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.rnn_conv_dim_size", false]], "rnn_head_size (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.rnn_head_size", false]], "rnn_head_size (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.rnn_head_size", false]], "rnn_hidden_size (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.rnn_hidden_size", false]], "rnn_hidden_size (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.rnn_hidden_size", false]], "robertaforquestionanswering (in module tensorrt_llm.models)": [[85, "tensorrt_llm.models.RobertaForQuestionAnswering", false]], "robertaforsequenceclassification (in module tensorrt_llm.models)": [[85, "tensorrt_llm.models.RobertaForSequenceClassification", false]], "robertamodel (in module tensorrt_llm.models)": [[85, "tensorrt_llm.models.RobertaModel", false]], "rope_gpt_neox (tensorrt_llm.functional.positionembeddingtype attribute)": [[83, "tensorrt_llm.functional.PositionEmbeddingType.rope_gpt_neox", false]], "rope_gptj (tensorrt_llm.functional.positionembeddingtype attribute)": [[83, "tensorrt_llm.functional.PositionEmbeddingType.rope_gptj", false]], "ropeembeddingutils (class in tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.RopeEmbeddingUtils", false]], "rotaryscalingtype (class in tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.RotaryScalingType", false]], "rotate_every_two() (tensorrt_llm.functional.ropeembeddingutils static method)": [[83, "tensorrt_llm.functional.RopeEmbeddingUtils.rotate_every_two", false]], "rotate_half() (tensorrt_llm.functional.ropeembeddingutils static method)": [[83, "tensorrt_llm.functional.RopeEmbeddingUtils.rotate_half", false]], "round() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.round", false]], "rowlinear (class in tensorrt_llm.layers.linear)": [[84, "tensorrt_llm.layers.linear.RowLinear", false]], "run() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.run", false]], "run() (tensorrt_llm.runtime.session method)": [[88, "tensorrt_llm.runtime.Session.run", false]], "runtime (tensorrt_llm.runtime.generationsession attribute)": [[88, "tensorrt_llm.runtime.GenerationSession.runtime", false]], "runtime (tensorrt_llm.runtime.session property)": [[88, "tensorrt_llm.runtime.Session.runtime", false]], "samplingconfig (class in tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.SamplingConfig", false]], "samplingparams (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.SamplingParams", false]], "save_checkpoint() (tensorrt_llm.models.llavanextvisionwrapper method)": [[85, "tensorrt_llm.models.LlavaNextVisionWrapper.save_checkpoint", false]], "save_checkpoint() (tensorrt_llm.models.pretrainedmodel method)": [[85, "tensorrt_llm.models.PretrainedModel.save_checkpoint", false]], "scatter() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.scatter", false]], "scatter_nd() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.scatter_nd", false]], "schedulerconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.SchedulerConfig", false]], "sd35adalayernormzerox (class in tensorrt_llm.layers.normalization)": [[84, "tensorrt_llm.layers.normalization.SD35AdaLayerNormZeroX", false]], "sd3patchembed (class in tensorrt_llm.layers.embedding)": [[84, "tensorrt_llm.layers.embedding.SD3PatchEmbed", false]], "sd3transformer2dmodel (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.SD3Transformer2DModel", false]], "secondary_offload_min_priority (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.KvCacheConfig.secondary_offload_min_priority", false]], "seed (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.seed", false]], "select() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.select", false]], "select() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.select", false]], "selective_scan() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.selective_scan", false]], "send() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.send", false]], "serialize_engine() (tensorrt_llm.runtime.modelrunner method)": [[88, "tensorrt_llm.runtime.ModelRunner.serialize_engine", false]], "session (class in tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.Session", false]], "set_attn_processor() (tensorrt_llm.models.sd3transformer2dmodel method)": [[85, "tensorrt_llm.models.SD3Transformer2DModel.set_attn_processor", false]], "set_from_optional (c macro)": [[1, "c.SET_FROM_OPTIONAL", false]], "set_if_not_exist() (tensorrt_llm.models.pretrainedconfig method)": [[85, "tensorrt_llm.models.PretrainedConfig.set_if_not_exist", false]], "set_rank() (tensorrt_llm.models.pretrainedconfig method)": [[85, "tensorrt_llm.models.PretrainedConfig.set_rank", false]], "set_rel_attn_table() (tensorrt_llm.layers.attention.attention method)": [[84, "tensorrt_llm.layers.attention.Attention.set_rel_attn_table", false]], "set_shapes() (tensorrt_llm.runtime.session method)": [[88, "tensorrt_llm.runtime.Session.set_shapes", false]], "setup() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.setup", false]], "setup_embedding_parallel_mode() (tensorrt_llm.llmapi.trtllmargs method)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.setup_embedding_parallel_mode", false]], "setup_fake_prompts() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.setup_fake_prompts", false]], "setup_fake_prompts_qwen2vl() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.setup_fake_prompts_qwen2vl", false]], "setup_fake_prompts_vila() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.setup_fake_prompts_vila", false]], "setup_inputs() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.setup_inputs", false]], "shape (tensorrt_llm.functional.tensor property)": [[83, "tensorrt_llm.functional.Tensor.shape", false]], "shape (tensorrt_llm.runtime.tensorinfo attribute)": [[88, "tensorrt_llm.runtime.TensorInfo.shape", false]], "shape() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.shape", false]], "shutdown() (tensorrt_llm.llmapi.llm method)": [[71, "tensorrt_llm.llmapi.LLM.shutdown", false]], "shutdown() (tensorrt_llm.llmapi.mpicommsession method)": [[71, "tensorrt_llm.llmapi.MpiCommSession.shutdown", false]], "sidestreamidtype (class in tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.SideStreamIDType", false]], "sigmoid() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.sigmoid", false]], "silu() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.silu", false]], "sin() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.sin", false]], "sink_token_length (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.KvCacheConfig.sink_token_length", false]], "sink_token_length (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.sink_token_length", false]], "size (tensorrt_llm.functional.sliceinputtype attribute)": [[83, "tensorrt_llm.functional.SliceInputType.size", false]], "size() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.size", false]], "skip_cross_attn_blocks (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.skip_cross_attn_blocks", false]], "skip_cross_kv (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.skip_cross_kv", false]], "skip_special_tokens (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.skip_special_tokens", false]], "slice() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.slice", false]], "sliceinputtype (class in tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.SliceInputType", false]], "sliding_window_causal (tensorrt_llm.functional.attentionmasktype attribute)": [[83, "tensorrt_llm.functional.AttentionMaskType.sliding_window_causal", false]], "smoothquant_val (tensorrt_llm.llmapi.quantconfig attribute)": [[71, "tensorrt_llm.llmapi.QuantConfig.smoothquant_val", false]], "softmax() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.softmax", false]], "softplus() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.softplus", false]], "spaces_between_special_tokens (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.spaces_between_special_tokens", false]], "spec_dec_mode (tensorrt_llm.llmapi.eagledecodingconfig property)": [[71, "tensorrt_llm.llmapi.EagleDecodingConfig.spec_dec_mode", false]], "spec_dec_mode (tensorrt_llm.llmapi.mtpdecodingconfig property)": [[71, "tensorrt_llm.llmapi.MTPDecodingConfig.spec_dec_mode", false]], "specdecodingparams (class in tensorrt_llm.layers.attention)": [[84, "tensorrt_llm.layers.attention.SpecDecodingParams", false]], "speculative_decoding_mode (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.speculative_decoding_mode", false]], "speculativedecodingmode (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.SpeculativeDecodingMode", false]], "split() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.split", false]], "split() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.split", false]], "split_prompt_by_images() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.split_prompt_by_images", false]], "sqrt() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.sqrt", false]], "sqrt() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.sqrt", false]], "squared_relu() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.squared_relu", false]], "squeeze() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.squeeze", false]], "squeeze() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.squeeze", false]], "squeeze() (tensorrt_llm.runtime.tensorinfo method)": [[88, "tensorrt_llm.runtime.TensorInfo.squeeze", false]], "stack() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.stack", false]], "start (tensorrt_llm.functional.sliceinputtype attribute)": [[83, "tensorrt_llm.functional.SliceInputType.start", false]], "state_dtype (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.state_dtype", false]], "state_dtype (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.state_dtype", false]], "state_size (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.state_size", false]], "state_size (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.state_size", false]], "static (tensorrt_llm.llmapi.batchingtype attribute)": [[71, "tensorrt_llm.llmapi.BatchingType.STATIC", false]], "static_batch (tensorrt_llm.llmapi.capacityschedulerpolicy attribute)": [[71, "tensorrt_llm.llmapi.CapacitySchedulerPolicy.STATIC_BATCH", false]], "step() (tensorrt_llm.runtime.kvcachemanager method)": [[88, "tensorrt_llm.runtime.KVCacheManager.step", false]], "stop (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.stop", false]], "stop_reason (tensorrt_llm.llmapi.completionoutput attribute)": [[71, "tensorrt_llm.llmapi.CompletionOutput.stop_reason", false]], "stop_token_ids (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.stop_token_ids", false]], "stop_words_list (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.stop_words_list", false]], "stoppingcriteria (class in tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.StoppingCriteria", false]], "stoppingcriterialist (class in tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.StoppingCriteriaList", false]], "stream_interval (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.stream_interval", false]], "stride (tensorrt_llm.functional.sliceinputtype attribute)": [[83, "tensorrt_llm.functional.SliceInputType.stride", false]], "strongly_typed (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.strongly_typed", false]], "structural_tag (tensorrt_llm.llmapi.guideddecodingparams attribute)": [[71, "tensorrt_llm.llmapi.GuidedDecodingParams.structural_tag", false]], "sub() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.sub", false]], "submit() (tensorrt_llm.llmapi.mpicommsession method)": [[71, "tensorrt_llm.llmapi.MpiCommSession.submit", false]], "submit_sync() (tensorrt_llm.llmapi.mpicommsession method)": [[71, "tensorrt_llm.llmapi.MpiCommSession.submit_sync", false]], "sum() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.sum", false]], "supports_backend() (tensorrt_llm.llmapi.drafttargetdecodingconfig method)": [[71, "tensorrt_llm.llmapi.DraftTargetDecodingConfig.supports_backend", false]], "supports_backend() (tensorrt_llm.llmapi.lookaheaddecodingconfig method)": [[71, "tensorrt_llm.llmapi.LookaheadDecodingConfig.supports_backend", false]], "supports_backend() (tensorrt_llm.llmapi.medusadecodingconfig method)": [[71, "tensorrt_llm.llmapi.MedusaDecodingConfig.supports_backend", false]], "supports_backend() (tensorrt_llm.llmapi.mtpdecodingconfig method)": [[71, "tensorrt_llm.llmapi.MTPDecodingConfig.supports_backend", false]], "supports_backend() (tensorrt_llm.llmapi.ngramdecodingconfig method)": [[71, "tensorrt_llm.llmapi.NGramDecodingConfig.supports_backend", false]], "swiglu() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.swiglu", false]], "sync_quant_config_with_kv_cache_config_dtype() (tensorrt_llm.llmapi.torchllmargs method)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.sync_quant_config_with_kv_cache_config_dtype", false]], "tanh() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.tanh", false]], "temperature (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.temperature", false]], "temperature (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.temperature", false]], "tensor (class in tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.Tensor", false]], "tensorinfo (class in tensorrt_llm.runtime)": [[88, "tensorrt_llm.runtime.TensorInfo", false]], "tensorrt_llm": [[83, "module-tensorrt_llm", false], [84, "module-tensorrt_llm", false], [85, "module-tensorrt_llm", false], [86, "module-tensorrt_llm", false], [87, "module-tensorrt_llm", false], [88, "module-tensorrt_llm", false]], "tensorrt_llm (c++ type)": [[0, "_CPPv412tensorrt_llm", false], [1, "_CPPv412tensorrt_llm", false]], "tensorrt_llm.functional": [[83, "module-tensorrt_llm.functional", false]], "tensorrt_llm.layers.activation": [[84, "module-tensorrt_llm.layers.activation", false]], "tensorrt_llm.layers.attention": [[84, "module-tensorrt_llm.layers.attention", false]], "tensorrt_llm.layers.cast": [[84, "module-tensorrt_llm.layers.cast", false]], "tensorrt_llm.layers.conv": [[84, "module-tensorrt_llm.layers.conv", false]], "tensorrt_llm.layers.embedding": [[84, "module-tensorrt_llm.layers.embedding", false]], "tensorrt_llm.layers.linear": [[84, "module-tensorrt_llm.layers.linear", false]], "tensorrt_llm.layers.mlp": [[84, "module-tensorrt_llm.layers.mlp", false]], "tensorrt_llm.layers.normalization": [[84, "module-tensorrt_llm.layers.normalization", false]], "tensorrt_llm.layers.pooling": [[84, "module-tensorrt_llm.layers.pooling", false]], "tensorrt_llm.models": [[85, "module-tensorrt_llm.models", false]], "tensorrt_llm.plugin": [[86, "module-tensorrt_llm.plugin", false]], "tensorrt_llm.quantization": [[87, "module-tensorrt_llm.quantization", false]], "tensorrt_llm.runtime": [[88, "module-tensorrt_llm.runtime", false]], "tensorrt_llm::batch_manager (c++ type)": [[0, "_CPPv4N12tensorrt_llm13batch_managerE", false], [1, "_CPPv4N12tensorrt_llm13batch_managerE", false]], "tensorrt_llm::batch_manager::kv_cache_manager (c++ type)": [[0, "_CPPv4N12tensorrt_llm13batch_manager16kv_cache_managerE", false]], "tensorrt_llm::executor (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executorE", false]], "tensorrt_llm::executor::additionalmodeloutput (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutputE", false]], "tensorrt_llm::executor::additionalmodeloutput::additionalmodeloutput (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutput21AdditionalModelOutputENSt6stringEb", false]], "tensorrt_llm::executor::additionalmodeloutput::gathercontext (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutput13gatherContextE", false]], "tensorrt_llm::executor::additionalmodeloutput::name (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutput4nameE", false]], "tensorrt_llm::executor::additionalmodeloutput::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor21AdditionalModelOutputeqERK21AdditionalModelOutput", false]], "tensorrt_llm::executor::additionaloutput (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputE", false]], "tensorrt_llm::executor::additionaloutput::additionaloutput (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputENSt6stringE6Tensor", false], [0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputERK16AdditionalOutput", false], [0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputERR16AdditionalOutput", false]], "tensorrt_llm::executor::additionaloutput::name (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput4nameE", false]], "tensorrt_llm::executor::additionaloutput::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputaSERK16AdditionalOutput", false], [0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputaSERR16AdditionalOutput", false]], "tensorrt_llm::executor::additionaloutput::output (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput6outputE", false]], "tensorrt_llm::executor::additionaloutput::~additionaloutput (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputD0Ev", false]], "tensorrt_llm::executor::batchingtype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor12BatchingTypeE", false]], "tensorrt_llm::executor::batchingtype::kinflight (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12BatchingType9kINFLIGHTE", false]], "tensorrt_llm::executor::batchingtype::kstatic (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12BatchingType7kSTATICE", false]], "tensorrt_llm::executor::beamtokens (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor10BeamTokensE", false]], "tensorrt_llm::executor::bufferview (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor10BufferViewE", false]], "tensorrt_llm::executor::cachetransceiverconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfigE", false]], "tensorrt_llm::executor::cachetransceiverconfig::backendtype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig11BackendTypeE", false]], "tensorrt_llm::executor::cachetransceiverconfig::backendtype::default (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig11BackendType7DEFAULTE", false]], "tensorrt_llm::executor::cachetransceiverconfig::backendtype::mpi (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig11BackendType3MPIE", false]], "tensorrt_llm::executor::cachetransceiverconfig::backendtype::nixl (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig11BackendType4NIXLE", false]], "tensorrt_llm::executor::cachetransceiverconfig::backendtype::ucx (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig11BackendType3UCXE", false]], "tensorrt_llm::executor::cachetransceiverconfig::cachetransceiverconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig22CacheTransceiverConfigENSt8optionalI11BackendTypeEENSt8optionalI6size_tEE", false]], "tensorrt_llm::executor::cachetransceiverconfig::getbackendtype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22CacheTransceiverConfig14getBackendTypeEv", false]], "tensorrt_llm::executor::cachetransceiverconfig::getmaxtokensinbuffer (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22CacheTransceiverConfig20getMaxTokensInBufferEv", false]], "tensorrt_llm::executor::cachetransceiverconfig::mbackendtype (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig12mBackendTypeE", false]], "tensorrt_llm::executor::cachetransceiverconfig::mmaxtokensinbuffer (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig18mMaxTokensInBufferE", false]], "tensorrt_llm::executor::cachetransceiverconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22CacheTransceiverConfigeqERK22CacheTransceiverConfig", false]], "tensorrt_llm::executor::cachetransceiverconfig::setbackendtype (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig14setBackendTypeENSt8optionalI11BackendTypeEE", false]], "tensorrt_llm::executor::cachetransceiverconfig::setmaxtokensinbuffer (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig20setMaxTokensInBufferENSt8optionalI6size_tEE", false]], "tensorrt_llm::executor::capacityschedulerpolicy (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicyE", false]], "tensorrt_llm::executor::capacityschedulerpolicy::kguaranteed_no_evict (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicy20kGUARANTEED_NO_EVICTE", false]], "tensorrt_llm::executor::capacityschedulerpolicy::kmax_utilization (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicy16kMAX_UTILIZATIONE", false]], "tensorrt_llm::executor::capacityschedulerpolicy::kstatic_batch (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicy13kSTATIC_BATCHE", false]], "tensorrt_llm::executor::communicationmode (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor17CommunicationModeE", false]], "tensorrt_llm::executor::communicationmode::kleader (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor17CommunicationMode7kLEADERE", false]], "tensorrt_llm::executor::communicationmode::korchestrator (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor17CommunicationMode13kORCHESTRATORE", false]], "tensorrt_llm::executor::communicationtype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor17CommunicationTypeE", false]], "tensorrt_llm::executor::communicationtype::kmpi (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor17CommunicationType4kMPIE", false]], "tensorrt_llm::executor::contextchunkingpolicy (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicyE", false]], "tensorrt_llm::executor::contextchunkingpolicy::kequal_progress (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicy15kEQUAL_PROGRESSE", false]], "tensorrt_llm::executor::contextchunkingpolicy::kfirst_come_first_served (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicy24kFIRST_COME_FIRST_SERVEDE", false]], "tensorrt_llm::executor::contextphaseparams (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsE", false]], "tensorrt_llm::executor::contextphaseparams::contextphaseparams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeNSt8optionalI9VecTokensEE", false], [0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypePvNSt8optionalI9VecTokensEE", false], [0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeRKNSt6vectorIcEENSt8optionalI9VecTokensEE", false], [0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsERK18ContextPhaseParams", false], [0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsERR18ContextPhaseParams", false]], "tensorrt_llm::executor::contextphaseparams::deleter (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams7deleterEPKv", false]], "tensorrt_llm::executor::contextphaseparams::getdrafttokens (c++ function)": [[0, "_CPPv4NKR12tensorrt_llm8executor18ContextPhaseParams14getDraftTokensEv", false]], "tensorrt_llm::executor::contextphaseparams::getfirstgentokens (c++ function)": [[0, "_CPPv4NKR12tensorrt_llm8executor18ContextPhaseParams17getFirstGenTokensEv", false]], "tensorrt_llm::executor::contextphaseparams::getreqid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParams8getReqIdEv", false]], "tensorrt_llm::executor::contextphaseparams::getserializedstate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParams18getSerializedStateEv", false]], "tensorrt_llm::executor::contextphaseparams::getstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams8getStateEv", false], [0, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParams8getStateEv", false]], "tensorrt_llm::executor::contextphaseparams::mdrafttokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams12mDraftTokensE", false]], "tensorrt_llm::executor::contextphaseparams::mfirstgentokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams15mFirstGenTokensE", false]], "tensorrt_llm::executor::contextphaseparams::mreqid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams6mReqIdE", false]], "tensorrt_llm::executor::contextphaseparams::mstate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams6mStateE", false]], "tensorrt_llm::executor::contextphaseparams::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsaSERK18ContextPhaseParams", false], [0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsaSERR18ContextPhaseParams", false]], "tensorrt_llm::executor::contextphaseparams::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParamseqERK18ContextPhaseParams", false]], "tensorrt_llm::executor::contextphaseparams::popfirstgentokens (c++ function)": [[0, "_CPPv4NO12tensorrt_llm8executor18ContextPhaseParams17popFirstGenTokensEv", false]], "tensorrt_llm::executor::contextphaseparams::releasestate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams12releaseStateEv", false]], "tensorrt_llm::executor::contextphaseparams::requestidtype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams13RequestIdTypeE", false]], "tensorrt_llm::executor::contextphaseparams::stateptr (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams8StatePtrE", false]], "tensorrt_llm::executor::contextphaseparams::~contextphaseparams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsD0Ev", false]], "tensorrt_llm::executor::datatransceiverstate (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor20DataTransceiverStateE", false]], "tensorrt_llm::executor::datatransceiverstate::datatransceiverstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState20DataTransceiverStateEN8kv_cache10CacheStateEN8kv_cache9CommStateE", false], [0, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState20DataTransceiverStateEv", false]], "tensorrt_llm::executor::datatransceiverstate::getcachestate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverState13getCacheStateEv", false]], "tensorrt_llm::executor::datatransceiverstate::getcommstate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverState12getCommStateEv", false]], "tensorrt_llm::executor::datatransceiverstate::mcachestate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState11mCacheStateE", false]], "tensorrt_llm::executor::datatransceiverstate::mcommstate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState10mCommStateE", false]], "tensorrt_llm::executor::datatransceiverstate::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverStateeqERK20DataTransceiverState", false]], "tensorrt_llm::executor::datatransceiverstate::setcachestate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState13setCacheStateEN8kv_cache10CacheStateE", false]], "tensorrt_llm::executor::datatransceiverstate::setcommstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState12setCommStateEN8kv_cache9CommStateE", false]], "tensorrt_llm::executor::datatransceiverstate::tostring (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverState8toStringEv", false]], "tensorrt_llm::executor::datatype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor8DataTypeE", false]], "tensorrt_llm::executor::datatype::kbf16 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType5kBF16E", false]], "tensorrt_llm::executor::datatype::kbool (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType5kBOOLE", false]], "tensorrt_llm::executor::datatype::kfp16 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType5kFP16E", false]], "tensorrt_llm::executor::datatype::kfp32 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType5kFP32E", false]], "tensorrt_llm::executor::datatype::kfp8 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType4kFP8E", false]], "tensorrt_llm::executor::datatype::kint32 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType6kINT32E", false]], "tensorrt_llm::executor::datatype::kint64 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType6kINT64E", false]], "tensorrt_llm::executor::datatype::kint8 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType5kINT8E", false]], "tensorrt_llm::executor::datatype::kuint8 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType6kUINT8E", false]], "tensorrt_llm::executor::datatype::kunknown (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType8kUNKNOWNE", false]], "tensorrt_llm::executor::debugconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfigE", false]], "tensorrt_llm::executor::debugconfig::debugconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig11DebugConfigEbb9StringVec10SizeType32", false]], "tensorrt_llm::executor::debugconfig::getdebuginputtensors (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11DebugConfig20getDebugInputTensorsEv", false]], "tensorrt_llm::executor::debugconfig::getdebugoutputtensors (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11DebugConfig21getDebugOutputTensorsEv", false]], "tensorrt_llm::executor::debugconfig::getdebugtensornames (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11DebugConfig19getDebugTensorNamesEv", false]], "tensorrt_llm::executor::debugconfig::getdebugtensorsmaxiterations (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11DebugConfig28getDebugTensorsMaxIterationsEv", false]], "tensorrt_llm::executor::debugconfig::mdebuginputtensors (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig18mDebugInputTensorsE", false]], "tensorrt_llm::executor::debugconfig::mdebugoutputtensors (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig19mDebugOutputTensorsE", false]], "tensorrt_llm::executor::debugconfig::mdebugtensornames (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig17mDebugTensorNamesE", false]], "tensorrt_llm::executor::debugconfig::mdebugtensorsmaxiterations (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig26mDebugTensorsMaxIterationsE", false]], "tensorrt_llm::executor::debugconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11DebugConfigeqERK11DebugConfig", false]], "tensorrt_llm::executor::debugconfig::setdebuginputtensors (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig20setDebugInputTensorsEb", false]], "tensorrt_llm::executor::debugconfig::setdebugoutputtensors (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig21setDebugOutputTensorsEb", false]], "tensorrt_llm::executor::debugconfig::setdebugtensornames (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig19setDebugTensorNamesERK9StringVec", false]], "tensorrt_llm::executor::debugconfig::setdebugtensorsmaxiterations (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig28setDebugTensorsMaxIterationsE10SizeType32", false]], "tensorrt_llm::executor::debugconfig::stringvec (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig9StringVecE", false]], "tensorrt_llm::executor::debugtensorsperiteration (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor24DebugTensorsPerIterationE", false]], "tensorrt_llm::executor::debugtensorsperiteration::debugtensors (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor24DebugTensorsPerIteration12debugTensorsE", false]], "tensorrt_llm::executor::debugtensorsperiteration::iter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor24DebugTensorsPerIteration4iterE", false]], "tensorrt_llm::executor::decodingconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfigE", false]], "tensorrt_llm::executor::decodingconfig::decodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14DecodingConfigENSt8optionalI12DecodingModeEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI13MedusaChoicesEENSt8optionalI11EagleConfigEE", false]], "tensorrt_llm::executor::decodingconfig::enableseamlesslookaheaddecoding (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig31enableSeamlessLookaheadDecodingEv", false]], "tensorrt_llm::executor::decodingconfig::getdecodingmode (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig15getDecodingModeEv", false]], "tensorrt_llm::executor::decodingconfig::geteagleconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig14getEagleConfigEv", false]], "tensorrt_llm::executor::decodingconfig::getlookaheaddecodingconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig26getLookaheadDecodingConfigEv", false]], "tensorrt_llm::executor::decodingconfig::getlookaheaddecodingmaxnumrequest (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig33getLookaheadDecodingMaxNumRequestEv", false]], "tensorrt_llm::executor::decodingconfig::getmedusachoices (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig16getMedusaChoicesEv", false]], "tensorrt_llm::executor::decodingconfig::mdecodingmode (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig13mDecodingModeE", false]], "tensorrt_llm::executor::decodingconfig::meagleconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig12mEagleConfigE", false]], "tensorrt_llm::executor::decodingconfig::mlookaheaddecodingconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig24mLookaheadDecodingConfigE", false]], "tensorrt_llm::executor::decodingconfig::mlookaheaddecodingmaxnumrequest (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig31mLookaheadDecodingMaxNumRequestE", false]], "tensorrt_llm::executor::decodingconfig::mmedusachoices (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14mMedusaChoicesE", false]], "tensorrt_llm::executor::decodingconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14DecodingConfigeqERK14DecodingConfig", false]], "tensorrt_llm::executor::decodingconfig::setdecodingmode (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig15setDecodingModeERK12DecodingMode", false]], "tensorrt_llm::executor::decodingconfig::seteagleconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14setEagleConfigERK11EagleConfig", false]], "tensorrt_llm::executor::decodingconfig::setlookaheaddecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig26setLookaheadDecodingConfigERK23LookaheadDecodingConfig", false]], "tensorrt_llm::executor::decodingconfig::setmedusachoices (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig16setMedusaChoicesERK13MedusaChoices", false]], "tensorrt_llm::executor::decodingmode (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingModeE", false]], "tensorrt_llm::executor::decodingmode::allbitset (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9allBitSetE14UnderlyingType", false]], "tensorrt_llm::executor::decodingmode::anybitset (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9anyBitSetE14UnderlyingType", false]], "tensorrt_llm::executor::decodingmode::auto (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode4AutoEv", false]], "tensorrt_llm::executor::decodingmode::beamsearch (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode10BeamSearchEv", false]], "tensorrt_llm::executor::decodingmode::decodingmode (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode12DecodingModeE14UnderlyingType", false]], "tensorrt_llm::executor::decodingmode::eagle (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode5EagleEv", false]], "tensorrt_llm::executor::decodingmode::explicitdrafttokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode19ExplicitDraftTokensEv", false]], "tensorrt_llm::executor::decodingmode::externaldrafttokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode19ExternalDraftTokensEv", false]], "tensorrt_llm::executor::decodingmode::getname (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode7getNameEv", false]], "tensorrt_llm::executor::decodingmode::getstate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode8getStateEv", false]], "tensorrt_llm::executor::decodingmode::isauto (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isAutoEv", false]], "tensorrt_llm::executor::decodingmode::isbeamsearch (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isBeamSearchEv", false]], "tensorrt_llm::executor::decodingmode::iseagle (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode7isEagleEv", false]], "tensorrt_llm::executor::decodingmode::isexplicitdrafttokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode21isExplicitDraftTokensEv", false]], "tensorrt_llm::executor::decodingmode::isexternaldrafttokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode21isExternalDraftTokensEv", false]], "tensorrt_llm::executor::decodingmode::islookahead (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode11isLookaheadEv", false]], "tensorrt_llm::executor::decodingmode::ismedusa (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode8isMedusaEv", false]], "tensorrt_llm::executor::decodingmode::istopk (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isTopKEv", false]], "tensorrt_llm::executor::decodingmode::istopkandtopp (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode13isTopKandTopPEv", false]], "tensorrt_llm::executor::decodingmode::istopkortopp (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isTopKorTopPEv", false]], "tensorrt_llm::executor::decodingmode::istopp (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isTopPEv", false]], "tensorrt_llm::executor::decodingmode::isusebantokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseBanTokensEv", false]], "tensorrt_llm::executor::decodingmode::isusebanwords (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode13isUseBanWordsEv", false]], "tensorrt_llm::executor::decodingmode::isuseexpliciteosstop (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode20isUseExplicitEosStopEv", false]], "tensorrt_llm::executor::decodingmode::isusefrequencypenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode21isUseFrequencyPenaltyEv", false]], "tensorrt_llm::executor::decodingmode::isusemaxlengthstop (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode18isUseMaxLengthStopEv", false]], "tensorrt_llm::executor::decodingmode::isuseminlength (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseMinLengthEv", false]], "tensorrt_llm::executor::decodingmode::isuseminp (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9isUseMinPEv", false]], "tensorrt_llm::executor::decodingmode::isusenorepeatngramsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseNoRepeatNgramSizeEv", false]], "tensorrt_llm::executor::decodingmode::isuseoccurrencepenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseOccurrencePenaltyEv", false]], "tensorrt_llm::executor::decodingmode::isusepenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isUsePenaltyEv", false]], "tensorrt_llm::executor::decodingmode::isusepresencepenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode20isUsePresencePenaltyEv", false]], "tensorrt_llm::executor::decodingmode::isuserepetitionpenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseRepetitionPenaltyEv", false]], "tensorrt_llm::executor::decodingmode::isusestopcriteria (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode17isUseStopCriteriaEv", false]], "tensorrt_llm::executor::decodingmode::isusestopwords (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseStopWordsEv", false]], "tensorrt_llm::executor::decodingmode::isusetemperature (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode16isUseTemperatureEv", false]], "tensorrt_llm::executor::decodingmode::isusevariablebeamwidthsearch (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode28isUseVariableBeamWidthSearchEv", false]], "tensorrt_llm::executor::decodingmode::kauto (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kAutoE", false]], "tensorrt_llm::executor::decodingmode::kbeamsearch (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode11kBeamSearchE", false]], "tensorrt_llm::executor::decodingmode::keagle (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode6kEagleE", false]], "tensorrt_llm::executor::decodingmode::kexplicitdrafttokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode20kExplicitDraftTokensE", false]], "tensorrt_llm::executor::decodingmode::kexternaldrafttokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode20kExternalDraftTokensE", false]], "tensorrt_llm::executor::decodingmode::klookahead (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode10kLookaheadE", false]], "tensorrt_llm::executor::decodingmode::kmedusa (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode7kMedusaE", false]], "tensorrt_llm::executor::decodingmode::knumflags (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode9kNumFlagsE", false]], "tensorrt_llm::executor::decodingmode::ktopk (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kTopKE", false]], "tensorrt_llm::executor::decodingmode::ktopktopp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode9kTopKTopPE", false]], "tensorrt_llm::executor::decodingmode::ktopp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kTopPE", false]], "tensorrt_llm::executor::decodingmode::kusebantokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseBanTokensE", false]], "tensorrt_llm::executor::decodingmode::kusebanwords (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode12kUseBanWordsE", false]], "tensorrt_llm::executor::decodingmode::kuseexpliciteosstop (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode19kUseExplicitEosStopE", false]], "tensorrt_llm::executor::decodingmode::kusefrequencypenalties (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode22kUseFrequencyPenaltiesE", false]], "tensorrt_llm::executor::decodingmode::kusemaxlengthstop (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode17kUseMaxLengthStopE", false]], "tensorrt_llm::executor::decodingmode::kuseminlength (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseMinLengthE", false]], "tensorrt_llm::executor::decodingmode::kuseminp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode8kUseMinPE", false]], "tensorrt_llm::executor::decodingmode::kusenorepeatngramsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode21kUseNoRepeatNgramSizeE", false]], "tensorrt_llm::executor::decodingmode::kuseoccurrencepenalties (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode23kUseOccurrencePenaltiesE", false]], "tensorrt_llm::executor::decodingmode::kusepenalties (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUsePenaltiesE", false]], "tensorrt_llm::executor::decodingmode::kusepresencepenalties (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode21kUsePresencePenaltiesE", false]], "tensorrt_llm::executor::decodingmode::kuserepetitionpenalties (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode23kUseRepetitionPenaltiesE", false]], "tensorrt_llm::executor::decodingmode::kusestandardstopcriteria (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode24kUseStandardStopCriteriaE", false]], "tensorrt_llm::executor::decodingmode::kusestopwords (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseStopWordsE", false]], "tensorrt_llm::executor::decodingmode::kusetemperature (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode15kUseTemperatureE", false]], "tensorrt_llm::executor::decodingmode::kusevariablebeamwidthsearch (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode27kUseVariableBeamWidthSearchE", false]], "tensorrt_llm::executor::decodingmode::lookahead (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode9LookaheadEv", false]], "tensorrt_llm::executor::decodingmode::medusa (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode6MedusaEv", false]], "tensorrt_llm::executor::decodingmode::mstate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode6mStateE", false]], "tensorrt_llm::executor::decodingmode::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingModeeqERK12DecodingMode", false]], "tensorrt_llm::executor::decodingmode::setbitto (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode8setBitToE14UnderlyingTypeb", false]], "tensorrt_llm::executor::decodingmode::topk (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode4TopKEv", false]], "tensorrt_llm::executor::decodingmode::topktopp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode8TopKTopPEv", false]], "tensorrt_llm::executor::decodingmode::topp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode4TopPEv", false]], "tensorrt_llm::executor::decodingmode::underlyingtype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode14UnderlyingTypeE", false]], "tensorrt_llm::executor::decodingmode::usebantokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useBanTokensEb", false]], "tensorrt_llm::executor::decodingmode::usebanwords (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode11useBanWordsEb", false]], "tensorrt_llm::executor::decodingmode::useexpliciteosstop (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode18useExplicitEosStopEb", false]], "tensorrt_llm::executor::decodingmode::usefrequencypenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode19useFrequencyPenaltyEb", false]], "tensorrt_llm::executor::decodingmode::usemaxlengthstop (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode16useMaxLengthStopEb", false]], "tensorrt_llm::executor::decodingmode::useminlength (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useMinLengthEb", false]], "tensorrt_llm::executor::decodingmode::useminp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode7useMinPEb", false]], "tensorrt_llm::executor::decodingmode::usenorepeatngramsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useNoRepeatNgramSizeEb", false]], "tensorrt_llm::executor::decodingmode::useoccurrencepenalties (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode22useOccurrencePenaltiesEb", false]], "tensorrt_llm::executor::decodingmode::usepresencepenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode18usePresencePenaltyEb", false]], "tensorrt_llm::executor::decodingmode::userepetitionpenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useRepetitionPenaltyEb", false]], "tensorrt_llm::executor::decodingmode::usestopwords (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useStopWordsEb", false]], "tensorrt_llm::executor::decodingmode::usetemperature (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode14useTemperatureEb", false]], "tensorrt_llm::executor::decodingmode::usevariablebeamwidthsearch (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode26useVariableBeamWidthSearchEb", false]], "tensorrt_llm::executor::detail (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor6detailE", false]], "tensorrt_llm::executor::detail::dimtype64 (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor6detail9DimType64E", false]], "tensorrt_llm::executor::detail::ofitensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE", false]], "tensorrt_llm::executor::detail::toitensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6detail9toITensorERK6Tensor", false]], "tensorrt_llm::executor::disagg_executor (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executorE", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestratorE", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::awaitcontextresponses (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator21awaitContextResponsesERKNSt8optionalINSt6chrono12millisecondsEEENSt8optionalIiEE", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::awaitgenerationresponses (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator24awaitGenerationResponsesERKNSt8optionalINSt6chrono12millisecondsEEENSt8optionalIiEE", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::canenqueue (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator10canEnqueueEv", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::disaggexecutororchestrator (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator26DisaggExecutorOrchestratorERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorIN8executor14ExecutorConfigEEERKNSt6vectorIN8executor14ExecutorConfigEEEbb", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::enqueuecontext (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator14enqueueContextERKNSt6vectorIN5texec7RequestEEENSt8optionalIiEEb", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::enqueuegeneration (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator17enqueueGenerationERKNSt6vectorIN5texec7RequestEEERKNSt6vectorI6IdTypeEENSt8optionalIiEEb", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::getcontextexecutors (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator19getContextExecutorsEv", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::getgenexecutors (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator15getGenExecutorsEv", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::mimpl (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator5mImplE", false]], "tensorrt_llm::executor::disagg_executor::disaggexecutororchestrator::~disaggexecutororchestrator (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestratorD0Ev", false]], "tensorrt_llm::executor::disagg_executor::responsewithid (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdE", false]], "tensorrt_llm::executor::disagg_executor::responsewithid::gid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId3gidE", false]], "tensorrt_llm::executor::disagg_executor::responsewithid::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdaSERK14ResponseWithId", false], [0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdaSERR14ResponseWithId", false]], "tensorrt_llm::executor::disagg_executor::responsewithid::response (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId8responseE", false]], "tensorrt_llm::executor::disagg_executor::responsewithid::responsewithid (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERK14ResponseWithId", false], [0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERKN12tensorrt_llm8executor8ResponseE6IdType", false], [0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERR14ResponseWithId", false], [0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERRN12tensorrt_llm8executor8ResponseE6IdType", false]], "tensorrt_llm::executor::disagg_executor::responsewithid::~responsewithid (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdD0Ev", false]], "tensorrt_llm::executor::disservingrequeststats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor22DisServingRequestStatsE", false]], "tensorrt_llm::executor::disservingrequeststats::kvcachesize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22DisServingRequestStats11kvCacheSizeE", false]], "tensorrt_llm::executor::disservingrequeststats::kvcachetransferms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22DisServingRequestStats17kvCacheTransferMSE", false]], "tensorrt_llm::executor::dynamicbatchconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfigE", false]], "tensorrt_llm::executor::dynamicbatchconfig::dynamicbatchconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig18DynamicBatchConfigEbb10SizeType32NSt6vectorINSt4pairI10SizeType3210SizeType32EEEE", false]], "tensorrt_llm::executor::dynamicbatchconfig::getbatchsizetable (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18DynamicBatchConfig17getBatchSizeTableEv", false]], "tensorrt_llm::executor::dynamicbatchconfig::getdynamicbatchmovingaveragewindow (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18DynamicBatchConfig34getDynamicBatchMovingAverageWindowEv", false]], "tensorrt_llm::executor::dynamicbatchconfig::getenablebatchsizetuning (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18DynamicBatchConfig24getEnableBatchSizeTuningEv", false]], "tensorrt_llm::executor::dynamicbatchconfig::getenablemaxnumtokenstuning (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18DynamicBatchConfig27getEnableMaxNumTokensTuningEv", false]], "tensorrt_llm::executor::dynamicbatchconfig::kdefaultbatchsizetable (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig22kDefaultBatchSizeTableE", false]], "tensorrt_llm::executor::dynamicbatchconfig::kdefaultdynamicbatchmovingaveragewindow (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig39kDefaultDynamicBatchMovingAverageWindowE", false]], "tensorrt_llm::executor::dynamicbatchconfig::mbatchsizetable (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig15mBatchSizeTableE", false]], "tensorrt_llm::executor::dynamicbatchconfig::mdynamicbatchmovingaveragewindow (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig32mDynamicBatchMovingAverageWindowE", false]], "tensorrt_llm::executor::dynamicbatchconfig::menablebatchsizetuning (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig22mEnableBatchSizeTuningE", false]], "tensorrt_llm::executor::dynamicbatchconfig::menablemaxnumtokenstuning (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig25mEnableMaxNumTokensTuningE", false]], "tensorrt_llm::executor::eaglechoices (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor12EagleChoicesE", false]], "tensorrt_llm::executor::eagleconfig (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor11EagleConfigE", false]], "tensorrt_llm::executor::eagleconfig::checkposteriorvalue (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11EagleConfig19checkPosteriorValueERKNSt8optionalIfEE", false]], "tensorrt_llm::executor::eagleconfig::eagleconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11EagleConfig11EagleConfigENSt8optionalI12EagleChoicesEEbNSt8optionalIfEEbNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::eagleconfig::getdynamictreemaxtopk (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11EagleConfig21getDynamicTreeMaxTopKEv", false]], "tensorrt_llm::executor::eagleconfig::geteaglechoices (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11EagleConfig15getEagleChoicesEv", false]], "tensorrt_llm::executor::eagleconfig::getposteriorthreshold (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11EagleConfig21getPosteriorThresholdEv", false]], "tensorrt_llm::executor::eagleconfig::isgreedysampling (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11EagleConfig16isGreedySamplingEv", false]], "tensorrt_llm::executor::eagleconfig::mdynamictreemaxtopk (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11EagleConfig19mDynamicTreeMaxTopKE", false]], "tensorrt_llm::executor::eagleconfig::meaglechoices (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11EagleConfig13mEagleChoicesE", false]], "tensorrt_llm::executor::eagleconfig::mgreedysampling (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11EagleConfig15mGreedySamplingE", false]], "tensorrt_llm::executor::eagleconfig::mposteriorthreshold (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11EagleConfig19mPosteriorThresholdE", false]], "tensorrt_llm::executor::eagleconfig::musedynamictree (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11EagleConfig15mUseDynamicTreeE", false]], "tensorrt_llm::executor::eagleconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11EagleConfigeqERK11EagleConfig", false]], "tensorrt_llm::executor::eagleconfig::usedynamictree (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11EagleConfig14useDynamicTreeEv", false]], "tensorrt_llm::executor::executor (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8ExecutorE", false]], "tensorrt_llm::executor::executor::awaitresponses (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERK6IdTypeRKNSt8optionalINSt6chrono12millisecondsEEE", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt6vectorI6IdTypeEERKNSt8optionalINSt6chrono12millisecondsEEE", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt8optionalINSt6chrono12millisecondsEEE", false]], "tensorrt_llm::executor::executor::cancelrequest (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor13cancelRequestE6IdType", false]], "tensorrt_llm::executor::executor::canenqueuerequests (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Executor18canEnqueueRequestsEv", false]], "tensorrt_llm::executor::executor::enqueuerequest (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor14enqueueRequestERK7Request", false]], "tensorrt_llm::executor::executor::enqueuerequests (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor15enqueueRequestsERKNSt6vectorI7RequestEE", false]], "tensorrt_llm::executor::executor::executor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEENSt10shared_ptrI5ModelEERK14ExecutorConfig", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEERK14ExecutorConfig", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK8Executor", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", false], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERR8Executor", false]], "tensorrt_llm::executor::executor::getkvcacheeventmanager (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Executor22getKVCacheEventManagerEv", false]], "tensorrt_llm::executor::executor::getlatestdebugtensors (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor21getLatestDebugTensorsEv", false]], "tensorrt_llm::executor::executor::getlatestiterationstats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor23getLatestIterationStatsEv", false]], "tensorrt_llm::executor::executor::getlatestrequeststats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor21getLatestRequestStatsEv", false]], "tensorrt_llm::executor::executor::getnumresponsesready (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Executor20getNumResponsesReadyERKNSt8optionalI6IdTypeEE", false]], "tensorrt_llm::executor::executor::isparticipant (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Executor13isParticipantEv", false]], "tensorrt_llm::executor::executor::mimpl (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor5mImplE", false]], "tensorrt_llm::executor::executor::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8ExecutoraSERK8Executor", false], [0, "_CPPv4N12tensorrt_llm8executor8ExecutoraSERR8Executor", false]], "tensorrt_llm::executor::executor::shutdown (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor8shutdownEv", false]], "tensorrt_llm::executor::executor::~executor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8ExecutorD0Ev", false]], "tensorrt_llm::executor::executorconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfigE", false]], "tensorrt_llm::executor::executorconfig::executorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", false]], "tensorrt_llm::executor::executorconfig::getadditionalmodeloutputs (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getAdditionalModelOutputsEv", false]], "tensorrt_llm::executor::executorconfig::getbatchingtype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getBatchingTypeEv", false]], "tensorrt_llm::executor::executorconfig::getcachetransceiverconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getCacheTransceiverConfigEv", false]], "tensorrt_llm::executor::executorconfig::getdebugconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig14getDebugConfigEv", false]], "tensorrt_llm::executor::executorconfig::getdecodingconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig17getDecodingConfigEv", false]], "tensorrt_llm::executor::executorconfig::getenablechunkedcontext (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig23getEnableChunkedContextEv", false]], "tensorrt_llm::executor::executorconfig::getenabletrtoverlap (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig19getEnableTrtOverlapEv", false]], "tensorrt_llm::executor::executorconfig::getextendedruntimeperfknobconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig32getExtendedRuntimePerfKnobConfigEv", false]], "tensorrt_llm::executor::executorconfig::getgathergenerationlogits (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getGatherGenerationLogitsEv", false]], "tensorrt_llm::executor::executorconfig::getgpuweightspercent (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig20getGpuWeightsPercentEv", false]], "tensorrt_llm::executor::executorconfig::getguideddecodingconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig23getGuidedDecodingConfigEv", false]], "tensorrt_llm::executor::executorconfig::getiterstatsmaxiterations (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getIterStatsMaxIterationsEv", false]], "tensorrt_llm::executor::executorconfig::getkvcacheconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig16getKvCacheConfigEv", false]], "tensorrt_llm::executor::executorconfig::getkvcacheconfigref (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19getKvCacheConfigRefEv", false]], "tensorrt_llm::executor::executorconfig::getlogitspostprocessorconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig28getLogitsPostProcessorConfigEv", false]], "tensorrt_llm::executor::executorconfig::getmaxbatchsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxBatchSizeEv", false]], "tensorrt_llm::executor::executorconfig::getmaxbeamwidth (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxBeamWidthEv", false]], "tensorrt_llm::executor::executorconfig::getmaxnumtokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxNumTokensEv", false]], "tensorrt_llm::executor::executorconfig::getmaxqueuesize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxQueueSizeEv", false]], "tensorrt_llm::executor::executorconfig::getmaxseqidlemicroseconds (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getMaxSeqIdleMicrosecondsEv", false]], "tensorrt_llm::executor::executorconfig::getnormalizelogprobs (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig20getNormalizeLogProbsEv", false]], "tensorrt_llm::executor::executorconfig::getparallelconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig17getParallelConfigEv", false]], "tensorrt_llm::executor::executorconfig::getpeftcacheconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig18getPeftCacheConfigEv", false]], "tensorrt_llm::executor::executorconfig::getprompttableoffloading (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig24getPromptTableOffloadingEv", false]], "tensorrt_llm::executor::executorconfig::getrecvpollperiodms (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig19getRecvPollPeriodMsEv", false]], "tensorrt_llm::executor::executorconfig::getrequeststatsmaxiterations (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig28getRequestStatsMaxIterationsEv", false]], "tensorrt_llm::executor::executorconfig::getschedulerconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig18getSchedulerConfigEv", false]], "tensorrt_llm::executor::executorconfig::getschedulerconfigref (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig21getSchedulerConfigRefEv", false]], "tensorrt_llm::executor::executorconfig::getspecdecconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig16getSpecDecConfigEv", false]], "tensorrt_llm::executor::executorconfig::getusegpudirectstorage (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig22getUseGpuDirectStorageEv", false]], "tensorrt_llm::executor::executorconfig::kdefaultiterstatsmaxiterations (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig30kDefaultIterStatsMaxIterationsE", false]], "tensorrt_llm::executor::executorconfig::kdefaultmaxseqidlemicroseconds (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig30kDefaultMaxSeqIdleMicrosecondsE", false]], "tensorrt_llm::executor::executorconfig::kdefaultrequeststatsmaxiterations (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig33kDefaultRequestStatsMaxIterationsE", false]], "tensorrt_llm::executor::executorconfig::madditionalmodeloutputs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mAdditionalModelOutputsE", false]], "tensorrt_llm::executor::executorconfig::mbatchingtype (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mBatchingTypeE", false]], "tensorrt_llm::executor::executorconfig::mcachetransceiverconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mCacheTransceiverConfigE", false]], "tensorrt_llm::executor::executorconfig::mdebugconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig12mDebugConfigE", false]], "tensorrt_llm::executor::executorconfig::mdecodingconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15mDecodingConfigE", false]], "tensorrt_llm::executor::executorconfig::menablechunkedcontext (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig21mEnableChunkedContextE", false]], "tensorrt_llm::executor::executorconfig::menabletrtoverlap (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17mEnableTrtOverlapE", false]], "tensorrt_llm::executor::executorconfig::mextendedruntimeperfknobconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig30mExtendedRuntimePerfKnobConfigE", false]], "tensorrt_llm::executor::executorconfig::mgathergenerationlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mGatherGenerationLogitsE", false]], "tensorrt_llm::executor::executorconfig::mgpuweightspercent (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18mGpuWeightsPercentE", false]], "tensorrt_llm::executor::executorconfig::mguideddecodingconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig21mGuidedDecodingConfigE", false]], "tensorrt_llm::executor::executorconfig::miterstatsmaxiterations (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mIterStatsMaxIterationsE", false]], "tensorrt_llm::executor::executorconfig::mkvcacheconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14mKvCacheConfigE", false]], "tensorrt_llm::executor::executorconfig::mlogitspostprocessorconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig26mLogitsPostProcessorConfigE", false]], "tensorrt_llm::executor::executorconfig::mmaxbatchsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxBatchSizeE", false]], "tensorrt_llm::executor::executorconfig::mmaxbeamwidth (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxBeamWidthE", false]], "tensorrt_llm::executor::executorconfig::mmaxnumtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxNumTokensE", false]], "tensorrt_llm::executor::executorconfig::mmaxqueuesize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxQueueSizeE", false]], "tensorrt_llm::executor::executorconfig::mmaxseqidlemicroseconds (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mMaxSeqIdleMicrosecondsE", false]], "tensorrt_llm::executor::executorconfig::mnormalizelogprobs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18mNormalizeLogProbsE", false]], "tensorrt_llm::executor::executorconfig::mparallelconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15mParallelConfigE", false]], "tensorrt_llm::executor::executorconfig::mpeftcacheconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16mPeftCacheConfigE", false]], "tensorrt_llm::executor::executorconfig::mprompttableoffloading (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig22mPromptTableOffloadingE", false]], "tensorrt_llm::executor::executorconfig::mrecvpollperiodms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17mRecvPollPeriodMsE", false]], "tensorrt_llm::executor::executorconfig::mrequeststatsmaxiterations (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig26mRequestStatsMaxIterationsE", false]], "tensorrt_llm::executor::executorconfig::mschedulerconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16mSchedulerConfigE", false]], "tensorrt_llm::executor::executorconfig::mspeculativedecodingconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig26mSpeculativeDecodingConfigE", false]], "tensorrt_llm::executor::executorconfig::musegpudirectstorage (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20mUseGpuDirectStorageE", false]], "tensorrt_llm::executor::executorconfig::setadditionalmodeloutputs (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setAdditionalModelOutputsERKNSt6vectorI21AdditionalModelOutputEE", false]], "tensorrt_llm::executor::executorconfig::setbatchingtype (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setBatchingTypeE12BatchingType", false]], "tensorrt_llm::executor::executorconfig::setcachetransceiverconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setCacheTransceiverConfigERK22CacheTransceiverConfig", false]], "tensorrt_llm::executor::executorconfig::setdebugconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14setDebugConfigERK11DebugConfig", false]], "tensorrt_llm::executor::executorconfig::setdecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setDecodingConfigERK14DecodingConfig", false]], "tensorrt_llm::executor::executorconfig::setenablechunkedcontext (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23setEnableChunkedContextEb", false]], "tensorrt_llm::executor::executorconfig::setenabletrtoverlap (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19setEnableTrtOverlapEb", false]], "tensorrt_llm::executor::executorconfig::setextendedruntimeperfknobconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig32setExtendedRuntimePerfKnobConfigERK29ExtendedRuntimePerfKnobConfig", false]], "tensorrt_llm::executor::executorconfig::setgathergenerationlogits (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setGatherGenerationLogitsEb", false]], "tensorrt_llm::executor::executorconfig::setgpuweightspercent (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setGpuWeightsPercentERKf", false]], "tensorrt_llm::executor::executorconfig::setguideddecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23setGuidedDecodingConfigERK20GuidedDecodingConfig", false]], "tensorrt_llm::executor::executorconfig::setiterstatsmaxiterations (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setIterStatsMaxIterationsE10SizeType32", false]], "tensorrt_llm::executor::executorconfig::setkvcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16setKvCacheConfigERK13KvCacheConfig", false]], "tensorrt_llm::executor::executorconfig::setlogitspostprocessorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setLogitsPostProcessorConfigERK25LogitsPostProcessorConfig", false]], "tensorrt_llm::executor::executorconfig::setmaxbatchsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBatchSizeE10SizeType32", false]], "tensorrt_llm::executor::executorconfig::setmaxbeamwidth (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBeamWidthE10SizeType32", false]], "tensorrt_llm::executor::executorconfig::setmaxnumtokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxNumTokensE10SizeType32", false]], "tensorrt_llm::executor::executorconfig::setmaxqueuesize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxQueueSizeERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::executorconfig::setmaxseqidlemicroseconds (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setMaxSeqIdleMicrosecondsE8uint64_t", false]], "tensorrt_llm::executor::executorconfig::setnormalizelogprobs (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setNormalizeLogProbsEb", false]], "tensorrt_llm::executor::executorconfig::setparallelconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setParallelConfigERK14ParallelConfig", false]], "tensorrt_llm::executor::executorconfig::setpeftcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setPeftCacheConfigERK15PeftCacheConfig", false]], "tensorrt_llm::executor::executorconfig::setprompttableoffloading (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig24setPromptTableOffloadingEb", false]], "tensorrt_llm::executor::executorconfig::setrecvpollperiodms (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19setRecvPollPeriodMsERK10SizeType32", false]], "tensorrt_llm::executor::executorconfig::setrequeststatsmaxiterations (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setRequestStatsMaxIterationsE10SizeType32", false]], "tensorrt_llm::executor::executorconfig::setschedulerconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setSchedulerConfigERK15SchedulerConfig", false]], "tensorrt_llm::executor::executorconfig::setspecdecconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16setSpecDecConfigERK25SpeculativeDecodingConfig", false]], "tensorrt_llm::executor::executorconfig::setusegpudirectstorage (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig22setUseGpuDirectStorageERKb", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfigE", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::extendedruntimeperfknobconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig29ExtendedRuntimePerfKnobConfigEbbb10SizeType32", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::getcudagraphcachesize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig21getCudaGraphCacheSizeEv", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::getcudagraphmode (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig16getCudaGraphModeEv", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::getenablecontextfmhafp32acc (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig27getEnableContextFMHAFP32AccEv", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::getmultiblockmode (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig17getMultiBlockModeEv", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::mcudagraphcachesize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig19mCudaGraphCacheSizeE", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::mcudagraphmode (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig14mCudaGraphModeE", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::menablecontextfmhafp32acc (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig25mEnableContextFMHAFP32AccE", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::mmultiblockmode (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig15mMultiBlockModeE", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfigeqERK29ExtendedRuntimePerfKnobConfig", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::setcudagraphcachesize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig21setCudaGraphCacheSizeE10SizeType32", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::setcudagraphmode (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig16setCudaGraphModeEb", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::setenablecontextfmhafp32acc (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig27setEnableContextFMHAFP32AccEb", false]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::setmultiblockmode (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig17setMultiBlockModeEb", false]], "tensorrt_llm::executor::externaldrafttokensconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfigE", false]], "tensorrt_llm::executor::externaldrafttokensconfig::externaldrafttokensconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig25ExternalDraftTokensConfigE9VecTokensNSt8optionalI6TensorEERKNSt8optionalI9FloatTypeEERKNSt8optionalIbEE", false]], "tensorrt_llm::executor::externaldrafttokensconfig::getacceptancethreshold (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig22getAcceptanceThresholdEv", false]], "tensorrt_llm::executor::externaldrafttokensconfig::getfastlogits (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig13getFastLogitsEv", false]], "tensorrt_llm::executor::externaldrafttokensconfig::getlogits (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig9getLogitsEv", false]], "tensorrt_llm::executor::externaldrafttokensconfig::gettokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig9getTokensEv", false]], "tensorrt_llm::executor::externaldrafttokensconfig::macceptancethreshold (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig20mAcceptanceThresholdE", false]], "tensorrt_llm::executor::externaldrafttokensconfig::mfastlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig11mFastLogitsE", false]], "tensorrt_llm::executor::externaldrafttokensconfig::mlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig7mLogitsE", false]], "tensorrt_llm::executor::externaldrafttokensconfig::mtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig7mTokensE", false]], "tensorrt_llm::executor::finishreason (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReasonE", false]], "tensorrt_llm::executor::finishreason::kcancelled (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReason10kCANCELLEDE", false]], "tensorrt_llm::executor::finishreason::kend_id (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReason7kEND_IDE", false]], "tensorrt_llm::executor::finishreason::klength (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReason7kLENGTHE", false]], "tensorrt_llm::executor::finishreason::knot_finished (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReason13kNOT_FINISHEDE", false]], "tensorrt_llm::executor::finishreason::kstop_words (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReason11kSTOP_WORDSE", false]], "tensorrt_llm::executor::finishreason::ktimed_out (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReason10kTIMED_OUTE", false]], "tensorrt_llm::executor::floattype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor9FloatTypeE", false]], "tensorrt_llm::executor::guideddecodingconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfigE", false]], "tensorrt_llm::executor::guideddecodingconfig::getbackend (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig10getBackendEv", false]], "tensorrt_llm::executor::guideddecodingconfig::getencodedvocab (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig15getEncodedVocabEv", false]], "tensorrt_llm::executor::guideddecodingconfig::getstoptokenids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig15getStopTokenIdsEv", false]], "tensorrt_llm::executor::guideddecodingconfig::gettokenizerstr (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig15getTokenizerStrEv", false]], "tensorrt_llm::executor::guideddecodingconfig::guideddecodingbackend (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig21GuidedDecodingBackendE", false]], "tensorrt_llm::executor::guideddecodingconfig::guideddecodingbackend::kllguidance (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig21GuidedDecodingBackend11kLLGUIDANCEE", false]], "tensorrt_llm::executor::guideddecodingconfig::guideddecodingbackend::kxgrammar (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig21GuidedDecodingBackend9kXGRAMMARE", false]], "tensorrt_llm::executor::guideddecodingconfig::guideddecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig20GuidedDecodingConfigE21GuidedDecodingBackendNSt8optionalINSt6vectorINSt6stringEEEEENSt8optionalINSt6stringEEENSt8optionalINSt6vectorI11TokenIdTypeEEEE", false]], "tensorrt_llm::executor::guideddecodingconfig::mbackend (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig8mBackendE", false]], "tensorrt_llm::executor::guideddecodingconfig::mencodedvocab (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig13mEncodedVocabE", false]], "tensorrt_llm::executor::guideddecodingconfig::mstoptokenids (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig13mStopTokenIdsE", false]], "tensorrt_llm::executor::guideddecodingconfig::mtokenizerstr (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig13mTokenizerStrE", false]], "tensorrt_llm::executor::guideddecodingconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfigeqERK20GuidedDecodingConfig", false]], "tensorrt_llm::executor::guideddecodingconfig::setbackend (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig10setBackendERK21GuidedDecodingBackend", false]], "tensorrt_llm::executor::guideddecodingconfig::setencodedvocab (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setEncodedVocabERKNSt6vectorINSt6stringEEE", false]], "tensorrt_llm::executor::guideddecodingconfig::setstoptokenids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setStopTokenIdsERKNSt6vectorI11TokenIdTypeEE", false]], "tensorrt_llm::executor::guideddecodingconfig::settokenizerstr (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setTokenizerStrERKNSt6stringE", false]], "tensorrt_llm::executor::guideddecodingconfig::validate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig8validateEv", false]], "tensorrt_llm::executor::guideddecodingparams (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParamsE", false]], "tensorrt_llm::executor::guideddecodingparams::getguide (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingParams8getGuideEv", false]], "tensorrt_llm::executor::guideddecodingparams::getguidetype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingParams12getGuideTypeEv", false]], "tensorrt_llm::executor::guideddecodingparams::guideddecodingparams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams20GuidedDecodingParamsE9GuideTypeNSt8optionalINSt6stringEEE", false]], "tensorrt_llm::executor::guideddecodingparams::guidetype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideTypeE", false]], "tensorrt_llm::executor::guideddecodingparams::guidetype::kebnf_grammar (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType13kEBNF_GRAMMARE", false]], "tensorrt_llm::executor::guideddecodingparams::guidetype::kjson (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType5kJSONE", false]], "tensorrt_llm::executor::guideddecodingparams::guidetype::kjson_schema (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType12kJSON_SCHEMAE", false]], "tensorrt_llm::executor::guideddecodingparams::guidetype::kregex (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType6kREGEXE", false]], "tensorrt_llm::executor::guideddecodingparams::guidetype::kstructural_tag (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType15kSTRUCTURAL_TAGE", false]], "tensorrt_llm::executor::guideddecodingparams::mguide (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams6mGuideE", false]], "tensorrt_llm::executor::guideddecodingparams::mguidetype (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams10mGuideTypeE", false]], "tensorrt_llm::executor::guideddecodingparams::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingParamseqERK20GuidedDecodingParams", false]], "tensorrt_llm::executor::idtype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor6IdTypeE", false]], "tensorrt_llm::executor::inflightbatchingstats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStatsE", false]], "tensorrt_llm::executor::inflightbatchingstats::avgnumdecodedtokensperiter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats26avgNumDecodedTokensPerIterE", false]], "tensorrt_llm::executor::inflightbatchingstats::microbatchid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats12microBatchIdE", false]], "tensorrt_llm::executor::inflightbatchingstats::numcontextrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats18numContextRequestsE", false]], "tensorrt_llm::executor::inflightbatchingstats::numctxtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats12numCtxTokensE", false]], "tensorrt_llm::executor::inflightbatchingstats::numgenrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats14numGenRequestsE", false]], "tensorrt_llm::executor::inflightbatchingstats::numpausedrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats17numPausedRequestsE", false]], "tensorrt_llm::executor::inflightbatchingstats::numscheduledrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats20numScheduledRequestsE", false]], "tensorrt_llm::executor::iterationstats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStatsE", false]], "tensorrt_llm::executor::iterationstats::cpumemusage (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats11cpuMemUsageE", false]], "tensorrt_llm::executor::iterationstats::crosskvcachestats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats17crossKvCacheStatsE", false]], "tensorrt_llm::executor::iterationstats::gpumemusage (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats11gpuMemUsageE", false]], "tensorrt_llm::executor::iterationstats::inflightbatchingstats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats21inflightBatchingStatsE", false]], "tensorrt_llm::executor::iterationstats::iter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats4iterE", false]], "tensorrt_llm::executor::iterationstats::iterlatencyms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats13iterLatencyMSE", false]], "tensorrt_llm::executor::iterationstats::kvcachestats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats12kvCacheStatsE", false]], "tensorrt_llm::executor::iterationstats::maxbatchsizeruntime (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats19maxBatchSizeRuntimeE", false]], "tensorrt_llm::executor::iterationstats::maxbatchsizestatic (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats18maxBatchSizeStaticE", false]], "tensorrt_llm::executor::iterationstats::maxbatchsizetunerrecommended (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats28maxBatchSizeTunerRecommendedE", false]], "tensorrt_llm::executor::iterationstats::maxnumactiverequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats20maxNumActiveRequestsE", false]], "tensorrt_llm::executor::iterationstats::maxnumtokensruntime (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats19maxNumTokensRuntimeE", false]], "tensorrt_llm::executor::iterationstats::maxnumtokensstatic (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats18maxNumTokensStaticE", false]], "tensorrt_llm::executor::iterationstats::maxnumtokenstunerrecommended (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats28maxNumTokensTunerRecommendedE", false]], "tensorrt_llm::executor::iterationstats::newactiverequestsqueuelatencyms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats31newActiveRequestsQueueLatencyMSE", false]], "tensorrt_llm::executor::iterationstats::numactiverequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats17numActiveRequestsE", false]], "tensorrt_llm::executor::iterationstats::numcompletedrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats20numCompletedRequestsE", false]], "tensorrt_llm::executor::iterationstats::numnewactiverequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats20numNewActiveRequestsE", false]], "tensorrt_llm::executor::iterationstats::numqueuedrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats17numQueuedRequestsE", false]], "tensorrt_llm::executor::iterationstats::pinnedmemusage (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats14pinnedMemUsageE", false]], "tensorrt_llm::executor::iterationstats::specdecodingstats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats17specDecodingStatsE", false]], "tensorrt_llm::executor::iterationstats::staticbatchingstats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats19staticBatchingStatsE", false]], "tensorrt_llm::executor::iterationstats::timestamp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats9timestampE", false]], "tensorrt_llm::executor::iterationtype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor13IterationTypeE", false]], "tensorrt_llm::executor::jsonserialization (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor17JsonSerializationE", false]], "tensorrt_llm::executor::jsonserialization::tojsonstr (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK12RequestStats", false], [0, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK14IterationStats", false], [0, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK24RequestStatsPerIteration", false]], "tensorrt_llm::executor::kv_cache (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cacheE", false]], "tensorrt_llm::executor::kv_cache::agentdesc (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache9AgentDescE", false]], "tensorrt_llm::executor::kv_cache::agentdesc::agentdesc (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache9AgentDesc9AgentDescENSt6stringE", false]], "tensorrt_llm::executor::kv_cache::agentdesc::getbackendagentdesc (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9AgentDesc19getBackendAgentDescEv", false]], "tensorrt_llm::executor::kv_cache::agentdesc::mbackendagentdesc (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache9AgentDesc17mBackendAgentDescE", false]], "tensorrt_llm::executor::kv_cache::agentstate (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentStateE", false]], "tensorrt_llm::executor::kv_cache::agentstate::agentstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState10AgentStateENSt6stringENSt6stringE", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState10AgentStateEv", false]], "tensorrt_llm::executor::kv_cache::agentstate::magentname (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState10mAgentNameE", false]], "tensorrt_llm::executor::kv_cache::agentstate::mconnectioninfo (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState15mConnectionInfoE", false]], "tensorrt_llm::executor::kv_cache::agentstate::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10AgentStateeqERK10AgentState", false]], "tensorrt_llm::executor::kv_cache::agentstate::tostring (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10AgentState8toStringEv", false]], "tensorrt_llm::executor::kv_cache::baseagentconfig (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15BaseAgentConfigE", false]], "tensorrt_llm::executor::kv_cache::baseagentconfig::mname (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15BaseAgentConfig5mNameE", false]], "tensorrt_llm::executor::kv_cache::baseagentconfig::useprogthread (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15BaseAgentConfig13useProgThreadE", false]], "tensorrt_llm::executor::kv_cache::basetransferagent (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgentE", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::checkremotedescs (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent16checkRemoteDescsERKNSt6stringERK11MemoryDescs", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::connectremoteagent (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent18connectRemoteAgentERKNSt6stringERK18ConnectionInfoType", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::deregistermemory (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent16deregisterMemoryERK13RegisterDescs", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::getconnectioninfo (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent17getConnectionInfoEv", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::getlocalagentdesc (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent17getLocalAgentDescEv", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::getnotifiedsyncmessages (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent23getNotifiedSyncMessagesEv", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::invalidateremoteagent (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent21invalidateRemoteAgentERKNSt6stringE", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::loadremoteagent (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent15loadRemoteAgentERKNSt6stringERK9AgentDesc", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::notifysyncmessage (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent17notifySyncMessageERKNSt6stringERK11SyncMessage", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::registermemory (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent14registerMemoryERK13RegisterDescs", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::submittransferrequests (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent22submitTransferRequestsERK15TransferRequest", false]], "tensorrt_llm::executor::kv_cache::basetransferagent::~basetransferagent (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgentD0Ev", false]], "tensorrt_llm::executor::kv_cache::cachestate (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheStateE", false]], "tensorrt_llm::executor::kv_cache::cachestate::attentionconfig (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfigE", false]], "tensorrt_llm::executor::kv_cache::cachestate::attentionconfig::attentionconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfig15AttentionConfigE13AttentionTypei", false]], "tensorrt_llm::executor::kv_cache::cachestate::attentionconfig::mattentiontype (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfig14mAttentionTypeE", false]], "tensorrt_llm::executor::kv_cache::cachestate::attentionconfig::mkvfactor (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfig9mKvFactorE", false]], "tensorrt_llm::executor::kv_cache::cachestate::attentiontype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState13AttentionTypeE", false]], "tensorrt_llm::executor::kv_cache::cachestate::attentiontype::kdefault (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState13AttentionType8kDEFAULTE", false]], "tensorrt_llm::executor::kv_cache::cachestate::attentiontype::kmla (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState13AttentionType4kMLAE", false]], "tensorrt_llm::executor::kv_cache::cachestate::cachestate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE11ModelConfigRKN7runtime11WorldConfigEN8nvinfer18DataTypeE13AttentionTypei", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", false]], "tensorrt_llm::executor::kv_cache::cachestate::getattentionconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState18getAttentionConfigEv", false]], "tensorrt_llm::executor::kv_cache::cachestate::getdatatype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState11getDataTypeEv", false]], "tensorrt_llm::executor::kv_cache::cachestate::getmodelconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState14getModelConfigEv", false]], "tensorrt_llm::executor::kv_cache::cachestate::getparallelconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState17getParallelConfigEv", false]], "tensorrt_llm::executor::kv_cache::cachestate::mattentionconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState16mAttentionConfigE", false]], "tensorrt_llm::executor::kv_cache::cachestate::mdatatype (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState9mDataTypeE", false]], "tensorrt_llm::executor::kv_cache::cachestate::mmodelconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState12mModelConfigE", false]], "tensorrt_llm::executor::kv_cache::cachestate::modelconfig (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState11ModelConfigE", false]], "tensorrt_llm::executor::kv_cache::cachestate::modelconfig::mnbkvheadsperlayer (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState11ModelConfig18mNbKvHeadsPerLayerE", false]], "tensorrt_llm::executor::kv_cache::cachestate::modelconfig::msizeperhead (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState11ModelConfig12mSizePerHeadE", false]], "tensorrt_llm::executor::kv_cache::cachestate::modelconfig::mtokensperblock (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState11ModelConfig15mTokensPerBlockE", false]], "tensorrt_llm::executor::kv_cache::cachestate::modelconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState11ModelConfigeqERK11ModelConfig", false]], "tensorrt_llm::executor::kv_cache::cachestate::mparallelconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15mParallelConfigE", false]], "tensorrt_llm::executor::kv_cache::cachestate::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheStateeqERKN8kv_cache10CacheStateE", false]], "tensorrt_llm::executor::kv_cache::cachestate::parallelconfig (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfigE", false]], "tensorrt_llm::executor::kv_cache::cachestate::parallelconfig::mdprank (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig7mDPrankE", false]], "tensorrt_llm::executor::kv_cache::cachestate::parallelconfig::mdpsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig7mDPsizeE", false]], "tensorrt_llm::executor::kv_cache::cachestate::parallelconfig::menableattentiondp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig18mEnableAttentionDPE", false]], "tensorrt_llm::executor::kv_cache::cachestate::parallelconfig::mpipelineparallelism (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig20mPipelineParallelismE", false]], "tensorrt_llm::executor::kv_cache::cachestate::parallelconfig::mtensorparallelism (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig18mTensorParallelismE", false]], "tensorrt_llm::executor::kv_cache::cachestate::parallelconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfigeqERK14ParallelConfig", false]], "tensorrt_llm::executor::kv_cache::cachestate::tostring (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState8toStringEv", false]], "tensorrt_llm::executor::kv_cache::commstate (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommStateE", false]], "tensorrt_llm::executor::kv_cache::commstate::commstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI10AgentStateEEi", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI10SizeType32EEi", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI11SocketStateEEi", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt8uint16_tENSt6stringE", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateEv", false]], "tensorrt_llm::executor::kv_cache::commstate::getagentstate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState13getAgentStateEv", false]], "tensorrt_llm::executor::kv_cache::commstate::getmpistate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState11getMpiStateEv", false]], "tensorrt_llm::executor::kv_cache::commstate::getselfidx (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState10getSelfIdxEv", false]], "tensorrt_llm::executor::kv_cache::commstate::getsocketstate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState14getSocketStateEv", false]], "tensorrt_llm::executor::kv_cache::commstate::isagentstate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState12isAgentStateEv", false]], "tensorrt_llm::executor::kv_cache::commstate::ismpistate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState10isMpiStateEv", false]], "tensorrt_llm::executor::kv_cache::commstate::issocketstate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState13isSocketStateEv", false]], "tensorrt_llm::executor::kv_cache::commstate::mselfidx (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState8mSelfIdxE", false]], "tensorrt_llm::executor::kv_cache::commstate::mstate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState6mStateE", false]], "tensorrt_llm::executor::kv_cache::commstate::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommStateeqERK9CommState", false]], "tensorrt_llm::executor::kv_cache::commstate::tostring (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState8toStringEv", false]], "tensorrt_llm::executor::kv_cache::connection (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10ConnectionE", false]], "tensorrt_llm::executor::kv_cache::connection::isthreadsafe (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection12isThreadSafeEv", false]], "tensorrt_llm::executor::kv_cache::connection::recv (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4recvERK11DataContextPv6size_t", false]], "tensorrt_llm::executor::kv_cache::connection::send (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4sendERK11DataContextPKv6size_t", false]], "tensorrt_llm::executor::kv_cache::connection::~connection (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10ConnectionD0Ev", false]], "tensorrt_llm::executor::kv_cache::connectioninfotype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache18ConnectionInfoTypeE", false]], "tensorrt_llm::executor::kv_cache::connectionmanager (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManagerE", false]], "tensorrt_llm::executor::kv_cache::connectionmanager::getcommstate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache17ConnectionManager12getCommStateEv", false]], "tensorrt_llm::executor::kv_cache::connectionmanager::getconnections (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManager14getConnectionsERK9CommState", false]], "tensorrt_llm::executor::kv_cache::connectionmanager::recvconnect (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManager11recvConnectERK11DataContextPv6size_t", false]], "tensorrt_llm::executor::kv_cache::connectionmanager::~connectionmanager (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManagerD0Ev", false]], "tensorrt_llm::executor::kv_cache::datacontext (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11DataContextE", false]], "tensorrt_llm::executor::kv_cache::datacontext::datacontext (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11DataContext11DataContextEi", false]], "tensorrt_llm::executor::kv_cache::datacontext::gettag (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache11DataContext6getTagEv", false]], "tensorrt_llm::executor::kv_cache::datacontext::mtag (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11DataContext4mTagE", false]], "tensorrt_llm::executor::kv_cache::dynlibloader (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoaderE", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::dlsym (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader5dlSymEPvPKc", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::dynlibloader (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader12DynLibLoaderERK12DynLibLoader", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader12DynLibLoaderEv", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::getfunctionpointer (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor8kv_cache12DynLibLoader18getFunctionPointerE9FunctionTRKNSt6stringERKNSt6stringE", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::gethandle (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader9getHandleERKNSt6stringE", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::getinstance (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader11getInstanceEv", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::mdllmutex (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader9mDllMutexE", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::mhandlers (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader9mHandlersE", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoaderaSERK12DynLibLoader", false]], "tensorrt_llm::executor::kv_cache::dynlibloader::~dynlibloader (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoaderD0Ev", false]], "tensorrt_llm::executor::kv_cache::maketransferagent (c++ function)": [[0, "_CPPv4IDpEN12tensorrt_llm8executor8kv_cache17makeTransferAgentENSt10unique_ptrI17BaseTransferAgentEERKNSt6stringEDpRR4Args", false]], "tensorrt_llm::executor::kv_cache::memorydesc (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDescE", false]], "tensorrt_llm::executor::kv_cache::memorydesc::deserialize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc11deserializeERNSt7istreamE", false]], "tensorrt_llm::executor::kv_cache::memorydesc::getaddr (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10MemoryDesc7getAddrEv", false]], "tensorrt_llm::executor::kv_cache::memorydesc::getdeviceid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10MemoryDesc11getDeviceIdEv", false]], "tensorrt_llm::executor::kv_cache::memorydesc::getlen (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache10MemoryDesc6getLenEv", false]], "tensorrt_llm::executor::kv_cache::memorydesc::maddr (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc5mAddrE", false]], "tensorrt_llm::executor::kv_cache::memorydesc::mdeviceid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc9mDeviceIdE", false]], "tensorrt_llm::executor::kv_cache::memorydesc::memorydesc (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescE9uintptr_t6size_t8uint32_t", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescEPv6size_t8uint32_t", false], [0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescERKNSt6vectorIcEE8uint32_t", false]], "tensorrt_llm::executor::kv_cache::memorydesc::mlen (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc4mLenE", false]], "tensorrt_llm::executor::kv_cache::memorydesc::serialize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc9serializeERK10MemoryDescRNSt7ostreamE", false]], "tensorrt_llm::executor::kv_cache::memorydesc::serializedsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc14serializedSizeERK10MemoryDesc", false]], "tensorrt_llm::executor::kv_cache::memorydescs (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescsE", false]], "tensorrt_llm::executor::kv_cache::memorydescs::getdescs (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache11MemoryDescs8getDescsEv", false]], "tensorrt_llm::executor::kv_cache::memorydescs::gettype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache11MemoryDescs7getTypeEv", false]], "tensorrt_llm::executor::kv_cache::memorydescs::mdescs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescs6mDescsE", false]], "tensorrt_llm::executor::kv_cache::memorydescs::memorydescs (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescs11MemoryDescsE10MemoryTypeNSt6vectorI10MemoryDescEE", false]], "tensorrt_llm::executor::kv_cache::memorydescs::mtype (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescs5mTypeE", false]], "tensorrt_llm::executor::kv_cache::memorytype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryTypeE", false]], "tensorrt_llm::executor::kv_cache::memorytype::kblk (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType4kBLKE", false]], "tensorrt_llm::executor::kv_cache::memorytype::kdram (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType5kDRAME", false]], "tensorrt_llm::executor::kv_cache::memorytype::kfile (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType5kFILEE", false]], "tensorrt_llm::executor::kv_cache::memorytype::kobj (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType4kOBJE", false]], "tensorrt_llm::executor::kv_cache::memorytype::kvram (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType5kVRAME", false]], "tensorrt_llm::executor::kv_cache::mpistate (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache8MpiStateE", false]], "tensorrt_llm::executor::kv_cache::mpistate::mranks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache8MpiState6mRanksE", false]], "tensorrt_llm::executor::kv_cache::mpistate::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache8MpiStateeqERK8MpiState", false]], "tensorrt_llm::executor::kv_cache::mpistate::tostring (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache8MpiState8toStringEv", false]], "tensorrt_llm::executor::kv_cache::registerdescs (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache13RegisterDescsE", false]], "tensorrt_llm::executor::kv_cache::socketstate (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11SocketStateE", false]], "tensorrt_llm::executor::kv_cache::socketstate::mip (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11SocketState3mIpE", false]], "tensorrt_llm::executor::kv_cache::socketstate::mport (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11SocketState5mPortE", false]], "tensorrt_llm::executor::kv_cache::socketstate::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache11SocketStateeqERK11SocketState", false]], "tensorrt_llm::executor::kv_cache::socketstate::tostring (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache11SocketState8toStringEv", false]], "tensorrt_llm::executor::kv_cache::syncmessage (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache11SyncMessageE", false]], "tensorrt_llm::executor::kv_cache::transferdescs (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache13TransferDescsE", false]], "tensorrt_llm::executor::kv_cache::transferop (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10TransferOpE", false]], "tensorrt_llm::executor::kv_cache::transferop::kread (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10TransferOp5kREADE", false]], "tensorrt_llm::executor::kv_cache::transferop::kwrite (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache10TransferOp6kWRITEE", false]], "tensorrt_llm::executor::kv_cache::transferrequest (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequestE", false]], "tensorrt_llm::executor::kv_cache::transferrequest::getdstdescs (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest11getDstDescsEv", false]], "tensorrt_llm::executor::kv_cache::transferrequest::getop (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest5getOpEv", false]], "tensorrt_llm::executor::kv_cache::transferrequest::getremotename (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest13getRemoteNameEv", false]], "tensorrt_llm::executor::kv_cache::transferrequest::getsrcdescs (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest11getSrcDescsEv", false]], "tensorrt_llm::executor::kv_cache::transferrequest::getsyncmessage (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest14getSyncMessageEv", false]], "tensorrt_llm::executor::kv_cache::transferrequest::mdstdescs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest9mDstDescsE", false]], "tensorrt_llm::executor::kv_cache::transferrequest::mop (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest3mOpE", false]], "tensorrt_llm::executor::kv_cache::transferrequest::mremotename (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest11mRemoteNameE", false]], "tensorrt_llm::executor::kv_cache::transferrequest::msrcdescs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest9mSrcDescsE", false]], "tensorrt_llm::executor::kv_cache::transferrequest::msyncmessage (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest12mSyncMessageE", false]], "tensorrt_llm::executor::kv_cache::transferrequest::transferrequest (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest15TransferRequestE10TransferOp13TransferDescs13TransferDescsRKNSt6stringENSt8optionalI11SyncMessageEE", false]], "tensorrt_llm::executor::kv_cache::transferstatus (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache14TransferStatusE", false]], "tensorrt_llm::executor::kv_cache::transferstatus::iscompleted (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache14TransferStatus11isCompletedEv", false]], "tensorrt_llm::executor::kv_cache::transferstatus::wait (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8kv_cache14TransferStatus4waitEv", false]], "tensorrt_llm::executor::kv_cache::transferstatus::~transferstatus (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cache14TransferStatusD0Ev", false]], "tensorrt_llm::executor::kvcacheconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfigE", false]], "tensorrt_llm::executor::kvcacheconfig::fillemptyfieldsfromruntimedefaults (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig34fillEmptyFieldsFromRuntimeDefaultsERKN12tensorrt_llm7runtime15RuntimeDefaultsE", false]], "tensorrt_llm::executor::kvcacheconfig::getcopyonpartialreuse (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig21getCopyOnPartialReuseEv", false]], "tensorrt_llm::executor::kvcacheconfig::getcrosskvcachefraction (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig23getCrossKvCacheFractionEv", false]], "tensorrt_llm::executor::kvcacheconfig::getenableblockreuse (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig19getEnableBlockReuseEv", false]], "tensorrt_llm::executor::kvcacheconfig::getenablepartialreuse (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig21getEnablePartialReuseEv", false]], "tensorrt_llm::executor::kvcacheconfig::geteventbuffermaxsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig21getEventBufferMaxSizeEv", false]], "tensorrt_llm::executor::kvcacheconfig::getfreegpumemoryfraction (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig24getFreeGpuMemoryFractionEv", false]], "tensorrt_llm::executor::kvcacheconfig::gethostcachesize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig16getHostCacheSizeEv", false]], "tensorrt_llm::executor::kvcacheconfig::getmaxattentionwindowvec (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig24getMaxAttentionWindowVecEv", false]], "tensorrt_llm::executor::kvcacheconfig::getmaxtokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig12getMaxTokensEv", false]], "tensorrt_llm::executor::kvcacheconfig::getonboardblocks (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig16getOnboardBlocksEv", false]], "tensorrt_llm::executor::kvcacheconfig::getsecondaryoffloadminpriority (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig30getSecondaryOffloadMinPriorityEv", false]], "tensorrt_llm::executor::kvcacheconfig::getsinktokenlength (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig18getSinkTokenLengthEv", false]], "tensorrt_llm::executor::kvcacheconfig::getuseuvm (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig9getUseUvmEv", false]], "tensorrt_llm::executor::kvcacheconfig::kdefaultgpumemfraction (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig22kDefaultGpuMemFractionE", false]], "tensorrt_llm::executor::kvcacheconfig::kvcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", false]], "tensorrt_llm::executor::kvcacheconfig::mcopyonpartialreuse (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19mCopyOnPartialReuseE", false]], "tensorrt_llm::executor::kvcacheconfig::mcrosskvcachefraction (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21mCrossKvCacheFractionE", false]], "tensorrt_llm::executor::kvcacheconfig::menableblockreuse (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig17mEnableBlockReuseE", false]], "tensorrt_llm::executor::kvcacheconfig::menablepartialreuse (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19mEnablePartialReuseE", false]], "tensorrt_llm::executor::kvcacheconfig::meventbuffermaxsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19mEventBufferMaxSizeE", false]], "tensorrt_llm::executor::kvcacheconfig::mfreegpumemoryfraction (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig22mFreeGpuMemoryFractionE", false]], "tensorrt_llm::executor::kvcacheconfig::mhostcachesize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig14mHostCacheSizeE", false]], "tensorrt_llm::executor::kvcacheconfig::mmaxattentionwindowvec (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig22mMaxAttentionWindowVecE", false]], "tensorrt_llm::executor::kvcacheconfig::mmaxtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig10mMaxTokensE", false]], "tensorrt_llm::executor::kvcacheconfig::monboardblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig14mOnboardBlocksE", false]], "tensorrt_llm::executor::kvcacheconfig::msecondaryoffloadminpriority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig28mSecondaryOffloadMinPriorityE", false]], "tensorrt_llm::executor::kvcacheconfig::msinktokenlength (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16mSinkTokenLengthE", false]], "tensorrt_llm::executor::kvcacheconfig::museuvm (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig7mUseUvmE", false]], "tensorrt_llm::executor::kvcacheconfig::setcopyonpartialreuse (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setCopyOnPartialReuseEb", false]], "tensorrt_llm::executor::kvcacheconfig::setcrosskvcachefraction (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig23setCrossKvCacheFractionE9FloatType", false]], "tensorrt_llm::executor::kvcacheconfig::setenableblockreuse (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19setEnableBlockReuseEb", false]], "tensorrt_llm::executor::kvcacheconfig::setenablepartialreuse (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setEnablePartialReuseEb", false]], "tensorrt_llm::executor::kvcacheconfig::seteventbuffermaxsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setEventBufferMaxSizeE6size_t", false]], "tensorrt_llm::executor::kvcacheconfig::setfreegpumemoryfraction (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setFreeGpuMemoryFractionE9FloatType", false]], "tensorrt_llm::executor::kvcacheconfig::sethostcachesize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setHostCacheSizeE6size_t", false]], "tensorrt_llm::executor::kvcacheconfig::setmaxattentionwindowvec (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setMaxAttentionWindowVecENSt6vectorI10SizeType32EE", false]], "tensorrt_llm::executor::kvcacheconfig::setmaxtokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig12setMaxTokensE10SizeType32", false]], "tensorrt_llm::executor::kvcacheconfig::setonboardblocks (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setOnboardBlocksEb", false]], "tensorrt_llm::executor::kvcacheconfig::setsecondaryoffloadminpriority (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig30setSecondaryOffloadMinPriorityENSt8optionalI17RetentionPriorityEE", false]], "tensorrt_llm::executor::kvcacheconfig::setsinktokenlength (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig18setSinkTokenLengthE10SizeType32", false]], "tensorrt_llm::executor::kvcacheconfig::setuseuvm (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig9setUseUvmEb", false]], "tensorrt_llm::executor::kvcachecreateddata (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheCreatedDataE", false]], "tensorrt_llm::executor::kvcachecreateddata::numblockspercachelevel (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheCreatedData22numBlocksPerCacheLevelE", false]], "tensorrt_llm::executor::kvcacheevent (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor12KVCacheEventE", false]], "tensorrt_llm::executor::kvcacheevent::data (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent4dataE", false]], "tensorrt_llm::executor::kvcacheevent::eventid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent7eventIdE", false]], "tensorrt_llm::executor::kvcacheevent::kvcacheevent (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent12KVCacheEventE6IdType16KVCacheEventData10SizeType32", false]], "tensorrt_llm::executor::kvcacheevent::windowsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent10windowSizeE", false]], "tensorrt_llm::executor::kvcacheeventdata (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor16KVCacheEventDataE", false]], "tensorrt_llm::executor::kvcacheeventdiff (c++ struct)": [[0, "_CPPv4I0EN12tensorrt_llm8executor16KVCacheEventDiffE", false]], "tensorrt_llm::executor::kvcacheeventdiff::newvalue (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor16KVCacheEventDiff8newValueE", false]], "tensorrt_llm::executor::kvcacheeventdiff::oldvalue (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor16KVCacheEventDiff8oldValueE", false]], "tensorrt_llm::executor::kvcacheeventmanager (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManagerE", false]], "tensorrt_llm::executor::kvcacheeventmanager::getlatestevents (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManager15getLatestEventsENSt8optionalINSt6chrono12millisecondsEEE", false]], "tensorrt_llm::executor::kvcacheeventmanager::kvcacheeventmanager (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManager19KVCacheEventManagerENSt10shared_ptrIN12tensorrt_llm13batch_manager16kv_cache_manager18BaseKVCacheManagerEEE", false]], "tensorrt_llm::executor::kvcacheeventmanager::kvcachemanager (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManager14kvCacheManagerE", false]], "tensorrt_llm::executor::kvcacheremoveddata (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheRemovedDataE", false]], "tensorrt_llm::executor::kvcacheremoveddata::blockhashes (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheRemovedData11blockHashesE", false]], "tensorrt_llm::executor::kvcacheretentionconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfigE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::getdecodedurationms (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig19getDecodeDurationMsEv", false]], "tensorrt_llm::executor::kvcacheretentionconfig::getdecoderetentionpriority (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig26getDecodeRetentionPriorityEv", false]], "tensorrt_llm::executor::kvcacheretentionconfig::getdirectory (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig12getDirectoryEv", false]], "tensorrt_llm::executor::kvcacheretentionconfig::getperblockretentionpriorityduration (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig36getPerBlockRetentionPriorityDurationE10SizeType3210SizeType32", false]], "tensorrt_llm::executor::kvcacheretentionconfig::gettokenrangeretentionconfigs (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig29getTokenRangeRetentionConfigsEv", false]], "tensorrt_llm::executor::kvcacheretentionconfig::gettransfermode (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig15getTransferModeEv", false]], "tensorrt_llm::executor::kvcacheretentionconfig::kdefaultretentionpriority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25kDefaultRetentionPriorityE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::kmaxretentionpriority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig21kMaxRetentionPriorityE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::kminretentionpriority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig21kMinRetentionPriorityE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::kvcacheretentionconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigERKNSt6vectorI25TokenRangeRetentionConfigEE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE19KvCacheTransferModeNSt8optionalINSt6stringEEE", false], [0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigEv", false]], "tensorrt_llm::executor::kvcacheretentionconfig::mdecodedurationms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig17mDecodeDurationMsE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::mdecoderetentionpriority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig24mDecodeRetentionPriorityE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::mdirectory (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig10mDirectoryE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::mtokenrangeretentionconfigs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig27mTokenRangeRetentionConfigsE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::mtransfermode (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig13mTransferModeE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfigeqERK22KvCacheRetentionConfig", false]], "tensorrt_llm::executor::kvcacheretentionconfig::tokenrangeretentionconfig (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfigE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::tokenrangeretentionconfig::durationms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig10durationMsE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::tokenrangeretentionconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfigeqERK25TokenRangeRetentionConfig", false]], "tensorrt_llm::executor::kvcacheretentionconfig::tokenrangeretentionconfig::priority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig8priorityE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::tokenrangeretentionconfig::tokenend (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig8tokenEndE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::tokenrangeretentionconfig::tokenrangeretentionconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig25TokenRangeRetentionConfigE10SizeType32NSt8optionalI10SizeType32EE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE", false]], "tensorrt_llm::executor::kvcacheretentionconfig::tokenrangeretentionconfig::tokenstart (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig10tokenStartE", false]], "tensorrt_llm::executor::kvcachestats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStatsE", false]], "tensorrt_llm::executor::kvcachestats::allocnewblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats14allocNewBlocksE", false]], "tensorrt_llm::executor::kvcachestats::alloctotalblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats16allocTotalBlocksE", false]], "tensorrt_llm::executor::kvcachestats::cachehitrate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12cacheHitRateE", false]], "tensorrt_llm::executor::kvcachestats::freenumblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats13freeNumBlocksE", false]], "tensorrt_llm::executor::kvcachestats::maxnumblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12maxNumBlocksE", false]], "tensorrt_llm::executor::kvcachestats::missedblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12missedBlocksE", false]], "tensorrt_llm::executor::kvcachestats::reusedblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12reusedBlocksE", false]], "tensorrt_llm::executor::kvcachestats::tokensperblock (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats14tokensPerBlockE", false]], "tensorrt_llm::executor::kvcachestats::usednumblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats13usedNumBlocksE", false]], "tensorrt_llm::executor::kvcachestoredblockdata (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockDataE", false]], "tensorrt_llm::executor::kvcachestoredblockdata::blockhash (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData9blockHashE", false]], "tensorrt_llm::executor::kvcachestoredblockdata::cachelevel (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData10cacheLevelE", false]], "tensorrt_llm::executor::kvcachestoredblockdata::kvcachestoredblockdata (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData22KVCacheStoredBlockDataE6IdTypeN12tensorrt_llm7runtime15VecUniqueTokensENSt8optionalIN12tensorrt_llm7runtime14LoraTaskIdTypeEEE10SizeType3210SizeType32", false]], "tensorrt_llm::executor::kvcachestoredblockdata::loraid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData6loraIdE", false]], "tensorrt_llm::executor::kvcachestoredblockdata::priority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData8priorityE", false]], "tensorrt_llm::executor::kvcachestoredblockdata::tokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData6tokensE", false]], "tensorrt_llm::executor::kvcachestoreddata (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor17KVCacheStoredDataE", false]], "tensorrt_llm::executor::kvcachestoreddata::blocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor17KVCacheStoredData6blocksE", false]], "tensorrt_llm::executor::kvcachestoreddata::parenthash (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor17KVCacheStoredData10parentHashE", false]], "tensorrt_llm::executor::kvcachetransfermode (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor19KvCacheTransferModeE", false]], "tensorrt_llm::executor::kvcachetransfermode::dram (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor19KvCacheTransferMode4DRAME", false]], "tensorrt_llm::executor::kvcachetransfermode::gds (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor19KvCacheTransferMode3GDSE", false]], "tensorrt_llm::executor::kvcachetransfermode::posix_debug_fallback (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor19KvCacheTransferMode20POSIX_DEBUG_FALLBACKE", false]], "tensorrt_llm::executor::kvcacheupdateddata (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedDataE", false]], "tensorrt_llm::executor::kvcacheupdateddata::blockhash (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData9blockHashE", false]], "tensorrt_llm::executor::kvcacheupdateddata::cachelevel (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData10cacheLevelE", false]], "tensorrt_llm::executor::kvcacheupdateddata::cachelevelupdated (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData17cacheLevelUpdatedE10SizeType3210SizeType32", false]], "tensorrt_llm::executor::kvcacheupdateddata::kvcacheupdateddata (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData18KVCacheUpdatedDataE6IdType", false]], "tensorrt_llm::executor::kvcacheupdateddata::priority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData8priorityE", false]], "tensorrt_llm::executor::kvcacheupdateddata::priorityupdated (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData15priorityUpdatedE10SizeType3210SizeType32", false]], "tensorrt_llm::executor::logitspostprocessor (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor19LogitsPostProcessorE", false]], "tensorrt_llm::executor::logitspostprocessorbatched (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor26LogitsPostProcessorBatchedE", false]], "tensorrt_llm::executor::logitspostprocessorconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfigE", false]], "tensorrt_llm::executor::logitspostprocessorconfig::getprocessorbatched (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig19getProcessorBatchedEv", false]], "tensorrt_llm::executor::logitspostprocessorconfig::getprocessormap (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig15getProcessorMapEv", false]], "tensorrt_llm::executor::logitspostprocessorconfig::getreplicate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig12getReplicateEv", false]], "tensorrt_llm::executor::logitspostprocessorconfig::logitspostprocessorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig25LogitsPostProcessorConfigENSt8optionalI22LogitsPostProcessorMapEENSt8optionalI26LogitsPostProcessorBatchedEEb", false]], "tensorrt_llm::executor::logitspostprocessorconfig::mprocessorbatched (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig17mProcessorBatchedE", false]], "tensorrt_llm::executor::logitspostprocessorconfig::mprocessormap (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig13mProcessorMapE", false]], "tensorrt_llm::executor::logitspostprocessorconfig::mreplicate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig10mReplicateE", false]], "tensorrt_llm::executor::logitspostprocessorconfig::setprocessorbatched (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig19setProcessorBatchedERK26LogitsPostProcessorBatched", false]], "tensorrt_llm::executor::logitspostprocessorconfig::setprocessormap (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig15setProcessorMapERK22LogitsPostProcessorMap", false]], "tensorrt_llm::executor::logitspostprocessorconfig::setreplicate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig12setReplicateEb", false]], "tensorrt_llm::executor::logitspostprocessormap (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor22LogitsPostProcessorMapE", false]], "tensorrt_llm::executor::lookaheaddecodingconfig (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfigE", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::calculatespeculativeresource (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig28calculateSpeculativeResourceEv", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::calculatespeculativeresourcetuple (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig33calculateSpeculativeResourceTupleE10SizeType3210SizeType3210SizeType32", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::get (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig3getEv", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::getngramsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig12getNgramSizeEv", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::getverificationsetsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig22getVerificationSetSizeEv", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::getwindowsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig13getWindowSizeEv", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::isle (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig4isLEERK23LookaheadDecodingConfig", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::islegal (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig7isLegalE10SizeType3210SizeType3210SizeType32", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::kdefaultlookaheaddecodingngram (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig30kDefaultLookaheadDecodingNgramE", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::kdefaultlookaheaddecodingverificationset (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig40kDefaultLookaheadDecodingVerificationSetE", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::kdefaultlookaheaddecodingwindow (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig31kDefaultLookaheadDecodingWindowE", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::lookaheaddecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigE10SizeType3210SizeType3210SizeType32", false], [0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigEv", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::mngramsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig10mNgramSizeE", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::mverificationsetsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig20mVerificationSetSizeE", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::mwindowsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig11mWindowSizeE", false]], "tensorrt_llm::executor::lookaheaddecodingconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfigeqERK23LookaheadDecodingConfig", false]], "tensorrt_llm::executor::loraconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor10LoraConfigE", false]], "tensorrt_llm::executor::loraconfig::getconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor10LoraConfig9getConfigEv", false]], "tensorrt_llm::executor::loraconfig::gettaskid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor10LoraConfig9getTaskIdEv", false]], "tensorrt_llm::executor::loraconfig::getweights (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor10LoraConfig10getWeightsEv", false]], "tensorrt_llm::executor::loraconfig::loraconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor10LoraConfig10LoraConfigE6IdTypeNSt8optionalI6TensorEENSt8optionalI6TensorEE", false]], "tensorrt_llm::executor::loraconfig::mconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10LoraConfig7mConfigE", false]], "tensorrt_llm::executor::loraconfig::mtaskid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10LoraConfig7mTaskIdE", false]], "tensorrt_llm::executor::loraconfig::mweights (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10LoraConfig8mWeightsE", false]], "tensorrt_llm::executor::medusachoices (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor13MedusaChoicesE", false]], "tensorrt_llm::executor::memorytype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryTypeE", false]], "tensorrt_llm::executor::memorytype::kcpu (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType4kCPUE", false]], "tensorrt_llm::executor::memorytype::kcpu_pinned (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType11kCPU_PINNEDE", false]], "tensorrt_llm::executor::memorytype::kcpu_pinnedpool (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType15kCPU_PINNEDPOOLE", false]], "tensorrt_llm::executor::memorytype::kgpu (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType4kGPUE", false]], "tensorrt_llm::executor::memorytype::kunknown (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType8kUNKNOWNE", false]], "tensorrt_llm::executor::memorytype::kuvm (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType4kUVME", false]], "tensorrt_llm::executor::millisecondstype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor16MillisecondsTypeE", false]], "tensorrt_llm::executor::modeltype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor9ModelTypeE", false]], "tensorrt_llm::executor::modeltype::kdecoder_only (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor9ModelType13kDECODER_ONLYE", false]], "tensorrt_llm::executor::modeltype::kencoder_decoder (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor9ModelType16kENCODER_DECODERE", false]], "tensorrt_llm::executor::modeltype::kencoder_only (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor9ModelType13kENCODER_ONLYE", false]], "tensorrt_llm::executor::mropeconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor11MropeConfigE", false]], "tensorrt_llm::executor::mropeconfig::getmropepositiondeltas (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11MropeConfig22getMRopePositionDeltasEv", false]], "tensorrt_llm::executor::mropeconfig::getmroperotarycossin (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11MropeConfig20getMRopeRotaryCosSinEv", false]], "tensorrt_llm::executor::mropeconfig::mmropepositiondeltas (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11MropeConfig20mMRopePositionDeltasE", false]], "tensorrt_llm::executor::mropeconfig::mmroperotarycossin (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11MropeConfig18mMRopeRotaryCosSinE", false]], "tensorrt_llm::executor::mropeconfig::mropeconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11MropeConfig11MropeConfigE6Tensor10SizeType32", false]], "tensorrt_llm::executor::multimodalinput (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor15MultimodalInputE", false]], "tensorrt_llm::executor::multimodalinput::getmultimodalhashes (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15MultimodalInput19getMultimodalHashesEv", false]], "tensorrt_llm::executor::multimodalinput::getmultimodallengths (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15MultimodalInput20getMultimodalLengthsEv", false]], "tensorrt_llm::executor::multimodalinput::getmultimodalpositions (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15MultimodalInput22getMultimodalPositionsEv", false]], "tensorrt_llm::executor::multimodalinput::mmultimodalhashes (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15MultimodalInput17mMultimodalHashesE", false]], "tensorrt_llm::executor::multimodalinput::mmultimodallengths (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15MultimodalInput18mMultimodalLengthsE", false]], "tensorrt_llm::executor::multimodalinput::mmultimodalpositions (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15MultimodalInput20mMultimodalPositionsE", false]], "tensorrt_llm::executor::multimodalinput::multimodalinput (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15MultimodalInput15MultimodalInputENSt6vectorINSt6vectorI10SizeType32EEEENSt6vectorI10SizeType32EENSt6vectorI10SizeType32EE", false]], "tensorrt_llm::executor::operator<< (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE21ContextChunkingPolicy", false], [0, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE23CapacitySchedulerPolicy", false]], "tensorrt_llm::executor::orchestratorconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfigE", false]], "tensorrt_llm::executor::orchestratorconfig::getisorchestrator (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getIsOrchestratorEv", false]], "tensorrt_llm::executor::orchestratorconfig::getorchleadercomm (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getOrchLeaderCommEv", false]], "tensorrt_llm::executor::orchestratorconfig::getspawnprocesses (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getSpawnProcessesEv", false]], "tensorrt_llm::executor::orchestratorconfig::getworkerexecutablepath (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig23getWorkerExecutablePathEv", false]], "tensorrt_llm::executor::orchestratorconfig::misorchestrator (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mIsOrchestratorE", false]], "tensorrt_llm::executor::orchestratorconfig::morchleadercomm (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mOrchLeaderCommE", false]], "tensorrt_llm::executor::orchestratorconfig::mspawnprocesses (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mSpawnProcessesE", false]], "tensorrt_llm::executor::orchestratorconfig::mworkerexecutablepath (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig21mWorkerExecutablePathE", false]], "tensorrt_llm::executor::orchestratorconfig::orchestratorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb", false]], "tensorrt_llm::executor::orchestratorconfig::setisorchestrator (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setIsOrchestratorEb", false]], "tensorrt_llm::executor::orchestratorconfig::setorchleadercomm (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setOrchLeaderCommERKNSt10shared_ptrIN3mpi7MpiCommEEE", false]], "tensorrt_llm::executor::orchestratorconfig::setspawnprocesses (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setSpawnProcessesEb", false]], "tensorrt_llm::executor::orchestratorconfig::setworkerexecutablepath (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig23setWorkerExecutablePathERKNSt6stringE", false]], "tensorrt_llm::executor::outputconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfigE", false]], "tensorrt_llm::executor::outputconfig::additionalmodeloutputs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig22additionalModelOutputsE", false]], "tensorrt_llm::executor::outputconfig::excludeinputfromoutput (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig22excludeInputFromOutputE", false]], "tensorrt_llm::executor::outputconfig::outputconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", false]], "tensorrt_llm::executor::outputconfig::returncontextlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig19returnContextLogitsE", false]], "tensorrt_llm::executor::outputconfig::returnencoderoutput (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig19returnEncoderOutputE", false]], "tensorrt_llm::executor::outputconfig::returngenerationlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig22returnGenerationLogitsE", false]], "tensorrt_llm::executor::outputconfig::returnlogprobs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig14returnLogProbsE", false]], "tensorrt_llm::executor::outputconfig::returnperfmetrics (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig17returnPerfMetricsE", false]], "tensorrt_llm::executor::parallelconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfigE", false]], "tensorrt_llm::executor::parallelconfig::getcommunicationmode (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig20getCommunicationModeEv", false]], "tensorrt_llm::executor::parallelconfig::getcommunicationtype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig20getCommunicationTypeEv", false]], "tensorrt_llm::executor::parallelconfig::getdeviceids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig12getDeviceIdsEv", false]], "tensorrt_llm::executor::parallelconfig::getnumnodes (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig11getNumNodesEv", false]], "tensorrt_llm::executor::parallelconfig::getorchestratorconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig21getOrchestratorConfigEv", false]], "tensorrt_llm::executor::parallelconfig::getparticipantids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig17getParticipantIdsEv", false]], "tensorrt_llm::executor::parallelconfig::mcommmode (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig9mCommModeE", false]], "tensorrt_llm::executor::parallelconfig::mcommtype (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig9mCommTypeE", false]], "tensorrt_llm::executor::parallelconfig::mdeviceids (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig10mDeviceIdsE", false]], "tensorrt_llm::executor::parallelconfig::mnumnodes (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig9mNumNodesE", false]], "tensorrt_llm::executor::parallelconfig::morchestratorconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig19mOrchestratorConfigE", false]], "tensorrt_llm::executor::parallelconfig::mparticipantids (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig15mParticipantIdsE", false]], "tensorrt_llm::executor::parallelconfig::parallelconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEENSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::parallelconfig::setcommunicationmode (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationModeE17CommunicationMode", false]], "tensorrt_llm::executor::parallelconfig::setcommunicationtype (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationTypeE17CommunicationType", false]], "tensorrt_llm::executor::parallelconfig::setdeviceids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig12setDeviceIdsERKNSt6vectorI10SizeType32EE", false]], "tensorrt_llm::executor::parallelconfig::setnumnodes (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig11setNumNodesE10SizeType32", false]], "tensorrt_llm::executor::parallelconfig::setorchestratorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig21setOrchestratorConfigERK18OrchestratorConfig", false]], "tensorrt_llm::executor::parallelconfig::setparticipantids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig17setParticipantIdsERKNSt6vectorI10SizeType32EE", false]], "tensorrt_llm::executor::peftcacheconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfigE", false]], "tensorrt_llm::executor::peftcacheconfig::getdevicecachepercent (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getDeviceCachePercentEv", false]], "tensorrt_llm::executor::peftcacheconfig::gethostcachesize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig16getHostCacheSizeEv", false]], "tensorrt_llm::executor::peftcacheconfig::getloraprefetchdir (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig18getLoraPrefetchDirEv", false]], "tensorrt_llm::executor::peftcacheconfig::getmaxadaptersize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig17getMaxAdapterSizeEv", false]], "tensorrt_llm::executor::peftcacheconfig::getmaxpagesperblockdevice (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig25getMaxPagesPerBlockDeviceEv", false]], "tensorrt_llm::executor::peftcacheconfig::getmaxpagesperblockhost (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig23getMaxPagesPerBlockHostEv", false]], "tensorrt_llm::executor::peftcacheconfig::getnumcopystreams (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig17getNumCopyStreamsEv", false]], "tensorrt_llm::executor::peftcacheconfig::getnumdevicemodulelayer (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig23getNumDeviceModuleLayerEv", false]], "tensorrt_llm::executor::peftcacheconfig::getnumensureworkers (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig19getNumEnsureWorkersEv", false]], "tensorrt_llm::executor::peftcacheconfig::getnumhostmodulelayer (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getNumHostModuleLayerEv", false]], "tensorrt_llm::executor::peftcacheconfig::getnumputworkers (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig16getNumPutWorkersEv", false]], "tensorrt_llm::executor::peftcacheconfig::getoptimaladaptersize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getOptimalAdapterSizeEv", false]], "tensorrt_llm::executor::peftcacheconfig::kdefaultmaxadaptersize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig22kDefaultMaxAdapterSizeE", false]], "tensorrt_llm::executor::peftcacheconfig::kdefaultmaxpagesperblockdevice (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig30kDefaultMaxPagesPerBlockDeviceE", false]], "tensorrt_llm::executor::peftcacheconfig::kdefaultmaxpagesperblockhost (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig28kDefaultMaxPagesPerBlockHostE", false]], "tensorrt_llm::executor::peftcacheconfig::kdefaultoptimaladaptersize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig26kDefaultOptimalAdapterSizeE", false]], "tensorrt_llm::executor::peftcacheconfig::mdevicecachepercent (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mDeviceCachePercentE", false]], "tensorrt_llm::executor::peftcacheconfig::mhostcachesize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig14mHostCacheSizeE", false]], "tensorrt_llm::executor::peftcacheconfig::mloraprefetchdir (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig16mLoraPrefetchDirE", false]], "tensorrt_llm::executor::peftcacheconfig::mmaxadaptersize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15mMaxAdapterSizeE", false]], "tensorrt_llm::executor::peftcacheconfig::mmaxpagesperblockdevice (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig23mMaxPagesPerBlockDeviceE", false]], "tensorrt_llm::executor::peftcacheconfig::mmaxpagesperblockhost (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig21mMaxPagesPerBlockHostE", false]], "tensorrt_llm::executor::peftcacheconfig::mnumcopystreams (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15mNumCopyStreamsE", false]], "tensorrt_llm::executor::peftcacheconfig::mnumdevicemodulelayer (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig21mNumDeviceModuleLayerE", false]], "tensorrt_llm::executor::peftcacheconfig::mnumensureworkers (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig17mNumEnsureWorkersE", false]], "tensorrt_llm::executor::peftcacheconfig::mnumhostmodulelayer (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mNumHostModuleLayerE", false]], "tensorrt_llm::executor::peftcacheconfig::mnumputworkers (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig14mNumPutWorkersE", false]], "tensorrt_llm::executor::peftcacheconfig::moptimaladaptersize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mOptimalAdapterSizeE", false]], "tensorrt_llm::executor::peftcacheconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfigeqERK15PeftCacheConfig", false]], "tensorrt_llm::executor::peftcacheconfig::peftcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", false]], "tensorrt_llm::executor::prioritytype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor12PriorityTypeE", false]], "tensorrt_llm::executor::prompttuningconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfigE", false]], "tensorrt_llm::executor::prompttuningconfig::getembeddingtable (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18PromptTuningConfig17getEmbeddingTableEv", false]], "tensorrt_llm::executor::prompttuningconfig::getinputtokenextraids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18PromptTuningConfig21getInputTokenExtraIdsEv", false]], "tensorrt_llm::executor::prompttuningconfig::membeddingtable (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig15mEmbeddingTableE", false]], "tensorrt_llm::executor::prompttuningconfig::minputtokenextraids (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig19mInputTokenExtraIdsE", false]], "tensorrt_llm::executor::prompttuningconfig::prompttuningconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig18PromptTuningConfigE6TensorNSt8optionalI16VecTokenExtraIdsEE", false]], "tensorrt_llm::executor::randomseedtype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor14RandomSeedTypeE", false]], "tensorrt_llm::executor::request (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor7RequestE", false]], "tensorrt_llm::executor::request::getadditionaloutputnames (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request24getAdditionalOutputNamesEv", false]], "tensorrt_llm::executor::request::getallottedtimems (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request17getAllottedTimeMsEv", false]], "tensorrt_llm::executor::request::getbadwords (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request11getBadWordsEv", false]], "tensorrt_llm::executor::request::getclientid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request11getClientIdEv", false]], "tensorrt_llm::executor::request::getcontextphaseparams (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request21getContextPhaseParamsEv", false]], "tensorrt_llm::executor::request::getcrossattentionmask (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request21getCrossAttentionMaskEv", false]], "tensorrt_llm::executor::request::geteagleconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request14getEagleConfigEv", false]], "tensorrt_llm::executor::request::getembeddingbias (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request16getEmbeddingBiasEv", false]], "tensorrt_llm::executor::request::getencoderinputfeatures (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request23getEncoderInputFeaturesEv", false]], "tensorrt_llm::executor::request::getencoderinputtokenids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request23getEncoderInputTokenIdsEv", false]], "tensorrt_llm::executor::request::getencoderoutputlength (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request22getEncoderOutputLengthEv", false]], "tensorrt_llm::executor::request::getendid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request8getEndIdEv", false]], "tensorrt_llm::executor::request::getexternaldrafttokensconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request28getExternalDraftTokensConfigEv", false]], "tensorrt_llm::executor::request::getguideddecodingparams (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request23getGuidedDecodingParamsEv", false]], "tensorrt_llm::executor::request::getinputtokenids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request16getInputTokenIdsEv", false]], "tensorrt_llm::executor::request::getkvcacheretentionconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request25getKvCacheRetentionConfigEv", false]], "tensorrt_llm::executor::request::getlanguageadapteruid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request21getLanguageAdapterUidEv", false]], "tensorrt_llm::executor::request::getlogitspostprocessor (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request22getLogitsPostProcessorEv", false]], "tensorrt_llm::executor::request::getlogitspostprocessorname (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request26getLogitsPostProcessorNameEv", false]], "tensorrt_llm::executor::request::getlookaheadconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request18getLookaheadConfigEv", false]], "tensorrt_llm::executor::request::getloraconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request13getLoraConfigEv", false]], "tensorrt_llm::executor::request::getmaxtokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request12getMaxTokensEv", false]], "tensorrt_llm::executor::request::getmropeconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request14getMropeConfigEv", false]], "tensorrt_llm::executor::request::getmultimodalembedding (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request22getMultimodalEmbeddingEv", false]], "tensorrt_llm::executor::request::getmultimodalinput (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request18getMultimodalInputEv", false]], "tensorrt_llm::executor::request::getoutputconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request15getOutputConfigEv", false]], "tensorrt_llm::executor::request::getpadid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request8getPadIdEv", false]], "tensorrt_llm::executor::request::getpositionids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request14getPositionIdsEv", false]], "tensorrt_llm::executor::request::getpriority (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request11getPriorityEv", false]], "tensorrt_llm::executor::request::getprompttuningconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request21getPromptTuningConfigEv", false]], "tensorrt_llm::executor::request::getrequesttype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request14getRequestTypeEv", false]], "tensorrt_llm::executor::request::getreturnallgeneratedtokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request27getReturnAllGeneratedTokensEv", false]], "tensorrt_llm::executor::request::getsamplingconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request17getSamplingConfigEv", false]], "tensorrt_llm::executor::request::getskipcrossattnblocks (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request22getSkipCrossAttnBlocksEv", false]], "tensorrt_llm::executor::request::getstopwords (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request12getStopWordsEv", false]], "tensorrt_llm::executor::request::getstreaming (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request12getStreamingEv", false]], "tensorrt_llm::executor::request::kbatchedpostprocessorname (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor7Request25kBatchedPostProcessorNameE", false]], "tensorrt_llm::executor::request::kdefaultpriority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor7Request16kDefaultPriorityE", false]], "tensorrt_llm::executor::request::kdynamicpostprocessornameprefix (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor7Request31kDynamicPostProcessorNamePrefixE", false]], "tensorrt_llm::executor::request::mimpl (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor7Request5mImplE", false]], "tensorrt_llm::executor::request::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7RequestaSERK7Request", false], [0, "_CPPv4N12tensorrt_llm8executor7RequestaSERR7Request", false]], "tensorrt_llm::executor::request::request (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", false], [0, "_CPPv4N12tensorrt_llm8executor7Request7RequestERK7Request", false], [0, "_CPPv4N12tensorrt_llm8executor7Request7RequestERR7Request", false]], "tensorrt_llm::executor::request::setallottedtimems (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request17setAllottedTimeMsE16MillisecondsType", false]], "tensorrt_llm::executor::request::setbadwords (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request11setBadWordsERKNSt4listI9VecTokensEE", false]], "tensorrt_llm::executor::request::setclientid (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request11setClientIdE6IdType", false]], "tensorrt_llm::executor::request::setcontextphaseparams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request21setContextPhaseParamsE18ContextPhaseParams", false]], "tensorrt_llm::executor::request::setcrossattentionmask (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request21setCrossAttentionMaskE6Tensor", false]], "tensorrt_llm::executor::request::seteagleconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request14setEagleConfigERKNSt8optionalI11EagleConfigEE", false]], "tensorrt_llm::executor::request::setembeddingbias (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request16setEmbeddingBiasERK6Tensor", false]], "tensorrt_llm::executor::request::setencoderinputfeatures (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputFeaturesE6Tensor", false]], "tensorrt_llm::executor::request::setencoderinputtokenids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputTokenIdsERK9VecTokens", false]], "tensorrt_llm::executor::request::setencoderoutputlength (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request22setEncoderOutputLengthE10SizeType32", false]], "tensorrt_llm::executor::request::setendid (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request8setEndIdE10SizeType32", false]], "tensorrt_llm::executor::request::setexternaldrafttokensconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request28setExternalDraftTokensConfigERK25ExternalDraftTokensConfig", false]], "tensorrt_llm::executor::request::setguideddecodingparams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request23setGuidedDecodingParamsERK20GuidedDecodingParams", false]], "tensorrt_llm::executor::request::setkvcacheretentionconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request25setKvCacheRetentionConfigERK22KvCacheRetentionConfig", false]], "tensorrt_llm::executor::request::setlanguageadapteruid (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request21setLanguageAdapterUidE10SizeType32", false]], "tensorrt_llm::executor::request::setlogitspostprocessor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request22setLogitsPostProcessorERKNSt8optionalI19LogitsPostProcessorEE", false]], "tensorrt_llm::executor::request::setlogitspostprocessorname (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request26setLogitsPostProcessorNameERKNSt6stringE", false]], "tensorrt_llm::executor::request::setlookaheadconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request18setLookaheadConfigERK23LookaheadDecodingConfig", false]], "tensorrt_llm::executor::request::setloraconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request13setLoraConfigERK10LoraConfig", false]], "tensorrt_llm::executor::request::setmropeconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request14setMropeConfigERK11MropeConfig", false]], "tensorrt_llm::executor::request::setmultimodalembedding (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request22setMultimodalEmbeddingERK6Tensor", false]], "tensorrt_llm::executor::request::setmultimodalinput (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request18setMultimodalInputERK15MultimodalInput", false]], "tensorrt_llm::executor::request::setoutputconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request15setOutputConfigERK12OutputConfig", false]], "tensorrt_llm::executor::request::setpadid (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request8setPadIdE10SizeType32", false]], "tensorrt_llm::executor::request::setpositionids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request14setPositionIdsERKNSt6vectorI10SizeType32EE", false]], "tensorrt_llm::executor::request::setpriority (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request11setPriorityE12PriorityType", false]], "tensorrt_llm::executor::request::setprompttuningconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request21setPromptTuningConfigERK18PromptTuningConfig", false]], "tensorrt_llm::executor::request::setrequesttype (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request14setRequestTypeERK11RequestType", false]], "tensorrt_llm::executor::request::setreturnallgeneratedtokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request27setReturnAllGeneratedTokensEb", false]], "tensorrt_llm::executor::request::setsamplingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request17setSamplingConfigERK14SamplingConfig", false]], "tensorrt_llm::executor::request::setskipcrossattnblocks (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request22setSkipCrossAttnBlocksE6Tensor", false]], "tensorrt_llm::executor::request::setstopwords (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request12setStopWordsERKNSt4listI9VecTokensEE", false]], "tensorrt_llm::executor::request::setstreaming (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request12setStreamingEb", false]], "tensorrt_llm::executor::request::~request (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7RequestD0Ev", false]], "tensorrt_llm::executor::requestperfmetrics (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetricsE", false]], "tensorrt_llm::executor::requestperfmetrics::firstiter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics9firstIterE", false]], "tensorrt_llm::executor::requestperfmetrics::iter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics4iterE", false]], "tensorrt_llm::executor::requestperfmetrics::kvcachemetrics (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14kvCacheMetricsE", false]], "tensorrt_llm::executor::requestperfmetrics::kvcachemetrics (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetricsE", false]], "tensorrt_llm::executor::requestperfmetrics::kvcachemetrics::kvcachehitrate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics14kvCacheHitRateE", false]], "tensorrt_llm::executor::requestperfmetrics::kvcachemetrics::nummissedblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics15numMissedBlocksE", false]], "tensorrt_llm::executor::requestperfmetrics::kvcachemetrics::numnewallocatedblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics21numNewAllocatedBlocksE", false]], "tensorrt_llm::executor::requestperfmetrics::kvcachemetrics::numreusedblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics15numReusedBlocksE", false]], "tensorrt_llm::executor::requestperfmetrics::kvcachemetrics::numtotalallocatedblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics23numTotalAllocatedBlocksE", false]], "tensorrt_llm::executor::requestperfmetrics::lastiter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics8lastIterE", false]], "tensorrt_llm::executor::requestperfmetrics::speculativedecoding (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics19speculativeDecodingE", false]], "tensorrt_llm::executor::requestperfmetrics::speculativedecodingmetrics (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics26SpeculativeDecodingMetricsE", false]], "tensorrt_llm::executor::requestperfmetrics::speculativedecodingmetrics::acceptancerate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics26SpeculativeDecodingMetrics14acceptanceRateE", false]], "tensorrt_llm::executor::requestperfmetrics::speculativedecodingmetrics::totalaccepteddrafttokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics26SpeculativeDecodingMetrics24totalAcceptedDraftTokensE", false]], "tensorrt_llm::executor::requestperfmetrics::speculativedecodingmetrics::totaldrafttokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics26SpeculativeDecodingMetrics16totalDraftTokensE", false]], "tensorrt_llm::executor::requestperfmetrics::timepoint (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics9TimePointE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13timingMetricsE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetricsE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics::arrivaltime (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics11arrivalTimeE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics::firstscheduledtime (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics18firstScheduledTimeE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics::firsttokentime (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics14firstTokenTimeE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics::kvcachesize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics11kvCacheSizeE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics::kvcachetransferend (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics18kvCacheTransferEndE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics::kvcachetransferstart (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics20kvCacheTransferStartE", false]], "tensorrt_llm::executor::requestperfmetrics::timingmetrics::lasttokentime (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics13lastTokenTimeE", false]], "tensorrt_llm::executor::requeststage (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStageE", false]], "tensorrt_llm::executor::requeststage::kcontext_in_progress (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStage20kCONTEXT_IN_PROGRESSE", false]], "tensorrt_llm::executor::requeststage::kencoder_in_progress (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStage20kENCODER_IN_PROGRESSE", false]], "tensorrt_llm::executor::requeststage::kgeneration_complete (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStage20kGENERATION_COMPLETEE", false]], "tensorrt_llm::executor::requeststage::kgeneration_in_progress (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStage23kGENERATION_IN_PROGRESSE", false]], "tensorrt_llm::executor::requeststage::kqueued (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStage7kQUEUEDE", false]], "tensorrt_llm::executor::requeststats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStatsE", false]], "tensorrt_llm::executor::requeststats::allocnewblocksperrequest (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats24allocNewBlocksPerRequestE", false]], "tensorrt_llm::executor::requeststats::alloctotalblocksperrequest (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats26allocTotalBlocksPerRequestE", false]], "tensorrt_llm::executor::requeststats::avgnumdecodedtokensperiter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats26avgNumDecodedTokensPerIterE", false]], "tensorrt_llm::executor::requeststats::contextprefillposition (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats22contextPrefillPositionE", false]], "tensorrt_llm::executor::requeststats::disservingstats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats15disServingStatsE", false]], "tensorrt_llm::executor::requeststats::id (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats2idE", false]], "tensorrt_llm::executor::requeststats::kvcachehitrateperrequest (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats24kvCacheHitRatePerRequestE", false]], "tensorrt_llm::executor::requeststats::missedblocksperrequest (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats22missedBlocksPerRequestE", false]], "tensorrt_llm::executor::requeststats::numgeneratedtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats18numGeneratedTokensE", false]], "tensorrt_llm::executor::requeststats::paused (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats6pausedE", false]], "tensorrt_llm::executor::requeststats::reusedblocksperrequest (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats22reusedBlocksPerRequestE", false]], "tensorrt_llm::executor::requeststats::scheduled (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats9scheduledE", false]], "tensorrt_llm::executor::requeststats::stage (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats5stageE", false]], "tensorrt_llm::executor::requeststatsperiteration (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIterationE", false]], "tensorrt_llm::executor::requeststatsperiteration::iter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIteration4iterE", false]], "tensorrt_llm::executor::requeststatsperiteration::requeststats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIteration12requestStatsE", false]], "tensorrt_llm::executor::requesttype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor11RequestTypeE", false]], "tensorrt_llm::executor::requesttype::request_type_context_and_generation (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor11RequestType35REQUEST_TYPE_CONTEXT_AND_GENERATIONE", false]], "tensorrt_llm::executor::requesttype::request_type_context_only (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor11RequestType25REQUEST_TYPE_CONTEXT_ONLYE", false]], "tensorrt_llm::executor::requesttype::request_type_generation_only (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor11RequestType28REQUEST_TYPE_GENERATION_ONLYE", false]], "tensorrt_llm::executor::response (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8ResponseE", false]], "tensorrt_llm::executor::response::getclientid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Response11getClientIdEv", false]], "tensorrt_llm::executor::response::geterrormsg (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Response11getErrorMsgEv", false]], "tensorrt_llm::executor::response::getrequestid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Response12getRequestIdEv", false]], "tensorrt_llm::executor::response::getresult (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Response9getResultEv", false]], "tensorrt_llm::executor::response::haserror (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Response8hasErrorEv", false]], "tensorrt_llm::executor::response::mimpl (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8Response5mImplE", false]], "tensorrt_llm::executor::response::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8ResponseaSERK8Response", false], [0, "_CPPv4N12tensorrt_llm8executor8ResponseaSERR8Response", false]], "tensorrt_llm::executor::response::response (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdType6ResultNSt8optionalI6IdTypeEE", false], [0, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdTypeNSt6stringENSt8optionalI6IdTypeEE", false], [0, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERK8Response", false], [0, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERR8Response", false]], "tensorrt_llm::executor::response::~response (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8ResponseD0Ev", false]], "tensorrt_llm::executor::result (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor6ResultE", false]], "tensorrt_llm::executor::result::additionaloutputs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result17additionalOutputsE", false]], "tensorrt_llm::executor::result::contextlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result13contextLogitsE", false]], "tensorrt_llm::executor::result::contextphaseparams (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result18contextPhaseParamsE", false]], "tensorrt_llm::executor::result::cumlogprobs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result11cumLogProbsE", false]], "tensorrt_llm::executor::result::decodingiter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result12decodingIterE", false]], "tensorrt_llm::executor::result::encoderoutput (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result13encoderOutputE", false]], "tensorrt_llm::executor::result::finishreasons (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result13finishReasonsE", false]], "tensorrt_llm::executor::result::generationlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result16generationLogitsE", false]], "tensorrt_llm::executor::result::isfinal (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result7isFinalE", false]], "tensorrt_llm::executor::result::issequencefinal (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result15isSequenceFinalE", false]], "tensorrt_llm::executor::result::logprobs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result8logProbsE", false]], "tensorrt_llm::executor::result::outputtokenids (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result14outputTokenIdsE", false]], "tensorrt_llm::executor::result::requestperfmetrics (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result18requestPerfMetricsE", false]], "tensorrt_llm::executor::result::sequenceindex (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result13sequenceIndexE", false]], "tensorrt_llm::executor::result::specdecfastlogitsinfo (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result21specDecFastLogitsInfoE", false]], "tensorrt_llm::executor::retentionpriority (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor17RetentionPriorityE", false]], "tensorrt_llm::executor::retentionpriorityandduration (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDurationE", false]], "tensorrt_llm::executor::retentionpriorityandduration::durationms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDuration10durationMsE", false]], "tensorrt_llm::executor::retentionpriorityandduration::retentionpriority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDuration17retentionPriorityE", false]], "tensorrt_llm::executor::retentionpriorityandduration::retentionpriorityandduration (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDuration28RetentionPriorityAndDurationERKNSt8optionalI17RetentionPriorityEERKNSt8optionalINSt6chrono12millisecondsEEE", false]], "tensorrt_llm::executor::samplingconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfigE", false]], "tensorrt_llm::executor::samplingconfig::checkbeamsearchdiversityrate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig28checkBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checkbeamwidth (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkBeamWidthE10SizeType32", false]], "tensorrt_llm::executor::samplingconfig::checkbeamwidtharray (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19checkBeamWidthArrayERKNSt8optionalINSt6vectorI10SizeType32EEEEK10SizeType32", false]], "tensorrt_llm::executor::samplingconfig::checkearlystopping (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18checkEarlyStoppingERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::samplingconfig::checklengthpenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18checkLengthPenaltyERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checkminp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkMinPERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checkmintokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkMinTokensERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::samplingconfig::checknorepeatngramsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::samplingconfig::checknumreturnsequences (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig23checkNumReturnSequencesERKNSt8optionalI10SizeType32EE10SizeType32", false]], "tensorrt_llm::executor::samplingconfig::checkrepetitionpenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkRepetitionPenaltyERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checktemperature (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16checkTemperatureERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checktopk (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopKERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checktopp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopPERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checktoppdecay (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkTopPDecayERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checktoppmin (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12checkTopPMinERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::checktoppresetids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17checkTopPResetIdsERKNSt8optionalI11TokenIdTypeEE", false]], "tensorrt_llm::executor::samplingconfig::getbeamsearchdiversityrate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig26getBeamSearchDiversityRateEv", false]], "tensorrt_llm::executor::samplingconfig::getbeamwidth (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getBeamWidthEv", false]], "tensorrt_llm::executor::samplingconfig::getbeamwidtharray (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig17getBeamWidthArrayEv", false]], "tensorrt_llm::executor::samplingconfig::getearlystopping (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig16getEarlyStoppingEv", false]], "tensorrt_llm::executor::samplingconfig::getfrequencypenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig19getFrequencyPenaltyEv", false]], "tensorrt_llm::executor::samplingconfig::getlengthpenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig16getLengthPenaltyEv", false]], "tensorrt_llm::executor::samplingconfig::getminp (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getMinPEv", false]], "tensorrt_llm::executor::samplingconfig::getmintokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getMinTokensEv", false]], "tensorrt_llm::executor::samplingconfig::getnorepeatngramsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig20getNoRepeatNgramSizeEv", false]], "tensorrt_llm::executor::samplingconfig::getnumreturnbeams (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig17getNumReturnBeamsEv", false]], "tensorrt_llm::executor::samplingconfig::getnumreturnsequences (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig21getNumReturnSequencesEv", false]], "tensorrt_llm::executor::samplingconfig::getpresencepenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig18getPresencePenaltyEv", false]], "tensorrt_llm::executor::samplingconfig::getrepetitionpenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig20getRepetitionPenaltyEv", false]], "tensorrt_llm::executor::samplingconfig::getseed (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getSeedEv", false]], "tensorrt_llm::executor::samplingconfig::gettemperature (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig14getTemperatureEv", false]], "tensorrt_llm::executor::samplingconfig::gettopk (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getTopKEv", false]], "tensorrt_llm::executor::samplingconfig::gettopp (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getTopPEv", false]], "tensorrt_llm::executor::samplingconfig::gettoppdecay (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getTopPDecayEv", false]], "tensorrt_llm::executor::samplingconfig::gettoppmin (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig10getTopPMinEv", false]], "tensorrt_llm::executor::samplingconfig::gettoppresetids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig15getTopPResetIdsEv", false]], "tensorrt_llm::executor::samplingconfig::mbeamsearchdiversityrate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig24mBeamSearchDiversityRateE", false]], "tensorrt_llm::executor::samplingconfig::mbeamwidth (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mBeamWidthE", false]], "tensorrt_llm::executor::samplingconfig::mbeamwidtharray (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig15mBeamWidthArrayE", false]], "tensorrt_llm::executor::samplingconfig::mearlystopping (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14mEarlyStoppingE", false]], "tensorrt_llm::executor::samplingconfig::mfrequencypenalty (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17mFrequencyPenaltyE", false]], "tensorrt_llm::executor::samplingconfig::mlengthpenalty (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14mLengthPenaltyE", false]], "tensorrt_llm::executor::samplingconfig::mminp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mMinPE", false]], "tensorrt_llm::executor::samplingconfig::mmintokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mMinTokensE", false]], "tensorrt_llm::executor::samplingconfig::mnorepeatngramsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18mNoRepeatNgramSizeE", false]], "tensorrt_llm::executor::samplingconfig::mnumreturnbeams (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig15mNumReturnBeamsE", false]], "tensorrt_llm::executor::samplingconfig::mnumreturnsequences (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19mNumReturnSequencesE", false]], "tensorrt_llm::executor::samplingconfig::mpresencepenalty (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16mPresencePenaltyE", false]], "tensorrt_llm::executor::samplingconfig::mrepetitionpenalty (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18mRepetitionPenaltyE", false]], "tensorrt_llm::executor::samplingconfig::mseed (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mSeedE", false]], "tensorrt_llm::executor::samplingconfig::mtemperature (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12mTemperatureE", false]], "tensorrt_llm::executor::samplingconfig::mtopk (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mTopKE", false]], "tensorrt_llm::executor::samplingconfig::mtopp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mTopPE", false]], "tensorrt_llm::executor::samplingconfig::mtoppdecay (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mTopPDecayE", false]], "tensorrt_llm::executor::samplingconfig::mtoppmin (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig8mTopPMinE", false]], "tensorrt_llm::executor::samplingconfig::mtoppresetids (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig13mTopPResetIdsE", false]], "tensorrt_llm::executor::samplingconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfigeqERK14SamplingConfig", false]], "tensorrt_llm::executor::samplingconfig::samplingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", false]], "tensorrt_llm::executor::samplingconfig::setbeamsearchdiversityrate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig26setBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::setbeamwidth (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setBeamWidthE10SizeType32", false]], "tensorrt_llm::executor::samplingconfig::setbeamwidtharray (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17setBeamWidthArrayERKNSt8optionalINSt6vectorI10SizeType32EEEE", false]], "tensorrt_llm::executor::samplingconfig::setearlystopping (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setEarlyStoppingERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::samplingconfig::setfrequencypenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19setFrequencyPenaltyERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::setlengthpenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setLengthPenaltyERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::setminp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setMinPERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::setmintokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setMinTokensERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::samplingconfig::setnorepeatngramsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::samplingconfig::setnumreturnsequences (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig21setNumReturnSequencesERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::samplingconfig::setpresencepenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18setPresencePenaltyERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::setrepetitionpenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setRepetitionPenaltyERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::setseed (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setSeedERKNSt8optionalI14RandomSeedTypeEE", false]], "tensorrt_llm::executor::samplingconfig::settemperature (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14setTemperatureERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::settopk (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopKERKNSt8optionalI10SizeType32EE", false]], "tensorrt_llm::executor::samplingconfig::settopp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopPERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::settoppdecay (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setTopPDecayERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::settoppmin (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10setTopPMinERKNSt8optionalI9FloatTypeEE", false]], "tensorrt_llm::executor::samplingconfig::settoppresetids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig15setTopPResetIdsERKNSt8optionalI11TokenIdTypeEE", false]], "tensorrt_llm::executor::samplingconfig::updatenumreturnbeams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20updateNumReturnBeamsEv", false]], "tensorrt_llm::executor::schedulerconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor15SchedulerConfigE", false]], "tensorrt_llm::executor::schedulerconfig::getcapacityschedulerpolicy (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfig26getCapacitySchedulerPolicyEv", false]], "tensorrt_llm::executor::schedulerconfig::getcontextchunkingpolicy (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfig24getContextChunkingPolicyEv", false]], "tensorrt_llm::executor::schedulerconfig::getdynamicbatchconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfig21getDynamicBatchConfigEv", false]], "tensorrt_llm::executor::schedulerconfig::mcapacityschedulerpolicy (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig24mCapacitySchedulerPolicyE", false]], "tensorrt_llm::executor::schedulerconfig::mcontextchunkingpolicy (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig22mContextChunkingPolicyE", false]], "tensorrt_llm::executor::schedulerconfig::mdynamicbatchconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig19mDynamicBatchConfigE", false]], "tensorrt_llm::executor::schedulerconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfigeqERK15SchedulerConfig", false]], "tensorrt_llm::executor::schedulerconfig::schedulerconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig15SchedulerConfigE23CapacitySchedulerPolicyNSt8optionalI21ContextChunkingPolicyEENSt8optionalI18DynamicBatchConfigEE", false]], "tensorrt_llm::executor::serialization (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor13SerializationE", false]], "tensorrt_llm::executor::serialization::deserializeadditionalmodeloutput (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeAdditionalModelOutputERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeadditionaloutput (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization27deserializeAdditionalOutputERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeagentstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeAgentStateERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializebool (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization15deserializeBoolERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializecachestate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeCacheStateERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializecachetransceiverconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeCacheTransceiverConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializecommstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeCommStateERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializecontextphaseparams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeContextPhaseParamsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializedatatransceiverstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeDataTransceiverStateERNSt6vectorIcEE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeDataTransceiverStateERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializedebugconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeDebugConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializedecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeDecodingConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializedecodingmode (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeDecodingModeERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializedisservingrequeststats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeDisServingRequestStatsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializedynamicbatchconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeDynamicBatchConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeeagleconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeEagleConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeexecutorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeExecutorConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeextendedruntimeperfknobconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization40deserializeExtendedRuntimePerfKnobConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeexternaldrafttokensconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeExternalDraftTokensConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeguideddecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeGuidedDecodingConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeguideddecodingparams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeGuidedDecodingParamsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeinflightbatchingstats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeInflightBatchingStatsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeiterationstats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt6vectorIcEE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeiterationstatsvec (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization28deserializeIterationStatsVecERNSt6vectorIcEE", false]], "tensorrt_llm::executor::serialization::deserializekvcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization24deserializeKvCacheConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializekvcacheretentionconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeKvCacheRetentionConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializekvcachestats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeKvCacheStatsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializelookaheaddecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization34deserializeLookaheadDecodingConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeloraconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeLoraConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializemodeltype (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeModelTypeERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializemropeconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeMropeConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializemultimodalinput (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializeMultimodalInputERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeorchestratorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeOrchestratorConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeoutputconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeOutputConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeparallelconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeParallelConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializepeftcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializePeftCacheConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeprompttuningconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializePromptTuningConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializerequest (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization18deserializeRequestERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializerequestperfmetrics (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeRequestPerfMetricsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializerequeststage (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeRequestStageERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializerequeststats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeRequestStatsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializerequeststatsperiteration (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization35deserializeRequestStatsPerIterationERNSt6vectorIcEE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization35deserializeRequestStatsPerIterationERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializerequeststatsperiterationvec (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization38deserializeRequestStatsPerIterationVecERNSt6vectorIcEE", false]], "tensorrt_llm::executor::serialization::deserializeresponse (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization19deserializeResponseERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeresponses (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeResponsesERNSt6vectorIcEE", false]], "tensorrt_llm::executor::serialization::deserializeresult (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeResultERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializesamplingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeSamplingConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializeschedulerconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializeSchedulerConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializesocketstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeSocketStateERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializespecdecfastlogitsinfo (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeSpecDecFastLogitsInfoERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializespecdecodingstats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization28deserializeSpecDecodingStatsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializespeculativedecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeSpeculativeDecodingConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializestaticbatchingstats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization30deserializeStaticBatchingStatsERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializestring (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeStringERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializetensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeTensorERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializetimepoint (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeTimePointERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::deserializetokenrangeretentionconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeTokenRangeRetentionConfigERNSt7istreamE", false]], "tensorrt_llm::executor::serialization::serialize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK10LoraConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11DebugConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11EagleConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11MropeConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12DecodingModeRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12KvCacheStatsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12OutputConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12RequestStageRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12RequestStatsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK13KvCacheConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14DecodingConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ExecutorConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStats", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStatsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ParallelConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14SamplingConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15MultimodalInputRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15PeftCacheConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15SchedulerConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK16AdditionalOutputRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK17SpecDecodingStatsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18ContextPhaseParamsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18DynamicBatchConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18OrchestratorConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18PromptTuningConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18RequestPerfMetricsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK19StaticBatchingStatsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20DataTransceiverState", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20DataTransceiverStateRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20GuidedDecodingConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20GuidedDecodingParamsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21AdditionalModelOutputRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21InflightBatchingStatsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22CacheTransceiverConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22DisServingRequestStatsRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22KvCacheRetentionConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK23LookaheadDecodingConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK24RequestStatsPerIteration", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK24RequestStatsPerIterationRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25ExternalDraftTokensConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25SpeculativeDecodingConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK29ExtendedRuntimePerfKnobConfigRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK33SpeculativeDecodingFastLogitsInfoRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6ResultRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6TensorRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK7RequestRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK8ResponseRNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN18RequestPerfMetrics9TimePointERNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN22KvCacheRetentionConfig25TokenRangeRetentionConfigERNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10AgentStateERNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10CacheStateERNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache11SocketStateERNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache9CommStateERNSt7ostreamE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI14IterationStatsEE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI24RequestStatsPerIterationEE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI8ResponseEE", false]], "tensorrt_llm::executor::serialization::serializedsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK10LoraConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11DebugConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11EagleConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11MropeConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12DecodingMode", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12KvCacheStats", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12OutputConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12RequestStage", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12RequestStats", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK13KvCacheConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14DecodingConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ExecutorConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14IterationStats", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ParallelConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14SamplingConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15MultimodalInput", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15PeftCacheConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15SchedulerConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK16AdditionalOutput", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK17SpecDecodingStats", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18ContextPhaseParams", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18DynamicBatchConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18OrchestratorConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18PromptTuningConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18RequestPerfMetrics", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK19StaticBatchingStats", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20DataTransceiverState", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20GuidedDecodingConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20GuidedDecodingParams", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK21AdditionalModelOutput", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK21InflightBatchingStats", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22CacheTransceiverConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22DisServingRequestStats", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22KvCacheRetentionConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK23LookaheadDecodingConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK24RequestStatsPerIteration", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK25ExternalDraftTokensConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK25SpeculativeDecodingConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK29ExtendedRuntimePerfKnobConfig", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK33SpeculativeDecodingFastLogitsInfo", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Result", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Tensor", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK7Request", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK8Response", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN18RequestPerfMetrics9TimePointE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN22KvCacheRetentionConfig25TokenRangeRetentionConfigE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache10AgentStateE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache10CacheStateE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache11SocketStateE", false], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache9CommStateE", false]], "tensorrt_llm::executor::shape (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor5ShapeE", false]], "tensorrt_llm::executor::shape::base (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor5Shape4BaseE", false]], "tensorrt_llm::executor::shape::dimtype64 (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor5Shape9DimType64E", false]], "tensorrt_llm::executor::shape::shape (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeENSt16initializer_listI9DimType64EE", false], [0, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEPK9DimType64N4Base9size_typeE", false], [0, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEv", false]], "tensorrt_llm::executor::sizetype32 (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor10SizeType32E", false]], "tensorrt_llm::executor::sizetype64 (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor10SizeType64E", false]], "tensorrt_llm::executor::specdecodingstats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStatsE", false]], "tensorrt_llm::executor::specdecodingstats::acceptancelength (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats16acceptanceLengthE", false]], "tensorrt_llm::executor::specdecodingstats::draftoverhead (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats13draftOverheadE", false]], "tensorrt_llm::executor::specdecodingstats::iterlatencyms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats13iterLatencyMSE", false]], "tensorrt_llm::executor::specdecodingstats::numacceptedtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats17numAcceptedTokensE", false]], "tensorrt_llm::executor::specdecodingstats::numdrafttokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats14numDraftTokensE", false]], "tensorrt_llm::executor::specdecodingstats::numrequestswithdrafttokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats26numRequestsWithDraftTokensE", false]], "tensorrt_llm::executor::speculativedecodingconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor25SpeculativeDecodingConfigE", false]], "tensorrt_llm::executor::speculativedecodingconfig::fastlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25SpeculativeDecodingConfig10fastLogitsE", false]], "tensorrt_llm::executor::speculativedecodingconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25SpeculativeDecodingConfigeqERK25SpeculativeDecodingConfig", false]], "tensorrt_llm::executor::speculativedecodingconfig::speculativedecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor25SpeculativeDecodingConfig25SpeculativeDecodingConfigEb", false]], "tensorrt_llm::executor::speculativedecodingfastlogitsinfo (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor33SpeculativeDecodingFastLogitsInfoE", false]], "tensorrt_llm::executor::speculativedecodingfastlogitsinfo::draftparticipantid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor33SpeculativeDecodingFastLogitsInfo18draftParticipantIdE", false]], "tensorrt_llm::executor::speculativedecodingfastlogitsinfo::draftrequestid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor33SpeculativeDecodingFastLogitsInfo14draftRequestIdE", false]], "tensorrt_llm::executor::speculativedecodingfastlogitsinfo::totensor (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor33SpeculativeDecodingFastLogitsInfo8toTensorEv", false]], "tensorrt_llm::executor::staticbatchingstats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStatsE", false]], "tensorrt_llm::executor::staticbatchingstats::emptygenslots (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats13emptyGenSlotsE", false]], "tensorrt_llm::executor::staticbatchingstats::numcontextrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats18numContextRequestsE", false]], "tensorrt_llm::executor::staticbatchingstats::numctxtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats12numCtxTokensE", false]], "tensorrt_llm::executor::staticbatchingstats::numgentokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats12numGenTokensE", false]], "tensorrt_llm::executor::staticbatchingstats::numscheduledrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats20numScheduledRequestsE", false]], "tensorrt_llm::executor::streamptr (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor9StreamPtrE", false]], "tensorrt_llm::executor::tensor (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor6TensorE", false]], "tensorrt_llm::executor::tensor::copyto (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor6copyToENSt10shared_ptrI4ImplEE13CudaStreamPtr", false]], "tensorrt_llm::executor::tensor::copytocpu (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToCpuEN6Tensor13CudaStreamPtrE", false]], "tensorrt_llm::executor::tensor::copytogpu (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToGpuEN6Tensor13CudaStreamPtrE", false]], "tensorrt_llm::executor::tensor::copytomanaged (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor13copyToManagedEN6Tensor13CudaStreamPtrE", false]], "tensorrt_llm::executor::tensor::copytopinned (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor12copyToPinnedEN6Tensor13CudaStreamPtrE", false]], "tensorrt_llm::executor::tensor::copytopooledpinned (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor18copyToPooledPinnedEN6Tensor13CudaStreamPtrE", false]], "tensorrt_llm::executor::tensor::cpu (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3cpuE6Tensor5Shape", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor3cpuE8DataType5Shape", false]], "tensorrt_llm::executor::tensor::cudastreamptr (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor13CudaStreamPtrE", false]], "tensorrt_llm::executor::tensor::detail::ofitensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE", false]], "tensorrt_llm::executor::tensor::detail::toitensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9toITensorERK6Tensor", false]], "tensorrt_llm::executor::tensor::getdata (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor7getDataEv", false], [0, "_CPPv4NK12tensorrt_llm8executor6Tensor7getDataEv", false]], "tensorrt_llm::executor::tensor::getdatatype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor11getDataTypeEv", false]], "tensorrt_llm::executor::tensor::getmemorytype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor13getMemoryTypeEv", false]], "tensorrt_llm::executor::tensor::getruntimetype (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor14getRuntimeTypeE8DataTypev", false]], "tensorrt_llm::executor::tensor::getshape (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor8getShapeEv", false]], "tensorrt_llm::executor::tensor::getsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor7getSizeEv", false]], "tensorrt_llm::executor::tensor::getsizeinbytes (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor14getSizeInBytesEv", false]], "tensorrt_llm::executor::tensor::gpu (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3gpuE6Tensor13CudaStreamPtr5Shape", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor3gpuE8DataType13CudaStreamPtr5Shape", false]], "tensorrt_llm::executor::tensor::impl (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor4ImplE", false]], "tensorrt_llm::executor::tensor::managed (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor7managedE6Tensor5Shape", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor7managedE8DataType5Shape", false]], "tensorrt_llm::executor::tensor::mtensor (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor7mTensorE", false]], "tensorrt_llm::executor::tensor::of (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorP1T5Shape", false], [0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorR1T", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor2ofE8DataTypePv5Shape", false]], "tensorrt_llm::executor::tensor::operator bool (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6TensorcvbEv", false]], "tensorrt_llm::executor::tensor::operator!= (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6TensorneERK6Tensor", false]], "tensorrt_llm::executor::tensor::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6TensoraSERK6Tensor", false], [0, "_CPPv4N12tensorrt_llm8executor6TensoraSERR6Tensor", false]], "tensorrt_llm::executor::tensor::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6TensoreqERK6Tensor", false]], "tensorrt_llm::executor::tensor::pinned (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor6pinnedE6Tensor5Shape", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor6pinnedE8DataType5Shape", false]], "tensorrt_llm::executor::tensor::pooledpinned (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor12pooledPinnedE6Tensor5Shape", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor12pooledPinnedE8DataType5Shape", false]], "tensorrt_llm::executor::tensor::setfrom (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor7setFromERK6Tensor13CudaStreamPtr", false]], "tensorrt_llm::executor::tensor::setzero (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor7setZeroE13CudaStreamPtr", false]], "tensorrt_llm::executor::tensor::tensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorENSt10shared_ptrIN7runtime7ITensorEEE", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERK6Tensor", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERR6Tensor", false], [0, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorEv", false]], "tensorrt_llm::executor::tensor::~tensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6TensorD0Ev", false]], "tensorrt_llm::executor::tensorptr (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor9TensorPtrE", false]], "tensorrt_llm::executor::tokenidtype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor11TokenIdTypeE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4I0_bEN12tensorrt_llm8executor10TypeTraitsE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsIbEE", false]], "tensorrt_llm::executor::typetraits::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIbE5valueE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsIfEE", false]], "tensorrt_llm::executor::typetraits::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIfE5valueE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsI4halfEE", false]], "tensorrt_llm::executor::typetraits::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsI4halfE5valueE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7int32_tEEE", false]], "tensorrt_llm::executor::typetraits::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7int32_tEE5valueE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7int64_tEEE", false]], "tensorrt_llm::executor::typetraits::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7int64_tEE5valueE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt6int8_tEEE", false]], "tensorrt_llm::executor::typetraits::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt6int8_tEE5valueE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7uint8_tEEE", false]], "tensorrt_llm::executor::typetraits::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7uint8_tEE5valueE", false]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4I0EN12tensorrt_llm8executor10TypeTraitsIP1TEE", false]], "tensorrt_llm::executor::typetraits::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIP1TE5valueE", false]], "tensorrt_llm::executor::veclogprobs (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor11VecLogProbsE", false]], "tensorrt_llm::executor::vectokenextraids (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor16VecTokenExtraIdsE", false]], "tensorrt_llm::executor::vectokens (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor9VecTokensE", false]], "tensorrt_llm::executor::version (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7versionEv", false]], "tensorrt_llm::layers (c++ type)": [[1, "_CPPv4N12tensorrt_llm6layersE", false]], "tensorrt_llm::mpi (c++ type)": [[0, "_CPPv4N12tensorrt_llm3mpiE", false]], "tensorrt_llm::runtime (c++ type)": [[0, "_CPPv4N12tensorrt_llm7runtimeE", false], [1, "_CPPv4N12tensorrt_llm7runtimeE", false]], "tensorrt_llm::runtime::allreducebuffers (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffersE", false]], "tensorrt_llm::runtime::allreducebuffers::allreducebuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", false]], "tensorrt_llm::runtime::allreducebuffers::mallreducecommptrs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers18mAllReduceCommPtrsE", false]], "tensorrt_llm::runtime::allreducebuffers::mflagptrs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers9mFlagPtrsE", false]], "tensorrt_llm::runtime::allreducebuffers::mipcmemoryhandles (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers17mIpcMemoryHandlesE", false]], "tensorrt_llm::runtime::allreducebuffers::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers9TensorPtrE", false]], "tensorrt_llm::runtime::buffercast (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEP1TR7IBuffer", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEPK1TRK7IBuffer", false]], "tensorrt_llm::runtime::buffercastornull (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7IBuffer9SharedPtrE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7ITensor9SharedPtrE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7IBuffer9SharedPtrEEE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7ITensor9SharedPtrEEE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7IBuffer14SharedConstPtrE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7ITensor14SharedConstPtrE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7IBuffer14SharedConstPtrEEE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7ITensor14SharedConstPtrEEE", false]], "tensorrt_llm::runtime::bufferdatatype (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataTypeE", false]], "tensorrt_llm::runtime::bufferdatatype::bufferdatatype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb", false]], "tensorrt_llm::runtime::bufferdatatype::getdatatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType11getDataTypeEv", false]], "tensorrt_llm::runtime::bufferdatatype::getsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType7getSizeEv", false]], "tensorrt_llm::runtime::bufferdatatype::getsizeinbits (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType13getSizeInBitsEv", false]], "tensorrt_llm::runtime::bufferdatatype::ispointer (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType9isPointerEv", false]], "tensorrt_llm::runtime::bufferdatatype::isunsigned (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType10isUnsignedEv", false]], "tensorrt_llm::runtime::bufferdatatype::ktrtpointertype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType15kTrtPointerTypeE", false]], "tensorrt_llm::runtime::bufferdatatype::mdatatype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType9mDataTypeE", false]], "tensorrt_llm::runtime::bufferdatatype::mpointer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType8mPointerE", false]], "tensorrt_llm::runtime::bufferdatatype::munsigned (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType9mUnsignedE", false]], "tensorrt_llm::runtime::bufferdatatype::operator nvinfer1::datatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataTypecvN8nvinfer18DataTypeEEv", false]], "tensorrt_llm::runtime::buffermanager (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManagerE", false]], "tensorrt_llm::runtime::buffermanager::allocate (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE", false], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::buffermanager (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager13BufferManagerE13CudaStreamPtrb", false]], "tensorrt_llm::runtime::buffermanager::copy (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer", false], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType", false], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv", false], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType", false], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferR7IBuffer", false]], "tensorrt_llm::runtime::buffermanager::copyfrom (c++ function)": [[1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10IBufferPtrRKNSt6vectorI1TEE10MemoryType", false], [1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType", false], [1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType", false], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7IBuffer10MemoryType", false], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7ITensor10MemoryType", false]], "tensorrt_llm::runtime::buffermanager::cpu (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", false], [1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuENSt6size_tEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::cudamempoolptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager14CudaMemPoolPtrE", false]], "tensorrt_llm::runtime::buffermanager::cudastreamptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager13CudaStreamPtrE", false]], "tensorrt_llm::runtime::buffermanager::emptybuffer (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyBufferE10MemoryTypeN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::emptytensor (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyTensorE10MemoryTypeN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::getstream (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager9getStreamEv", false]], "tensorrt_llm::runtime::buffermanager::gpu (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", false], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuENSt6size_tEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::gpusync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncEN8nvinfer14DimsEN8nvinfer18DataTypeE", false], [1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncENSt6size_tEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::ibufferptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10IBufferPtrE", false]], "tensorrt_llm::runtime::buffermanager::ipcnvls (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7ipcNvlsENSt3setIiEEN8nvinfer14DimsEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::itensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10ITensorPtrE", false]], "tensorrt_llm::runtime::buffermanager::kbyte_type (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE", false]], "tensorrt_llm::runtime::buffermanager::managed (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedEN8nvinfer14DimsEN8nvinfer18DataTypeE", false], [1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedENSt6size_tEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::memorypoolfree (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager14memoryPoolFreeEv", false]], "tensorrt_llm::runtime::buffermanager::memorypoolreserved (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager18memoryPoolReservedEv", false]], "tensorrt_llm::runtime::buffermanager::memorypooltrimto (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager16memoryPoolTrimToENSt6size_tE", false]], "tensorrt_llm::runtime::buffermanager::memorypoolused (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager14memoryPoolUsedEv", false]], "tensorrt_llm::runtime::buffermanager::mpool (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager5mPoolE", false]], "tensorrt_llm::runtime::buffermanager::mstream (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7mStreamE", false]], "tensorrt_llm::runtime::buffermanager::mtrimpool (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager9mTrimPoolE", false]], "tensorrt_llm::runtime::buffermanager::pinned (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedEN8nvinfer14DimsEN8nvinfer18DataTypeE", false], [1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedENSt6size_tEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::pinnedpool (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolEN8nvinfer14DimsEN8nvinfer18DataTypeE", false], [1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolENSt6size_tEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::buffermanager::setmem (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager6setMemER7IBuffer7int32_t", false]], "tensorrt_llm::runtime::buffermanager::setzero (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager7setZeroER7IBuffer", false]], "tensorrt_llm::runtime::buffermanager::~buffermanager (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManagerD0Ev", false]], "tensorrt_llm::runtime::bufferrange (c++ class)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime11BufferRangeE", false]], "tensorrt_llm::runtime::bufferrange::base (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime11BufferRange4BaseE", false]], "tensorrt_llm::runtime::bufferrange::bufferrange (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI1UEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeERK7IBuffer", false], [1, "_CPPv4I0_NSt11enable_if_tIXntNSt10is_const_vI1UEEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeER7IBuffer", false], [1, "_CPPv4N12tensorrt_llm7runtime11BufferRange11BufferRangeEP1T9size_type", false]], "tensorrt_llm::runtime::canaccesspeer (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13canAccessPeerERK11WorldConfig", false]], "tensorrt_llm::runtime::constpointercast (c++ function)": [[1, "_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERKNSt10shared_ptrI1TEE", false]], "tensorrt_llm::runtime::cudaevent (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEventE", false]], "tensorrt_llm::runtime::cudaevent::cudaevent (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventE7pointerb", false], [1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventEj", false]], "tensorrt_llm::runtime::cudaevent::deleter (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7DeleterE", false]], "tensorrt_llm::runtime::cudaevent::deleter::deleter (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEb", false], [1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEv", false]], "tensorrt_llm::runtime::cudaevent::deleter::mownsevent (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter10mOwnsEventE", false]], "tensorrt_llm::runtime::cudaevent::deleter::operator() (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent7DeleterclE7pointer", false]], "tensorrt_llm::runtime::cudaevent::element_type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent12element_typeE", false]], "tensorrt_llm::runtime::cudaevent::eventptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent8EventPtrE", false]], "tensorrt_llm::runtime::cudaevent::get (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent3getEv", false]], "tensorrt_llm::runtime::cudaevent::mevent (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent6mEventE", false]], "tensorrt_llm::runtime::cudaevent::pointer (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7pointerE", false]], "tensorrt_llm::runtime::cudaevent::synchronize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent11synchronizeEv", false]], "tensorrt_llm::runtime::cudastream (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStreamE", false]], "tensorrt_llm::runtime::cudastream::cudastream (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_t", false], [1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib", false], [1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamEji", false]], "tensorrt_llm::runtime::cudastream::deleter (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7DeleterE", false]], "tensorrt_llm::runtime::cudastream::deleter::deleter (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEb", false], [1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEv", false]], "tensorrt_llm::runtime::cudastream::deleter::mownsstream (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter11mOwnsStreamE", false]], "tensorrt_llm::runtime::cudastream::deleter::operator() (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream7DeleterclE12cudaStream_t", false]], "tensorrt_llm::runtime::cudastream::get (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream3getEv", false]], "tensorrt_llm::runtime::cudastream::getdevice (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream9getDeviceEv", false]], "tensorrt_llm::runtime::cudastream::mdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7mDeviceE", false]], "tensorrt_llm::runtime::cudastream::mstream (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7mStreamE", false]], "tensorrt_llm::runtime::cudastream::record (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordEN9CudaEvent7pointerE", false], [1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordERK9CudaEvent", false]], "tensorrt_llm::runtime::cudastream::streamptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream9StreamPtrE", false]], "tensorrt_llm::runtime::cudastream::synchronize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream11synchronizeEv", false]], "tensorrt_llm::runtime::cudastream::wait (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitEN9CudaEvent7pointerE", false], [1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitERK9CudaEvent", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4I_N8nvinfer18DataTypeE_b_bEN12tensorrt_llm7runtime14DataTypeTraitsE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4typeE", false]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedEE", false]], "tensorrt_llm::runtime::datatypetraits::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4nameE", false]], "tensorrt_llm::runtime::datatypetraits::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4sizeE", false]], "tensorrt_llm::runtime::datatypetraits::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4typeE", false]], "tensorrt_llm::runtime::decoder (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoderE", false]], "tensorrt_llm::runtime::decoder::beamsearchbuffers (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffersE", false]], "tensorrt_llm::runtime::decoder::beamsearchbuffers::beamsearchbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers17BeamSearchBuffersERK13BufferManager", false]], "tensorrt_llm::runtime::decoder::beamsearchbuffers::mcumlogprobstmp (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers15mCumLogProbsTmpE", false]], "tensorrt_llm::runtime::decoder::beamsearchbuffers::mnumsms (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers7mNumSMsE", false]], "tensorrt_llm::runtime::decoder::beamsearchbuffers::moutputbeamhypotheses (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers21mOutputBeamHypothesesE", false]], "tensorrt_llm::runtime::decoder::beamsearchbuffers::reshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers7reshapeE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::decoder::decoderstate (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderStateE", false]], "tensorrt_llm::runtime::decoder::decoderstate::decoderstate (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState12DecoderStateEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::decodinginputptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState16DecodingInputPtrE", false]], "tensorrt_llm::runtime::decoder::decoderstate::decodingoutputptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState17DecodingOutputPtrE", false]], "tensorrt_llm::runtime::decoder::decoderstate::disablelookahead (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState16disableLookaheadERK13RequestVector", false]], "tensorrt_llm::runtime::decoder::decoderstate::getacceptedlengthscumsum (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState24getAcceptedLengthsCumSumEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getacceptedpackedpaths (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState22getAcceptedPackedPathsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getallnewtokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState15getAllNewTokensEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getbeamsearchbuffers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState20getBeamSearchBuffersEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getcacheindirectioninput (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState24getCacheIndirectionInputEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getcacheindirectionoutput (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState25getCacheIndirectionOutputEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getcumlogprobs (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getCumLogProbsE10SizeType32", false], [1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getCumLogProbsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::geteaglebuffers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState15getEagleBuffersEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getexplicitdrafttokensbuffers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState29getExplicitDraftTokensBuffersEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getfinishedsteps (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState16getFinishedStepsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getfinishedsum (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getFinishedSumEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getfinishreasons (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState16getFinishReasonsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getgatheredids (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getGatheredIdsE10SizeType32", false], [1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getGatheredIdsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getgenerationsteps (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getGenerationStepsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getids (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState6getIdsE10SizeType32", false], [1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState6getIdsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getjointdecodinginput (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState21getJointDecodingInputEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getjointdecodingoutput (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState22getJointDecodingOutputEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getlogprobs (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState11getLogProbsE10SizeType32", false], [1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState11getLogProbsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getlookaheadbuffers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState19getLookaheadBuffersEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getmaxbatchsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState15getMaxBatchSizeEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getmaxbeamwidth (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState15getMaxBeamWidthEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getmaxdecodingdecodertokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState27getMaxDecodingDecoderTokensEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getmaxdecodingenginetokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getMaxDecodingEngineTokensEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getmaxsequencelength (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState20getMaxSequenceLengthEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getnextdrafttokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getNextDraftTokensEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getnextdrafttokenslengths (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState25getNextDraftTokensLengthsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getnumdecodingenginetokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getNumDecodingEngineTokensE10SizeType32", false], [1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getNumDecodingEngineTokensEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getparentids (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState12getParentIdsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getprevdrafttokenslengths (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState25getPrevDraftTokensLengthsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getsequencelengths (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getSequenceLengthsE10SizeType32", false], [1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getSequenceLengthsEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::getspeculativedecodingmode (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getSpeculativeDecodingModeEv", false]], "tensorrt_llm::runtime::decoder::decoderstate::llmrequestptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState13LlmRequestPtrE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mbeamsearchbuffers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState18mBeamSearchBuffersE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mfinishedsteps (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14mFinishedStepsE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mjointdecodinginput (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState19mJointDecodingInputE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mjointdecodingoutput (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState20mJointDecodingOutputE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mmaxbatchsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState13mMaxBatchSizeE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mmaxbeamwidth (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState13mMaxBeamWidthE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mmaxdecodingdecodertokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState25mMaxDecodingDecoderTokensE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mmaxdecodingenginetokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24mMaxDecodingEngineTokensE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mmaxsequencelength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState18mMaxSequenceLengthE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mnumdecodingenginetokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24mNumDecodingEngineTokensE", false]], "tensorrt_llm::runtime::decoder::decoderstate::mspeculativedecodingmode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24mSpeculativeDecodingModeE", false]], "tensorrt_llm::runtime::decoder::decoderstate::requestvector (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState13RequestVectorE", false]], "tensorrt_llm::runtime::decoder::decoderstate::reshapebuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", false]], "tensorrt_llm::runtime::decoder::decoderstate::reshapecacheindirectionbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState30reshapeCacheIndirectionBuffersE10SizeType3210SizeType3210SizeType32", false]], "tensorrt_llm::runtime::decoder::decoderstate::reshapespeculativedecodingbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState33reshapeSpeculativeDecodingBuffersERK23SpeculativeDecodingMode10SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", false]], "tensorrt_llm::runtime::decoder::decoderstate::setgenerationsteps (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState18setGenerationStepsERKNSt6vectorI10SizeType32EE", false]], "tensorrt_llm::runtime::decoder::decoderstate::setnumdecodingenginetokens (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState26setNumDecodingEngineTokensE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::decoder::decoderstate::setup (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", false]], "tensorrt_llm::runtime::decoder::decoderstate::setupbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState12setupBuffersEN8nvinfer18DataTypeERK13BufferManager", false]], "tensorrt_llm::runtime::decoder::decoderstate::setupcacheindirection (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState21setupCacheIndirectionE10SizeType3210SizeType3210SizeType32RK13BufferManager", false]], "tensorrt_llm::runtime::decoder::decoderstate::setupcacheindirectionbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState28setupCacheIndirectionBuffersERK13BufferManager", false]], "tensorrt_llm::runtime::decoder::decoderstate::setupspeculativedecoding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24setupSpeculativeDecodingERK23SpeculativeDecodingMode10SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", false]], "tensorrt_llm::runtime::decoder::decoderstate::setupspeculativedecodingbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState31setupSpeculativeDecodingBuffersE23SpeculativeDecodingModeN8nvinfer18DataTypeERK13BufferManager", false]], "tensorrt_llm::runtime::decoder::decoderstate::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState9TensorPtrE", false]], "tensorrt_llm::runtime::decoder_batch (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batchE", false]], "tensorrt_llm::runtime::decoder_batch::input (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5InputE", false]], "tensorrt_llm::runtime::decoder_batch::input::batchslots (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input10batchSlotsE", false]], "tensorrt_llm::runtime::decoder_batch::input::input (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI14TensorConstPtrEE", false], [1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorINSt6vectorI14TensorConstPtrEEEE10SizeType32", false]], "tensorrt_llm::runtime::decoder_batch::input::logits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input6logitsE", false]], "tensorrt_llm::runtime::decoder_batch::input::maxdecodersteps (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input15maxDecoderStepsE", false]], "tensorrt_llm::runtime::decoder_batch::input::tensorconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input14TensorConstPtrE", false]], "tensorrt_llm::runtime::decoder_batch::input::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input9TensorPtrE", false]], "tensorrt_llm::runtime::decoder_batch::request (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7RequestE", false]], "tensorrt_llm::runtime::decoder_batch::request::badwordslist (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request12badWordsListE", false]], "tensorrt_llm::runtime::decoder_batch::request::bufferptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9BufferPtrE", false]], "tensorrt_llm::runtime::decoder_batch::request::draftlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11draftLogitsE", false]], "tensorrt_llm::runtime::decoder_batch::request::drafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11draftTokensE", false]], "tensorrt_llm::runtime::decoder_batch::request::eagleconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11eagleConfigE", false]], "tensorrt_llm::runtime::decoder_batch::request::embeddingbias (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13embeddingBiasE", false]], "tensorrt_llm::runtime::decoder_batch::request::endid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request5endIdE", false]], "tensorrt_llm::runtime::decoder_batch::request::generatedtokensperenginestep (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request28generatedTokensPerEngineStepE", false]], "tensorrt_llm::runtime::decoder_batch::request::ids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request3idsE", false]], "tensorrt_llm::runtime::decoder_batch::request::inputlen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request8inputLenE", false]], "tensorrt_llm::runtime::decoder_batch::request::lookaheadruntimeconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request22lookaheadRuntimeConfigE", false]], "tensorrt_llm::runtime::decoder_batch::request::maxnewtokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request12maxNewTokensE", false]], "tensorrt_llm::runtime::decoder_batch::request::medusapaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11medusaPathsE", false]], "tensorrt_llm::runtime::decoder_batch::request::medusatreeids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13medusaTreeIdsE", false]], "tensorrt_llm::runtime::decoder_batch::request::request (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14TensorConstPtr10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", false]], "tensorrt_llm::runtime::decoder_batch::request::stopwordslist (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13stopWordsListE", false]], "tensorrt_llm::runtime::decoder_batch::request::tensorconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request14TensorConstPtrE", false]], "tensorrt_llm::runtime::decoder_batch::request::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9TensorPtrE", false]], "tensorrt_llm::runtime::decodinginput (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInputE", false]], "tensorrt_llm::runtime::decodinginput::badwordslens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12badWordsLensE", false]], "tensorrt_llm::runtime::decodinginput::badwordslists (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13badWordsListsE", false]], "tensorrt_llm::runtime::decodinginput::badwordsptrs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12badWordsPtrsE", false]], "tensorrt_llm::runtime::decodinginput::batchsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9batchSizeE", false]], "tensorrt_llm::runtime::decodinginput::batchslots (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput10batchSlotsE", false]], "tensorrt_llm::runtime::decodinginput::beamwidths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput10beamWidthsE", false]], "tensorrt_llm::runtime::decodinginput::cacheindirection (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput16cacheIndirectionE", false]], "tensorrt_llm::runtime::decodinginput::decodinginput (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13DecodingInputEv", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11eagleInputsE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputsE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::acceptedlens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs12acceptedLensE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::acceptedpathids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs15acceptedPathIdsE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::acceptedtokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs14acceptedTokensE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::chunkedcontextnexttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs24chunkedContextNextTokensE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::lastdraftlens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs13lastDraftLensE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::lastdraftpaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs14lastDraftPathsE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::lastdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs15lastDraftTokensE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::nextdraftlens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs13nextDraftLensE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::nextdraftpaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs14nextDraftPathsE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::nextdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs15nextDraftTokensE", false]], "tensorrt_llm::runtime::decodinginput::eagleinputs::seqslots (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs8seqSlotsE", false]], "tensorrt_llm::runtime::decodinginput::embeddingbias (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13embeddingBiasE", false]], "tensorrt_llm::runtime::decodinginput::endids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput6endIdsE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputsE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25explicitDraftTokensInputsE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::bestpathindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15bestPathIndicesE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::bestpathlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15bestPathLengthsE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::lastdraftindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs16lastDraftIndicesE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::lastdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15lastDraftTokensE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::lastgenerationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs21lastGenerationLengthsE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::lastpositionidsbase (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs19lastPositionIdsBaseE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::masks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs5masksE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::maxgenlengthdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs18maxGenLengthDeviceE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::nextdraftindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs16nextDraftIndicesE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::nextdraftprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs14nextDraftProbsE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::nextdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15nextDraftTokensE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::nextflattokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs14nextFlatTokensE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::nextgenerationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs21nextGenerationLengthsE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::packedpositionids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs17packedPositionIdsE", false]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::seqslots (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs8seqSlotsE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputsE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25externalDraftTokensInputsE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::constantthreshold (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs17constantThresholdE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::draftlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs11draftLogitsE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::draftprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs10draftProbsE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::drafttokenids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs13draftTokenIdsE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::numdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs14numDraftTokensE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::numdrafttokenshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs18numDraftTokensHostE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::step (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs4stepE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::targetprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs11targetProbsE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::usedraftlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs14useDraftLogitsE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::usedraftlogitshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs18useDraftLogitsHostE", false]], "tensorrt_llm::runtime::decodinginput::externaldrafttokensinputs::userandomacceptancethreshold (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs28useRandomAcceptanceThresholdE", false]], "tensorrt_llm::runtime::decodinginput::finishreasons (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13finishReasonsE", false]], "tensorrt_llm::runtime::decodinginput::generationsteps (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15generationStepsE", false]], "tensorrt_llm::runtime::decodinginput::lengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput7lengthsE", false]], "tensorrt_llm::runtime::decodinginput::logitsvec (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9logitsVecE", false]], "tensorrt_llm::runtime::decodinginput::lookaheadinputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15lookaheadInputsE", false]], "tensorrt_llm::runtime::decodinginput::lookaheadinputs (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15LookaheadInputsE", false]], "tensorrt_llm::runtime::decodinginput::lookaheadinputs::tokensperstep (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15LookaheadInputs13tokensPerStepE", false]], "tensorrt_llm::runtime::decodinginput::maxattentionwindow (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput18maxAttentionWindowE", false]], "tensorrt_llm::runtime::decodinginput::maxbadwordslen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput14maxBadWordsLenE", false]], "tensorrt_llm::runtime::decodinginput::maxlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9maxLengthE", false]], "tensorrt_llm::runtime::decodinginput::maxstopwordslen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15maxStopWordsLenE", false]], "tensorrt_llm::runtime::decodinginput::medusainputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputsE", false]], "tensorrt_llm::runtime::decodinginput::medusainputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12medusaInputsE", false]], "tensorrt_llm::runtime::decodinginput::medusainputs::medusacurtokensperstep (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs22medusaCurTokensPerStepE", false]], "tensorrt_llm::runtime::decodinginput::medusainputs::medusalogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs12medusaLogitsE", false]], "tensorrt_llm::runtime::decodinginput::medusainputs::medusapaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs11medusaPathsE", false]], "tensorrt_llm::runtime::decodinginput::medusainputs::medusatargettokensperstep (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs25medusaTargetTokensPerStepE", false]], "tensorrt_llm::runtime::decodinginput::medusainputs::medusatreeids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs13medusaTreeIdsE", false]], "tensorrt_llm::runtime::decodinginput::norepeatngramsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput17noRepeatNgramSizeE", false]], "tensorrt_llm::runtime::decodinginput::sequencelimitlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput19sequenceLimitLengthE", false]], "tensorrt_llm::runtime::decodinginput::sinktokenlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15sinkTokenLengthE", false]], "tensorrt_llm::runtime::decodinginput::step (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput4stepE", false]], "tensorrt_llm::runtime::decodinginput::stopwordslens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13stopWordsLensE", false]], "tensorrt_llm::runtime::decodinginput::stopwordslists (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput14stopWordsListsE", false]], "tensorrt_llm::runtime::decodinginput::stopwordsptrs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13stopWordsPtrsE", false]], "tensorrt_llm::runtime::decodinginput::tensorconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput14TensorConstPtrE", false]], "tensorrt_llm::runtime::decodinginput::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE", false]], "tensorrt_llm::runtime::decodingoutput (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutputE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypothesesE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14beamHypothesesE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::batchdones (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses10batchDonesE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::cumlogprobscba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses14cumLogProbsCBAE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::empty (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5emptyERK13BufferManager", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::init (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses4initERK13BufferManager11TokenIdType", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::logprobscba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses11logProbsCBAE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::minnormedscorescba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses18minNormedScoresCBAE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::normedscorescba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses15normedScoresCBAE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::numbeamscba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses11numBeamsCBAE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::outputidscba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses12outputIdsCBAE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::release (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7releaseEv", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::reshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE10SizeType3210SizeType3210SizeType32", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::sequencelengthscba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses18sequenceLengthsCBAE", false]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::slice (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5sliceE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::decodingoutput::cacheindirection (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput16cacheIndirectionE", false]], "tensorrt_llm::runtime::decodingoutput::cumlogprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11cumLogProbsE", false]], "tensorrt_llm::runtime::decodingoutput::decodingoutput (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14DecodingOutputEv", false]], "tensorrt_llm::runtime::decodingoutput::eaglebuffers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput12eagleBuffersE", false]], "tensorrt_llm::runtime::decodingoutput::explicitdrafttokensbuffers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26explicitDraftTokensBuffersE", false]], "tensorrt_llm::runtime::decodingoutput::finishedsum (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11finishedSumE", false]], "tensorrt_llm::runtime::decodingoutput::finishreasons (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput13finishReasonsE", false]], "tensorrt_llm::runtime::decodingoutput::gatheredids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11gatheredIdsE", false]], "tensorrt_llm::runtime::decodingoutput::ids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput3idsE", false]], "tensorrt_llm::runtime::decodingoutput::knegativeinfinity (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput17kNegativeInfinityE", false]], "tensorrt_llm::runtime::decodingoutput::lengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput7lengthsE", false]], "tensorrt_llm::runtime::decodingoutput::logprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput8logProbsE", false]], "tensorrt_llm::runtime::decodingoutput::logprobstiled (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput13logProbsTiledE", false]], "tensorrt_llm::runtime::decodingoutput::lookaheadoutputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput16lookaheadOutputsE", false]], "tensorrt_llm::runtime::decodingoutput::newtokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9newTokensE", false]], "tensorrt_llm::runtime::decodingoutput::newtokenssteps (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14newTokensStepsE", false]], "tensorrt_llm::runtime::decodingoutput::newtokensvec (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput12newTokensVecE", false]], "tensorrt_llm::runtime::decodingoutput::parentids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9parentIdsE", false]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputsE", false]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26speculativeDecodingOutputsE", false]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::acceptedlengthscumsum (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs21acceptedLengthsCumSumE", false]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::acceptedtokenslen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs17acceptedTokensLenE", false]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::nextdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs15nextDraftTokensE", false]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::nextdrafttokenslen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs18nextDraftTokensLenE", false]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::pathsoffsets (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs12pathsOffsetsE", false]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::prevdrafttokenslen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs18prevDraftTokensLenE", false]], "tensorrt_llm::runtime::decodingoutput::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE", false]], "tensorrt_llm::runtime::deviceallocationnvls (c++ class)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime20DeviceAllocationNvlsE", false]], "tensorrt_llm::runtime::deviceallocationnvls::_capacity (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls9_capacityE", false]], "tensorrt_llm::runtime::deviceallocationnvls::_handle (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls7_handleE", false]], "tensorrt_llm::runtime::deviceallocationnvls::deviceallocationnvls (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls20DeviceAllocationNvlsEv", false]], "tensorrt_llm::runtime::deviceallocationnvls::free (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls4freeEv", false]], "tensorrt_llm::runtime::deviceallocationnvls::getcapacity (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime20DeviceAllocationNvls11getCapacityEv", false]], "tensorrt_llm::runtime::deviceallocationnvls::getipcunicastpointers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls21getIpcUnicastPointersEv", false]], "tensorrt_llm::runtime::deviceallocationnvls::getmulticastpointer (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime20DeviceAllocationNvls19getMulticastPointerEv", false]], "tensorrt_llm::runtime::deviceallocationnvls::getunicastpointer (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime20DeviceAllocationNvls17getUnicastPointerEv", false]], "tensorrt_llm::runtime::deviceallocationnvls::reset (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls5resetE6size_tNSt3setIiEE", false]], "tensorrt_llm::runtime::deviceallocationnvls::~deviceallocationnvls (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvlsD0Ev", false]], "tensorrt_llm::runtime::eaglebuffers (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffersE", false]], "tensorrt_llm::runtime::eaglebuffers::bufferptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers9BufferPtrE", false]], "tensorrt_llm::runtime::eaglebuffers::chunkedcontextnexttokenshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers28chunkedContextNextTokensHostE", false]], "tensorrt_llm::runtime::eaglebuffers::cumsumgenerationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers23cumSumGenerationLengthsE", false]], "tensorrt_llm::runtime::eaglebuffers::eaglebuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12EagleBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigE", false]], "tensorrt_llm::runtime::eaglebuffers::engineinputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12engineInputsE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputsE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13engineOutputsE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs::acceptedlens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs12acceptedLensE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs::acceptedpaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs13acceptedPathsE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs::acceptedtokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs14acceptedTokensE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs::chunkedcontextnexttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs24chunkedContextNextTokensE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs::nextdraftlens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs13nextDraftLensE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs::nextdraftpaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs14nextDraftPathsE", false]], "tensorrt_llm::runtime::eaglebuffers::engineoutputs::nextdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs15nextDraftTokensE", false]], "tensorrt_llm::runtime::eaglebuffers::greedysamplinghost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers18greedySamplingHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6InputsE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::alllayersdrafttokenids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs22allLayersDraftTokenIdsE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::alllayersdrafttokenidspredecessor (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs33allLayersDraftTokenIdsPredecessorE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::alllayersscores (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs15allLayersScoresE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::chunkedcontextnexttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs24chunkedContextNextTokensE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::create (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs6createE10SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfig", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::currentexpandindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs20currentExpandIndicesE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::draftlens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs9draftLensE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::draftpaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs10draftPathsE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::draftpathshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs14draftPathsHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::drafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs11draftTokensE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::dynamictreemaxtopkhost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs22dynamicTreeMaxTopKHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::eaglenetctxcontextlengthshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs29eagleNetCtxContextLengthsHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::eaglenetctxpastkeyvaluelengthshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs34eagleNetCtxPastKeyValueLengthsHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::eaglenetctxrequesttypeshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs27eagleNetCtxRequestTypesHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::eaglenetgencontextlengthshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs29eagleNetGenContextLengthsHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::eaglenetgenpastkeyvaluelengthshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs34eagleNetGenPastKeyValueLengthsHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::eaglenetgenrequesttypeshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs27eagleNetGenRequestTypesHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::inputgentokenshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs18inputGenTokensHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::posterioralpha (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs14posteriorAlphaE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::posteriorthreshold (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs18posteriorThresholdE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::prevscores (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs10prevScoresE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::randomdatasample (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs16randomDataSampleE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::randomdatavalidation (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs20randomDataValidationE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::specdecodinggenerationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs29specDecodingGenerationLengthsE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::specdecodinggenerationlengthshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs33specDecodingGenerationLengthsHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::specdecodingpackedmasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs23specDecodingPackedMasksE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::specdecodingpositionoffsets (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs27specDecodingPositionOffsetsE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::temperatures (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs12temperaturesE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::usedynamictreehost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs18useDynamicTreeHostE", false]], "tensorrt_llm::runtime::eaglebuffers::inputs::usespecdecoding (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs15useSpecDecodingE", false]], "tensorrt_llm::runtime::eaglebuffers::insertinputtensors (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", false]], "tensorrt_llm::runtime::eaglebuffers::itensor (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers7ITensorE", false]], "tensorrt_llm::runtime::eaglebuffers::llmrequestptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13LlmRequestPtrE", false]], "tensorrt_llm::runtime::eaglebuffers::maxgenerationlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers19maxGenerationLengthE", false]], "tensorrt_llm::runtime::eaglebuffers::mdefaultposteriorthreshold (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers26mDefaultPosteriorThresholdE", false]], "tensorrt_llm::runtime::eaglebuffers::mdogreedysampling (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers17mDoGreedySamplingE", false]], "tensorrt_llm::runtime::eaglebuffers::posterioralphahost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers18posteriorAlphaHostE", false]], "tensorrt_llm::runtime::eaglebuffers::posteriorthresholdhost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers22posteriorThresholdHostE", false]], "tensorrt_llm::runtime::eaglebuffers::requestvector (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13RequestVectorE", false]], "tensorrt_llm::runtime::eaglebuffers::reshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", false]], "tensorrt_llm::runtime::eaglebuffers::scanreducetempstorage (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers21scanReduceTempStorageE", false]], "tensorrt_llm::runtime::eaglebuffers::scanreducetempstoragebytes (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers26scanReduceTempStorageBytesE", false]], "tensorrt_llm::runtime::eaglebuffers::setfrominputs (c++ function)": [[1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", false], [1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", false]], "tensorrt_llm::runtime::eaglebuffers::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers10SizeType32E", false]], "tensorrt_llm::runtime::eaglebuffers::tensormap (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers9TensorMapE", false]], "tensorrt_llm::runtime::eaglebuffers::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers9TensorPtrE", false]], "tensorrt_llm::runtime::eaglemodule (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime11EagleModuleE", false]], "tensorrt_llm::runtime::eaglemodule::eaglemodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11EagleModule11EagleModuleE10SizeType3210SizeType3210SizeType3210SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime11EagleModule11EagleModuleEv", false]], "tensorrt_llm::runtime::eaglemodule::getdefaulteaglechoices (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11EagleModule22getDefaultEagleChoicesEv", false]], "tensorrt_llm::runtime::eaglemodule::getmaxnonleafnodesperlayer (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11EagleModule26getMaxNonLeafNodesPerLayerEv", false]], "tensorrt_llm::runtime::eaglemodule::getnumtransformerlayers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11EagleModule23getNumTransformerLayersEv", false]], "tensorrt_llm::runtime::eaglemodule::mdefaulteaglechoices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11EagleModule20mDefaultEagleChoicesE", false]], "tensorrt_llm::runtime::eaglemodule::mmaxnonleafnodesperlayer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11EagleModule24mMaxNonLeafNodesPerLayerE", false]], "tensorrt_llm::runtime::eaglemodule::mnumtransformerslayer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11EagleModule21mNumTransformersLayerE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffersE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::bufferptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers9BufferPtrE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::cumsumgenerationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers23cumSumGenerationLengthsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineinputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineinputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12engineInputsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineinputs::positionoffsets (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputs15positionOffsetsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineinputs::requesttypesdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputs18requestTypesDeviceE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13engineOutputsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::bestpathindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15bestPathIndicesE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::bestpathlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15bestPathLengthsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::masks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs5masksE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::maxgentoken (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs11maxGenTokenE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextdraftindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs16nextDraftIndicesE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextdraftprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs14nextDraftProbsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15nextDraftTokensE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextflattokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs14nextFlatTokensE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextgenerationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs21nextGenerationLengthsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextpositionoffsets (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs19nextPositionOffsetsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::packedpositionids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs17packedPositionIdsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::totalgentoken (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs13totalGenTokenE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::explicitdrafttokensbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6InputsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::create (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::draftindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs12draftIndicesE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::draftprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs10draftProbsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::drafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11draftTokensE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::generationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs17generationLengthsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::generationlengthshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs21generationLengthsHostE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::maxgenlengthhost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs16maxGenLengthHostE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::packedmasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11packedMasksE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::positionids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11positionIdsE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::positionidsbase (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs15positionIdsBaseE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::randomdatasample (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs16randomDataSampleE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::randomdatavalidation (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs20randomDataValidationE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::temperatures (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs12temperaturesE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::usespecdecoding (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs15useSpecDecodingE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::insertinputtensors (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::itensor (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7ITensorE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::reshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::scantempstorage (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers15scanTempStorageE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::scantempstoragebytes (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers20scanTempStorageBytesE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::setfrominputs (c++ function)": [[1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", false], [1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers10SizeType32E", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::tensormap (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers9TensorMapE", false]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers9TensorPtrE", false]], "tensorrt_llm::runtime::genericprompttuningparams (c++ class)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime25GenericPromptTuningParamsE", false]], "tensorrt_llm::runtime::genericprompttuningparams::embeddingtable (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams14embeddingTableE", false]], "tensorrt_llm::runtime::genericprompttuningparams::genericprompttuningparams (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", false]], "tensorrt_llm::runtime::genericprompttuningparams::prompttuningenabled (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams19promptTuningEnabledE", false]], "tensorrt_llm::runtime::genericprompttuningparams::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams10SizeType32E", false]], "tensorrt_llm::runtime::genericprompttuningparams::tasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams5tasksE", false]], "tensorrt_llm::runtime::genericprompttuningparams::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE", false]], "tensorrt_llm::runtime::genericprompttuningparams::vocabsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9vocabSizeE", false]], "tensorrt_llm::runtime::getdefaultbatchslots (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20getDefaultBatchSlotsEN7runtime10SizeType32E", false]], "tensorrt_llm::runtime::gptdecoder (c++ class)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime10GptDecoderE", false]], "tensorrt_llm::runtime::gptdecoder::cudastreamptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13CudaStreamPtrE", false]], "tensorrt_llm::runtime::gptdecoder::disablelookahead (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", false]], "tensorrt_llm::runtime::gptdecoder::forwardasync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", false]], "tensorrt_llm::runtime::gptdecoder::forwardsync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", false]], "tensorrt_llm::runtime::gptdecoder::getsamplingconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder17getSamplingConfigEv", false]], "tensorrt_llm::runtime::gptdecoder::gptdecoder (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", false]], "tensorrt_llm::runtime::gptdecoder::mdecodinglayerworkspace (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder23mDecodingLayerWorkspaceE", false]], "tensorrt_llm::runtime::gptdecoder::mdecodingmode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13mDecodingModeE", false]], "tensorrt_llm::runtime::gptdecoder::mdynamicdecodelayer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder19mDynamicDecodeLayerE", false]], "tensorrt_llm::runtime::gptdecoder::mmanager (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder8mManagerE", false]], "tensorrt_llm::runtime::gptdecoder::mmaxbatchsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13mMaxBatchSizeE", false]], "tensorrt_llm::runtime::gptdecoder::msamplingconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder15mSamplingConfigE", false]], "tensorrt_llm::runtime::gptdecoder::mvocabsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10mVocabSizeE", false]], "tensorrt_llm::runtime::gptdecoder::mvocabsizepadded (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder16mVocabSizePaddedE", false]], "tensorrt_llm::runtime::gptdecoder::setup (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", false]], "tensorrt_llm::runtime::gptdecoder::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder9TensorPtrE", false]], "tensorrt_llm::runtime::gptdecoderbatched (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatchedE", false]], "tensorrt_llm::runtime::gptdecoderbatched::cudastreamptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13CudaStreamPtrE", false]], "tensorrt_llm::runtime::gptdecoderbatched::disablelookahead (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16disableLookaheadERK13RequestVectorRK9TensorPtr", false]], "tensorrt_llm::runtime::gptdecoderbatched::finalize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", false]], "tensorrt_llm::runtime::gptdecoderbatched::forward (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched7forwardERKN7decoder12DecoderStateERKN13decoder_batch5InputE", false]], "tensorrt_llm::runtime::gptdecoderbatched::forwardasync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12forwardAsyncERKN7decoder12DecoderStateERKN13decoder_batch5InputE", false]], "tensorrt_llm::runtime::gptdecoderbatched::forwarddispatch (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15forwardDispatchERKN7decoder12DecoderStateERKN13decoder_batch5InputE", false]], "tensorrt_llm::runtime::gptdecoderbatched::getbuffermanager (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched16getBufferManagerEv", false]], "tensorrt_llm::runtime::gptdecoderbatched::getdecoderstream (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched16getDecoderStreamEv", false]], "tensorrt_llm::runtime::gptdecoderbatched::getunderlyingdecoder (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched20getUnderlyingDecoderEv", false]], "tensorrt_llm::runtime::gptdecoderbatched::gptdecoderbatched (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched17GptDecoderBatchedE13CudaStreamPtr", false]], "tensorrt_llm::runtime::gptdecoderbatched::gptdecoderptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13GptDecoderPtrE", false]], "tensorrt_llm::runtime::gptdecoderbatched::llmrequestptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13LlmRequestPtrE", false]], "tensorrt_llm::runtime::gptdecoderbatched::mbuffermanager (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mBufferManagerE", false]], "tensorrt_llm::runtime::gptdecoderbatched::mdecoder (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched8mDecoderE", false]], "tensorrt_llm::runtime::gptdecoderbatched::mdecoderstream (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mDecoderStreamE", false]], "tensorrt_llm::runtime::gptdecoderbatched::mruntimestream (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mRuntimeStreamE", false]], "tensorrt_llm::runtime::gptdecoderbatched::requestvector (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13RequestVectorE", false]], "tensorrt_llm::runtime::gptdecoderbatched::setup (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", false]], "tensorrt_llm::runtime::gptdecoderbatched::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched9TensorPtrE", false]], "tensorrt_llm::runtime::gptjsonconfig (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfigE", false]], "tensorrt_llm::runtime::gptjsonconfig::enginefilename (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfig", false], [1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfigRKNSt6stringE", false]], "tensorrt_llm::runtime::gptjsonconfig::getcontextparallelism (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig21getContextParallelismEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getgpuspernode (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14getGpusPerNodeEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getmodelconfig (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14getModelConfigEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getmodelconfigmutable (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig21getModelConfigMutableEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getname (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig7getNameEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getpipelineparallelism (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig22getPipelineParallelismEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getprecision (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getPrecisionEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getruntimedefaults (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig18getRuntimeDefaultsEv", false]], "tensorrt_llm::runtime::gptjsonconfig::gettensorparallelism (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig20getTensorParallelismEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getversion (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig10getVersionEv", false]], "tensorrt_llm::runtime::gptjsonconfig::getworldsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getWorldSizeEv", false]], "tensorrt_llm::runtime::gptjsonconfig::gptjsonconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", false]], "tensorrt_llm::runtime::gptjsonconfig::mcontextparallelism (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig19mContextParallelismE", false]], "tensorrt_llm::runtime::gptjsonconfig::mgpuspernode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig12mGpusPerNodeE", false]], "tensorrt_llm::runtime::gptjsonconfig::mmodelconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig12mModelConfigE", false]], "tensorrt_llm::runtime::gptjsonconfig::mname (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5mNameE", false]], "tensorrt_llm::runtime::gptjsonconfig::mpipelineparallelism (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig20mPipelineParallelismE", false]], "tensorrt_llm::runtime::gptjsonconfig::mprecision (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig10mPrecisionE", false]], "tensorrt_llm::runtime::gptjsonconfig::mruntimedefaults (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig16mRuntimeDefaultsE", false]], "tensorrt_llm::runtime::gptjsonconfig::mtensorparallelism (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig18mTensorParallelismE", false]], "tensorrt_llm::runtime::gptjsonconfig::mversion (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig8mVersionE", false]], "tensorrt_llm::runtime::gptjsonconfig::parse (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt10filesystem4pathE", false], [1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt6stringE", false], [1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERNSt7istreamE", false]], "tensorrt_llm::runtime::ibuffer (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBufferE", false]], "tensorrt_llm::runtime::ibuffer::data (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE", false], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4dataEv", false], [1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE", false], [1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataEv", false]], "tensorrt_llm::runtime::ibuffer::datatype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer8DataTypeE", false]], "tensorrt_llm::runtime::ibuffer::getcapacity (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer11getCapacityEv", false]], "tensorrt_llm::runtime::ibuffer::getdatatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer11getDataTypeEv", false]], "tensorrt_llm::runtime::ibuffer::getdatatypename (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer15getDataTypeNameE8DataType", false], [1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer15getDataTypeNameEv", false]], "tensorrt_llm::runtime::ibuffer::getmemorytype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer13getMemoryTypeEv", false]], "tensorrt_llm::runtime::ibuffer::getmemorytypename (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer17getMemoryTypeNameEv", false]], "tensorrt_llm::runtime::ibuffer::getsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer7getSizeEv", false]], "tensorrt_llm::runtime::ibuffer::getsizeinbytes (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer14getSizeInBytesEv", false]], "tensorrt_llm::runtime::ibuffer::ibuffer (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferERK7IBuffer", false], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferEv", false]], "tensorrt_llm::runtime::ibuffer::memorytype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer10memoryTypeEPKv", false]], "tensorrt_llm::runtime::ibuffer::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBufferaSERK7IBuffer", false]], "tensorrt_llm::runtime::ibuffer::release (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer7releaseEv", false]], "tensorrt_llm::runtime::ibuffer::resize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer6resizeENSt6size_tE", false]], "tensorrt_llm::runtime::ibuffer::sharedconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer14SharedConstPtrE", false]], "tensorrt_llm::runtime::ibuffer::sharedptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer9SharedPtrE", false]], "tensorrt_llm::runtime::ibuffer::slice (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", false], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", false], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tE", false], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE", false]], "tensorrt_llm::runtime::ibuffer::tobytes (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer7toBytesENSt6size_tE", false]], "tensorrt_llm::runtime::ibuffer::uniqueconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer14UniqueConstPtrE", false]], "tensorrt_llm::runtime::ibuffer::uniqueptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE", false]], "tensorrt_llm::runtime::ibuffer::view (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE", false], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtr", false], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtrNSt6size_tE", false]], "tensorrt_llm::runtime::ibuffer::wrap (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrRNSt6vectorI1TEE", false], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE", false], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE", false]], "tensorrt_llm::runtime::ibuffer::~ibuffer (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBufferD0Ev", false]], "tensorrt_llm::runtime::igptdecoder (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoderE", false]], "tensorrt_llm::runtime::igptdecoder::create (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", false]], "tensorrt_llm::runtime::igptdecoder::disablelookahead (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", false]], "tensorrt_llm::runtime::igptdecoder::forwardasync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", false]], "tensorrt_llm::runtime::igptdecoder::forwardsync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", false]], "tensorrt_llm::runtime::igptdecoder::getsamplingconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder17getSamplingConfigEv", false]], "tensorrt_llm::runtime::igptdecoder::setup (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", false]], "tensorrt_llm::runtime::igptdecoder::tensorconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder14TensorConstPtrE", false]], "tensorrt_llm::runtime::igptdecoder::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder9TensorPtrE", false]], "tensorrt_llm::runtime::igptdecoder::~igptdecoder (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoderD0Ev", false]], "tensorrt_llm::runtime::igptdecoderbatched (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatchedE", false]], "tensorrt_llm::runtime::igptdecoderbatched::cudastreamptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched13CudaStreamPtrE", false]], "tensorrt_llm::runtime::igptdecoderbatched::disablelookahead (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched16disableLookaheadERK13RequestVectorRK9TensorPtr", false]], "tensorrt_llm::runtime::igptdecoderbatched::finalize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", false]], "tensorrt_llm::runtime::igptdecoderbatched::forward (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched7forwardERKN7decoder12DecoderStateERKN13decoder_batch5InputE", false]], "tensorrt_llm::runtime::igptdecoderbatched::forwardasync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched12forwardAsyncERKN7decoder12DecoderStateERKN13decoder_batch5InputE", false]], "tensorrt_llm::runtime::igptdecoderbatched::igptdecoderbatched (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched18IGptDecoderBatchedEv", false]], "tensorrt_llm::runtime::igptdecoderbatched::llmrequestptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched13LlmRequestPtrE", false]], "tensorrt_llm::runtime::igptdecoderbatched::requestvector (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched13RequestVectorE", false]], "tensorrt_llm::runtime::igptdecoderbatched::setup (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", false]], "tensorrt_llm::runtime::igptdecoderbatched::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched9TensorPtrE", false]], "tensorrt_llm::runtime::igptdecoderbatched::~igptdecoderbatched (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatchedD0Ev", false]], "tensorrt_llm::runtime::ipcmemory (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryE", false]], "tensorrt_llm::runtime::ipcmemory::allocateipcmemory (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfig", false]], "tensorrt_llm::runtime::ipcmemory::bufferptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9BufferPtrE", false]], "tensorrt_llm::runtime::ipcmemory::destroyipcmemory (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory16destroyIpcMemoryEv", false]], "tensorrt_llm::runtime::ipcmemory::flags_size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory10FLAGS_SIZEE", false]], "tensorrt_llm::runtime::ipcmemory::getcommptrs (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9IpcMemory11getCommPtrsEv", false]], "tensorrt_llm::runtime::ipcmemory::ipcmemory (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb", false], [1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryERK9IpcMemory", false], [1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryERR9IpcMemory", false]], "tensorrt_llm::runtime::ipcmemory::mbuffer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory7mBufferE", false]], "tensorrt_llm::runtime::ipcmemory::mcommptrs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9mCommPtrsE", false]], "tensorrt_llm::runtime::ipcmemory::mopenipc (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory8mOpenIpcE", false]], "tensorrt_llm::runtime::ipcmemory::mtprank (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory7mTpRankE", false]], "tensorrt_llm::runtime::ipcmemory::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryaSERK9IpcMemory", false], [1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryaSERR9IpcMemory", false]], "tensorrt_llm::runtime::ipcmemory::~ipcmemory (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryD0Ev", false]], "tensorrt_llm::runtime::ipcnvlsallocate (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime15ipcNvlsAllocateE6size_tNSt3setIiEE", false]], "tensorrt_llm::runtime::ipcnvlsfree (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ipcNvlsFreeEP13IpcNvlsHandle", false]], "tensorrt_llm::runtime::ipcnvlshandle (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandleE", false]], "tensorrt_llm::runtime::ipcnvlshandle::ipc_uc_handles (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle14ipc_uc_handlesE", false]], "tensorrt_llm::runtime::ipcnvlshandle::ipc_uc_ptrs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle11ipc_uc_ptrsE", false]], "tensorrt_llm::runtime::ipcnvlshandle::ipc_uc_vas (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle10ipc_uc_vasE", false]], "tensorrt_llm::runtime::ipcnvlshandle::mc_handle (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle9mc_handleE", false]], "tensorrt_llm::runtime::ipcnvlshandle::mc_ptr (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle6mc_ptrE", false]], "tensorrt_llm::runtime::ipcnvlshandle::mc_va (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle5mc_vaE", false]], "tensorrt_llm::runtime::ipcnvlshandle::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle4sizeE", false]], "tensorrt_llm::runtime::ipcnvlshandle::uc_handle (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle9uc_handleE", false]], "tensorrt_llm::runtime::ipcnvlshandle::uc_ptr (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle6uc_ptrE", false]], "tensorrt_llm::runtime::ipcnvlshandle::uc_va (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle5uc_vaE", false]], "tensorrt_llm::runtime::ipcnvlssupported (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime16ipcNvlsSupportedEv", false]], "tensorrt_llm::runtime::itensor (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensorE", false]], "tensorrt_llm::runtime::itensor::at (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atE14UniqueConstPtrRR9TConstPtrRK5Shape", false], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atEN7ITensor14UniqueConstPtrERR9TConstPtrRKNSt16initializer_listI9DimType64EE", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRK5Shape", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRKNSt16initializer_listI9DimType64EE", false]], "tensorrt_llm::runtime::itensor::castsize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor8castSizeE6size_t", false]], "tensorrt_llm::runtime::itensor::dimtype64 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9DimType64E", false]], "tensorrt_llm::runtime::itensor::flattenn (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor8flattenNE9SharedPtrNSt7int64_tE", false]], "tensorrt_llm::runtime::itensor::getdimension (c++ function)": [[1, "_CPPv4I_10SizeType32ENK12tensorrt_llm7runtime7ITensor12getDimensionE9DimType64v", false]], "tensorrt_llm::runtime::itensor::getshape (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7ITensor8getShapeEv", false]], "tensorrt_llm::runtime::itensor::itensor (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorERK7ITensor", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorEv", false]], "tensorrt_llm::runtime::itensor::makeshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9makeShapeERKNSt16initializer_listI9DimType64EE", false]], "tensorrt_llm::runtime::itensor::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensoraSERK7ITensor", false]], "tensorrt_llm::runtime::itensor::reshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor7reshapeERK5Shape", false]], "tensorrt_llm::runtime::itensor::resize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor6resizeENSt6size_tE", false]], "tensorrt_llm::runtime::itensor::shape (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE", false]], "tensorrt_llm::runtime::itensor::shapeequals (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T10SizeType32", false], [1, "_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T10SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapeRK5Shape", false], [1, "_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERK5Shape", false], [1, "_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERKNSt16initializer_listI10SizeType32EE", false]], "tensorrt_llm::runtime::itensor::sharedconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor14SharedConstPtrE", false]], "tensorrt_llm::runtime::itensor::sharedptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE", false]], "tensorrt_llm::runtime::itensor::slice (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", false], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", false], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5Shape", false], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5ShapeNSt6size_tE", false], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EE", false], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EENSt6size_tE", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tE", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape9DimType64", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE9DimType64", false]], "tensorrt_llm::runtime::itensor::squeeze (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeE10SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeERK5Shape10SizeType32", false]], "tensorrt_llm::runtime::itensor::strides (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor7stridesERK5Shape", false]], "tensorrt_llm::runtime::itensor::tensormap (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9TensorMapE", false]], "tensorrt_llm::runtime::itensor::tostring (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor8toStringERK5Shape", false]], "tensorrt_llm::runtime::itensor::uniqueconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor14UniqueConstPtrE", false]], "tensorrt_llm::runtime::itensor::uniqueptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE", false]], "tensorrt_llm::runtime::itensor::unsqueeze (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeE10SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeERK5Shape10SizeType32", false]], "tensorrt_llm::runtime::itensor::view (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewE9SharedPtr", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewEN7IBuffer9SharedPtrERK5Shape", false]], "tensorrt_llm::runtime::itensor::volume (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor6volumeERK5Shape", false]], "tensorrt_llm::runtime::itensor::volumenonnegative (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor17volumeNonNegativeERK5Shape", false]], "tensorrt_llm::runtime::itensor::wrap (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE", false], [1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape", false], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE", false]], "tensorrt_llm::runtime::itensor::~itensor (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensorD0Ev", false]], "tensorrt_llm::runtime::lamportinitializeall (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20lamportInitializeAllEPvPvPv6size_t", false]], "tensorrt_llm::runtime::lookaheaddecodingbuffers (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffersE", false]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::generationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers17generationLengthsE", false]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::lookaheaddecodingbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers24LookaheadDecodingBuffersE10SizeType3210SizeType32RK13BufferManager", false]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::packedmasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers11packedMasksE", false]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::positionids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers11positionIdsE", false]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::positionoffsets (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers15positionOffsetsE", false]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers9TensorPtrE", false]], "tensorrt_llm::runtime::lookaheadmodule (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModuleE", false]], "tensorrt_llm::runtime::lookaheadmodule::getexecutionconfig (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime15LookaheadModule18getExecutionConfigEv", false]], "tensorrt_llm::runtime::lookaheadmodule::lookaheadmodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleE10SizeType3210SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleEv", false]], "tensorrt_llm::runtime::lookaheadmodule::mexecutionconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule16mExecutionConfigE", false]], "tensorrt_llm::runtime::lookaheadmodule::setexecutionconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule18setExecutionConfigERKN8executor23LookaheadDecodingConfigE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffersE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::batchslotshostcopy (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers18batchSlotsHostCopyE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::cumsumlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers12cumSumLengthE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::disablelookaheaddecoding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers24disableLookaheadDecodingEv", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::enablelookaheaddecoding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23enableLookaheadDecodingE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::generationlengthsdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23generationLengthsDeviceE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::generationlengthshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers21generationLengthsHostE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::generationlengthshostcopy (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers25generationLengthsHostCopyE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::insertinputtensors (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers18insertInputTensorsER9TensorMapR9TensorMapRK11WorldConfig", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::lookaheadruntimebuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::packedmaskhost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers14packedMaskHostE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::packedmaskhostcopy (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers18packedMaskHostCopyE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::packedmasksdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers17packedMasksDeviceE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionidsdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers17positionIdsDeviceE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionidshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers15positionIdsHostE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionidshostcopy (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers19positionIdsHostCopyE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionoffsetsdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers21positionOffsetsDeviceE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionoffsetshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers19positionOffsetsHostE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionoffsetshostcopy (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23positionOffsetsHostCopyE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::reshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers7reshapeE10SizeType3210SizeType3210SizeType32", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::setfrominputs (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::tensormap (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers9TensorMapE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers9TensorPtrE", false]], "tensorrt_llm::runtime::lookaheadruntimebuffers::usespecdecoding (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers15useSpecDecodingE", false]], "tensorrt_llm::runtime::loracache (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCacheE", false]], "tensorrt_llm::runtime::loracache::bump (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache4bumpE10TaskIdType", false]], "tensorrt_llm::runtime::loracache::bumptaskinprogress (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache18bumpTaskInProgressE10TaskIdType", false]], "tensorrt_llm::runtime::loracache::claimpageswithevict (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache19claimPagesWithEvictE10SizeType32", false]], "tensorrt_llm::runtime::loracache::copytask (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache8copyTaskE10TaskIdTypeR9LoraCacheb", false]], "tensorrt_llm::runtime::loracache::copytaskmappages (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache", false]], "tensorrt_llm::runtime::loracache::copytopages (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", false]], "tensorrt_llm::runtime::loracache::determinenumpages (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE10TaskIdType", false], [1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE9TensorPtr", false]], "tensorrt_llm::runtime::loracache::fits (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache4fitsE9TensorPtr", false]], "tensorrt_llm::runtime::loracache::get (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3getE10TaskIdType", false]], "tensorrt_llm::runtime::loracache::getnumpages (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache11getNumPagesEv", false]], "tensorrt_llm::runtime::loracache::getpageptr (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache10getPagePtrE6size_t", false]], "tensorrt_llm::runtime::loracache::getstatus (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache9getStatusE10TaskIdType", false]], "tensorrt_llm::runtime::loracache::has (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache3hasE10TaskIdType", false]], "tensorrt_llm::runtime::loracache::isdone (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache6isDoneE10TaskIdType", false]], "tensorrt_llm::runtime::loracache::isloaded (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache8isLoadedE10TaskIdType", false]], "tensorrt_llm::runtime::loracache::loadweights (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsE10TaskIdType9TensorPtr9TensorPtr", false], [1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsER9TaskValue9TensorPtr9TensorPtr", false]], "tensorrt_llm::runtime::loracache::loracache (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager", false]], "tensorrt_llm::runtime::loracache::markalldone (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11markAllDoneEv", false]], "tensorrt_llm::runtime::loracache::marktaskdone (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12markTaskDoneE10TaskIdType", false]], "tensorrt_llm::runtime::loracache::mbuffermanager (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache14mBufferManagerE", false]], "tensorrt_llm::runtime::loracache::mcachemap (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9mCacheMapE", false]], "tensorrt_llm::runtime::loracache::mcachemutex (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11mCacheMutexE", false]], "tensorrt_llm::runtime::loracache::mcachepagemanager (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17mCachePageManagerE", false]], "tensorrt_llm::runtime::loracache::mdevicebuffermanagers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21mDeviceBufferManagersE", false]], "tensorrt_llm::runtime::loracache::mdonetasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache10mDoneTasksE", false]], "tensorrt_llm::runtime::loracache::minprogresstasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16mInProgressTasksE", false]], "tensorrt_llm::runtime::loracache::mmodelconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12mModelConfigE", false]], "tensorrt_llm::runtime::loracache::mmoduleidtomodule (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17mModuleIdToModuleE", false]], "tensorrt_llm::runtime::loracache::mpagemanagerconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache18mPageManagerConfigE", false]], "tensorrt_llm::runtime::loracache::mpagesmutex (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11mPagesMutexE", false]], "tensorrt_llm::runtime::loracache::mworldconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12mWorldConfigE", false]], "tensorrt_llm::runtime::loracache::put (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb", false]], "tensorrt_llm::runtime::loracache::splittransposecpu (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loracache::splittransposecpuinner (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loracache::taskidtype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache10TaskIdTypeE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfigE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::adaptersize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig11adapterSizeE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::insize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig6inSizeE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::layerid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7layerIdE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::moduleid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8moduleIdE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::numslots (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8numSlotsE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::operator== (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfigeqERKN9LoraCache21TaskLayerModuleConfigE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::outsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7outSizeE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::pageid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig6pageIdE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::scalingvecpointer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig17scalingVecPointerE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::slotidx (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7slotIdxE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::tostring (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8toStringEv", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::weightsinpointer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig16weightsInPointerE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::weightsoutpointer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig17weightsOutPointerE", false]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfiglistptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache28TaskLayerModuleConfigListPtrE", false]], "tensorrt_llm::runtime::loracache::taskvalue (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueE", false]], "tensorrt_llm::runtime::loracache::taskvalue::configs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue7configsE", false]], "tensorrt_llm::runtime::loracache::taskvalue::done (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue4doneE", false]], "tensorrt_llm::runtime::loracache::taskvalue::inprogress (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue10inProgressE", false]], "tensorrt_llm::runtime::loracache::taskvalue::it (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue2itE", false]], "tensorrt_llm::runtime::loracache::taskvalue::loaded (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue6loadedE", false]], "tensorrt_llm::runtime::loracache::taskvalue::loadinprogress (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue14loadInProgressE", false]], "tensorrt_llm::runtime::loracache::taskvalue::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueaSERR9TaskValue", false]], "tensorrt_llm::runtime::loracache::taskvalue::pageids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue7pageIdsE", false]], "tensorrt_llm::runtime::loracache::taskvalue::taskvalue (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", false], [1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERR9TaskValue", false], [1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueEv", false]], "tensorrt_llm::runtime::loracache::taskvalue::~taskvalue (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueD0Ev", false]], "tensorrt_llm::runtime::loracache::taskvalueptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12TaskValuePtrE", false]], "tensorrt_llm::runtime::loracache::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TensorPtrE", false]], "tensorrt_llm::runtime::loracache::valuestatus (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatusE", false]], "tensorrt_llm::runtime::loracache::valuestatus::kvalue_status_loaded (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus20kVALUE_STATUS_LOADEDE", false]], "tensorrt_llm::runtime::loracache::valuestatus::kvalue_status_missing (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus21kVALUE_STATUS_MISSINGE", false]], "tensorrt_llm::runtime::loracache::valuestatus::kvalue_status_processing (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus24kVALUE_STATUS_PROCESSINGE", false]], "tensorrt_llm::runtime::loracachefullexception (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullExceptionE", false]], "tensorrt_llm::runtime::loracachefullexception::loracachefullexception (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullException22LoraCacheFullExceptionERKNSt6stringE", false]], "tensorrt_llm::runtime::loracachefullexception::~loracachefullexception (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullExceptionD0Ev", false]], "tensorrt_llm::runtime::loracachepagemanager (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManagerE", false]], "tensorrt_llm::runtime::loracachepagemanager::blockptr (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager8blockPtrE10SizeType32", false]], "tensorrt_llm::runtime::loracachepagemanager::claimpages (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10claimPagesE10SizeType32", false]], "tensorrt_llm::runtime::loracachepagemanager::initialize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10initializeERK13BufferManager", false]], "tensorrt_llm::runtime::loracachepagemanager::loracachepagemanager (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager20LoraCachePageManagerERK26LoraCachePageManagerConfigRK13BufferManager", false]], "tensorrt_llm::runtime::loracachepagemanager::mconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager7mConfigE", false]], "tensorrt_llm::runtime::loracachepagemanager::mfreepageids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager12mFreePageIdsE", false]], "tensorrt_llm::runtime::loracachepagemanager::mispagefree (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager11mIsPageFreeE", false]], "tensorrt_llm::runtime::loracachepagemanager::mpageblocks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager11mPageBlocksE", false]], "tensorrt_llm::runtime::loracachepagemanager::mutablepageptr (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager14mutablePagePtrENSt6size_tE", false]], "tensorrt_llm::runtime::loracachepagemanager::numavailablepages (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager17numAvailablePagesEv", false]], "tensorrt_llm::runtime::loracachepagemanager::pageptr (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager7pagePtrENSt6size_tE", false]], "tensorrt_llm::runtime::loracachepagemanager::releasepages (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager12releasePagesERKNSt6vectorINSt6size_tEEE", false]], "tensorrt_llm::runtime::loracachepagemanager::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager9TensorPtrE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfigE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getdatatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig11getDataTypeEv", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getinittozero (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig13getInitToZeroEv", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getmaxpagesperblock (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig19getMaxPagesPerBlockEv", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getmemorytype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig13getMemoryTypeEv", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getnumcopystreams (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig17getNumCopyStreamsEv", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getpagewidth (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig12getPageWidthEv", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getslotsperpage (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig15getSlotsPerPageEv", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::gettotalnumpages (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig16getTotalNumPagesEv", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::loracachepagemanagerconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mdatatype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig9mDataTypeE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::minittozero (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11mInitToZeroE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mmaxpagesperblock (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig17mMaxPagesPerBlockE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mmemorytype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11mMemoryTypeE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mnumcopystreams (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15mNumCopyStreamsE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mpagewidth (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig10mPageWidthE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mslotsperpage (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13mSlotsPerPageE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mtotalnumpages (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig14mTotalNumPagesE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setdatatype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11setDataTypeERKN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setinittozero (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setInitToZeroEb", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setmaxpagesperblock (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig19setMaxPagesPerBlockERK10SizeType32", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setmemorytype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setMemoryTypeERKN7runtime10MemoryTypeE", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setnumcopystreams (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig17setNumCopyStreamsE10SizeType32", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setpagewidth (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig12setPageWidthERK10SizeType32", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setslotsperpage (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setSlotsPerPageERK10SizeType32", false]], "tensorrt_llm::runtime::loracachepagemanagerconfig::settotalnumpage (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setTotalNumPageERK10SizeType32", false]], "tensorrt_llm::runtime::loraexpectedexception (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedExceptionE", false]], "tensorrt_llm::runtime::loraexpectedexception::loraexpectedexception (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedException21LoraExpectedExceptionERKNSt6stringE", false]], "tensorrt_llm::runtime::loraexpectedexception::~loraexpectedexception (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedExceptionD0Ev", false]], "tensorrt_llm::runtime::loramodule (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModuleE", false]], "tensorrt_llm::runtime::loramodule::createloramodules (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loramodule::flattenedinoutsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18flattenedInOutSizeE10SizeType32b", false]], "tensorrt_llm::runtime::loramodule::indim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule5inDimEv", false]], "tensorrt_llm::runtime::loramodule::indimfirst (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule10inDimFirstEv", false]], "tensorrt_llm::runtime::loramodule::insize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule6inSizeE10SizeType32", false]], "tensorrt_llm::runtime::loramodule::intpsplitdim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12inTpSplitDimEv", false]], "tensorrt_llm::runtime::loramodule::localinadaptersize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18localInAdapterSizeE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loramodule::localindim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule10localInDimE10SizeType32", false]], "tensorrt_llm::runtime::loramodule::localinoutsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localInOutSizeE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loramodule::localinsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localInSizeE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loramodule::localoutadaptersize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule19localOutAdapterSizeE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loramodule::localoutdim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localOutDimE10SizeType32", false]], "tensorrt_llm::runtime::loramodule::localoutsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12localOutSizeE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::loramodule::localscalessize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule15localScalesSizeE10SizeType32b", false]], "tensorrt_llm::runtime::loramodule::localtotalsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localTotalSizeE10SizeType3210SizeType32b", false]], "tensorrt_llm::runtime::loramodule::loramodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10LoraModule", false], [1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleEv", false]], "tensorrt_llm::runtime::loramodule::mindim (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule6mInDimE", false]], "tensorrt_llm::runtime::loramodule::mindimfirst (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule11mInDimFirstE", false]], "tensorrt_llm::runtime::loramodule::mintpsplitdim (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule13mInTpSplitDimE", false]], "tensorrt_llm::runtime::loramodule::moduletype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleTypeE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kattn_dense (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kATTN_DENSEE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kattn_k (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_KE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kattn_q (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_QE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kattn_qkv (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kATTN_QKVE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kattn_v (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_VE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kcross_attn_dense (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType17kCROSS_ATTN_DENSEE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kcross_attn_k (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_KE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kcross_attn_q (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_QE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kcross_attn_qkv (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType15kCROSS_ATTN_QKVE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kcross_attn_v (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_VE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kinvalid (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType8kINVALIDE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmlp_4h_to_h (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMLP_4H_TO_HE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmlp_gate (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kMLP_GATEE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmlp_gate_up (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMLP_GATE_UPE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmlp_h_to_4h (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMLP_H_TO_4HE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmlp_router (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kMLP_ROUTERE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmoe_4h_to_h (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMOE_4H_TO_HE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmoe_gate (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kMOE_GATEE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmoe_h_to_4h (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMOE_H_TO_4HE", false]], "tensorrt_llm::runtime::loramodule::moduletype::kmoe_router (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kMOE_ROUTERE", false]], "tensorrt_llm::runtime::loramodule::moutdim (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule7mOutDimE", false]], "tensorrt_llm::runtime::loramodule::moutdimfirst (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12mOutDimFirstE", false]], "tensorrt_llm::runtime::loramodule::mouttpsplitdim (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule14mOutTpSplitDimE", false]], "tensorrt_llm::runtime::loramodule::mtype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule5mTypeE", false]], "tensorrt_llm::runtime::loramodule::name (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule4nameEv", false]], "tensorrt_llm::runtime::loramodule::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModuleaSERK10LoraModule", false]], "tensorrt_llm::runtime::loramodule::outdim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule6outDimEv", false]], "tensorrt_llm::runtime::loramodule::outdimfirst (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11outDimFirstEv", false]], "tensorrt_llm::runtime::loramodule::outsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule7outSizeE10SizeType32", false]], "tensorrt_llm::runtime::loramodule::outtpsplitdim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule13outTpSplitDimEv", false]], "tensorrt_llm::runtime::loramodule::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule9TensorPtrE", false]], "tensorrt_llm::runtime::loramodule::tomodulename (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10ModuleType", false], [1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10SizeType32", false]], "tensorrt_llm::runtime::loramodule::tomoduletype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleTypeERKNSt11string_viewE", false]], "tensorrt_llm::runtime::loramodule::value (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule5valueEv", false]], "tensorrt_llm::runtime::lorataskidtype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14LoraTaskIdTypeE", false]], "tensorrt_llm::runtime::medusamodule (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModuleE", false]], "tensorrt_llm::runtime::medusamodule::getmedusachoices (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule16getMedusaChoicesEv", false]], "tensorrt_llm::runtime::medusamodule::mdefaultmedusachoices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule21mDefaultMedusaChoicesE", false]], "tensorrt_llm::runtime::medusamodule::medusachoices (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule13MedusaChoicesE", false]], "tensorrt_llm::runtime::medusamodule::medusamodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleE10SizeType3210SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleEv", false]], "tensorrt_llm::runtime::medusamodule::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule9TensorPtrE", false]], "tensorrt_llm::runtime::memorycounters (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCountersE", false]], "tensorrt_llm::runtime::memorycounters::allocate (c++ function)": [[1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters8allocateEv10SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8allocateE10MemoryType10SizeType32", false]], "tensorrt_llm::runtime::memorycounters::bytestostring (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE10SizeType32i", false], [1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8DiffTypei", false]], "tensorrt_llm::runtime::memorycounters::deallocate (c++ function)": [[1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters10deallocateEv10SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10deallocateE10MemoryType10SizeType32", false]], "tensorrt_llm::runtime::memorycounters::difftype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE", false]], "tensorrt_llm::runtime::memorycounters::getcpu (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getCpuEv", false]], "tensorrt_llm::runtime::memorycounters::getcpudiff (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getCpuDiffEv", false]], "tensorrt_llm::runtime::memorycounters::getgpu (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getGpuEv", false]], "tensorrt_llm::runtime::memorycounters::getgpudiff (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getGpuDiffEv", false]], "tensorrt_llm::runtime::memorycounters::getinstance (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11getInstanceEv", false]], "tensorrt_llm::runtime::memorycounters::getpinned (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters9getPinnedEv", false]], "tensorrt_llm::runtime::memorycounters::getpinneddiff (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters13getPinnedDiffEv", false]], "tensorrt_llm::runtime::memorycounters::getpinnedpool (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters13getPinnedPoolEv", false]], "tensorrt_llm::runtime::memorycounters::getpinnedpooldiff (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters17getPinnedPoolDiffEv", false]], "tensorrt_llm::runtime::memorycounters::getuvm (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getUVMEv", false]], "tensorrt_llm::runtime::memorycounters::getuvmdiff (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getUVMDiffEv", false]], "tensorrt_llm::runtime::memorycounters::mcpu (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mCpuE", false]], "tensorrt_llm::runtime::memorycounters::mcpudiff (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mCpuDiffE", false]], "tensorrt_llm::runtime::memorycounters::memorycounters (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters14MemoryCountersEv", false]], "tensorrt_llm::runtime::memorycounters::mgpu (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mGpuE", false]], "tensorrt_llm::runtime::memorycounters::mgpudiff (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mGpuDiffE", false]], "tensorrt_llm::runtime::memorycounters::mpinned (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters7mPinnedE", false]], "tensorrt_llm::runtime::memorycounters::mpinneddiff (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11mPinnedDiffE", false]], "tensorrt_llm::runtime::memorycounters::mpinnedpool (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11mPinnedPoolE", false]], "tensorrt_llm::runtime::memorycounters::mpinnedpooldiff (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters15mPinnedPoolDiffE", false]], "tensorrt_llm::runtime::memorycounters::muvm (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mUVME", false]], "tensorrt_llm::runtime::memorycounters::muvmdiff (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mUVMDiffE", false]], "tensorrt_llm::runtime::memorycounters::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10SizeType32E", false]], "tensorrt_llm::runtime::memorycounters::tostring (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters8toStringEv", false]], "tensorrt_llm::runtime::memorytype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryTypeE", false]], "tensorrt_llm::runtime::memorytype::kcpu (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kCPUE", false]], "tensorrt_llm::runtime::memorytype::kgpu (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kGPUE", false]], "tensorrt_llm::runtime::memorytype::kpinned (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryType7kPINNEDE", false]], "tensorrt_llm::runtime::memorytype::kpinnedpool (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryType11kPINNEDPOOLE", false]], "tensorrt_llm::runtime::memorytype::kuvm (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kUVME", false]], "tensorrt_llm::runtime::memorytypestring (c++ struct)": [[1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime16MemoryTypeStringE", false]], "tensorrt_llm::runtime::memorytypestring (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEEE", false]], "tensorrt_llm::runtime::memorytypestring::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEE5valueE", false]], "tensorrt_llm::runtime::memorytypestring (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEEE", false]], "tensorrt_llm::runtime::memorytypestring::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEE5valueE", false]], "tensorrt_llm::runtime::memorytypestring (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEEE", false]], "tensorrt_llm::runtime::memorytypestring::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEE5valueE", false]], "tensorrt_llm::runtime::memorytypestring (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType11kPINNEDPOOLEEE", false]], "tensorrt_llm::runtime::memorytypestring::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType11kPINNEDPOOLEE5valueE", false]], "tensorrt_llm::runtime::memorytypestring (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kUVMEEE", false]], "tensorrt_llm::runtime::memorytypestring::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kUVMEE5valueE", false]], "tensorrt_llm::runtime::modelconfig (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfigE", false]], "tensorrt_llm::runtime::modelconfig::computecontextlogits (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20computeContextLogitsEb", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20computeContextLogitsEv", false]], "tensorrt_llm::runtime::modelconfig::computegenerationlogits (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23computeGenerationLogitsEb", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig23computeGenerationLogitsEv", false]], "tensorrt_llm::runtime::modelconfig::countlocallayers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16countLocalLayersE9LayerType10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::modelconfig::countlowerranklayers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20countLowerRankLayersE9LayerType10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::modelconfig::disableseamlesslookaheaddecoding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig32disableSeamlessLookaheadDecodingEv", false]], "tensorrt_llm::runtime::modelconfig::enableseamlesslookaheaddecoding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig31enableSeamlessLookaheadDecodingE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::getcontextfmha (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getContextFMHAEv", false]], "tensorrt_llm::runtime::modelconfig::getdatatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig11getDataTypeEv", false]], "tensorrt_llm::runtime::modelconfig::getencoderhiddensize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getEncoderHiddenSizeEv", false]], "tensorrt_llm::runtime::modelconfig::getfirstlocallayer (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getFirstLocalLayerE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::modelconfig::getgemmallreducedtype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21getGemmAllReduceDtypeEv", false]], "tensorrt_llm::runtime::modelconfig::gethiddensize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getHiddenSizeEv", false]], "tensorrt_llm::runtime::modelconfig::getkvcachetype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getKVCacheTypeEv", false]], "tensorrt_llm::runtime::modelconfig::getkvdatatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getKvDataTypeEv", false]], "tensorrt_llm::runtime::modelconfig::getlayertypes (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getLayerTypesEv", false]], "tensorrt_llm::runtime::modelconfig::getlogitsdtype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getLogitsDtypeEv", false]], "tensorrt_llm::runtime::modelconfig::getloramodules (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getLoraModulesEv", false]], "tensorrt_llm::runtime::modelconfig::getmanageweightstype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getManageWeightsTypeEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxbatchsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxBatchSizeEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxbeamwidth (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxBeamWidthEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxdecodingdrafttokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig25getMaxDecodingDraftTokensEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxdecodingtokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getMaxDecodingTokensEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxencoderlen (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16getMaxEncoderLenEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxinputlen (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getMaxInputLenEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxlorarank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getMaxLoraRankEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxnumtokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxNumTokensEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxpositionembeddings (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig24getMaxPositionEmbeddingsEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxpromptembeddingtablesize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig30getMaxPromptEmbeddingTableSizeEv", false]], "tensorrt_llm::runtime::modelconfig::getmaxsequencelen (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17getMaxSequenceLenEv", false]], "tensorrt_llm::runtime::modelconfig::getmlphiddensize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16getMlpHiddenSizeEv", false]], "tensorrt_llm::runtime::modelconfig::getmodelname (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getModelNameEv", false]], "tensorrt_llm::runtime::modelconfig::getmodelvariant (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getModelVariantEv", false]], "tensorrt_llm::runtime::modelconfig::getnbattentionlayers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getNbAttentionLayersE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::modelconfig::getnbheads (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig10getNbHeadsEv", false]], "tensorrt_llm::runtime::modelconfig::getnbkvheads (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getNbKvHeadsE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::getnblayers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig11getNbLayersE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::modelconfig::getnbrnnlayers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getNbRnnLayersE10SizeType3210SizeType32", false]], "tensorrt_llm::runtime::modelconfig::getnumkvheadsforgivenlayers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig27getNumKvHeadsForGivenLayersERKNSt6vectorI10SizeType32EEb", false]], "tensorrt_llm::runtime::modelconfig::getnumkvheadsperlayer (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21getNumKvHeadsPerLayerEv", false]], "tensorrt_llm::runtime::modelconfig::getnumkvheadsperlayerlocalrange (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig31getNumKvHeadsPerLayerLocalRangeE10SizeType3210SizeType32b", false]], "tensorrt_llm::runtime::modelconfig::getnumlanguages (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getNumLanguagesEv", false]], "tensorrt_llm::runtime::modelconfig::getoptprofilessplitpoints (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig25getOptProfilesSplitPointsEv", false]], "tensorrt_llm::runtime::modelconfig::getpagedcontextfmha (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig19getPagedContextFMHAEv", false]], "tensorrt_llm::runtime::modelconfig::getppreducescatter (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getPpReduceScatterEv", false]], "tensorrt_llm::runtime::modelconfig::getquantmode (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getQuantModeEv", false]], "tensorrt_llm::runtime::modelconfig::getrnnconfig (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getRnnConfigEv", false]], "tensorrt_llm::runtime::modelconfig::getrotaryembeddingdim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21getRotaryEmbeddingDimEv", false]], "tensorrt_llm::runtime::modelconfig::getsizeperhead (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getSizePerHeadEv", false]], "tensorrt_llm::runtime::modelconfig::getspeculativedecodingmode (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig26getSpeculativeDecodingModeEv", false]], "tensorrt_llm::runtime::modelconfig::getspeculativedecodingmodule (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig28getSpeculativeDecodingModuleEv", false]], "tensorrt_llm::runtime::modelconfig::getspeculativedecodingmoduleptr (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig31getSpeculativeDecodingModulePtrEv", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig31getSpeculativeDecodingModulePtrEv", false]], "tensorrt_llm::runtime::modelconfig::gettokensperblock (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17getTokensPerBlockEv", false]], "tensorrt_llm::runtime::modelconfig::getvocabsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getVocabSizeEv", false]], "tensorrt_llm::runtime::modelconfig::getvocabsizepadded (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getVocabSizePaddedE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::hasrnnconfig (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12hasRnnConfigEv", false]], "tensorrt_llm::runtime::modelconfig::hasspeculativedecodingmodule (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig28hasSpeculativeDecodingModuleEv", false]], "tensorrt_llm::runtime::modelconfig::iscontinuouskvcache (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig19isContinuousKVCacheEv", false]], "tensorrt_llm::runtime::modelconfig::iskvcacheenabled (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16isKVCacheEnabledEv", false]], "tensorrt_llm::runtime::modelconfig::ismultimodal (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12isMultiModalEv", false]], "tensorrt_llm::runtime::modelconfig::ispagedkvcache (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14isPagedKVCacheEv", false]], "tensorrt_llm::runtime::modelconfig::isrnnbased (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig10isRnnBasedEv", false]], "tensorrt_llm::runtime::modelconfig::istransformerbased (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18isTransformerBasedEv", false]], "tensorrt_llm::runtime::modelconfig::iswhisper (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig9isWhisperEv", false]], "tensorrt_llm::runtime::modelconfig::kdefault_num_tokens_per_block (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig29kDEFAULT_NUM_TOKENS_PER_BLOCKE", false]], "tensorrt_llm::runtime::modelconfig::kopt_profiles_split_points (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26kOPT_PROFILES_SPLIT_POINTSE", false]], "tensorrt_llm::runtime::modelconfig::kvcachetype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheTypeE", false]], "tensorrt_llm::runtime::modelconfig::kvcachetype::kcontinuous (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType11kCONTINUOUSE", false]], "tensorrt_llm::runtime::modelconfig::kvcachetype::kdisabled (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType9kDISABLEDE", false]], "tensorrt_llm::runtime::modelconfig::kvcachetype::kpaged (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType6kPAGEDE", false]], "tensorrt_llm::runtime::modelconfig::kvcachetypefromstring (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21KVCacheTypeFromStringENSt6stringE", false]], "tensorrt_llm::runtime::modelconfig::layertype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerTypeE", false]], "tensorrt_llm::runtime::modelconfig::layertype::kattention (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType10kATTENTIONE", false]], "tensorrt_llm::runtime::modelconfig::layertype::klinear (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType7kLINEARE", false]], "tensorrt_llm::runtime::modelconfig::layertype::knoop (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType5kNOOPE", false]], "tensorrt_llm::runtime::modelconfig::layertype::krecurrent (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType10kRECURRENTE", false]], "tensorrt_llm::runtime::modelconfig::manageweightstype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsTypeE", false]], "tensorrt_llm::runtime::modelconfig::manageweightstype::kdisabled (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsType9kDisabledE", false]], "tensorrt_llm::runtime::modelconfig::manageweightstype::kenabled (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsType8kEnabledE", false]], "tensorrt_llm::runtime::modelconfig::mcomputecontextlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mComputeContextLogitsE", false]], "tensorrt_llm::runtime::modelconfig::mcomputegenerationlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24mComputeGenerationLogitsE", false]], "tensorrt_llm::runtime::modelconfig::mcontextfmha (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mContextFMHAE", false]], "tensorrt_llm::runtime::modelconfig::mdatatype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9mDataTypeE", false]], "tensorrt_llm::runtime::modelconfig::mencoderhiddensize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mEncoderHiddenSizeE", false]], "tensorrt_llm::runtime::modelconfig::mgemmallreducedtype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig19mGemmAllReduceDtypeE", false]], "tensorrt_llm::runtime::modelconfig::mhiddensize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mHiddenSizeE", false]], "tensorrt_llm::runtime::modelconfig::minputpacked (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mInputPackedE", false]], "tensorrt_llm::runtime::modelconfig::mkvcachetype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mKVCacheTypeE", false]], "tensorrt_llm::runtime::modelconfig::mlayertypes (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mLayerTypesE", false]], "tensorrt_llm::runtime::modelconfig::mlogitsdtype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mLogitsDtypeE", false]], "tensorrt_llm::runtime::modelconfig::mloramodules (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mLoraModulesE", false]], "tensorrt_llm::runtime::modelconfig::mmanageweightstype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mManageWeightsTypeE", false]], "tensorrt_llm::runtime::modelconfig::mmaxbatchsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxBatchSizeE", false]], "tensorrt_llm::runtime::modelconfig::mmaxbeamwidth (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxBeamWidthE", false]], "tensorrt_llm::runtime::modelconfig::mmaxencoderlen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mMaxEncoderLenE", false]], "tensorrt_llm::runtime::modelconfig::mmaxinputlen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mMaxInputLenE", false]], "tensorrt_llm::runtime::modelconfig::mmaxlorarank (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mMaxLoraRankE", false]], "tensorrt_llm::runtime::modelconfig::mmaxnumtokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxNumTokensE", false]], "tensorrt_llm::runtime::modelconfig::mmaxpositionembeddings (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22mMaxPositionEmbeddingsE", false]], "tensorrt_llm::runtime::modelconfig::mmaxpromptembeddingtablesize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28mMaxPromptEmbeddingTableSizeE", false]], "tensorrt_llm::runtime::modelconfig::mmaxsequencelen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15mMaxSequenceLenE", false]], "tensorrt_llm::runtime::modelconfig::mmlphiddensize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mMlpHiddenSizeE", false]], "tensorrt_llm::runtime::modelconfig::mmodelname (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mModelNameE", false]], "tensorrt_llm::runtime::modelconfig::mmodelvariant (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mModelVariantE", false]], "tensorrt_llm::runtime::modelconfig::mnbattentionlayers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mNbAttentionLayersE", false]], "tensorrt_llm::runtime::modelconfig::mnbheads (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig8mNbHeadsE", false]], "tensorrt_llm::runtime::modelconfig::mnblayers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9mNbLayersE", false]], "tensorrt_llm::runtime::modelconfig::mnbrnnlayers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mNbRnnLayersE", false]], "tensorrt_llm::runtime::modelconfig::mnumkvheadsperattentionlayer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28mNumKvHeadsPerAttentionLayerE", false]], "tensorrt_llm::runtime::modelconfig::mnumkvheadspercrossattentionlayer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig33mNumKvHeadsPerCrossAttentionLayerE", false]], "tensorrt_llm::runtime::modelconfig::mnumlanguages (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mNumLanguagesE", false]], "tensorrt_llm::runtime::modelconfig::modelconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::modelconfig::modelvariant (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariantE", false]], "tensorrt_llm::runtime::modelconfig::modelvariant::kchatglm (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant8kChatGlmE", false]], "tensorrt_llm::runtime::modelconfig::modelvariant::kencdec (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant7kEncDecE", false]], "tensorrt_llm::runtime::modelconfig::modelvariant::kglm (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant4kGlmE", false]], "tensorrt_llm::runtime::modelconfig::modelvariant::kgpt (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant4kGptE", false]], "tensorrt_llm::runtime::modelconfig::modelvariant::kmamba (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant6kMambaE", false]], "tensorrt_llm::runtime::modelconfig::modelvariant::krecurrentgemma (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant15kRecurrentGemmaE", false]], "tensorrt_llm::runtime::modelconfig::mpagedcontextfmha (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17mPagedContextFMHAE", false]], "tensorrt_llm::runtime::modelconfig::mpagedstate (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mPagedStateE", false]], "tensorrt_llm::runtime::modelconfig::mppreducescatter (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16mPpReduceScatterE", false]], "tensorrt_llm::runtime::modelconfig::mquantmode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mQuantModeE", false]], "tensorrt_llm::runtime::modelconfig::mrnnconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mRnnConfigE", false]], "tensorrt_llm::runtime::modelconfig::mrotaryembeddingdim (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig19mRotaryEmbeddingDimE", false]], "tensorrt_llm::runtime::modelconfig::msizeperhead (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mSizePerHeadE", false]], "tensorrt_llm::runtime::modelconfig::mskipcrossattnblocks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20mSkipCrossAttnBlocksE", false]], "tensorrt_llm::runtime::modelconfig::mspeculativedecodingmode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24mSpeculativeDecodingModeE", false]], "tensorrt_llm::runtime::modelconfig::mspeculativedecodingmodule (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26mSpeculativeDecodingModuleE", false]], "tensorrt_llm::runtime::modelconfig::mtokensperblock (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15mTokensPerBlockE", false]], "tensorrt_llm::runtime::modelconfig::musecrossattention (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mUseCrossAttentionE", false]], "tensorrt_llm::runtime::modelconfig::musegemmallreduceplugin (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23mUseGemmAllReducePluginE", false]], "tensorrt_llm::runtime::modelconfig::musegptattentionplugin (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22mUseGptAttentionPluginE", false]], "tensorrt_llm::runtime::modelconfig::museloraplugin (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mUseLoraPluginE", false]], "tensorrt_llm::runtime::modelconfig::musemambaconv1dplugin (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mUseMambaConv1dPluginE", false]], "tensorrt_llm::runtime::modelconfig::musemrope (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9mUseMropeE", false]], "tensorrt_llm::runtime::modelconfig::musepositionembedding (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mUsePositionEmbeddingE", false]], "tensorrt_llm::runtime::modelconfig::museshapeinference (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mUseShapeInferenceE", false]], "tensorrt_llm::runtime::modelconfig::musetokentypeembedding (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22mUseTokenTypeEmbeddingE", false]], "tensorrt_llm::runtime::modelconfig::mvocabsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mVocabSizeE", false]], "tensorrt_llm::runtime::modelconfig::resetspeculativedecodingmodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig30resetSpeculativeDecodingModuleEv", false]], "tensorrt_llm::runtime::modelconfig::rnnconfig (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfigE", false]], "tensorrt_llm::runtime::modelconfig::rnnconfig::convkernel (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig10convKernelE", false]], "tensorrt_llm::runtime::modelconfig::rnnconfig::rnnconvdimsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig14rnnConvDimSizeE", false]], "tensorrt_llm::runtime::modelconfig::rnnconfig::rnnheadsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig11rnnHeadSizeE", false]], "tensorrt_llm::runtime::modelconfig::rnnconfig::rnnhiddensize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig13rnnHiddenSizeE", false]], "tensorrt_llm::runtime::modelconfig::rnnconfig::statesize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig9stateSizeE", false]], "tensorrt_llm::runtime::modelconfig::setcontextfmha (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setContextFMHAEb", false]], "tensorrt_llm::runtime::modelconfig::setencoderhiddensize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setEncoderHiddenSizeE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setgemmallreducedtype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setGemmAllReduceDtypeEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::modelconfig::setkvcachetype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setKVCacheTypeE11KVCacheType", false]], "tensorrt_llm::runtime::modelconfig::setlayertypes (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13setLayerTypesERKNSt6vectorI9LayerTypeEE", false]], "tensorrt_llm::runtime::modelconfig::setlogitsdtype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLogitsDtypeEN8nvinfer18DataTypeE", false]], "tensorrt_llm::runtime::modelconfig::setloramodules (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLoraModulesERKNSt6vectorI10LoraModuleEE", false]], "tensorrt_llm::runtime::modelconfig::setmanageweightstype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setManageWeightsTypeEK17ManageWeightsType", false]], "tensorrt_llm::runtime::modelconfig::setmaxbatchsize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBatchSizeE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmaxbeamwidth (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBeamWidthE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmaxencoderlen (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMaxEncoderLenE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmaxinputlen (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxInputLenE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmaxlorarank (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxLoraRankE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmaxnumtokens (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxNumTokensENSt8optionalI10SizeType32EE", false]], "tensorrt_llm::runtime::modelconfig::setmaxpositionembeddings (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24setMaxPositionEmbeddingsE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmaxpromptembeddingtablesize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig30setMaxPromptEmbeddingTableSizeE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmaxsequencelen (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setMaxSequenceLenE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmlphiddensize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMlpHiddenSizeE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setmodelname (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setModelNameERKNSt6stringE", false]], "tensorrt_llm::runtime::modelconfig::setmodelvariant (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setModelVariantE12ModelVariant", false]], "tensorrt_llm::runtime::modelconfig::setnbcrosskvheads (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setNbCrossKvHeadsE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setnbkvheads (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setNbKvHeadsE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setnumkvheadspercrosslayer (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26setNumKvHeadsPerCrossLayerERKNSt6vectorI10SizeType32EE", false]], "tensorrt_llm::runtime::modelconfig::setnumkvheadsperlayer (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setNumKvHeadsPerLayerERKNSt6vectorI10SizeType32EE", false]], "tensorrt_llm::runtime::modelconfig::setnumlanguages (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setNumLanguagesENSt8optionalI10SizeType32EE", false]], "tensorrt_llm::runtime::modelconfig::setpagedcontextfmha (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig19setPagedContextFMHAEb", false]], "tensorrt_llm::runtime::modelconfig::setppreducescatter (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18setPpReduceScatterEb", false]], "tensorrt_llm::runtime::modelconfig::setquantmode (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setQuantModeEN6common9QuantModeE", false]], "tensorrt_llm::runtime::modelconfig::setrnnconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setRnnConfigERK9RnnConfig", false]], "tensorrt_llm::runtime::modelconfig::setrotaryembeddingdim (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setRotaryEmbeddingDimE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setsizeperhead (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setSizePerHeadE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setskipcrossattnblocks (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22setSkipCrossAttnBlocksEb", false]], "tensorrt_llm::runtime::modelconfig::setspeculativedecodingmode (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26setSpeculativeDecodingModeE23SpeculativeDecodingMode", false]], "tensorrt_llm::runtime::modelconfig::setspeculativedecodingmodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28setSpeculativeDecodingModuleERKNSt10shared_ptrI25SpeculativeDecodingModuleEE", false]], "tensorrt_llm::runtime::modelconfig::settokensperblock (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setTokensPerBlockE10SizeType32", false]], "tensorrt_llm::runtime::modelconfig::setusecrossattention (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseCrossAttentionEb", false]], "tensorrt_llm::runtime::modelconfig::setusemrope (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11setUseMropeEb", false]], "tensorrt_llm::runtime::modelconfig::setusepositionembedding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23setUsePositionEmbeddingEb", false]], "tensorrt_llm::runtime::modelconfig::setuseshapeinference (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseShapeInferenceEb", false]], "tensorrt_llm::runtime::modelconfig::setusetokentypeembedding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24setUseTokenTypeEmbeddingEb", false]], "tensorrt_llm::runtime::modelconfig::skipcrossattnblocks (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig19skipCrossAttnBlocksEv", false]], "tensorrt_llm::runtime::modelconfig::supportsinflightbatching (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig24supportsInflightBatchingEv", false]], "tensorrt_llm::runtime::modelconfig::usecrossattention (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17useCrossAttentionEv", false]], "tensorrt_llm::runtime::modelconfig::usegemmallreduceplugin (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22useGemmAllReducePluginEb", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig22useGemmAllReducePluginEv", false]], "tensorrt_llm::runtime::modelconfig::usegptattentionplugin (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21useGptAttentionPluginEb", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21useGptAttentionPluginEv", false]], "tensorrt_llm::runtime::modelconfig::uselanguageadapter (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18useLanguageAdapterEv", false]], "tensorrt_llm::runtime::modelconfig::useloraplugin (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13useLoraPluginEb", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13useLoraPluginEv", false]], "tensorrt_llm::runtime::modelconfig::usemambaconv1dplugin (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20useMambaConv1dPluginEb", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20useMambaConv1dPluginEv", false]], "tensorrt_llm::runtime::modelconfig::usemrope (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig8useMropeEv", false]], "tensorrt_llm::runtime::modelconfig::usepackedinput (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14usePackedInputEb", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14usePackedInputEv", false]], "tensorrt_llm::runtime::modelconfig::usepagedstate (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13usePagedStateEb", false], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13usePagedStateEv", false]], "tensorrt_llm::runtime::modelconfig::usepositionembedding (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20usePositionEmbeddingEv", false]], "tensorrt_llm::runtime::modelconfig::useprompttuning (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15usePromptTuningEv", false]], "tensorrt_llm::runtime::modelconfig::useshapeinference (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17useShapeInferenceEv", false]], "tensorrt_llm::runtime::modelconfig::usetokentypeembedding (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21useTokenTypeEmbeddingEv", false]], "tensorrt_llm::runtime::mpi_group_barrier (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17MPI_group_barrierENSt3setIiEE", false]], "tensorrt_llm::runtime::operator<< (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK10LoraModule", false], [1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK26LoraCachePageManagerConfig", false], [1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7IBuffer", false], [1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7ITensor", false], [1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN7ITensor5ShapeE", false], [1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN9LoraCache21TaskLayerModuleConfigE", false]], "tensorrt_llm::runtime::pointerelementtype (c++ type)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE", false]], "tensorrt_llm::runtime::prompttuningparams (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParamsE", false]], "tensorrt_llm::runtime::prompttuningparams::filltaskstensor (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", false]], "tensorrt_llm::runtime::prompttuningparams::prompttuningparams (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", false]], "tensorrt_llm::runtime::prompttuningparams::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams10SizeType32E", false]], "tensorrt_llm::runtime::prompttuningparams::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams9TensorPtrE", false]], "tensorrt_llm::runtime::rawengine (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngineE", false]], "tensorrt_llm::runtime::rawengine::getaddress (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine10getAddressEv", false]], "tensorrt_llm::runtime::rawengine::gethostmemory (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine13getHostMemoryEv", false]], "tensorrt_llm::runtime::rawengine::getmanagedweightsmapopt (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine23getManagedWeightsMapOptEv", false]], "tensorrt_llm::runtime::rawengine::getpath (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getPathEv", false]], "tensorrt_llm::runtime::rawengine::getpathopt (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine10getPathOptEv", false]], "tensorrt_llm::runtime::rawengine::getsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getSizeEv", false]], "tensorrt_llm::runtime::rawengine::gettype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getTypeEv", false]], "tensorrt_llm::runtime::rawengine::mengineaddr (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEngineAddrE", false]], "tensorrt_llm::runtime::rawengine::menginebuffer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine13mEngineBufferE", false]], "tensorrt_llm::runtime::rawengine::menginepath (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEnginePathE", false]], "tensorrt_llm::runtime::rawengine::menginesize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEngineSizeE", false]], "tensorrt_llm::runtime::rawengine::mmanagedweightsmap (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine18mManagedWeightsMapE", false]], "tensorrt_llm::runtime::rawengine::mtype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine5mTypeE", false]], "tensorrt_llm::runtime::rawengine::rawengine (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineENSt10filesystem4pathE", false], [1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKN8nvinfer111IHostMemoryE", false], [1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKvNSt6size_tE", false]], "tensorrt_llm::runtime::rawengine::setmanagedweightsmap (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine20setManagedWeightsMapENSt3mapINSt6stringEN12tensorrt_llm8executor6TensorEEE", false]], "tensorrt_llm::runtime::rawengine::setpath (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine7setPathENSt10filesystem4pathE", false]], "tensorrt_llm::runtime::rawengine::type (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4TypeE", false]], "tensorrt_llm::runtime::rawengine::type::addresswithsize (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type15AddressWithSizeE", false]], "tensorrt_llm::runtime::rawengine::type::filepath (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type8FilePathE", false]], "tensorrt_llm::runtime::rawengine::type::hostmemory (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type10HostMemoryE", false]], "tensorrt_llm::runtime::requesttype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime11RequestTypeE", false]], "tensorrt_llm::runtime::requesttype::kcontext (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11RequestType8kCONTEXTE", false]], "tensorrt_llm::runtime::requesttype::kgeneration (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11RequestType11kGENERATIONE", false]], "tensorrt_llm::runtime::runtimedefaults (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaultsE", false]], "tensorrt_llm::runtime::runtimedefaults::maxattentionwindowvec (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults21maxAttentionWindowVecE", false]], "tensorrt_llm::runtime::runtimedefaults::runtimedefaults (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults15RuntimeDefaultsENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalI10SizeType32EE", false], [1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults15RuntimeDefaultsEv", false]], "tensorrt_llm::runtime::runtimedefaults::sinktokenlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults15sinkTokenLengthE", false]], "tensorrt_llm::runtime::samplingconfig (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfigE", false]], "tensorrt_llm::runtime::samplingconfig::beamsearchdiversityrate (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig23beamSearchDiversityRateE", false]], "tensorrt_llm::runtime::samplingconfig::beamwidth (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9beamWidthE", false]], "tensorrt_llm::runtime::samplingconfig::beamwidtharray (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14beamWidthArrayE", false]], "tensorrt_llm::runtime::samplingconfig::cumlogprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig11cumLogProbsE", false]], "tensorrt_llm::runtime::samplingconfig::draftacceptancethreshold (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig24draftAcceptanceThresholdE", false]], "tensorrt_llm::runtime::samplingconfig::earlystopping (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig13earlyStoppingE", false]], "tensorrt_llm::runtime::samplingconfig::floattype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE", false]], "tensorrt_llm::runtime::samplingconfig::frequencypenalty (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig16frequencyPenaltyE", false]], "tensorrt_llm::runtime::samplingconfig::fusevalues (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T", false]], "tensorrt_llm::runtime::samplingconfig::getmaxbeamwidth (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14SamplingConfig15getMaxBeamWidthEv", false]], "tensorrt_llm::runtime::samplingconfig::getnumreturnbeams (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14SamplingConfig17getNumReturnBeamsEv", false]], "tensorrt_llm::runtime::samplingconfig::lengthpenalty (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig13lengthPenaltyE", false]], "tensorrt_llm::runtime::samplingconfig::minlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9minLengthE", false]], "tensorrt_llm::runtime::samplingconfig::minp (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig4minPE", false]], "tensorrt_llm::runtime::samplingconfig::norepeatngramsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17noRepeatNgramSizeE", false]], "tensorrt_llm::runtime::samplingconfig::normalizelogprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17normalizeLogProbsE", false]], "tensorrt_llm::runtime::samplingconfig::numreturnsequences (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig18numReturnSequencesE", false]], "tensorrt_llm::runtime::samplingconfig::operator== (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14SamplingConfigeqERK14SamplingConfig", false]], "tensorrt_llm::runtime::samplingconfig::optvec (c++ type)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE", false]], "tensorrt_llm::runtime::samplingconfig::originaltemperature (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig19originalTemperatureE", false]], "tensorrt_llm::runtime::samplingconfig::outputlogprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14outputLogProbsE", false]], "tensorrt_llm::runtime::samplingconfig::presencepenalty (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig15presencePenaltyE", false]], "tensorrt_llm::runtime::samplingconfig::randomseed (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig10randomSeedE", false]], "tensorrt_llm::runtime::samplingconfig::repetitionpenalty (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17repetitionPenaltyE", false]], "tensorrt_llm::runtime::samplingconfig::samplingconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigE10SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKN8executor14SamplingConfigERKNSt8optionalIN8executor25ExternalDraftTokensConfigEEE", false], [1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKNSt6vectorI14SamplingConfigEE", false]], "tensorrt_llm::runtime::samplingconfig::temperature (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig11temperatureE", false]], "tensorrt_llm::runtime::samplingconfig::topk (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topKE", false]], "tensorrt_llm::runtime::samplingconfig::topkmedusaheads (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig15topKMedusaHeadsE", false]], "tensorrt_llm::runtime::samplingconfig::topp (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topPE", false]], "tensorrt_llm::runtime::samplingconfig::toppdecay (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9topPDecayE", false]], "tensorrt_llm::runtime::samplingconfig::toppmin (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig7topPMinE", false]], "tensorrt_llm::runtime::samplingconfig::toppresetids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig12topPResetIdsE", false]], "tensorrt_llm::runtime::samplingconfig::usedefaultvalues (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig16useDefaultValuesEbRK6OptVecI1TE1T", false]], "tensorrt_llm::runtime::samplingconfig::validate (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig8validateEv", false]], "tensorrt_llm::runtime::samplingconfig::validatevec (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", false]], "tensorrt_llm::runtime::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10SizeType32E", false]], "tensorrt_llm::runtime::sizetype64 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10SizeType64E", false]], "tensorrt_llm::runtime::speculativedecodingmode (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingModeE", false]], "tensorrt_llm::runtime::speculativedecodingmode::allbitset (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9allBitSetE14UnderlyingType", false]], "tensorrt_llm::runtime::speculativedecodingmode::anybitset (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9anyBitSetE14UnderlyingType", false]], "tensorrt_llm::runtime::speculativedecodingmode::drafttokensexternal (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode19DraftTokensExternalEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::eagle (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode5EagleEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::explicitdrafttokens (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode19ExplicitDraftTokensEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::hasdraftlogits (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode14hasDraftLogitsEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::isdrafttokensexternal (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21isDraftTokensExternalEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::iseagle (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode7isEagleEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::isexplicitdrafttokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21isExplicitDraftTokensEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::islookaheaddecoding (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19isLookaheadDecodingEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::ismedusa (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode8isMedusaEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::isnone (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode6isNoneEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::kdrafttokensexternal (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode20kDraftTokensExternalE", false]], "tensorrt_llm::runtime::speculativedecodingmode::keagle (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode6kEagleE", false]], "tensorrt_llm::runtime::speculativedecodingmode::kexplicitdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode20kExplicitDraftTokensE", false]], "tensorrt_llm::runtime::speculativedecodingmode::klookaheaddecoding (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode18kLookaheadDecodingE", false]], "tensorrt_llm::runtime::speculativedecodingmode::kmedusa (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode7kMedusaE", false]], "tensorrt_llm::runtime::speculativedecodingmode::knone (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode5kNoneE", false]], "tensorrt_llm::runtime::speculativedecodingmode::lookaheaddecoding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode17LookaheadDecodingEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::medusa (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode6MedusaEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::mstate (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode6mStateE", false]], "tensorrt_llm::runtime::speculativedecodingmode::needsdecoderprologue (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode20needsDecoderPrologueEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::needskvcacherewind (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode18needsKVCacheRewindEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::none (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode4NoneEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::operator== (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingModeeqERK23SpeculativeDecodingMode", false]], "tensorrt_llm::runtime::speculativedecodingmode::predictsdrafttokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19predictsDraftTokensEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::requiresattentionmask (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21requiresAttentionMaskEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::speculativedecodingmode (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode23SpeculativeDecodingModeE14UnderlyingType", false]], "tensorrt_llm::runtime::speculativedecodingmode::underlyingtype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode14UnderlyingTypeE", false]], "tensorrt_llm::runtime::speculativedecodingmode::updatespositionids (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode18updatesPositionIdsEv", false]], "tensorrt_llm::runtime::speculativedecodingmode::variabledraftlength (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19variableDraftLengthEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleE", false]], "tensorrt_llm::runtime::speculativedecodingmodule::computenumpackedmasks (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule21computeNumPackedMasksEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule::getmaxdecodingdrafttokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule25getMaxDecodingDraftTokensEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule::getmaxdecodingtokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule20getMaxDecodingTokensEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule::getmaxdraftpathlen (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule18getMaxDraftPathLenEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule::getmaxnumpaths (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule14getMaxNumPathsEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule::getmaxpathlen (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule13getMaxPathLenEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule::getnumpackedmasks (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule17getNumPackedMasksEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule::mmaxdecodingdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule23mMaxDecodingDraftTokensE", false]], "tensorrt_llm::runtime::speculativedecodingmodule::mmaxdraftpathlen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule16mMaxDraftPathLenE", false]], "tensorrt_llm::runtime::speculativedecodingmodule::mmaxnumpackedmasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule18mMaxNumPackedMasksE", false]], "tensorrt_llm::runtime::speculativedecodingmodule::mmaxnumpaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule12mMaxNumPathsE", false]], "tensorrt_llm::runtime::speculativedecodingmodule::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleaSERK25SpeculativeDecodingModule", false]], "tensorrt_llm::runtime::speculativedecodingmodule::setmaxdraftpathlen (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule18setMaxDraftPathLenE10SizeType32", false]], "tensorrt_llm::runtime::speculativedecodingmodule::setmaxdrafttokens (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule17setMaxDraftTokensE10SizeType32", false]], "tensorrt_llm::runtime::speculativedecodingmodule::setmaxnumpaths (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule14setMaxNumPathsE10SizeType32", false]], "tensorrt_llm::runtime::speculativedecodingmodule::speculativedecodingmodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleE10SizeType3210SizeType3210SizeType32", false], [1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleERK25SpeculativeDecodingModule", false], [1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleEv", false]], "tensorrt_llm::runtime::speculativedecodingmodule::~speculativedecodingmodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleD0Ev", false]], "tensorrt_llm::runtime::stringptrmap (c++ type)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime12StringPtrMapE", false]], "tensorrt_llm::runtime::tllmlogger (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime10TllmLoggerE", false]], "tensorrt_llm::runtime::tllmlogger::getlevel (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger8getLevelEv", false]], "tensorrt_llm::runtime::tllmlogger::log (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger3logE8SeverityPKN8nvinfer19AsciiCharE", false]], "tensorrt_llm::runtime::tllmlogger::setlevel (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger8setLevelE8Severity", false]], "tensorrt_llm::runtime::to_string (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9to_stringERK26LoraCachePageManagerConfig", false], [1, "_CPPv4N12tensorrt_llm7runtime9to_stringERKN9LoraCache21TaskLayerModuleConfigE", false]], "tensorrt_llm::runtime::tokenextraidtype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime16TokenExtraIdTypeE", false]], "tensorrt_llm::runtime::tokenidtype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime11TokenIdTypeE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4I0_bEN12tensorrt_llm7runtime11TRTDataTypeE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIbEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIbE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIfEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIfE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeI4halfEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeI4halfE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIN7kernels13FinishedStateEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIN7kernels13FinishedStateEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIN7kernels12KVCacheIndexEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIN7kernels12KVCacheIndexEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIN7runtime11RequestTypeEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIN7runtime11RequestTypeEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime11TRTDataTypeIP1TEE", false]], "tensorrt_llm::runtime::trtdatatype::kunderlyingtype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE15kUnderlyingTypeE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE5valueE", false]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIPvEE", false]], "tensorrt_llm::runtime::trtdatatype::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIPvE5valueE", false]], "tensorrt_llm::runtime::uniquetoken (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime11UniqueTokenE", false]], "tensorrt_llm::runtime::uniquetoken::operator== (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11UniqueTokeneqERK11UniqueToken", false]], "tensorrt_llm::runtime::uniquetoken::tokenextraid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11UniqueToken12tokenExtraIdE", false]], "tensorrt_llm::runtime::uniquetoken::tokenid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11UniqueToken7tokenIdE", false]], "tensorrt_llm::runtime::vectokenextraids (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime16VecTokenExtraIdsE", false]], "tensorrt_llm::runtime::vecuniquetokens (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime15VecUniqueTokensE", false]], "tensorrt_llm::runtime::worldconfig (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfigE", false]], "tensorrt_llm::runtime::worldconfig::enableattentiondp (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig17enableAttentionDPEv", false]], "tensorrt_llm::runtime::worldconfig::getcontextparallelgroup (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig23getContextParallelGroupEv", false]], "tensorrt_llm::runtime::worldconfig::getcontextparallelism (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig21getContextParallelismEv", false]], "tensorrt_llm::runtime::worldconfig::getcontextparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getContextParallelRankEv", false]], "tensorrt_llm::runtime::worldconfig::getdevice (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig9getDeviceEv", false]], "tensorrt_llm::runtime::worldconfig::getdeviceof (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getDeviceOfE10SizeType32", false]], "tensorrt_llm::runtime::worldconfig::getgpuspergroup (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig15getGpusPerGroupEv", false]], "tensorrt_llm::runtime::worldconfig::getgpuspernode (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig14getGpusPerNodeEv", false]], "tensorrt_llm::runtime::worldconfig::getlastrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getLastRankEv", false]], "tensorrt_llm::runtime::worldconfig::getlocalrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig12getLocalRankEv", false]], "tensorrt_llm::runtime::worldconfig::getnoderank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getNodeRankEv", false]], "tensorrt_llm::runtime::worldconfig::getnoderankof (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig13getNodeRankOfE10SizeType32", false]], "tensorrt_llm::runtime::worldconfig::getpipelineparallelgroup (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig24getPipelineParallelGroupEv", false]], "tensorrt_llm::runtime::worldconfig::getpipelineparallelism (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getPipelineParallelismEv", false]], "tensorrt_llm::runtime::worldconfig::getpipelineparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig23getPipelineParallelRankEv", false]], "tensorrt_llm::runtime::worldconfig::getrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getRankEv", false]], "tensorrt_llm::runtime::worldconfig::getsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getSizeEv", false]], "tensorrt_llm::runtime::worldconfig::gettensorparallelgroup (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getTensorParallelGroupEv", false]], "tensorrt_llm::runtime::worldconfig::gettensorparallelism (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig20getTensorParallelismEv", false]], "tensorrt_llm::runtime::worldconfig::gettensorparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig21getTensorParallelRankEv", false]], "tensorrt_llm::runtime::worldconfig::iscontextparallel (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig17isContextParallelEv", false]], "tensorrt_llm::runtime::worldconfig::isfirstcontextparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig26isFirstContextParallelRankEv", false]], "tensorrt_llm::runtime::worldconfig::isfirstpipelineparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig27isFirstPipelineParallelRankEv", false]], "tensorrt_llm::runtime::worldconfig::isfirsttensorparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig25isFirstTensorParallelRankEv", false]], "tensorrt_llm::runtime::worldconfig::islastpipelineparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig26isLastPipelineParallelRankEv", false]], "tensorrt_llm::runtime::worldconfig::ispipelineparallel (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig18isPipelineParallelEv", false]], "tensorrt_llm::runtime::worldconfig::istensorparallel (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig16isTensorParallelEv", false]], "tensorrt_llm::runtime::worldconfig::kdefaultgpuspernode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig19kDefaultGpusPerNodeE", false]], "tensorrt_llm::runtime::worldconfig::mcontextparallelism (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig19mContextParallelismE", false]], "tensorrt_llm::runtime::worldconfig::mdeviceids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig10mDeviceIdsE", false]], "tensorrt_llm::runtime::worldconfig::menableattentiondp (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig18mEnableAttentionDPE", false]], "tensorrt_llm::runtime::worldconfig::mgpuspernode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig12mGpusPerNodeE", false]], "tensorrt_llm::runtime::worldconfig::mpi (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEEb", false]], "tensorrt_llm::runtime::worldconfig::mpipelineparallelism (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig20mPipelineParallelismE", false]], "tensorrt_llm::runtime::worldconfig::mrank (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig5mRankE", false]], "tensorrt_llm::runtime::worldconfig::mtensorparallelism (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig18mTensorParallelismE", false]], "tensorrt_llm::runtime::worldconfig::validmpiconfig (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig14validMpiConfigEv", false]], "tensorrt_llm::runtime::worldconfig::worldconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", false]], "text (tensorrt_llm.llmapi.completionoutput attribute)": [[71, "tensorrt_llm.llmapi.CompletionOutput.text", false]], "text_diff (tensorrt_llm.llmapi.completionoutput attribute)": [[71, "tensorrt_llm.llmapi.CompletionOutput.text_diff", false]], "text_diff (tensorrt_llm.llmapi.completionoutput property)": [[71, "id4", false]], "timestepembedding (class in tensorrt_llm.layers.embedding)": [[84, "tensorrt_llm.layers.embedding.TimestepEmbedding", false]], "timesteps (class in tensorrt_llm.layers.embedding)": [[84, "tensorrt_llm.layers.embedding.Timesteps", false]], "to_dict() (tensorrt_llm.llmapi.buildconfig method)": [[71, "tensorrt_llm.llmapi.BuildConfig.to_dict", false]], "to_dict() (tensorrt_llm.llmapi.calibconfig method)": [[71, "tensorrt_llm.llmapi.CalibConfig.to_dict", false]], "to_dict() (tensorrt_llm.llmapi.quantconfig method)": [[71, "tensorrt_llm.llmapi.QuantConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.chatglmconfig method)": [[85, "tensorrt_llm.models.ChatGLMConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.cogvlmconfig method)": [[85, "tensorrt_llm.models.CogVLMConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.dbrxconfig method)": [[85, "tensorrt_llm.models.DbrxConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.falconconfig method)": [[85, "tensorrt_llm.models.FalconConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.gemmaconfig method)": [[85, "tensorrt_llm.models.GemmaConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.gptconfig method)": [[85, "tensorrt_llm.models.GPTConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.gptjconfig method)": [[85, "tensorrt_llm.models.GPTJConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.llamaconfig method)": [[85, "tensorrt_llm.models.LLaMAConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.medusaconfig method)": [[85, "tensorrt_llm.models.MedusaConfig.to_dict", false]], "to_dict() (tensorrt_llm.models.pretrainedconfig method)": [[85, "tensorrt_llm.models.PretrainedConfig.to_dict", false]], "to_json_file() (tensorrt_llm.models.pretrainedconfig method)": [[85, "tensorrt_llm.models.PretrainedConfig.to_json_file", false]], "to_layer_quant_config() (tensorrt_llm.models.pretrainedconfig method)": [[85, "tensorrt_llm.models.PretrainedConfig.to_layer_quant_config", false]], "to_legacy_setting() (tensorrt_llm.plugin.pluginconfig method)": [[86, "tensorrt_llm.plugin.PluginConfig.to_legacy_setting", false]], "token_drop() (tensorrt_llm.layers.embedding.labelembedding method)": [[84, "tensorrt_llm.layers.embedding.LabelEmbedding.token_drop", false]], "token_end (tensorrt_llm.llmapi.kvcacheretentionconfig.tokenrangeretentionconfig property)": [[71, "tensorrt_llm.llmapi.KvCacheRetentionConfig.TokenRangeRetentionConfig.token_end", false]], "token_ids (tensorrt_llm.llmapi.completionoutput attribute)": [[71, "tensorrt_llm.llmapi.CompletionOutput.token_ids", false]], "token_ids_diff (tensorrt_llm.llmapi.completionoutput attribute)": [[71, "tensorrt_llm.llmapi.CompletionOutput.token_ids_diff", false]], "token_ids_diff (tensorrt_llm.llmapi.completionoutput property)": [[71, "id5", false]], "token_range_retention_configs (tensorrt_llm.llmapi.kvcacheretentionconfig property)": [[71, "tensorrt_llm.llmapi.KvCacheRetentionConfig.token_range_retention_configs", false]], "token_start (tensorrt_llm.llmapi.kvcacheretentionconfig.tokenrangeretentionconfig property)": [[71, "tensorrt_llm.llmapi.KvCacheRetentionConfig.TokenRangeRetentionConfig.token_start", false]], "tokenizer (tensorrt_llm.llmapi.llm attribute)": [[71, "tensorrt_llm.llmapi.LLM.tokenizer", false]], "tokenizer (tensorrt_llm.llmapi.llm property)": [[71, "id1", false]], "tokenizer_image_token() (tensorrt_llm.runtime.multimodalmodelrunner static method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.tokenizer_image_token", false]], "tokenizer_max_seq_length (tensorrt_llm.llmapi.calibconfig attribute)": [[71, "tensorrt_llm.llmapi.CalibConfig.tokenizer_max_seq_length", false]], "tokens_per_block (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.tokens_per_block", false]], "tokens_per_block (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.tokens_per_block", false]], "top_k (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.top_k", false]], "top_k (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.top_k", false]], "top_p (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.top_p", false]], "top_p (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.top_p", false]], "top_p_decay (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.top_p_decay", false]], "top_p_decay (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.top_p_decay", false]], "top_p_min (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.top_p_min", false]], "top_p_min (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.top_p_min", false]], "top_p_reset_ids (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.top_p_reset_ids", false]], "top_p_reset_ids (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.top_p_reset_ids", false]], "topk() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.topk", false]], "torch_compile_config (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.torch_compile_config", false]], "torchcompileconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.TorchCompileConfig", false]], "torchllmargs (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs", false]], "tp_split_dim() (tensorrt_llm.layers.linear.linear class method)": [[84, "tensorrt_llm.layers.linear.Linear.tp_split_dim", false]], "tp_split_dim() (tensorrt_llm.layers.linear.linearbase class method)": [[84, "tensorrt_llm.layers.linear.LinearBase.tp_split_dim", false]], "tp_split_dim() (tensorrt_llm.layers.linear.rowlinear class method)": [[84, "tensorrt_llm.layers.linear.RowLinear.tp_split_dim", false]], "transfer_mode (tensorrt_llm.llmapi.kvcacheretentionconfig property)": [[71, "tensorrt_llm.llmapi.KvCacheRetentionConfig.transfer_mode", false]], "transpose() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.transpose", false]], "transpose() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.transpose", false]], "trtllm-bench command line option": [[33, "cmdoption-trtllm-bench-log_level", false], [33, "cmdoption-trtllm-bench-m", false], [33, "cmdoption-trtllm-bench-model_path", false], [33, "cmdoption-trtllm-bench-w", false]], "trtllm-bench-build command line option": [[33, "cmdoption-trtllm-bench-build-dataset", false], [33, "cmdoption-trtllm-bench-build-max_batch_size", false], [33, "cmdoption-trtllm-bench-build-max_num_tokens", false], [33, "cmdoption-trtllm-bench-build-max_seq_len", false], [33, "cmdoption-trtllm-bench-build-no_weights_loading", false], [33, "cmdoption-trtllm-bench-build-pp", false], [33, "cmdoption-trtllm-bench-build-q", false], [33, "cmdoption-trtllm-bench-build-target_input_len", false], [33, "cmdoption-trtllm-bench-build-target_output_len", false], [33, "cmdoption-trtllm-bench-build-tp", false], [33, "cmdoption-trtllm-bench-build-trust_remote_code", false]], "trtllm-bench-latency command line option": [[33, "cmdoption-trtllm-bench-latency-backend", false], [33, "cmdoption-trtllm-bench-latency-beam_width", false], [33, "cmdoption-trtllm-bench-latency-concurrency", false], [33, "cmdoption-trtllm-bench-latency-dataset", false], [33, "cmdoption-trtllm-bench-latency-engine_dir", false], [33, "cmdoption-trtllm-bench-latency-ep", false], [33, "cmdoption-trtllm-bench-latency-iteration_log", false], [33, "cmdoption-trtllm-bench-latency-kv_cache_free_gpu_mem_fraction", false], [33, "cmdoption-trtllm-bench-latency-max_input_len", false], [33, "cmdoption-trtllm-bench-latency-max_seq_len", false], [33, "cmdoption-trtllm-bench-latency-medusa_choices", false], [33, "cmdoption-trtllm-bench-latency-modality", false], [33, "cmdoption-trtllm-bench-latency-num_requests", false], [33, "cmdoption-trtllm-bench-latency-pp", false], [33, "cmdoption-trtllm-bench-latency-report_json", false], [33, "cmdoption-trtllm-bench-latency-tp", false], [33, "cmdoption-trtllm-bench-latency-warmup", false]], "trtllm-bench-throughput command line option": [[33, "cmdoption-trtllm-bench-throughput-backend", false], [33, "cmdoption-trtllm-bench-throughput-beam_width", false], [33, "cmdoption-trtllm-bench-throughput-cluster_size", false], [33, "cmdoption-trtllm-bench-throughput-concurrency", false], [33, "cmdoption-trtllm-bench-throughput-dataset", false], [33, "cmdoption-trtllm-bench-throughput-enable_chunked_context", false], [33, "cmdoption-trtllm-bench-throughput-engine_dir", false], [33, "cmdoption-trtllm-bench-throughput-eos_id", false], [33, "cmdoption-trtllm-bench-throughput-ep", false], [33, "cmdoption-trtllm-bench-throughput-extra_llm_api_options", false], [33, "cmdoption-trtllm-bench-throughput-iteration_log", false], [33, "cmdoption-trtllm-bench-throughput-kv_cache_free_gpu_mem_fraction", false], [33, "cmdoption-trtllm-bench-throughput-max_batch_size", false], [33, "cmdoption-trtllm-bench-throughput-max_input_len", false], [33, "cmdoption-trtllm-bench-throughput-max_num_tokens", false], [33, "cmdoption-trtllm-bench-throughput-max_seq_len", false], [33, "cmdoption-trtllm-bench-throughput-modality", false], [33, "cmdoption-trtllm-bench-throughput-num_requests", false], [33, "cmdoption-trtllm-bench-throughput-output_json", false], [33, "cmdoption-trtllm-bench-throughput-pp", false], [33, "cmdoption-trtllm-bench-throughput-report_json", false], [33, "cmdoption-trtllm-bench-throughput-request_json", false], [33, "cmdoption-trtllm-bench-throughput-scheduler_policy", false], [33, "cmdoption-trtllm-bench-throughput-streaming", false], [33, "cmdoption-trtllm-bench-throughput-target_input_len", false], [33, "cmdoption-trtllm-bench-throughput-target_output_len", false], [33, "cmdoption-trtllm-bench-throughput-tp", false], [33, "cmdoption-trtllm-bench-throughput-warmup", false]], "trtllm-serve-disaggregated command line option": [[35, "cmdoption-trtllm-serve-disaggregated-c", false], [35, "cmdoption-trtllm-serve-disaggregated-l", false], [35, "cmdoption-trtllm-serve-disaggregated-m", false], [35, "cmdoption-trtllm-serve-disaggregated-r", false], [35, "cmdoption-trtllm-serve-disaggregated-t", false]], "trtllm-serve-disaggregated_mpi_worker command line option": [[35, "cmdoption-trtllm-serve-disaggregated_mpi_worker-c", false], [35, "cmdoption-trtllm-serve-disaggregated_mpi_worker-log_level", false]], "trtllm-serve-serve command line option": [[35, "cmdoption-trtllm-serve-serve-arg-MODEL", false], [35, "cmdoption-trtllm-serve-serve-backend", false], [35, "cmdoption-trtllm-serve-serve-cluster_size", false], [35, "cmdoption-trtllm-serve-serve-ep_size", false], [35, "cmdoption-trtllm-serve-serve-extra_llm_api_options", false], [35, "cmdoption-trtllm-serve-serve-gpus_per_node", false], [35, "cmdoption-trtllm-serve-serve-host", false], [35, "cmdoption-trtllm-serve-serve-kv_cache_free_gpu_memory_fraction", false], [35, "cmdoption-trtllm-serve-serve-log_level", false], [35, "cmdoption-trtllm-serve-serve-max_batch_size", false], [35, "cmdoption-trtllm-serve-serve-max_beam_width", false], [35, "cmdoption-trtllm-serve-serve-max_num_tokens", false], [35, "cmdoption-trtllm-serve-serve-max_seq_len", false], [35, "cmdoption-trtllm-serve-serve-metadata_server_config_file", false], [35, "cmdoption-trtllm-serve-serve-num_postprocess_workers", false], [35, "cmdoption-trtllm-serve-serve-port", false], [35, "cmdoption-trtllm-serve-serve-pp_size", false], [35, "cmdoption-trtllm-serve-serve-reasoning_parser", false], [35, "cmdoption-trtllm-serve-serve-server_role", false], [35, "cmdoption-trtllm-serve-serve-tokenizer", false], [35, "cmdoption-trtllm-serve-serve-tp_size", false], [35, "cmdoption-trtllm-serve-serve-trust_remote_code", false]], "trtllm_modules_to_hf_modules (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.trtllm_modules_to_hf_modules", false]], "trtllmargs (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs", false]], "truncate_prompt_tokens (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.truncate_prompt_tokens", false]], "twoshot (tensorrt_llm.functional.allreducestrategy attribute)": [[83, "tensorrt_llm.functional.AllReduceStrategy.TWOSHOT", false]], "ub (tensorrt_llm.functional.allreducestrategy attribute)": [[83, "tensorrt_llm.functional.AllReduceStrategy.UB", false]], "unary() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.unary", false]], "unbind() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.unbind", false]], "unbind() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.unbind", false]], "unfuse_qkv_projections() (tensorrt_llm.models.sd3transformer2dmodel method)": [[85, "tensorrt_llm.models.SD3Transformer2DModel.unfuse_qkv_projections", false]], "unpatchify() (tensorrt_llm.models.dit method)": [[85, "tensorrt_llm.models.DiT.unpatchify", false]], "unsqueeze() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.unsqueeze", false]], "unsqueeze() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.unsqueeze", false]], "update() (tensorrt_llm.llmapi.buildconfig method)": [[71, "tensorrt_llm.llmapi.BuildConfig.update", false]], "update() (tensorrt_llm.runtime.samplingconfig method)": [[88, "tensorrt_llm.runtime.SamplingConfig.update", false]], "update_from_dict() (tensorrt_llm.llmapi.buildconfig method)": [[71, "tensorrt_llm.llmapi.BuildConfig.update_from_dict", false]], "update_from_model_config() (tensorrt_llm.llmapi.mtpdecodingconfig method)": [[71, "tensorrt_llm.llmapi.MTPDecodingConfig.update_from_model_config", false]], "update_kv_cache_type() (tensorrt_llm.llmapi.buildconfig method)": [[71, "tensorrt_llm.llmapi.BuildConfig.update_kv_cache_type", false]], "update_output_ids_by_offset() (tensorrt_llm.runtime.generationsession method)": [[88, "tensorrt_llm.runtime.GenerationSession.update_output_ids_by_offset", false]], "update_strategy() (tensorrt_llm.functional.allreduceparams method)": [[83, "tensorrt_llm.functional.AllReduceParams.update_strategy", false]], "use_beam_hyps (tensorrt_llm.runtime.samplingconfig attribute)": [[88, "tensorrt_llm.runtime.SamplingConfig.use_beam_hyps", false]], "use_beam_search (tensorrt_llm.llmapi.samplingparams attribute)": [[71, "tensorrt_llm.llmapi.SamplingParams.use_beam_search", false]], "use_dynamic_tree (tensorrt_llm.llmapi.eagledecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.EagleDecodingConfig.use_dynamic_tree", false]], "use_gemm_allreduce_plugin (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.use_gemm_allreduce_plugin", false]], "use_gpt_attention_plugin (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.use_gpt_attention_plugin", false]], "use_kv_cache (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.use_kv_cache", false]], "use_lora() (tensorrt_llm.models.decodermodel method)": [[85, "tensorrt_llm.models.DecoderModel.use_lora", false]], "use_lora() (tensorrt_llm.models.encodermodel method)": [[85, "tensorrt_llm.models.EncoderModel.use_lora", false]], "use_lora() (tensorrt_llm.models.gemmaforcausallm method)": [[85, "tensorrt_llm.models.GemmaForCausalLM.use_lora", false]], "use_lora() (tensorrt_llm.models.gptforcausallm method)": [[85, "tensorrt_llm.models.GPTForCausalLM.use_lora", false]], "use_lora() (tensorrt_llm.models.llamaforcausallm method)": [[85, "tensorrt_llm.models.LLaMAForCausalLM.use_lora", false]], "use_lora() (tensorrt_llm.models.mllamaforcausallm method)": [[85, "tensorrt_llm.models.MLLaMAForCausalLM.use_lora", false]], "use_lora() (tensorrt_llm.models.phi3forcausallm method)": [[85, "tensorrt_llm.models.Phi3ForCausalLM.use_lora", false]], "use_lora() (tensorrt_llm.models.phiforcausallm method)": [[85, "tensorrt_llm.models.PhiForCausalLM.use_lora", false]], "use_lora_plugin (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.use_lora_plugin", false]], "use_lora_plugin (tensorrt_llm.runtime.modelrunner property)": [[88, "tensorrt_llm.runtime.ModelRunner.use_lora_plugin", false]], "use_mamba_conv1d_plugin (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.use_mamba_conv1d_plugin", false]], "use_meta_recipe (tensorrt_llm.llmapi.quantconfig attribute)": [[71, "tensorrt_llm.llmapi.QuantConfig.use_meta_recipe", false]], "use_mrope (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.use_mrope", false]], "use_mtp_vanilla (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.MTPDecodingConfig.use_mtp_vanilla", false]], "use_prompt_tuning() (tensorrt_llm.models.encodermodel method)": [[85, "tensorrt_llm.models.EncoderModel.use_prompt_tuning", false]], "use_refit (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.use_refit", false]], "use_relaxed_acceptance_for_thinking (tensorrt_llm.llmapi.mtpdecodingconfig attribute)": [[71, "tensorrt_llm.llmapi.MTPDecodingConfig.use_relaxed_acceptance_for_thinking", false]], "use_strip_plan (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.use_strip_plan", false]], "use_uvm (tensorrt_llm.llmapi.kvcacheconfig attribute)": [[71, "tensorrt_llm.llmapi.KvCacheConfig.use_uvm", false]], "user_provided (tensorrt_llm.models.speculativedecodingmode attribute)": [[85, "tensorrt_llm.models.SpeculativeDecodingMode.USER_PROVIDED", false]], "userprovideddecodingconfig (class in tensorrt_llm.llmapi)": [[71, "tensorrt_llm.llmapi.UserProvidedDecodingConfig", false]], "validate() (tensorrt_llm.llmapi.eagledecodingconfig method)": [[71, "tensorrt_llm.llmapi.EagleDecodingConfig.validate", false]], "validate_auto_parallel() (tensorrt_llm.llmapi.trtllmargs method)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.validate_auto_parallel", false]], "validate_checkpoint_format() (tensorrt_llm.llmapi.torchllmargs method)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.validate_checkpoint_format", false]], "validate_cuda_graph_config() (tensorrt_llm.llmapi.torchllmargs method)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.validate_cuda_graph_config", false]], "validate_cuda_graph_max_batch_size() (tensorrt_llm.llmapi.cudagraphconfig class method)": [[71, "tensorrt_llm.llmapi.CudaGraphConfig.validate_cuda_graph_max_batch_size", false]], "validate_enable_build_cache() (tensorrt_llm.llmapi.trtllmargs method)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.validate_enable_build_cache", false]], "validate_kv_cache_dtype() (tensorrt_llm.llmapi.trtllmargs method)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.validate_kv_cache_dtype", false]], "validate_load_balancer() (tensorrt_llm.llmapi.torchllmargs method)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.validate_load_balancer", false]], "validate_positive_values() (tensorrt_llm.llmapi.lookaheaddecodingconfig class method)": [[71, "tensorrt_llm.llmapi.LookaheadDecodingConfig.validate_positive_values", false]], "validate_quant_config() (tensorrt_llm.llmapi.trtllmargs class method)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.validate_quant_config", false]], "validate_stream_interval() (tensorrt_llm.llmapi.torchllmargs method)": [[71, "tensorrt_llm.llmapi.TorchLlmArgs.validate_stream_interval", false]], "verbatim (tensorrt_llm.models.gemmaconfig attribute)": [[85, "tensorrt_llm.models.GemmaConfig.VERBATIM", false]], "video_preprocess() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.video_preprocess", false]], "view() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.view", false]], "view() (tensorrt_llm.functional.tensor method)": [[83, "tensorrt_llm.functional.Tensor.view", false]], "view() (tensorrt_llm.runtime.tensorinfo method)": [[88, "tensorrt_llm.runtime.TensorInfo.view", false]], "visual_engine_dir (tensorrt_llm.runtime.multimodalmodelrunner property)": [[88, "tensorrt_llm.runtime.MultimodalModelRunner.visual_engine_dir", false]], "visualize_network (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.visualize_network", false]], "vocab_size (tensorrt_llm.runtime.generationsession property)": [[88, "tensorrt_llm.runtime.GenerationSession.vocab_size", false]], "vocab_size (tensorrt_llm.runtime.modelconfig attribute)": [[88, "tensorrt_llm.runtime.ModelConfig.vocab_size", false]], "vocab_size (tensorrt_llm.runtime.modelrunner property)": [[88, "tensorrt_llm.runtime.ModelRunner.vocab_size", false]], "vocab_size (tensorrt_llm.runtime.modelrunnercpp property)": [[88, "tensorrt_llm.runtime.ModelRunnerCpp.vocab_size", false]], "vocab_size_padded (tensorrt_llm.runtime.modelrunner property)": [[88, "tensorrt_llm.runtime.ModelRunner.vocab_size_padded", false]], "vocab_size_padded (tensorrt_llm.runtime.modelrunnercpp property)": [[88, "tensorrt_llm.runtime.ModelRunnerCpp.vocab_size_padded", false]], "w4a16 (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.W4A16", false]], "w4a16_awq (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.W4A16_AWQ", false]], "w4a16_gptq (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.W4A16_GPTQ", false]], "w4a8_awq (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.W4A8_AWQ", false]], "w4a8_mxfp4_fp8 (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.W4A8_MXFP4_FP8", false]], "w4a8_qserve_per_channel (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.W4A8_QSERVE_PER_CHANNEL", false]], "w4a8_qserve_per_group (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.W4A8_QSERVE_PER_GROUP", false]], "w8a16 (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.W8A16", false]], "w8a16_gptq (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.W8A16_GPTQ", false]], "w8a8_sq_per_channel (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.W8A8_SQ_PER_CHANNEL", false]], "w8a8_sq_per_channel_per_tensor_plugin (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.W8A8_SQ_PER_CHANNEL_PER_TENSOR_PLUGIN", false]], "w8a8_sq_per_channel_per_token_plugin (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.W8A8_SQ_PER_CHANNEL_PER_TOKEN_PLUGIN", false]], "w8a8_sq_per_tensor_per_token_plugin (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.W8A8_SQ_PER_TENSOR_PER_TOKEN_PLUGIN", false]], "w8a8_sq_per_tensor_plugin (tensorrt_llm.llmapi.quantalgo attribute)": [[71, "tensorrt_llm.llmapi.QuantAlgo.W8A8_SQ_PER_TENSOR_PLUGIN", false]], "weight_loader() (tensorrt_llm.layers.attention.deepseekv2attention method)": [[84, "tensorrt_llm.layers.attention.DeepseekV2Attention.weight_loader", false]], "weight_loader() (tensorrt_llm.layers.embedding.embedding method)": [[84, "tensorrt_llm.layers.embedding.Embedding.weight_loader", false]], "weight_loader() (tensorrt_llm.layers.linear.linearbase method)": [[84, "tensorrt_llm.layers.linear.LinearBase.weight_loader", false]], "weight_sparsity (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.weight_sparsity", false]], "weight_streaming (tensorrt_llm.llmapi.buildconfig attribute)": [[71, "tensorrt_llm.llmapi.BuildConfig.weight_streaming", false]], "where() (in module tensorrt_llm.functional)": [[83, "tensorrt_llm.functional.where", false]], "whisperencoder (class in tensorrt_llm.models)": [[85, "tensorrt_llm.models.WhisperEncoder", false]], "workspace (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "tensorrt_llm.llmapi.TrtLlmArgs.workspace", false]], "wrapped_property (tensorrt_llm.llmapi.torchllmargs attribute)": [[71, "id11", false], [71, "id14", false], [71, "id17", false], [71, "tensorrt_llm.llmapi.TorchLlmArgs.wrapped_property", false]], "wrapped_property (tensorrt_llm.llmapi.trtllmargs attribute)": [[71, "id20", false], [71, "id23", false], [71, "id26", false], [71, "id29", false], [71, "id32", false], [71, "tensorrt_llm.llmapi.TrtLlmArgs.wrapped_property", false]], "yarn (tensorrt_llm.functional.positionembeddingtype attribute)": [[83, "tensorrt_llm.functional.PositionEmbeddingType.yarn", false]], "yarn (tensorrt_llm.functional.rotaryscalingtype attribute)": [[83, "tensorrt_llm.functional.RotaryScalingType.yarn", false]]}, "objects": {"": [[1, 0, 1, "c.FMT_DIM", "FMT_DIM"], [1, 0, 1, "c.SET_FROM_OPTIONAL", "SET_FROM_OPTIONAL"], [1, 1, 1, "_CPPv48nvinfer1", "nvinfer1"], [0, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [0, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [0, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [0, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [0, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [0, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [0, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [0, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [1, 1, 1, "_CPPv412tensorrt_llm", "tensorrt_llm"], [0, 1, 1, "_CPPv4N12tensorrt_llm13batch_managerE", "tensorrt_llm::batch_manager"], [1, 1, 1, "_CPPv4N12tensorrt_llm13batch_managerE", "tensorrt_llm::batch_manager"], [1, 1, 1, "_CPPv4N12tensorrt_llm13batch_managerE", "tensorrt_llm::batch_manager"], [1, 1, 1, "_CPPv4N12tensorrt_llm13batch_managerE", "tensorrt_llm::batch_manager"], [1, 1, 1, "_CPPv4N12tensorrt_llm13batch_managerE", "tensorrt_llm::batch_manager"], [0, 1, 1, "_CPPv4N12tensorrt_llm13batch_manager16kv_cache_managerE", "tensorrt_llm::batch_manager::kv_cache_manager"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executorE", "tensorrt_llm::executor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executorE", "tensorrt_llm::executor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executorE", "tensorrt_llm::executor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executorE", "tensorrt_llm::executor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executorE", "tensorrt_llm::executor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executorE", "tensorrt_llm::executor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executorE", "tensorrt_llm::executor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executorE", "tensorrt_llm::executor"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutputE", "tensorrt_llm::executor::AdditionalModelOutput"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutput21AdditionalModelOutputENSt6stringEb", "tensorrt_llm::executor::AdditionalModelOutput::AdditionalModelOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutput21AdditionalModelOutputENSt6stringEb", "tensorrt_llm::executor::AdditionalModelOutput::AdditionalModelOutput::gatherContext"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutput21AdditionalModelOutputENSt6stringEb", "tensorrt_llm::executor::AdditionalModelOutput::AdditionalModelOutput::name"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutput13gatherContextE", "tensorrt_llm::executor::AdditionalModelOutput::gatherContext"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21AdditionalModelOutput4nameE", "tensorrt_llm::executor::AdditionalModelOutput::name"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor21AdditionalModelOutputeqERK21AdditionalModelOutput", "tensorrt_llm::executor::AdditionalModelOutput::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor21AdditionalModelOutputeqERK21AdditionalModelOutput", "tensorrt_llm::executor::AdditionalModelOutput::operator==::other"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputE", "tensorrt_llm::executor::AdditionalOutput"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputENSt6stringE6Tensor", "tensorrt_llm::executor::AdditionalOutput::AdditionalOutput"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputERK16AdditionalOutput", "tensorrt_llm::executor::AdditionalOutput::AdditionalOutput"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputERR16AdditionalOutput", "tensorrt_llm::executor::AdditionalOutput::AdditionalOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputENSt6stringE6Tensor", "tensorrt_llm::executor::AdditionalOutput::AdditionalOutput::name"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputERK16AdditionalOutput", "tensorrt_llm::executor::AdditionalOutput::AdditionalOutput::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputERR16AdditionalOutput", "tensorrt_llm::executor::AdditionalOutput::AdditionalOutput::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput16AdditionalOutputENSt6stringE6Tensor", "tensorrt_llm::executor::AdditionalOutput::AdditionalOutput::output"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput4nameE", "tensorrt_llm::executor::AdditionalOutput::name"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputaSERK16AdditionalOutput", "tensorrt_llm::executor::AdditionalOutput::operator="], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputaSERR16AdditionalOutput", "tensorrt_llm::executor::AdditionalOutput::operator="], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputaSERK16AdditionalOutput", "tensorrt_llm::executor::AdditionalOutput::operator=::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputaSERR16AdditionalOutput", "tensorrt_llm::executor::AdditionalOutput::operator=::other"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutput6outputE", "tensorrt_llm::executor::AdditionalOutput::output"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor16AdditionalOutputD0Ev", "tensorrt_llm::executor::AdditionalOutput::~AdditionalOutput"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12BatchingTypeE", "tensorrt_llm::executor::BatchingType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12BatchingType9kINFLIGHTE", "tensorrt_llm::executor::BatchingType::kINFLIGHT"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12BatchingType7kSTATICE", "tensorrt_llm::executor::BatchingType::kSTATIC"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor10BeamTokensE", "tensorrt_llm::executor::BeamTokens"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor10BufferViewE", "tensorrt_llm::executor::BufferView"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfigE", "tensorrt_llm::executor::CacheTransceiverConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig11BackendTypeE", "tensorrt_llm::executor::CacheTransceiverConfig::BackendType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig11BackendType7DEFAULTE", "tensorrt_llm::executor::CacheTransceiverConfig::BackendType::DEFAULT"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig11BackendType3MPIE", "tensorrt_llm::executor::CacheTransceiverConfig::BackendType::MPI"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig11BackendType4NIXLE", "tensorrt_llm::executor::CacheTransceiverConfig::BackendType::NIXL"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig11BackendType3UCXE", "tensorrt_llm::executor::CacheTransceiverConfig::BackendType::UCX"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig22CacheTransceiverConfigENSt8optionalI11BackendTypeEENSt8optionalI6size_tEE", "tensorrt_llm::executor::CacheTransceiverConfig::CacheTransceiverConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig22CacheTransceiverConfigENSt8optionalI11BackendTypeEENSt8optionalI6size_tEE", "tensorrt_llm::executor::CacheTransceiverConfig::CacheTransceiverConfig::backendType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig22CacheTransceiverConfigENSt8optionalI11BackendTypeEENSt8optionalI6size_tEE", "tensorrt_llm::executor::CacheTransceiverConfig::CacheTransceiverConfig::maxNumTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22CacheTransceiverConfig14getBackendTypeEv", "tensorrt_llm::executor::CacheTransceiverConfig::getBackendType"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22CacheTransceiverConfig20getMaxTokensInBufferEv", "tensorrt_llm::executor::CacheTransceiverConfig::getMaxTokensInBuffer"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig12mBackendTypeE", "tensorrt_llm::executor::CacheTransceiverConfig::mBackendType"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig18mMaxTokensInBufferE", "tensorrt_llm::executor::CacheTransceiverConfig::mMaxTokensInBuffer"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22CacheTransceiverConfigeqERK22CacheTransceiverConfig", "tensorrt_llm::executor::CacheTransceiverConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor22CacheTransceiverConfigeqERK22CacheTransceiverConfig", "tensorrt_llm::executor::CacheTransceiverConfig::operator==::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig14setBackendTypeENSt8optionalI11BackendTypeEE", "tensorrt_llm::executor::CacheTransceiverConfig::setBackendType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig14setBackendTypeENSt8optionalI11BackendTypeEE", "tensorrt_llm::executor::CacheTransceiverConfig::setBackendType::backendType"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig20setMaxTokensInBufferENSt8optionalI6size_tEE", "tensorrt_llm::executor::CacheTransceiverConfig::setMaxTokensInBuffer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22CacheTransceiverConfig20setMaxTokensInBufferENSt8optionalI6size_tEE", "tensorrt_llm::executor::CacheTransceiverConfig::setMaxTokensInBuffer::maxTokensInBuffer"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicyE", "tensorrt_llm::executor::CapacitySchedulerPolicy"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicy20kGUARANTEED_NO_EVICTE", "tensorrt_llm::executor::CapacitySchedulerPolicy::kGUARANTEED_NO_EVICT"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicy16kMAX_UTILIZATIONE", "tensorrt_llm::executor::CapacitySchedulerPolicy::kMAX_UTILIZATION"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicy13kSTATIC_BATCHE", "tensorrt_llm::executor::CapacitySchedulerPolicy::kSTATIC_BATCH"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor17CommunicationModeE", "tensorrt_llm::executor::CommunicationMode"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor17CommunicationMode7kLEADERE", "tensorrt_llm::executor::CommunicationMode::kLEADER"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor17CommunicationMode13kORCHESTRATORE", "tensorrt_llm::executor::CommunicationMode::kORCHESTRATOR"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor17CommunicationTypeE", "tensorrt_llm::executor::CommunicationType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor17CommunicationType4kMPIE", "tensorrt_llm::executor::CommunicationType::kMPI"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicyE", "tensorrt_llm::executor::ContextChunkingPolicy"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicy15kEQUAL_PROGRESSE", "tensorrt_llm::executor::ContextChunkingPolicy::kEQUAL_PROGRESS"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicy24kFIRST_COME_FIRST_SERVEDE", "tensorrt_llm::executor::ContextChunkingPolicy::kFIRST_COME_FIRST_SERVED"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsE", "tensorrt_llm::executor::ContextPhaseParams"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypePvNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeRKNSt6vectorIcEENSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsERK18ContextPhaseParams", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsERR18ContextPhaseParams", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::draftTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypePvNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::draftTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeRKNSt6vectorIcEENSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::draftTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::firstGenTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypePvNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::firstGenTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeRKNSt6vectorIcEENSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::firstGenTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::reqId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypePvNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::reqId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeRKNSt6vectorIcEENSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::reqId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypeRKNSt6vectorIcEENSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::serializedState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens13RequestIdTypePvNSt8optionalI9VecTokensEE", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::state"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams13RequestIdTypeE", "tensorrt_llm::executor::ContextPhaseParams::RequestIdType"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams8StatePtrE", "tensorrt_llm::executor::ContextPhaseParams::StatePtr"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams7deleterEPKv", "tensorrt_llm::executor::ContextPhaseParams::deleter"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams7deleterEPKv", "tensorrt_llm::executor::ContextPhaseParams::deleter::data"], [0, 3, 1, "_CPPv4NKR12tensorrt_llm8executor18ContextPhaseParams14getDraftTokensEv", "tensorrt_llm::executor::ContextPhaseParams::getDraftTokens"], [0, 3, 1, "_CPPv4NKR12tensorrt_llm8executor18ContextPhaseParams17getFirstGenTokensEv", "tensorrt_llm::executor::ContextPhaseParams::getFirstGenTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParams8getReqIdEv", "tensorrt_llm::executor::ContextPhaseParams::getReqId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParams18getSerializedStateEv", "tensorrt_llm::executor::ContextPhaseParams::getSerializedState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams8getStateEv", "tensorrt_llm::executor::ContextPhaseParams::getState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParams8getStateEv", "tensorrt_llm::executor::ContextPhaseParams::getState"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams12mDraftTokensE", "tensorrt_llm::executor::ContextPhaseParams::mDraftTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams15mFirstGenTokensE", "tensorrt_llm::executor::ContextPhaseParams::mFirstGenTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams6mReqIdE", "tensorrt_llm::executor::ContextPhaseParams::mReqId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams6mStateE", "tensorrt_llm::executor::ContextPhaseParams::mState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsaSERK18ContextPhaseParams", "tensorrt_llm::executor::ContextPhaseParams::operator="], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsaSERR18ContextPhaseParams", "tensorrt_llm::executor::ContextPhaseParams::operator="], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParamseqERK18ContextPhaseParams", "tensorrt_llm::executor::ContextPhaseParams::operator=="], [0, 3, 1, "_CPPv4NO12tensorrt_llm8executor18ContextPhaseParams17popFirstGenTokensEv", "tensorrt_llm::executor::ContextPhaseParams::popFirstGenTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams12releaseStateEv", "tensorrt_llm::executor::ContextPhaseParams::releaseState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsD0Ev", "tensorrt_llm::executor::ContextPhaseParams::~ContextPhaseParams"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverStateE", "tensorrt_llm::executor::DataTransceiverState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState20DataTransceiverStateEN8kv_cache10CacheStateEN8kv_cache9CommStateE", "tensorrt_llm::executor::DataTransceiverState::DataTransceiverState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState20DataTransceiverStateEv", "tensorrt_llm::executor::DataTransceiverState::DataTransceiverState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState20DataTransceiverStateEN8kv_cache10CacheStateEN8kv_cache9CommStateE", "tensorrt_llm::executor::DataTransceiverState::DataTransceiverState::cacheState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState20DataTransceiverStateEN8kv_cache10CacheStateEN8kv_cache9CommStateE", "tensorrt_llm::executor::DataTransceiverState::DataTransceiverState::commState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverState13getCacheStateEv", "tensorrt_llm::executor::DataTransceiverState::getCacheState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverState12getCommStateEv", "tensorrt_llm::executor::DataTransceiverState::getCommState"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState11mCacheStateE", "tensorrt_llm::executor::DataTransceiverState::mCacheState"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState10mCommStateE", "tensorrt_llm::executor::DataTransceiverState::mCommState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverStateeqERK20DataTransceiverState", "tensorrt_llm::executor::DataTransceiverState::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverStateeqERK20DataTransceiverState", "tensorrt_llm::executor::DataTransceiverState::operator==::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState13setCacheStateEN8kv_cache10CacheStateE", "tensorrt_llm::executor::DataTransceiverState::setCacheState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState13setCacheStateEN8kv_cache10CacheStateE", "tensorrt_llm::executor::DataTransceiverState::setCacheState::state"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState12setCommStateEN8kv_cache9CommStateE", "tensorrt_llm::executor::DataTransceiverState::setCommState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20DataTransceiverState12setCommStateEN8kv_cache9CommStateE", "tensorrt_llm::executor::DataTransceiverState::setCommState::state"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20DataTransceiverState8toStringEv", "tensorrt_llm::executor::DataTransceiverState::toString"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8DataTypeE", "tensorrt_llm::executor::DataType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType5kBF16E", "tensorrt_llm::executor::DataType::kBF16"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType5kBOOLE", "tensorrt_llm::executor::DataType::kBOOL"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType5kFP16E", "tensorrt_llm::executor::DataType::kFP16"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType5kFP32E", "tensorrt_llm::executor::DataType::kFP32"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType4kFP8E", "tensorrt_llm::executor::DataType::kFP8"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType6kINT32E", "tensorrt_llm::executor::DataType::kINT32"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType6kINT64E", "tensorrt_llm::executor::DataType::kINT64"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType5kINT8E", "tensorrt_llm::executor::DataType::kINT8"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType6kUINT8E", "tensorrt_llm::executor::DataType::kUINT8"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8DataType8kUNKNOWNE", "tensorrt_llm::executor::DataType::kUNKNOWN"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfigE", "tensorrt_llm::executor::DebugConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig11DebugConfigEbb9StringVec10SizeType32", "tensorrt_llm::executor::DebugConfig::DebugConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig11DebugConfigEbb9StringVec10SizeType32", "tensorrt_llm::executor::DebugConfig::DebugConfig::debugInputTensors"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig11DebugConfigEbb9StringVec10SizeType32", "tensorrt_llm::executor::DebugConfig::DebugConfig::debugOutputTensors"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig11DebugConfigEbb9StringVec10SizeType32", "tensorrt_llm::executor::DebugConfig::DebugConfig::debugTensorNames"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig11DebugConfigEbb9StringVec10SizeType32", "tensorrt_llm::executor::DebugConfig::DebugConfig::debugTensorsMaxIterations"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig9StringVecE", "tensorrt_llm::executor::DebugConfig::StringVec"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11DebugConfig20getDebugInputTensorsEv", "tensorrt_llm::executor::DebugConfig::getDebugInputTensors"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11DebugConfig21getDebugOutputTensorsEv", "tensorrt_llm::executor::DebugConfig::getDebugOutputTensors"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11DebugConfig19getDebugTensorNamesEv", "tensorrt_llm::executor::DebugConfig::getDebugTensorNames"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11DebugConfig28getDebugTensorsMaxIterationsEv", "tensorrt_llm::executor::DebugConfig::getDebugTensorsMaxIterations"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig18mDebugInputTensorsE", "tensorrt_llm::executor::DebugConfig::mDebugInputTensors"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig19mDebugOutputTensorsE", "tensorrt_llm::executor::DebugConfig::mDebugOutputTensors"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig17mDebugTensorNamesE", "tensorrt_llm::executor::DebugConfig::mDebugTensorNames"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig26mDebugTensorsMaxIterationsE", "tensorrt_llm::executor::DebugConfig::mDebugTensorsMaxIterations"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11DebugConfigeqERK11DebugConfig", "tensorrt_llm::executor::DebugConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor11DebugConfigeqERK11DebugConfig", "tensorrt_llm::executor::DebugConfig::operator==::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig20setDebugInputTensorsEb", "tensorrt_llm::executor::DebugConfig::setDebugInputTensors"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig20setDebugInputTensorsEb", "tensorrt_llm::executor::DebugConfig::setDebugInputTensors::debugInputTensors"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig21setDebugOutputTensorsEb", "tensorrt_llm::executor::DebugConfig::setDebugOutputTensors"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig21setDebugOutputTensorsEb", "tensorrt_llm::executor::DebugConfig::setDebugOutputTensors::debugOutputTensors"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig19setDebugTensorNamesERK9StringVec", "tensorrt_llm::executor::DebugConfig::setDebugTensorNames"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig19setDebugTensorNamesERK9StringVec", "tensorrt_llm::executor::DebugConfig::setDebugTensorNames::debugTensorNames"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig28setDebugTensorsMaxIterationsE10SizeType32", "tensorrt_llm::executor::DebugConfig::setDebugTensorsMaxIterations"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig28setDebugTensorsMaxIterationsE10SizeType32", "tensorrt_llm::executor::DebugConfig::setDebugTensorsMaxIterations::debugTensorsMaxIterations"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor24DebugTensorsPerIterationE", "tensorrt_llm::executor::DebugTensorsPerIteration"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor24DebugTensorsPerIteration12debugTensorsE", "tensorrt_llm::executor::DebugTensorsPerIteration::debugTensors"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor24DebugTensorsPerIteration4iterE", "tensorrt_llm::executor::DebugTensorsPerIteration::iter"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfigE", "tensorrt_llm::executor::DecodingConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14DecodingConfigENSt8optionalI12DecodingModeEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI13MedusaChoicesEENSt8optionalI11EagleConfigEE", "tensorrt_llm::executor::DecodingConfig::DecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14DecodingConfigENSt8optionalI12DecodingModeEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI13MedusaChoicesEENSt8optionalI11EagleConfigEE", "tensorrt_llm::executor::DecodingConfig::DecodingConfig::decodingMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14DecodingConfigENSt8optionalI12DecodingModeEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI13MedusaChoicesEENSt8optionalI11EagleConfigEE", "tensorrt_llm::executor::DecodingConfig::DecodingConfig::eagleConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14DecodingConfigENSt8optionalI12DecodingModeEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI13MedusaChoicesEENSt8optionalI11EagleConfigEE", "tensorrt_llm::executor::DecodingConfig::DecodingConfig::lookaheadDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14DecodingConfigENSt8optionalI12DecodingModeEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI13MedusaChoicesEENSt8optionalI11EagleConfigEE", "tensorrt_llm::executor::DecodingConfig::DecodingConfig::medusaChoices"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig31enableSeamlessLookaheadDecodingEv", "tensorrt_llm::executor::DecodingConfig::enableSeamlessLookaheadDecoding"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig15getDecodingModeEv", "tensorrt_llm::executor::DecodingConfig::getDecodingMode"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig14getEagleConfigEv", "tensorrt_llm::executor::DecodingConfig::getEagleConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig26getLookaheadDecodingConfigEv", "tensorrt_llm::executor::DecodingConfig::getLookaheadDecodingConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig33getLookaheadDecodingMaxNumRequestEv", "tensorrt_llm::executor::DecodingConfig::getLookaheadDecodingMaxNumRequest"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig16getMedusaChoicesEv", "tensorrt_llm::executor::DecodingConfig::getMedusaChoices"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig13mDecodingModeE", "tensorrt_llm::executor::DecodingConfig::mDecodingMode"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig12mEagleConfigE", "tensorrt_llm::executor::DecodingConfig::mEagleConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig24mLookaheadDecodingConfigE", "tensorrt_llm::executor::DecodingConfig::mLookaheadDecodingConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig31mLookaheadDecodingMaxNumRequestE", "tensorrt_llm::executor::DecodingConfig::mLookaheadDecodingMaxNumRequest"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14mMedusaChoicesE", "tensorrt_llm::executor::DecodingConfig::mMedusaChoices"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfigeqERK14DecodingConfig", "tensorrt_llm::executor::DecodingConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfigeqERK14DecodingConfig", "tensorrt_llm::executor::DecodingConfig::operator==::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig15setDecodingModeERK12DecodingMode", "tensorrt_llm::executor::DecodingConfig::setDecodingMode"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14setEagleConfigERK11EagleConfig", "tensorrt_llm::executor::DecodingConfig::setEagleConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig26setLookaheadDecodingConfigERK23LookaheadDecodingConfig", "tensorrt_llm::executor::DecodingConfig::setLookaheadDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig26setLookaheadDecodingConfigERK23LookaheadDecodingConfig", "tensorrt_llm::executor::DecodingConfig::setLookaheadDecodingConfig::lookaheadDecodingConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig16setMedusaChoicesERK13MedusaChoices", "tensorrt_llm::executor::DecodingConfig::setMedusaChoices"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor12DecodingModeE", "tensorrt_llm::executor::DecodingMode"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode4AutoEv", "tensorrt_llm::executor::DecodingMode::Auto"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode10BeamSearchEv", "tensorrt_llm::executor::DecodingMode::BeamSearch"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12DecodingModeE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::DecodingMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12DecodingModeE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::DecodingMode::state"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode5EagleEv", "tensorrt_llm::executor::DecodingMode::Eagle"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode19ExplicitDraftTokensEv", "tensorrt_llm::executor::DecodingMode::ExplicitDraftTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode19ExternalDraftTokensEv", "tensorrt_llm::executor::DecodingMode::ExternalDraftTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode9LookaheadEv", "tensorrt_llm::executor::DecodingMode::Lookahead"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode6MedusaEv", "tensorrt_llm::executor::DecodingMode::Medusa"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode4TopKEv", "tensorrt_llm::executor::DecodingMode::TopK"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode8TopKTopPEv", "tensorrt_llm::executor::DecodingMode::TopKTopP"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode4TopPEv", "tensorrt_llm::executor::DecodingMode::TopP"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode14UnderlyingTypeE", "tensorrt_llm::executor::DecodingMode::UnderlyingType"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9allBitSetE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::allBitSet"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9allBitSetE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::allBitSet::bits"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9anyBitSetE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::anyBitSet"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9anyBitSetE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::anyBitSet::bits"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode7getNameEv", "tensorrt_llm::executor::DecodingMode::getName"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode8getStateEv", "tensorrt_llm::executor::DecodingMode::getState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isAutoEv", "tensorrt_llm::executor::DecodingMode::isAuto"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isBeamSearchEv", "tensorrt_llm::executor::DecodingMode::isBeamSearch"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode7isEagleEv", "tensorrt_llm::executor::DecodingMode::isEagle"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode21isExplicitDraftTokensEv", "tensorrt_llm::executor::DecodingMode::isExplicitDraftTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode21isExternalDraftTokensEv", "tensorrt_llm::executor::DecodingMode::isExternalDraftTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode11isLookaheadEv", "tensorrt_llm::executor::DecodingMode::isLookahead"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode8isMedusaEv", "tensorrt_llm::executor::DecodingMode::isMedusa"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isTopKEv", "tensorrt_llm::executor::DecodingMode::isTopK"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode13isTopKandTopPEv", "tensorrt_llm::executor::DecodingMode::isTopKandTopP"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isTopKorTopPEv", "tensorrt_llm::executor::DecodingMode::isTopKorTopP"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isTopPEv", "tensorrt_llm::executor::DecodingMode::isTopP"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseBanTokensEv", "tensorrt_llm::executor::DecodingMode::isUseBanTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode13isUseBanWordsEv", "tensorrt_llm::executor::DecodingMode::isUseBanWords"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode20isUseExplicitEosStopEv", "tensorrt_llm::executor::DecodingMode::isUseExplicitEosStop"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode21isUseFrequencyPenaltyEv", "tensorrt_llm::executor::DecodingMode::isUseFrequencyPenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode18isUseMaxLengthStopEv", "tensorrt_llm::executor::DecodingMode::isUseMaxLengthStop"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseMinLengthEv", "tensorrt_llm::executor::DecodingMode::isUseMinLength"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9isUseMinPEv", "tensorrt_llm::executor::DecodingMode::isUseMinP"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseNoRepeatNgramSizeEv", "tensorrt_llm::executor::DecodingMode::isUseNoRepeatNgramSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseOccurrencePenaltyEv", "tensorrt_llm::executor::DecodingMode::isUseOccurrencePenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isUsePenaltyEv", "tensorrt_llm::executor::DecodingMode::isUsePenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode20isUsePresencePenaltyEv", "tensorrt_llm::executor::DecodingMode::isUsePresencePenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseRepetitionPenaltyEv", "tensorrt_llm::executor::DecodingMode::isUseRepetitionPenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode17isUseStopCriteriaEv", "tensorrt_llm::executor::DecodingMode::isUseStopCriteria"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseStopWordsEv", "tensorrt_llm::executor::DecodingMode::isUseStopWords"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode16isUseTemperatureEv", "tensorrt_llm::executor::DecodingMode::isUseTemperature"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode28isUseVariableBeamWidthSearchEv", "tensorrt_llm::executor::DecodingMode::isUseVariableBeamWidthSearch"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kAutoE", "tensorrt_llm::executor::DecodingMode::kAuto"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode11kBeamSearchE", "tensorrt_llm::executor::DecodingMode::kBeamSearch"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode6kEagleE", "tensorrt_llm::executor::DecodingMode::kEagle"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode20kExplicitDraftTokensE", "tensorrt_llm::executor::DecodingMode::kExplicitDraftTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode20kExternalDraftTokensE", "tensorrt_llm::executor::DecodingMode::kExternalDraftTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode10kLookaheadE", "tensorrt_llm::executor::DecodingMode::kLookahead"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode7kMedusaE", "tensorrt_llm::executor::DecodingMode::kMedusa"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode9kNumFlagsE", "tensorrt_llm::executor::DecodingMode::kNumFlags"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kTopKE", "tensorrt_llm::executor::DecodingMode::kTopK"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode9kTopKTopPE", "tensorrt_llm::executor::DecodingMode::kTopKTopP"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kTopPE", "tensorrt_llm::executor::DecodingMode::kTopP"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseBanTokensE", "tensorrt_llm::executor::DecodingMode::kUseBanTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12kUseBanWordsE", "tensorrt_llm::executor::DecodingMode::kUseBanWords"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode19kUseExplicitEosStopE", "tensorrt_llm::executor::DecodingMode::kUseExplicitEosStop"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode22kUseFrequencyPenaltiesE", "tensorrt_llm::executor::DecodingMode::kUseFrequencyPenalties"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode17kUseMaxLengthStopE", "tensorrt_llm::executor::DecodingMode::kUseMaxLengthStop"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseMinLengthE", "tensorrt_llm::executor::DecodingMode::kUseMinLength"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode8kUseMinPE", "tensorrt_llm::executor::DecodingMode::kUseMinP"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode21kUseNoRepeatNgramSizeE", "tensorrt_llm::executor::DecodingMode::kUseNoRepeatNgramSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode23kUseOccurrencePenaltiesE", "tensorrt_llm::executor::DecodingMode::kUseOccurrencePenalties"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUsePenaltiesE", "tensorrt_llm::executor::DecodingMode::kUsePenalties"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode21kUsePresencePenaltiesE", "tensorrt_llm::executor::DecodingMode::kUsePresencePenalties"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode23kUseRepetitionPenaltiesE", "tensorrt_llm::executor::DecodingMode::kUseRepetitionPenalties"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode24kUseStandardStopCriteriaE", "tensorrt_llm::executor::DecodingMode::kUseStandardStopCriteria"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseStopWordsE", "tensorrt_llm::executor::DecodingMode::kUseStopWords"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode15kUseTemperatureE", "tensorrt_llm::executor::DecodingMode::kUseTemperature"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode27kUseVariableBeamWidthSearchE", "tensorrt_llm::executor::DecodingMode::kUseVariableBeamWidthSearch"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode6mStateE", "tensorrt_llm::executor::DecodingMode::mState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingModeeqERK12DecodingMode", "tensorrt_llm::executor::DecodingMode::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingModeeqERK12DecodingMode", "tensorrt_llm::executor::DecodingMode::operator==::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode8setBitToE14UnderlyingTypeb", "tensorrt_llm::executor::DecodingMode::setBitTo"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode8setBitToE14UnderlyingTypeb", "tensorrt_llm::executor::DecodingMode::setBitTo::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode8setBitToE14UnderlyingTypeb", "tensorrt_llm::executor::DecodingMode::setBitTo::x"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useBanTokensEb", "tensorrt_llm::executor::DecodingMode::useBanTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useBanTokensEb", "tensorrt_llm::executor::DecodingMode::useBanTokens::banTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode11useBanWordsEb", "tensorrt_llm::executor::DecodingMode::useBanWords"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode11useBanWordsEb", "tensorrt_llm::executor::DecodingMode::useBanWords::banWords"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode18useExplicitEosStopEb", "tensorrt_llm::executor::DecodingMode::useExplicitEosStop"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode18useExplicitEosStopEb", "tensorrt_llm::executor::DecodingMode::useExplicitEosStop::explicitEosStop"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode19useFrequencyPenaltyEb", "tensorrt_llm::executor::DecodingMode::useFrequencyPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode19useFrequencyPenaltyEb", "tensorrt_llm::executor::DecodingMode::useFrequencyPenalty::usePenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode16useMaxLengthStopEb", "tensorrt_llm::executor::DecodingMode::useMaxLengthStop"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode16useMaxLengthStopEb", "tensorrt_llm::executor::DecodingMode::useMaxLengthStop::maxLengthStop"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useMinLengthEb", "tensorrt_llm::executor::DecodingMode::useMinLength"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useMinLengthEb", "tensorrt_llm::executor::DecodingMode::useMinLength::useMinLen"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode7useMinPEb", "tensorrt_llm::executor::DecodingMode::useMinP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode7useMinPEb", "tensorrt_llm::executor::DecodingMode::useMinP::useMinP"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useNoRepeatNgramSizeEb", "tensorrt_llm::executor::DecodingMode::useNoRepeatNgramSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useNoRepeatNgramSizeEb", "tensorrt_llm::executor::DecodingMode::useNoRepeatNgramSize::noRepeatNgramSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode22useOccurrencePenaltiesEb", "tensorrt_llm::executor::DecodingMode::useOccurrencePenalties"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode22useOccurrencePenaltiesEb", "tensorrt_llm::executor::DecodingMode::useOccurrencePenalties::usePenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode18usePresencePenaltyEb", "tensorrt_llm::executor::DecodingMode::usePresencePenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode18usePresencePenaltyEb", "tensorrt_llm::executor::DecodingMode::usePresencePenalty::usePenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useRepetitionPenaltyEb", "tensorrt_llm::executor::DecodingMode::useRepetitionPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useRepetitionPenaltyEb", "tensorrt_llm::executor::DecodingMode::useRepetitionPenalty::usePenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useStopWordsEb", "tensorrt_llm::executor::DecodingMode::useStopWords"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useStopWordsEb", "tensorrt_llm::executor::DecodingMode::useStopWords::stopWords"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode14useTemperatureEb", "tensorrt_llm::executor::DecodingMode::useTemperature"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode14useTemperatureEb", "tensorrt_llm::executor::DecodingMode::useTemperature::useTemp"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode26useVariableBeamWidthSearchEb", "tensorrt_llm::executor::DecodingMode::useVariableBeamWidthSearch"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode26useVariableBeamWidthSearchEb", "tensorrt_llm::executor::DecodingMode::useVariableBeamWidthSearch::useVariableBeamWidthSearch"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor22DisServingRequestStatsE", "tensorrt_llm::executor::DisServingRequestStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22DisServingRequestStats11kvCacheSizeE", "tensorrt_llm::executor::DisServingRequestStats::kvCacheSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22DisServingRequestStats17kvCacheTransferMSE", "tensorrt_llm::executor::DisServingRequestStats::kvCacheTransferMS"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfigE", "tensorrt_llm::executor::DynamicBatchConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig18DynamicBatchConfigEbb10SizeType32NSt6vectorINSt4pairI10SizeType3210SizeType32EEEE", "tensorrt_llm::executor::DynamicBatchConfig::DynamicBatchConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig18DynamicBatchConfigEbb10SizeType32NSt6vectorINSt4pairI10SizeType3210SizeType32EEEE", "tensorrt_llm::executor::DynamicBatchConfig::DynamicBatchConfig::batchSizeTable"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig18DynamicBatchConfigEbb10SizeType32NSt6vectorINSt4pairI10SizeType3210SizeType32EEEE", "tensorrt_llm::executor::DynamicBatchConfig::DynamicBatchConfig::dynamicBatchMovingAverageWindow"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig18DynamicBatchConfigEbb10SizeType32NSt6vectorINSt4pairI10SizeType3210SizeType32EEEE", "tensorrt_llm::executor::DynamicBatchConfig::DynamicBatchConfig::enableBatchSizeTuning"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig18DynamicBatchConfigEbb10SizeType32NSt6vectorINSt4pairI10SizeType3210SizeType32EEEE", "tensorrt_llm::executor::DynamicBatchConfig::DynamicBatchConfig::enableMaxNumTokensTuning"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18DynamicBatchConfig17getBatchSizeTableEv", "tensorrt_llm::executor::DynamicBatchConfig::getBatchSizeTable"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18DynamicBatchConfig34getDynamicBatchMovingAverageWindowEv", "tensorrt_llm::executor::DynamicBatchConfig::getDynamicBatchMovingAverageWindow"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18DynamicBatchConfig24getEnableBatchSizeTuningEv", "tensorrt_llm::executor::DynamicBatchConfig::getEnableBatchSizeTuning"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18DynamicBatchConfig27getEnableMaxNumTokensTuningEv", "tensorrt_llm::executor::DynamicBatchConfig::getEnableMaxNumTokensTuning"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig22kDefaultBatchSizeTableE", "tensorrt_llm::executor::DynamicBatchConfig::kDefaultBatchSizeTable"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig39kDefaultDynamicBatchMovingAverageWindowE", "tensorrt_llm::executor::DynamicBatchConfig::kDefaultDynamicBatchMovingAverageWindow"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig15mBatchSizeTableE", "tensorrt_llm::executor::DynamicBatchConfig::mBatchSizeTable"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig32mDynamicBatchMovingAverageWindowE", "tensorrt_llm::executor::DynamicBatchConfig::mDynamicBatchMovingAverageWindow"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig22mEnableBatchSizeTuningE", "tensorrt_llm::executor::DynamicBatchConfig::mEnableBatchSizeTuning"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18DynamicBatchConfig25mEnableMaxNumTokensTuningE", "tensorrt_llm::executor::DynamicBatchConfig::mEnableMaxNumTokensTuning"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor12EagleChoicesE", "tensorrt_llm::executor::EagleChoices"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfigE", "tensorrt_llm::executor::EagleConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig11EagleConfigENSt8optionalI12EagleChoicesEEbNSt8optionalIfEEbNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::EagleConfig::EagleConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig11EagleConfigENSt8optionalI12EagleChoicesEEbNSt8optionalIfEEbNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::EagleConfig::EagleConfig::dynamicTreeMaxTopK"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig11EagleConfigENSt8optionalI12EagleChoicesEEbNSt8optionalIfEEbNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::EagleConfig::EagleConfig::eagleChoices"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig11EagleConfigENSt8optionalI12EagleChoicesEEbNSt8optionalIfEEbNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::EagleConfig::EagleConfig::greedySampling"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig11EagleConfigENSt8optionalI12EagleChoicesEEbNSt8optionalIfEEbNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::EagleConfig::EagleConfig::posteriorThreshold"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig11EagleConfigENSt8optionalI12EagleChoicesEEbNSt8optionalIfEEbNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::EagleConfig::EagleConfig::useDynamicTree"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig19checkPosteriorValueERKNSt8optionalIfEE", "tensorrt_llm::executor::EagleConfig::checkPosteriorValue"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig19checkPosteriorValueERKNSt8optionalIfEE", "tensorrt_llm::executor::EagleConfig::checkPosteriorValue::value"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11EagleConfig21getDynamicTreeMaxTopKEv", "tensorrt_llm::executor::EagleConfig::getDynamicTreeMaxTopK"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11EagleConfig15getEagleChoicesEv", "tensorrt_llm::executor::EagleConfig::getEagleChoices"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11EagleConfig21getPosteriorThresholdEv", "tensorrt_llm::executor::EagleConfig::getPosteriorThreshold"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11EagleConfig16isGreedySamplingEv", "tensorrt_llm::executor::EagleConfig::isGreedySampling"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig19mDynamicTreeMaxTopKE", "tensorrt_llm::executor::EagleConfig::mDynamicTreeMaxTopK"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig13mEagleChoicesE", "tensorrt_llm::executor::EagleConfig::mEagleChoices"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig15mGreedySamplingE", "tensorrt_llm::executor::EagleConfig::mGreedySampling"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig19mPosteriorThresholdE", "tensorrt_llm::executor::EagleConfig::mPosteriorThreshold"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11EagleConfig15mUseDynamicTreeE", "tensorrt_llm::executor::EagleConfig::mUseDynamicTree"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11EagleConfigeqERK11EagleConfig", "tensorrt_llm::executor::EagleConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor11EagleConfigeqERK11EagleConfig", "tensorrt_llm::executor::EagleConfig::operator==::other"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11EagleConfig14useDynamicTreeEv", "tensorrt_llm::executor::EagleConfig::useDynamicTree"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8ExecutorE", "tensorrt_llm::executor::Executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK8Executor", "tensorrt_llm::executor::Executor::Executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERR8Executor", "tensorrt_llm::executor::Executor::Executor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::decoderEngineBuffer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::decoderJsonConfigStr"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::decoderModel"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::decoderModelPath"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::encoderEngineBuffer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::encoderJsonConfigStr"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::encoderModel"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::encoderModelPath"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor::engineBuffer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK8Executor", "tensorrt_llm::executor::Executor::Executor::executor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor::jsonConfigStr"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor::managedWeights"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::model"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::modelPath"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor::modelType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::modelType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::modelType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::modelType"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERK6IdTypeRKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt6vectorI6IdTypeEERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERK6IdTypeRKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses::requestId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt6vectorI6IdTypeEERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses::requestIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERK6IdTypeRKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses::timeout"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt6vectorI6IdTypeEERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses::timeout"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses::timeout"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Executor18canEnqueueRequestsEv", "tensorrt_llm::executor::Executor::canEnqueueRequests"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor13cancelRequestE6IdType", "tensorrt_llm::executor::Executor::cancelRequest"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor13cancelRequestE6IdType", "tensorrt_llm::executor::Executor::cancelRequest::requestId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor14enqueueRequestERK7Request", "tensorrt_llm::executor::Executor::enqueueRequest"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor14enqueueRequestERK7Request", "tensorrt_llm::executor::Executor::enqueueRequest::request"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor15enqueueRequestsERKNSt6vectorI7RequestEE", "tensorrt_llm::executor::Executor::enqueueRequests"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Executor15enqueueRequestsERKNSt6vectorI7RequestEE", "tensorrt_llm::executor::Executor::enqueueRequests::requests"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Executor22getKVCacheEventManagerEv", "tensorrt_llm::executor::Executor::getKVCacheEventManager"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor21getLatestDebugTensorsEv", "tensorrt_llm::executor::Executor::getLatestDebugTensors"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor23getLatestIterationStatsEv", "tensorrt_llm::executor::Executor::getLatestIterationStats"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor21getLatestRequestStatsEv", "tensorrt_llm::executor::Executor::getLatestRequestStats"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Executor20getNumResponsesReadyERKNSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Executor::getNumResponsesReady"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8Executor20getNumResponsesReadyERKNSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Executor::getNumResponsesReady::requestId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Executor13isParticipantEv", "tensorrt_llm::executor::Executor::isParticipant"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Executor5mImplE", "tensorrt_llm::executor::Executor::mImpl"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8ExecutoraSERK8Executor", "tensorrt_llm::executor::Executor::operator="], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8ExecutoraSERR8Executor", "tensorrt_llm::executor::Executor::operator="], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8ExecutoraSERK8Executor", "tensorrt_llm::executor::Executor::operator=::executor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Executor8shutdownEv", "tensorrt_llm::executor::Executor::shutdown"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8ExecutorD0Ev", "tensorrt_llm::executor::Executor::~Executor"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfigE", "tensorrt_llm::executor::ExecutorConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::additionalModelOutputs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::batchingType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::cacheTransceiverConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::debugConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::decodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::enableChunkedContext"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::enableTrtOverlap"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::extendedRuntimePerfKnobConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::gatherGenerationLogits"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::gpuWeightsPercent"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::guidedDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::iterStatsMaxIterations"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::kvCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::logitsPostProcessorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::maxBatchSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::maxBeamWidth"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::maxNumTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::maxQueueSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::maxSeqIdleMicroseconds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::normalizeLogProbs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::parallelConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::peftCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::promptTableOffloading"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::recvPollPeriodMs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::requestStatsMaxIterations"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::schedulerConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::specDecConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType3215SchedulerConfig13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEbfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_tNSt8optionalI25SpeculativeDecodingConfigEENSt8optionalI20GuidedDecodingConfigEENSt8optionalINSt6vectorI21AdditionalModelOutputEEEENSt8optionalI22CacheTransceiverConfigEEbbb", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::useGpuDirectStorage"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getAdditionalModelOutputsEv", "tensorrt_llm::executor::ExecutorConfig::getAdditionalModelOutputs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getBatchingTypeEv", "tensorrt_llm::executor::ExecutorConfig::getBatchingType"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getCacheTransceiverConfigEv", "tensorrt_llm::executor::ExecutorConfig::getCacheTransceiverConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig14getDebugConfigEv", "tensorrt_llm::executor::ExecutorConfig::getDebugConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig17getDecodingConfigEv", "tensorrt_llm::executor::ExecutorConfig::getDecodingConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig23getEnableChunkedContextEv", "tensorrt_llm::executor::ExecutorConfig::getEnableChunkedContext"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig19getEnableTrtOverlapEv", "tensorrt_llm::executor::ExecutorConfig::getEnableTrtOverlap"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig32getExtendedRuntimePerfKnobConfigEv", "tensorrt_llm::executor::ExecutorConfig::getExtendedRuntimePerfKnobConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getGatherGenerationLogitsEv", "tensorrt_llm::executor::ExecutorConfig::getGatherGenerationLogits"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig20getGpuWeightsPercentEv", "tensorrt_llm::executor::ExecutorConfig::getGpuWeightsPercent"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig23getGuidedDecodingConfigEv", "tensorrt_llm::executor::ExecutorConfig::getGuidedDecodingConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getIterStatsMaxIterationsEv", "tensorrt_llm::executor::ExecutorConfig::getIterStatsMaxIterations"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig16getKvCacheConfigEv", "tensorrt_llm::executor::ExecutorConfig::getKvCacheConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19getKvCacheConfigRefEv", "tensorrt_llm::executor::ExecutorConfig::getKvCacheConfigRef"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig28getLogitsPostProcessorConfigEv", "tensorrt_llm::executor::ExecutorConfig::getLogitsPostProcessorConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxBatchSizeEv", "tensorrt_llm::executor::ExecutorConfig::getMaxBatchSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxBeamWidthEv", "tensorrt_llm::executor::ExecutorConfig::getMaxBeamWidth"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxNumTokensEv", "tensorrt_llm::executor::ExecutorConfig::getMaxNumTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxQueueSizeEv", "tensorrt_llm::executor::ExecutorConfig::getMaxQueueSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getMaxSeqIdleMicrosecondsEv", "tensorrt_llm::executor::ExecutorConfig::getMaxSeqIdleMicroseconds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig20getNormalizeLogProbsEv", "tensorrt_llm::executor::ExecutorConfig::getNormalizeLogProbs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig17getParallelConfigEv", "tensorrt_llm::executor::ExecutorConfig::getParallelConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig18getPeftCacheConfigEv", "tensorrt_llm::executor::ExecutorConfig::getPeftCacheConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig24getPromptTableOffloadingEv", "tensorrt_llm::executor::ExecutorConfig::getPromptTableOffloading"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig19getRecvPollPeriodMsEv", "tensorrt_llm::executor::ExecutorConfig::getRecvPollPeriodMs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig28getRequestStatsMaxIterationsEv", "tensorrt_llm::executor::ExecutorConfig::getRequestStatsMaxIterations"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig18getSchedulerConfigEv", "tensorrt_llm::executor::ExecutorConfig::getSchedulerConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig21getSchedulerConfigRefEv", "tensorrt_llm::executor::ExecutorConfig::getSchedulerConfigRef"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig16getSpecDecConfigEv", "tensorrt_llm::executor::ExecutorConfig::getSpecDecConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig22getUseGpuDirectStorageEv", "tensorrt_llm::executor::ExecutorConfig::getUseGpuDirectStorage"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig30kDefaultIterStatsMaxIterationsE", "tensorrt_llm::executor::ExecutorConfig::kDefaultIterStatsMaxIterations"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig30kDefaultMaxSeqIdleMicrosecondsE", "tensorrt_llm::executor::ExecutorConfig::kDefaultMaxSeqIdleMicroseconds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig33kDefaultRequestStatsMaxIterationsE", "tensorrt_llm::executor::ExecutorConfig::kDefaultRequestStatsMaxIterations"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mAdditionalModelOutputsE", "tensorrt_llm::executor::ExecutorConfig::mAdditionalModelOutputs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mBatchingTypeE", "tensorrt_llm::executor::ExecutorConfig::mBatchingType"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mCacheTransceiverConfigE", "tensorrt_llm::executor::ExecutorConfig::mCacheTransceiverConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig12mDebugConfigE", "tensorrt_llm::executor::ExecutorConfig::mDebugConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15mDecodingConfigE", "tensorrt_llm::executor::ExecutorConfig::mDecodingConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig21mEnableChunkedContextE", "tensorrt_llm::executor::ExecutorConfig::mEnableChunkedContext"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17mEnableTrtOverlapE", "tensorrt_llm::executor::ExecutorConfig::mEnableTrtOverlap"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig30mExtendedRuntimePerfKnobConfigE", "tensorrt_llm::executor::ExecutorConfig::mExtendedRuntimePerfKnobConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mGatherGenerationLogitsE", "tensorrt_llm::executor::ExecutorConfig::mGatherGenerationLogits"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18mGpuWeightsPercentE", "tensorrt_llm::executor::ExecutorConfig::mGpuWeightsPercent"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig21mGuidedDecodingConfigE", "tensorrt_llm::executor::ExecutorConfig::mGuidedDecodingConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mIterStatsMaxIterationsE", "tensorrt_llm::executor::ExecutorConfig::mIterStatsMaxIterations"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14mKvCacheConfigE", "tensorrt_llm::executor::ExecutorConfig::mKvCacheConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig26mLogitsPostProcessorConfigE", "tensorrt_llm::executor::ExecutorConfig::mLogitsPostProcessorConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxBatchSizeE", "tensorrt_llm::executor::ExecutorConfig::mMaxBatchSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxBeamWidthE", "tensorrt_llm::executor::ExecutorConfig::mMaxBeamWidth"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxNumTokensE", "tensorrt_llm::executor::ExecutorConfig::mMaxNumTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxQueueSizeE", "tensorrt_llm::executor::ExecutorConfig::mMaxQueueSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mMaxSeqIdleMicrosecondsE", "tensorrt_llm::executor::ExecutorConfig::mMaxSeqIdleMicroseconds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18mNormalizeLogProbsE", "tensorrt_llm::executor::ExecutorConfig::mNormalizeLogProbs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15mParallelConfigE", "tensorrt_llm::executor::ExecutorConfig::mParallelConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16mPeftCacheConfigE", "tensorrt_llm::executor::ExecutorConfig::mPeftCacheConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig22mPromptTableOffloadingE", "tensorrt_llm::executor::ExecutorConfig::mPromptTableOffloading"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17mRecvPollPeriodMsE", "tensorrt_llm::executor::ExecutorConfig::mRecvPollPeriodMs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig26mRequestStatsMaxIterationsE", "tensorrt_llm::executor::ExecutorConfig::mRequestStatsMaxIterations"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16mSchedulerConfigE", "tensorrt_llm::executor::ExecutorConfig::mSchedulerConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig26mSpeculativeDecodingConfigE", "tensorrt_llm::executor::ExecutorConfig::mSpeculativeDecodingConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20mUseGpuDirectStorageE", "tensorrt_llm::executor::ExecutorConfig::mUseGpuDirectStorage"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setAdditionalModelOutputsERKNSt6vectorI21AdditionalModelOutputEE", "tensorrt_llm::executor::ExecutorConfig::setAdditionalModelOutputs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setAdditionalModelOutputsERKNSt6vectorI21AdditionalModelOutputEE", "tensorrt_llm::executor::ExecutorConfig::setAdditionalModelOutputs::additionalModelOutputs"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setBatchingTypeE12BatchingType", "tensorrt_llm::executor::ExecutorConfig::setBatchingType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setBatchingTypeE12BatchingType", "tensorrt_llm::executor::ExecutorConfig::setBatchingType::batchingType"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setCacheTransceiverConfigERK22CacheTransceiverConfig", "tensorrt_llm::executor::ExecutorConfig::setCacheTransceiverConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setCacheTransceiverConfigERK22CacheTransceiverConfig", "tensorrt_llm::executor::ExecutorConfig::setCacheTransceiverConfig::cacheTransceiverConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14setDebugConfigERK11DebugConfig", "tensorrt_llm::executor::ExecutorConfig::setDebugConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14setDebugConfigERK11DebugConfig", "tensorrt_llm::executor::ExecutorConfig::setDebugConfig::debugConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setDecodingConfigERK14DecodingConfig", "tensorrt_llm::executor::ExecutorConfig::setDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setDecodingConfigERK14DecodingConfig", "tensorrt_llm::executor::ExecutorConfig::setDecodingConfig::decodingConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23setEnableChunkedContextEb", "tensorrt_llm::executor::ExecutorConfig::setEnableChunkedContext"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23setEnableChunkedContextEb", "tensorrt_llm::executor::ExecutorConfig::setEnableChunkedContext::enableChunkedContext"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19setEnableTrtOverlapEb", "tensorrt_llm::executor::ExecutorConfig::setEnableTrtOverlap"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19setEnableTrtOverlapEb", "tensorrt_llm::executor::ExecutorConfig::setEnableTrtOverlap::enableTrtOverlap"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig32setExtendedRuntimePerfKnobConfigERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::ExecutorConfig::setExtendedRuntimePerfKnobConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig32setExtendedRuntimePerfKnobConfigERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::ExecutorConfig::setExtendedRuntimePerfKnobConfig::extendedRuntimePerfKnobConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setGatherGenerationLogitsEb", "tensorrt_llm::executor::ExecutorConfig::setGatherGenerationLogits"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setGatherGenerationLogitsEb", "tensorrt_llm::executor::ExecutorConfig::setGatherGenerationLogits::gatherGenerationLogits"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setGpuWeightsPercentERKf", "tensorrt_llm::executor::ExecutorConfig::setGpuWeightsPercent"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setGpuWeightsPercentERKf", "tensorrt_llm::executor::ExecutorConfig::setGpuWeightsPercent::gpuWeightsPercent"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23setGuidedDecodingConfigERK20GuidedDecodingConfig", "tensorrt_llm::executor::ExecutorConfig::setGuidedDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23setGuidedDecodingConfigERK20GuidedDecodingConfig", "tensorrt_llm::executor::ExecutorConfig::setGuidedDecodingConfig::guidedDecodingConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setIterStatsMaxIterationsE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setIterStatsMaxIterations"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setIterStatsMaxIterationsE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setIterStatsMaxIterations::iterStatsMaxIterations"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16setKvCacheConfigERK13KvCacheConfig", "tensorrt_llm::executor::ExecutorConfig::setKvCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16setKvCacheConfigERK13KvCacheConfig", "tensorrt_llm::executor::ExecutorConfig::setKvCacheConfig::kvCacheConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setLogitsPostProcessorConfigERK25LogitsPostProcessorConfig", "tensorrt_llm::executor::ExecutorConfig::setLogitsPostProcessorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setLogitsPostProcessorConfigERK25LogitsPostProcessorConfig", "tensorrt_llm::executor::ExecutorConfig::setLogitsPostProcessorConfig::logitsPostProcessorConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBatchSizeE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxBatchSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBatchSizeE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxBatchSize::maxBatchSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBeamWidthE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxBeamWidth"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBeamWidthE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxBeamWidth::maxBeamWidth"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxNumTokensE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxNumTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxNumTokensE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxNumTokens::maxNumTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxQueueSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ExecutorConfig::setMaxQueueSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxQueueSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ExecutorConfig::setMaxQueueSize::maxQueueSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setMaxSeqIdleMicrosecondsE8uint64_t", "tensorrt_llm::executor::ExecutorConfig::setMaxSeqIdleMicroseconds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setMaxSeqIdleMicrosecondsE8uint64_t", "tensorrt_llm::executor::ExecutorConfig::setMaxSeqIdleMicroseconds::maxSeqIdleMicroseconds"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setNormalizeLogProbsEb", "tensorrt_llm::executor::ExecutorConfig::setNormalizeLogProbs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setNormalizeLogProbsEb", "tensorrt_llm::executor::ExecutorConfig::setNormalizeLogProbs::normalizeLogProbs"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setParallelConfigERK14ParallelConfig", "tensorrt_llm::executor::ExecutorConfig::setParallelConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setParallelConfigERK14ParallelConfig", "tensorrt_llm::executor::ExecutorConfig::setParallelConfig::parallelConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setPeftCacheConfigERK15PeftCacheConfig", "tensorrt_llm::executor::ExecutorConfig::setPeftCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setPeftCacheConfigERK15PeftCacheConfig", "tensorrt_llm::executor::ExecutorConfig::setPeftCacheConfig::peftCacheConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig24setPromptTableOffloadingEb", "tensorrt_llm::executor::ExecutorConfig::setPromptTableOffloading"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig24setPromptTableOffloadingEb", "tensorrt_llm::executor::ExecutorConfig::setPromptTableOffloading::promptTableOffloading"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19setRecvPollPeriodMsERK10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setRecvPollPeriodMs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19setRecvPollPeriodMsERK10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setRecvPollPeriodMs::recvPollPeriodMs"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setRequestStatsMaxIterationsE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setRequestStatsMaxIterations"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setRequestStatsMaxIterationsE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setRequestStatsMaxIterations::requestStatsMaxIterations"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setSchedulerConfigERK15SchedulerConfig", "tensorrt_llm::executor::ExecutorConfig::setSchedulerConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setSchedulerConfigERK15SchedulerConfig", "tensorrt_llm::executor::ExecutorConfig::setSchedulerConfig::schedulerConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16setSpecDecConfigERK25SpeculativeDecodingConfig", "tensorrt_llm::executor::ExecutorConfig::setSpecDecConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16setSpecDecConfigERK25SpeculativeDecodingConfig", "tensorrt_llm::executor::ExecutorConfig::setSpecDecConfig::specDecConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig22setUseGpuDirectStorageERKb", "tensorrt_llm::executor::ExecutorConfig::setUseGpuDirectStorage"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig22setUseGpuDirectStorageERKb", "tensorrt_llm::executor::ExecutorConfig::setUseGpuDirectStorage::useGpuDirectStorage"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfigE", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig29ExtendedRuntimePerfKnobConfigEbbb10SizeType32", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::ExtendedRuntimePerfKnobConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig29ExtendedRuntimePerfKnobConfigEbbb10SizeType32", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::ExtendedRuntimePerfKnobConfig::cudaGraphCacheSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig29ExtendedRuntimePerfKnobConfigEbbb10SizeType32", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::ExtendedRuntimePerfKnobConfig::cudaGraphMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig29ExtendedRuntimePerfKnobConfigEbbb10SizeType32", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::ExtendedRuntimePerfKnobConfig::enableContextFMHAFP32Acc"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig29ExtendedRuntimePerfKnobConfigEbbb10SizeType32", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::ExtendedRuntimePerfKnobConfig::multiBlockMode"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig21getCudaGraphCacheSizeEv", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::getCudaGraphCacheSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig16getCudaGraphModeEv", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::getCudaGraphMode"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig27getEnableContextFMHAFP32AccEv", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::getEnableContextFMHAFP32Acc"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig17getMultiBlockModeEv", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::getMultiBlockMode"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig19mCudaGraphCacheSizeE", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::mCudaGraphCacheSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig14mCudaGraphModeE", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::mCudaGraphMode"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig25mEnableContextFMHAFP32AccE", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::mEnableContextFMHAFP32Acc"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig15mMultiBlockModeE", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::mMultiBlockMode"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfigeqERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfigeqERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::operator==::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig21setCudaGraphCacheSizeE10SizeType32", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setCudaGraphCacheSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig21setCudaGraphCacheSizeE10SizeType32", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setCudaGraphCacheSize::cacheSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig16setCudaGraphModeEb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setCudaGraphMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig16setCudaGraphModeEb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setCudaGraphMode::cudaGraphMode"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig27setEnableContextFMHAFP32AccEb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setEnableContextFMHAFP32Acc"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig27setEnableContextFMHAFP32AccEb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setEnableContextFMHAFP32Acc::enableContextFMHAFP32Acc"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig17setMultiBlockModeEb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setMultiBlockMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig17setMultiBlockModeEb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setMultiBlockMode::multiBlockMode"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfigE", "tensorrt_llm::executor::ExternalDraftTokensConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig25ExternalDraftTokensConfigE9VecTokensNSt8optionalI6TensorEERKNSt8optionalI9FloatTypeEERKNSt8optionalIbEE", "tensorrt_llm::executor::ExternalDraftTokensConfig::ExternalDraftTokensConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig25ExternalDraftTokensConfigE9VecTokensNSt8optionalI6TensorEERKNSt8optionalI9FloatTypeEERKNSt8optionalIbEE", "tensorrt_llm::executor::ExternalDraftTokensConfig::ExternalDraftTokensConfig::acceptanceThreshold"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig25ExternalDraftTokensConfigE9VecTokensNSt8optionalI6TensorEERKNSt8optionalI9FloatTypeEERKNSt8optionalIbEE", "tensorrt_llm::executor::ExternalDraftTokensConfig::ExternalDraftTokensConfig::fastLogits"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig25ExternalDraftTokensConfigE9VecTokensNSt8optionalI6TensorEERKNSt8optionalI9FloatTypeEERKNSt8optionalIbEE", "tensorrt_llm::executor::ExternalDraftTokensConfig::ExternalDraftTokensConfig::logits"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig25ExternalDraftTokensConfigE9VecTokensNSt8optionalI6TensorEERKNSt8optionalI9FloatTypeEERKNSt8optionalIbEE", "tensorrt_llm::executor::ExternalDraftTokensConfig::ExternalDraftTokensConfig::tokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig22getAcceptanceThresholdEv", "tensorrt_llm::executor::ExternalDraftTokensConfig::getAcceptanceThreshold"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig13getFastLogitsEv", "tensorrt_llm::executor::ExternalDraftTokensConfig::getFastLogits"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig9getLogitsEv", "tensorrt_llm::executor::ExternalDraftTokensConfig::getLogits"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig9getTokensEv", "tensorrt_llm::executor::ExternalDraftTokensConfig::getTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig20mAcceptanceThresholdE", "tensorrt_llm::executor::ExternalDraftTokensConfig::mAcceptanceThreshold"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig11mFastLogitsE", "tensorrt_llm::executor::ExternalDraftTokensConfig::mFastLogits"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig7mLogitsE", "tensorrt_llm::executor::ExternalDraftTokensConfig::mLogits"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig7mTokensE", "tensorrt_llm::executor::ExternalDraftTokensConfig::mTokens"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12FinishReasonE", "tensorrt_llm::executor::FinishReason"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12FinishReason10kCANCELLEDE", "tensorrt_llm::executor::FinishReason::kCANCELLED"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12FinishReason7kEND_IDE", "tensorrt_llm::executor::FinishReason::kEND_ID"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12FinishReason7kLENGTHE", "tensorrt_llm::executor::FinishReason::kLENGTH"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12FinishReason13kNOT_FINISHEDE", "tensorrt_llm::executor::FinishReason::kNOT_FINISHED"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12FinishReason11kSTOP_WORDSE", "tensorrt_llm::executor::FinishReason::kSTOP_WORDS"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12FinishReason10kTIMED_OUTE", "tensorrt_llm::executor::FinishReason::kTIMED_OUT"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor9FloatTypeE", "tensorrt_llm::executor::FloatType"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfigE", "tensorrt_llm::executor::GuidedDecodingConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig21GuidedDecodingBackendE", "tensorrt_llm::executor::GuidedDecodingConfig::GuidedDecodingBackend"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig21GuidedDecodingBackend11kLLGUIDANCEE", "tensorrt_llm::executor::GuidedDecodingConfig::GuidedDecodingBackend::kLLGUIDANCE"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig21GuidedDecodingBackend9kXGRAMMARE", "tensorrt_llm::executor::GuidedDecodingConfig::GuidedDecodingBackend::kXGRAMMAR"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig20GuidedDecodingConfigE21GuidedDecodingBackendNSt8optionalINSt6vectorINSt6stringEEEEENSt8optionalINSt6stringEEENSt8optionalINSt6vectorI11TokenIdTypeEEEE", "tensorrt_llm::executor::GuidedDecodingConfig::GuidedDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig20GuidedDecodingConfigE21GuidedDecodingBackendNSt8optionalINSt6vectorINSt6stringEEEEENSt8optionalINSt6stringEEENSt8optionalINSt6vectorI11TokenIdTypeEEEE", "tensorrt_llm::executor::GuidedDecodingConfig::GuidedDecodingConfig::backend"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig20GuidedDecodingConfigE21GuidedDecodingBackendNSt8optionalINSt6vectorINSt6stringEEEEENSt8optionalINSt6stringEEENSt8optionalINSt6vectorI11TokenIdTypeEEEE", "tensorrt_llm::executor::GuidedDecodingConfig::GuidedDecodingConfig::encodedVocab"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig20GuidedDecodingConfigE21GuidedDecodingBackendNSt8optionalINSt6vectorINSt6stringEEEEENSt8optionalINSt6stringEEENSt8optionalINSt6vectorI11TokenIdTypeEEEE", "tensorrt_llm::executor::GuidedDecodingConfig::GuidedDecodingConfig::stopTokenIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig20GuidedDecodingConfigE21GuidedDecodingBackendNSt8optionalINSt6vectorINSt6stringEEEEENSt8optionalINSt6stringEEENSt8optionalINSt6vectorI11TokenIdTypeEEEE", "tensorrt_llm::executor::GuidedDecodingConfig::GuidedDecodingConfig::tokenizerStr"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig10getBackendEv", "tensorrt_llm::executor::GuidedDecodingConfig::getBackend"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig15getEncodedVocabEv", "tensorrt_llm::executor::GuidedDecodingConfig::getEncodedVocab"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig15getStopTokenIdsEv", "tensorrt_llm::executor::GuidedDecodingConfig::getStopTokenIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig15getTokenizerStrEv", "tensorrt_llm::executor::GuidedDecodingConfig::getTokenizerStr"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig8mBackendE", "tensorrt_llm::executor::GuidedDecodingConfig::mBackend"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig13mEncodedVocabE", "tensorrt_llm::executor::GuidedDecodingConfig::mEncodedVocab"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig13mStopTokenIdsE", "tensorrt_llm::executor::GuidedDecodingConfig::mStopTokenIds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig13mTokenizerStrE", "tensorrt_llm::executor::GuidedDecodingConfig::mTokenizerStr"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfigeqERK20GuidedDecodingConfig", "tensorrt_llm::executor::GuidedDecodingConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfigeqERK20GuidedDecodingConfig", "tensorrt_llm::executor::GuidedDecodingConfig::operator==::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig10setBackendERK21GuidedDecodingBackend", "tensorrt_llm::executor::GuidedDecodingConfig::setBackend"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig10setBackendERK21GuidedDecodingBackend", "tensorrt_llm::executor::GuidedDecodingConfig::setBackend::backend"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setEncodedVocabERKNSt6vectorINSt6stringEEE", "tensorrt_llm::executor::GuidedDecodingConfig::setEncodedVocab"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setEncodedVocabERKNSt6vectorINSt6stringEEE", "tensorrt_llm::executor::GuidedDecodingConfig::setEncodedVocab::encodedVocab"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setStopTokenIdsERKNSt6vectorI11TokenIdTypeEE", "tensorrt_llm::executor::GuidedDecodingConfig::setStopTokenIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setStopTokenIdsERKNSt6vectorI11TokenIdTypeEE", "tensorrt_llm::executor::GuidedDecodingConfig::setStopTokenIds::stopTokenIds"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setTokenizerStrERKNSt6stringE", "tensorrt_llm::executor::GuidedDecodingConfig::setTokenizerStr"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingConfig15setTokenizerStrERKNSt6stringE", "tensorrt_llm::executor::GuidedDecodingConfig::setTokenizerStr::tokenizerStr"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingConfig8validateEv", "tensorrt_llm::executor::GuidedDecodingConfig::validate"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParamsE", "tensorrt_llm::executor::GuidedDecodingParams"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideTypeE", "tensorrt_llm::executor::GuidedDecodingParams::GuideType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType13kEBNF_GRAMMARE", "tensorrt_llm::executor::GuidedDecodingParams::GuideType::kEBNF_GRAMMAR"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType5kJSONE", "tensorrt_llm::executor::GuidedDecodingParams::GuideType::kJSON"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType12kJSON_SCHEMAE", "tensorrt_llm::executor::GuidedDecodingParams::GuideType::kJSON_SCHEMA"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType6kREGEXE", "tensorrt_llm::executor::GuidedDecodingParams::GuideType::kREGEX"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams9GuideType15kSTRUCTURAL_TAGE", "tensorrt_llm::executor::GuidedDecodingParams::GuideType::kSTRUCTURAL_TAG"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams20GuidedDecodingParamsE9GuideTypeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::GuidedDecodingParams::GuidedDecodingParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams20GuidedDecodingParamsE9GuideTypeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::GuidedDecodingParams::GuidedDecodingParams::guide"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams20GuidedDecodingParamsE9GuideTypeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::GuidedDecodingParams::GuidedDecodingParams::guideType"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingParams8getGuideEv", "tensorrt_llm::executor::GuidedDecodingParams::getGuide"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingParams12getGuideTypeEv", "tensorrt_llm::executor::GuidedDecodingParams::getGuideType"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams6mGuideE", "tensorrt_llm::executor::GuidedDecodingParams::mGuide"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor20GuidedDecodingParams10mGuideTypeE", "tensorrt_llm::executor::GuidedDecodingParams::mGuideType"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingParamseqERK20GuidedDecodingParams", "tensorrt_llm::executor::GuidedDecodingParams::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor20GuidedDecodingParamseqERK20GuidedDecodingParams", "tensorrt_llm::executor::GuidedDecodingParams::operator==::other"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor6IdTypeE", "tensorrt_llm::executor::IdType"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStatsE", "tensorrt_llm::executor::InflightBatchingStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats26avgNumDecodedTokensPerIterE", "tensorrt_llm::executor::InflightBatchingStats::avgNumDecodedTokensPerIter"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats12microBatchIdE", "tensorrt_llm::executor::InflightBatchingStats::microBatchId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats18numContextRequestsE", "tensorrt_llm::executor::InflightBatchingStats::numContextRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats12numCtxTokensE", "tensorrt_llm::executor::InflightBatchingStats::numCtxTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats14numGenRequestsE", "tensorrt_llm::executor::InflightBatchingStats::numGenRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats17numPausedRequestsE", "tensorrt_llm::executor::InflightBatchingStats::numPausedRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats20numScheduledRequestsE", "tensorrt_llm::executor::InflightBatchingStats::numScheduledRequests"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor14IterationStatsE", "tensorrt_llm::executor::IterationStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats11cpuMemUsageE", "tensorrt_llm::executor::IterationStats::cpuMemUsage"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats17crossKvCacheStatsE", "tensorrt_llm::executor::IterationStats::crossKvCacheStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats11gpuMemUsageE", "tensorrt_llm::executor::IterationStats::gpuMemUsage"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats21inflightBatchingStatsE", "tensorrt_llm::executor::IterationStats::inflightBatchingStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats4iterE", "tensorrt_llm::executor::IterationStats::iter"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats13iterLatencyMSE", "tensorrt_llm::executor::IterationStats::iterLatencyMS"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats12kvCacheStatsE", "tensorrt_llm::executor::IterationStats::kvCacheStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats19maxBatchSizeRuntimeE", "tensorrt_llm::executor::IterationStats::maxBatchSizeRuntime"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats18maxBatchSizeStaticE", "tensorrt_llm::executor::IterationStats::maxBatchSizeStatic"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats28maxBatchSizeTunerRecommendedE", "tensorrt_llm::executor::IterationStats::maxBatchSizeTunerRecommended"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats20maxNumActiveRequestsE", "tensorrt_llm::executor::IterationStats::maxNumActiveRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats19maxNumTokensRuntimeE", "tensorrt_llm::executor::IterationStats::maxNumTokensRuntime"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats18maxNumTokensStaticE", "tensorrt_llm::executor::IterationStats::maxNumTokensStatic"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats28maxNumTokensTunerRecommendedE", "tensorrt_llm::executor::IterationStats::maxNumTokensTunerRecommended"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats31newActiveRequestsQueueLatencyMSE", "tensorrt_llm::executor::IterationStats::newActiveRequestsQueueLatencyMS"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats17numActiveRequestsE", "tensorrt_llm::executor::IterationStats::numActiveRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats20numCompletedRequestsE", "tensorrt_llm::executor::IterationStats::numCompletedRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats20numNewActiveRequestsE", "tensorrt_llm::executor::IterationStats::numNewActiveRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats17numQueuedRequestsE", "tensorrt_llm::executor::IterationStats::numQueuedRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats14pinnedMemUsageE", "tensorrt_llm::executor::IterationStats::pinnedMemUsage"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats17specDecodingStatsE", "tensorrt_llm::executor::IterationStats::specDecodingStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats19staticBatchingStatsE", "tensorrt_llm::executor::IterationStats::staticBatchingStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats9timestampE", "tensorrt_llm::executor::IterationStats::timestamp"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor13IterationTypeE", "tensorrt_llm::executor::IterationType"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerializationE", "tensorrt_llm::executor::JsonSerialization"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK12RequestStats", "tensorrt_llm::executor::JsonSerialization::toJsonStr"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK14IterationStats", "tensorrt_llm::executor::JsonSerialization::toJsonStr"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK24RequestStatsPerIteration", "tensorrt_llm::executor::JsonSerialization::toJsonStr"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK14IterationStats", "tensorrt_llm::executor::JsonSerialization::toJsonStr::iterationStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK12RequestStats", "tensorrt_llm::executor::JsonSerialization::toJsonStr::requestStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK24RequestStatsPerIteration", "tensorrt_llm::executor::JsonSerialization::toJsonStr::requestStatsPerIter"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheCreatedDataE", "tensorrt_llm::executor::KVCacheCreatedData"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheCreatedData22numBlocksPerCacheLevelE", "tensorrt_llm::executor::KVCacheCreatedData::numBlocksPerCacheLevel"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor12KVCacheEventE", "tensorrt_llm::executor::KVCacheEvent"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent12KVCacheEventE6IdType16KVCacheEventData10SizeType32", "tensorrt_llm::executor::KVCacheEvent::KVCacheEvent"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent12KVCacheEventE6IdType16KVCacheEventData10SizeType32", "tensorrt_llm::executor::KVCacheEvent::KVCacheEvent::data"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent12KVCacheEventE6IdType16KVCacheEventData10SizeType32", "tensorrt_llm::executor::KVCacheEvent::KVCacheEvent::eventId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent12KVCacheEventE6IdType16KVCacheEventData10SizeType32", "tensorrt_llm::executor::KVCacheEvent::KVCacheEvent::windowSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent4dataE", "tensorrt_llm::executor::KVCacheEvent::data"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent7eventIdE", "tensorrt_llm::executor::KVCacheEvent::eventId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KVCacheEvent10windowSizeE", "tensorrt_llm::executor::KVCacheEvent::windowSize"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor16KVCacheEventDataE", "tensorrt_llm::executor::KVCacheEventData"], [0, 2, 1, "_CPPv4I0EN12tensorrt_llm8executor16KVCacheEventDiffE", "tensorrt_llm::executor::KVCacheEventDiff"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor16KVCacheEventDiffE", "tensorrt_llm::executor::KVCacheEventDiff::T"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor16KVCacheEventDiff8newValueE", "tensorrt_llm::executor::KVCacheEventDiff::newValue"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor16KVCacheEventDiff8oldValueE", "tensorrt_llm::executor::KVCacheEventDiff::oldValue"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManagerE", "tensorrt_llm::executor::KVCacheEventManager"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManager19KVCacheEventManagerENSt10shared_ptrIN12tensorrt_llm13batch_manager16kv_cache_manager18BaseKVCacheManagerEEE", "tensorrt_llm::executor::KVCacheEventManager::KVCacheEventManager"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManager19KVCacheEventManagerENSt10shared_ptrIN12tensorrt_llm13batch_manager16kv_cache_manager18BaseKVCacheManagerEEE", "tensorrt_llm::executor::KVCacheEventManager::KVCacheEventManager::kvCacheManager"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManager15getLatestEventsENSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::KVCacheEventManager::getLatestEvents"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManager15getLatestEventsENSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::KVCacheEventManager::getLatestEvents::timeout"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor19KVCacheEventManager14kvCacheManagerE", "tensorrt_llm::executor::KVCacheEventManager::kvCacheManager"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheRemovedDataE", "tensorrt_llm::executor::KVCacheRemovedData"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheRemovedData11blockHashesE", "tensorrt_llm::executor::KVCacheRemovedData::blockHashes"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockDataE", "tensorrt_llm::executor::KVCacheStoredBlockData"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData22KVCacheStoredBlockDataE6IdTypeN12tensorrt_llm7runtime15VecUniqueTokensENSt8optionalIN12tensorrt_llm7runtime14LoraTaskIdTypeEEE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheStoredBlockData::KVCacheStoredBlockData"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData22KVCacheStoredBlockDataE6IdTypeN12tensorrt_llm7runtime15VecUniqueTokensENSt8optionalIN12tensorrt_llm7runtime14LoraTaskIdTypeEEE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheStoredBlockData::KVCacheStoredBlockData::blockHash"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData22KVCacheStoredBlockDataE6IdTypeN12tensorrt_llm7runtime15VecUniqueTokensENSt8optionalIN12tensorrt_llm7runtime14LoraTaskIdTypeEEE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheStoredBlockData::KVCacheStoredBlockData::cacheLevel"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData22KVCacheStoredBlockDataE6IdTypeN12tensorrt_llm7runtime15VecUniqueTokensENSt8optionalIN12tensorrt_llm7runtime14LoraTaskIdTypeEEE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheStoredBlockData::KVCacheStoredBlockData::loraId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData22KVCacheStoredBlockDataE6IdTypeN12tensorrt_llm7runtime15VecUniqueTokensENSt8optionalIN12tensorrt_llm7runtime14LoraTaskIdTypeEEE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheStoredBlockData::KVCacheStoredBlockData::priority"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData22KVCacheStoredBlockDataE6IdTypeN12tensorrt_llm7runtime15VecUniqueTokensENSt8optionalIN12tensorrt_llm7runtime14LoraTaskIdTypeEEE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheStoredBlockData::KVCacheStoredBlockData::tokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData9blockHashE", "tensorrt_llm::executor::KVCacheStoredBlockData::blockHash"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData10cacheLevelE", "tensorrt_llm::executor::KVCacheStoredBlockData::cacheLevel"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData6loraIdE", "tensorrt_llm::executor::KVCacheStoredBlockData::loraId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData8priorityE", "tensorrt_llm::executor::KVCacheStoredBlockData::priority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KVCacheStoredBlockData6tokensE", "tensorrt_llm::executor::KVCacheStoredBlockData::tokens"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor17KVCacheStoredDataE", "tensorrt_llm::executor::KVCacheStoredData"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17KVCacheStoredData6blocksE", "tensorrt_llm::executor::KVCacheStoredData::blocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17KVCacheStoredData10parentHashE", "tensorrt_llm::executor::KVCacheStoredData::parentHash"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedDataE", "tensorrt_llm::executor::KVCacheUpdatedData"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData18KVCacheUpdatedDataE6IdType", "tensorrt_llm::executor::KVCacheUpdatedData::KVCacheUpdatedData"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData18KVCacheUpdatedDataE6IdType", "tensorrt_llm::executor::KVCacheUpdatedData::KVCacheUpdatedData::blockHash"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData9blockHashE", "tensorrt_llm::executor::KVCacheUpdatedData::blockHash"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData10cacheLevelE", "tensorrt_llm::executor::KVCacheUpdatedData::cacheLevel"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData17cacheLevelUpdatedE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheUpdatedData::cacheLevelUpdated"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData17cacheLevelUpdatedE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheUpdatedData::cacheLevelUpdated::newValue"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData17cacheLevelUpdatedE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheUpdatedData::cacheLevelUpdated::oldValue"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData8priorityE", "tensorrt_llm::executor::KVCacheUpdatedData::priority"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData15priorityUpdatedE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheUpdatedData::priorityUpdated"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData15priorityUpdatedE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheUpdatedData::priorityUpdated::newValue"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18KVCacheUpdatedData15priorityUpdatedE10SizeType3210SizeType32", "tensorrt_llm::executor::KVCacheUpdatedData::priorityUpdated::oldValue"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfigE", "tensorrt_llm::executor::KvCacheConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::copyOnPartialReuse"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::crossKvCacheFraction"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::enableBlockReuse"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::enablePartialReuse"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::eventBufferMaxSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::freeGpuMemoryFraction"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::hostCacheSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::maxAttentionWindowVec"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::maxTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::onboardBlocks"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::runtimeDefaults"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::secondaryOffloadMinPriority"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::sinkTokenLength"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEbRKNSt8optionalI9FloatTypeEENSt8optionalI17RetentionPriorityEE6size_tbbbRKNSt8optionalIN12tensorrt_llm7runtime15RuntimeDefaultsEEE", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::useUvm"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig34fillEmptyFieldsFromRuntimeDefaultsERKN12tensorrt_llm7runtime15RuntimeDefaultsE", "tensorrt_llm::executor::KvCacheConfig::fillEmptyFieldsFromRuntimeDefaults"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig34fillEmptyFieldsFromRuntimeDefaultsERKN12tensorrt_llm7runtime15RuntimeDefaultsE", "tensorrt_llm::executor::KvCacheConfig::fillEmptyFieldsFromRuntimeDefaults::runtimeDefaults"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig21getCopyOnPartialReuseEv", "tensorrt_llm::executor::KvCacheConfig::getCopyOnPartialReuse"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig23getCrossKvCacheFractionEv", "tensorrt_llm::executor::KvCacheConfig::getCrossKvCacheFraction"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig19getEnableBlockReuseEv", "tensorrt_llm::executor::KvCacheConfig::getEnableBlockReuse"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig21getEnablePartialReuseEv", "tensorrt_llm::executor::KvCacheConfig::getEnablePartialReuse"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig21getEventBufferMaxSizeEv", "tensorrt_llm::executor::KvCacheConfig::getEventBufferMaxSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig24getFreeGpuMemoryFractionEv", "tensorrt_llm::executor::KvCacheConfig::getFreeGpuMemoryFraction"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig16getHostCacheSizeEv", "tensorrt_llm::executor::KvCacheConfig::getHostCacheSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig24getMaxAttentionWindowVecEv", "tensorrt_llm::executor::KvCacheConfig::getMaxAttentionWindowVec"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig12getMaxTokensEv", "tensorrt_llm::executor::KvCacheConfig::getMaxTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig16getOnboardBlocksEv", "tensorrt_llm::executor::KvCacheConfig::getOnboardBlocks"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig30getSecondaryOffloadMinPriorityEv", "tensorrt_llm::executor::KvCacheConfig::getSecondaryOffloadMinPriority"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig18getSinkTokenLengthEv", "tensorrt_llm::executor::KvCacheConfig::getSinkTokenLength"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig9getUseUvmEv", "tensorrt_llm::executor::KvCacheConfig::getUseUvm"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig22kDefaultGpuMemFractionE", "tensorrt_llm::executor::KvCacheConfig::kDefaultGpuMemFraction"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19mCopyOnPartialReuseE", "tensorrt_llm::executor::KvCacheConfig::mCopyOnPartialReuse"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21mCrossKvCacheFractionE", "tensorrt_llm::executor::KvCacheConfig::mCrossKvCacheFraction"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig17mEnableBlockReuseE", "tensorrt_llm::executor::KvCacheConfig::mEnableBlockReuse"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19mEnablePartialReuseE", "tensorrt_llm::executor::KvCacheConfig::mEnablePartialReuse"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19mEventBufferMaxSizeE", "tensorrt_llm::executor::KvCacheConfig::mEventBufferMaxSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig22mFreeGpuMemoryFractionE", "tensorrt_llm::executor::KvCacheConfig::mFreeGpuMemoryFraction"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig14mHostCacheSizeE", "tensorrt_llm::executor::KvCacheConfig::mHostCacheSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig22mMaxAttentionWindowVecE", "tensorrt_llm::executor::KvCacheConfig::mMaxAttentionWindowVec"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig10mMaxTokensE", "tensorrt_llm::executor::KvCacheConfig::mMaxTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig14mOnboardBlocksE", "tensorrt_llm::executor::KvCacheConfig::mOnboardBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig28mSecondaryOffloadMinPriorityE", "tensorrt_llm::executor::KvCacheConfig::mSecondaryOffloadMinPriority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16mSinkTokenLengthE", "tensorrt_llm::executor::KvCacheConfig::mSinkTokenLength"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig7mUseUvmE", "tensorrt_llm::executor::KvCacheConfig::mUseUvm"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setCopyOnPartialReuseEb", "tensorrt_llm::executor::KvCacheConfig::setCopyOnPartialReuse"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setCopyOnPartialReuseEb", "tensorrt_llm::executor::KvCacheConfig::setCopyOnPartialReuse::copyOnPartialReuse"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig23setCrossKvCacheFractionE9FloatType", "tensorrt_llm::executor::KvCacheConfig::setCrossKvCacheFraction"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig23setCrossKvCacheFractionE9FloatType", "tensorrt_llm::executor::KvCacheConfig::setCrossKvCacheFraction::crossKvCacheFraction"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19setEnableBlockReuseEb", "tensorrt_llm::executor::KvCacheConfig::setEnableBlockReuse"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19setEnableBlockReuseEb", "tensorrt_llm::executor::KvCacheConfig::setEnableBlockReuse::enableBlockReuse"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setEnablePartialReuseEb", "tensorrt_llm::executor::KvCacheConfig::setEnablePartialReuse"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setEnablePartialReuseEb", "tensorrt_llm::executor::KvCacheConfig::setEnablePartialReuse::enablePartialReuse"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setEventBufferMaxSizeE6size_t", "tensorrt_llm::executor::KvCacheConfig::setEventBufferMaxSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig21setEventBufferMaxSizeE6size_t", "tensorrt_llm::executor::KvCacheConfig::setEventBufferMaxSize::eventBufferMaxSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setFreeGpuMemoryFractionE9FloatType", "tensorrt_llm::executor::KvCacheConfig::setFreeGpuMemoryFraction"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setFreeGpuMemoryFractionE9FloatType", "tensorrt_llm::executor::KvCacheConfig::setFreeGpuMemoryFraction::freeGpuMemoryFraction"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setHostCacheSizeE6size_t", "tensorrt_llm::executor::KvCacheConfig::setHostCacheSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setHostCacheSizeE6size_t", "tensorrt_llm::executor::KvCacheConfig::setHostCacheSize::hostCacheSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setMaxAttentionWindowVecENSt6vectorI10SizeType32EE", "tensorrt_llm::executor::KvCacheConfig::setMaxAttentionWindowVec"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setMaxAttentionWindowVecENSt6vectorI10SizeType32EE", "tensorrt_llm::executor::KvCacheConfig::setMaxAttentionWindowVec::maxAttentionWindowVec"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig12setMaxTokensE10SizeType32", "tensorrt_llm::executor::KvCacheConfig::setMaxTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig12setMaxTokensE10SizeType32", "tensorrt_llm::executor::KvCacheConfig::setMaxTokens::maxTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setOnboardBlocksEb", "tensorrt_llm::executor::KvCacheConfig::setOnboardBlocks"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setOnboardBlocksEb", "tensorrt_llm::executor::KvCacheConfig::setOnboardBlocks::onboardBlocks"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig30setSecondaryOffloadMinPriorityENSt8optionalI17RetentionPriorityEE", "tensorrt_llm::executor::KvCacheConfig::setSecondaryOffloadMinPriority"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig30setSecondaryOffloadMinPriorityENSt8optionalI17RetentionPriorityEE", "tensorrt_llm::executor::KvCacheConfig::setSecondaryOffloadMinPriority::secondaryOffloadMinPriority"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig18setSinkTokenLengthE10SizeType32", "tensorrt_llm::executor::KvCacheConfig::setSinkTokenLength"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig18setSinkTokenLengthE10SizeType32", "tensorrt_llm::executor::KvCacheConfig::setSinkTokenLength::sinkTokenLength"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig9setUseUvmEb", "tensorrt_llm::executor::KvCacheConfig::setUseUvm"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig9setUseUvmEb", "tensorrt_llm::executor::KvCacheConfig::setUseUvm::useUvm"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfigE", "tensorrt_llm::executor::KvCacheRetentionConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigERKNSt6vectorI25TokenRangeRetentionConfigEE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE19KvCacheTransferModeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::KvCacheRetentionConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigEv", "tensorrt_llm::executor::KvCacheRetentionConfig::KvCacheRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigERKNSt6vectorI25TokenRangeRetentionConfigEE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE19KvCacheTransferModeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::KvCacheRetentionConfig::decodeDurationMs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigERKNSt6vectorI25TokenRangeRetentionConfigEE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE19KvCacheTransferModeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::KvCacheRetentionConfig::decodeRetentionPriority"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigERKNSt6vectorI25TokenRangeRetentionConfigEE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE19KvCacheTransferModeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::KvCacheRetentionConfig::directory"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigERKNSt6vectorI25TokenRangeRetentionConfigEE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE19KvCacheTransferModeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::KvCacheRetentionConfig::tokenRangeRetentionPriorities"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig22KvCacheRetentionConfigERKNSt6vectorI25TokenRangeRetentionConfigEE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE19KvCacheTransferModeNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::KvCacheRetentionConfig::transferMode"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfigE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig25TokenRangeRetentionConfigE10SizeType32NSt8optionalI10SizeType32EE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::TokenRangeRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig25TokenRangeRetentionConfigE10SizeType32NSt8optionalI10SizeType32EE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::TokenRangeRetentionConfig::durationMs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig25TokenRangeRetentionConfigE10SizeType32NSt8optionalI10SizeType32EE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::TokenRangeRetentionConfig::priority"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig25TokenRangeRetentionConfigE10SizeType32NSt8optionalI10SizeType32EE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::TokenRangeRetentionConfig::tokenEnd"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig25TokenRangeRetentionConfigE10SizeType32NSt8optionalI10SizeType32EE17RetentionPriorityNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::TokenRangeRetentionConfig::tokenStart"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig10durationMsE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::durationMs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfigeqERK25TokenRangeRetentionConfig", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfigeqERK25TokenRangeRetentionConfig", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::operator==::other"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig8priorityE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::priority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig8tokenEndE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::tokenEnd"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25TokenRangeRetentionConfig10tokenStartE", "tensorrt_llm::executor::KvCacheRetentionConfig::TokenRangeRetentionConfig::tokenStart"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig19getDecodeDurationMsEv", "tensorrt_llm::executor::KvCacheRetentionConfig::getDecodeDurationMs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig26getDecodeRetentionPriorityEv", "tensorrt_llm::executor::KvCacheRetentionConfig::getDecodeRetentionPriority"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig12getDirectoryEv", "tensorrt_llm::executor::KvCacheRetentionConfig::getDirectory"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig36getPerBlockRetentionPriorityDurationE10SizeType3210SizeType32", "tensorrt_llm::executor::KvCacheRetentionConfig::getPerBlockRetentionPriorityDuration"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig36getPerBlockRetentionPriorityDurationE10SizeType3210SizeType32", "tensorrt_llm::executor::KvCacheRetentionConfig::getPerBlockRetentionPriorityDuration::blockSize"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig36getPerBlockRetentionPriorityDurationE10SizeType3210SizeType32", "tensorrt_llm::executor::KvCacheRetentionConfig::getPerBlockRetentionPriorityDuration::seqLen"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig29getTokenRangeRetentionConfigsEv", "tensorrt_llm::executor::KvCacheRetentionConfig::getTokenRangeRetentionConfigs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfig15getTransferModeEv", "tensorrt_llm::executor::KvCacheRetentionConfig::getTransferMode"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig25kDefaultRetentionPriorityE", "tensorrt_llm::executor::KvCacheRetentionConfig::kDefaultRetentionPriority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig21kMaxRetentionPriorityE", "tensorrt_llm::executor::KvCacheRetentionConfig::kMaxRetentionPriority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig21kMinRetentionPriorityE", "tensorrt_llm::executor::KvCacheRetentionConfig::kMinRetentionPriority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig17mDecodeDurationMsE", "tensorrt_llm::executor::KvCacheRetentionConfig::mDecodeDurationMs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig24mDecodeRetentionPriorityE", "tensorrt_llm::executor::KvCacheRetentionConfig::mDecodeRetentionPriority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig10mDirectoryE", "tensorrt_llm::executor::KvCacheRetentionConfig::mDirectory"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig27mTokenRangeRetentionConfigsE", "tensorrt_llm::executor::KvCacheRetentionConfig::mTokenRangeRetentionConfigs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor22KvCacheRetentionConfig13mTransferModeE", "tensorrt_llm::executor::KvCacheRetentionConfig::mTransferMode"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfigeqERK22KvCacheRetentionConfig", "tensorrt_llm::executor::KvCacheRetentionConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor22KvCacheRetentionConfigeqERK22KvCacheRetentionConfig", "tensorrt_llm::executor::KvCacheRetentionConfig::operator==::other"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStatsE", "tensorrt_llm::executor::KvCacheStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats14allocNewBlocksE", "tensorrt_llm::executor::KvCacheStats::allocNewBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats16allocTotalBlocksE", "tensorrt_llm::executor::KvCacheStats::allocTotalBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12cacheHitRateE", "tensorrt_llm::executor::KvCacheStats::cacheHitRate"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats13freeNumBlocksE", "tensorrt_llm::executor::KvCacheStats::freeNumBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12maxNumBlocksE", "tensorrt_llm::executor::KvCacheStats::maxNumBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12missedBlocksE", "tensorrt_llm::executor::KvCacheStats::missedBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12reusedBlocksE", "tensorrt_llm::executor::KvCacheStats::reusedBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats14tokensPerBlockE", "tensorrt_llm::executor::KvCacheStats::tokensPerBlock"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats13usedNumBlocksE", "tensorrt_llm::executor::KvCacheStats::usedNumBlocks"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor19KvCacheTransferModeE", "tensorrt_llm::executor::KvCacheTransferMode"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor19KvCacheTransferMode4DRAME", "tensorrt_llm::executor::KvCacheTransferMode::DRAM"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor19KvCacheTransferMode3GDSE", "tensorrt_llm::executor::KvCacheTransferMode::GDS"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor19KvCacheTransferMode20POSIX_DEBUG_FALLBACKE", "tensorrt_llm::executor::KvCacheTransferMode::POSIX_DEBUG_FALLBACK"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor19LogitsPostProcessorE", "tensorrt_llm::executor::LogitsPostProcessor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor26LogitsPostProcessorBatchedE", "tensorrt_llm::executor::LogitsPostProcessorBatched"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfigE", "tensorrt_llm::executor::LogitsPostProcessorConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig25LogitsPostProcessorConfigENSt8optionalI22LogitsPostProcessorMapEENSt8optionalI26LogitsPostProcessorBatchedEEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::LogitsPostProcessorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig25LogitsPostProcessorConfigENSt8optionalI22LogitsPostProcessorMapEENSt8optionalI26LogitsPostProcessorBatchedEEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::LogitsPostProcessorConfig::processorBatched"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig25LogitsPostProcessorConfigENSt8optionalI22LogitsPostProcessorMapEENSt8optionalI26LogitsPostProcessorBatchedEEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::LogitsPostProcessorConfig::processorMap"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig25LogitsPostProcessorConfigENSt8optionalI22LogitsPostProcessorMapEENSt8optionalI26LogitsPostProcessorBatchedEEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::LogitsPostProcessorConfig::replicate"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig19getProcessorBatchedEv", "tensorrt_llm::executor::LogitsPostProcessorConfig::getProcessorBatched"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig15getProcessorMapEv", "tensorrt_llm::executor::LogitsPostProcessorConfig::getProcessorMap"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig12getReplicateEv", "tensorrt_llm::executor::LogitsPostProcessorConfig::getReplicate"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig17mProcessorBatchedE", "tensorrt_llm::executor::LogitsPostProcessorConfig::mProcessorBatched"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig13mProcessorMapE", "tensorrt_llm::executor::LogitsPostProcessorConfig::mProcessorMap"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig10mReplicateE", "tensorrt_llm::executor::LogitsPostProcessorConfig::mReplicate"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig19setProcessorBatchedERK26LogitsPostProcessorBatched", "tensorrt_llm::executor::LogitsPostProcessorConfig::setProcessorBatched"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig19setProcessorBatchedERK26LogitsPostProcessorBatched", "tensorrt_llm::executor::LogitsPostProcessorConfig::setProcessorBatched::processorBatched"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig15setProcessorMapERK22LogitsPostProcessorMap", "tensorrt_llm::executor::LogitsPostProcessorConfig::setProcessorMap"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig15setProcessorMapERK22LogitsPostProcessorMap", "tensorrt_llm::executor::LogitsPostProcessorConfig::setProcessorMap::processorMap"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig12setReplicateEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::setReplicate"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig12setReplicateEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::setReplicate::replicate"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor22LogitsPostProcessorMapE", "tensorrt_llm::executor::LogitsPostProcessorMap"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfigE", "tensorrt_llm::executor::LookaheadDecodingConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::LookaheadDecodingConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigEv", "tensorrt_llm::executor::LookaheadDecodingConfig::LookaheadDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::LookaheadDecodingConfig::ngramSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::LookaheadDecodingConfig::verificationSetSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::LookaheadDecodingConfig::windowSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig28calculateSpeculativeResourceEv", "tensorrt_llm::executor::LookaheadDecodingConfig::calculateSpeculativeResource"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig33calculateSpeculativeResourceTupleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::calculateSpeculativeResourceTuple"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig33calculateSpeculativeResourceTupleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::calculateSpeculativeResourceTuple::ngramSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig33calculateSpeculativeResourceTupleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::calculateSpeculativeResourceTuple::verificationSetSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig33calculateSpeculativeResourceTupleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::calculateSpeculativeResourceTuple::windowSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig3getEv", "tensorrt_llm::executor::LookaheadDecodingConfig::get"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig12getNgramSizeEv", "tensorrt_llm::executor::LookaheadDecodingConfig::getNgramSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig22getVerificationSetSizeEv", "tensorrt_llm::executor::LookaheadDecodingConfig::getVerificationSetSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig13getWindowSizeEv", "tensorrt_llm::executor::LookaheadDecodingConfig::getWindowSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig4isLEERK23LookaheadDecodingConfig", "tensorrt_llm::executor::LookaheadDecodingConfig::isLE"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig4isLEERK23LookaheadDecodingConfig", "tensorrt_llm::executor::LookaheadDecodingConfig::isLE::that"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig7isLegalE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::isLegal"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig7isLegalE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::isLegal::ngramSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig7isLegalE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::isLegal::verificationSetSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig7isLegalE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::isLegal::windowSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig30kDefaultLookaheadDecodingNgramE", "tensorrt_llm::executor::LookaheadDecodingConfig::kDefaultLookaheadDecodingNgram"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig40kDefaultLookaheadDecodingVerificationSetE", "tensorrt_llm::executor::LookaheadDecodingConfig::kDefaultLookaheadDecodingVerificationSet"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig31kDefaultLookaheadDecodingWindowE", "tensorrt_llm::executor::LookaheadDecodingConfig::kDefaultLookaheadDecodingWindow"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig10mNgramSizeE", "tensorrt_llm::executor::LookaheadDecodingConfig::mNgramSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig20mVerificationSetSizeE", "tensorrt_llm::executor::LookaheadDecodingConfig::mVerificationSetSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig11mWindowSizeE", "tensorrt_llm::executor::LookaheadDecodingConfig::mWindowSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfigeqERK23LookaheadDecodingConfig", "tensorrt_llm::executor::LookaheadDecodingConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfigeqERK23LookaheadDecodingConfig", "tensorrt_llm::executor::LookaheadDecodingConfig::operator==::other"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfigE", "tensorrt_llm::executor::LoraConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig10LoraConfigE6IdTypeNSt8optionalI6TensorEENSt8optionalI6TensorEE", "tensorrt_llm::executor::LoraConfig::LoraConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig10LoraConfigE6IdTypeNSt8optionalI6TensorEENSt8optionalI6TensorEE", "tensorrt_llm::executor::LoraConfig::LoraConfig::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig10LoraConfigE6IdTypeNSt8optionalI6TensorEENSt8optionalI6TensorEE", "tensorrt_llm::executor::LoraConfig::LoraConfig::taskId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig10LoraConfigE6IdTypeNSt8optionalI6TensorEENSt8optionalI6TensorEE", "tensorrt_llm::executor::LoraConfig::LoraConfig::weights"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor10LoraConfig9getConfigEv", "tensorrt_llm::executor::LoraConfig::getConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor10LoraConfig9getTaskIdEv", "tensorrt_llm::executor::LoraConfig::getTaskId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor10LoraConfig10getWeightsEv", "tensorrt_llm::executor::LoraConfig::getWeights"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig7mConfigE", "tensorrt_llm::executor::LoraConfig::mConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig7mTaskIdE", "tensorrt_llm::executor::LoraConfig::mTaskId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig8mWeightsE", "tensorrt_llm::executor::LoraConfig::mWeights"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor13MedusaChoicesE", "tensorrt_llm::executor::MedusaChoices"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor10MemoryTypeE", "tensorrt_llm::executor::MemoryType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType4kCPUE", "tensorrt_llm::executor::MemoryType::kCPU"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType11kCPU_PINNEDE", "tensorrt_llm::executor::MemoryType::kCPU_PINNED"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType15kCPU_PINNEDPOOLE", "tensorrt_llm::executor::MemoryType::kCPU_PINNEDPOOL"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType4kGPUE", "tensorrt_llm::executor::MemoryType::kGPU"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType8kUNKNOWNE", "tensorrt_llm::executor::MemoryType::kUNKNOWN"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType4kUVME", "tensorrt_llm::executor::MemoryType::kUVM"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor16MillisecondsTypeE", "tensorrt_llm::executor::MillisecondsType"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor9ModelTypeE", "tensorrt_llm::executor::ModelType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor9ModelType13kDECODER_ONLYE", "tensorrt_llm::executor::ModelType::kDECODER_ONLY"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor9ModelType16kENCODER_DECODERE", "tensorrt_llm::executor::ModelType::kENCODER_DECODER"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor9ModelType13kENCODER_ONLYE", "tensorrt_llm::executor::ModelType::kENCODER_ONLY"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor11MropeConfigE", "tensorrt_llm::executor::MropeConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11MropeConfig11MropeConfigE6Tensor10SizeType32", "tensorrt_llm::executor::MropeConfig::MropeConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11MropeConfig11MropeConfigE6Tensor10SizeType32", "tensorrt_llm::executor::MropeConfig::MropeConfig::mropePositionDeltas"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11MropeConfig11MropeConfigE6Tensor10SizeType32", "tensorrt_llm::executor::MropeConfig::MropeConfig::mropeRoratySinCos"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11MropeConfig22getMRopePositionDeltasEv", "tensorrt_llm::executor::MropeConfig::getMRopePositionDeltas"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor11MropeConfig20getMRopeRotaryCosSinEv", "tensorrt_llm::executor::MropeConfig::getMRopeRotaryCosSin"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11MropeConfig20mMRopePositionDeltasE", "tensorrt_llm::executor::MropeConfig::mMRopePositionDeltas"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11MropeConfig18mMRopeRotaryCosSinE", "tensorrt_llm::executor::MropeConfig::mMRopeRotaryCosSin"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor15MultimodalInputE", "tensorrt_llm::executor::MultimodalInput"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15MultimodalInput15MultimodalInputENSt6vectorINSt6vectorI10SizeType32EEEENSt6vectorI10SizeType32EENSt6vectorI10SizeType32EE", "tensorrt_llm::executor::MultimodalInput::MultimodalInput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15MultimodalInput15MultimodalInputENSt6vectorINSt6vectorI10SizeType32EEEENSt6vectorI10SizeType32EENSt6vectorI10SizeType32EE", "tensorrt_llm::executor::MultimodalInput::MultimodalInput::multimodalHashes"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15MultimodalInput15MultimodalInputENSt6vectorINSt6vectorI10SizeType32EEEENSt6vectorI10SizeType32EENSt6vectorI10SizeType32EE", "tensorrt_llm::executor::MultimodalInput::MultimodalInput::multimodalLengths"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15MultimodalInput15MultimodalInputENSt6vectorINSt6vectorI10SizeType32EEEENSt6vectorI10SizeType32EENSt6vectorI10SizeType32EE", "tensorrt_llm::executor::MultimodalInput::MultimodalInput::multimodalPositions"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15MultimodalInput19getMultimodalHashesEv", "tensorrt_llm::executor::MultimodalInput::getMultimodalHashes"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15MultimodalInput20getMultimodalLengthsEv", "tensorrt_llm::executor::MultimodalInput::getMultimodalLengths"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15MultimodalInput22getMultimodalPositionsEv", "tensorrt_llm::executor::MultimodalInput::getMultimodalPositions"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15MultimodalInput17mMultimodalHashesE", "tensorrt_llm::executor::MultimodalInput::mMultimodalHashes"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15MultimodalInput18mMultimodalLengthsE", "tensorrt_llm::executor::MultimodalInput::mMultimodalLengths"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15MultimodalInput20mMultimodalPositionsE", "tensorrt_llm::executor::MultimodalInput::mMultimodalPositions"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfigE", "tensorrt_llm::executor::OrchestratorConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb", "tensorrt_llm::executor::OrchestratorConfig::OrchestratorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb", "tensorrt_llm::executor::OrchestratorConfig::OrchestratorConfig::isOrchestrator"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb", "tensorrt_llm::executor::OrchestratorConfig::OrchestratorConfig::orchLeaderComm"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb", "tensorrt_llm::executor::OrchestratorConfig::OrchestratorConfig::spawnProcesses"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb", "tensorrt_llm::executor::OrchestratorConfig::OrchestratorConfig::workerExecutablePath"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getIsOrchestratorEv", "tensorrt_llm::executor::OrchestratorConfig::getIsOrchestrator"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getOrchLeaderCommEv", "tensorrt_llm::executor::OrchestratorConfig::getOrchLeaderComm"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getSpawnProcessesEv", "tensorrt_llm::executor::OrchestratorConfig::getSpawnProcesses"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig23getWorkerExecutablePathEv", "tensorrt_llm::executor::OrchestratorConfig::getWorkerExecutablePath"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mIsOrchestratorE", "tensorrt_llm::executor::OrchestratorConfig::mIsOrchestrator"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mOrchLeaderCommE", "tensorrt_llm::executor::OrchestratorConfig::mOrchLeaderComm"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mSpawnProcessesE", "tensorrt_llm::executor::OrchestratorConfig::mSpawnProcesses"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig21mWorkerExecutablePathE", "tensorrt_llm::executor::OrchestratorConfig::mWorkerExecutablePath"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setIsOrchestratorEb", "tensorrt_llm::executor::OrchestratorConfig::setIsOrchestrator"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setIsOrchestratorEb", "tensorrt_llm::executor::OrchestratorConfig::setIsOrchestrator::isOrchestrator"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setOrchLeaderCommERKNSt10shared_ptrIN3mpi7MpiCommEEE", "tensorrt_llm::executor::OrchestratorConfig::setOrchLeaderComm"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setOrchLeaderCommERKNSt10shared_ptrIN3mpi7MpiCommEEE", "tensorrt_llm::executor::OrchestratorConfig::setOrchLeaderComm::orchLeaderComm"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setSpawnProcessesEb", "tensorrt_llm::executor::OrchestratorConfig::setSpawnProcesses"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setSpawnProcessesEb", "tensorrt_llm::executor::OrchestratorConfig::setSpawnProcesses::spawnProcesses"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig23setWorkerExecutablePathERKNSt6stringE", "tensorrt_llm::executor::OrchestratorConfig::setWorkerExecutablePath"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig23setWorkerExecutablePathERKNSt6stringE", "tensorrt_llm::executor::OrchestratorConfig::setWorkerExecutablePath::workerExecutablePath"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfigE", "tensorrt_llm::executor::OutputConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", "tensorrt_llm::executor::OutputConfig::OutputConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", "tensorrt_llm::executor::OutputConfig::OutputConfig::additionalModelOutputs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", "tensorrt_llm::executor::OutputConfig::OutputConfig::excludeInputFromOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", "tensorrt_llm::executor::OutputConfig::OutputConfig::returnContextLogits"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", "tensorrt_llm::executor::OutputConfig::OutputConfig::returnEncoderOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", "tensorrt_llm::executor::OutputConfig::OutputConfig::returnGenerationLogits"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", "tensorrt_llm::executor::OutputConfig::OutputConfig::returnLogProbs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbbbNSt8optionalINSt6vectorI21AdditionalModelOutputEEEE", "tensorrt_llm::executor::OutputConfig::OutputConfig::returnPerfMetrics"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig22additionalModelOutputsE", "tensorrt_llm::executor::OutputConfig::additionalModelOutputs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig22excludeInputFromOutputE", "tensorrt_llm::executor::OutputConfig::excludeInputFromOutput"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig19returnContextLogitsE", "tensorrt_llm::executor::OutputConfig::returnContextLogits"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig19returnEncoderOutputE", "tensorrt_llm::executor::OutputConfig::returnEncoderOutput"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig22returnGenerationLogitsE", "tensorrt_llm::executor::OutputConfig::returnGenerationLogits"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig14returnLogProbsE", "tensorrt_llm::executor::OutputConfig::returnLogProbs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig17returnPerfMetricsE", "tensorrt_llm::executor::OutputConfig::returnPerfMetrics"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfigE", "tensorrt_llm::executor::ParallelConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEENSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEENSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig::commMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEENSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig::commType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEENSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig::deviceIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEENSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig::numNodes"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEENSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig::orchestratorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEENSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig::participantIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig20getCommunicationModeEv", "tensorrt_llm::executor::ParallelConfig::getCommunicationMode"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig20getCommunicationTypeEv", "tensorrt_llm::executor::ParallelConfig::getCommunicationType"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig12getDeviceIdsEv", "tensorrt_llm::executor::ParallelConfig::getDeviceIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig11getNumNodesEv", "tensorrt_llm::executor::ParallelConfig::getNumNodes"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig21getOrchestratorConfigEv", "tensorrt_llm::executor::ParallelConfig::getOrchestratorConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig17getParticipantIdsEv", "tensorrt_llm::executor::ParallelConfig::getParticipantIds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig9mCommModeE", "tensorrt_llm::executor::ParallelConfig::mCommMode"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig9mCommTypeE", "tensorrt_llm::executor::ParallelConfig::mCommType"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig10mDeviceIdsE", "tensorrt_llm::executor::ParallelConfig::mDeviceIds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig9mNumNodesE", "tensorrt_llm::executor::ParallelConfig::mNumNodes"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig19mOrchestratorConfigE", "tensorrt_llm::executor::ParallelConfig::mOrchestratorConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig15mParticipantIdsE", "tensorrt_llm::executor::ParallelConfig::mParticipantIds"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationModeE17CommunicationMode", "tensorrt_llm::executor::ParallelConfig::setCommunicationMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationModeE17CommunicationMode", "tensorrt_llm::executor::ParallelConfig::setCommunicationMode::mode"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationTypeE17CommunicationType", "tensorrt_llm::executor::ParallelConfig::setCommunicationType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationTypeE17CommunicationType", "tensorrt_llm::executor::ParallelConfig::setCommunicationType::type"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig12setDeviceIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::setDeviceIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig12setDeviceIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::setDeviceIds::deviceIds"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig11setNumNodesE10SizeType32", "tensorrt_llm::executor::ParallelConfig::setNumNodes"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig11setNumNodesE10SizeType32", "tensorrt_llm::executor::ParallelConfig::setNumNodes::numNodes"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig21setOrchestratorConfigERK18OrchestratorConfig", "tensorrt_llm::executor::ParallelConfig::setOrchestratorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig21setOrchestratorConfigERK18OrchestratorConfig", "tensorrt_llm::executor::ParallelConfig::setOrchestratorConfig::orchestratorConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig17setParticipantIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::setParticipantIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig17setParticipantIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::setParticipantIds::participantIds"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfigE", "tensorrt_llm::executor::PeftCacheConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::deviceCachePercent"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::hostCacheSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::loraPrefetchDir"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::maxAdapterSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::maxPagesPerBlockDevice"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::maxPagesPerBlockHost"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::numCopyStreams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::numDeviceModuleLayer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::numEnsureWorkers"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::numHostModuleLayer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::numPutWorkers"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEERKNSt8optionalINSt6stringEEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::optimalAdapterSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getDeviceCachePercentEv", "tensorrt_llm::executor::PeftCacheConfig::getDeviceCachePercent"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig16getHostCacheSizeEv", "tensorrt_llm::executor::PeftCacheConfig::getHostCacheSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig18getLoraPrefetchDirEv", "tensorrt_llm::executor::PeftCacheConfig::getLoraPrefetchDir"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig17getMaxAdapterSizeEv", "tensorrt_llm::executor::PeftCacheConfig::getMaxAdapterSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig25getMaxPagesPerBlockDeviceEv", "tensorrt_llm::executor::PeftCacheConfig::getMaxPagesPerBlockDevice"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig23getMaxPagesPerBlockHostEv", "tensorrt_llm::executor::PeftCacheConfig::getMaxPagesPerBlockHost"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig17getNumCopyStreamsEv", "tensorrt_llm::executor::PeftCacheConfig::getNumCopyStreams"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig23getNumDeviceModuleLayerEv", "tensorrt_llm::executor::PeftCacheConfig::getNumDeviceModuleLayer"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig19getNumEnsureWorkersEv", "tensorrt_llm::executor::PeftCacheConfig::getNumEnsureWorkers"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getNumHostModuleLayerEv", "tensorrt_llm::executor::PeftCacheConfig::getNumHostModuleLayer"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig16getNumPutWorkersEv", "tensorrt_llm::executor::PeftCacheConfig::getNumPutWorkers"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getOptimalAdapterSizeEv", "tensorrt_llm::executor::PeftCacheConfig::getOptimalAdapterSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig22kDefaultMaxAdapterSizeE", "tensorrt_llm::executor::PeftCacheConfig::kDefaultMaxAdapterSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig30kDefaultMaxPagesPerBlockDeviceE", "tensorrt_llm::executor::PeftCacheConfig::kDefaultMaxPagesPerBlockDevice"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig28kDefaultMaxPagesPerBlockHostE", "tensorrt_llm::executor::PeftCacheConfig::kDefaultMaxPagesPerBlockHost"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig26kDefaultOptimalAdapterSizeE", "tensorrt_llm::executor::PeftCacheConfig::kDefaultOptimalAdapterSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mDeviceCachePercentE", "tensorrt_llm::executor::PeftCacheConfig::mDeviceCachePercent"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig14mHostCacheSizeE", "tensorrt_llm::executor::PeftCacheConfig::mHostCacheSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig16mLoraPrefetchDirE", "tensorrt_llm::executor::PeftCacheConfig::mLoraPrefetchDir"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15mMaxAdapterSizeE", "tensorrt_llm::executor::PeftCacheConfig::mMaxAdapterSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig23mMaxPagesPerBlockDeviceE", "tensorrt_llm::executor::PeftCacheConfig::mMaxPagesPerBlockDevice"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig21mMaxPagesPerBlockHostE", "tensorrt_llm::executor::PeftCacheConfig::mMaxPagesPerBlockHost"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15mNumCopyStreamsE", "tensorrt_llm::executor::PeftCacheConfig::mNumCopyStreams"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig21mNumDeviceModuleLayerE", "tensorrt_llm::executor::PeftCacheConfig::mNumDeviceModuleLayer"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig17mNumEnsureWorkersE", "tensorrt_llm::executor::PeftCacheConfig::mNumEnsureWorkers"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mNumHostModuleLayerE", "tensorrt_llm::executor::PeftCacheConfig::mNumHostModuleLayer"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig14mNumPutWorkersE", "tensorrt_llm::executor::PeftCacheConfig::mNumPutWorkers"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mOptimalAdapterSizeE", "tensorrt_llm::executor::PeftCacheConfig::mOptimalAdapterSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfigeqERK15PeftCacheConfig", "tensorrt_llm::executor::PeftCacheConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfigeqERK15PeftCacheConfig", "tensorrt_llm::executor::PeftCacheConfig::operator==::other"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor12PriorityTypeE", "tensorrt_llm::executor::PriorityType"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfigE", "tensorrt_llm::executor::PromptTuningConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig18PromptTuningConfigE6TensorNSt8optionalI16VecTokenExtraIdsEE", "tensorrt_llm::executor::PromptTuningConfig::PromptTuningConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig18PromptTuningConfigE6TensorNSt8optionalI16VecTokenExtraIdsEE", "tensorrt_llm::executor::PromptTuningConfig::PromptTuningConfig::embeddingTable"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig18PromptTuningConfigE6TensorNSt8optionalI16VecTokenExtraIdsEE", "tensorrt_llm::executor::PromptTuningConfig::PromptTuningConfig::inputTokenExtraIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18PromptTuningConfig17getEmbeddingTableEv", "tensorrt_llm::executor::PromptTuningConfig::getEmbeddingTable"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor18PromptTuningConfig21getInputTokenExtraIdsEv", "tensorrt_llm::executor::PromptTuningConfig::getInputTokenExtraIds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig15mEmbeddingTableE", "tensorrt_llm::executor::PromptTuningConfig::mEmbeddingTable"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig19mInputTokenExtraIdsE", "tensorrt_llm::executor::PromptTuningConfig::mInputTokenExtraIds"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor14RandomSeedTypeE", "tensorrt_llm::executor::RandomSeedType"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor7RequestE", "tensorrt_llm::executor::Request"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestERK7Request", "tensorrt_llm::executor::Request::Request"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestERR7Request", "tensorrt_llm::executor::Request::Request"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::allottedTimeMs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::badWords"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::clientId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::contextPhaseParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::crossAttentionMask"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::eagleConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::embeddingBias"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::encoderInputFeatures"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::encoderInputTokenIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::encoderOutputLength"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::endId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::externalDraftTokensConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::guidedDecodingParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::inputTokenIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::kvCacheRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::languageAdapterUid"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::logitsPostProcessor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::logitsPostProcessorName"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::lookaheadConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::loraConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::mRopeConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::maxTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::multimodalEmbedding"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::multimodalInput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::numReturnSequences"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestERK7Request", "tensorrt_llm::executor::Request::Request::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestERR7Request", "tensorrt_llm::executor::Request::Request::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::outputConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::pTuningConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::padId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::positionIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::priority"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::returnAllGeneratedTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::samplingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::skipCrossAttnBlocks"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::stopWords"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::streaming"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI15MultimodalInputEENSt8optionalI6TensorEENSt8optionalI11MropeConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI22KvCacheRetentionConfigEENSt8optionalINSt6stringEEENSt8optionalI19LogitsPostProcessorEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EENSt8optionalI6TensorEE10SizeType32NSt8optionalI11EagleConfigEENSt8optionalI6TensorEENSt8optionalI20GuidedDecodingParamsEENSt8optionalI10SizeType32EENSt8optionalI16MillisecondsTypeEE", "tensorrt_llm::executor::Request::Request::type"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request24getAdditionalOutputNamesEv", "tensorrt_llm::executor::Request::getAdditionalOutputNames"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request17getAllottedTimeMsEv", "tensorrt_llm::executor::Request::getAllottedTimeMs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request11getBadWordsEv", "tensorrt_llm::executor::Request::getBadWords"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request11getClientIdEv", "tensorrt_llm::executor::Request::getClientId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request21getContextPhaseParamsEv", "tensorrt_llm::executor::Request::getContextPhaseParams"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request21getCrossAttentionMaskEv", "tensorrt_llm::executor::Request::getCrossAttentionMask"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request14getEagleConfigEv", "tensorrt_llm::executor::Request::getEagleConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request16getEmbeddingBiasEv", "tensorrt_llm::executor::Request::getEmbeddingBias"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request23getEncoderInputFeaturesEv", "tensorrt_llm::executor::Request::getEncoderInputFeatures"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request23getEncoderInputTokenIdsEv", "tensorrt_llm::executor::Request::getEncoderInputTokenIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request22getEncoderOutputLengthEv", "tensorrt_llm::executor::Request::getEncoderOutputLength"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request8getEndIdEv", "tensorrt_llm::executor::Request::getEndId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request28getExternalDraftTokensConfigEv", "tensorrt_llm::executor::Request::getExternalDraftTokensConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request23getGuidedDecodingParamsEv", "tensorrt_llm::executor::Request::getGuidedDecodingParams"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request16getInputTokenIdsEv", "tensorrt_llm::executor::Request::getInputTokenIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request25getKvCacheRetentionConfigEv", "tensorrt_llm::executor::Request::getKvCacheRetentionConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request21getLanguageAdapterUidEv", "tensorrt_llm::executor::Request::getLanguageAdapterUid"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request22getLogitsPostProcessorEv", "tensorrt_llm::executor::Request::getLogitsPostProcessor"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request26getLogitsPostProcessorNameEv", "tensorrt_llm::executor::Request::getLogitsPostProcessorName"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request18getLookaheadConfigEv", "tensorrt_llm::executor::Request::getLookaheadConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request13getLoraConfigEv", "tensorrt_llm::executor::Request::getLoraConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request12getMaxTokensEv", "tensorrt_llm::executor::Request::getMaxTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request14getMropeConfigEv", "tensorrt_llm::executor::Request::getMropeConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request22getMultimodalEmbeddingEv", "tensorrt_llm::executor::Request::getMultimodalEmbedding"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request18getMultimodalInputEv", "tensorrt_llm::executor::Request::getMultimodalInput"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request15getOutputConfigEv", "tensorrt_llm::executor::Request::getOutputConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request8getPadIdEv", "tensorrt_llm::executor::Request::getPadId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request14getPositionIdsEv", "tensorrt_llm::executor::Request::getPositionIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request11getPriorityEv", "tensorrt_llm::executor::Request::getPriority"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request21getPromptTuningConfigEv", "tensorrt_llm::executor::Request::getPromptTuningConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request14getRequestTypeEv", "tensorrt_llm::executor::Request::getRequestType"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request27getReturnAllGeneratedTokensEv", "tensorrt_llm::executor::Request::getReturnAllGeneratedTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request17getSamplingConfigEv", "tensorrt_llm::executor::Request::getSamplingConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request22getSkipCrossAttnBlocksEv", "tensorrt_llm::executor::Request::getSkipCrossAttnBlocks"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request12getStopWordsEv", "tensorrt_llm::executor::Request::getStopWords"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor7Request12getStreamingEv", "tensorrt_llm::executor::Request::getStreaming"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request25kBatchedPostProcessorNameE", "tensorrt_llm::executor::Request::kBatchedPostProcessorName"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request16kDefaultPriorityE", "tensorrt_llm::executor::Request::kDefaultPriority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request31kDynamicPostProcessorNamePrefixE", "tensorrt_llm::executor::Request::kDynamicPostProcessorNamePrefix"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request5mImplE", "tensorrt_llm::executor::Request::mImpl"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7RequestaSERK7Request", "tensorrt_llm::executor::Request::operator="], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7RequestaSERR7Request", "tensorrt_llm::executor::Request::operator="], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7RequestaSERK7Request", "tensorrt_llm::executor::Request::operator=::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7RequestaSERR7Request", "tensorrt_llm::executor::Request::operator=::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request17setAllottedTimeMsE16MillisecondsType", "tensorrt_llm::executor::Request::setAllottedTimeMs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request17setAllottedTimeMsE16MillisecondsType", "tensorrt_llm::executor::Request::setAllottedTimeMs::allottedTimeMs"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request11setBadWordsERKNSt4listI9VecTokensEE", "tensorrt_llm::executor::Request::setBadWords"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request11setBadWordsERKNSt4listI9VecTokensEE", "tensorrt_llm::executor::Request::setBadWords::badWords"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request11setClientIdE6IdType", "tensorrt_llm::executor::Request::setClientId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request11setClientIdE6IdType", "tensorrt_llm::executor::Request::setClientId::clientId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request21setContextPhaseParamsE18ContextPhaseParams", "tensorrt_llm::executor::Request::setContextPhaseParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request21setContextPhaseParamsE18ContextPhaseParams", "tensorrt_llm::executor::Request::setContextPhaseParams::contextPhaseParams"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request21setCrossAttentionMaskE6Tensor", "tensorrt_llm::executor::Request::setCrossAttentionMask"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request21setCrossAttentionMaskE6Tensor", "tensorrt_llm::executor::Request::setCrossAttentionMask::crossAttentionMask"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request14setEagleConfigERKNSt8optionalI11EagleConfigEE", "tensorrt_llm::executor::Request::setEagleConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request14setEagleConfigERKNSt8optionalI11EagleConfigEE", "tensorrt_llm::executor::Request::setEagleConfig::eagleConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request16setEmbeddingBiasERK6Tensor", "tensorrt_llm::executor::Request::setEmbeddingBias"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request16setEmbeddingBiasERK6Tensor", "tensorrt_llm::executor::Request::setEmbeddingBias::embeddingBias"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputFeaturesE6Tensor", "tensorrt_llm::executor::Request::setEncoderInputFeatures"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputFeaturesE6Tensor", "tensorrt_llm::executor::Request::setEncoderInputFeatures::encoderInputFeatures"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputTokenIdsERK9VecTokens", "tensorrt_llm::executor::Request::setEncoderInputTokenIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputTokenIdsERK9VecTokens", "tensorrt_llm::executor::Request::setEncoderInputTokenIds::encoderInputTokenIds"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request22setEncoderOutputLengthE10SizeType32", "tensorrt_llm::executor::Request::setEncoderOutputLength"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request22setEncoderOutputLengthE10SizeType32", "tensorrt_llm::executor::Request::setEncoderOutputLength::encoderOutputLength"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request8setEndIdE10SizeType32", "tensorrt_llm::executor::Request::setEndId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request8setEndIdE10SizeType32", "tensorrt_llm::executor::Request::setEndId::endId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request28setExternalDraftTokensConfigERK25ExternalDraftTokensConfig", "tensorrt_llm::executor::Request::setExternalDraftTokensConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request28setExternalDraftTokensConfigERK25ExternalDraftTokensConfig", "tensorrt_llm::executor::Request::setExternalDraftTokensConfig::externalDraftTokensConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request23setGuidedDecodingParamsERK20GuidedDecodingParams", "tensorrt_llm::executor::Request::setGuidedDecodingParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request23setGuidedDecodingParamsERK20GuidedDecodingParams", "tensorrt_llm::executor::Request::setGuidedDecodingParams::guidedDecodingParams"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request25setKvCacheRetentionConfigERK22KvCacheRetentionConfig", "tensorrt_llm::executor::Request::setKvCacheRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request25setKvCacheRetentionConfigERK22KvCacheRetentionConfig", "tensorrt_llm::executor::Request::setKvCacheRetentionConfig::kvCacheRetentionConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request21setLanguageAdapterUidE10SizeType32", "tensorrt_llm::executor::Request::setLanguageAdapterUid"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request21setLanguageAdapterUidE10SizeType32", "tensorrt_llm::executor::Request::setLanguageAdapterUid::languageAdapterUid"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request22setLogitsPostProcessorERKNSt8optionalI19LogitsPostProcessorEE", "tensorrt_llm::executor::Request::setLogitsPostProcessor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request22setLogitsPostProcessorERKNSt8optionalI19LogitsPostProcessorEE", "tensorrt_llm::executor::Request::setLogitsPostProcessor::logitsPostProcessor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request26setLogitsPostProcessorNameERKNSt6stringE", "tensorrt_llm::executor::Request::setLogitsPostProcessorName"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request26setLogitsPostProcessorNameERKNSt6stringE", "tensorrt_llm::executor::Request::setLogitsPostProcessorName::logitsPostProcessorName"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request18setLookaheadConfigERK23LookaheadDecodingConfig", "tensorrt_llm::executor::Request::setLookaheadConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request18setLookaheadConfigERK23LookaheadDecodingConfig", "tensorrt_llm::executor::Request::setLookaheadConfig::lookaheadConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request13setLoraConfigERK10LoraConfig", "tensorrt_llm::executor::Request::setLoraConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request13setLoraConfigERK10LoraConfig", "tensorrt_llm::executor::Request::setLoraConfig::loraConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request14setMropeConfigERK11MropeConfig", "tensorrt_llm::executor::Request::setMropeConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request14setMropeConfigERK11MropeConfig", "tensorrt_llm::executor::Request::setMropeConfig::mRopeConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request22setMultimodalEmbeddingERK6Tensor", "tensorrt_llm::executor::Request::setMultimodalEmbedding"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request22setMultimodalEmbeddingERK6Tensor", "tensorrt_llm::executor::Request::setMultimodalEmbedding::multimodalEmbedding"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request18setMultimodalInputERK15MultimodalInput", "tensorrt_llm::executor::Request::setMultimodalInput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request18setMultimodalInputERK15MultimodalInput", "tensorrt_llm::executor::Request::setMultimodalInput::multimodalInput"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request15setOutputConfigERK12OutputConfig", "tensorrt_llm::executor::Request::setOutputConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request15setOutputConfigERK12OutputConfig", "tensorrt_llm::executor::Request::setOutputConfig::outputConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request8setPadIdE10SizeType32", "tensorrt_llm::executor::Request::setPadId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request8setPadIdE10SizeType32", "tensorrt_llm::executor::Request::setPadId::padId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request14setPositionIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::Request::setPositionIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request14setPositionIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::Request::setPositionIds::positionIds"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request11setPriorityE12PriorityType", "tensorrt_llm::executor::Request::setPriority"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request11setPriorityE12PriorityType", "tensorrt_llm::executor::Request::setPriority::priority"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request21setPromptTuningConfigERK18PromptTuningConfig", "tensorrt_llm::executor::Request::setPromptTuningConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request21setPromptTuningConfigERK18PromptTuningConfig", "tensorrt_llm::executor::Request::setPromptTuningConfig::pTuningConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request14setRequestTypeERK11RequestType", "tensorrt_llm::executor::Request::setRequestType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request14setRequestTypeERK11RequestType", "tensorrt_llm::executor::Request::setRequestType::requestType"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request27setReturnAllGeneratedTokensEb", "tensorrt_llm::executor::Request::setReturnAllGeneratedTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request27setReturnAllGeneratedTokensEb", "tensorrt_llm::executor::Request::setReturnAllGeneratedTokens::returnAllGeneratedTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request17setSamplingConfigERK14SamplingConfig", "tensorrt_llm::executor::Request::setSamplingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request17setSamplingConfigERK14SamplingConfig", "tensorrt_llm::executor::Request::setSamplingConfig::config"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request22setSkipCrossAttnBlocksE6Tensor", "tensorrt_llm::executor::Request::setSkipCrossAttnBlocks"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request22setSkipCrossAttnBlocksE6Tensor", "tensorrt_llm::executor::Request::setSkipCrossAttnBlocks::skipCrossAttnBlocks"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request12setStopWordsERKNSt4listI9VecTokensEE", "tensorrt_llm::executor::Request::setStopWords"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request12setStopWordsERKNSt4listI9VecTokensEE", "tensorrt_llm::executor::Request::setStopWords::stopWords"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7Request12setStreamingEb", "tensorrt_llm::executor::Request::setStreaming"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7Request12setStreamingEb", "tensorrt_llm::executor::Request::setStreaming::streaming"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7RequestD0Ev", "tensorrt_llm::executor::Request::~Request"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetricsE", "tensorrt_llm::executor::RequestPerfMetrics"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetricsE", "tensorrt_llm::executor::RequestPerfMetrics::KvCacheMetrics"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics14kvCacheHitRateE", "tensorrt_llm::executor::RequestPerfMetrics::KvCacheMetrics::kvCacheHitRate"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics15numMissedBlocksE", "tensorrt_llm::executor::RequestPerfMetrics::KvCacheMetrics::numMissedBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics21numNewAllocatedBlocksE", "tensorrt_llm::executor::RequestPerfMetrics::KvCacheMetrics::numNewAllocatedBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics15numReusedBlocksE", "tensorrt_llm::executor::RequestPerfMetrics::KvCacheMetrics::numReusedBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14KvCacheMetrics23numTotalAllocatedBlocksE", "tensorrt_llm::executor::RequestPerfMetrics::KvCacheMetrics::numTotalAllocatedBlocks"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics26SpeculativeDecodingMetricsE", "tensorrt_llm::executor::RequestPerfMetrics::SpeculativeDecodingMetrics"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics26SpeculativeDecodingMetrics14acceptanceRateE", "tensorrt_llm::executor::RequestPerfMetrics::SpeculativeDecodingMetrics::acceptanceRate"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics26SpeculativeDecodingMetrics24totalAcceptedDraftTokensE", "tensorrt_llm::executor::RequestPerfMetrics::SpeculativeDecodingMetrics::totalAcceptedDraftTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics26SpeculativeDecodingMetrics16totalDraftTokensE", "tensorrt_llm::executor::RequestPerfMetrics::SpeculativeDecodingMetrics::totalDraftTokens"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics9TimePointE", "tensorrt_llm::executor::RequestPerfMetrics::TimePoint"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetricsE", "tensorrt_llm::executor::RequestPerfMetrics::TimingMetrics"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics11arrivalTimeE", "tensorrt_llm::executor::RequestPerfMetrics::TimingMetrics::arrivalTime"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics18firstScheduledTimeE", "tensorrt_llm::executor::RequestPerfMetrics::TimingMetrics::firstScheduledTime"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics14firstTokenTimeE", "tensorrt_llm::executor::RequestPerfMetrics::TimingMetrics::firstTokenTime"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics11kvCacheSizeE", "tensorrt_llm::executor::RequestPerfMetrics::TimingMetrics::kvCacheSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics18kvCacheTransferEndE", "tensorrt_llm::executor::RequestPerfMetrics::TimingMetrics::kvCacheTransferEnd"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics20kvCacheTransferStartE", "tensorrt_llm::executor::RequestPerfMetrics::TimingMetrics::kvCacheTransferStart"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13TimingMetrics13lastTokenTimeE", "tensorrt_llm::executor::RequestPerfMetrics::TimingMetrics::lastTokenTime"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics9firstIterE", "tensorrt_llm::executor::RequestPerfMetrics::firstIter"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics4iterE", "tensorrt_llm::executor::RequestPerfMetrics::iter"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics14kvCacheMetricsE", "tensorrt_llm::executor::RequestPerfMetrics::kvCacheMetrics"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics8lastIterE", "tensorrt_llm::executor::RequestPerfMetrics::lastIter"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics19speculativeDecodingE", "tensorrt_llm::executor::RequestPerfMetrics::speculativeDecoding"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18RequestPerfMetrics13timingMetricsE", "tensorrt_llm::executor::RequestPerfMetrics::timingMetrics"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12RequestStageE", "tensorrt_llm::executor::RequestStage"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12RequestStage20kCONTEXT_IN_PROGRESSE", "tensorrt_llm::executor::RequestStage::kCONTEXT_IN_PROGRESS"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12RequestStage20kENCODER_IN_PROGRESSE", "tensorrt_llm::executor::RequestStage::kENCODER_IN_PROGRESS"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12RequestStage20kGENERATION_COMPLETEE", "tensorrt_llm::executor::RequestStage::kGENERATION_COMPLETE"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12RequestStage23kGENERATION_IN_PROGRESSE", "tensorrt_llm::executor::RequestStage::kGENERATION_IN_PROGRESS"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12RequestStage7kQUEUEDE", "tensorrt_llm::executor::RequestStage::kQUEUED"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor12RequestStatsE", "tensorrt_llm::executor::RequestStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats24allocNewBlocksPerRequestE", "tensorrt_llm::executor::RequestStats::allocNewBlocksPerRequest"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats26allocTotalBlocksPerRequestE", "tensorrt_llm::executor::RequestStats::allocTotalBlocksPerRequest"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats26avgNumDecodedTokensPerIterE", "tensorrt_llm::executor::RequestStats::avgNumDecodedTokensPerIter"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats22contextPrefillPositionE", "tensorrt_llm::executor::RequestStats::contextPrefillPosition"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats15disServingStatsE", "tensorrt_llm::executor::RequestStats::disServingStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats2idE", "tensorrt_llm::executor::RequestStats::id"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats24kvCacheHitRatePerRequestE", "tensorrt_llm::executor::RequestStats::kvCacheHitRatePerRequest"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats22missedBlocksPerRequestE", "tensorrt_llm::executor::RequestStats::missedBlocksPerRequest"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats18numGeneratedTokensE", "tensorrt_llm::executor::RequestStats::numGeneratedTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats6pausedE", "tensorrt_llm::executor::RequestStats::paused"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats22reusedBlocksPerRequestE", "tensorrt_llm::executor::RequestStats::reusedBlocksPerRequest"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats9scheduledE", "tensorrt_llm::executor::RequestStats::scheduled"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats5stageE", "tensorrt_llm::executor::RequestStats::stage"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIterationE", "tensorrt_llm::executor::RequestStatsPerIteration"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIteration4iterE", "tensorrt_llm::executor::RequestStatsPerIteration::iter"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIteration12requestStatsE", "tensorrt_llm::executor::RequestStatsPerIteration::requestStats"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor11RequestTypeE", "tensorrt_llm::executor::RequestType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor11RequestType35REQUEST_TYPE_CONTEXT_AND_GENERATIONE", "tensorrt_llm::executor::RequestType::REQUEST_TYPE_CONTEXT_AND_GENERATION"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor11RequestType25REQUEST_TYPE_CONTEXT_ONLYE", "tensorrt_llm::executor::RequestType::REQUEST_TYPE_CONTEXT_ONLY"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor11RequestType28REQUEST_TYPE_GENERATION_ONLYE", "tensorrt_llm::executor::RequestType::REQUEST_TYPE_GENERATION_ONLY"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8ResponseE", "tensorrt_llm::executor::Response"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdType6ResultNSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Response::Response"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdTypeNSt6stringENSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Response::Response"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERK8Response", "tensorrt_llm::executor::Response::Response"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERR8Response", "tensorrt_llm::executor::Response::Response"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdType6ResultNSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Response::Response::Result"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdType6ResultNSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Response::Response::clientId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdTypeNSt6stringENSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Response::Response::clientId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdTypeNSt6stringENSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Response::Response::errorMsg"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERK8Response", "tensorrt_llm::executor::Response::Response::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERR8Response", "tensorrt_llm::executor::Response::Response::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdType6ResultNSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Response::Response::requestId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdTypeNSt6stringENSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Response::Response::requestId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Response11getClientIdEv", "tensorrt_llm::executor::Response::getClientId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Response11getErrorMsgEv", "tensorrt_llm::executor::Response::getErrorMsg"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Response12getRequestIdEv", "tensorrt_llm::executor::Response::getRequestId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Response9getResultEv", "tensorrt_llm::executor::Response::getResult"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8Response8hasErrorEv", "tensorrt_llm::executor::Response::hasError"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Response5mImplE", "tensorrt_llm::executor::Response::mImpl"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8ResponseaSERK8Response", "tensorrt_llm::executor::Response::operator="], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8ResponseaSERR8Response", "tensorrt_llm::executor::Response::operator="], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8ResponseaSERK8Response", "tensorrt_llm::executor::Response::operator=::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8ResponseaSERR8Response", "tensorrt_llm::executor::Response::operator=::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8ResponseD0Ev", "tensorrt_llm::executor::Response::~Response"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor6ResultE", "tensorrt_llm::executor::Result"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result17additionalOutputsE", "tensorrt_llm::executor::Result::additionalOutputs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result13contextLogitsE", "tensorrt_llm::executor::Result::contextLogits"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result18contextPhaseParamsE", "tensorrt_llm::executor::Result::contextPhaseParams"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result11cumLogProbsE", "tensorrt_llm::executor::Result::cumLogProbs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result12decodingIterE", "tensorrt_llm::executor::Result::decodingIter"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result13encoderOutputE", "tensorrt_llm::executor::Result::encoderOutput"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result13finishReasonsE", "tensorrt_llm::executor::Result::finishReasons"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result16generationLogitsE", "tensorrt_llm::executor::Result::generationLogits"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result7isFinalE", "tensorrt_llm::executor::Result::isFinal"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result15isSequenceFinalE", "tensorrt_llm::executor::Result::isSequenceFinal"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result8logProbsE", "tensorrt_llm::executor::Result::logProbs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result14outputTokenIdsE", "tensorrt_llm::executor::Result::outputTokenIds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result18requestPerfMetricsE", "tensorrt_llm::executor::Result::requestPerfMetrics"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result13sequenceIndexE", "tensorrt_llm::executor::Result::sequenceIndex"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Result21specDecFastLogitsInfoE", "tensorrt_llm::executor::Result::specDecFastLogitsInfo"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor17RetentionPriorityE", "tensorrt_llm::executor::RetentionPriority"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDurationE", "tensorrt_llm::executor::RetentionPriorityAndDuration"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDuration28RetentionPriorityAndDurationERKNSt8optionalI17RetentionPriorityEERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::RetentionPriorityAndDuration::RetentionPriorityAndDuration"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDuration28RetentionPriorityAndDurationERKNSt8optionalI17RetentionPriorityEERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::RetentionPriorityAndDuration::RetentionPriorityAndDuration::durationMs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDuration28RetentionPriorityAndDurationERKNSt8optionalI17RetentionPriorityEERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::RetentionPriorityAndDuration::RetentionPriorityAndDuration::retentionPriority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDuration10durationMsE", "tensorrt_llm::executor::RetentionPriorityAndDuration::durationMs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor28RetentionPriorityAndDuration17retentionPriorityE", "tensorrt_llm::executor::RetentionPriorityAndDuration::retentionPriority"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfigE", "tensorrt_llm::executor::SamplingConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::beamSearchDiversityRate"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::beamWidth"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::beamWidthArray"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::earlyStopping"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::frequencyPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::lengthPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::minP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::minTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::noRepeatNgramSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::numReturnSequences"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::presencePenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::repetitionPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::seed"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::temperature"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::topK"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::topP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::topPDecay"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::topPMin"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::topPResetIds"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig28checkBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkBeamSearchDiversityRate"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig28checkBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkBeamSearchDiversityRate::beamSearchDiversityRate"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkBeamWidthE10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkBeamWidth"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkBeamWidthE10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkBeamWidth::beamWidth"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19checkBeamWidthArrayERKNSt8optionalINSt6vectorI10SizeType32EEEEK10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkBeamWidthArray"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19checkBeamWidthArrayERKNSt8optionalINSt6vectorI10SizeType32EEEEK10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkBeamWidthArray::beamWidth"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19checkBeamWidthArrayERKNSt8optionalINSt6vectorI10SizeType32EEEEK10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkBeamWidthArray::beamWidthArray"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18checkEarlyStoppingERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::checkEarlyStopping"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18checkEarlyStoppingERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::checkEarlyStopping::earlyStopping"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18checkLengthPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkLengthPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18checkLengthPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkLengthPenalty::lengthPenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkMinPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkMinP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkMinPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkMinP::minP"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkMinTokensERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::checkMinTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkMinTokensERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::checkMinTokens::minTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::checkNoRepeatNgramSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::checkNoRepeatNgramSize::noRepeatNgramSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig23checkNumReturnSequencesERKNSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkNumReturnSequences"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig23checkNumReturnSequencesERKNSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkNumReturnSequences::beamWidth"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig23checkNumReturnSequencesERKNSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkNumReturnSequences::numReturnSequences"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkRepetitionPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkRepetitionPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkRepetitionPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkRepetitionPenalty::repetitionpenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16checkTemperatureERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTemperature"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16checkTemperatureERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTemperature::temperature"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopKERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopK"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopKERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopK::topK"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopP::topP"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkTopPDecayERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPDecay"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkTopPDecayERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPDecay::topPDecay"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12checkTopPMinERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPMin"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12checkTopPMinERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPMin::topPMin"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17checkTopPResetIdsERKNSt8optionalI11TokenIdTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPResetIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17checkTopPResetIdsERKNSt8optionalI11TokenIdTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPResetIds::topPResetIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig26getBeamSearchDiversityRateEv", "tensorrt_llm::executor::SamplingConfig::getBeamSearchDiversityRate"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getBeamWidthEv", "tensorrt_llm::executor::SamplingConfig::getBeamWidth"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig17getBeamWidthArrayEv", "tensorrt_llm::executor::SamplingConfig::getBeamWidthArray"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig16getEarlyStoppingEv", "tensorrt_llm::executor::SamplingConfig::getEarlyStopping"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig19getFrequencyPenaltyEv", "tensorrt_llm::executor::SamplingConfig::getFrequencyPenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig16getLengthPenaltyEv", "tensorrt_llm::executor::SamplingConfig::getLengthPenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getMinPEv", "tensorrt_llm::executor::SamplingConfig::getMinP"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getMinTokensEv", "tensorrt_llm::executor::SamplingConfig::getMinTokens"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig20getNoRepeatNgramSizeEv", "tensorrt_llm::executor::SamplingConfig::getNoRepeatNgramSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig17getNumReturnBeamsEv", "tensorrt_llm::executor::SamplingConfig::getNumReturnBeams"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig21getNumReturnSequencesEv", "tensorrt_llm::executor::SamplingConfig::getNumReturnSequences"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig18getPresencePenaltyEv", "tensorrt_llm::executor::SamplingConfig::getPresencePenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig20getRepetitionPenaltyEv", "tensorrt_llm::executor::SamplingConfig::getRepetitionPenalty"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getSeedEv", "tensorrt_llm::executor::SamplingConfig::getSeed"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig14getTemperatureEv", "tensorrt_llm::executor::SamplingConfig::getTemperature"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getTopKEv", "tensorrt_llm::executor::SamplingConfig::getTopK"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getTopPEv", "tensorrt_llm::executor::SamplingConfig::getTopP"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getTopPDecayEv", "tensorrt_llm::executor::SamplingConfig::getTopPDecay"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig10getTopPMinEv", "tensorrt_llm::executor::SamplingConfig::getTopPMin"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig15getTopPResetIdsEv", "tensorrt_llm::executor::SamplingConfig::getTopPResetIds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig24mBeamSearchDiversityRateE", "tensorrt_llm::executor::SamplingConfig::mBeamSearchDiversityRate"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mBeamWidthE", "tensorrt_llm::executor::SamplingConfig::mBeamWidth"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig15mBeamWidthArrayE", "tensorrt_llm::executor::SamplingConfig::mBeamWidthArray"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14mEarlyStoppingE", "tensorrt_llm::executor::SamplingConfig::mEarlyStopping"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17mFrequencyPenaltyE", "tensorrt_llm::executor::SamplingConfig::mFrequencyPenalty"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14mLengthPenaltyE", "tensorrt_llm::executor::SamplingConfig::mLengthPenalty"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mMinPE", "tensorrt_llm::executor::SamplingConfig::mMinP"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mMinTokensE", "tensorrt_llm::executor::SamplingConfig::mMinTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18mNoRepeatNgramSizeE", "tensorrt_llm::executor::SamplingConfig::mNoRepeatNgramSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig15mNumReturnBeamsE", "tensorrt_llm::executor::SamplingConfig::mNumReturnBeams"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19mNumReturnSequencesE", "tensorrt_llm::executor::SamplingConfig::mNumReturnSequences"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16mPresencePenaltyE", "tensorrt_llm::executor::SamplingConfig::mPresencePenalty"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18mRepetitionPenaltyE", "tensorrt_llm::executor::SamplingConfig::mRepetitionPenalty"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mSeedE", "tensorrt_llm::executor::SamplingConfig::mSeed"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12mTemperatureE", "tensorrt_llm::executor::SamplingConfig::mTemperature"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mTopKE", "tensorrt_llm::executor::SamplingConfig::mTopK"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mTopPE", "tensorrt_llm::executor::SamplingConfig::mTopP"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mTopPDecayE", "tensorrt_llm::executor::SamplingConfig::mTopPDecay"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig8mTopPMinE", "tensorrt_llm::executor::SamplingConfig::mTopPMin"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig13mTopPResetIdsE", "tensorrt_llm::executor::SamplingConfig::mTopPResetIds"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfigeqERK14SamplingConfig", "tensorrt_llm::executor::SamplingConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfigeqERK14SamplingConfig", "tensorrt_llm::executor::SamplingConfig::operator==::other"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig26setBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setBeamSearchDiversityRate"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig26setBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setBeamSearchDiversityRate::beamSearchDiversityRate"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setBeamWidthE10SizeType32", "tensorrt_llm::executor::SamplingConfig::setBeamWidth"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setBeamWidthE10SizeType32", "tensorrt_llm::executor::SamplingConfig::setBeamWidth::beamWidth"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17setBeamWidthArrayERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::setBeamWidthArray"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17setBeamWidthArrayERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::executor::SamplingConfig::setBeamWidthArray::beamWidthArray"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setEarlyStoppingERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setEarlyStopping"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setEarlyStoppingERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setEarlyStopping::earlyStopping"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19setFrequencyPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setFrequencyPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19setFrequencyPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setFrequencyPenalty::frequencyPenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setLengthPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setLengthPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setLengthPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setLengthPenalty::lengthPenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setMinPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setMinP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setMinPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setMinP::minP"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setMinTokensERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setMinTokens"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setMinTokensERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setMinTokens::minTokens"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setNoRepeatNgramSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setNoRepeatNgramSize::noRepeatNgramSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig21setNumReturnSequencesERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setNumReturnSequences"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig21setNumReturnSequencesERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setNumReturnSequences::numReturnSequences"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18setPresencePenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setPresencePenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18setPresencePenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setPresencePenalty::presencePenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setRepetitionPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setRepetitionPenalty"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setRepetitionPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setRepetitionPenalty::repetitionPenalty"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setSeedERKNSt8optionalI14RandomSeedTypeEE", "tensorrt_llm::executor::SamplingConfig::setSeed"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setSeedERKNSt8optionalI14RandomSeedTypeEE", "tensorrt_llm::executor::SamplingConfig::setSeed::seed"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14setTemperatureERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTemperature"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14setTemperatureERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTemperature::temperature"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopKERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setTopK"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopKERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setTopK::topK"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopP::topP"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setTopPDecayERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPDecay"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setTopPDecayERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPDecay::topPDecay"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10setTopPMinERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPMin"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10setTopPMinERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPMin::topPMin"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig15setTopPResetIdsERKNSt8optionalI11TokenIdTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPResetIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig15setTopPResetIdsERKNSt8optionalI11TokenIdTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPResetIds::topPResetIds"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20updateNumReturnBeamsEv", "tensorrt_llm::executor::SamplingConfig::updateNumReturnBeams"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfigE", "tensorrt_llm::executor::SchedulerConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig15SchedulerConfigE23CapacitySchedulerPolicyNSt8optionalI21ContextChunkingPolicyEENSt8optionalI18DynamicBatchConfigEE", "tensorrt_llm::executor::SchedulerConfig::SchedulerConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig15SchedulerConfigE23CapacitySchedulerPolicyNSt8optionalI21ContextChunkingPolicyEENSt8optionalI18DynamicBatchConfigEE", "tensorrt_llm::executor::SchedulerConfig::SchedulerConfig::capacitySchedulerPolicy"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig15SchedulerConfigE23CapacitySchedulerPolicyNSt8optionalI21ContextChunkingPolicyEENSt8optionalI18DynamicBatchConfigEE", "tensorrt_llm::executor::SchedulerConfig::SchedulerConfig::contextChunkingPolicy"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig15SchedulerConfigE23CapacitySchedulerPolicyNSt8optionalI21ContextChunkingPolicyEENSt8optionalI18DynamicBatchConfigEE", "tensorrt_llm::executor::SchedulerConfig::SchedulerConfig::dynamicBatchConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfig26getCapacitySchedulerPolicyEv", "tensorrt_llm::executor::SchedulerConfig::getCapacitySchedulerPolicy"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfig24getContextChunkingPolicyEv", "tensorrt_llm::executor::SchedulerConfig::getContextChunkingPolicy"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfig21getDynamicBatchConfigEv", "tensorrt_llm::executor::SchedulerConfig::getDynamicBatchConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig24mCapacitySchedulerPolicyE", "tensorrt_llm::executor::SchedulerConfig::mCapacitySchedulerPolicy"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig22mContextChunkingPolicyE", "tensorrt_llm::executor::SchedulerConfig::mContextChunkingPolicy"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig19mDynamicBatchConfigE", "tensorrt_llm::executor::SchedulerConfig::mDynamicBatchConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfigeqERK15SchedulerConfig", "tensorrt_llm::executor::SchedulerConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfigeqERK15SchedulerConfig", "tensorrt_llm::executor::SchedulerConfig::operator==::other"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor13SerializationE", "tensorrt_llm::executor::Serialization"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeAdditionalModelOutputERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeAdditionalModelOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeAdditionalModelOutputERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeAdditionalModelOutput::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization27deserializeAdditionalOutputERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeAdditionalOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization27deserializeAdditionalOutputERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeAdditionalOutput::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeAgentStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeAgentState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeAgentStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeAgentState::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization15deserializeBoolERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeBool"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization15deserializeBoolERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeBool::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeCacheStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeCacheState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeCacheStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeCacheState::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeCacheTransceiverConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeCacheTransceiverConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeCacheTransceiverConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeCacheTransceiverConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeCommStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeCommState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeCommStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeCommState::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeContextPhaseParamsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeContextPhaseParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeContextPhaseParamsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeContextPhaseParams::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeDataTransceiverStateERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeDataTransceiverState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeDataTransceiverStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDataTransceiverState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeDataTransceiverStateERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeDataTransceiverState::buffer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeDataTransceiverStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDataTransceiverState::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeDebugConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDebugConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeDebugConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDebugConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDecodingConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeDecodingModeERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDecodingMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeDecodingModeERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDecodingMode::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeDisServingRequestStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDisServingRequestStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeDisServingRequestStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDisServingRequestStats::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeDynamicBatchConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDynamicBatchConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeDynamicBatchConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDynamicBatchConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeEagleConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeEagleConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeEagleConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeEagleConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeExecutorConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExecutorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeExecutorConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExecutorConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization40deserializeExtendedRuntimePerfKnobConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExtendedRuntimePerfKnobConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization40deserializeExtendedRuntimePerfKnobConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExtendedRuntimePerfKnobConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeExternalDraftTokensConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExternalDraftTokensConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeExternalDraftTokensConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExternalDraftTokensConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeGuidedDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeGuidedDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeGuidedDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeGuidedDecodingConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeGuidedDecodingParamsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeGuidedDecodingParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization31deserializeGuidedDecodingParamsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeGuidedDecodingParams::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeInflightBatchingStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeInflightBatchingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeInflightBatchingStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeInflightBatchingStats::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeIterationStats"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeIterationStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeIterationStats::buffer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeIterationStats::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization28deserializeIterationStatsVecERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeIterationStatsVec"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization28deserializeIterationStatsVecERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeIterationStatsVec::buffer"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization24deserializeKvCacheConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeKvCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization24deserializeKvCacheConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeKvCacheConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeKvCacheRetentionConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeKvCacheRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization33deserializeKvCacheRetentionConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeKvCacheRetentionConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeKvCacheStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeKvCacheStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeKvCacheStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeKvCacheStats::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization34deserializeLookaheadDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeLookaheadDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization34deserializeLookaheadDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeLookaheadDecodingConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeLoraConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeLoraConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeLoraConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeLoraConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeModelTypeERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeModelType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeModelTypeERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeModelType::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeMropeConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeMropeConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeMropeConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeMropeConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializeMultimodalInputERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeMultimodalInput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializeMultimodalInputERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeMultimodalInput::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeOrchestratorConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeOrchestratorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeOrchestratorConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeOrchestratorConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeOutputConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeOutputConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeOutputConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeOutputConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeParallelConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeParallelConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeParallelConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeParallelConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializePeftCacheConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializePeftCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializePeftCacheConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializePeftCacheConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializePromptTuningConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializePromptTuningConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializePromptTuningConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializePromptTuningConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization18deserializeRequestERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequest"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization18deserializeRequestERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequest::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeRequestPerfMetricsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequestPerfMetrics"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeRequestPerfMetricsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequestPerfMetrics::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeRequestStageERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequestStage"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeRequestStageERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequestStage::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeRequestStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequestStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeRequestStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequestStats::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization35deserializeRequestStatsPerIterationERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeRequestStatsPerIteration"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization35deserializeRequestStatsPerIterationERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequestStatsPerIteration"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization35deserializeRequestStatsPerIterationERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeRequestStatsPerIteration::buffer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization35deserializeRequestStatsPerIterationERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequestStatsPerIteration::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization38deserializeRequestStatsPerIterationVecERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeRequestStatsPerIterationVec"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization38deserializeRequestStatsPerIterationVecERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeRequestStatsPerIterationVec::buffer"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization19deserializeResponseERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeResponse"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization19deserializeResponseERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeResponse::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeResponsesERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeResponses"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeResponsesERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeResponses::buffer"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeResultERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeResult"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeResultERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeResult::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeSamplingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSamplingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeSamplingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSamplingConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializeSchedulerConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSchedulerConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializeSchedulerConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSchedulerConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeSocketStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSocketState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeSocketStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSocketState::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeSpecDecFastLogitsInfoERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSpecDecFastLogitsInfo"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeSpecDecFastLogitsInfoERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSpecDecFastLogitsInfo::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization28deserializeSpecDecodingStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSpecDecodingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization28deserializeSpecDecodingStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSpecDecodingStats::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeSpeculativeDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSpeculativeDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeSpeculativeDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSpeculativeDecodingConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization30deserializeStaticBatchingStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeStaticBatchingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization30deserializeStaticBatchingStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeStaticBatchingStats::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeStringERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeString"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeStringERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeString::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeTensorERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeTensor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeTensorERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeTensor::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeTimePointERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeTimePoint"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeTimePointERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeTimePoint::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeTokenRangeRetentionConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeTokenRangeRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeTokenRangeRetentionConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeTokenRangeRetentionConfig::is"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK10LoraConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11DebugConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11EagleConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11MropeConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12DecodingModeRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12KvCacheStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12OutputConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12RequestStageRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12RequestStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK13KvCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14DecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ExecutorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStats", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ParallelConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14SamplingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15MultimodalInputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15PeftCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15SchedulerConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK16AdditionalOutputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK17SpecDecodingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18ContextPhaseParamsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18DynamicBatchConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18OrchestratorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18PromptTuningConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18RequestPerfMetricsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK19StaticBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20DataTransceiverState", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20DataTransceiverStateRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20GuidedDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20GuidedDecodingParamsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21AdditionalModelOutputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21InflightBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22CacheTransceiverConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22DisServingRequestStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22KvCacheRetentionConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK23LookaheadDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK24RequestStatsPerIteration", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK24RequestStatsPerIterationRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25ExternalDraftTokensConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25SpeculativeDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK29ExtendedRuntimePerfKnobConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK33SpeculativeDecodingFastLogitsInfoRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6ResultRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6TensorRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK7RequestRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK8ResponseRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN18RequestPerfMetrics9TimePointERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN22KvCacheRetentionConfig25TokenRangeRetentionConfigERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10AgentStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10CacheStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache11SocketStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache9CommStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI14IterationStatsEE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI24RequestStatsPerIterationEE", "tensorrt_llm::executor::Serialization::serialize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI8ResponseEE", "tensorrt_llm::executor::Serialization::serialize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21AdditionalModelOutputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::additionalModelOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK16AdditionalOutputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::additionalOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22CacheTransceiverConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::cacheTransceiverConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK10LoraConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11MropeConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12OutputConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14SamplingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18PromptTuningConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25ExternalDraftTokensConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18ContextPhaseParamsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::contextPhaseParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20DataTransceiverState", "tensorrt_llm::executor::Serialization::serialize::dataTransceiverState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20DataTransceiverStateRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::dataTransceiverState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11DebugConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::debugConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14DecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::decodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12DecodingModeRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::decodingMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18DynamicBatchConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::dynamicBatchConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11EagleConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::eagleConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ExecutorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::executorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK29ExtendedRuntimePerfKnobConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::extendedRuntimePerfKnobConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20GuidedDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::guidedDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20GuidedDecodingParamsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::guidedDecodingParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21InflightBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::inflightBatchingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK33SpeculativeDecodingFastLogitsInfoRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::info"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStats", "tensorrt_llm::executor::Serialization::serialize::iterStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::iterStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI14IterationStatsEE", "tensorrt_llm::executor::Serialization::serialize::iterStatsVec"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK13KvCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::kvCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22KvCacheRetentionConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::kvCacheRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12KvCacheStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::kvCacheStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK23LookaheadDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::lookaheadDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18RequestPerfMetricsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::metrics"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15MultimodalInputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::multimodalInput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18OrchestratorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::orchestratorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK10LoraConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11DebugConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11EagleConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11MropeConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12DecodingModeRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12KvCacheStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12OutputConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12RequestStageRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12RequestStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK13KvCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14DecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ExecutorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ParallelConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14SamplingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15MultimodalInputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15PeftCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15SchedulerConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK16AdditionalOutputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK17SpecDecodingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18ContextPhaseParamsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18DynamicBatchConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18OrchestratorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18PromptTuningConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18RequestPerfMetricsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK19StaticBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20DataTransceiverStateRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20GuidedDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK20GuidedDecodingParamsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21AdditionalModelOutputRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21InflightBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22CacheTransceiverConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22DisServingRequestStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22KvCacheRetentionConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK23LookaheadDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK24RequestStatsPerIterationRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25ExternalDraftTokensConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25SpeculativeDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK29ExtendedRuntimePerfKnobConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK33SpeculativeDecodingFastLogitsInfoRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6ResultRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6TensorRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK7RequestRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK8ResponseRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN18RequestPerfMetrics9TimePointERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN22KvCacheRetentionConfig25TokenRangeRetentionConfigERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10AgentStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10CacheStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache11SocketStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache9CommStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ParallelConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::parallelConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15PeftCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::peftCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK7RequestRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::request"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12RequestStageRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::requestStage"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI24RequestStatsPerIterationEE", "tensorrt_llm::executor::Serialization::serialize::requestStatsVec"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK8ResponseRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::response"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI8ResponseEE", "tensorrt_llm::executor::Serialization::serialize::responses"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6ResultRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::result"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15SchedulerConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::schedulerConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25SpeculativeDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::specDecConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK17SpecDecodingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::specDecodingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12RequestStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK24RequestStatsPerIteration", "tensorrt_llm::executor::Serialization::serialize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK24RequestStatsPerIterationRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10AgentStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10CacheStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache11SocketStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache9CommStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK19StaticBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::staticBatchingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK22DisServingRequestStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::stats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6TensorRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::tensor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN22KvCacheRetentionConfig25TokenRangeRetentionConfigERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::tokenRangeRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN18RequestPerfMetrics9TimePointERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::tp"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK10LoraConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11DebugConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11EagleConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11MropeConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12DecodingMode", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12KvCacheStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12OutputConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12RequestStage", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12RequestStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK13KvCacheConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14DecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ExecutorConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14IterationStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ParallelConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14SamplingConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15MultimodalInput", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15PeftCacheConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15SchedulerConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK16AdditionalOutput", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK17SpecDecodingStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18ContextPhaseParams", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18DynamicBatchConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18OrchestratorConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18PromptTuningConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18RequestPerfMetrics", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK19StaticBatchingStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20DataTransceiverState", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20GuidedDecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20GuidedDecodingParams", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK21AdditionalModelOutput", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK21InflightBatchingStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22CacheTransceiverConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22DisServingRequestStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22KvCacheRetentionConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK23LookaheadDecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK24RequestStatsPerIteration", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK25ExternalDraftTokensConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK25SpeculativeDecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK33SpeculativeDecodingFastLogitsInfo", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Result", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Tensor", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK7Request", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK8Response", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN18RequestPerfMetrics9TimePointE", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN22KvCacheRetentionConfig25TokenRangeRetentionConfigE", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache10AgentStateE", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache10CacheStateE", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache11SocketStateE", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache9CommStateE", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK21AdditionalModelOutput", "tensorrt_llm::executor::Serialization::serializedSize::additionalModelOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK16AdditionalOutput", "tensorrt_llm::executor::Serialization::serializedSize::additionalOutput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22CacheTransceiverConfig", "tensorrt_llm::executor::Serialization::serializedSize::cacheTransceiverConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK10LoraConfig", "tensorrt_llm::executor::Serialization::serializedSize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11MropeConfig", "tensorrt_llm::executor::Serialization::serializedSize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12OutputConfig", "tensorrt_llm::executor::Serialization::serializedSize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14SamplingConfig", "tensorrt_llm::executor::Serialization::serializedSize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18PromptTuningConfig", "tensorrt_llm::executor::Serialization::serializedSize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK25ExternalDraftTokensConfig", "tensorrt_llm::executor::Serialization::serializedSize::config"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18ContextPhaseParams", "tensorrt_llm::executor::Serialization::serializedSize::contextPhaseParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20DataTransceiverState", "tensorrt_llm::executor::Serialization::serializedSize::dataTransceiverState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11DebugConfig", "tensorrt_llm::executor::Serialization::serializedSize::debugConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14DecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize::decodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12DecodingMode", "tensorrt_llm::executor::Serialization::serializedSize::decodingMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22DisServingRequestStats", "tensorrt_llm::executor::Serialization::serializedSize::disServingRequestStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18DynamicBatchConfig", "tensorrt_llm::executor::Serialization::serializedSize::dynamicBatchConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11EagleConfig", "tensorrt_llm::executor::Serialization::serializedSize::eagleConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ExecutorConfig", "tensorrt_llm::executor::Serialization::serializedSize::executorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::Serialization::serializedSize::extendedRuntimePerfKnobConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20GuidedDecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize::guidedDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK20GuidedDecodingParams", "tensorrt_llm::executor::Serialization::serializedSize::guidedDecodingParams"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK21InflightBatchingStats", "tensorrt_llm::executor::Serialization::serializedSize::inflightBatchingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK33SpeculativeDecodingFastLogitsInfo", "tensorrt_llm::executor::Serialization::serializedSize::info"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14IterationStats", "tensorrt_llm::executor::Serialization::serializedSize::iterStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK13KvCacheConfig", "tensorrt_llm::executor::Serialization::serializedSize::kvCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK22KvCacheRetentionConfig", "tensorrt_llm::executor::Serialization::serializedSize::kvCacheRetentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12KvCacheStats", "tensorrt_llm::executor::Serialization::serializedSize::kvCacheStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK23LookaheadDecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize::lookaheadDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18RequestPerfMetrics", "tensorrt_llm::executor::Serialization::serializedSize::metrics"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15MultimodalInput", "tensorrt_llm::executor::Serialization::serializedSize::multimodalInput"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18OrchestratorConfig", "tensorrt_llm::executor::Serialization::serializedSize::orchestratorConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ParallelConfig", "tensorrt_llm::executor::Serialization::serializedSize::parallelConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15PeftCacheConfig", "tensorrt_llm::executor::Serialization::serializedSize::peftCacheConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK7Request", "tensorrt_llm::executor::Serialization::serializedSize::request"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12RequestStage", "tensorrt_llm::executor::Serialization::serializedSize::requestStage"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK8Response", "tensorrt_llm::executor::Serialization::serializedSize::response"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Result", "tensorrt_llm::executor::Serialization::serializedSize::result"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15SchedulerConfig", "tensorrt_llm::executor::Serialization::serializedSize::schedulerConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK25SpeculativeDecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize::specDecConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK17SpecDecodingStats", "tensorrt_llm::executor::Serialization::serializedSize::specDecodingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12RequestStats", "tensorrt_llm::executor::Serialization::serializedSize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK24RequestStatsPerIteration", "tensorrt_llm::executor::Serialization::serializedSize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache10AgentStateE", "tensorrt_llm::executor::Serialization::serializedSize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache10CacheStateE", "tensorrt_llm::executor::Serialization::serializedSize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache11SocketStateE", "tensorrt_llm::executor::Serialization::serializedSize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache9CommStateE", "tensorrt_llm::executor::Serialization::serializedSize::state"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK19StaticBatchingStats", "tensorrt_llm::executor::Serialization::serializedSize::staticBatchingStats"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Tensor", "tensorrt_llm::executor::Serialization::serializedSize::tensor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN22KvCacheRetentionConfig25TokenRangeRetentionConfigE", "tensorrt_llm::executor::Serialization::serializedSize::tokenRangeRetentionConfig"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor5ShapeE", "tensorrt_llm::executor::Shape"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor5Shape4BaseE", "tensorrt_llm::executor::Shape::Base"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor5Shape9DimType64E", "tensorrt_llm::executor::Shape::DimType64"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeENSt16initializer_listI9DimType64EE", "tensorrt_llm::executor::Shape::Shape"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEPK9DimType64N4Base9size_typeE", "tensorrt_llm::executor::Shape::Shape"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEv", "tensorrt_llm::executor::Shape::Shape"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEPK9DimType64N4Base9size_typeE", "tensorrt_llm::executor::Shape::Shape::data"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeENSt16initializer_listI9DimType64EE", "tensorrt_llm::executor::Shape::Shape::dims"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEPK9DimType64N4Base9size_typeE", "tensorrt_llm::executor::Shape::Shape::size"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor10SizeType32E", "tensorrt_llm::executor::SizeType32"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor10SizeType64E", "tensorrt_llm::executor::SizeType64"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStatsE", "tensorrt_llm::executor::SpecDecodingStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats16acceptanceLengthE", "tensorrt_llm::executor::SpecDecodingStats::acceptanceLength"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats13draftOverheadE", "tensorrt_llm::executor::SpecDecodingStats::draftOverhead"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats13iterLatencyMSE", "tensorrt_llm::executor::SpecDecodingStats::iterLatencyMS"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats17numAcceptedTokensE", "tensorrt_llm::executor::SpecDecodingStats::numAcceptedTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats14numDraftTokensE", "tensorrt_llm::executor::SpecDecodingStats::numDraftTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17SpecDecodingStats26numRequestsWithDraftTokensE", "tensorrt_llm::executor::SpecDecodingStats::numRequestsWithDraftTokens"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor25SpeculativeDecodingConfigE", "tensorrt_llm::executor::SpeculativeDecodingConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor25SpeculativeDecodingConfig25SpeculativeDecodingConfigEb", "tensorrt_llm::executor::SpeculativeDecodingConfig::SpeculativeDecodingConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25SpeculativeDecodingConfig25SpeculativeDecodingConfigEb", "tensorrt_llm::executor::SpeculativeDecodingConfig::SpeculativeDecodingConfig::fastLogits"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25SpeculativeDecodingConfig10fastLogitsE", "tensorrt_llm::executor::SpeculativeDecodingConfig::fastLogits"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor25SpeculativeDecodingConfigeqERK25SpeculativeDecodingConfig", "tensorrt_llm::executor::SpeculativeDecodingConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor25SpeculativeDecodingConfigeqERK25SpeculativeDecodingConfig", "tensorrt_llm::executor::SpeculativeDecodingConfig::operator==::other"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor33SpeculativeDecodingFastLogitsInfoE", "tensorrt_llm::executor::SpeculativeDecodingFastLogitsInfo"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor33SpeculativeDecodingFastLogitsInfo18draftParticipantIdE", "tensorrt_llm::executor::SpeculativeDecodingFastLogitsInfo::draftParticipantId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor33SpeculativeDecodingFastLogitsInfo14draftRequestIdE", "tensorrt_llm::executor::SpeculativeDecodingFastLogitsInfo::draftRequestId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor33SpeculativeDecodingFastLogitsInfo8toTensorEv", "tensorrt_llm::executor::SpeculativeDecodingFastLogitsInfo::toTensor"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStatsE", "tensorrt_llm::executor::StaticBatchingStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats13emptyGenSlotsE", "tensorrt_llm::executor::StaticBatchingStats::emptyGenSlots"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats18numContextRequestsE", "tensorrt_llm::executor::StaticBatchingStats::numContextRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats12numCtxTokensE", "tensorrt_llm::executor::StaticBatchingStats::numCtxTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats12numGenTokensE", "tensorrt_llm::executor::StaticBatchingStats::numGenTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats20numScheduledRequestsE", "tensorrt_llm::executor::StaticBatchingStats::numScheduledRequests"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor9StreamPtrE", "tensorrt_llm::executor::StreamPtr"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor6TensorE", "tensorrt_llm::executor::Tensor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::CudaStreamPtr"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor6Tensor4ImplE", "tensorrt_llm::executor::Tensor::Impl"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::Tensor::Tensor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERK6Tensor", "tensorrt_llm::executor::Tensor::Tensor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERR6Tensor", "tensorrt_llm::executor::Tensor::Tensor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorEv", "tensorrt_llm::executor::Tensor::Tensor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERK6Tensor", "tensorrt_llm::executor::Tensor::Tensor::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERR6Tensor", "tensorrt_llm::executor::Tensor::Tensor::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::Tensor::Tensor::tensor"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor6copyToENSt10shared_ptrI4ImplEE13CudaStreamPtr", "tensorrt_llm::executor::Tensor::copyTo"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor6copyToENSt10shared_ptrI4ImplEE13CudaStreamPtr", "tensorrt_llm::executor::Tensor::copyTo::stream"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor6copyToENSt10shared_ptrI4ImplEE13CudaStreamPtr", "tensorrt_llm::executor::Tensor::copyTo::tensor"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToCpuEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToCpu"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToCpuEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToCpu::stream"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToGpuEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToGpu"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToGpuEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToGpu::stream"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor13copyToManagedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToManaged"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor13copyToManagedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToManaged::stream"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor12copyToPinnedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToPinned"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor12copyToPinnedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToPinned::stream"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor18copyToPooledPinnedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToPooledPinned"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor18copyToPooledPinnedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToPooledPinned::stream"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3cpuE6Tensor5Shape", "tensorrt_llm::executor::Tensor::cpu"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3cpuE8DataType5Shape", "tensorrt_llm::executor::Tensor::cpu"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3cpuE6Tensor5Shape", "tensorrt_llm::executor::Tensor::cpu::T"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3cpuE8DataType5Shape", "tensorrt_llm::executor::Tensor::cpu::dataType"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3cpuE6Tensor5Shape", "tensorrt_llm::executor::Tensor::cpu::shape"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3cpuE8DataType5Shape", "tensorrt_llm::executor::Tensor::cpu::shape"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::Tensor::detail::ofITensor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::Tensor::detail::ofITensor::tensor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9toITensorERK6Tensor", "tensorrt_llm::executor::Tensor::detail::toITensor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9toITensorERK6Tensor", "tensorrt_llm::executor::Tensor::detail::toITensor::tensor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7getDataEv", "tensorrt_llm::executor::Tensor::getData"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor7getDataEv", "tensorrt_llm::executor::Tensor::getData"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor11getDataTypeEv", "tensorrt_llm::executor::Tensor::getDataType"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor13getMemoryTypeEv", "tensorrt_llm::executor::Tensor::getMemoryType"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor14getRuntimeTypeE8DataTypev", "tensorrt_llm::executor::Tensor::getRuntimeType"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor14getRuntimeTypeE8DataTypev", "tensorrt_llm::executor::Tensor::getRuntimeType::T"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor8getShapeEv", "tensorrt_llm::executor::Tensor::getShape"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor7getSizeEv", "tensorrt_llm::executor::Tensor::getSize"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor14getSizeInBytesEv", "tensorrt_llm::executor::Tensor::getSizeInBytes"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3gpuE6Tensor13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3gpuE8DataType13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3gpuE6Tensor13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::T"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3gpuE8DataType13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::dataType"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3gpuE6Tensor13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::shape"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3gpuE8DataType13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::shape"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3gpuE6Tensor13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::stream"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3gpuE8DataType13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::stream"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7mTensorE", "tensorrt_llm::executor::Tensor::mTensor"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor7managedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::managed"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7managedE8DataType5Shape", "tensorrt_llm::executor::Tensor::managed"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor7managedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::managed::T"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7managedE8DataType5Shape", "tensorrt_llm::executor::Tensor::managed::dataType"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor7managedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::managed::shape"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7managedE8DataType5Shape", "tensorrt_llm::executor::Tensor::managed::shape"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorP1T5Shape", "tensorrt_llm::executor::Tensor::of"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorR1T", "tensorrt_llm::executor::Tensor::of"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor2ofE8DataTypePv5Shape", "tensorrt_llm::executor::Tensor::of"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorP1T5Shape", "tensorrt_llm::executor::Tensor::of::T"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorR1T", "tensorrt_llm::executor::Tensor::of::T"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorP1T5Shape", "tensorrt_llm::executor::Tensor::of::data"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorR1T", "tensorrt_llm::executor::Tensor::of::data"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor2ofE8DataTypePv5Shape", "tensorrt_llm::executor::Tensor::of::data"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor2ofE8DataTypePv5Shape", "tensorrt_llm::executor::Tensor::of::dataType"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorP1T5Shape", "tensorrt_llm::executor::Tensor::of::shape"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor2ofE8DataTypePv5Shape", "tensorrt_llm::executor::Tensor::of::shape"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6TensorcvbEv", "tensorrt_llm::executor::Tensor::operator bool"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6TensorneERK6Tensor", "tensorrt_llm::executor::Tensor::operator!="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6TensorneERK6Tensor", "tensorrt_llm::executor::Tensor::operator!=::rhs"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6TensoraSERK6Tensor", "tensorrt_llm::executor::Tensor::operator="], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6TensoraSERR6Tensor", "tensorrt_llm::executor::Tensor::operator="], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6TensoraSERK6Tensor", "tensorrt_llm::executor::Tensor::operator=::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6TensoraSERR6Tensor", "tensorrt_llm::executor::Tensor::operator=::other"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor6TensoreqERK6Tensor", "tensorrt_llm::executor::Tensor::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor6TensoreqERK6Tensor", "tensorrt_llm::executor::Tensor::operator==::rhs"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor6pinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pinned"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6pinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pinned"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor6pinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pinned::T"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6pinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pinned::dataType"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor6pinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pinned::shape"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6pinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pinned::shape"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor12pooledPinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pooledPinned"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor12pooledPinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pooledPinned"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor12pooledPinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pooledPinned::T"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor12pooledPinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pooledPinned::dataType"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor12pooledPinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pooledPinned::shape"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor12pooledPinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pooledPinned::shape"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7setFromERK6Tensor13CudaStreamPtr", "tensorrt_llm::executor::Tensor::setFrom"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7setFromERK6Tensor13CudaStreamPtr", "tensorrt_llm::executor::Tensor::setFrom::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7setFromERK6Tensor13CudaStreamPtr", "tensorrt_llm::executor::Tensor::setFrom::stream"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7setZeroE13CudaStreamPtr", "tensorrt_llm::executor::Tensor::setZero"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7setZeroE13CudaStreamPtr", "tensorrt_llm::executor::Tensor::setZero::stream"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6TensorD0Ev", "tensorrt_llm::executor::Tensor::~Tensor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor9TensorPtrE", "tensorrt_llm::executor::TensorPtr"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor11TokenIdTypeE", "tensorrt_llm::executor::TokenIdType"], [0, 2, 1, "_CPPv4I0_bEN12tensorrt_llm8executor10TypeTraitsE", "tensorrt_llm::executor::TypeTraits"], [0, 8, 1, "_CPPv4I0_bEN12tensorrt_llm8executor10TypeTraitsE", "tensorrt_llm::executor::TypeTraits::T"], [0, 2, 1, "_CPPv4I0EN12tensorrt_llm8executor10TypeTraitsIP1TEE", "tensorrt_llm::executor::TypeTraits<T*>"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor10TypeTraitsIP1TEE", "tensorrt_llm::executor::TypeTraits<T*>::T"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIP1TE5valueE", "tensorrt_llm::executor::TypeTraits<T*>::value"], [0, 2, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsIbEE", "tensorrt_llm::executor::TypeTraits<bool>"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIbE5valueE", "tensorrt_llm::executor::TypeTraits<bool>::value"], [0, 2, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsIfEE", "tensorrt_llm::executor::TypeTraits<float>"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIfE5valueE", "tensorrt_llm::executor::TypeTraits<float>::value"], [0, 2, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsI4halfEE", "tensorrt_llm::executor::TypeTraits<half>"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsI4halfE5valueE", "tensorrt_llm::executor::TypeTraits<half>::value"], [0, 2, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7int32_tEEE", "tensorrt_llm::executor::TypeTraits<std::int32_t>"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7int32_tEE5valueE", "tensorrt_llm::executor::TypeTraits<std::int32_t>::value"], [0, 2, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7int64_tEEE", "tensorrt_llm::executor::TypeTraits<std::int64_t>"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7int64_tEE5valueE", "tensorrt_llm::executor::TypeTraits<std::int64_t>::value"], [0, 2, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt6int8_tEEE", "tensorrt_llm::executor::TypeTraits<std::int8_t>"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt6int8_tEE5valueE", "tensorrt_llm::executor::TypeTraits<std::int8_t>::value"], [0, 2, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7uint8_tEEE", "tensorrt_llm::executor::TypeTraits<std::uint8_t>"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7uint8_tEE5valueE", "tensorrt_llm::executor::TypeTraits<std::uint8_t>::value"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor11VecLogProbsE", "tensorrt_llm::executor::VecLogProbs"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor16VecTokenExtraIdsE", "tensorrt_llm::executor::VecTokenExtraIds"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor9VecTokensE", "tensorrt_llm::executor::VecTokens"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor6detailE", "tensorrt_llm::executor::detail"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor6detail9DimType64E", "tensorrt_llm::executor::detail::DimType64"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::detail::ofITensor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::detail::ofITensor::tensor"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor6detail9toITensorERK6Tensor", "tensorrt_llm::executor::detail::toITensor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6detail9toITensorERK6Tensor", "tensorrt_llm::executor::detail::toITensor::tensor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executorE", "tensorrt_llm::executor::disagg_executor"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestratorE", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator26DisaggExecutorOrchestratorERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorIN8executor14ExecutorConfigEEERKNSt6vectorIN8executor14ExecutorConfigEEEbb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::DisaggExecutorOrchestrator"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator26DisaggExecutorOrchestratorERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorIN8executor14ExecutorConfigEEERKNSt6vectorIN8executor14ExecutorConfigEEEbb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::DisaggExecutorOrchestrator::ctxEnginePaths"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator26DisaggExecutorOrchestratorERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorIN8executor14ExecutorConfigEEERKNSt6vectorIN8executor14ExecutorConfigEEEbb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::DisaggExecutorOrchestrator::ctxExecutorConfigs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator26DisaggExecutorOrchestratorERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorIN8executor14ExecutorConfigEEERKNSt6vectorIN8executor14ExecutorConfigEEEbb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::DisaggExecutorOrchestrator::genEnginePaths"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator26DisaggExecutorOrchestratorERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorIN8executor14ExecutorConfigEEERKNSt6vectorIN8executor14ExecutorConfigEEEbb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::DisaggExecutorOrchestrator::genExecutorConfigs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator26DisaggExecutorOrchestratorERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorIN8executor14ExecutorConfigEEERKNSt6vectorIN8executor14ExecutorConfigEEEbb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::DisaggExecutorOrchestrator::hasContextAwaitThreads"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator26DisaggExecutorOrchestratorERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorINSt10filesystem4pathEEERKNSt6vectorIN8executor14ExecutorConfigEEERKNSt6vectorIN8executor14ExecutorConfigEEEbb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::DisaggExecutorOrchestrator::hasGenAwaitThreads"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator21awaitContextResponsesERKNSt8optionalINSt6chrono12millisecondsEEENSt8optionalIiEE", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::awaitContextResponses"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator21awaitContextResponsesERKNSt8optionalINSt6chrono12millisecondsEEENSt8optionalIiEE", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::awaitContextResponses::contextIdx"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator21awaitContextResponsesERKNSt8optionalINSt6chrono12millisecondsEEENSt8optionalIiEE", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::awaitContextResponses::timeout"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator24awaitGenerationResponsesERKNSt8optionalINSt6chrono12millisecondsEEENSt8optionalIiEE", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::awaitGenerationResponses"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator24awaitGenerationResponsesERKNSt8optionalINSt6chrono12millisecondsEEENSt8optionalIiEE", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::awaitGenerationResponses::genIdx"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator24awaitGenerationResponsesERKNSt8optionalINSt6chrono12millisecondsEEENSt8optionalIiEE", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::awaitGenerationResponses::timeout"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator10canEnqueueEv", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::canEnqueue"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator14enqueueContextERKNSt6vectorIN5texec7RequestEEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueContext"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator14enqueueContextERKNSt6vectorIN5texec7RequestEEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueContext::batch"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator14enqueueContextERKNSt6vectorIN5texec7RequestEEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueContext::requests"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator14enqueueContextERKNSt6vectorIN5texec7RequestEEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueContext::selectContextId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator17enqueueGenerationERKNSt6vectorIN5texec7RequestEEERKNSt6vectorI6IdTypeEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueGeneration"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator17enqueueGenerationERKNSt6vectorIN5texec7RequestEEERKNSt6vectorI6IdTypeEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueGeneration::batch"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator17enqueueGenerationERKNSt6vectorIN5texec7RequestEEERKNSt6vectorI6IdTypeEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueGeneration::globalRequestIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator17enqueueGenerationERKNSt6vectorIN5texec7RequestEEERKNSt6vectorI6IdTypeEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueGeneration::requests"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator17enqueueGenerationERKNSt6vectorIN5texec7RequestEEERKNSt6vectorI6IdTypeEENSt8optionalIiEEb", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::enqueueGeneration::selectGenIdx"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator19getContextExecutorsEv", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::getContextExecutors"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator15getGenExecutorsEv", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::getGenExecutors"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestrator5mImplE", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::mImpl"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor26DisaggExecutorOrchestratorD0Ev", "tensorrt_llm::executor::disagg_executor::DisaggExecutorOrchestrator::~DisaggExecutorOrchestrator"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdE", "tensorrt_llm::executor::disagg_executor::ResponseWithId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERK14ResponseWithId", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERKN12tensorrt_llm8executor8ResponseE6IdType", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERR14ResponseWithId", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERRN12tensorrt_llm8executor8ResponseE6IdType", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERKN12tensorrt_llm8executor8ResponseE6IdType", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId::gid"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERRN12tensorrt_llm8executor8ResponseE6IdType", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId::gid"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERK14ResponseWithId", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERR14ResponseWithId", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERKN12tensorrt_llm8executor8ResponseE6IdType", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId::response"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId14ResponseWithIdERRN12tensorrt_llm8executor8ResponseE6IdType", "tensorrt_llm::executor::disagg_executor::ResponseWithId::ResponseWithId::response"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId3gidE", "tensorrt_llm::executor::disagg_executor::ResponseWithId::gid"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdaSERK14ResponseWithId", "tensorrt_llm::executor::disagg_executor::ResponseWithId::operator="], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdaSERR14ResponseWithId", "tensorrt_llm::executor::disagg_executor::ResponseWithId::operator="], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdaSERK14ResponseWithId", "tensorrt_llm::executor::disagg_executor::ResponseWithId::operator=::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdaSERR14ResponseWithId", "tensorrt_llm::executor::disagg_executor::ResponseWithId::operator=::other"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithId8responseE", "tensorrt_llm::executor::disagg_executor::ResponseWithId::response"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor15disagg_executor14ResponseWithIdD0Ev", "tensorrt_llm::executor::disagg_executor::ResponseWithId::~ResponseWithId"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor8kv_cacheE", "tensorrt_llm::executor::kv_cache"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor8kv_cacheE", "tensorrt_llm::executor::kv_cache"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor8kv_cacheE", "tensorrt_llm::executor::kv_cache"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor8kv_cacheE", "tensorrt_llm::executor::kv_cache"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9AgentDescE", "tensorrt_llm::executor::kv_cache::AgentDesc"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9AgentDesc9AgentDescENSt6stringE", "tensorrt_llm::executor::kv_cache::AgentDesc::AgentDesc"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9AgentDesc9AgentDescENSt6stringE", "tensorrt_llm::executor::kv_cache::AgentDesc::AgentDesc::backendAgentDesc"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9AgentDesc19getBackendAgentDescEv", "tensorrt_llm::executor::kv_cache::AgentDesc::getBackendAgentDesc"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9AgentDesc17mBackendAgentDescE", "tensorrt_llm::executor::kv_cache::AgentDesc::mBackendAgentDesc"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentStateE", "tensorrt_llm::executor::kv_cache::AgentState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState10AgentStateENSt6stringENSt6stringE", "tensorrt_llm::executor::kv_cache::AgentState::AgentState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState10AgentStateEv", "tensorrt_llm::executor::kv_cache::AgentState::AgentState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState10AgentStateENSt6stringENSt6stringE", "tensorrt_llm::executor::kv_cache::AgentState::AgentState::agentName"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState10AgentStateENSt6stringENSt6stringE", "tensorrt_llm::executor::kv_cache::AgentState::AgentState::connectionInfo"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState10mAgentNameE", "tensorrt_llm::executor::kv_cache::AgentState::mAgentName"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10AgentState15mConnectionInfoE", "tensorrt_llm::executor::kv_cache::AgentState::mConnectionInfo"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10AgentStateeqERK10AgentState", "tensorrt_llm::executor::kv_cache::AgentState::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10AgentStateeqERK10AgentState", "tensorrt_llm::executor::kv_cache::AgentState::operator==::other"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10AgentState8toStringEv", "tensorrt_llm::executor::kv_cache::AgentState::toString"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15BaseAgentConfigE", "tensorrt_llm::executor::kv_cache::BaseAgentConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15BaseAgentConfig5mNameE", "tensorrt_llm::executor::kv_cache::BaseAgentConfig::mName"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15BaseAgentConfig13useProgThreadE", "tensorrt_llm::executor::kv_cache::BaseAgentConfig::useProgThread"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgentE", "tensorrt_llm::executor::kv_cache::BaseTransferAgent"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent16checkRemoteDescsERKNSt6stringERK11MemoryDescs", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::checkRemoteDescs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent16checkRemoteDescsERKNSt6stringERK11MemoryDescs", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::checkRemoteDescs::memoryDescs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent16checkRemoteDescsERKNSt6stringERK11MemoryDescs", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::checkRemoteDescs::name"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent18connectRemoteAgentERKNSt6stringERK18ConnectionInfoType", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::connectRemoteAgent"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent18connectRemoteAgentERKNSt6stringERK18ConnectionInfoType", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::connectRemoteAgent::connectionInfo"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent18connectRemoteAgentERKNSt6stringERK18ConnectionInfoType", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::connectRemoteAgent::name"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent16deregisterMemoryERK13RegisterDescs", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::deregisterMemory"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent16deregisterMemoryERK13RegisterDescs", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::deregisterMemory::descs"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent17getConnectionInfoEv", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::getConnectionInfo"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent17getLocalAgentDescEv", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::getLocalAgentDesc"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent23getNotifiedSyncMessagesEv", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::getNotifiedSyncMessages"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent21invalidateRemoteAgentERKNSt6stringE", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::invalidateRemoteAgent"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent21invalidateRemoteAgentERKNSt6stringE", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::invalidateRemoteAgent::name"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent15loadRemoteAgentERKNSt6stringERK9AgentDesc", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::loadRemoteAgent"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent15loadRemoteAgentERKNSt6stringERK9AgentDesc", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::loadRemoteAgent::agentDesc"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent15loadRemoteAgentERKNSt6stringERK9AgentDesc", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::loadRemoteAgent::name"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent17notifySyncMessageERKNSt6stringERK11SyncMessage", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::notifySyncMessage"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent17notifySyncMessageERKNSt6stringERK11SyncMessage", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::notifySyncMessage::name"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent17notifySyncMessageERKNSt6stringERK11SyncMessage", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::notifySyncMessage::syncMessage"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent14registerMemoryERK13RegisterDescs", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::registerMemory"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent14registerMemoryERK13RegisterDescs", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::registerMemory::descs"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent22submitTransferRequestsERK15TransferRequest", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::submitTransferRequests"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgent22submitTransferRequestsERK15TransferRequest", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::submitTransferRequests::request"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17BaseTransferAgentD0Ev", "tensorrt_llm::executor::kv_cache::BaseTransferAgent::~BaseTransferAgent"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheStateE", "tensorrt_llm::executor::kv_cache::CacheState"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfigE", "tensorrt_llm::executor::kv_cache::CacheState::AttentionConfig"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfig15AttentionConfigE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::AttentionConfig::AttentionConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfig15AttentionConfigE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::AttentionConfig::AttentionConfig::attentionType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfig15AttentionConfigE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::AttentionConfig::AttentionConfig::kvFactor"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfig14mAttentionTypeE", "tensorrt_llm::executor::kv_cache::CacheState::AttentionConfig::mAttentionType"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15AttentionConfig9mKvFactorE", "tensorrt_llm::executor::kv_cache::CacheState::AttentionConfig::mKvFactor"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState13AttentionTypeE", "tensorrt_llm::executor::kv_cache::CacheState::AttentionType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState13AttentionType8kDEFAULTE", "tensorrt_llm::executor::kv_cache::CacheState::AttentionType::kDEFAULT"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState13AttentionType4kMLAE", "tensorrt_llm::executor::kv_cache::CacheState::AttentionType::kMLA"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE11ModelConfigRKN7runtime11WorldConfigEN8nvinfer18DataTypeE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::CacheState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::DPrank"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::DPrank"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::DPsize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::DPsize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::attentionType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE11ModelConfigRKN7runtime11WorldConfigEN8nvinfer18DataTypeE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::attentionType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::attentionType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::dataType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE11ModelConfigRKN7runtime11WorldConfigEN8nvinfer18DataTypeE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::dataType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::dataType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::enableAttentionDP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::enableAttentionDP"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::kvFactor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE11ModelConfigRKN7runtime11WorldConfigEN8nvinfer18DataTypeE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::kvFactor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::kvFactor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE11ModelConfigRKN7runtime11WorldConfigEN8nvinfer18DataTypeE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::modelConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::nbAttentionLayers"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::nbKvHeadPerLayer"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::nbKvHeads"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::pipelineParallelism"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::pipelineParallelism"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::sizePerHead"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::sizePerHead"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::tensorParallelism"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::tensorParallelism"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::tokensPerBlock"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateENSt6vectorI10SizeType32EE10SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE13AttentionTypeibii", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::tokensPerBlock"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState10CacheStateE11ModelConfigRKN7runtime11WorldConfigEN8nvinfer18DataTypeE13AttentionTypei", "tensorrt_llm::executor::kv_cache::CacheState::CacheState::worldConfig"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState11ModelConfigE", "tensorrt_llm::executor::kv_cache::CacheState::ModelConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState11ModelConfig18mNbKvHeadsPerLayerE", "tensorrt_llm::executor::kv_cache::CacheState::ModelConfig::mNbKvHeadsPerLayer"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState11ModelConfig12mSizePerHeadE", "tensorrt_llm::executor::kv_cache::CacheState::ModelConfig::mSizePerHead"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState11ModelConfig15mTokensPerBlockE", "tensorrt_llm::executor::kv_cache::CacheState::ModelConfig::mTokensPerBlock"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState11ModelConfigeqERK11ModelConfig", "tensorrt_llm::executor::kv_cache::CacheState::ModelConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState11ModelConfigeqERK11ModelConfig", "tensorrt_llm::executor::kv_cache::CacheState::ModelConfig::operator==::other"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfigE", "tensorrt_llm::executor::kv_cache::CacheState::ParallelConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig7mDPrankE", "tensorrt_llm::executor::kv_cache::CacheState::ParallelConfig::mDPrank"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig7mDPsizeE", "tensorrt_llm::executor::kv_cache::CacheState::ParallelConfig::mDPsize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig18mEnableAttentionDPE", "tensorrt_llm::executor::kv_cache::CacheState::ParallelConfig::mEnableAttentionDP"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig20mPipelineParallelismE", "tensorrt_llm::executor::kv_cache::CacheState::ParallelConfig::mPipelineParallelism"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfig18mTensorParallelismE", "tensorrt_llm::executor::kv_cache::CacheState::ParallelConfig::mTensorParallelism"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfigeqERK14ParallelConfig", "tensorrt_llm::executor::kv_cache::CacheState::ParallelConfig::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState14ParallelConfigeqERK14ParallelConfig", "tensorrt_llm::executor::kv_cache::CacheState::ParallelConfig::operator==::other"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState18getAttentionConfigEv", "tensorrt_llm::executor::kv_cache::CacheState::getAttentionConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState11getDataTypeEv", "tensorrt_llm::executor::kv_cache::CacheState::getDataType"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState14getModelConfigEv", "tensorrt_llm::executor::kv_cache::CacheState::getModelConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState17getParallelConfigEv", "tensorrt_llm::executor::kv_cache::CacheState::getParallelConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState16mAttentionConfigE", "tensorrt_llm::executor::kv_cache::CacheState::mAttentionConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState9mDataTypeE", "tensorrt_llm::executor::kv_cache::CacheState::mDataType"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState12mModelConfigE", "tensorrt_llm::executor::kv_cache::CacheState::mModelConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10CacheState15mParallelConfigE", "tensorrt_llm::executor::kv_cache::CacheState::mParallelConfig"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheStateeqERKN8kv_cache10CacheStateE", "tensorrt_llm::executor::kv_cache::CacheState::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheStateeqERKN8kv_cache10CacheStateE", "tensorrt_llm::executor::kv_cache::CacheState::operator==::other"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10CacheState8toStringEv", "tensorrt_llm::executor::kv_cache::CacheState::toString"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommStateE", "tensorrt_llm::executor::kv_cache::CommState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI10AgentStateEEi", "tensorrt_llm::executor::kv_cache::CommState::CommState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI10SizeType32EEi", "tensorrt_llm::executor::kv_cache::CommState::CommState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI11SocketStateEEi", "tensorrt_llm::executor::kv_cache::CommState::CommState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt8uint16_tENSt6stringE", "tensorrt_llm::executor::kv_cache::CommState::CommState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateEv", "tensorrt_llm::executor::kv_cache::CommState::CommState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI10AgentStateEEi", "tensorrt_llm::executor::kv_cache::CommState::CommState::agentState"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt8uint16_tENSt6stringE", "tensorrt_llm::executor::kv_cache::CommState::CommState::ip"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt8uint16_tENSt6stringE", "tensorrt_llm::executor::kv_cache::CommState::CommState::port"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI10SizeType32EEi", "tensorrt_llm::executor::kv_cache::CommState::CommState::ranks"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI10AgentStateEEi", "tensorrt_llm::executor::kv_cache::CommState::CommState::selfIdx"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI10SizeType32EEi", "tensorrt_llm::executor::kv_cache::CommState::CommState::selfIdx"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI11SocketStateEEi", "tensorrt_llm::executor::kv_cache::CommState::CommState::selfIdx"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState9CommStateENSt6vectorI11SocketStateEEi", "tensorrt_llm::executor::kv_cache::CommState::CommState::socketState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState13getAgentStateEv", "tensorrt_llm::executor::kv_cache::CommState::getAgentState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState11getMpiStateEv", "tensorrt_llm::executor::kv_cache::CommState::getMpiState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState10getSelfIdxEv", "tensorrt_llm::executor::kv_cache::CommState::getSelfIdx"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState14getSocketStateEv", "tensorrt_llm::executor::kv_cache::CommState::getSocketState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState12isAgentStateEv", "tensorrt_llm::executor::kv_cache::CommState::isAgentState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState10isMpiStateEv", "tensorrt_llm::executor::kv_cache::CommState::isMpiState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState13isSocketStateEv", "tensorrt_llm::executor::kv_cache::CommState::isSocketState"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState8mSelfIdxE", "tensorrt_llm::executor::kv_cache::CommState::mSelfIdx"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache9CommState6mStateE", "tensorrt_llm::executor::kv_cache::CommState::mState"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommStateeqERK9CommState", "tensorrt_llm::executor::kv_cache::CommState::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommStateeqERK9CommState", "tensorrt_llm::executor::kv_cache::CommState::operator==::other"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache9CommState8toStringEv", "tensorrt_llm::executor::kv_cache::CommState::toString"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10ConnectionE", "tensorrt_llm::executor::kv_cache::Connection"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection12isThreadSafeEv", "tensorrt_llm::executor::kv_cache::Connection::isThreadSafe"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4recvERK11DataContextPv6size_t", "tensorrt_llm::executor::kv_cache::Connection::recv"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4recvERK11DataContextPv6size_t", "tensorrt_llm::executor::kv_cache::Connection::recv::ctx"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4recvERK11DataContextPv6size_t", "tensorrt_llm::executor::kv_cache::Connection::recv::data"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4recvERK11DataContextPv6size_t", "tensorrt_llm::executor::kv_cache::Connection::recv::size"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4sendERK11DataContextPKv6size_t", "tensorrt_llm::executor::kv_cache::Connection::send"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4sendERK11DataContextPKv6size_t", "tensorrt_llm::executor::kv_cache::Connection::send::ctx"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4sendERK11DataContextPKv6size_t", "tensorrt_llm::executor::kv_cache::Connection::send::data"], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10Connection4sendERK11DataContextPKv6size_t", "tensorrt_llm::executor::kv_cache::Connection::send::size"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10ConnectionD0Ev", "tensorrt_llm::executor::kv_cache::Connection::~Connection"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache18ConnectionInfoTypeE", "tensorrt_llm::executor::kv_cache::ConnectionInfoType"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManagerE", "tensorrt_llm::executor::kv_cache::ConnectionManager"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache17ConnectionManager12getCommStateEv", "tensorrt_llm::executor::kv_cache::ConnectionManager::getCommState"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManager14getConnectionsERK9CommState", "tensorrt_llm::executor::kv_cache::ConnectionManager::getConnections"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManager14getConnectionsERK9CommState", "tensorrt_llm::executor::kv_cache::ConnectionManager::getConnections::state"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManager11recvConnectERK11DataContextPv6size_t", "tensorrt_llm::executor::kv_cache::ConnectionManager::recvConnect"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManager11recvConnectERK11DataContextPv6size_t", "tensorrt_llm::executor::kv_cache::ConnectionManager::recvConnect::ctx"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManager11recvConnectERK11DataContextPv6size_t", "tensorrt_llm::executor::kv_cache::ConnectionManager::recvConnect::data"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManager11recvConnectERK11DataContextPv6size_t", "tensorrt_llm::executor::kv_cache::ConnectionManager::recvConnect::size"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache17ConnectionManagerD0Ev", "tensorrt_llm::executor::kv_cache::ConnectionManager::~ConnectionManager"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11DataContextE", "tensorrt_llm::executor::kv_cache::DataContext"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11DataContext11DataContextEi", "tensorrt_llm::executor::kv_cache::DataContext::DataContext"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11DataContext11DataContextEi", "tensorrt_llm::executor::kv_cache::DataContext::DataContext::tag"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache11DataContext6getTagEv", "tensorrt_llm::executor::kv_cache::DataContext::getTag"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11DataContext4mTagE", "tensorrt_llm::executor::kv_cache::DataContext::mTag"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoaderE", "tensorrt_llm::executor::kv_cache::DynLibLoader"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader12DynLibLoaderERK12DynLibLoader", "tensorrt_llm::executor::kv_cache::DynLibLoader::DynLibLoader"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader12DynLibLoaderEv", "tensorrt_llm::executor::kv_cache::DynLibLoader::DynLibLoader"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader5dlSymEPvPKc", "tensorrt_llm::executor::kv_cache::DynLibLoader::dlSym"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader5dlSymEPvPKc", "tensorrt_llm::executor::kv_cache::DynLibLoader::dlSym::handle"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader5dlSymEPvPKc", "tensorrt_llm::executor::kv_cache::DynLibLoader::dlSym::symbol"], [0, 3, 1, "_CPPv4I0EN12tensorrt_llm8executor8kv_cache12DynLibLoader18getFunctionPointerE9FunctionTRKNSt6stringERKNSt6stringE", "tensorrt_llm::executor::kv_cache::DynLibLoader::getFunctionPointer"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor8kv_cache12DynLibLoader18getFunctionPointerE9FunctionTRKNSt6stringERKNSt6stringE", "tensorrt_llm::executor::kv_cache::DynLibLoader::getFunctionPointer::FunctionT"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor8kv_cache12DynLibLoader18getFunctionPointerE9FunctionTRKNSt6stringERKNSt6stringE", "tensorrt_llm::executor::kv_cache::DynLibLoader::getFunctionPointer::funcName"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor8kv_cache12DynLibLoader18getFunctionPointerE9FunctionTRKNSt6stringERKNSt6stringE", "tensorrt_llm::executor::kv_cache::DynLibLoader::getFunctionPointer::libName"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader9getHandleERKNSt6stringE", "tensorrt_llm::executor::kv_cache::DynLibLoader::getHandle"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader9getHandleERKNSt6stringE", "tensorrt_llm::executor::kv_cache::DynLibLoader::getHandle::name"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader11getInstanceEv", "tensorrt_llm::executor::kv_cache::DynLibLoader::getInstance"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader9mDllMutexE", "tensorrt_llm::executor::kv_cache::DynLibLoader::mDllMutex"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoader9mHandlersE", "tensorrt_llm::executor::kv_cache::DynLibLoader::mHandlers"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoaderaSERK12DynLibLoader", "tensorrt_llm::executor::kv_cache::DynLibLoader::operator="], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache12DynLibLoaderD0Ev", "tensorrt_llm::executor::kv_cache::DynLibLoader::~DynLibLoader"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDescE", "tensorrt_llm::executor::kv_cache::MemoryDesc"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescE9uintptr_t6size_t8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescEPv6size_t8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescERKNSt6vectorIcEE8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescE9uintptr_t6size_t8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc::addr"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescEPv6size_t8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc::addr"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescE9uintptr_t6size_t8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc::deviceId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescEPv6size_t8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc::deviceId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescERKNSt6vectorIcEE8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc::deviceId"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescE9uintptr_t6size_t8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc::len"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescEPv6size_t8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc::len"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc10MemoryDescERKNSt6vectorIcEE8uint32_t", "tensorrt_llm::executor::kv_cache::MemoryDesc::MemoryDesc::vec"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc11deserializeERNSt7istreamE", "tensorrt_llm::executor::kv_cache::MemoryDesc::deserialize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc11deserializeERNSt7istreamE", "tensorrt_llm::executor::kv_cache::MemoryDesc::deserialize::is"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10MemoryDesc7getAddrEv", "tensorrt_llm::executor::kv_cache::MemoryDesc::getAddr"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10MemoryDesc11getDeviceIdEv", "tensorrt_llm::executor::kv_cache::MemoryDesc::getDeviceId"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache10MemoryDesc6getLenEv", "tensorrt_llm::executor::kv_cache::MemoryDesc::getLen"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc5mAddrE", "tensorrt_llm::executor::kv_cache::MemoryDesc::mAddr"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc9mDeviceIdE", "tensorrt_llm::executor::kv_cache::MemoryDesc::mDeviceId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc4mLenE", "tensorrt_llm::executor::kv_cache::MemoryDesc::mLen"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc9serializeERK10MemoryDescRNSt7ostreamE", "tensorrt_llm::executor::kv_cache::MemoryDesc::serialize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc9serializeERK10MemoryDescRNSt7ostreamE", "tensorrt_llm::executor::kv_cache::MemoryDesc::serialize::memoryDesc"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc9serializeERK10MemoryDescRNSt7ostreamE", "tensorrt_llm::executor::kv_cache::MemoryDesc::serialize::os"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc14serializedSizeERK10MemoryDesc", "tensorrt_llm::executor::kv_cache::MemoryDesc::serializedSize"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryDesc14serializedSizeERK10MemoryDesc", "tensorrt_llm::executor::kv_cache::MemoryDesc::serializedSize::memoryDesc"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescsE", "tensorrt_llm::executor::kv_cache::MemoryDescs"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescs11MemoryDescsE10MemoryTypeNSt6vectorI10MemoryDescEE", "tensorrt_llm::executor::kv_cache::MemoryDescs::MemoryDescs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescs11MemoryDescsE10MemoryTypeNSt6vectorI10MemoryDescEE", "tensorrt_llm::executor::kv_cache::MemoryDescs::MemoryDescs::descs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescs11MemoryDescsE10MemoryTypeNSt6vectorI10MemoryDescEE", "tensorrt_llm::executor::kv_cache::MemoryDescs::MemoryDescs::type"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache11MemoryDescs8getDescsEv", "tensorrt_llm::executor::kv_cache::MemoryDescs::getDescs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache11MemoryDescs7getTypeEv", "tensorrt_llm::executor::kv_cache::MemoryDescs::getType"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescs6mDescsE", "tensorrt_llm::executor::kv_cache::MemoryDescs::mDescs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11MemoryDescs5mTypeE", "tensorrt_llm::executor::kv_cache::MemoryDescs::mType"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryTypeE", "tensorrt_llm::executor::kv_cache::MemoryType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType4kBLKE", "tensorrt_llm::executor::kv_cache::MemoryType::kBLK"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType5kDRAME", "tensorrt_llm::executor::kv_cache::MemoryType::kDRAM"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType5kFILEE", "tensorrt_llm::executor::kv_cache::MemoryType::kFILE"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType4kOBJE", "tensorrt_llm::executor::kv_cache::MemoryType::kOBJ"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10MemoryType5kVRAME", "tensorrt_llm::executor::kv_cache::MemoryType::kVRAM"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache8MpiStateE", "tensorrt_llm::executor::kv_cache::MpiState"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache8MpiState6mRanksE", "tensorrt_llm::executor::kv_cache::MpiState::mRanks"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache8MpiStateeqERK8MpiState", "tensorrt_llm::executor::kv_cache::MpiState::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache8MpiStateeqERK8MpiState", "tensorrt_llm::executor::kv_cache::MpiState::operator==::other"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache8MpiState8toStringEv", "tensorrt_llm::executor::kv_cache::MpiState::toString"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache13RegisterDescsE", "tensorrt_llm::executor::kv_cache::RegisterDescs"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11SocketStateE", "tensorrt_llm::executor::kv_cache::SocketState"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11SocketState3mIpE", "tensorrt_llm::executor::kv_cache::SocketState::mIp"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11SocketState5mPortE", "tensorrt_llm::executor::kv_cache::SocketState::mPort"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache11SocketStateeqERK11SocketState", "tensorrt_llm::executor::kv_cache::SocketState::operator=="], [0, 4, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache11SocketStateeqERK11SocketState", "tensorrt_llm::executor::kv_cache::SocketState::operator==::other"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache11SocketState8toStringEv", "tensorrt_llm::executor::kv_cache::SocketState::toString"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache11SyncMessageE", "tensorrt_llm::executor::kv_cache::SyncMessage"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache13TransferDescsE", "tensorrt_llm::executor::kv_cache::TransferDescs"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10TransferOpE", "tensorrt_llm::executor::kv_cache::TransferOp"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10TransferOp5kREADE", "tensorrt_llm::executor::kv_cache::TransferOp::kREAD"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache10TransferOp6kWRITEE", "tensorrt_llm::executor::kv_cache::TransferOp::kWRITE"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequestE", "tensorrt_llm::executor::kv_cache::TransferRequest"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest15TransferRequestE10TransferOp13TransferDescs13TransferDescsRKNSt6stringENSt8optionalI11SyncMessageEE", "tensorrt_llm::executor::kv_cache::TransferRequest::TransferRequest"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest15TransferRequestE10TransferOp13TransferDescs13TransferDescsRKNSt6stringENSt8optionalI11SyncMessageEE", "tensorrt_llm::executor::kv_cache::TransferRequest::TransferRequest::dstDescs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest15TransferRequestE10TransferOp13TransferDescs13TransferDescsRKNSt6stringENSt8optionalI11SyncMessageEE", "tensorrt_llm::executor::kv_cache::TransferRequest::TransferRequest::op"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest15TransferRequestE10TransferOp13TransferDescs13TransferDescsRKNSt6stringENSt8optionalI11SyncMessageEE", "tensorrt_llm::executor::kv_cache::TransferRequest::TransferRequest::remoteName"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest15TransferRequestE10TransferOp13TransferDescs13TransferDescsRKNSt6stringENSt8optionalI11SyncMessageEE", "tensorrt_llm::executor::kv_cache::TransferRequest::TransferRequest::srcDescs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest15TransferRequestE10TransferOp13TransferDescs13TransferDescsRKNSt6stringENSt8optionalI11SyncMessageEE", "tensorrt_llm::executor::kv_cache::TransferRequest::TransferRequest::syncMessage"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest11getDstDescsEv", "tensorrt_llm::executor::kv_cache::TransferRequest::getDstDescs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest5getOpEv", "tensorrt_llm::executor::kv_cache::TransferRequest::getOp"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest13getRemoteNameEv", "tensorrt_llm::executor::kv_cache::TransferRequest::getRemoteName"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest11getSrcDescsEv", "tensorrt_llm::executor::kv_cache::TransferRequest::getSrcDescs"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache15TransferRequest14getSyncMessageEv", "tensorrt_llm::executor::kv_cache::TransferRequest::getSyncMessage"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest9mDstDescsE", "tensorrt_llm::executor::kv_cache::TransferRequest::mDstDescs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest3mOpE", "tensorrt_llm::executor::kv_cache::TransferRequest::mOp"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest11mRemoteNameE", "tensorrt_llm::executor::kv_cache::TransferRequest::mRemoteName"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest9mSrcDescsE", "tensorrt_llm::executor::kv_cache::TransferRequest::mSrcDescs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache15TransferRequest12mSyncMessageE", "tensorrt_llm::executor::kv_cache::TransferRequest::mSyncMessage"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache14TransferStatusE", "tensorrt_llm::executor::kv_cache::TransferStatus"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache14TransferStatus11isCompletedEv", "tensorrt_llm::executor::kv_cache::TransferStatus::isCompleted"], [0, 3, 1, "_CPPv4NK12tensorrt_llm8executor8kv_cache14TransferStatus4waitEv", "tensorrt_llm::executor::kv_cache::TransferStatus::wait"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8kv_cache14TransferStatusD0Ev", "tensorrt_llm::executor::kv_cache::TransferStatus::~TransferStatus"], [0, 3, 1, "_CPPv4IDpEN12tensorrt_llm8executor8kv_cache17makeTransferAgentENSt10unique_ptrI17BaseTransferAgentEERKNSt6stringEDpRR4Args", "tensorrt_llm::executor::kv_cache::makeTransferAgent"], [0, 8, 1, "_CPPv4IDpEN12tensorrt_llm8executor8kv_cache17makeTransferAgentENSt10unique_ptrI17BaseTransferAgentEERKNSt6stringEDpRR4Args", "tensorrt_llm::executor::kv_cache::makeTransferAgent::Args"], [0, 4, 1, "_CPPv4IDpEN12tensorrt_llm8executor8kv_cache17makeTransferAgentENSt10unique_ptrI17BaseTransferAgentEERKNSt6stringEDpRR4Args", "tensorrt_llm::executor::kv_cache::makeTransferAgent::args"], [0, 4, 1, "_CPPv4IDpEN12tensorrt_llm8executor8kv_cache17makeTransferAgentENSt10unique_ptrI17BaseTransferAgentEERKNSt6stringEDpRR4Args", "tensorrt_llm::executor::kv_cache::makeTransferAgent::backend"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE21ContextChunkingPolicy", "tensorrt_llm::executor::operator<<"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE23CapacitySchedulerPolicy", "tensorrt_llm::executor::operator<<"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE21ContextChunkingPolicy", "tensorrt_llm::executor::operator<<::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE23CapacitySchedulerPolicy", "tensorrt_llm::executor::operator<<::os"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE21ContextChunkingPolicy", "tensorrt_llm::executor::operator<<::policy"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE23CapacitySchedulerPolicy", "tensorrt_llm::executor::operator<<::policy"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor7versionEv", "tensorrt_llm::executor::version"], [1, 1, 1, "_CPPv4N12tensorrt_llm6layersE", "tensorrt_llm::layers"], [0, 1, 1, "_CPPv4N12tensorrt_llm3mpiE", "tensorrt_llm::mpi"], [0, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [0, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtimeE", "tensorrt_llm::runtime"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffersE", "tensorrt_llm::runtime::AllReduceBuffers"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::fakeBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::hiddenSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::maxSequenceLength"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfigKb", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::worldConfig"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers9TensorPtrE", "tensorrt_llm::runtime::AllReduceBuffers::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers18mAllReduceCommPtrsE", "tensorrt_llm::runtime::AllReduceBuffers::mAllReduceCommPtrs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers9mFlagPtrsE", "tensorrt_llm::runtime::AllReduceBuffers::mFlagPtrs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers17mIpcMemoryHandlesE", "tensorrt_llm::runtime::AllReduceBuffers::mIpcMemoryHandles"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataTypeE", "tensorrt_llm::runtime::BufferDataType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb", "tensorrt_llm::runtime::BufferDataType::BufferDataType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb", "tensorrt_llm::runtime::BufferDataType::BufferDataType::_unsigned"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb", "tensorrt_llm::runtime::BufferDataType::BufferDataType::dataType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb", "tensorrt_llm::runtime::BufferDataType::BufferDataType::pointer"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType11getDataTypeEv", "tensorrt_llm::runtime::BufferDataType::getDataType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType7getSizeEv", "tensorrt_llm::runtime::BufferDataType::getSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType13getSizeInBitsEv", "tensorrt_llm::runtime::BufferDataType::getSizeInBits"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType9isPointerEv", "tensorrt_llm::runtime::BufferDataType::isPointer"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType10isUnsignedEv", "tensorrt_llm::runtime::BufferDataType::isUnsigned"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType15kTrtPointerTypeE", "tensorrt_llm::runtime::BufferDataType::kTrtPointerType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType9mDataTypeE", "tensorrt_llm::runtime::BufferDataType::mDataType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType8mPointerE", "tensorrt_llm::runtime::BufferDataType::mPointer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType9mUnsignedE", "tensorrt_llm::runtime::BufferDataType::mUnsigned"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataTypecvN8nvinfer18DataTypeEEv", "tensorrt_llm::runtime::BufferDataType::operator nvinfer1::DataType"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManagerE", "tensorrt_llm::runtime::BufferManager"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager13BufferManagerE13CudaStreamPtrb", "tensorrt_llm::runtime::BufferManager::BufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager13BufferManagerE13CudaStreamPtrb", "tensorrt_llm::runtime::BufferManager::BufferManager::stream"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager13BufferManagerE13CudaStreamPtrb", "tensorrt_llm::runtime::BufferManager::BufferManager::trimPool"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager14CudaMemPoolPtrE", "tensorrt_llm::runtime::BufferManager::CudaMemPoolPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::BufferManager::CudaStreamPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10IBufferPtrE", "tensorrt_llm::runtime::BufferManager::IBufferPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10ITensorPtrE", "tensorrt_llm::runtime::BufferManager::ITensorPtr"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::dims"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::memoryType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::memoryType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::size"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::type"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::type"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copy"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv", "tensorrt_llm::runtime::BufferManager::copy"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType", "tensorrt_llm::runtime::BufferManager::copy"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy::dst"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::dst"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv", "tensorrt_llm::runtime::BufferManager::copy::dst"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::dst"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy::dst"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::dstType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy::src"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::src"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv", "tensorrt_llm::runtime::BufferManager::copy::src"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::src"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy::src"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::srcType"], [1, 3, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10IBufferPtrRKNSt6vectorI1TEE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom"], [1, 3, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom"], [1, 3, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7ITensor10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom"], [1, 8, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10IBufferPtrRKNSt6vectorI1TEE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::T"], [1, 8, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::T"], [1, 8, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::T"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::dims"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::dims"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10IBufferPtrRKNSt6vectorI1TEE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::memoryType"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::memoryType"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::memoryType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::memoryType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7ITensor10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::memoryType"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10IBufferPtrRKNSt6vectorI1TEE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::src"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::src"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::src"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::src"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7ITensor10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::src"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu::dims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu::type"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu::type"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyBufferE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyBuffer"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyBufferE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyBuffer::memoryType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyBufferE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyBuffer::type"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyTensorE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyTensor"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyTensorE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyTensor::memoryType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyTensorE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyTensor::type"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager9getStreamEv", "tensorrt_llm::runtime::BufferManager::getStream"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu::dims"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu::size"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu::type"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu::type"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync::dims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync::type"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync::type"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7ipcNvlsENSt3setIiEEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::ipcNvls"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7ipcNvlsENSt3setIiEEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::ipcNvls::dims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7ipcNvlsENSt3setIiEEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::ipcNvls::ranks"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7ipcNvlsENSt3setIiEEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::ipcNvls::type"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE", "tensorrt_llm::runtime::BufferManager::kBYTE_TYPE"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager5mPoolE", "tensorrt_llm::runtime::BufferManager::mPool"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7mStreamE", "tensorrt_llm::runtime::BufferManager::mStream"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager9mTrimPoolE", "tensorrt_llm::runtime::BufferManager::mTrimPool"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed::dims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed::type"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed::type"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager14memoryPoolFreeEv", "tensorrt_llm::runtime::BufferManager::memoryPoolFree"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager18memoryPoolReservedEv", "tensorrt_llm::runtime::BufferManager::memoryPoolReserved"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager16memoryPoolTrimToENSt6size_tE", "tensorrt_llm::runtime::BufferManager::memoryPoolTrimTo"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager16memoryPoolTrimToENSt6size_tE", "tensorrt_llm::runtime::BufferManager::memoryPoolTrimTo::size"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager14memoryPoolUsedEv", "tensorrt_llm::runtime::BufferManager::memoryPoolUsed"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned::dims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned::type"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned::type"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool::dims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool::type"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool::type"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager6setMemER7IBuffer7int32_t", "tensorrt_llm::runtime::BufferManager::setMem"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager6setMemER7IBuffer7int32_t", "tensorrt_llm::runtime::BufferManager::setMem::buffer"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager6setMemER7IBuffer7int32_t", "tensorrt_llm::runtime::BufferManager::setMem::value"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager7setZeroER7IBuffer", "tensorrt_llm::runtime::BufferManager::setZero"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager7setZeroER7IBuffer", "tensorrt_llm::runtime::BufferManager::setZero::buffer"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManagerD0Ev", "tensorrt_llm::runtime::BufferManager::~BufferManager"], [1, 2, 1, "_CPPv4I0EN12tensorrt_llm7runtime11BufferRangeE", "tensorrt_llm::runtime::BufferRange"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime11BufferRange4BaseE", "tensorrt_llm::runtime::BufferRange::Base"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI1UEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeERK7IBuffer", "tensorrt_llm::runtime::BufferRange::BufferRange"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tIXntNSt10is_const_vI1UEEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeER7IBuffer", "tensorrt_llm::runtime::BufferRange::BufferRange"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11BufferRange11BufferRangeEP1T9size_type", "tensorrt_llm::runtime::BufferRange::BufferRange"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI1UEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeERK7IBuffer", "tensorrt_llm::runtime::BufferRange::BufferRange::U"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tIXntNSt10is_const_vI1UEEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeER7IBuffer", "tensorrt_llm::runtime::BufferRange::BufferRange::U"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI1UEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeERK7IBuffer", "tensorrt_llm::runtime::BufferRange::BufferRange::buffer"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tIXntNSt10is_const_vI1UEEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeER7IBuffer", "tensorrt_llm::runtime::BufferRange::BufferRange::buffer"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11BufferRange11BufferRangeEP1T9size_type", "tensorrt_llm::runtime::BufferRange::BufferRange::data"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11BufferRange11BufferRangeEP1T9size_type", "tensorrt_llm::runtime::BufferRange::BufferRange::size"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime11BufferRangeE", "tensorrt_llm::runtime::BufferRange::T"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEventE", "tensorrt_llm::runtime::CudaEvent"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventE7pointerb", "tensorrt_llm::runtime::CudaEvent::CudaEvent"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventEj", "tensorrt_llm::runtime::CudaEvent::CudaEvent"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventE7pointerb", "tensorrt_llm::runtime::CudaEvent::CudaEvent::event"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventEj", "tensorrt_llm::runtime::CudaEvent::CudaEvent::flags"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventE7pointerb", "tensorrt_llm::runtime::CudaEvent::CudaEvent::ownsEvent"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7DeleterE", "tensorrt_llm::runtime::CudaEvent::Deleter"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEb", "tensorrt_llm::runtime::CudaEvent::Deleter::Deleter"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEv", "tensorrt_llm::runtime::CudaEvent::Deleter::Deleter"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEb", "tensorrt_llm::runtime::CudaEvent::Deleter::Deleter::ownsEvent"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter10mOwnsEventE", "tensorrt_llm::runtime::CudaEvent::Deleter::mOwnsEvent"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent7DeleterclE7pointer", "tensorrt_llm::runtime::CudaEvent::Deleter::operator()"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent7DeleterclE7pointer", "tensorrt_llm::runtime::CudaEvent::Deleter::operator()::event"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent8EventPtrE", "tensorrt_llm::runtime::CudaEvent::EventPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent12element_typeE", "tensorrt_llm::runtime::CudaEvent::element_type"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent3getEv", "tensorrt_llm::runtime::CudaEvent::get"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent6mEventE", "tensorrt_llm::runtime::CudaEvent::mEvent"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7pointerE", "tensorrt_llm::runtime::CudaEvent::pointer"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent11synchronizeEv", "tensorrt_llm::runtime::CudaEvent::synchronize"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStreamE", "tensorrt_llm::runtime::CudaStream"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_t", "tensorrt_llm::runtime::CudaStream::CudaStream"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib", "tensorrt_llm::runtime::CudaStream::CudaStream"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamEji", "tensorrt_llm::runtime::CudaStream::CudaStream"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib", "tensorrt_llm::runtime::CudaStream::CudaStream::device"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamEji", "tensorrt_llm::runtime::CudaStream::CudaStream::flags"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib", "tensorrt_llm::runtime::CudaStream::CudaStream::ownsStream"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamEji", "tensorrt_llm::runtime::CudaStream::CudaStream::priority"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_t", "tensorrt_llm::runtime::CudaStream::CudaStream::stream"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib", "tensorrt_llm::runtime::CudaStream::CudaStream::stream"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7DeleterE", "tensorrt_llm::runtime::CudaStream::Deleter"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEb", "tensorrt_llm::runtime::CudaStream::Deleter::Deleter"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEv", "tensorrt_llm::runtime::CudaStream::Deleter::Deleter"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEb", "tensorrt_llm::runtime::CudaStream::Deleter::Deleter::ownsStream"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter11mOwnsStreamE", "tensorrt_llm::runtime::CudaStream::Deleter::mOwnsStream"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream7DeleterclE12cudaStream_t", "tensorrt_llm::runtime::CudaStream::Deleter::operator()"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream7DeleterclE12cudaStream_t", "tensorrt_llm::runtime::CudaStream::Deleter::operator()::stream"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream9StreamPtrE", "tensorrt_llm::runtime::CudaStream::StreamPtr"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream3getEv", "tensorrt_llm::runtime::CudaStream::get"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream9getDeviceEv", "tensorrt_llm::runtime::CudaStream::getDevice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7mDeviceE", "tensorrt_llm::runtime::CudaStream::mDevice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7mStreamE", "tensorrt_llm::runtime::CudaStream::mStream"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordEN9CudaEvent7pointerE", "tensorrt_llm::runtime::CudaStream::record"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordERK9CudaEvent", "tensorrt_llm::runtime::CudaStream::record"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordEN9CudaEvent7pointerE", "tensorrt_llm::runtime::CudaStream::record::event"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordERK9CudaEvent", "tensorrt_llm::runtime::CudaStream::record::event"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream11synchronizeEv", "tensorrt_llm::runtime::CudaStream::synchronize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitEN9CudaEvent7pointerE", "tensorrt_llm::runtime::CudaStream::wait"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitERK9CudaEvent", "tensorrt_llm::runtime::CudaStream::wait"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitEN9CudaEvent7pointerE", "tensorrt_llm::runtime::CudaStream::wait::event"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitERK9CudaEvent", "tensorrt_llm::runtime::CudaStream::wait::event"], [1, 2, 1, "_CPPv4I_N8nvinfer18DataTypeE_b_bEN12tensorrt_llm7runtime14DataTypeTraitsE", "tensorrt_llm::runtime::DataTypeTraits"], [1, 8, 1, "_CPPv4I_N8nvinfer18DataTypeE_b_bEN12tensorrt_llm7runtime14DataTypeTraitsE", "tensorrt_llm::runtime::DataTypeTraits::kDataType"], [1, 8, 1, "_CPPv4I_N8nvinfer18DataTypeE_b_bEN12tensorrt_llm7runtime14DataTypeTraitsE", "tensorrt_llm::runtime::DataTypeTraits::kIsPointer"], [1, 8, 1, "_CPPv4I_N8nvinfer18DataTypeE_b_bEN12tensorrt_llm7runtime14DataTypeTraitsE", "tensorrt_llm::runtime::DataTypeTraits::kIsUnsigned"], [1, 2, 1, "_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE", "tensorrt_llm::runtime::DataTypeTraits<kDataType, kUnsigned, true>"], [1, 8, 1, "_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE", "tensorrt_llm::runtime::DataTypeTraits<kDataType, kUnsigned, true>::kDataType"], [1, 8, 1, "_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE", "tensorrt_llm::runtime::DataTypeTraits<kDataType, kUnsigned, true>::kUnsigned"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4nameE", "tensorrt_llm::runtime::DataTypeTraits<kDataType, kUnsigned, true>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<kDataType, kUnsigned, true>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4typeE", "tensorrt_llm::runtime::DataTypeTraits<kDataType, kUnsigned, true>::type"], [1, 2, 1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kBOOL, kUnsigned>"], [1, 8, 1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kBOOL, kUnsigned>::kUnsigned"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kBOOL, kUnsigned>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kBOOL, kUnsigned>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kBOOL, kUnsigned>::type"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kFLOAT>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kFLOAT>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kFLOAT>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kFLOAT>::type"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kHALF>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kHALF>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kHALF>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kHALF>::type"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32, true>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32, true>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32, true>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32, true>::type"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32>::type"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64, true>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64, true>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64, true>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64, true>::type"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64>::type"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT8>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT8>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT8>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT8>::type"], [1, 2, 1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kUINT8, kUnsigned>"], [1, 8, 1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedEE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kUINT8, kUnsigned>::kUnsigned"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4nameE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kUINT8, kUnsigned>::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4sizeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kUINT8, kUnsigned>::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4typeE", "tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kUINT8, kUnsigned>::type"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInputE", "tensorrt_llm::runtime::DecodingInput"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13DecodingInputEv", "tensorrt_llm::runtime::DecodingInput::DecodingInput"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputsE", "tensorrt_llm::runtime::DecodingInput::EagleInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs12acceptedLensE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::acceptedLens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs15acceptedPathIdsE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::acceptedPathIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs14acceptedTokensE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::acceptedTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs24chunkedContextNextTokensE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::chunkedContextNextTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs13lastDraftLensE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::lastDraftLens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs14lastDraftPathsE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::lastDraftPaths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs15lastDraftTokensE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::lastDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs13nextDraftLensE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::nextDraftLens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs14nextDraftPathsE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::nextDraftPaths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs15nextDraftTokensE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::nextDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11EagleInputs8seqSlotsE", "tensorrt_llm::runtime::DecodingInput::EagleInputs::seqSlots"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15bestPathIndicesE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::bestPathIndices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15bestPathLengthsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::bestPathLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs16lastDraftIndicesE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::lastDraftIndices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15lastDraftTokensE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::lastDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs21lastGenerationLengthsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::lastGenerationLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs19lastPositionIdsBaseE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::lastPositionIdsBase"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs5masksE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::masks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs18maxGenLengthDeviceE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::maxGenLengthDevice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs16nextDraftIndicesE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::nextDraftIndices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs14nextDraftProbsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::nextDraftProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15nextDraftTokensE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::nextDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs14nextFlatTokensE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::nextFlatTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs21nextGenerationLengthsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::nextGenerationLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs17packedPositionIdsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::packedPositionIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs8seqSlotsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::seqSlots"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputsE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs17constantThresholdE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::constantThreshold"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs11draftLogitsE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::draftLogits"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs10draftProbsE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::draftProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs13draftTokenIdsE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::draftTokenIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs14numDraftTokensE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::numDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs18numDraftTokensHostE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::numDraftTokensHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs4stepE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::step"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs11targetProbsE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::targetProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs14useDraftLogitsE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::useDraftLogits"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs18useDraftLogitsHostE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::useDraftLogitsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExternalDraftTokensInputs28useRandomAcceptanceThresholdE", "tensorrt_llm::runtime::DecodingInput::ExternalDraftTokensInputs::useRandomAcceptanceThreshold"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15LookaheadInputsE", "tensorrt_llm::runtime::DecodingInput::LookaheadInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15LookaheadInputs13tokensPerStepE", "tensorrt_llm::runtime::DecodingInput::LookaheadInputs::tokensPerStep"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputsE", "tensorrt_llm::runtime::DecodingInput::MedusaInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs22medusaCurTokensPerStepE", "tensorrt_llm::runtime::DecodingInput::MedusaInputs::medusaCurTokensPerStep"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs12medusaLogitsE", "tensorrt_llm::runtime::DecodingInput::MedusaInputs::medusaLogits"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs11medusaPathsE", "tensorrt_llm::runtime::DecodingInput::MedusaInputs::medusaPaths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs25medusaTargetTokensPerStepE", "tensorrt_llm::runtime::DecodingInput::MedusaInputs::medusaTargetTokensPerStep"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs13medusaTreeIdsE", "tensorrt_llm::runtime::DecodingInput::MedusaInputs::medusaTreeIds"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput14TensorConstPtrE", "tensorrt_llm::runtime::DecodingInput::TensorConstPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE", "tensorrt_llm::runtime::DecodingInput::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12badWordsLensE", "tensorrt_llm::runtime::DecodingInput::badWordsLens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13badWordsListsE", "tensorrt_llm::runtime::DecodingInput::badWordsLists"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12badWordsPtrsE", "tensorrt_llm::runtime::DecodingInput::badWordsPtrs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9batchSizeE", "tensorrt_llm::runtime::DecodingInput::batchSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput10batchSlotsE", "tensorrt_llm::runtime::DecodingInput::batchSlots"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput10beamWidthsE", "tensorrt_llm::runtime::DecodingInput::beamWidths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput16cacheIndirectionE", "tensorrt_llm::runtime::DecodingInput::cacheIndirection"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput11eagleInputsE", "tensorrt_llm::runtime::DecodingInput::eagleInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13embeddingBiasE", "tensorrt_llm::runtime::DecodingInput::embeddingBias"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput6endIdsE", "tensorrt_llm::runtime::DecodingInput::endIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25explicitDraftTokensInputsE", "tensorrt_llm::runtime::DecodingInput::explicitDraftTokensInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25externalDraftTokensInputsE", "tensorrt_llm::runtime::DecodingInput::externalDraftTokensInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13finishReasonsE", "tensorrt_llm::runtime::DecodingInput::finishReasons"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15generationStepsE", "tensorrt_llm::runtime::DecodingInput::generationSteps"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput7lengthsE", "tensorrt_llm::runtime::DecodingInput::lengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9logitsVecE", "tensorrt_llm::runtime::DecodingInput::logitsVec"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15lookaheadInputsE", "tensorrt_llm::runtime::DecodingInput::lookaheadInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput18maxAttentionWindowE", "tensorrt_llm::runtime::DecodingInput::maxAttentionWindow"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput14maxBadWordsLenE", "tensorrt_llm::runtime::DecodingInput::maxBadWordsLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9maxLengthE", "tensorrt_llm::runtime::DecodingInput::maxLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15maxStopWordsLenE", "tensorrt_llm::runtime::DecodingInput::maxStopWordsLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12medusaInputsE", "tensorrt_llm::runtime::DecodingInput::medusaInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput17noRepeatNgramSizeE", "tensorrt_llm::runtime::DecodingInput::noRepeatNgramSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput19sequenceLimitLengthE", "tensorrt_llm::runtime::DecodingInput::sequenceLimitLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15sinkTokenLengthE", "tensorrt_llm::runtime::DecodingInput::sinkTokenLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput4stepE", "tensorrt_llm::runtime::DecodingInput::step"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13stopWordsLensE", "tensorrt_llm::runtime::DecodingInput::stopWordsLens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput14stopWordsListsE", "tensorrt_llm::runtime::DecodingInput::stopWordsLists"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13stopWordsPtrsE", "tensorrt_llm::runtime::DecodingInput::stopWordsPtrs"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutputE", "tensorrt_llm::runtime::DecodingOutput"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypothesesE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses10batchDonesE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::batchDones"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses14cumLogProbsCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::cumLogProbsCBA"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5emptyERK13BufferManager", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::empty"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5emptyERK13BufferManager", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::empty::manager"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses4initERK13BufferManager11TokenIdType", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::init"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses4initERK13BufferManager11TokenIdType", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::init::endId"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses4initERK13BufferManager11TokenIdType", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::init::manager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses11logProbsCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::logProbsCBA"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses18minNormedScoresCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::minNormedScoresCBA"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses15normedScoresCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::normedScoresCBA"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses11numBeamsCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::numBeamsCBA"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses12outputIdsCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::outputIdsCBA"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7releaseEv", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::release"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::reshape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::reshape::batchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::reshape::beamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::reshape::maxSequenceLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses18sequenceLengthsCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::sequenceLengthsCBA"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5sliceE10SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::slice"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5sliceE10SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::slice::batchIndex"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5sliceE10SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::slice::size"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14DecodingOutputEv", "tensorrt_llm::runtime::DecodingOutput::DecodingOutput"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputsE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs21acceptedLengthsCumSumE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::acceptedLengthsCumSum"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs17acceptedTokensLenE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::acceptedTokensLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs15nextDraftTokensE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::nextDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs18nextDraftTokensLenE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::nextDraftTokensLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs12pathsOffsetsE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::pathsOffsets"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs18prevDraftTokensLenE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::prevDraftTokensLen"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE", "tensorrt_llm::runtime::DecodingOutput::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14beamHypothesesE", "tensorrt_llm::runtime::DecodingOutput::beamHypotheses"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput16cacheIndirectionE", "tensorrt_llm::runtime::DecodingOutput::cacheIndirection"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11cumLogProbsE", "tensorrt_llm::runtime::DecodingOutput::cumLogProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput12eagleBuffersE", "tensorrt_llm::runtime::DecodingOutput::eagleBuffers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26explicitDraftTokensBuffersE", "tensorrt_llm::runtime::DecodingOutput::explicitDraftTokensBuffers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput13finishReasonsE", "tensorrt_llm::runtime::DecodingOutput::finishReasons"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11finishedSumE", "tensorrt_llm::runtime::DecodingOutput::finishedSum"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11gatheredIdsE", "tensorrt_llm::runtime::DecodingOutput::gatheredIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput3idsE", "tensorrt_llm::runtime::DecodingOutput::ids"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput17kNegativeInfinityE", "tensorrt_llm::runtime::DecodingOutput::kNegativeInfinity"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput7lengthsE", "tensorrt_llm::runtime::DecodingOutput::lengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput8logProbsE", "tensorrt_llm::runtime::DecodingOutput::logProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput13logProbsTiledE", "tensorrt_llm::runtime::DecodingOutput::logProbsTiled"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput16lookaheadOutputsE", "tensorrt_llm::runtime::DecodingOutput::lookaheadOutputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9newTokensE", "tensorrt_llm::runtime::DecodingOutput::newTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14newTokensStepsE", "tensorrt_llm::runtime::DecodingOutput::newTokensSteps"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput12newTokensVecE", "tensorrt_llm::runtime::DecodingOutput::newTokensVec"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9parentIdsE", "tensorrt_llm::runtime::DecodingOutput::parentIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26speculativeDecodingOutputsE", "tensorrt_llm::runtime::DecodingOutput::speculativeDecodingOutputs"], [1, 2, 1, "_CPPv4I0EN12tensorrt_llm7runtime20DeviceAllocationNvlsE", "tensorrt_llm::runtime::DeviceAllocationNvls"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls20DeviceAllocationNvlsEv", "tensorrt_llm::runtime::DeviceAllocationNvls::DeviceAllocationNvls"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime20DeviceAllocationNvlsE", "tensorrt_llm::runtime::DeviceAllocationNvls::T"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls9_capacityE", "tensorrt_llm::runtime::DeviceAllocationNvls::_capacity"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls7_handleE", "tensorrt_llm::runtime::DeviceAllocationNvls::_handle"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls4freeEv", "tensorrt_llm::runtime::DeviceAllocationNvls::free"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime20DeviceAllocationNvls11getCapacityEv", "tensorrt_llm::runtime::DeviceAllocationNvls::getCapacity"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls21getIpcUnicastPointersEv", "tensorrt_llm::runtime::DeviceAllocationNvls::getIpcUnicastPointers"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime20DeviceAllocationNvls19getMulticastPointerEv", "tensorrt_llm::runtime::DeviceAllocationNvls::getMulticastPointer"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime20DeviceAllocationNvls17getUnicastPointerEv", "tensorrt_llm::runtime::DeviceAllocationNvls::getUnicastPointer"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls5resetE6size_tNSt3setIiEE", "tensorrt_llm::runtime::DeviceAllocationNvls::reset"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls5resetE6size_tNSt3setIiEE", "tensorrt_llm::runtime::DeviceAllocationNvls::reset::ranks"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvls5resetE6size_tNSt3setIiEE", "tensorrt_llm::runtime::DeviceAllocationNvls::reset::size"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20DeviceAllocationNvlsD0Ev", "tensorrt_llm::runtime::DeviceAllocationNvls::~DeviceAllocationNvls"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffersE", "tensorrt_llm::runtime::EagleBuffers"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers9BufferPtrE", "tensorrt_llm::runtime::EagleBuffers::BufferPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12EagleBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigE", "tensorrt_llm::runtime::EagleBuffers::EagleBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12EagleBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigE", "tensorrt_llm::runtime::EagleBuffers::EagleBuffers::decodingConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12EagleBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigE", "tensorrt_llm::runtime::EagleBuffers::EagleBuffers::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12EagleBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigE", "tensorrt_llm::runtime::EagleBuffers::EagleBuffers::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12EagleBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigE", "tensorrt_llm::runtime::EagleBuffers::EagleBuffers::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12EagleBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigE", "tensorrt_llm::runtime::EagleBuffers::EagleBuffers::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12EagleBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigE", "tensorrt_llm::runtime::EagleBuffers::EagleBuffers::worldConfig"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputsE", "tensorrt_llm::runtime::EagleBuffers::EngineOutputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs12acceptedLensE", "tensorrt_llm::runtime::EagleBuffers::EngineOutputs::acceptedLens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs13acceptedPathsE", "tensorrt_llm::runtime::EagleBuffers::EngineOutputs::acceptedPaths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs14acceptedTokensE", "tensorrt_llm::runtime::EagleBuffers::EngineOutputs::acceptedTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs24chunkedContextNextTokensE", "tensorrt_llm::runtime::EagleBuffers::EngineOutputs::chunkedContextNextTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs13nextDraftLensE", "tensorrt_llm::runtime::EagleBuffers::EngineOutputs::nextDraftLens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs14nextDraftPathsE", "tensorrt_llm::runtime::EagleBuffers::EngineOutputs::nextDraftPaths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13EngineOutputs15nextDraftTokensE", "tensorrt_llm::runtime::EagleBuffers::EngineOutputs::nextDraftTokens"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers7ITensorE", "tensorrt_llm::runtime::EagleBuffers::ITensor"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6InputsE", "tensorrt_llm::runtime::EagleBuffers::Inputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs22allLayersDraftTokenIdsE", "tensorrt_llm::runtime::EagleBuffers::Inputs::allLayersDraftTokenIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs33allLayersDraftTokenIdsPredecessorE", "tensorrt_llm::runtime::EagleBuffers::Inputs::allLayersDraftTokenIdsPredecessor"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs15allLayersScoresE", "tensorrt_llm::runtime::EagleBuffers::Inputs::allLayersScores"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs24chunkedContextNextTokensE", "tensorrt_llm::runtime::EagleBuffers::Inputs::chunkedContextNextTokens"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs6createE10SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::EagleBuffers::Inputs::create"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs6createE10SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::EagleBuffers::Inputs::create::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs6createE10SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::EagleBuffers::Inputs::create::maxNumSequences"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs6createE10SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::EagleBuffers::Inputs::create::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs6createE10SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::EagleBuffers::Inputs::create::worldConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs20currentExpandIndicesE", "tensorrt_llm::runtime::EagleBuffers::Inputs::currentExpandIndices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs9draftLensE", "tensorrt_llm::runtime::EagleBuffers::Inputs::draftLens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs10draftPathsE", "tensorrt_llm::runtime::EagleBuffers::Inputs::draftPaths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs14draftPathsHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::draftPathsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs11draftTokensE", "tensorrt_llm::runtime::EagleBuffers::Inputs::draftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs22dynamicTreeMaxTopKHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::dynamicTreeMaxTopKHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs29eagleNetCtxContextLengthsHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::eagleNetCtxContextLengthsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs34eagleNetCtxPastKeyValueLengthsHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::eagleNetCtxPastKeyValueLengthsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs27eagleNetCtxRequestTypesHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::eagleNetCtxRequestTypesHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs29eagleNetGenContextLengthsHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::eagleNetGenContextLengthsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs34eagleNetGenPastKeyValueLengthsHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::eagleNetGenPastKeyValueLengthsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs27eagleNetGenRequestTypesHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::eagleNetGenRequestTypesHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs18inputGenTokensHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::inputGenTokensHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs14posteriorAlphaE", "tensorrt_llm::runtime::EagleBuffers::Inputs::posteriorAlpha"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs18posteriorThresholdE", "tensorrt_llm::runtime::EagleBuffers::Inputs::posteriorThreshold"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs10prevScoresE", "tensorrt_llm::runtime::EagleBuffers::Inputs::prevScores"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs16randomDataSampleE", "tensorrt_llm::runtime::EagleBuffers::Inputs::randomDataSample"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs20randomDataValidationE", "tensorrt_llm::runtime::EagleBuffers::Inputs::randomDataValidation"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs29specDecodingGenerationLengthsE", "tensorrt_llm::runtime::EagleBuffers::Inputs::specDecodingGenerationLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs33specDecodingGenerationLengthsHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::specDecodingGenerationLengthsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs23specDecodingPackedMasksE", "tensorrt_llm::runtime::EagleBuffers::Inputs::specDecodingPackedMasks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs27specDecodingPositionOffsetsE", "tensorrt_llm::runtime::EagleBuffers::Inputs::specDecodingPositionOffsets"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs12temperaturesE", "tensorrt_llm::runtime::EagleBuffers::Inputs::temperatures"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs18useDynamicTreeHostE", "tensorrt_llm::runtime::EagleBuffers::Inputs::useDynamicTreeHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers6Inputs15useSpecDecodingE", "tensorrt_llm::runtime::EagleBuffers::Inputs::useSpecDecoding"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13LlmRequestPtrE", "tensorrt_llm::runtime::EagleBuffers::LlmRequestPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13RequestVectorE", "tensorrt_llm::runtime::EagleBuffers::RequestVector"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers10SizeType32E", "tensorrt_llm::runtime::EagleBuffers::SizeType32"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers9TensorMapE", "tensorrt_llm::runtime::EagleBuffers::TensorMap"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers9TensorPtrE", "tensorrt_llm::runtime::EagleBuffers::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers28chunkedContextNextTokensHostE", "tensorrt_llm::runtime::EagleBuffers::chunkedContextNextTokensHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers23cumSumGenerationLengthsE", "tensorrt_llm::runtime::EagleBuffers::cumSumGenerationLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers12engineInputsE", "tensorrt_llm::runtime::EagleBuffers::engineInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers13engineOutputsE", "tensorrt_llm::runtime::EagleBuffers::engineOutputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers18greedySamplingHostE", "tensorrt_llm::runtime::EagleBuffers::greedySamplingHost"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::insertInputTensors"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::insertInputTensors::inputBuffers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::insertInputTensors::outputBuffers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::insertInputTensors::worldConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers26mDefaultPosteriorThresholdE", "tensorrt_llm::runtime::EagleBuffers::mDefaultPosteriorThreshold"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers17mDoGreedySamplingE", "tensorrt_llm::runtime::EagleBuffers::mDoGreedySampling"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers19maxGenerationLengthE", "tensorrt_llm::runtime::EagleBuffers::maxGenerationLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers18posteriorAlphaHostE", "tensorrt_llm::runtime::EagleBuffers::posteriorAlphaHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers22posteriorThresholdHostE", "tensorrt_llm::runtime::EagleBuffers::posteriorThresholdHost"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::EagleBuffers::reshape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::EagleBuffers::reshape::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::EagleBuffers::reshape::numCtxSequences"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::EagleBuffers::reshape::numGenSequences"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers21scanReduceTempStorageE", "tensorrt_llm::runtime::EagleBuffers::scanReduceTempStorage"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12EagleBuffers26scanReduceTempStorageBytesE", "tensorrt_llm::runtime::EagleBuffers::scanReduceTempStorageBytes"], [1, 3, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs"], [1, 8, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::T"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::contextRequests"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::contextRequests"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::decoderBuffers"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::draftBuffers"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::eagleModule"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::genRequests"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::genRequests"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::manager"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::manager"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::modelConfig"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::requestTypes"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::seqSlots"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::seqSlots"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime12EagleBuffers13setFromInputsEvRK13RequestVectorRK13RequestVector10SizeType32RK7ITensorRKN12EagleBuffers6InputsERKN7runtime11EagleModuleERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::vocabSizePadded"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime12EagleBuffers13setFromInputsERK13RequestVectorRK13RequestVectorRKN7runtime7ITensorERK7ITensorRKN12EagleBuffers6InputsERKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::EagleBuffers::setFromInputs::worldConfig"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModuleE", "tensorrt_llm::runtime::EagleModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule11EagleModuleE10SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::EagleModule::EagleModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule11EagleModuleEv", "tensorrt_llm::runtime::EagleModule::EagleModule"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule11EagleModuleE10SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::EagleModule::EagleModule::maxDecodingDraftTokens"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule11EagleModuleE10SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::EagleModule::EagleModule::maxDraftPathLen"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule11EagleModuleE10SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::EagleModule::EagleModule::maxNonLeafNodesPerLayer"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule11EagleModuleE10SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::EagleModule::EagleModule::numTransformersLayer"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11EagleModule22getDefaultEagleChoicesEv", "tensorrt_llm::runtime::EagleModule::getDefaultEagleChoices"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11EagleModule26getMaxNonLeafNodesPerLayerEv", "tensorrt_llm::runtime::EagleModule::getMaxNonLeafNodesPerLayer"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11EagleModule23getNumTransformerLayersEv", "tensorrt_llm::runtime::EagleModule::getNumTransformerLayers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule20mDefaultEagleChoicesE", "tensorrt_llm::runtime::EagleModule::mDefaultEagleChoices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule24mMaxNonLeafNodesPerLayerE", "tensorrt_llm::runtime::EagleModule::mMaxNonLeafNodesPerLayer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11EagleModule21mNumTransformersLayerE", "tensorrt_llm::runtime::EagleModule::mNumTransformersLayer"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffersE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers9BufferPtrE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::BufferPtr"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputs15positionOffsetsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineInputs::positionOffsets"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputs18requestTypesDeviceE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineInputs::requestTypesDevice"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15bestPathIndicesE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::bestPathIndices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15bestPathLengthsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::bestPathLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs5masksE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::masks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs11maxGenTokenE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::maxGenToken"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs16nextDraftIndicesE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextDraftIndices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs14nextDraftProbsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextDraftProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15nextDraftTokensE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs14nextFlatTokensE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextFlatTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs21nextGenerationLengthsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextGenerationLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs19nextPositionOffsetsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextPositionOffsets"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs17packedPositionIdsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::packedPositionIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs13totalGenTokenE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::totalGenToken"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers::worldConfig"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7ITensorE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ITensor"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6InputsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::create"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::create::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::create::maxNumSequences"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::create::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::create::worldConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs12draftIndicesE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::draftIndices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs10draftProbsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::draftProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11draftTokensE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::draftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs17generationLengthsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::generationLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs21generationLengthsHostE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::generationLengthsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs16maxGenLengthHostE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::maxGenLengthHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11packedMasksE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::packedMasks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11positionIdsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::positionIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs15positionIdsBaseE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::positionIdsBase"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs16randomDataSampleE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::randomDataSample"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs20randomDataValidationE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::randomDataValidation"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs12temperaturesE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::temperatures"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs15useSpecDecodingE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::useSpecDecoding"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers10SizeType32E", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::SizeType32"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers9TensorMapE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::TensorMap"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers9TensorPtrE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers23cumSumGenerationLengthsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::cumSumGenerationLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12engineInputsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::engineInputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13engineOutputsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::engineOutputs"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::insertInputTensors"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::insertInputTensors::inputBuffers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::insertInputTensors::outputBuffers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::insertInputTensors::worldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::reshape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::reshape::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::reshape::numCtxSequences"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::reshape::numGenSequences"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers15scanTempStorageE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::scanTempStorage"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers20scanTempStorageBytesE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::scanTempStorageBytes"], [1, 3, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs"], [1, 8, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::T"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::contextPositionIds"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::contextPositionIds"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::decoderBuffers"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::draftBuffers"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::explicitDraftTokensModule"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::manager"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::modelConfig"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::numCtxSequences"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::numCtxSequences"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::numGenSequences"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::numGenSequences"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::requestTypes"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::seqSlots"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::seqSlots"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::stream"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::stream"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::vocabSizePadded"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN7runtime13BufferManagerERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::worldConfig"], [1, 2, 1, "_CPPv4I0EN12tensorrt_llm7runtime25GenericPromptTuningParamsE", "tensorrt_llm::runtime::GenericPromptTuningParams"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::GenericPromptTuningParams::GenericPromptTuningParams"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::GenericPromptTuningParams::GenericPromptTuningParams::embeddingTable"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::GenericPromptTuningParams::GenericPromptTuningParams::tasks"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::GenericPromptTuningParams::GenericPromptTuningParams::vocabSize"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams10SizeType32E", "tensorrt_llm::runtime::GenericPromptTuningParams::SizeType32"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime25GenericPromptTuningParamsE", "tensorrt_llm::runtime::GenericPromptTuningParams::TTensor"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE", "tensorrt_llm::runtime::GenericPromptTuningParams::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams14embeddingTableE", "tensorrt_llm::runtime::GenericPromptTuningParams::embeddingTable"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams19promptTuningEnabledE", "tensorrt_llm::runtime::GenericPromptTuningParams::promptTuningEnabled"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams5tasksE", "tensorrt_llm::runtime::GenericPromptTuningParams::tasks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9vocabSizeE", "tensorrt_llm::runtime::GenericPromptTuningParams::vocabSize"], [1, 2, 1, "_CPPv4I0EN12tensorrt_llm7runtime10GptDecoderE", "tensorrt_llm::runtime::GptDecoder"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13CudaStreamPtrE", "tensorrt_llm::runtime::GptDecoder::CudaStreamPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::mode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::speculativeDecodingModule"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::stream"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::vocabSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::vocabSizePadded"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime10GptDecoderE", "tensorrt_llm::runtime::GptDecoder::T"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder9TensorPtrE", "tensorrt_llm::runtime::GptDecoder::TensorPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", "tensorrt_llm::runtime::GptDecoder::disableLookahead"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", "tensorrt_llm::runtime::GptDecoder::disableLookahead::batchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", "tensorrt_llm::runtime::GptDecoder::disableLookahead::batchSlots"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", "tensorrt_llm::runtime::GptDecoder::disableLookahead::samplingConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardAsync"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardAsync::input"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardAsync::output"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardSync"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardSync::input"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardSync::output"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder17getSamplingConfigEv", "tensorrt_llm::runtime::GptDecoder::getSamplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder23mDecodingLayerWorkspaceE", "tensorrt_llm::runtime::GptDecoder::mDecodingLayerWorkspace"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13mDecodingModeE", "tensorrt_llm::runtime::GptDecoder::mDecodingMode"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder19mDynamicDecodeLayerE", "tensorrt_llm::runtime::GptDecoder::mDynamicDecodeLayer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder8mManagerE", "tensorrt_llm::runtime::GptDecoder::mManager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13mMaxBatchSizeE", "tensorrt_llm::runtime::GptDecoder::mMaxBatchSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder15mSamplingConfigE", "tensorrt_llm::runtime::GptDecoder::mSamplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10mVocabSizeE", "tensorrt_llm::runtime::GptDecoder::mVocabSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder16mVocabSizePaddedE", "tensorrt_llm::runtime::GptDecoder::mVocabSizePadded"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::GptDecoder::setup"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::batchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::batchSlots"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::explicitDraftTokensDType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::lookaheadAlgoConfigs"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::lookaheadPrompt"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::output"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::samplingConfig"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatchedE", "tensorrt_llm::runtime::GptDecoderBatched"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13CudaStreamPtrE", "tensorrt_llm::runtime::GptDecoderBatched::CudaStreamPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched17GptDecoderBatchedE13CudaStreamPtr", "tensorrt_llm::runtime::GptDecoderBatched::GptDecoderBatched"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched17GptDecoderBatchedE13CudaStreamPtr", "tensorrt_llm::runtime::GptDecoderBatched::GptDecoderBatched::stream"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13GptDecoderPtrE", "tensorrt_llm::runtime::GptDecoderBatched::GptDecoderPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13LlmRequestPtrE", "tensorrt_llm::runtime::GptDecoderBatched::LlmRequestPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13RequestVectorE", "tensorrt_llm::runtime::GptDecoderBatched::RequestVector"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched9TensorPtrE", "tensorrt_llm::runtime::GptDecoderBatched::TensorPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16disableLookaheadERK13RequestVectorRK9TensorPtr", "tensorrt_llm::runtime::GptDecoderBatched::disableLookahead"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16disableLookaheadERK13RequestVectorRK9TensorPtr", "tensorrt_llm::runtime::GptDecoderBatched::disableLookahead::batchSlots"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16disableLookaheadERK13RequestVectorRK9TensorPtr", "tensorrt_llm::runtime::GptDecoderBatched::disableLookahead::genRequests"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::finalize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::finalize::batchSlot"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::finalize::decoderState"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::finalize::samplingConfig"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::finalize::streaming"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched7forwardERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forward"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched7forwardERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forward::decoderState"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched7forwardERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forward::input"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12forwardAsyncERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardAsync"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12forwardAsyncERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardAsync::decoderState"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12forwardAsyncERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardAsync::input"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15forwardDispatchERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardDispatch"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15forwardDispatchERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardDispatch::decoderState"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15forwardDispatchERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardDispatch::input"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched16getBufferManagerEv", "tensorrt_llm::runtime::GptDecoderBatched::getBufferManager"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched16getDecoderStreamEv", "tensorrt_llm::runtime::GptDecoderBatched::getDecoderStream"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched20getUnderlyingDecoderEv", "tensorrt_llm::runtime::GptDecoderBatched::getUnderlyingDecoder"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mBufferManagerE", "tensorrt_llm::runtime::GptDecoderBatched::mBufferManager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched8mDecoderE", "tensorrt_llm::runtime::GptDecoderBatched::mDecoder"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mDecoderStreamE", "tensorrt_llm::runtime::GptDecoderBatched::mDecoderStream"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mRuntimeStreamE", "tensorrt_llm::runtime::GptDecoderBatched::mRuntimeStream"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::dtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::mode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::worldConfig"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfigE", "tensorrt_llm::runtime::GptJsonConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::contextParallelism"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::gpusPerNode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::name"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::pipelineParallelism"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::precision"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::runtimeDefaults"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::tensorParallelism"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3210SizeType3211ModelConfigNSt8optionalI15RuntimeDefaultsEE", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::version"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfig", "tensorrt_llm::runtime::GptJsonConfig::engineFilename"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfigRKNSt6stringE", "tensorrt_llm::runtime::GptJsonConfig::engineFilename"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfigRKNSt6stringE", "tensorrt_llm::runtime::GptJsonConfig::engineFilename::model"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfig", "tensorrt_llm::runtime::GptJsonConfig::engineFilename::worldConfig"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfigRKNSt6stringE", "tensorrt_llm::runtime::GptJsonConfig::engineFilename::worldConfig"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig21getContextParallelismEv", "tensorrt_llm::runtime::GptJsonConfig::getContextParallelism"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14getGpusPerNodeEv", "tensorrt_llm::runtime::GptJsonConfig::getGpusPerNode"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14getModelConfigEv", "tensorrt_llm::runtime::GptJsonConfig::getModelConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig21getModelConfigMutableEv", "tensorrt_llm::runtime::GptJsonConfig::getModelConfigMutable"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig7getNameEv", "tensorrt_llm::runtime::GptJsonConfig::getName"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig22getPipelineParallelismEv", "tensorrt_llm::runtime::GptJsonConfig::getPipelineParallelism"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getPrecisionEv", "tensorrt_llm::runtime::GptJsonConfig::getPrecision"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig18getRuntimeDefaultsEv", "tensorrt_llm::runtime::GptJsonConfig::getRuntimeDefaults"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig20getTensorParallelismEv", "tensorrt_llm::runtime::GptJsonConfig::getTensorParallelism"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig10getVersionEv", "tensorrt_llm::runtime::GptJsonConfig::getVersion"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getWorldSizeEv", "tensorrt_llm::runtime::GptJsonConfig::getWorldSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig19mContextParallelismE", "tensorrt_llm::runtime::GptJsonConfig::mContextParallelism"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig12mGpusPerNodeE", "tensorrt_llm::runtime::GptJsonConfig::mGpusPerNode"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig12mModelConfigE", "tensorrt_llm::runtime::GptJsonConfig::mModelConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5mNameE", "tensorrt_llm::runtime::GptJsonConfig::mName"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig20mPipelineParallelismE", "tensorrt_llm::runtime::GptJsonConfig::mPipelineParallelism"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig10mPrecisionE", "tensorrt_llm::runtime::GptJsonConfig::mPrecision"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig16mRuntimeDefaultsE", "tensorrt_llm::runtime::GptJsonConfig::mRuntimeDefaults"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig18mTensorParallelismE", "tensorrt_llm::runtime::GptJsonConfig::mTensorParallelism"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig8mVersionE", "tensorrt_llm::runtime::GptJsonConfig::mVersion"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt10filesystem4pathE", "tensorrt_llm::runtime::GptJsonConfig::parse"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt6stringE", "tensorrt_llm::runtime::GptJsonConfig::parse"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERNSt7istreamE", "tensorrt_llm::runtime::GptJsonConfig::parse"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt6stringE", "tensorrt_llm::runtime::GptJsonConfig::parse::json"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERNSt7istreamE", "tensorrt_llm::runtime::GptJsonConfig::parse::json"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt10filesystem4pathE", "tensorrt_llm::runtime::GptJsonConfig::parse::path"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime7IBufferE", "tensorrt_llm::runtime::IBuffer"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer8DataTypeE", "tensorrt_llm::runtime::IBuffer::DataType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferERK7IBuffer", "tensorrt_llm::runtime::IBuffer::IBuffer"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferEv", "tensorrt_llm::runtime::IBuffer::IBuffer"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer14SharedConstPtrE", "tensorrt_llm::runtime::IBuffer::SharedConstPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer9SharedPtrE", "tensorrt_llm::runtime::IBuffer::SharedPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer14UniqueConstPtrE", "tensorrt_llm::runtime::IBuffer::UniqueConstPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE", "tensorrt_llm::runtime::IBuffer::UniquePtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE", "tensorrt_llm::runtime::IBuffer::data"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4dataEv", "tensorrt_llm::runtime::IBuffer::data"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE", "tensorrt_llm::runtime::IBuffer::data"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataEv", "tensorrt_llm::runtime::IBuffer::data"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE", "tensorrt_llm::runtime::IBuffer::data::index"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE", "tensorrt_llm::runtime::IBuffer::data::index"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer11getCapacityEv", "tensorrt_llm::runtime::IBuffer::getCapacity"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer11getDataTypeEv", "tensorrt_llm::runtime::IBuffer::getDataType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer15getDataTypeNameE8DataType", "tensorrt_llm::runtime::IBuffer::getDataTypeName"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer15getDataTypeNameEv", "tensorrt_llm::runtime::IBuffer::getDataTypeName"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer15getDataTypeNameE8DataType", "tensorrt_llm::runtime::IBuffer::getDataTypeName::dataType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer13getMemoryTypeEv", "tensorrt_llm::runtime::IBuffer::getMemoryType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer17getMemoryTypeNameEv", "tensorrt_llm::runtime::IBuffer::getMemoryTypeName"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer7getSizeEv", "tensorrt_llm::runtime::IBuffer::getSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer14getSizeInBytesEv", "tensorrt_llm::runtime::IBuffer::getSizeInBytes"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer10memoryTypeEPKv", "tensorrt_llm::runtime::IBuffer::memoryType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer10memoryTypeEPKv", "tensorrt_llm::runtime::IBuffer::memoryType::data"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBufferaSERK7IBuffer", "tensorrt_llm::runtime::IBuffer::operator="], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer7releaseEv", "tensorrt_llm::runtime::IBuffer::release"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer6resizeENSt6size_tE", "tensorrt_llm::runtime::IBuffer::resize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer6resizeENSt6size_tE", "tensorrt_llm::runtime::IBuffer::resize::newSize"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::TConstPtr"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::TConstPtr"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::buffer"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::buffer"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::offset"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::offset"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::offset"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::offset"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::size"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::tensor"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::tensor"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer7toBytesENSt6size_tE", "tensorrt_llm::runtime::IBuffer::toBytes"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer7toBytesENSt6size_tE", "tensorrt_llm::runtime::IBuffer::toBytes::size"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtr", "tensorrt_llm::runtime::IBuffer::view"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view::TConstPtr"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view::size"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtr", "tensorrt_llm::runtime::IBuffer::view::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view::tensor"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrRNSt6vectorI1TEE", "tensorrt_llm::runtime::IBuffer::wrap"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrRNSt6vectorI1TEE", "tensorrt_llm::runtime::IBuffer::wrap::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::capacity"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::capacity"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::data"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::data"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::data"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::data"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::size"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::type"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::type"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrRNSt6vectorI1TEE", "tensorrt_llm::runtime::IBuffer::wrap::v"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7IBufferD0Ev", "tensorrt_llm::runtime::IBuffer::~IBuffer"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoderE", "tensorrt_llm::runtime::IGptDecoder"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder14TensorConstPtrE", "tensorrt_llm::runtime::IGptDecoder::TensorConstPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder9TensorPtrE", "tensorrt_llm::runtime::IGptDecoder::TensorPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::dtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::mode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::speculativeDecodingModule"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::stream"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::vocabSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrERKNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::vocabSizePadded"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", "tensorrt_llm::runtime::IGptDecoder::disableLookahead"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", "tensorrt_llm::runtime::IGptDecoder::disableLookahead::batchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", "tensorrt_llm::runtime::IGptDecoder::disableLookahead::batchSlots"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder16disableLookaheadERKNSt8optionalI14SamplingConfigEE10SizeType3214TensorConstPtr", "tensorrt_llm::runtime::IGptDecoder::disableLookahead::samplingConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardAsync"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardAsync::input"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardAsync::output"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardSync"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardSync::input"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardSync::output"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder17getSamplingConfigEv", "tensorrt_llm::runtime::IGptDecoder::getSamplingConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::batchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::batchSlots"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::explicitDraftTokensDType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::lookaheadAlgoConfigs"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::lookaheadPrompt"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::output"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEENSt8optionalIN8nvinfer18DataTypeEEERKNSt8optionalINSt6vectorI14TensorConstPtrEEEERKNSt8optionalINSt6vectorIN8executor23LookaheadDecodingConfigEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::samplingConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoderD0Ev", "tensorrt_llm::runtime::IGptDecoder::~IGptDecoder"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatchedE", "tensorrt_llm::runtime::IGptDecoderBatched"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoderBatched::CudaStreamPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched18IGptDecoderBatchedEv", "tensorrt_llm::runtime::IGptDecoderBatched::IGptDecoderBatched"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched13LlmRequestPtrE", "tensorrt_llm::runtime::IGptDecoderBatched::LlmRequestPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched13RequestVectorE", "tensorrt_llm::runtime::IGptDecoderBatched::RequestVector"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched9TensorPtrE", "tensorrt_llm::runtime::IGptDecoderBatched::TensorPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched16disableLookaheadERK13RequestVectorRK9TensorPtr", "tensorrt_llm::runtime::IGptDecoderBatched::disableLookahead"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched16disableLookaheadERK13RequestVectorRK9TensorPtr", "tensorrt_llm::runtime::IGptDecoderBatched::disableLookahead::batchSlots"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched16disableLookaheadERK13RequestVectorRK9TensorPtr", "tensorrt_llm::runtime::IGptDecoderBatched::disableLookahead::genRequests"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::IGptDecoderBatched::finalize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::IGptDecoderBatched::finalize::batchSlot"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::IGptDecoderBatched::finalize::decoderState"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::IGptDecoderBatched::finalize::samplingConfig"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched8finalizeERKN7decoder12DecoderStateE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::IGptDecoderBatched::finalize::streaming"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched7forwardERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forward"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched7forwardERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forward::decoderState"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched7forwardERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forward::input"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched12forwardAsyncERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forwardAsync"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched12forwardAsyncERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forwardAsync::decoderState"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched12forwardAsyncERKN7decoder12DecoderStateERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forwardAsync::input"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::IGptDecoderBatched::setup"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::IGptDecoderBatched::setup::dtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::IGptDecoderBatched::setup::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::IGptDecoderBatched::setup::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::IGptDecoderBatched::setup::mode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::IGptDecoderBatched::setup::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::IGptDecoderBatched::setup::worldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatchedD0Ev", "tensorrt_llm::runtime::IGptDecoderBatched::~IGptDecoderBatched"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime7ITensorE", "tensorrt_llm::runtime::ITensor"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9DimType64E", "tensorrt_llm::runtime::ITensor::DimType64"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorERK7ITensor", "tensorrt_llm::runtime::ITensor::ITensor"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorEv", "tensorrt_llm::runtime::ITensor::ITensor"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE", "tensorrt_llm::runtime::ITensor::Shape"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor14SharedConstPtrE", "tensorrt_llm::runtime::ITensor::SharedConstPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE", "tensorrt_llm::runtime::ITensor::SharedPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9TensorMapE", "tensorrt_llm::runtime::ITensor::TensorMap"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor14UniqueConstPtrE", "tensorrt_llm::runtime::ITensor::UniqueConstPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE", "tensorrt_llm::runtime::ITensor::UniquePtr"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atEN7ITensor14UniqueConstPtrERR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at::TConstPtr"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atEN7ITensor14UniqueConstPtrERR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at::TConstPtr"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at::offsetDims"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atEN7ITensor14UniqueConstPtrERR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at::offsetDims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at::offsetDims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at::offsetDims"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at::tensor"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atEN7ITensor14UniqueConstPtrERR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at::tensor"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8castSizeE6size_t", "tensorrt_llm::runtime::ITensor::castSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8castSizeE6size_t", "tensorrt_llm::runtime::ITensor::castSize::newSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8flattenNE9SharedPtrNSt7int64_tE", "tensorrt_llm::runtime::ITensor::flattenN"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8flattenNE9SharedPtrNSt7int64_tE", "tensorrt_llm::runtime::ITensor::flattenN::sliceN"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8flattenNE9SharedPtrNSt7int64_tE", "tensorrt_llm::runtime::ITensor::flattenN::tensor"], [1, 3, 1, "_CPPv4I_10SizeType32ENK12tensorrt_llm7runtime7ITensor12getDimensionE9DimType64v", "tensorrt_llm::runtime::ITensor::getDimension"], [1, 8, 1, "_CPPv4I_10SizeType32ENK12tensorrt_llm7runtime7ITensor12getDimensionE9DimType64v", "tensorrt_llm::runtime::ITensor::getDimension::n"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7ITensor8getShapeEv", "tensorrt_llm::runtime::ITensor::getShape"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9makeShapeERKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::makeShape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9makeShapeERKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::makeShape::dims"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensoraSERK7ITensor", "tensorrt_llm::runtime::ITensor::operator="], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7reshapeERK5Shape", "tensorrt_llm::runtime::ITensor::reshape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7reshapeERK5Shape", "tensorrt_llm::runtime::ITensor::reshape::dims"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor6resizeENSt6size_tE", "tensorrt_llm::runtime::ITensor::resize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor6resizeENSt6size_tE", "tensorrt_llm::runtime::ITensor::resize::newSize"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals"], [1, 3, 1, "_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapeRK5Shape", "tensorrt_llm::runtime::ITensor::shapeEquals"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERK5Shape", "tensorrt_llm::runtime::ITensor::shapeEquals"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERKNSt16initializer_listI10SizeType32EE", "tensorrt_llm::runtime::ITensor::shapeEquals"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::T"], [1, 8, 1, "_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::count"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::count"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::dims"], [1, 4, 1, "_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::dims"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::lhs"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapeRK5Shape", "tensorrt_llm::runtime::ITensor::shapeEquals::lhs"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERK5Shape", "tensorrt_llm::runtime::ITensor::shapeEquals::other"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERKNSt16initializer_listI10SizeType32EE", "tensorrt_llm::runtime::ITensor::shapeEquals::other"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapeRK5Shape", "tensorrt_llm::runtime::ITensor::shapeEquals::rhs"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape9DimType64", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE9DimType64", "tensorrt_llm::runtime::ITensor::slice"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::TConstPtr"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::TConstPtr"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice::TConstPtr"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::TConstPtr"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice::TConstPtr"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::TConstPtr"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offset"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offset"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offset"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offset"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape9DimType64", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE9DimType64", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape9DimType64", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE9DimType64", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape9DimType64", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE9DimType64", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeE10SizeType32", "tensorrt_llm::runtime::ITensor::squeeze"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::squeeze"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeE10SizeType32", "tensorrt_llm::runtime::ITensor::squeeze::dim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::squeeze::dim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::squeeze::shape"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7stridesERK5Shape", "tensorrt_llm::runtime::ITensor::strides"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7stridesERK5Shape", "tensorrt_llm::runtime::ITensor::strides::dims"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8toStringERK5Shape", "tensorrt_llm::runtime::ITensor::toString"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8toStringERK5Shape", "tensorrt_llm::runtime::ITensor::toString::dims"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeE10SizeType32", "tensorrt_llm::runtime::ITensor::unsqueeze"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::unsqueeze"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeE10SizeType32", "tensorrt_llm::runtime::ITensor::unsqueeze::dim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::unsqueeze::dim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::unsqueeze::shape"], [1, 3, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::view"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewE9SharedPtr", "tensorrt_llm::runtime::ITensor::view"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewEN7IBuffer9SharedPtrERK5Shape", "tensorrt_llm::runtime::ITensor::view"], [1, 8, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::view::TConstPtr"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewEN7IBuffer9SharedPtrERK5Shape", "tensorrt_llm::runtime::ITensor::view::buffer"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::view::dims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewEN7IBuffer9SharedPtrERK5Shape", "tensorrt_llm::runtime::ITensor::view::dims"], [1, 4, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::view::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewE9SharedPtr", "tensorrt_llm::runtime::ITensor::view::tensor"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor6volumeERK5Shape", "tensorrt_llm::runtime::ITensor::volume"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor6volumeERK5Shape", "tensorrt_llm::runtime::ITensor::volume::dims"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor17volumeNonNegativeERK5Shape", "tensorrt_llm::runtime::ITensor::volumeNonNegative"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor17volumeNonNegativeERK5Shape", "tensorrt_llm::runtime::ITensor::volumeNonNegative::shape"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape", "tensorrt_llm::runtime::ITensor::wrap"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape", "tensorrt_llm::runtime::ITensor::wrap"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape", "tensorrt_llm::runtime::ITensor::wrap"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape", "tensorrt_llm::runtime::ITensor::wrap::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape", "tensorrt_llm::runtime::ITensor::wrap::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::capacity"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::capacity"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape", "tensorrt_llm::runtime::ITensor::wrap::data"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::data"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape", "tensorrt_llm::runtime::ITensor::wrap::data"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::data"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape", "tensorrt_llm::runtime::ITensor::wrap::shape"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::shape"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape", "tensorrt_llm::runtime::ITensor::wrap::shape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape", "tensorrt_llm::runtime::ITensor::wrap::shape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::shape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape", "tensorrt_llm::runtime::ITensor::wrap::type"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::type"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape", "tensorrt_llm::runtime::ITensor::wrap::v"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7ITensorD0Ev", "tensorrt_llm::runtime::ITensor::~ITensor"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryE", "tensorrt_llm::runtime::IpcMemory"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9BufferPtrE", "tensorrt_llm::runtime::IpcMemory::BufferPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory10FLAGS_SIZEE", "tensorrt_llm::runtime::IpcMemory::FLAGS_SIZE"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb", "tensorrt_llm::runtime::IpcMemory::IpcMemory"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryERK9IpcMemory", "tensorrt_llm::runtime::IpcMemory::IpcMemory"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryERR9IpcMemory", "tensorrt_llm::runtime::IpcMemory::IpcMemory"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb", "tensorrt_llm::runtime::IpcMemory::IpcMemory::bufferSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb", "tensorrt_llm::runtime::IpcMemory::IpcMemory::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb", "tensorrt_llm::runtime::IpcMemory::IpcMemory::openIpc"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb", "tensorrt_llm::runtime::IpcMemory::IpcMemory::worldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::IpcMemory::allocateIpcMemory"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::IpcMemory::allocateIpcMemory::bufferSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::IpcMemory::allocateIpcMemory::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::IpcMemory::allocateIpcMemory::worldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory16destroyIpcMemoryEv", "tensorrt_llm::runtime::IpcMemory::destroyIpcMemory"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9IpcMemory11getCommPtrsEv", "tensorrt_llm::runtime::IpcMemory::getCommPtrs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory7mBufferE", "tensorrt_llm::runtime::IpcMemory::mBuffer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9mCommPtrsE", "tensorrt_llm::runtime::IpcMemory::mCommPtrs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory8mOpenIpcE", "tensorrt_llm::runtime::IpcMemory::mOpenIpc"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory7mTpRankE", "tensorrt_llm::runtime::IpcMemory::mTpRank"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryaSERK9IpcMemory", "tensorrt_llm::runtime::IpcMemory::operator="], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryaSERR9IpcMemory", "tensorrt_llm::runtime::IpcMemory::operator="], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryD0Ev", "tensorrt_llm::runtime::IpcMemory::~IpcMemory"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandleE", "tensorrt_llm::runtime::IpcNvlsHandle"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle14ipc_uc_handlesE", "tensorrt_llm::runtime::IpcNvlsHandle::ipc_uc_handles"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle11ipc_uc_ptrsE", "tensorrt_llm::runtime::IpcNvlsHandle::ipc_uc_ptrs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle10ipc_uc_vasE", "tensorrt_llm::runtime::IpcNvlsHandle::ipc_uc_vas"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle9mc_handleE", "tensorrt_llm::runtime::IpcNvlsHandle::mc_handle"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle6mc_ptrE", "tensorrt_llm::runtime::IpcNvlsHandle::mc_ptr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle5mc_vaE", "tensorrt_llm::runtime::IpcNvlsHandle::mc_va"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle4sizeE", "tensorrt_llm::runtime::IpcNvlsHandle::size"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle9uc_handleE", "tensorrt_llm::runtime::IpcNvlsHandle::uc_handle"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle6uc_ptrE", "tensorrt_llm::runtime::IpcNvlsHandle::uc_ptr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13IpcNvlsHandle5uc_vaE", "tensorrt_llm::runtime::IpcNvlsHandle::uc_va"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffersE", "tensorrt_llm::runtime::LookaheadDecodingBuffers"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers24LookaheadDecodingBuffersE10SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::LookaheadDecodingBuffers::LookaheadDecodingBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers24LookaheadDecodingBuffersE10SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::LookaheadDecodingBuffers::LookaheadDecodingBuffers::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers24LookaheadDecodingBuffersE10SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::LookaheadDecodingBuffers::LookaheadDecodingBuffers::maxNumSequences"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers24LookaheadDecodingBuffersE10SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::LookaheadDecodingBuffers::LookaheadDecodingBuffers::maxTokensPerStep"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers9TensorPtrE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers17generationLengthsE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::generationLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers11packedMasksE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::packedMasks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers11positionIdsE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::positionIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers15positionOffsetsE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::positionOffsets"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModuleE", "tensorrt_llm::runtime::LookaheadModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadModule::LookaheadModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleEv", "tensorrt_llm::runtime::LookaheadModule::LookaheadModule"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadModule::LookaheadModule::maxDecodingDraftTokens"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadModule::LookaheadModule::maxDraftPathLen"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime15LookaheadModule18getExecutionConfigEv", "tensorrt_llm::runtime::LookaheadModule::getExecutionConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule16mExecutionConfigE", "tensorrt_llm::runtime::LookaheadModule::mExecutionConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule18setExecutionConfigERKN8executor23LookaheadDecodingConfigE", "tensorrt_llm::runtime::LookaheadModule::setExecutionConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule18setExecutionConfigERKN8executor23LookaheadDecodingConfigE", "tensorrt_llm::runtime::LookaheadModule::setExecutionConfig::config"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffersE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::decodingConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::runtime"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RK13BufferManagerRK11ModelConfigRK11WorldConfigRKN8executor14DecodingConfigERK11TllmRuntime", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::worldConfig"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers9TensorMapE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::TensorMap"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers9TensorPtrE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers18batchSlotsHostCopyE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::batchSlotsHostCopy"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers12cumSumLengthE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::cumSumLength"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers24disableLookaheadDecodingEv", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::disableLookaheadDecoding"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23enableLookaheadDecodingE10SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::enableLookaheadDecoding"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23enableLookaheadDecodingE10SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::enableLookaheadDecoding::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23enableLookaheadDecodingE10SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::enableLookaheadDecoding::tokensPerStep"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23generationLengthsDeviceE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::generationLengthsDevice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers21generationLengthsHostE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::generationLengthsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers25generationLengthsHostCopyE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::generationLengthsHostCopy"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers18insertInputTensorsER9TensorMapR9TensorMapRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::insertInputTensors"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers18insertInputTensorsER9TensorMapR9TensorMapRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::insertInputTensors::inputBuffers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers18insertInputTensorsER9TensorMapR9TensorMapRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::insertInputTensors::outputBuffers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers18insertInputTensorsER9TensorMapR9TensorMapRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::insertInputTensors::worldConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers14packedMaskHostE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::packedMaskHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers18packedMaskHostCopyE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::packedMaskHostCopy"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers17packedMasksDeviceE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::packedMasksDevice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers17positionIdsDeviceE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionIdsDevice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers15positionIdsHostE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionIdsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers19positionIdsHostCopyE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionIdsHostCopy"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers21positionOffsetsDeviceE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionOffsetsDevice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers19positionOffsetsHostE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionOffsetsHost"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23positionOffsetsHostCopyE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionOffsetsHostCopy"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::reshape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::reshape::numCtxSequences"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::reshape::numGenSequences"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::reshape::tokensPerStep"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::decoderLookaheadBuffers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::modelConfig"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::numCtxSequences"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::numGenSequences"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::requestTypes"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::runtime"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::seqSlots"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RK7ITensorRK7ITensorRK24LookaheadDecodingBuffersRK11TllmRuntimeRK11ModelConfigRK11WorldConfig", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::worldConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers15useSpecDecodingE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::useSpecDecoding"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCacheE", "tensorrt_llm::runtime::LoraCache"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCache::LoraCache"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCache::LoraCache::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCache::LoraCache::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCache::LoraCache::pageManagerConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCache::LoraCache::worldConfig"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache10TaskIdTypeE", "tensorrt_llm::runtime::LoraCache::TaskIdType"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig11adapterSizeE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::adapterSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig6inSizeE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::inSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7layerIdE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::layerId"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8moduleIdE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::moduleId"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8numSlotsE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::numSlots"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfigeqERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::operator=="], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfigeqERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::operator==::o"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7outSizeE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::outSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig6pageIdE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::pageId"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig17scalingVecPointerE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::scalingVecPointer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7slotIdxE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::slotIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8toStringEv", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::toString"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig16weightsInPointerE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::weightsInPointer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig17weightsOutPointerE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::weightsOutPointer"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache28TaskLayerModuleConfigListPtrE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfigListPtr"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueE", "tensorrt_llm::runtime::LoraCache::TaskValue"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERR9TaskValue", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueEv", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::configs"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::done"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::inProgress"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::it"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::loadInProgress"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::loaded"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERR9TaskValue", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::o"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::pageIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue7configsE", "tensorrt_llm::runtime::LoraCache::TaskValue::configs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue4doneE", "tensorrt_llm::runtime::LoraCache::TaskValue::done"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue10inProgressE", "tensorrt_llm::runtime::LoraCache::TaskValue::inProgress"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue2itE", "tensorrt_llm::runtime::LoraCache::TaskValue::it"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue14loadInProgressE", "tensorrt_llm::runtime::LoraCache::TaskValue::loadInProgress"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue6loadedE", "tensorrt_llm::runtime::LoraCache::TaskValue::loaded"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueaSERR9TaskValue", "tensorrt_llm::runtime::LoraCache::TaskValue::operator="], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueaSERR9TaskValue", "tensorrt_llm::runtime::LoraCache::TaskValue::operator=::o"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue7pageIdsE", "tensorrt_llm::runtime::LoraCache::TaskValue::pageIds"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueD0Ev", "tensorrt_llm::runtime::LoraCache::TaskValue::~TaskValue"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12TaskValuePtrE", "tensorrt_llm::runtime::LoraCache::TaskValuePtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TensorPtrE", "tensorrt_llm::runtime::LoraCache::TensorPtr"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatusE", "tensorrt_llm::runtime::LoraCache::ValueStatus"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus20kVALUE_STATUS_LOADEDE", "tensorrt_llm::runtime::LoraCache::ValueStatus::kVALUE_STATUS_LOADED"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus21kVALUE_STATUS_MISSINGE", "tensorrt_llm::runtime::LoraCache::ValueStatus::kVALUE_STATUS_MISSING"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus24kVALUE_STATUS_PROCESSINGE", "tensorrt_llm::runtime::LoraCache::ValueStatus::kVALUE_STATUS_PROCESSING"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache4bumpE10TaskIdType", "tensorrt_llm::runtime::LoraCache::bump"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache4bumpE10TaskIdType", "tensorrt_llm::runtime::LoraCache::bump::taskId"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache18bumpTaskInProgressE10TaskIdType", "tensorrt_llm::runtime::LoraCache::bumpTaskInProgress"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache18bumpTaskInProgressE10TaskIdType", "tensorrt_llm::runtime::LoraCache::bumpTaskInProgress::taskId"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache19claimPagesWithEvictE10SizeType32", "tensorrt_llm::runtime::LoraCache::claimPagesWithEvict"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache19claimPagesWithEvictE10SizeType32", "tensorrt_llm::runtime::LoraCache::claimPagesWithEvict::numPages"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache8copyTaskE10TaskIdTypeR9LoraCacheb", "tensorrt_llm::runtime::LoraCache::copyTask"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache8copyTaskE10TaskIdTypeR9LoraCacheb", "tensorrt_llm::runtime::LoraCache::copyTask::deviceCache"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache8copyTaskE10TaskIdTypeR9LoraCacheb", "tensorrt_llm::runtime::LoraCache::copyTask::markDone"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache8copyTaskE10TaskIdTypeR9LoraCacheb", "tensorrt_llm::runtime::LoraCache::copyTask::taskId"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache", "tensorrt_llm::runtime::LoraCache::copyTaskMapPages"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache", "tensorrt_llm::runtime::LoraCache::copyTaskMapPages::sourceTaskValue"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache", "tensorrt_llm::runtime::LoraCache::copyTaskMapPages::targetCache"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache", "tensorrt_llm::runtime::LoraCache::copyTaskMapPages::targetPageIds"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache", "tensorrt_llm::runtime::LoraCache::copyTaskMapPages::targetTaskValue"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::config"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::moduleIdToModel"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::pageIds"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::pages"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::weights"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::worldConfig"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE10TaskIdType", "tensorrt_llm::runtime::LoraCache::determineNumPages"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE9TensorPtr", "tensorrt_llm::runtime::LoraCache::determineNumPages"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE9TensorPtr", "tensorrt_llm::runtime::LoraCache::determineNumPages::config"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE10TaskIdType", "tensorrt_llm::runtime::LoraCache::determineNumPages::taskId"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache4fitsE9TensorPtr", "tensorrt_llm::runtime::LoraCache::fits"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache4fitsE9TensorPtr", "tensorrt_llm::runtime::LoraCache::fits::config"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3getE10TaskIdType", "tensorrt_llm::runtime::LoraCache::get"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3getE10TaskIdType", "tensorrt_llm::runtime::LoraCache::get::taskId"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache11getNumPagesEv", "tensorrt_llm::runtime::LoraCache::getNumPages"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache10getPagePtrE6size_t", "tensorrt_llm::runtime::LoraCache::getPagePtr"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache10getPagePtrE6size_t", "tensorrt_llm::runtime::LoraCache::getPagePtr::pageId"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache9getStatusE10TaskIdType", "tensorrt_llm::runtime::LoraCache::getStatus"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache9getStatusE10TaskIdType", "tensorrt_llm::runtime::LoraCache::getStatus::taskId"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache3hasE10TaskIdType", "tensorrt_llm::runtime::LoraCache::has"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache3hasE10TaskIdType", "tensorrt_llm::runtime::LoraCache::has::taskId"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache6isDoneE10TaskIdType", "tensorrt_llm::runtime::LoraCache::isDone"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache6isDoneE10TaskIdType", "tensorrt_llm::runtime::LoraCache::isDone::taskId"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache8isLoadedE10TaskIdType", "tensorrt_llm::runtime::LoraCache::isLoaded"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache8isLoadedE10TaskIdType", "tensorrt_llm::runtime::LoraCache::isLoaded::taskId"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus20kVALUE_STATUS_LOADEDE", "tensorrt_llm::runtime::LoraCache::kVALUE_STATUS_LOADED"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus21kVALUE_STATUS_MISSINGE", "tensorrt_llm::runtime::LoraCache::kVALUE_STATUS_MISSING"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus24kVALUE_STATUS_PROCESSINGE", "tensorrt_llm::runtime::LoraCache::kVALUE_STATUS_PROCESSING"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsE10TaskIdType9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsER9TaskValue9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsER9TaskValue9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::cacheValue"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsE10TaskIdType9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::config"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsER9TaskValue9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::config"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsE10TaskIdType9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::taskId"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsE10TaskIdType9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::weights"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsER9TaskValue9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::weights"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache14mBufferManagerE", "tensorrt_llm::runtime::LoraCache::mBufferManager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9mCacheMapE", "tensorrt_llm::runtime::LoraCache::mCacheMap"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11mCacheMutexE", "tensorrt_llm::runtime::LoraCache::mCacheMutex"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17mCachePageManagerE", "tensorrt_llm::runtime::LoraCache::mCachePageManager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21mDeviceBufferManagersE", "tensorrt_llm::runtime::LoraCache::mDeviceBufferManagers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache10mDoneTasksE", "tensorrt_llm::runtime::LoraCache::mDoneTasks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16mInProgressTasksE", "tensorrt_llm::runtime::LoraCache::mInProgressTasks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12mModelConfigE", "tensorrt_llm::runtime::LoraCache::mModelConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17mModuleIdToModuleE", "tensorrt_llm::runtime::LoraCache::mModuleIdToModule"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache18mPageManagerConfigE", "tensorrt_llm::runtime::LoraCache::mPageManagerConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11mPagesMutexE", "tensorrt_llm::runtime::LoraCache::mPagesMutex"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12mWorldConfigE", "tensorrt_llm::runtime::LoraCache::mWorldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11markAllDoneEv", "tensorrt_llm::runtime::LoraCache::markAllDone"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12markTaskDoneE10TaskIdType", "tensorrt_llm::runtime::LoraCache::markTaskDone"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12markTaskDoneE10TaskIdType", "tensorrt_llm::runtime::LoraCache::markTaskDone::taskId"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb", "tensorrt_llm::runtime::LoraCache::put"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb", "tensorrt_llm::runtime::LoraCache::put::config"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb", "tensorrt_llm::runtime::LoraCache::put::load"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb", "tensorrt_llm::runtime::LoraCache::put::taskId"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb", "tensorrt_llm::runtime::LoraCache::put::weights"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpu"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpu::input"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpu::output"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpu::tpRank"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpu::tpSize"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner::input"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner::output"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner::tpRank"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner::tpSize"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullExceptionE", "tensorrt_llm::runtime::LoraCacheFullException"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullException22LoraCacheFullExceptionERKNSt6stringE", "tensorrt_llm::runtime::LoraCacheFullException::LoraCacheFullException"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullException22LoraCacheFullExceptionERKNSt6stringE", "tensorrt_llm::runtime::LoraCacheFullException::LoraCacheFullException::msg"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullExceptionD0Ev", "tensorrt_llm::runtime::LoraCacheFullException::~LoraCacheFullException"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManagerE", "tensorrt_llm::runtime::LoraCachePageManager"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager20LoraCachePageManagerERK26LoraCachePageManagerConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCachePageManager::LoraCachePageManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager20LoraCachePageManagerERK26LoraCachePageManagerConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCachePageManager::LoraCachePageManager::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager20LoraCachePageManagerERK26LoraCachePageManagerConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCachePageManager::LoraCachePageManager::config"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager9TensorPtrE", "tensorrt_llm::runtime::LoraCachePageManager::TensorPtr"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager8blockPtrE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManager::blockPtr"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager8blockPtrE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManager::blockPtr::blockIdx"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10claimPagesE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManager::claimPages"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10claimPagesE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManager::claimPages::numPages"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10initializeERK13BufferManager", "tensorrt_llm::runtime::LoraCachePageManager::initialize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10initializeERK13BufferManager", "tensorrt_llm::runtime::LoraCachePageManager::initialize::bufferManager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager7mConfigE", "tensorrt_llm::runtime::LoraCachePageManager::mConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager12mFreePageIdsE", "tensorrt_llm::runtime::LoraCachePageManager::mFreePageIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager11mIsPageFreeE", "tensorrt_llm::runtime::LoraCachePageManager::mIsPageFree"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager11mPageBlocksE", "tensorrt_llm::runtime::LoraCachePageManager::mPageBlocks"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager14mutablePagePtrENSt6size_tE", "tensorrt_llm::runtime::LoraCachePageManager::mutablePagePtr"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager14mutablePagePtrENSt6size_tE", "tensorrt_llm::runtime::LoraCachePageManager::mutablePagePtr::pageIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager17numAvailablePagesEv", "tensorrt_llm::runtime::LoraCachePageManager::numAvailablePages"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager7pagePtrENSt6size_tE", "tensorrt_llm::runtime::LoraCachePageManager::pagePtr"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager7pagePtrENSt6size_tE", "tensorrt_llm::runtime::LoraCachePageManager::pagePtr::pageIdx"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager12releasePagesERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCachePageManager::releasePages"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager12releasePagesERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCachePageManager::releasePages::pages"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfigE", "tensorrt_llm::runtime::LoraCachePageManagerConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::dType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::maxPagesPerBlock"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::memType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::numCopyStreams"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::pageWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::slotsPerPage"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::totalNumPages"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig11getDataTypeEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getDataType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig13getInitToZeroEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getInitToZero"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig19getMaxPagesPerBlockEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getMaxPagesPerBlock"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig13getMemoryTypeEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getMemoryType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig17getNumCopyStreamsEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getNumCopyStreams"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig12getPageWidthEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getPageWidth"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig15getSlotsPerPageEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getSlotsPerPage"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig16getTotalNumPagesEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getTotalNumPages"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig9mDataTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mDataType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11mInitToZeroE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mInitToZero"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig17mMaxPagesPerBlockE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mMaxPagesPerBlock"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11mMemoryTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mMemoryType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15mNumCopyStreamsE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mNumCopyStreams"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig10mPageWidthE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mPageWidth"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13mSlotsPerPageE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mSlotsPerPage"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig14mTotalNumPagesE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mTotalNumPages"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11setDataTypeERKN8nvinfer18DataTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setDataType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11setDataTypeERKN8nvinfer18DataTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setDataType::dtype"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setInitToZeroEb", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setInitToZero"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setInitToZeroEb", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setInitToZero::initToZero"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig19setMaxPagesPerBlockERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setMaxPagesPerBlock"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig19setMaxPagesPerBlockERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setMaxPagesPerBlock::maxPagesPerBlock"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setMemoryTypeERKN7runtime10MemoryTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setMemoryType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setMemoryTypeERKN7runtime10MemoryTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setMemoryType::memoryType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig17setNumCopyStreamsE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setNumCopyStreams"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig17setNumCopyStreamsE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setNumCopyStreams::numCopyStreams"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig12setPageWidthERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setPageWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig12setPageWidthERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setPageWidth::pageWidth"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setSlotsPerPageERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setSlotsPerPage"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setSlotsPerPageERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setSlotsPerPage::slotsPerPage"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setTotalNumPageERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setTotalNumPage"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setTotalNumPageERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setTotalNumPage::totalNumPages"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedExceptionE", "tensorrt_llm::runtime::LoraExpectedException"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedException21LoraExpectedExceptionERKNSt6stringE", "tensorrt_llm::runtime::LoraExpectedException::LoraExpectedException"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedException21LoraExpectedExceptionERKNSt6stringE", "tensorrt_llm::runtime::LoraExpectedException::LoraExpectedException::msg"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedExceptionD0Ev", "tensorrt_llm::runtime::LoraExpectedException::~LoraExpectedException"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModuleE", "tensorrt_llm::runtime::LoraModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10LoraModule", "tensorrt_llm::runtime::LoraModule::LoraModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleEv", "tensorrt_llm::runtime::LoraModule::LoraModule"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::inDim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::inDimFirst"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::inTpSplitDim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10LoraModule", "tensorrt_llm::runtime::LoraModule::LoraModule::o"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::outDim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::outDimFirst"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::outTpSplitDim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::t"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleTypeE", "tensorrt_llm::runtime::LoraModule::ModuleType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kATTN_DENSEE", "tensorrt_llm::runtime::LoraModule::ModuleType::kATTN_DENSE"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_KE", "tensorrt_llm::runtime::LoraModule::ModuleType::kATTN_K"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_QE", "tensorrt_llm::runtime::LoraModule::ModuleType::kATTN_Q"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kATTN_QKVE", "tensorrt_llm::runtime::LoraModule::ModuleType::kATTN_QKV"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_VE", "tensorrt_llm::runtime::LoraModule::ModuleType::kATTN_V"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType17kCROSS_ATTN_DENSEE", "tensorrt_llm::runtime::LoraModule::ModuleType::kCROSS_ATTN_DENSE"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_KE", "tensorrt_llm::runtime::LoraModule::ModuleType::kCROSS_ATTN_K"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_QE", "tensorrt_llm::runtime::LoraModule::ModuleType::kCROSS_ATTN_Q"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType15kCROSS_ATTN_QKVE", "tensorrt_llm::runtime::LoraModule::ModuleType::kCROSS_ATTN_QKV"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_VE", "tensorrt_llm::runtime::LoraModule::ModuleType::kCROSS_ATTN_V"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType8kINVALIDE", "tensorrt_llm::runtime::LoraModule::ModuleType::kINVALID"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMLP_4H_TO_HE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMLP_4H_TO_H"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kMLP_GATEE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMLP_GATE"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMLP_GATE_UPE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMLP_GATE_UP"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMLP_H_TO_4HE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMLP_H_TO_4H"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kMLP_ROUTERE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMLP_ROUTER"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMOE_4H_TO_HE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMOE_4H_TO_H"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kMOE_GATEE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMOE_GATE"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMOE_H_TO_4HE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMOE_H_TO_4H"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kMOE_ROUTERE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMOE_ROUTER"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule9TensorPtrE", "tensorrt_llm::runtime::LoraModule::TensorPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::attentionHeadSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::hiddenSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::loraModuleNames"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::mlpHiddenSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::numAttentionHeads"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::numExperts"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::numKvAttentionHeads"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18flattenedInOutSizeE10SizeType32b", "tensorrt_llm::runtime::LoraModule::flattenedInOutSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18flattenedInOutSizeE10SizeType32b", "tensorrt_llm::runtime::LoraModule::flattenedInOutSize::adapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18flattenedInOutSizeE10SizeType32b", "tensorrt_llm::runtime::LoraModule::flattenedInOutSize::isDora"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule5inDimEv", "tensorrt_llm::runtime::LoraModule::inDim"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule10inDimFirstEv", "tensorrt_llm::runtime::LoraModule::inDimFirst"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule6inSizeE10SizeType32", "tensorrt_llm::runtime::LoraModule::inSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule6inSizeE10SizeType32", "tensorrt_llm::runtime::LoraModule::inSize::adapterSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12inTpSplitDimEv", "tensorrt_llm::runtime::LoraModule::inTpSplitDim"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18localInAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInAdapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18localInAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInAdapterSize::adapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18localInAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInAdapterSize::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule10localInDimE10SizeType32", "tensorrt_llm::runtime::LoraModule::localInDim"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule10localInDimE10SizeType32", "tensorrt_llm::runtime::LoraModule::localInDim::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localInOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInOutSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localInOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInOutSize::adapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localInOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInOutSize::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localInSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localInSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInSize::adapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localInSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInSize::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule19localOutAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutAdapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule19localOutAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutAdapterSize::adapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule19localOutAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutAdapterSize::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localOutDimE10SizeType32", "tensorrt_llm::runtime::LoraModule::localOutDim"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localOutDimE10SizeType32", "tensorrt_llm::runtime::LoraModule::localOutDim::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12localOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12localOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutSize::adapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12localOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutSize::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule15localScalesSizeE10SizeType32b", "tensorrt_llm::runtime::LoraModule::localScalesSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule15localScalesSizeE10SizeType32b", "tensorrt_llm::runtime::LoraModule::localScalesSize::isDora"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule15localScalesSizeE10SizeType32b", "tensorrt_llm::runtime::LoraModule::localScalesSize::tpSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localTotalSizeE10SizeType3210SizeType32b", "tensorrt_llm::runtime::LoraModule::localTotalSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localTotalSizeE10SizeType3210SizeType32b", "tensorrt_llm::runtime::LoraModule::localTotalSize::adapterSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localTotalSizeE10SizeType3210SizeType32b", "tensorrt_llm::runtime::LoraModule::localTotalSize::isDora"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localTotalSizeE10SizeType3210SizeType32b", "tensorrt_llm::runtime::LoraModule::localTotalSize::tpSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule6mInDimE", "tensorrt_llm::runtime::LoraModule::mInDim"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule11mInDimFirstE", "tensorrt_llm::runtime::LoraModule::mInDimFirst"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule13mInTpSplitDimE", "tensorrt_llm::runtime::LoraModule::mInTpSplitDim"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule7mOutDimE", "tensorrt_llm::runtime::LoraModule::mOutDim"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12mOutDimFirstE", "tensorrt_llm::runtime::LoraModule::mOutDimFirst"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule14mOutTpSplitDimE", "tensorrt_llm::runtime::LoraModule::mOutTpSplitDim"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule5mTypeE", "tensorrt_llm::runtime::LoraModule::mType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule4nameEv", "tensorrt_llm::runtime::LoraModule::name"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModuleaSERK10LoraModule", "tensorrt_llm::runtime::LoraModule::operator="], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModuleaSERK10LoraModule", "tensorrt_llm::runtime::LoraModule::operator=::o"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule6outDimEv", "tensorrt_llm::runtime::LoraModule::outDim"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11outDimFirstEv", "tensorrt_llm::runtime::LoraModule::outDimFirst"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule7outSizeE10SizeType32", "tensorrt_llm::runtime::LoraModule::outSize"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule7outSizeE10SizeType32", "tensorrt_llm::runtime::LoraModule::outSize::adapterSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule13outTpSplitDimEv", "tensorrt_llm::runtime::LoraModule::outTpSplitDim"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10ModuleType", "tensorrt_llm::runtime::LoraModule::toModuleName"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10SizeType32", "tensorrt_llm::runtime::LoraModule::toModuleName"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10SizeType32", "tensorrt_llm::runtime::LoraModule::toModuleName::id"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10ModuleType", "tensorrt_llm::runtime::LoraModule::toModuleName::t"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleTypeERKNSt11string_viewE", "tensorrt_llm::runtime::LoraModule::toModuleType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleTypeERKNSt11string_viewE", "tensorrt_llm::runtime::LoraModule::toModuleType::name"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule5valueEv", "tensorrt_llm::runtime::LoraModule::value"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14LoraTaskIdTypeE", "tensorrt_llm::runtime::LoraTaskIdType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime17MPI_group_barrierENSt3setIiEE", "tensorrt_llm::runtime::MPI_group_barrier"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17MPI_group_barrierENSt3setIiEE", "tensorrt_llm::runtime::MPI_group_barrier::ranks"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModuleE", "tensorrt_llm::runtime::MedusaModule"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule13MedusaChoicesE", "tensorrt_llm::runtime::MedusaModule::MedusaChoices"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::MedusaModule::MedusaModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleEv", "tensorrt_llm::runtime::MedusaModule::MedusaModule"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::MedusaModule::MedusaModule::maxAcceptedTokens"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::MedusaModule::MedusaModule::maxDraftTokens"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule9TensorPtrE", "tensorrt_llm::runtime::MedusaModule::TensorPtr"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule16getMedusaChoicesEv", "tensorrt_llm::runtime::MedusaModule::getMedusaChoices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule21mDefaultMedusaChoicesE", "tensorrt_llm::runtime::MedusaModule::mDefaultMedusaChoices"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCountersE", "tensorrt_llm::runtime::MemoryCounters"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE", "tensorrt_llm::runtime::MemoryCounters::DiffType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters14MemoryCountersEv", "tensorrt_llm::runtime::MemoryCounters::MemoryCounters"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10SizeType32E", "tensorrt_llm::runtime::MemoryCounters::SizeType32"], [1, 3, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters8allocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8allocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate"], [1, 8, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters8allocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate::T"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8allocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate::memoryType"], [1, 4, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters8allocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8allocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate::size"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE10SizeType32i", "tensorrt_llm::runtime::MemoryCounters::bytesToString"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8DiffTypei", "tensorrt_llm::runtime::MemoryCounters::bytesToString"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE10SizeType32i", "tensorrt_llm::runtime::MemoryCounters::bytesToString::bytes"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8DiffTypei", "tensorrt_llm::runtime::MemoryCounters::bytesToString::bytes"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE10SizeType32i", "tensorrt_llm::runtime::MemoryCounters::bytesToString::precision"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8DiffTypei", "tensorrt_llm::runtime::MemoryCounters::bytesToString::precision"], [1, 3, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters10deallocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10deallocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate"], [1, 8, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters10deallocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate::T"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10deallocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate::memoryType"], [1, 4, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters10deallocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate::size"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10deallocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate::size"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getCpuEv", "tensorrt_llm::runtime::MemoryCounters::getCpu"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getCpuDiffEv", "tensorrt_llm::runtime::MemoryCounters::getCpuDiff"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getGpuEv", "tensorrt_llm::runtime::MemoryCounters::getGpu"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getGpuDiffEv", "tensorrt_llm::runtime::MemoryCounters::getGpuDiff"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11getInstanceEv", "tensorrt_llm::runtime::MemoryCounters::getInstance"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters9getPinnedEv", "tensorrt_llm::runtime::MemoryCounters::getPinned"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters13getPinnedDiffEv", "tensorrt_llm::runtime::MemoryCounters::getPinnedDiff"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters13getPinnedPoolEv", "tensorrt_llm::runtime::MemoryCounters::getPinnedPool"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters17getPinnedPoolDiffEv", "tensorrt_llm::runtime::MemoryCounters::getPinnedPoolDiff"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getUVMEv", "tensorrt_llm::runtime::MemoryCounters::getUVM"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getUVMDiffEv", "tensorrt_llm::runtime::MemoryCounters::getUVMDiff"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mCpuE", "tensorrt_llm::runtime::MemoryCounters::mCpu"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mCpuDiffE", "tensorrt_llm::runtime::MemoryCounters::mCpuDiff"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mGpuE", "tensorrt_llm::runtime::MemoryCounters::mGpu"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mGpuDiffE", "tensorrt_llm::runtime::MemoryCounters::mGpuDiff"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters7mPinnedE", "tensorrt_llm::runtime::MemoryCounters::mPinned"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11mPinnedDiffE", "tensorrt_llm::runtime::MemoryCounters::mPinnedDiff"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11mPinnedPoolE", "tensorrt_llm::runtime::MemoryCounters::mPinnedPool"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters15mPinnedPoolDiffE", "tensorrt_llm::runtime::MemoryCounters::mPinnedPoolDiff"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mUVME", "tensorrt_llm::runtime::MemoryCounters::mUVM"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mUVMDiffE", "tensorrt_llm::runtime::MemoryCounters::mUVMDiff"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters8toStringEv", "tensorrt_llm::runtime::MemoryCounters::toString"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryTypeE", "tensorrt_llm::runtime::MemoryType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kCPUE", "tensorrt_llm::runtime::MemoryType::kCPU"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kGPUE", "tensorrt_llm::runtime::MemoryType::kGPU"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryType7kPINNEDE", "tensorrt_llm::runtime::MemoryType::kPINNED"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryType11kPINNEDPOOLE", "tensorrt_llm::runtime::MemoryType::kPINNEDPOOL"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kUVME", "tensorrt_llm::runtime::MemoryType::kUVM"], [1, 2, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime16MemoryTypeStringE", "tensorrt_llm::runtime::MemoryTypeString"], [1, 8, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime16MemoryTypeStringE", "tensorrt_llm::runtime::MemoryTypeString::T"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEEE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kCPU>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEE5valueE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kCPU>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEEE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kGPU>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEE5valueE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kGPU>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEEE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kPINNED>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEE5valueE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kPINNED>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType11kPINNEDPOOLEEE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kPINNEDPOOL>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType11kPINNEDPOOLEE5valueE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kPINNEDPOOL>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kUVMEEE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kUVM>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kUVMEE5valueE", "tensorrt_llm::runtime::MemoryTypeString<MemoryType::kUVM>::value"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfigE", "tensorrt_llm::runtime::ModelConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheTypeE", "tensorrt_llm::runtime::ModelConfig::KVCacheType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType11kCONTINUOUSE", "tensorrt_llm::runtime::ModelConfig::KVCacheType::kCONTINUOUS"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType9kDISABLEDE", "tensorrt_llm::runtime::ModelConfig::KVCacheType::kDISABLED"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType6kPAGEDE", "tensorrt_llm::runtime::ModelConfig::KVCacheType::kPAGED"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21KVCacheTypeFromStringENSt6stringE", "tensorrt_llm::runtime::ModelConfig::KVCacheTypeFromString"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21KVCacheTypeFromStringENSt6stringE", "tensorrt_llm::runtime::ModelConfig::KVCacheTypeFromString::value"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerTypeE", "tensorrt_llm::runtime::ModelConfig::LayerType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType10kATTENTIONE", "tensorrt_llm::runtime::ModelConfig::LayerType::kATTENTION"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType7kLINEARE", "tensorrt_llm::runtime::ModelConfig::LayerType::kLINEAR"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType5kNOOPE", "tensorrt_llm::runtime::ModelConfig::LayerType::kNOOP"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType10kRECURRENTE", "tensorrt_llm::runtime::ModelConfig::LayerType::kRECURRENT"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsTypeE", "tensorrt_llm::runtime::ModelConfig::ManageWeightsType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsType9kDisabledE", "tensorrt_llm::runtime::ModelConfig::ManageWeightsType::kDisabled"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsType8kEnabledE", "tensorrt_llm::runtime::ModelConfig::ManageWeightsType::kEnabled"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::dtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::hiddenSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::nbAttentionLayers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::nbHeads"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::nbLayers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::nbRnnLayers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::vocabSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariantE", "tensorrt_llm::runtime::ModelConfig::ModelVariant"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant8kChatGlmE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kChatGlm"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant7kEncDecE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kEncDec"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant4kGlmE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kGlm"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant4kGptE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kGpt"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant6kMambaE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kMamba"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant15kRecurrentGemmaE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kRecurrentGemma"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfigE", "tensorrt_llm::runtime::ModelConfig::RnnConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig10convKernelE", "tensorrt_llm::runtime::ModelConfig::RnnConfig::convKernel"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig14rnnConvDimSizeE", "tensorrt_llm::runtime::ModelConfig::RnnConfig::rnnConvDimSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig11rnnHeadSizeE", "tensorrt_llm::runtime::ModelConfig::RnnConfig::rnnHeadSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig13rnnHiddenSizeE", "tensorrt_llm::runtime::ModelConfig::RnnConfig::rnnHiddenSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig9stateSizeE", "tensorrt_llm::runtime::ModelConfig::RnnConfig::stateSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20computeContextLogitsEb", "tensorrt_llm::runtime::ModelConfig::computeContextLogits"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20computeContextLogitsEv", "tensorrt_llm::runtime::ModelConfig::computeContextLogits"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20computeContextLogitsEb", "tensorrt_llm::runtime::ModelConfig::computeContextLogits::computeContextLogits"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23computeGenerationLogitsEb", "tensorrt_llm::runtime::ModelConfig::computeGenerationLogits"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig23computeGenerationLogitsEv", "tensorrt_llm::runtime::ModelConfig::computeGenerationLogits"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23computeGenerationLogitsEb", "tensorrt_llm::runtime::ModelConfig::computeGenerationLogits::computeGenerationLogits"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16countLocalLayersE9LayerType10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::countLocalLayers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16countLocalLayersE9LayerType10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::countLocalLayers::layerType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16countLocalLayersE9LayerType10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::countLocalLayers::pipelineParallelism"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16countLocalLayersE9LayerType10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::countLocalLayers::pipelineParallelismRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20countLowerRankLayersE9LayerType10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::countLowerRankLayers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20countLowerRankLayersE9LayerType10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::countLowerRankLayers::layerType"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20countLowerRankLayersE9LayerType10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::countLowerRankLayers::pipelineParallelism"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20countLowerRankLayersE9LayerType10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::countLowerRankLayers::pipelineParallelismRank"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig32disableSeamlessLookaheadDecodingEv", "tensorrt_llm::runtime::ModelConfig::disableSeamlessLookaheadDecoding"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig31enableSeamlessLookaheadDecodingE10SizeType32", "tensorrt_llm::runtime::ModelConfig::enableSeamlessLookaheadDecoding"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig31enableSeamlessLookaheadDecodingE10SizeType32", "tensorrt_llm::runtime::ModelConfig::enableSeamlessLookaheadDecoding::maxDraftTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getContextFMHAEv", "tensorrt_llm::runtime::ModelConfig::getContextFMHA"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig11getDataTypeEv", "tensorrt_llm::runtime::ModelConfig::getDataType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getEncoderHiddenSizeEv", "tensorrt_llm::runtime::ModelConfig::getEncoderHiddenSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getFirstLocalLayerE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getFirstLocalLayer"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getFirstLocalLayerE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getFirstLocalLayer::pipelineParallelism"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getFirstLocalLayerE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getFirstLocalLayer::pipelineParallelismRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21getGemmAllReduceDtypeEv", "tensorrt_llm::runtime::ModelConfig::getGemmAllReduceDtype"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getHiddenSizeEv", "tensorrt_llm::runtime::ModelConfig::getHiddenSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getKVCacheTypeEv", "tensorrt_llm::runtime::ModelConfig::getKVCacheType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getKvDataTypeEv", "tensorrt_llm::runtime::ModelConfig::getKvDataType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getLayerTypesEv", "tensorrt_llm::runtime::ModelConfig::getLayerTypes"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getLogitsDtypeEv", "tensorrt_llm::runtime::ModelConfig::getLogitsDtype"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getLoraModulesEv", "tensorrt_llm::runtime::ModelConfig::getLoraModules"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getManageWeightsTypeEv", "tensorrt_llm::runtime::ModelConfig::getManageWeightsType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxBatchSizeEv", "tensorrt_llm::runtime::ModelConfig::getMaxBatchSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxBeamWidthEv", "tensorrt_llm::runtime::ModelConfig::getMaxBeamWidth"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig25getMaxDecodingDraftTokensEv", "tensorrt_llm::runtime::ModelConfig::getMaxDecodingDraftTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getMaxDecodingTokensEv", "tensorrt_llm::runtime::ModelConfig::getMaxDecodingTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16getMaxEncoderLenEv", "tensorrt_llm::runtime::ModelConfig::getMaxEncoderLen"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getMaxInputLenEv", "tensorrt_llm::runtime::ModelConfig::getMaxInputLen"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getMaxLoraRankEv", "tensorrt_llm::runtime::ModelConfig::getMaxLoraRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxNumTokensEv", "tensorrt_llm::runtime::ModelConfig::getMaxNumTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig24getMaxPositionEmbeddingsEv", "tensorrt_llm::runtime::ModelConfig::getMaxPositionEmbeddings"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig30getMaxPromptEmbeddingTableSizeEv", "tensorrt_llm::runtime::ModelConfig::getMaxPromptEmbeddingTableSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17getMaxSequenceLenEv", "tensorrt_llm::runtime::ModelConfig::getMaxSequenceLen"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16getMlpHiddenSizeEv", "tensorrt_llm::runtime::ModelConfig::getMlpHiddenSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getModelNameEv", "tensorrt_llm::runtime::ModelConfig::getModelName"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getModelVariantEv", "tensorrt_llm::runtime::ModelConfig::getModelVariant"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getNbAttentionLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbAttentionLayers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getNbAttentionLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbAttentionLayers::pipelineParallelism"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getNbAttentionLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbAttentionLayers::pipelineParallelismRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig10getNbHeadsEv", "tensorrt_llm::runtime::ModelConfig::getNbHeads"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getNbKvHeadsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbKvHeads"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getNbKvHeadsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbKvHeads::layerIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig11getNbLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbLayers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig11getNbLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbLayers::pipelineParallelism"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig11getNbLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbLayers::pipelineParallelismRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getNbRnnLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbRnnLayers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getNbRnnLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbRnnLayers::pipelineParallelism"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getNbRnnLayersE10SizeType3210SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbRnnLayers::pipelineParallelismRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig27getNumKvHeadsForGivenLayersERKNSt6vectorI10SizeType32EEb", "tensorrt_llm::runtime::ModelConfig::getNumKvHeadsForGivenLayers"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig27getNumKvHeadsForGivenLayersERKNSt6vectorI10SizeType32EEb", "tensorrt_llm::runtime::ModelConfig::getNumKvHeadsForGivenLayers::isCrossAttention"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig27getNumKvHeadsForGivenLayersERKNSt6vectorI10SizeType32EEb", "tensorrt_llm::runtime::ModelConfig::getNumKvHeadsForGivenLayers::layers"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21getNumKvHeadsPerLayerEv", "tensorrt_llm::runtime::ModelConfig::getNumKvHeadsPerLayer"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig31getNumKvHeadsPerLayerLocalRangeE10SizeType3210SizeType32b", "tensorrt_llm::runtime::ModelConfig::getNumKvHeadsPerLayerLocalRange"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig31getNumKvHeadsPerLayerLocalRangeE10SizeType3210SizeType32b", "tensorrt_llm::runtime::ModelConfig::getNumKvHeadsPerLayerLocalRange::isCrossAttention"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig31getNumKvHeadsPerLayerLocalRangeE10SizeType3210SizeType32b", "tensorrt_llm::runtime::ModelConfig::getNumKvHeadsPerLayerLocalRange::pipelineParallelism"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig31getNumKvHeadsPerLayerLocalRangeE10SizeType3210SizeType32b", "tensorrt_llm::runtime::ModelConfig::getNumKvHeadsPerLayerLocalRange::pipelineParallelismRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getNumLanguagesEv", "tensorrt_llm::runtime::ModelConfig::getNumLanguages"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig25getOptProfilesSplitPointsEv", "tensorrt_llm::runtime::ModelConfig::getOptProfilesSplitPoints"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig19getPagedContextFMHAEv", "tensorrt_llm::runtime::ModelConfig::getPagedContextFMHA"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getPpReduceScatterEv", "tensorrt_llm::runtime::ModelConfig::getPpReduceScatter"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getQuantModeEv", "tensorrt_llm::runtime::ModelConfig::getQuantMode"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getRnnConfigEv", "tensorrt_llm::runtime::ModelConfig::getRnnConfig"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21getRotaryEmbeddingDimEv", "tensorrt_llm::runtime::ModelConfig::getRotaryEmbeddingDim"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getSizePerHeadEv", "tensorrt_llm::runtime::ModelConfig::getSizePerHead"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig26getSpeculativeDecodingModeEv", "tensorrt_llm::runtime::ModelConfig::getSpeculativeDecodingMode"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig28getSpeculativeDecodingModuleEv", "tensorrt_llm::runtime::ModelConfig::getSpeculativeDecodingModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig31getSpeculativeDecodingModulePtrEv", "tensorrt_llm::runtime::ModelConfig::getSpeculativeDecodingModulePtr"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig31getSpeculativeDecodingModulePtrEv", "tensorrt_llm::runtime::ModelConfig::getSpeculativeDecodingModulePtr"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17getTokensPerBlockEv", "tensorrt_llm::runtime::ModelConfig::getTokensPerBlock"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getVocabSizeEv", "tensorrt_llm::runtime::ModelConfig::getVocabSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getVocabSizePaddedE10SizeType32", "tensorrt_llm::runtime::ModelConfig::getVocabSizePadded"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getVocabSizePaddedE10SizeType32", "tensorrt_llm::runtime::ModelConfig::getVocabSizePadded::worldSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12hasRnnConfigEv", "tensorrt_llm::runtime::ModelConfig::hasRnnConfig"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig28hasSpeculativeDecodingModuleEv", "tensorrt_llm::runtime::ModelConfig::hasSpeculativeDecodingModule"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig19isContinuousKVCacheEv", "tensorrt_llm::runtime::ModelConfig::isContinuousKVCache"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16isKVCacheEnabledEv", "tensorrt_llm::runtime::ModelConfig::isKVCacheEnabled"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12isMultiModalEv", "tensorrt_llm::runtime::ModelConfig::isMultiModal"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14isPagedKVCacheEv", "tensorrt_llm::runtime::ModelConfig::isPagedKVCache"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig10isRnnBasedEv", "tensorrt_llm::runtime::ModelConfig::isRnnBased"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18isTransformerBasedEv", "tensorrt_llm::runtime::ModelConfig::isTransformerBased"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig9isWhisperEv", "tensorrt_llm::runtime::ModelConfig::isWhisper"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig29kDEFAULT_NUM_TOKENS_PER_BLOCKE", "tensorrt_llm::runtime::ModelConfig::kDEFAULT_NUM_TOKENS_PER_BLOCK"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26kOPT_PROFILES_SPLIT_POINTSE", "tensorrt_llm::runtime::ModelConfig::kOPT_PROFILES_SPLIT_POINTS"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mComputeContextLogitsE", "tensorrt_llm::runtime::ModelConfig::mComputeContextLogits"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24mComputeGenerationLogitsE", "tensorrt_llm::runtime::ModelConfig::mComputeGenerationLogits"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mContextFMHAE", "tensorrt_llm::runtime::ModelConfig::mContextFMHA"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9mDataTypeE", "tensorrt_llm::runtime::ModelConfig::mDataType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mEncoderHiddenSizeE", "tensorrt_llm::runtime::ModelConfig::mEncoderHiddenSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig19mGemmAllReduceDtypeE", "tensorrt_llm::runtime::ModelConfig::mGemmAllReduceDtype"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mHiddenSizeE", "tensorrt_llm::runtime::ModelConfig::mHiddenSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mInputPackedE", "tensorrt_llm::runtime::ModelConfig::mInputPacked"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mKVCacheTypeE", "tensorrt_llm::runtime::ModelConfig::mKVCacheType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mLayerTypesE", "tensorrt_llm::runtime::ModelConfig::mLayerTypes"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mLogitsDtypeE", "tensorrt_llm::runtime::ModelConfig::mLogitsDtype"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mLoraModulesE", "tensorrt_llm::runtime::ModelConfig::mLoraModules"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mManageWeightsTypeE", "tensorrt_llm::runtime::ModelConfig::mManageWeightsType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxBatchSizeE", "tensorrt_llm::runtime::ModelConfig::mMaxBatchSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxBeamWidthE", "tensorrt_llm::runtime::ModelConfig::mMaxBeamWidth"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mMaxEncoderLenE", "tensorrt_llm::runtime::ModelConfig::mMaxEncoderLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mMaxInputLenE", "tensorrt_llm::runtime::ModelConfig::mMaxInputLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mMaxLoraRankE", "tensorrt_llm::runtime::ModelConfig::mMaxLoraRank"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxNumTokensE", "tensorrt_llm::runtime::ModelConfig::mMaxNumTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22mMaxPositionEmbeddingsE", "tensorrt_llm::runtime::ModelConfig::mMaxPositionEmbeddings"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28mMaxPromptEmbeddingTableSizeE", "tensorrt_llm::runtime::ModelConfig::mMaxPromptEmbeddingTableSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15mMaxSequenceLenE", "tensorrt_llm::runtime::ModelConfig::mMaxSequenceLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mMlpHiddenSizeE", "tensorrt_llm::runtime::ModelConfig::mMlpHiddenSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mModelNameE", "tensorrt_llm::runtime::ModelConfig::mModelName"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mModelVariantE", "tensorrt_llm::runtime::ModelConfig::mModelVariant"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mNbAttentionLayersE", "tensorrt_llm::runtime::ModelConfig::mNbAttentionLayers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig8mNbHeadsE", "tensorrt_llm::runtime::ModelConfig::mNbHeads"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9mNbLayersE", "tensorrt_llm::runtime::ModelConfig::mNbLayers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mNbRnnLayersE", "tensorrt_llm::runtime::ModelConfig::mNbRnnLayers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28mNumKvHeadsPerAttentionLayerE", "tensorrt_llm::runtime::ModelConfig::mNumKvHeadsPerAttentionLayer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig33mNumKvHeadsPerCrossAttentionLayerE", "tensorrt_llm::runtime::ModelConfig::mNumKvHeadsPerCrossAttentionLayer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mNumLanguagesE", "tensorrt_llm::runtime::ModelConfig::mNumLanguages"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17mPagedContextFMHAE", "tensorrt_llm::runtime::ModelConfig::mPagedContextFMHA"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mPagedStateE", "tensorrt_llm::runtime::ModelConfig::mPagedState"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16mPpReduceScatterE", "tensorrt_llm::runtime::ModelConfig::mPpReduceScatter"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mQuantModeE", "tensorrt_llm::runtime::ModelConfig::mQuantMode"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mRnnConfigE", "tensorrt_llm::runtime::ModelConfig::mRnnConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig19mRotaryEmbeddingDimE", "tensorrt_llm::runtime::ModelConfig::mRotaryEmbeddingDim"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mSizePerHeadE", "tensorrt_llm::runtime::ModelConfig::mSizePerHead"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20mSkipCrossAttnBlocksE", "tensorrt_llm::runtime::ModelConfig::mSkipCrossAttnBlocks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24mSpeculativeDecodingModeE", "tensorrt_llm::runtime::ModelConfig::mSpeculativeDecodingMode"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26mSpeculativeDecodingModuleE", "tensorrt_llm::runtime::ModelConfig::mSpeculativeDecodingModule"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15mTokensPerBlockE", "tensorrt_llm::runtime::ModelConfig::mTokensPerBlock"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mUseCrossAttentionE", "tensorrt_llm::runtime::ModelConfig::mUseCrossAttention"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23mUseGemmAllReducePluginE", "tensorrt_llm::runtime::ModelConfig::mUseGemmAllReducePlugin"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22mUseGptAttentionPluginE", "tensorrt_llm::runtime::ModelConfig::mUseGptAttentionPlugin"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mUseLoraPluginE", "tensorrt_llm::runtime::ModelConfig::mUseLoraPlugin"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mUseMambaConv1dPluginE", "tensorrt_llm::runtime::ModelConfig::mUseMambaConv1dPlugin"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9mUseMropeE", "tensorrt_llm::runtime::ModelConfig::mUseMrope"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mUsePositionEmbeddingE", "tensorrt_llm::runtime::ModelConfig::mUsePositionEmbedding"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mUseShapeInferenceE", "tensorrt_llm::runtime::ModelConfig::mUseShapeInference"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22mUseTokenTypeEmbeddingE", "tensorrt_llm::runtime::ModelConfig::mUseTokenTypeEmbedding"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mVocabSizeE", "tensorrt_llm::runtime::ModelConfig::mVocabSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig30resetSpeculativeDecodingModuleEv", "tensorrt_llm::runtime::ModelConfig::resetSpeculativeDecodingModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setContextFMHAEb", "tensorrt_llm::runtime::ModelConfig::setContextFMHA"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setContextFMHAEb", "tensorrt_llm::runtime::ModelConfig::setContextFMHA::contextFMHA"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setEncoderHiddenSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setEncoderHiddenSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setEncoderHiddenSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setEncoderHiddenSize::encoderHiddenSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setGemmAllReduceDtypeEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::setGemmAllReduceDtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setGemmAllReduceDtypeEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::setGemmAllReduceDtype::inputDtype"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setKVCacheTypeE11KVCacheType", "tensorrt_llm::runtime::ModelConfig::setKVCacheType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setKVCacheTypeE11KVCacheType", "tensorrt_llm::runtime::ModelConfig::setKVCacheType::kvCacheType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13setLayerTypesERKNSt6vectorI9LayerTypeEE", "tensorrt_llm::runtime::ModelConfig::setLayerTypes"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13setLayerTypesERKNSt6vectorI9LayerTypeEE", "tensorrt_llm::runtime::ModelConfig::setLayerTypes::layerTypes"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLogitsDtypeEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::setLogitsDtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLogitsDtypeEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::setLogitsDtype::inputDtype"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLoraModulesERKNSt6vectorI10LoraModuleEE", "tensorrt_llm::runtime::ModelConfig::setLoraModules"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLoraModulesERKNSt6vectorI10LoraModuleEE", "tensorrt_llm::runtime::ModelConfig::setLoraModules::loraModules"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setManageWeightsTypeEK17ManageWeightsType", "tensorrt_llm::runtime::ModelConfig::setManageWeightsType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setManageWeightsTypeEK17ManageWeightsType", "tensorrt_llm::runtime::ModelConfig::setManageWeightsType::manageWeightType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBatchSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBatchSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxBatchSize::maxBatchSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBeamWidthE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBeamWidthE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxBeamWidth::maxBeamWidth"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMaxEncoderLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxEncoderLen"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMaxEncoderLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxEncoderLen::maxEncoderLen"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxInputLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxInputLen"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxInputLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxInputLen::maxInputLen"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxLoraRankE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxLoraRank"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxLoraRankE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxLoraRank::maxLoraRank"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxNumTokensENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setMaxNumTokens"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxNumTokensENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setMaxNumTokens::maxNumTokens"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24setMaxPositionEmbeddingsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxPositionEmbeddings"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24setMaxPositionEmbeddingsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxPositionEmbeddings::maxPositionEmbeddings"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig30setMaxPromptEmbeddingTableSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxPromptEmbeddingTableSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig30setMaxPromptEmbeddingTableSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxPromptEmbeddingTableSize::maxPromptEmbeddingTableSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setMaxSequenceLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxSequenceLen"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setMaxSequenceLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxSequenceLen::maxSequenceLen"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMlpHiddenSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMlpHiddenSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMlpHiddenSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMlpHiddenSize::mlpHiddenSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setModelNameERKNSt6stringE", "tensorrt_llm::runtime::ModelConfig::setModelName"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setModelNameERKNSt6stringE", "tensorrt_llm::runtime::ModelConfig::setModelName::modelName"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setModelVariantE12ModelVariant", "tensorrt_llm::runtime::ModelConfig::setModelVariant"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setModelVariantE12ModelVariant", "tensorrt_llm::runtime::ModelConfig::setModelVariant::modelVariant"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setNbCrossKvHeadsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setNbCrossKvHeads"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setNbCrossKvHeadsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setNbCrossKvHeads::nbKvHeads"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setNbKvHeadsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setNbKvHeads"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setNbKvHeadsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setNbKvHeads::nbKvHeads"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26setNumKvHeadsPerCrossLayerERKNSt6vectorI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setNumKvHeadsPerCrossLayer"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26setNumKvHeadsPerCrossLayerERKNSt6vectorI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setNumKvHeadsPerCrossLayer::headsPerLayer"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setNumKvHeadsPerLayerERKNSt6vectorI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setNumKvHeadsPerLayer"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setNumKvHeadsPerLayerERKNSt6vectorI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setNumKvHeadsPerLayer::headsPerLayer"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setNumLanguagesENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setNumLanguages"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setNumLanguagesENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setNumLanguages::numLanguages"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig19setPagedContextFMHAEb", "tensorrt_llm::runtime::ModelConfig::setPagedContextFMHA"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig19setPagedContextFMHAEb", "tensorrt_llm::runtime::ModelConfig::setPagedContextFMHA::pagedContextFMHA"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18setPpReduceScatterEb", "tensorrt_llm::runtime::ModelConfig::setPpReduceScatter"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18setPpReduceScatterEb", "tensorrt_llm::runtime::ModelConfig::setPpReduceScatter::ppReduceScatter"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setQuantModeEN6common9QuantModeE", "tensorrt_llm::runtime::ModelConfig::setQuantMode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setQuantModeEN6common9QuantModeE", "tensorrt_llm::runtime::ModelConfig::setQuantMode::QuantMode"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setRnnConfigERK9RnnConfig", "tensorrt_llm::runtime::ModelConfig::setRnnConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setRnnConfigERK9RnnConfig", "tensorrt_llm::runtime::ModelConfig::setRnnConfig::rnnConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setRotaryEmbeddingDimE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setRotaryEmbeddingDim"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21setRotaryEmbeddingDimE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setRotaryEmbeddingDim::rotaryEmbeddingDim"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setSizePerHeadE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setSizePerHead"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setSizePerHeadE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setSizePerHead::sizePerHead"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22setSkipCrossAttnBlocksEb", "tensorrt_llm::runtime::ModelConfig::setSkipCrossAttnBlocks"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22setSkipCrossAttnBlocksEb", "tensorrt_llm::runtime::ModelConfig::setSkipCrossAttnBlocks::skipCrossAttnBlocks"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26setSpeculativeDecodingModeE23SpeculativeDecodingMode", "tensorrt_llm::runtime::ModelConfig::setSpeculativeDecodingMode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26setSpeculativeDecodingModeE23SpeculativeDecodingMode", "tensorrt_llm::runtime::ModelConfig::setSpeculativeDecodingMode::mode"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28setSpeculativeDecodingModuleERKNSt10shared_ptrI25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::ModelConfig::setSpeculativeDecodingModule"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28setSpeculativeDecodingModuleERKNSt10shared_ptrI25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::ModelConfig::setSpeculativeDecodingModule::speculativeDecodingModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setTokensPerBlockE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setTokensPerBlock"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setTokensPerBlockE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setTokensPerBlock::TokensPerBlock"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseCrossAttentionEb", "tensorrt_llm::runtime::ModelConfig::setUseCrossAttention"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseCrossAttentionEb", "tensorrt_llm::runtime::ModelConfig::setUseCrossAttention::useCrossAttention"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11setUseMropeEb", "tensorrt_llm::runtime::ModelConfig::setUseMrope"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11setUseMropeEb", "tensorrt_llm::runtime::ModelConfig::setUseMrope::useMrope"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23setUsePositionEmbeddingEb", "tensorrt_llm::runtime::ModelConfig::setUsePositionEmbedding"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23setUsePositionEmbeddingEb", "tensorrt_llm::runtime::ModelConfig::setUsePositionEmbedding::usePositionEmbedding"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseShapeInferenceEb", "tensorrt_llm::runtime::ModelConfig::setUseShapeInference"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseShapeInferenceEb", "tensorrt_llm::runtime::ModelConfig::setUseShapeInference::useShapeInference"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24setUseTokenTypeEmbeddingEb", "tensorrt_llm::runtime::ModelConfig::setUseTokenTypeEmbedding"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24setUseTokenTypeEmbeddingEb", "tensorrt_llm::runtime::ModelConfig::setUseTokenTypeEmbedding::useTokenTypeEmbedding"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig19skipCrossAttnBlocksEv", "tensorrt_llm::runtime::ModelConfig::skipCrossAttnBlocks"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig24supportsInflightBatchingEv", "tensorrt_llm::runtime::ModelConfig::supportsInflightBatching"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17useCrossAttentionEv", "tensorrt_llm::runtime::ModelConfig::useCrossAttention"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22useGemmAllReducePluginEb", "tensorrt_llm::runtime::ModelConfig::useGemmAllReducePlugin"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig22useGemmAllReducePluginEv", "tensorrt_llm::runtime::ModelConfig::useGemmAllReducePlugin"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22useGemmAllReducePluginEb", "tensorrt_llm::runtime::ModelConfig::useGemmAllReducePlugin::useGemmAllReducePlugin"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21useGptAttentionPluginEb", "tensorrt_llm::runtime::ModelConfig::useGptAttentionPlugin"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21useGptAttentionPluginEv", "tensorrt_llm::runtime::ModelConfig::useGptAttentionPlugin"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21useGptAttentionPluginEb", "tensorrt_llm::runtime::ModelConfig::useGptAttentionPlugin::useGptAttentionPlugin"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18useLanguageAdapterEv", "tensorrt_llm::runtime::ModelConfig::useLanguageAdapter"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13useLoraPluginEb", "tensorrt_llm::runtime::ModelConfig::useLoraPlugin"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13useLoraPluginEv", "tensorrt_llm::runtime::ModelConfig::useLoraPlugin"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13useLoraPluginEb", "tensorrt_llm::runtime::ModelConfig::useLoraPlugin::useLoraPlugin"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20useMambaConv1dPluginEb", "tensorrt_llm::runtime::ModelConfig::useMambaConv1dPlugin"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20useMambaConv1dPluginEv", "tensorrt_llm::runtime::ModelConfig::useMambaConv1dPlugin"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20useMambaConv1dPluginEb", "tensorrt_llm::runtime::ModelConfig::useMambaConv1dPlugin::useMambaConv1dPlugin"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig8useMropeEv", "tensorrt_llm::runtime::ModelConfig::useMrope"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14usePackedInputEb", "tensorrt_llm::runtime::ModelConfig::usePackedInput"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14usePackedInputEv", "tensorrt_llm::runtime::ModelConfig::usePackedInput"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14usePackedInputEb", "tensorrt_llm::runtime::ModelConfig::usePackedInput::inputPacked"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13usePagedStateEb", "tensorrt_llm::runtime::ModelConfig::usePagedState"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13usePagedStateEv", "tensorrt_llm::runtime::ModelConfig::usePagedState"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13usePagedStateEb", "tensorrt_llm::runtime::ModelConfig::usePagedState::pagedState"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20usePositionEmbeddingEv", "tensorrt_llm::runtime::ModelConfig::usePositionEmbedding"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15usePromptTuningEv", "tensorrt_llm::runtime::ModelConfig::usePromptTuning"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17useShapeInferenceEv", "tensorrt_llm::runtime::ModelConfig::useShapeInference"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21useTokenTypeEmbeddingEv", "tensorrt_llm::runtime::ModelConfig::useTokenTypeEmbedding"], [1, 1, 1, "_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE", "tensorrt_llm::runtime::PointerElementType"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE", "tensorrt_llm::runtime::PointerElementType::T"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParamsE", "tensorrt_llm::runtime::PromptTuningParams"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::PromptTuningParams::PromptTuningParams"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::PromptTuningParams::PromptTuningParams::embeddingTable"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::PromptTuningParams::PromptTuningParams::tasks"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::PromptTuningParams::PromptTuningParams::vocabSize"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams10SizeType32E", "tensorrt_llm::runtime::PromptTuningParams::SizeType32"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams9TensorPtrE", "tensorrt_llm::runtime::PromptTuningParams::TensorPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::batchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::manager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::numContextRequests"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::packedInput"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::reqBeamWidths"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::reqPromptLengths"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtr10SizeType3210SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::tasksHost"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngineE", "tensorrt_llm::runtime::RawEngine"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type15AddressWithSizeE", "tensorrt_llm::runtime::RawEngine::AddressWithSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type8FilePathE", "tensorrt_llm::runtime::RawEngine::FilePath"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type10HostMemoryE", "tensorrt_llm::runtime::RawEngine::HostMemory"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineENSt10filesystem4pathE", "tensorrt_llm::runtime::RawEngine::RawEngine"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKN8nvinfer111IHostMemoryE", "tensorrt_llm::runtime::RawEngine::RawEngine"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKvNSt6size_tE", "tensorrt_llm::runtime::RawEngine::RawEngine"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKvNSt6size_tE", "tensorrt_llm::runtime::RawEngine::RawEngine::engineAddr"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKN8nvinfer111IHostMemoryE", "tensorrt_llm::runtime::RawEngine::RawEngine::engineBuffer"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineENSt10filesystem4pathE", "tensorrt_llm::runtime::RawEngine::RawEngine::enginePath"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKvNSt6size_tE", "tensorrt_llm::runtime::RawEngine::RawEngine::engineSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4TypeE", "tensorrt_llm::runtime::RawEngine::Type"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type15AddressWithSizeE", "tensorrt_llm::runtime::RawEngine::Type::AddressWithSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type8FilePathE", "tensorrt_llm::runtime::RawEngine::Type::FilePath"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type10HostMemoryE", "tensorrt_llm::runtime::RawEngine::Type::HostMemory"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine10getAddressEv", "tensorrt_llm::runtime::RawEngine::getAddress"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine13getHostMemoryEv", "tensorrt_llm::runtime::RawEngine::getHostMemory"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine23getManagedWeightsMapOptEv", "tensorrt_llm::runtime::RawEngine::getManagedWeightsMapOpt"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getPathEv", "tensorrt_llm::runtime::RawEngine::getPath"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine10getPathOptEv", "tensorrt_llm::runtime::RawEngine::getPathOpt"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getSizeEv", "tensorrt_llm::runtime::RawEngine::getSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getTypeEv", "tensorrt_llm::runtime::RawEngine::getType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEngineAddrE", "tensorrt_llm::runtime::RawEngine::mEngineAddr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine13mEngineBufferE", "tensorrt_llm::runtime::RawEngine::mEngineBuffer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEnginePathE", "tensorrt_llm::runtime::RawEngine::mEnginePath"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEngineSizeE", "tensorrt_llm::runtime::RawEngine::mEngineSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine18mManagedWeightsMapE", "tensorrt_llm::runtime::RawEngine::mManagedWeightsMap"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine5mTypeE", "tensorrt_llm::runtime::RawEngine::mType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine20setManagedWeightsMapENSt3mapINSt6stringEN12tensorrt_llm8executor6TensorEEE", "tensorrt_llm::runtime::RawEngine::setManagedWeightsMap"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine20setManagedWeightsMapENSt3mapINSt6stringEN12tensorrt_llm8executor6TensorEEE", "tensorrt_llm::runtime::RawEngine::setManagedWeightsMap::managedWeightsMap"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine7setPathENSt10filesystem4pathE", "tensorrt_llm::runtime::RawEngine::setPath"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine7setPathENSt10filesystem4pathE", "tensorrt_llm::runtime::RawEngine::setPath::enginePath"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11RequestTypeE", "tensorrt_llm::runtime::RequestType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11RequestType8kCONTEXTE", "tensorrt_llm::runtime::RequestType::kCONTEXT"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11RequestType11kGENERATIONE", "tensorrt_llm::runtime::RequestType::kGENERATION"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaultsE", "tensorrt_llm::runtime::RuntimeDefaults"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults15RuntimeDefaultsENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::RuntimeDefaults::RuntimeDefaults"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults15RuntimeDefaultsEv", "tensorrt_llm::runtime::RuntimeDefaults::RuntimeDefaults"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults15RuntimeDefaultsENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::RuntimeDefaults::RuntimeDefaults::maxAttentionWindowVec"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults15RuntimeDefaultsENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::RuntimeDefaults::RuntimeDefaults::sinkTokenLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults21maxAttentionWindowVecE", "tensorrt_llm::runtime::RuntimeDefaults::maxAttentionWindowVec"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime15RuntimeDefaults15sinkTokenLengthE", "tensorrt_llm::runtime::RuntimeDefaults::sinkTokenLength"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfigE", "tensorrt_llm::runtime::SamplingConfig"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE", "tensorrt_llm::runtime::SamplingConfig::FloatType"], [1, 1, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE", "tensorrt_llm::runtime::SamplingConfig::OptVec"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE", "tensorrt_llm::runtime::SamplingConfig::OptVec::T"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigE10SizeType32", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKN8executor14SamplingConfigERKNSt8optionalIN8executor25ExternalDraftTokensConfigEEE", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKNSt6vectorI14SamplingConfigEE", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigE10SizeType32", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig::beamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKNSt6vectorI14SamplingConfigEE", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig::configs"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKN8executor14SamplingConfigERKNSt8optionalIN8executor25ExternalDraftTokensConfigEEE", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig::externalDraftTokensConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKN8executor14SamplingConfigERKNSt8optionalIN8executor25ExternalDraftTokensConfigEEE", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig::samplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig23beamSearchDiversityRateE", "tensorrt_llm::runtime::SamplingConfig::beamSearchDiversityRate"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9beamWidthE", "tensorrt_llm::runtime::SamplingConfig::beamWidth"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14beamWidthArrayE", "tensorrt_llm::runtime::SamplingConfig::beamWidthArray"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig11cumLogProbsE", "tensorrt_llm::runtime::SamplingConfig::cumLogProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig24draftAcceptanceThresholdE", "tensorrt_llm::runtime::SamplingConfig::draftAcceptanceThreshold"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig13earlyStoppingE", "tensorrt_llm::runtime::SamplingConfig::earlyStopping"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig16frequencyPenaltyE", "tensorrt_llm::runtime::SamplingConfig::frequencyPenalty"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T", "tensorrt_llm::runtime::SamplingConfig::fuseValues"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T", "tensorrt_llm::runtime::SamplingConfig::fuseValues::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T", "tensorrt_llm::runtime::SamplingConfig::fuseValues::accessor"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T", "tensorrt_llm::runtime::SamplingConfig::fuseValues::configs"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T", "tensorrt_llm::runtime::SamplingConfig::fuseValues::defaultValue"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14SamplingConfig15getMaxBeamWidthEv", "tensorrt_llm::runtime::SamplingConfig::getMaxBeamWidth"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14SamplingConfig17getNumReturnBeamsEv", "tensorrt_llm::runtime::SamplingConfig::getNumReturnBeams"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig13lengthPenaltyE", "tensorrt_llm::runtime::SamplingConfig::lengthPenalty"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9minLengthE", "tensorrt_llm::runtime::SamplingConfig::minLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig4minPE", "tensorrt_llm::runtime::SamplingConfig::minP"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17noRepeatNgramSizeE", "tensorrt_llm::runtime::SamplingConfig::noRepeatNgramSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17normalizeLogProbsE", "tensorrt_llm::runtime::SamplingConfig::normalizeLogProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig18numReturnSequencesE", "tensorrt_llm::runtime::SamplingConfig::numReturnSequences"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime14SamplingConfigeqERK14SamplingConfig", "tensorrt_llm::runtime::SamplingConfig::operator=="], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime14SamplingConfigeqERK14SamplingConfig", "tensorrt_llm::runtime::SamplingConfig::operator==::other"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig19originalTemperatureE", "tensorrt_llm::runtime::SamplingConfig::originalTemperature"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14outputLogProbsE", "tensorrt_llm::runtime::SamplingConfig::outputLogProbs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig15presencePenaltyE", "tensorrt_llm::runtime::SamplingConfig::presencePenalty"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig10randomSeedE", "tensorrt_llm::runtime::SamplingConfig::randomSeed"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17repetitionPenaltyE", "tensorrt_llm::runtime::SamplingConfig::repetitionPenalty"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig11temperatureE", "tensorrt_llm::runtime::SamplingConfig::temperature"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topKE", "tensorrt_llm::runtime::SamplingConfig::topK"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig15topKMedusaHeadsE", "tensorrt_llm::runtime::SamplingConfig::topKMedusaHeads"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topPE", "tensorrt_llm::runtime::SamplingConfig::topP"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9topPDecayE", "tensorrt_llm::runtime::SamplingConfig::topPDecay"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig7topPMinE", "tensorrt_llm::runtime::SamplingConfig::topPMin"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig12topPResetIdsE", "tensorrt_llm::runtime::SamplingConfig::topPResetIds"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig16useDefaultValuesEbRK6OptVecI1TE1T", "tensorrt_llm::runtime::SamplingConfig::useDefaultValues"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig16useDefaultValuesEbRK6OptVecI1TE1T", "tensorrt_llm::runtime::SamplingConfig::useDefaultValues::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig16useDefaultValuesEbRK6OptVecI1TE1T", "tensorrt_llm::runtime::SamplingConfig::useDefaultValues::defaultValue"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig16useDefaultValuesEbRK6OptVecI1TE1T", "tensorrt_llm::runtime::SamplingConfig::useDefaultValues::vec"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig8validateEv", "tensorrt_llm::runtime::SamplingConfig::validate"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec::max"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec::min"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec::name"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec::vec"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10SizeType32E", "tensorrt_llm::runtime::SizeType32"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10SizeType64E", "tensorrt_llm::runtime::SizeType64"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingModeE", "tensorrt_llm::runtime::SpeculativeDecodingMode"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode19DraftTokensExternalEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::DraftTokensExternal"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode5EagleEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::Eagle"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode19ExplicitDraftTokensEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::ExplicitDraftTokens"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode17LookaheadDecodingEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::LookaheadDecoding"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode6MedusaEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::Medusa"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode4NoneEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::None"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode23SpeculativeDecodingModeE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::SpeculativeDecodingMode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode23SpeculativeDecodingModeE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::SpeculativeDecodingMode::state"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode14UnderlyingTypeE", "tensorrt_llm::runtime::SpeculativeDecodingMode::UnderlyingType"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9allBitSetE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::allBitSet"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9allBitSetE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::allBitSet::bits"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9anyBitSetE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::anyBitSet"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9anyBitSetE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::anyBitSet::bits"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode14hasDraftLogitsEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::hasDraftLogits"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21isDraftTokensExternalEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::isDraftTokensExternal"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode7isEagleEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::isEagle"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21isExplicitDraftTokensEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::isExplicitDraftTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19isLookaheadDecodingEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::isLookaheadDecoding"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode8isMedusaEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::isMedusa"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode6isNoneEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::isNone"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode20kDraftTokensExternalE", "tensorrt_llm::runtime::SpeculativeDecodingMode::kDraftTokensExternal"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode6kEagleE", "tensorrt_llm::runtime::SpeculativeDecodingMode::kEagle"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode20kExplicitDraftTokensE", "tensorrt_llm::runtime::SpeculativeDecodingMode::kExplicitDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode18kLookaheadDecodingE", "tensorrt_llm::runtime::SpeculativeDecodingMode::kLookaheadDecoding"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode7kMedusaE", "tensorrt_llm::runtime::SpeculativeDecodingMode::kMedusa"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode5kNoneE", "tensorrt_llm::runtime::SpeculativeDecodingMode::kNone"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode6mStateE", "tensorrt_llm::runtime::SpeculativeDecodingMode::mState"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode20needsDecoderPrologueEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::needsDecoderPrologue"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode18needsKVCacheRewindEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::needsKVCacheRewind"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingModeeqERK23SpeculativeDecodingMode", "tensorrt_llm::runtime::SpeculativeDecodingMode::operator=="], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingModeeqERK23SpeculativeDecodingMode", "tensorrt_llm::runtime::SpeculativeDecodingMode::operator==::other"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19predictsDraftTokensEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::predictsDraftTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21requiresAttentionMaskEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::requiresAttentionMask"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode18updatesPositionIdsEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::updatesPositionIds"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19variableDraftLengthEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::variableDraftLength"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleE", "tensorrt_llm::runtime::SpeculativeDecodingModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleERK25SpeculativeDecodingModule", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule::maxDecodingDraftTokens"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule::maxDraftPathLen"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule::maxNumPaths"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleERK25SpeculativeDecodingModule", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule::o"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule21computeNumPackedMasksEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::computeNumPackedMasks"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule25getMaxDecodingDraftTokensEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getMaxDecodingDraftTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule20getMaxDecodingTokensEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getMaxDecodingTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule18getMaxDraftPathLenEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getMaxDraftPathLen"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule14getMaxNumPathsEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getMaxNumPaths"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule13getMaxPathLenEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getMaxPathLen"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule17getNumPackedMasksEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getNumPackedMasks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule23mMaxDecodingDraftTokensE", "tensorrt_llm::runtime::SpeculativeDecodingModule::mMaxDecodingDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule16mMaxDraftPathLenE", "tensorrt_llm::runtime::SpeculativeDecodingModule::mMaxDraftPathLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule18mMaxNumPackedMasksE", "tensorrt_llm::runtime::SpeculativeDecodingModule::mMaxNumPackedMasks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule12mMaxNumPathsE", "tensorrt_llm::runtime::SpeculativeDecodingModule::mMaxNumPaths"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleaSERK25SpeculativeDecodingModule", "tensorrt_llm::runtime::SpeculativeDecodingModule::operator="], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleaSERK25SpeculativeDecodingModule", "tensorrt_llm::runtime::SpeculativeDecodingModule::operator=::o"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule18setMaxDraftPathLenE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxDraftPathLen"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule18setMaxDraftPathLenE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxDraftPathLen::maxDraftPathLen"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule17setMaxDraftTokensE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxDraftTokens"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule17setMaxDraftTokensE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxDraftTokens::maxDraftTokens"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule14setMaxNumPathsE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxNumPaths"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule14setMaxNumPathsE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxNumPaths::maxNumPaths"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleD0Ev", "tensorrt_llm::runtime::SpeculativeDecodingModule::~SpeculativeDecodingModule"], [1, 1, 1, "_CPPv4I0EN12tensorrt_llm7runtime12StringPtrMapE", "tensorrt_llm::runtime::StringPtrMap"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime12StringPtrMapE", "tensorrt_llm::runtime::StringPtrMap::T"], [1, 2, 1, "_CPPv4I0_bEN12tensorrt_llm7runtime11TRTDataTypeE", "tensorrt_llm::runtime::TRTDataType"], [1, 8, 1, "_CPPv4I0_bEN12tensorrt_llm7runtime11TRTDataTypeE", "tensorrt_llm::runtime::TRTDataType::T"], [1, 2, 1, "_CPPv4I0EN12tensorrt_llm7runtime11TRTDataTypeIP1TEE", "tensorrt_llm::runtime::TRTDataType<T*>"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime11TRTDataTypeIP1TEE", "tensorrt_llm::runtime::TRTDataType<T*>::T"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE15kUnderlyingTypeE", "tensorrt_llm::runtime::TRTDataType<T*>::kUnderlyingType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE5valueE", "tensorrt_llm::runtime::TRTDataType<T*>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIbEE", "tensorrt_llm::runtime::TRTDataType<bool>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIbE5valueE", "tensorrt_llm::runtime::TRTDataType<bool>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIfEE", "tensorrt_llm::runtime::TRTDataType<float>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIfE5valueE", "tensorrt_llm::runtime::TRTDataType<float>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeI4halfEE", "tensorrt_llm::runtime::TRTDataType<half>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeI4halfE5valueE", "tensorrt_llm::runtime::TRTDataType<half>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIN7kernels13FinishedStateEEE", "tensorrt_llm::runtime::TRTDataType<kernels::FinishedState>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIN7kernels13FinishedStateEE5valueE", "tensorrt_llm::runtime::TRTDataType<kernels::FinishedState>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIN7kernels12KVCacheIndexEEE", "tensorrt_llm::runtime::TRTDataType<kernels::KVCacheIndex>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIN7kernels12KVCacheIndexEE5valueE", "tensorrt_llm::runtime::TRTDataType<kernels::KVCacheIndex>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIN7runtime11RequestTypeEEE", "tensorrt_llm::runtime::TRTDataType<runtime::RequestType>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIN7runtime11RequestTypeEE5valueE", "tensorrt_llm::runtime::TRTDataType<runtime::RequestType>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEEE", "tensorrt_llm::runtime::TRTDataType<std::int32_t>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEE5valueE", "tensorrt_llm::runtime::TRTDataType<std::int32_t>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEEE", "tensorrt_llm::runtime::TRTDataType<std::int64_t>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEE5valueE", "tensorrt_llm::runtime::TRTDataType<std::int64_t>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEEE", "tensorrt_llm::runtime::TRTDataType<std::int8_t>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEE5valueE", "tensorrt_llm::runtime::TRTDataType<std::int8_t>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEEE", "tensorrt_llm::runtime::TRTDataType<std::uint32_t>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEE5valueE", "tensorrt_llm::runtime::TRTDataType<std::uint32_t>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEEE", "tensorrt_llm::runtime::TRTDataType<std::uint64_t>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEE5valueE", "tensorrt_llm::runtime::TRTDataType<std::uint64_t>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEEE", "tensorrt_llm::runtime::TRTDataType<std::uint8_t>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEE5valueE", "tensorrt_llm::runtime::TRTDataType<std::uint8_t>::value"], [1, 2, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIPvEE", "tensorrt_llm::runtime::TRTDataType<void*>"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIPvE5valueE", "tensorrt_llm::runtime::TRTDataType<void*>::value"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLoggerE", "tensorrt_llm::runtime::TllmLogger"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger8getLevelEv", "tensorrt_llm::runtime::TllmLogger::getLevel"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger3logE8SeverityPKN8nvinfer19AsciiCharE", "tensorrt_llm::runtime::TllmLogger::log"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger3logE8SeverityPKN8nvinfer19AsciiCharE", "tensorrt_llm::runtime::TllmLogger::log::msg"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger3logE8SeverityPKN8nvinfer19AsciiCharE", "tensorrt_llm::runtime::TllmLogger::log::severity"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger8setLevelE8Severity", "tensorrt_llm::runtime::TllmLogger::setLevel"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger8setLevelE8Severity", "tensorrt_llm::runtime::TllmLogger::setLevel::level"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime16TokenExtraIdTypeE", "tensorrt_llm::runtime::TokenExtraIdType"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime11TokenIdTypeE", "tensorrt_llm::runtime::TokenIdType"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime11UniqueTokenE", "tensorrt_llm::runtime::UniqueToken"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11UniqueTokeneqERK11UniqueToken", "tensorrt_llm::runtime::UniqueToken::operator=="], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11UniqueTokeneqERK11UniqueToken", "tensorrt_llm::runtime::UniqueToken::operator==::other"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11UniqueToken12tokenExtraIdE", "tensorrt_llm::runtime::UniqueToken::tokenExtraId"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11UniqueToken7tokenIdE", "tensorrt_llm::runtime::UniqueToken::tokenId"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime16VecTokenExtraIdsE", "tensorrt_llm::runtime::VecTokenExtraIds"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime15VecUniqueTokensE", "tensorrt_llm::runtime::VecUniqueTokens"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfigE", "tensorrt_llm::runtime::WorldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::WorldConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::WorldConfig::contextParallelism"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::WorldConfig::deviceIds"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::WorldConfig::enableAttentionDP"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::WorldConfig::gpusPerNode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::WorldConfig::pipelineParallelism"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::WorldConfig::rank"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::WorldConfig::tensorParallelism"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig17enableAttentionDPEv", "tensorrt_llm::runtime::WorldConfig::enableAttentionDP"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig23getContextParallelGroupEv", "tensorrt_llm::runtime::WorldConfig::getContextParallelGroup"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getContextParallelRankEv", "tensorrt_llm::runtime::WorldConfig::getContextParallelRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig21getContextParallelismEv", "tensorrt_llm::runtime::WorldConfig::getContextParallelism"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig9getDeviceEv", "tensorrt_llm::runtime::WorldConfig::getDevice"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getDeviceOfE10SizeType32", "tensorrt_llm::runtime::WorldConfig::getDeviceOf"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getDeviceOfE10SizeType32", "tensorrt_llm::runtime::WorldConfig::getDeviceOf::rank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig15getGpusPerGroupEv", "tensorrt_llm::runtime::WorldConfig::getGpusPerGroup"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig14getGpusPerNodeEv", "tensorrt_llm::runtime::WorldConfig::getGpusPerNode"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getLastRankEv", "tensorrt_llm::runtime::WorldConfig::getLastRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig12getLocalRankEv", "tensorrt_llm::runtime::WorldConfig::getLocalRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getNodeRankEv", "tensorrt_llm::runtime::WorldConfig::getNodeRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig13getNodeRankOfE10SizeType32", "tensorrt_llm::runtime::WorldConfig::getNodeRankOf"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig13getNodeRankOfE10SizeType32", "tensorrt_llm::runtime::WorldConfig::getNodeRankOf::rank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig24getPipelineParallelGroupEv", "tensorrt_llm::runtime::WorldConfig::getPipelineParallelGroup"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig23getPipelineParallelRankEv", "tensorrt_llm::runtime::WorldConfig::getPipelineParallelRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getPipelineParallelismEv", "tensorrt_llm::runtime::WorldConfig::getPipelineParallelism"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getRankEv", "tensorrt_llm::runtime::WorldConfig::getRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getSizeEv", "tensorrt_llm::runtime::WorldConfig::getSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getTensorParallelGroupEv", "tensorrt_llm::runtime::WorldConfig::getTensorParallelGroup"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig21getTensorParallelRankEv", "tensorrt_llm::runtime::WorldConfig::getTensorParallelRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig20getTensorParallelismEv", "tensorrt_llm::runtime::WorldConfig::getTensorParallelism"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig17isContextParallelEv", "tensorrt_llm::runtime::WorldConfig::isContextParallel"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig26isFirstContextParallelRankEv", "tensorrt_llm::runtime::WorldConfig::isFirstContextParallelRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig27isFirstPipelineParallelRankEv", "tensorrt_llm::runtime::WorldConfig::isFirstPipelineParallelRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig25isFirstTensorParallelRankEv", "tensorrt_llm::runtime::WorldConfig::isFirstTensorParallelRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig26isLastPipelineParallelRankEv", "tensorrt_llm::runtime::WorldConfig::isLastPipelineParallelRank"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig18isPipelineParallelEv", "tensorrt_llm::runtime::WorldConfig::isPipelineParallel"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig16isTensorParallelEv", "tensorrt_llm::runtime::WorldConfig::isTensorParallel"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig19kDefaultGpusPerNodeE", "tensorrt_llm::runtime::WorldConfig::kDefaultGpusPerNode"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig19mContextParallelismE", "tensorrt_llm::runtime::WorldConfig::mContextParallelism"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig10mDeviceIdsE", "tensorrt_llm::runtime::WorldConfig::mDeviceIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig18mEnableAttentionDPE", "tensorrt_llm::runtime::WorldConfig::mEnableAttentionDP"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig12mGpusPerNodeE", "tensorrt_llm::runtime::WorldConfig::mGpusPerNode"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig20mPipelineParallelismE", "tensorrt_llm::runtime::WorldConfig::mPipelineParallelism"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig5mRankE", "tensorrt_llm::runtime::WorldConfig::mRank"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig18mTensorParallelismE", "tensorrt_llm::runtime::WorldConfig::mTensorParallelism"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::mpi"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::mpi::contextParallelism"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::mpi::deviceIds"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::mpi::enableAttentionDP"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::mpi::gpusPerNode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::mpi::pipelineParallelism"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEEb", "tensorrt_llm::runtime::WorldConfig::mpi::tensorParallelism"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig14validMpiConfigEv", "tensorrt_llm::runtime::WorldConfig::validMpiConfig"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEP1TR7IBuffer", "tensorrt_llm::runtime::bufferCast"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEPK1TRK7IBuffer", "tensorrt_llm::runtime::bufferCast"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEP1TR7IBuffer", "tensorrt_llm::runtime::bufferCast::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEPK1TRK7IBuffer", "tensorrt_llm::runtime::bufferCast::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEP1TR7IBuffer", "tensorrt_llm::runtime::bufferCast::buffer"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEPK1TRK7IBuffer", "tensorrt_llm::runtime::bufferCast::buffer"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7IBuffer9SharedPtrE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7ITensor9SharedPtrE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7IBuffer9SharedPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7ITensor9SharedPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7IBuffer14SharedConstPtrE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7ITensor14SharedConstPtrE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7IBuffer14SharedConstPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7ITensor14SharedConstPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7IBuffer9SharedPtrE", "tensorrt_llm::runtime::bufferCastOrNull::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7ITensor9SharedPtrE", "tensorrt_llm::runtime::bufferCastOrNull::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7IBuffer9SharedPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7ITensor9SharedPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7IBuffer14SharedConstPtrE", "tensorrt_llm::runtime::bufferCastOrNull::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7ITensor14SharedConstPtrE", "tensorrt_llm::runtime::bufferCastOrNull::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7IBuffer14SharedConstPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7ITensor14SharedConstPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7IBuffer9SharedPtrE", "tensorrt_llm::runtime::bufferCastOrNull::bufferPtr"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7IBuffer14SharedConstPtrE", "tensorrt_llm::runtime::bufferCastOrNull::bufferPtr"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7IBuffer9SharedPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::optionalBufferPtr"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7IBuffer14SharedConstPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::optionalBufferPtr"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7ITensor9SharedPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::optionalTensorPtr"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7ITensor14SharedConstPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::optionalTensorPtr"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7ITensor9SharedPtrE", "tensorrt_llm::runtime::bufferCastOrNull::tensorPtr"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7ITensor14SharedConstPtrE", "tensorrt_llm::runtime::bufferCastOrNull::tensorPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13canAccessPeerERK11WorldConfig", "tensorrt_llm::runtime::canAccessPeer"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13canAccessPeerERK11WorldConfig", "tensorrt_llm::runtime::canAccessPeer::worldConfig"], [1, 3, 1, "_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE", "tensorrt_llm::runtime::constPointerCast"], [1, 3, 1, "_CPPv4I0EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERKNSt10shared_ptrI1TEE", "tensorrt_llm::runtime::constPointerCast"], [1, 8, 1, "_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE", "tensorrt_llm::runtime::constPointerCast::D"], [1, 8, 1, "_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE", "tensorrt_llm::runtime::constPointerCast::T"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERKNSt10shared_ptrI1TEE", "tensorrt_llm::runtime::constPointerCast::T"], [1, 4, 1, "_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE", "tensorrt_llm::runtime::constPointerCast::ptr"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERKNSt10shared_ptrI1TEE", "tensorrt_llm::runtime::constPointerCast::ptr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7decoderE", "tensorrt_llm::runtime::decoder"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7decoderE", "tensorrt_llm::runtime::decoder"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffersE", "tensorrt_llm::runtime::decoder::BeamSearchBuffers"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers17BeamSearchBuffersERK13BufferManager", "tensorrt_llm::runtime::decoder::BeamSearchBuffers::BeamSearchBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers17BeamSearchBuffersERK13BufferManager", "tensorrt_llm::runtime::decoder::BeamSearchBuffers::BeamSearchBuffers::bufferManager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers15mCumLogProbsTmpE", "tensorrt_llm::runtime::decoder::BeamSearchBuffers::mCumLogProbsTmp"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers7mNumSMsE", "tensorrt_llm::runtime::decoder::BeamSearchBuffers::mNumSMs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers21mOutputBeamHypothesesE", "tensorrt_llm::runtime::decoder::BeamSearchBuffers::mOutputBeamHypotheses"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers7reshapeE10SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::BeamSearchBuffers::reshape"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers7reshapeE10SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::BeamSearchBuffers::reshape::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder17BeamSearchBuffers7reshapeE10SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::BeamSearchBuffers::reshape::maxSequenceLength"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderStateE", "tensorrt_llm::runtime::decoder::DecoderState"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState12DecoderStateEv", "tensorrt_llm::runtime::decoder::DecoderState::DecoderState"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState16DecodingInputPtrE", "tensorrt_llm::runtime::decoder::DecoderState::DecodingInputPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState17DecodingOutputPtrE", "tensorrt_llm::runtime::decoder::DecoderState::DecodingOutputPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState13LlmRequestPtrE", "tensorrt_llm::runtime::decoder::DecoderState::LlmRequestPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState13RequestVectorE", "tensorrt_llm::runtime::decoder::DecoderState::RequestVector"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState9TensorPtrE", "tensorrt_llm::runtime::decoder::DecoderState::TensorPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState16disableLookaheadERK13RequestVector", "tensorrt_llm::runtime::decoder::DecoderState::disableLookahead"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState16disableLookaheadERK13RequestVector", "tensorrt_llm::runtime::decoder::DecoderState::disableLookahead::genRequests"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState24getAcceptedLengthsCumSumEv", "tensorrt_llm::runtime::decoder::DecoderState::getAcceptedLengthsCumSum"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState22getAcceptedPackedPathsEv", "tensorrt_llm::runtime::decoder::DecoderState::getAcceptedPackedPaths"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState15getAllNewTokensEv", "tensorrt_llm::runtime::decoder::DecoderState::getAllNewTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState20getBeamSearchBuffersEv", "tensorrt_llm::runtime::decoder::DecoderState::getBeamSearchBuffers"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState24getCacheIndirectionInputEv", "tensorrt_llm::runtime::decoder::DecoderState::getCacheIndirectionInput"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState25getCacheIndirectionOutputEv", "tensorrt_llm::runtime::decoder::DecoderState::getCacheIndirectionOutput"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getCumLogProbsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getCumLogProbs"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getCumLogProbsEv", "tensorrt_llm::runtime::decoder::DecoderState::getCumLogProbs"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getCumLogProbsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getCumLogProbs::batchIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState15getEagleBuffersEv", "tensorrt_llm::runtime::decoder::DecoderState::getEagleBuffers"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState29getExplicitDraftTokensBuffersEv", "tensorrt_llm::runtime::decoder::DecoderState::getExplicitDraftTokensBuffers"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState16getFinishReasonsEv", "tensorrt_llm::runtime::decoder::DecoderState::getFinishReasons"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState16getFinishedStepsEv", "tensorrt_llm::runtime::decoder::DecoderState::getFinishedSteps"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getFinishedSumEv", "tensorrt_llm::runtime::decoder::DecoderState::getFinishedSum"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getGatheredIdsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getGatheredIds"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getGatheredIdsEv", "tensorrt_llm::runtime::decoder::DecoderState::getGatheredIds"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState14getGatheredIdsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getGatheredIds::batchIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getGenerationStepsEv", "tensorrt_llm::runtime::decoder::DecoderState::getGenerationSteps"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState6getIdsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getIds"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState6getIdsEv", "tensorrt_llm::runtime::decoder::DecoderState::getIds"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState6getIdsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getIds::batchIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState21getJointDecodingInputEv", "tensorrt_llm::runtime::decoder::DecoderState::getJointDecodingInput"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState22getJointDecodingOutputEv", "tensorrt_llm::runtime::decoder::DecoderState::getJointDecodingOutput"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState11getLogProbsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getLogProbs"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState11getLogProbsEv", "tensorrt_llm::runtime::decoder::DecoderState::getLogProbs"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState11getLogProbsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getLogProbs::batchIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState19getLookaheadBuffersEv", "tensorrt_llm::runtime::decoder::DecoderState::getLookaheadBuffers"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState15getMaxBatchSizeEv", "tensorrt_llm::runtime::decoder::DecoderState::getMaxBatchSize"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState15getMaxBeamWidthEv", "tensorrt_llm::runtime::decoder::DecoderState::getMaxBeamWidth"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState27getMaxDecodingDecoderTokensEv", "tensorrt_llm::runtime::decoder::DecoderState::getMaxDecodingDecoderTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getMaxDecodingEngineTokensEv", "tensorrt_llm::runtime::decoder::DecoderState::getMaxDecodingEngineTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState20getMaxSequenceLengthEv", "tensorrt_llm::runtime::decoder::DecoderState::getMaxSequenceLength"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getNextDraftTokensEv", "tensorrt_llm::runtime::decoder::DecoderState::getNextDraftTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState25getNextDraftTokensLengthsEv", "tensorrt_llm::runtime::decoder::DecoderState::getNextDraftTokensLengths"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getNumDecodingEngineTokensE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getNumDecodingEngineTokens"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getNumDecodingEngineTokensEv", "tensorrt_llm::runtime::decoder::DecoderState::getNumDecodingEngineTokens"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getNumDecodingEngineTokensE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getNumDecodingEngineTokens::batchIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState12getParentIdsEv", "tensorrt_llm::runtime::decoder::DecoderState::getParentIds"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState25getPrevDraftTokensLengthsEv", "tensorrt_llm::runtime::decoder::DecoderState::getPrevDraftTokensLengths"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getSequenceLengthsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getSequenceLengths"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getSequenceLengthsEv", "tensorrt_llm::runtime::decoder::DecoderState::getSequenceLengths"], [1, 4, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState18getSequenceLengthsE10SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::getSequenceLengths::batchIdx"], [1, 3, 1, "_CPPv4NK12tensorrt_llm7runtime7decoder12DecoderState26getSpeculativeDecodingModeEv", "tensorrt_llm::runtime::decoder::DecoderState::getSpeculativeDecodingMode"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState18mBeamSearchBuffersE", "tensorrt_llm::runtime::decoder::DecoderState::mBeamSearchBuffers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14mFinishedStepsE", "tensorrt_llm::runtime::decoder::DecoderState::mFinishedSteps"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState19mJointDecodingInputE", "tensorrt_llm::runtime::decoder::DecoderState::mJointDecodingInput"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState20mJointDecodingOutputE", "tensorrt_llm::runtime::decoder::DecoderState::mJointDecodingOutput"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState13mMaxBatchSizeE", "tensorrt_llm::runtime::decoder::DecoderState::mMaxBatchSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState13mMaxBeamWidthE", "tensorrt_llm::runtime::decoder::DecoderState::mMaxBeamWidth"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState25mMaxDecodingDecoderTokensE", "tensorrt_llm::runtime::decoder::DecoderState::mMaxDecodingDecoderTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24mMaxDecodingEngineTokensE", "tensorrt_llm::runtime::decoder::DecoderState::mMaxDecodingEngineTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState18mMaxSequenceLengthE", "tensorrt_llm::runtime::decoder::DecoderState::mMaxSequenceLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24mNumDecodingEngineTokensE", "tensorrt_llm::runtime::decoder::DecoderState::mNumDecodingEngineTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24mSpeculativeDecodingModeE", "tensorrt_llm::runtime::decoder::DecoderState::mSpeculativeDecodingMode"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers::maxAttentionWindow"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers::maxSequenceLength"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers::sinkTokenLength"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState14reshapeBuffersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeBuffers::worldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState30reshapeCacheIndirectionBuffersE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::reshapeCacheIndirectionBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState30reshapeCacheIndirectionBuffersE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::reshapeCacheIndirectionBuffers::maxAttentionWindow"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState30reshapeCacheIndirectionBuffersE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::reshapeCacheIndirectionBuffers::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState30reshapeCacheIndirectionBuffersE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::reshapeCacheIndirectionBuffers::maxBeamWidth"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState33reshapeSpeculativeDecodingBuffersERK23SpeculativeDecodingMode10SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeSpeculativeDecodingBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState33reshapeSpeculativeDecodingBuffersERK23SpeculativeDecodingMode10SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeSpeculativeDecodingBuffers::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState33reshapeSpeculativeDecodingBuffersERK23SpeculativeDecodingMode10SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeSpeculativeDecodingBuffers::maxTokensPerEngineStep"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState33reshapeSpeculativeDecodingBuffersERK23SpeculativeDecodingMode10SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeSpeculativeDecodingBuffers::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState33reshapeSpeculativeDecodingBuffersERK23SpeculativeDecodingMode10SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeSpeculativeDecodingBuffers::speculativeDecodingMode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState33reshapeSpeculativeDecodingBuffersERK23SpeculativeDecodingMode10SizeType32RK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::reshapeSpeculativeDecodingBuffers::worldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState18setGenerationStepsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::runtime::decoder::DecoderState::setGenerationSteps"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState18setGenerationStepsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::runtime::decoder::DecoderState::setGenerationSteps::generationSteps"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState26setNumDecodingEngineTokensE10SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::setNumDecodingEngineTokens"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState26setNumDecodingEngineTokensE10SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::setNumDecodingEngineTokens::batchIdx"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState26setNumDecodingEngineTokensE10SizeType3210SizeType32", "tensorrt_llm::runtime::decoder::DecoderState::setNumDecodingEngineTokens::numTokens"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::dtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::maxAttentionWindow"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::maxBeamWidth"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::maxSequenceLength"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::sinkTokenLength"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState5setupE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setup::worldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState12setupBuffersEN8nvinfer18DataTypeERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState12setupBuffersEN8nvinfer18DataTypeERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupBuffers::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState12setupBuffersEN8nvinfer18DataTypeERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupBuffers::dtype"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState21setupCacheIndirectionE10SizeType3210SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupCacheIndirection"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState21setupCacheIndirectionE10SizeType3210SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupCacheIndirection::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState21setupCacheIndirectionE10SizeType3210SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupCacheIndirection::maxAttentionWindow"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState21setupCacheIndirectionE10SizeType3210SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupCacheIndirection::maxBatchSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState21setupCacheIndirectionE10SizeType3210SizeType3210SizeType32RK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupCacheIndirection::maxBeamWidth"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState28setupCacheIndirectionBuffersERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupCacheIndirectionBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState28setupCacheIndirectionBuffersERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupCacheIndirectionBuffers::bufferManager"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24setupSpeculativeDecodingERK23SpeculativeDecodingMode10SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecoding"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24setupSpeculativeDecodingERK23SpeculativeDecodingMode10SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecoding::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24setupSpeculativeDecodingERK23SpeculativeDecodingMode10SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecoding::dtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24setupSpeculativeDecodingERK23SpeculativeDecodingMode10SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecoding::maxTokensPerEngineStep"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24setupSpeculativeDecodingERK23SpeculativeDecodingMode10SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecoding::modelConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24setupSpeculativeDecodingERK23SpeculativeDecodingMode10SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecoding::speculativeDecodingMode"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState24setupSpeculativeDecodingERK23SpeculativeDecodingMode10SizeType32N8nvinfer18DataTypeERK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecoding::worldConfig"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState31setupSpeculativeDecodingBuffersE23SpeculativeDecodingModeN8nvinfer18DataTypeERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecodingBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState31setupSpeculativeDecodingBuffersE23SpeculativeDecodingModeN8nvinfer18DataTypeERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecodingBuffers::bufferManager"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState31setupSpeculativeDecodingBuffersE23SpeculativeDecodingModeN8nvinfer18DataTypeERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecodingBuffers::dtype"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder12DecoderState31setupSpeculativeDecodingBuffersE23SpeculativeDecodingModeN8nvinfer18DataTypeERK13BufferManager", "tensorrt_llm::runtime::decoder::DecoderState::setupSpeculativeDecodingBuffers::speculativeDecodingMode"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batchE", "tensorrt_llm::runtime::decoder_batch"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batchE", "tensorrt_llm::runtime::decoder_batch"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5InputE", "tensorrt_llm::runtime::decoder_batch::Input"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI14TensorConstPtrEE", "tensorrt_llm::runtime::decoder_batch::Input::Input"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorINSt6vectorI14TensorConstPtrEEEE10SizeType32", "tensorrt_llm::runtime::decoder_batch::Input::Input"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI14TensorConstPtrEE", "tensorrt_llm::runtime::decoder_batch::Input::Input::logits"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorINSt6vectorI14TensorConstPtrEEEE10SizeType32", "tensorrt_llm::runtime::decoder_batch::Input::Input::logits"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorINSt6vectorI14TensorConstPtrEEEE10SizeType32", "tensorrt_llm::runtime::decoder_batch::Input::Input::maxDecoderSteps"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input14TensorConstPtrE", "tensorrt_llm::runtime::decoder_batch::Input::TensorConstPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input9TensorPtrE", "tensorrt_llm::runtime::decoder_batch::Input::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input10batchSlotsE", "tensorrt_llm::runtime::decoder_batch::Input::batchSlots"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input6logitsE", "tensorrt_llm::runtime::decoder_batch::Input::logits"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input15maxDecoderStepsE", "tensorrt_llm::runtime::decoder_batch::Input::maxDecoderSteps"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7RequestE", "tensorrt_llm::runtime::decoder_batch::Request"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9BufferPtrE", "tensorrt_llm::runtime::decoder_batch::Request::BufferPtr"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14TensorConstPtr10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::decoder_batch::Request::Request"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14TensorConstPtr10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::decoder_batch::Request::Request::endId"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14TensorConstPtr10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::decoder_batch::Request::Request::ids"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14TensorConstPtr10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::decoder_batch::Request::Request::inputLen"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14TensorConstPtr10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::decoder_batch::Request::Request::maxNewTokens"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request14TensorConstPtrE", "tensorrt_llm::runtime::decoder_batch::Request::TensorConstPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9TensorPtrE", "tensorrt_llm::runtime::decoder_batch::Request::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request12badWordsListE", "tensorrt_llm::runtime::decoder_batch::Request::badWordsList"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11draftLogitsE", "tensorrt_llm::runtime::decoder_batch::Request::draftLogits"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11draftTokensE", "tensorrt_llm::runtime::decoder_batch::Request::draftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11eagleConfigE", "tensorrt_llm::runtime::decoder_batch::Request::eagleConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13embeddingBiasE", "tensorrt_llm::runtime::decoder_batch::Request::embeddingBias"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request5endIdE", "tensorrt_llm::runtime::decoder_batch::Request::endId"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request28generatedTokensPerEngineStepE", "tensorrt_llm::runtime::decoder_batch::Request::generatedTokensPerEngineStep"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request3idsE", "tensorrt_llm::runtime::decoder_batch::Request::ids"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request8inputLenE", "tensorrt_llm::runtime::decoder_batch::Request::inputLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request22lookaheadRuntimeConfigE", "tensorrt_llm::runtime::decoder_batch::Request::lookaheadRuntimeConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request12maxNewTokensE", "tensorrt_llm::runtime::decoder_batch::Request::maxNewTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11medusaPathsE", "tensorrt_llm::runtime::decoder_batch::Request::medusaPaths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13medusaTreeIdsE", "tensorrt_llm::runtime::decoder_batch::Request::medusaTreeIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13stopWordsListE", "tensorrt_llm::runtime::decoder_batch::Request::stopWordsList"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20getDefaultBatchSlotsEN7runtime10SizeType32E", "tensorrt_llm::runtime::getDefaultBatchSlots"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20getDefaultBatchSlotsEN7runtime10SizeType32E", "tensorrt_llm::runtime::getDefaultBatchSlots::batchSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime15ipcNvlsAllocateE6size_tNSt3setIiEE", "tensorrt_llm::runtime::ipcNvlsAllocate"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime15ipcNvlsAllocateE6size_tNSt3setIiEE", "tensorrt_llm::runtime::ipcNvlsAllocate::ranks"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime15ipcNvlsAllocateE6size_tNSt3setIiEE", "tensorrt_llm::runtime::ipcNvlsAllocate::size"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ipcNvlsFreeEP13IpcNvlsHandle", "tensorrt_llm::runtime::ipcNvlsFree"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ipcNvlsFreeEP13IpcNvlsHandle", "tensorrt_llm::runtime::ipcNvlsFree::handle"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime16ipcNvlsSupportedEv", "tensorrt_llm::runtime::ipcNvlsSupported"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime20lamportInitializeAllEPvPvPv6size_t", "tensorrt_llm::runtime::lamportInitializeAll"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20lamportInitializeAllEPvPvPv6size_t", "tensorrt_llm::runtime::lamportInitializeAll::buffer_0"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20lamportInitializeAllEPvPvPv6size_t", "tensorrt_llm::runtime::lamportInitializeAll::buffer_1"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20lamportInitializeAllEPvPvPv6size_t", "tensorrt_llm::runtime::lamportInitializeAll::buffer_2"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20lamportInitializeAllEPvPvPv6size_t", "tensorrt_llm::runtime::lamportInitializeAll::size"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK10LoraModule", "tensorrt_llm::runtime::operator<<"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK26LoraCachePageManagerConfig", "tensorrt_llm::runtime::operator<<"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7IBuffer", "tensorrt_llm::runtime::operator<<"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7ITensor", "tensorrt_llm::runtime::operator<<"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN7ITensor5ShapeE", "tensorrt_llm::runtime::operator<<"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::operator<<"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7IBuffer", "tensorrt_llm::runtime::operator<<::buffer"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK26LoraCachePageManagerConfig", "tensorrt_llm::runtime::operator<<::c"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN7ITensor5ShapeE", "tensorrt_llm::runtime::operator<<::dims"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK10LoraModule", "tensorrt_llm::runtime::operator<<::module"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK26LoraCachePageManagerConfig", "tensorrt_llm::runtime::operator<<::os"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::operator<<::os"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK10LoraModule", "tensorrt_llm::runtime::operator<<::output"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7IBuffer", "tensorrt_llm::runtime::operator<<::output"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7ITensor", "tensorrt_llm::runtime::operator<<::output"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN7ITensor5ShapeE", "tensorrt_llm::runtime::operator<<::output"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7ITensor", "tensorrt_llm::runtime::operator<<::tensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::operator<<::v"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9to_stringERK26LoraCachePageManagerConfig", "tensorrt_llm::runtime::to_string"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9to_stringERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::to_string"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9to_stringERK26LoraCachePageManagerConfig", "tensorrt_llm::runtime::to_string::c"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9to_stringERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::to_string::v"], [88, 9, 0, "-", "tensorrt_llm"]], "tensorrt_llm": [[83, 9, 0, "-", "functional"], [85, 9, 0, "-", "models"], [86, 9, 0, "-", "plugin"], [87, 9, 0, "-", "quantization"], [88, 9, 0, "-", "runtime"]], "tensorrt_llm.functional": [[83, 10, 1, "", "AllReduceFusionOp"], [83, 10, 1, "", "AllReduceParams"], [83, 10, 1, "", "AllReduceStrategy"], [83, 10, 1, "", "AttentionMaskType"], [83, 10, 1, "", "Conditional"], [83, 10, 1, "", "DimRange"], [83, 10, 1, "", "LayerNormPositionType"], [83, 10, 1, "", "LayerNormType"], [83, 10, 1, "", "MLPType"], [83, 10, 1, "", "MoEAllReduceParams"], [83, 10, 1, "", "PositionEmbeddingType"], [83, 10, 1, "", "RopeEmbeddingUtils"], [83, 10, 1, "", "RotaryScalingType"], [83, 10, 1, "", "SideStreamIDType"], [83, 10, 1, "", "SliceInputType"], [83, 10, 1, "", "Tensor"], [83, 14, 1, "", "abs"], [83, 14, 1, "", "activation"], [83, 14, 1, "", "add"], [83, 14, 1, "", "allgather"], [83, 14, 1, "", "allreduce"], [83, 14, 1, "", "arange"], [83, 14, 1, "", "argmax"], [83, 14, 1, "", "assertion"], [83, 14, 1, "", "avg_pool2d"], [83, 14, 1, "", "bert_attention"], [83, 14, 1, "", "broadcast_helper"], [83, 14, 1, "", "cast"], [83, 14, 1, "", "categorical_sample"], [83, 14, 1, "", "chunk"], [83, 14, 1, "", "clip"], [83, 14, 1, "", "concat"], [83, 14, 1, "", "constant"], [83, 14, 1, "", "constant_to_tensor_"], [83, 14, 1, "", "constants_to_tensors_"], [83, 14, 1, "", "conv1d"], [83, 14, 1, "", "conv2d"], [83, 14, 1, "", "conv3d"], [83, 14, 1, "", "conv_transpose2d"], [83, 14, 1, "", "cos"], [83, 14, 1, "", "cp_split_plugin"], [83, 14, 1, "", "create_allreduce_plugin"], [83, 14, 1, "", "cuda_stream_sync"], [83, 14, 1, "", "cumsum"], [83, 14, 1, "", "div"], [83, 14, 1, "", "dora_plugin"], [83, 14, 1, "", "einsum"], [83, 14, 1, "", "elementwise_binary"], [83, 14, 1, "", "embedding"], [83, 14, 1, "", "eq"], [83, 14, 1, "", "exp"], [83, 14, 1, "", "expand"], [83, 14, 1, "", "expand_dims"], [83, 14, 1, "", "expand_dims_like"], [83, 14, 1, "", "expand_mask"], [83, 14, 1, "", "flatten"], [83, 14, 1, "", "flip"], [83, 14, 1, "", "floordiv"], [83, 14, 1, "", "gather"], [83, 14, 1, "", "gather_last_token_logits"], [83, 14, 1, "", "gather_nd"], [83, 14, 1, "", "gegelu"], [83, 14, 1, "", "geglu"], [83, 14, 1, "", "gelu"], [83, 14, 1, "", "gemm_allreduce"], [83, 14, 1, "", "gemm_swiglu"], [83, 14, 1, "", "generate_alibi_biases"], [83, 14, 1, "", "generate_alibi_slopes"], [83, 14, 1, "", "generate_logn_scaling"], [83, 14, 1, "", "gpt_attention"], [83, 14, 1, "", "group_norm"], [83, 14, 1, "", "gt"], [83, 14, 1, "", "identity"], [83, 14, 1, "", "index_select"], [83, 14, 1, "", "int_clip"], [83, 14, 1, "", "interpolate"], [83, 14, 1, "", "is_gated_activation"], [83, 14, 1, "", "layer_norm"], [83, 14, 1, "", "log"], [83, 14, 1, "", "log_softmax"], [83, 14, 1, "", "lora_plugin"], [83, 14, 1, "", "low_latency_gemm"], [83, 14, 1, "", "low_latency_gemm_swiglu"], [83, 14, 1, "", "lt"], [83, 14, 1, "", "mamba_conv1d"], [83, 14, 1, "", "masked_scatter"], [83, 14, 1, "", "masked_select"], [83, 14, 1, "", "matmul"], [83, 14, 1, "", "max"], [83, 14, 1, "", "maximum"], [83, 14, 1, "", "mean"], [83, 14, 1, "", "meshgrid2d"], [83, 14, 1, "", "min"], [83, 14, 1, "", "minimum"], [83, 14, 1, "", "modulo"], [83, 14, 1, "", "mul"], [83, 14, 1, "", "non_gated_version"], [83, 14, 1, "", "nonzero"], [83, 14, 1, "", "not_op"], [83, 14, 1, "", "op_and"], [83, 14, 1, "", "op_or"], [83, 14, 1, "", "op_xor"], [83, 14, 1, "", "outer"], [83, 14, 1, "", "pad"], [83, 14, 1, "", "permute"], [83, 14, 1, "", "pow"], [83, 14, 1, "", "prod"], [83, 14, 1, "", "quick_gelu"], [83, 14, 1, "", "rand"], [83, 14, 1, "", "rearrange"], [83, 14, 1, "", "recv"], [83, 14, 1, "", "reduce"], [83, 14, 1, "", "reduce_scatter"], [83, 14, 1, "", "relu"], [83, 14, 1, "", "repeat"], [83, 14, 1, "", "repeat_interleave"], [83, 14, 1, "", "rg_lru"], [83, 14, 1, "", "rms_norm"], [83, 14, 1, "", "round"], [83, 14, 1, "", "scatter"], [83, 14, 1, "", "scatter_nd"], [83, 14, 1, "", "select"], [83, 14, 1, "", "selective_scan"], [83, 14, 1, "", "send"], [83, 14, 1, "", "shape"], [83, 14, 1, "", "sigmoid"], [83, 14, 1, "", "silu"], [83, 14, 1, "", "sin"], [83, 14, 1, "", "slice"], [83, 14, 1, "", "softmax"], [83, 14, 1, "", "softplus"], [83, 14, 1, "", "split"], [83, 14, 1, "", "sqrt"], [83, 14, 1, "", "squared_relu"], [83, 14, 1, "", "squeeze"], [83, 14, 1, "", "stack"], [83, 14, 1, "", "sub"], [83, 14, 1, "", "sum"], [83, 14, 1, "", "swiglu"], [83, 14, 1, "", "tanh"], [83, 14, 1, "", "topk"], [83, 14, 1, "", "transpose"], [83, 14, 1, "", "unary"], [83, 14, 1, "", "unbind"], [83, 14, 1, "", "unsqueeze"], [83, 14, 1, "", "view"], [83, 14, 1, "", "where"]], "tensorrt_llm.functional.AllReduceFusionOp": [[83, 11, 1, "", "LAST_PROCESS_FOR_UB"], [83, 11, 1, "", "MOE_FINALIZE_ALLREDUCE_RESIDUAL_RMS_NORM"], [83, 11, 1, "", "NONE"], [83, 11, 1, "", "RESIDUAL_RMS_NORM"], [83, 11, 1, "", "RESIDUAL_RMS_NORM_OUT_QUANT_FP8"], [83, 11, 1, "", "RESIDUAL_RMS_NORM_OUT_QUANT_NVFP4"], [83, 11, 1, "", "RESIDUAL_RMS_NORM_QUANT_FP8"], [83, 11, 1, "", "RESIDUAL_RMS_NORM_QUANT_NVFP4"], [83, 11, 1, "", "RESIDUAL_RMS_PREPOST_NORM"]], "tensorrt_llm.functional.AllReduceParams": [[83, 12, 1, "", "has_affine"], [83, 12, 1, "", "has_bias"], [83, 12, 1, "", "has_scale"], [83, 12, 1, "", "update_strategy"]], "tensorrt_llm.functional.AllReduceStrategy": [[83, 11, 1, "", "AUTO"], [83, 11, 1, "", "LOWPRECISION"], [83, 11, 1, "", "MIN_LATENCY"], [83, 11, 1, "", "MNNVL"], [83, 11, 1, "", "NCCL"], [83, 11, 1, "", "ONESHOT"], [83, 11, 1, "", "TWOSHOT"], [83, 11, 1, "", "UB"]], "tensorrt_llm.functional.AttentionMaskType": [[83, 11, 1, "", "bidirectional"], [83, 11, 1, "", "bidirectionalglm"], [83, 11, 1, "", "blocksparse"], [83, 11, 1, "", "causal"], [83, 11, 1, "", "custom_mask"], [83, 11, 1, "", "padding"], [83, 11, 1, "", "sliding_window_causal"]], "tensorrt_llm.functional.Conditional": [[83, 12, 1, "", "add_input"], [83, 12, 1, "", "add_output"]], "tensorrt_llm.functional.LayerNormPositionType": [[83, 11, 1, "", "post_layernorm"], [83, 11, 1, "", "pre_layernorm"]], "tensorrt_llm.functional.LayerNormType": [[83, 11, 1, "", "GroupNorm"], [83, 11, 1, "", "LayerNorm"], [83, 11, 1, "", "RmsNorm"]], "tensorrt_llm.functional.MLPType": [[83, 11, 1, "", "FusedGatedMLP"], [83, 11, 1, "", "GatedMLP"], [83, 11, 1, "", "MLP"]], "tensorrt_llm.functional.MoEAllReduceParams": [[83, 12, 1, "", "is_valid"]], "tensorrt_llm.functional.PositionEmbeddingType": [[83, 11, 1, "", "alibi"], [83, 11, 1, "", "alibi_with_scale"], [83, 11, 1, "", "chatglm"], [83, 12, 1, "", "choices"], [83, 11, 1, "", "deferred"], [83, 12, 1, "", "from_string"], [83, 12, 1, "", "is_alibi"], [83, 12, 1, "", "is_deferred"], [83, 12, 1, "", "is_mrope"], [83, 12, 1, "", "is_rope"], [83, 11, 1, "", "learned_absolute"], [83, 11, 1, "", "long_rope"], [83, 11, 1, "", "mrope"], [83, 11, 1, "", "relative"], [83, 11, 1, "", "rope_gpt_neox"], [83, 11, 1, "", "rope_gptj"], [83, 11, 1, "", "yarn"]], "tensorrt_llm.functional.RopeEmbeddingUtils": [[83, 12, 1, "", "apply_llama3_scaling"], [83, 12, 1, "", "apply_rotary_pos_emb"], [83, 12, 1, "", "apply_rotary_pos_emb_chatglm"], [83, 12, 1, "", "apply_rotary_pos_emb_cogvlm"], [83, 12, 1, "", "create_fake_weight"], [83, 12, 1, "", "create_sinusoidal_positions"], [83, 12, 1, "", "create_sinusoidal_positions_for_attention_plugin"], [83, 12, 1, "", "create_sinusoidal_positions_for_cogvlm_attention_plugin"], [83, 12, 1, "", "create_sinusoidal_positions_long_rope"], [83, 12, 1, "", "create_sinusoidal_positions_long_rope_for_attention_plugin"], [83, 12, 1, "", "create_sinusoidal_positions_yarn"], [83, 12, 1, "", "rotate_every_two"], [83, 12, 1, "", "rotate_half"]], "tensorrt_llm.functional.RotaryScalingType": [[83, 11, 1, "", "dynamic"], [83, 12, 1, "", "from_string"], [83, 11, 1, "", "linear"], [83, 11, 1, "", "llama3"], [83, 11, 1, "", "longrope"], [83, 11, 1, "", "mrope"], [83, 11, 1, "", "none"], [83, 11, 1, "", "yarn"]], "tensorrt_llm.functional.SideStreamIDType": [[83, 11, 1, "", "disable"], [83, 11, 1, "", "moe"]], "tensorrt_llm.functional.SliceInputType": [[83, 11, 1, "", "axes"], [83, 11, 1, "", "data"], [83, 11, 1, "", "fill_value"], [83, 11, 1, "", "size"], [83, 11, 1, "", "start"], [83, 11, 1, "", "stride"]], "tensorrt_llm.functional.Tensor": [[83, 12, 1, "", "abs"], [83, 12, 1, "", "cast"], [83, 13, 1, "", "dtype"], [83, 12, 1, "", "flatten"], [83, 12, 1, "", "get_parent"], [83, 12, 1, "", "get_users"], [83, 12, 1, "", "is_dynamic"], [83, 12, 1, "", "is_trt_wrapper"], [83, 13, 1, "", "location"], [83, 12, 1, "", "log"], [83, 12, 1, "", "mark_output"], [83, 12, 1, "", "max"], [83, 12, 1, "", "mean"], [83, 13, 1, "", "name"], [83, 12, 1, "", "ndim"], [83, 13, 1, "", "network"], [83, 12, 1, "", "permute"], [83, 12, 1, "", "rank"], [83, 12, 1, "", "repeat"], [83, 12, 1, "", "replace_all_uses_with"], [83, 12, 1, "", "select"], [83, 13, 1, "", "shape"], [83, 12, 1, "", "size"], [83, 12, 1, "", "split"], [83, 12, 1, "", "sqrt"], [83, 12, 1, "", "squeeze"], [83, 12, 1, "", "transpose"], [83, 12, 1, "", "unbind"], [83, 12, 1, "", "unsqueeze"], [83, 12, 1, "", "view"]], "tensorrt_llm.layers": [[84, 9, 0, "-", "activation"], [84, 9, 0, "-", "attention"], [84, 9, 0, "-", "cast"], [84, 9, 0, "-", "conv"], [84, 9, 0, "-", "embedding"], [84, 9, 0, "-", "linear"], [84, 9, 0, "-", "mlp"], [84, 9, 0, "-", "normalization"], [84, 9, 0, "-", "pooling"]], "tensorrt_llm.layers.activation": [[84, 10, 1, "", "Mish"]], "tensorrt_llm.layers.activation.Mish": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.attention": [[84, 10, 1, "", "Attention"], [84, 10, 1, "", "AttentionMaskParams"], [84, 10, 1, "", "AttentionParams"], [84, 10, 1, "", "BertAttention"], [84, 10, 1, "", "BlockSparseAttnParams"], [84, 10, 1, "", "CogVLMAttention"], [84, 10, 1, "", "DeepseekV2Attention"], [84, 10, 1, "", "DiffusersAttention"], [84, 10, 1, "", "KeyValueCacheParams"], [84, 10, 1, "", "MropeParams"], [84, 10, 1, "", "SpecDecodingParams"], [84, 14, 1, "", "compute_relative_bias"], [84, 14, 1, "", "make_causal_mask"]], "tensorrt_llm.layers.attention.Attention": [[84, 12, 1, "", "create_attention_const_params"], [84, 12, 1, "", "fill_attention_params"], [84, 12, 1, "", "forward"], [84, 12, 1, "", "postprocess"], [84, 12, 1, "", "set_rel_attn_table"]], "tensorrt_llm.layers.attention.AttentionParams": [[84, 12, 1, "", "fill_attention_const_params_for_long_rope"], [84, 12, 1, "", "fill_attention_const_params_for_rope"], [84, 12, 1, "", "is_valid"], [84, 12, 1, "", "is_valid_cross_attn"]], "tensorrt_llm.layers.attention.BertAttention": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.attention.CogVLMAttention": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.attention.DeepseekV2Attention": [[84, 12, 1, "", "forward"], [84, 12, 1, "", "postprocess"], [84, 12, 1, "", "weight_loader"]], "tensorrt_llm.layers.attention.DiffusersAttention": [[84, 12, 1, "", "forward"], [84, 12, 1, "", "joint_attn_forward"]], "tensorrt_llm.layers.attention.KeyValueCacheParams": [[84, 12, 1, "", "fill_none_tensor_list"], [84, 12, 1, "", "get_first_past_key_value"], [84, 12, 1, "", "is_valid"]], "tensorrt_llm.layers.cast": [[84, 10, 1, "", "Cast"]], "tensorrt_llm.layers.cast.Cast": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.conv": [[84, 10, 1, "", "Conv1d"], [84, 10, 1, "", "Conv2d"], [84, 10, 1, "", "Conv3d"], [84, 10, 1, "", "ConvTranspose2d"]], "tensorrt_llm.layers.conv.Conv1d": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.conv.Conv2d": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.conv.Conv3d": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.conv.ConvTranspose2d": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.embedding": [[84, 10, 1, "", "CombinedTimestepLabelEmbeddings"], [84, 10, 1, "", "CombinedTimestepTextProjEmbeddings"], [84, 10, 1, "", "Embedding"], [84, 10, 1, "", "LabelEmbedding"], [84, 10, 1, "", "PixArtAlphaTextProjection"], [84, 10, 1, "", "PromptTuningEmbedding"], [84, 10, 1, "", "SD3PatchEmbed"], [84, 10, 1, "", "TimestepEmbedding"], [84, 10, 1, "", "Timesteps"], [84, 14, 1, "", "get_1d_sincos_pos_embed_from_grid"], [84, 14, 1, "", "get_2d_sincos_pos_embed"], [84, 14, 1, "", "get_2d_sincos_pos_embed_from_grid"], [84, 14, 1, "", "get_timestep_embedding"]], "tensorrt_llm.layers.embedding.CombinedTimestepLabelEmbeddings": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.embedding.CombinedTimestepTextProjEmbeddings": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.embedding.Embedding": [[84, 12, 1, "", "forward"], [84, 12, 1, "", "postprocess"], [84, 12, 1, "", "weight_loader"]], "tensorrt_llm.layers.embedding.LabelEmbedding": [[84, 12, 1, "", "forward"], [84, 12, 1, "", "token_drop"]], "tensorrt_llm.layers.embedding.PixArtAlphaTextProjection": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.embedding.PromptTuningEmbedding": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.embedding.SD3PatchEmbed": [[84, 12, 1, "", "cropped_pos_embed"], [84, 12, 1, "", "forward"]], "tensorrt_llm.layers.embedding.TimestepEmbedding": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.embedding.Timesteps": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.linear": [[84, 11, 1, "", "ColumnLinear"], [84, 10, 1, "", "Linear"], [84, 10, 1, "", "LinearBase"], [84, 10, 1, "", "RowLinear"]], "tensorrt_llm.layers.linear.Linear": [[84, 12, 1, "", "collect_and_bias"], [84, 12, 1, "", "postprocess"], [84, 12, 1, "", "tp_split_dim"]], "tensorrt_llm.layers.linear.LinearBase": [[84, 12, 1, "", "collect_and_bias"], [84, 12, 1, "", "forward"], [84, 12, 1, "", "get_weight"], [84, 12, 1, "", "multiply_and_lora"], [84, 12, 1, "", "multiply_collect"], [84, 12, 1, "", "tp_split_dim"], [84, 12, 1, "", "weight_loader"]], "tensorrt_llm.layers.linear.RowLinear": [[84, 12, 1, "", "collect_and_bias"], [84, 12, 1, "", "multiply_collect"], [84, 12, 1, "", "tp_split_dim"]], "tensorrt_llm.layers.mlp": [[84, 10, 1, "", "FusedGatedMLP"], [84, 10, 1, "", "GatedMLP"], [84, 10, 1, "", "LinearActivation"], [84, 10, 1, "", "LinearApproximateGELU"], [84, 10, 1, "", "LinearGEGLU"], [84, 10, 1, "", "LinearGELU"], [84, 10, 1, "", "LinearSwiGLU"], [84, 10, 1, "", "MLP"], [84, 14, 1, "", "fc_gate_dora"], [84, 14, 1, "", "fc_gate_lora"]], "tensorrt_llm.layers.mlp.FusedGatedMLP": [[84, 12, 1, "", "fc_gate"], [84, 12, 1, "", "fc_gate_plugin"], [84, 12, 1, "", "forward"]], "tensorrt_llm.layers.mlp.GatedMLP": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.mlp.LinearActivation": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.mlp.LinearApproximateGELU": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.mlp.LinearGEGLU": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.mlp.LinearGELU": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.mlp.LinearSwiGLU": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.mlp.MLP": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization": [[84, 10, 1, "", "AdaLayerNorm"], [84, 10, 1, "", "AdaLayerNormContinuous"], [84, 10, 1, "", "AdaLayerNormZero"], [84, 10, 1, "", "AdaLayerNormZeroSingle"], [84, 10, 1, "", "GroupNorm"], [84, 10, 1, "", "LayerNorm"], [84, 10, 1, "", "RmsNorm"], [84, 10, 1, "", "SD35AdaLayerNormZeroX"]], "tensorrt_llm.layers.normalization.AdaLayerNorm": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization.AdaLayerNormContinuous": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization.AdaLayerNormZero": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization.AdaLayerNormZeroSingle": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization.GroupNorm": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization.LayerNorm": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization.RmsNorm": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization.SD35AdaLayerNormZeroX": [[84, 12, 1, "", "forward"]], "tensorrt_llm.layers.pooling": [[84, 10, 1, "", "AvgPool2d"]], "tensorrt_llm.layers.pooling.AvgPool2d": [[84, 12, 1, "", "forward"]], "tensorrt_llm.llmapi": [[71, 10, 1, "", "BatchingType"], [71, 10, 1, "", "BuildCacheConfig"], [71, 10, 1, "", "BuildConfig"], [71, 10, 1, "", "CacheTransceiverConfig"], [71, 10, 1, "", "CalibConfig"], [71, 10, 1, "", "CapacitySchedulerPolicy"], [71, 10, 1, "", "CompletionOutput"], [71, 10, 1, "", "ContextChunkingPolicy"], [71, 10, 1, "", "CudaGraphConfig"], [71, 10, 1, "", "DisaggregatedParams"], [71, 10, 1, "", "DraftTargetDecodingConfig"], [71, 10, 1, "", "DynamicBatchConfig"], [71, 10, 1, "", "EagleDecodingConfig"], [71, 10, 1, "", "ExtendedRuntimePerfKnobConfig"], [71, 10, 1, "", "GuidedDecodingParams"], [71, 10, 1, "", "KvCacheConfig"], [71, 10, 1, "", "KvCacheRetentionConfig"], [71, 10, 1, "", "LLM"], [71, 11, 1, "", "LlmArgs"], [71, 10, 1, "", "LookaheadDecodingConfig"], [71, 10, 1, "", "MTPDecodingConfig"], [71, 10, 1, "", "MedusaDecodingConfig"], [71, 10, 1, "", "MoeConfig"], [71, 10, 1, "", "MpiCommSession"], [71, 10, 1, "", "NGramDecodingConfig"], [71, 10, 1, "", "QuantAlgo"], [71, 10, 1, "", "QuantConfig"], [71, 10, 1, "", "RequestError"], [71, 10, 1, "", "RequestOutput"], [71, 10, 1, "", "SamplingParams"], [71, 10, 1, "", "SchedulerConfig"], [71, 10, 1, "", "TorchCompileConfig"], [71, 10, 1, "", "TorchLlmArgs"], [71, 10, 1, "", "TrtLlmArgs"], [71, 10, 1, "", "UserProvidedDecodingConfig"]], "tensorrt_llm.llmapi.BatchingType": [[71, 11, 1, "", "INFLIGHT"], [71, 11, 1, "", "STATIC"]], "tensorrt_llm.llmapi.BuildCacheConfig": [[71, 12, 1, "", "__init__"], [71, 13, 1, "id7", "cache_root"], [71, 13, 1, "id8", "max_cache_storage_gb"], [71, 13, 1, "id9", "max_records"]], "tensorrt_llm.llmapi.BuildConfig": [[71, 12, 1, "", "__init__"], [71, 11, 1, "", "auto_parallel_config"], [71, 11, 1, "", "dry_run"], [71, 11, 1, "", "enable_debug_output"], [71, 11, 1, "", "force_num_profiles"], [71, 12, 1, "", "from_dict"], [71, 12, 1, "", "from_json_file"], [71, 11, 1, "", "gather_context_logits"], [71, 11, 1, "", "gather_generation_logits"], [71, 12, 1, "", "get_build_config_defaults"], [71, 11, 1, "", "input_timing_cache"], [71, 11, 1, "", "kv_cache_type"], [71, 11, 1, "", "lora_config"], [71, 11, 1, "", "max_batch_size"], [71, 11, 1, "", "max_beam_width"], [71, 11, 1, "", "max_draft_len"], [71, 11, 1, "", "max_encoder_input_len"], [71, 11, 1, "", "max_input_len"], [71, 11, 1, "", "max_num_tokens"], [71, 11, 1, "", "max_prompt_embedding_table_size"], [71, 11, 1, "", "max_seq_len"], [71, 11, 1, "", "monitor_memory"], [71, 11, 1, "", "opt_batch_size"], [71, 11, 1, "", "opt_num_tokens"], [71, 11, 1, "", "output_timing_cache"], [71, 11, 1, "", "plugin_config"], [71, 11, 1, "", "profiling_verbosity"], [71, 11, 1, "", "speculative_decoding_mode"], [71, 11, 1, "", "strongly_typed"], [71, 12, 1, "", "to_dict"], [71, 12, 1, "", "update"], [71, 12, 1, "", "update_from_dict"], [71, 12, 1, "", "update_kv_cache_type"], [71, 11, 1, "", "use_mrope"], [71, 11, 1, "", "use_refit"], [71, 11, 1, "", "use_strip_plan"], [71, 11, 1, "", "visualize_network"], [71, 11, 1, "", "weight_sparsity"], [71, 11, 1, "", "weight_streaming"]], "tensorrt_llm.llmapi.CacheTransceiverConfig": [[71, 15, 1, "", "backend"], [71, 15, 1, "", "max_tokens_in_buffer"], [71, 11, 1, "", "model_config"]], "tensorrt_llm.llmapi.CalibConfig": [[71, 15, 1, "", "calib_batch_size"], [71, 15, 1, "", "calib_batches"], [71, 15, 1, "", "calib_dataset"], [71, 15, 1, "", "calib_max_seq_length"], [71, 15, 1, "", "device"], [71, 12, 1, "", "from_dict"], [71, 11, 1, "", "model_config"], [71, 15, 1, "", "random_seed"], [71, 12, 1, "", "to_dict"], [71, 15, 1, "", "tokenizer_max_seq_length"]], "tensorrt_llm.llmapi.CapacitySchedulerPolicy": [[71, 11, 1, "", "GUARANTEED_NO_EVICT"], [71, 11, 1, "", "MAX_UTILIZATION"], [71, 11, 1, "", "STATIC_BATCH"]], "tensorrt_llm.llmapi.CompletionOutput": [[71, 12, 1, "", "__init__"], [71, 11, 1, "", "cumulative_logprob"], [71, 11, 1, "", "disaggregated_params"], [71, 11, 1, "", "finish_reason"], [71, 11, 1, "", "generation_logits"], [71, 11, 1, "", "index"], [71, 13, 1, "id2", "length"], [71, 11, 1, "", "logprobs"], [71, 13, 1, "id3", "logprobs_diff"], [71, 11, 1, "", "prompt_logprobs"], [71, 11, 1, "", "request_perf_metrics"], [71, 11, 1, "", "stop_reason"], [71, 11, 1, "", "text"], [71, 13, 1, "id4", "text_diff"], [71, 11, 1, "", "token_ids"], [71, 13, 1, "id5", "token_ids_diff"]], "tensorrt_llm.llmapi.ContextChunkingPolicy": [[71, 11, 1, "", "EQUAL_PROGRESS"], [71, 11, 1, "", "FIRST_COME_FIRST_SERVED"]], "tensorrt_llm.llmapi.CudaGraphConfig": [[71, 15, 1, "", "batch_sizes"], [71, 15, 1, "", "enable_padding"], [71, 15, 1, "", "max_batch_size"], [71, 11, 1, "", "model_config"], [71, 16, 1, "", "validate_cuda_graph_max_batch_size"]], "tensorrt_llm.llmapi.DisaggregatedParams": [[71, 12, 1, "", "__init__"], [71, 11, 1, "", "ctx_request_id"], [71, 11, 1, "", "draft_tokens"], [71, 11, 1, "", "first_gen_tokens"], [71, 12, 1, "", "get_context_phase_params"], [71, 12, 1, "", "get_request_type"], [71, 11, 1, "", "opaque_state"], [71, 11, 1, "", "request_type"]], "tensorrt_llm.llmapi.DraftTargetDecodingConfig": [[71, 11, 1, "", "decoding_type"], [71, 12, 1, "", "from_dict"], [71, 11, 1, "", "model_config"], [71, 12, 1, "", "supports_backend"]], "tensorrt_llm.llmapi.DynamicBatchConfig": [[71, 15, 1, "", "dynamic_batch_moving_average_window"], [71, 15, 1, "", "enable_batch_size_tuning"], [71, 15, 1, "", "enable_max_num_tokens_tuning"], [71, 11, 1, "", "model_config"]], "tensorrt_llm.llmapi.EagleDecodingConfig": [[71, 11, 1, "", "decoding_type"], [71, 15, 1, "", "dynamic_tree_max_topK"], [71, 15, 1, "", "eagle3_one_model"], [71, 15, 1, "", "eagle_choices"], [71, 12, 1, "", "from_dict"], [71, 12, 1, "", "get_draft_model_prompt"], [71, 15, 1, "", "greedy_sampling"], [71, 15, 1, "", "max_non_leaves_per_layer"], [71, 11, 1, "", "model_config"], [71, 15, 1, "", "num_eagle_layers"], [71, 15, 1, "", "posterior_threshold"], [71, 13, 1, "", "spec_dec_mode"], [71, 15, 1, "", "use_dynamic_tree"], [71, 12, 1, "", "validate"]], "tensorrt_llm.llmapi.ExtendedRuntimePerfKnobConfig": [[71, 15, 1, "", "cuda_graph_cache_size"], [71, 15, 1, "", "cuda_graph_mode"], [71, 15, 1, "", "enable_context_fmha_fp32_acc"], [71, 11, 1, "", "model_config"], [71, 15, 1, "", "multi_block_mode"]], "tensorrt_llm.llmapi.GuidedDecodingParams": [[71, 12, 1, "", "__init__"], [71, 11, 1, "", "grammar"], [71, 11, 1, "", "json"], [71, 11, 1, "", "json_object"], [71, 11, 1, "", "regex"], [71, 11, 1, "", "structural_tag"]], "tensorrt_llm.llmapi.KvCacheConfig": [[71, 15, 1, "", "copy_on_partial_reuse"], [71, 15, 1, "", "cross_kv_cache_fraction"], [71, 15, 1, "", "dtype"], [71, 15, 1, "", "enable_block_reuse"], [71, 15, 1, "", "enable_partial_reuse"], [71, 15, 1, "", "event_buffer_max_size"], [71, 15, 1, "", "free_gpu_memory_fraction"], [71, 15, 1, "", "host_cache_size"], [71, 15, 1, "", "max_attention_window"], [71, 15, 1, "", "max_tokens"], [71, 11, 1, "", "model_config"], [71, 15, 1, "", "onboard_blocks"], [71, 15, 1, "", "secondary_offload_min_priority"], [71, 15, 1, "", "sink_token_length"], [71, 15, 1, "", "use_uvm"]], "tensorrt_llm.llmapi.KvCacheRetentionConfig": [[71, 10, 1, "", "TokenRangeRetentionConfig"], [71, 12, 1, "", "__init__"], [71, 13, 1, "", "decode_duration_ms"], [71, 13, 1, "", "decode_retention_priority"], [71, 13, 1, "", "directory"], [71, 13, 1, "", "token_range_retention_configs"], [71, 13, 1, "", "transfer_mode"]], "tensorrt_llm.llmapi.KvCacheRetentionConfig.TokenRangeRetentionConfig": [[71, 12, 1, "", "__init__"], [71, 13, 1, "", "duration_ms"], [71, 13, 1, "", "priority"], [71, 13, 1, "", "token_end"], [71, 13, 1, "", "token_start"]], "tensorrt_llm.llmapi.LLM": [[71, 12, 1, "", "generate"], [71, 12, 1, "", "generate_async"], [71, 12, 1, "", "get_kv_cache_events"], [71, 12, 1, "", "get_kv_cache_events_async"], [71, 12, 1, "", "get_stats"], [71, 12, 1, "", "get_stats_async"], [71, 13, 1, "id0", "llm_id"], [71, 12, 1, "", "shutdown"], [71, 13, 1, "id1", "tokenizer"]], "tensorrt_llm.llmapi.LookaheadDecodingConfig": [[71, 12, 1, "", "__init__"], [71, 12, 1, "", "calculate_speculative_resource"], [71, 11, 1, "", "decoding_type"], [71, 12, 1, "", "from_dict"], [71, 15, 1, "", "max_ngram_size"], [71, 15, 1, "", "max_verification_set_size"], [71, 15, 1, "", "max_window_size"], [71, 11, 1, "", "model_config"], [71, 12, 1, "", "supports_backend"], [71, 16, 1, "", "validate_positive_values"]], "tensorrt_llm.llmapi.MTPDecodingConfig": [[71, 15, 1, "", "BEGIN_THINKING_PHASE_TOKEN"], [71, 15, 1, "", "END_THINKING_PHASE_TOKEN"], [71, 11, 1, "", "decoding_type"], [71, 12, 1, "", "from_dict"], [71, 11, 1, "", "model_config"], [71, 15, 1, "", "num_nextn_predict_layers"], [71, 15, 1, "", "num_nextn_predict_layers_from_model_config"], [71, 15, 1, "", "relaxed_delta"], [71, 15, 1, "", "relaxed_topk"], [71, 13, 1, "", "spec_dec_mode"], [71, 12, 1, "", "supports_backend"], [71, 12, 1, "", "update_from_model_config"], [71, 15, 1, "", "use_mtp_vanilla"], [71, 15, 1, "", "use_relaxed_acceptance_for_thinking"]], "tensorrt_llm.llmapi.MedusaDecodingConfig": [[71, 11, 1, "", "decoding_type"], [71, 12, 1, "", "from_dict"], [71, 15, 1, "", "medusa_choices"], [71, 11, 1, "", "model_config"], [71, 15, 1, "", "num_medusa_heads"], [71, 12, 1, "", "supports_backend"]], "tensorrt_llm.llmapi.MoeConfig": [[71, 15, 1, "", "backend"], [71, 12, 1, "", "from_dict"], [71, 15, 1, "", "load_balancer"], [71, 15, 1, "", "max_num_tokens"], [71, 11, 1, "", "model_config"]], "tensorrt_llm.llmapi.MpiCommSession": [[71, 12, 1, "", "__init__"], [71, 12, 1, "", "abort"], [71, 12, 1, "", "get_comm"], [71, 12, 1, "", "shutdown"], [71, 12, 1, "", "submit"], [71, 12, 1, "", "submit_sync"]], "tensorrt_llm.llmapi.NGramDecodingConfig": [[71, 11, 1, "", "decoding_type"], [71, 12, 1, "", "from_dict"], [71, 15, 1, "", "is_keep_all"], [71, 15, 1, "", "is_public_pool"], [71, 15, 1, "", "is_use_oldest"], [71, 15, 1, "", "max_matching_ngram_size"], [71, 11, 1, "", "model_config"], [71, 12, 1, "", "supports_backend"]], "tensorrt_llm.llmapi.QuantAlgo": [[71, 11, 1, "", "FP8"], [71, 11, 1, "", "FP8_BLOCK_SCALES"], [71, 11, 1, "", "FP8_PER_CHANNEL_PER_TOKEN"], [71, 11, 1, "", "INT8"], [71, 11, 1, "", "MIXED_PRECISION"], [71, 11, 1, "", "NO_QUANT"], [71, 11, 1, "", "NVFP4"], [71, 11, 1, "", "W4A16"], [71, 11, 1, "", "W4A16_AWQ"], [71, 11, 1, "", "W4A16_GPTQ"], [71, 11, 1, "", "W4A8_AWQ"], [71, 11, 1, "", "W4A8_MXFP4_FP8"], [71, 11, 1, "", "W4A8_QSERVE_PER_CHANNEL"], [71, 11, 1, "", "W4A8_QSERVE_PER_GROUP"], [71, 11, 1, "", "W8A16"], [71, 11, 1, "", "W8A16_GPTQ"], [71, 11, 1, "", "W8A8_SQ_PER_CHANNEL"], [71, 11, 1, "", "W8A8_SQ_PER_CHANNEL_PER_TENSOR_PLUGIN"], [71, 11, 1, "", "W8A8_SQ_PER_CHANNEL_PER_TOKEN_PLUGIN"], [71, 11, 1, "", "W8A8_SQ_PER_TENSOR_PER_TOKEN_PLUGIN"], [71, 11, 1, "", "W8A8_SQ_PER_TENSOR_PLUGIN"]], "tensorrt_llm.llmapi.QuantConfig": [[71, 12, 1, "", "__init__"], [71, 11, 1, "", "clamp_val"], [71, 11, 1, "", "exclude_modules"], [71, 12, 1, "", "from_dict"], [71, 11, 1, "", "group_size"], [71, 11, 1, "", "has_zero_point"], [71, 12, 1, "", "is_module_excluded_from_quantization"], [71, 11, 1, "", "kv_cache_quant_algo"], [71, 13, 1, "", "layer_quant_mode"], [71, 11, 1, "", "pre_quant_scale"], [71, 11, 1, "", "quant_algo"], [71, 13, 1, "", "quant_mode"], [71, 11, 1, "", "smoothquant_val"], [71, 12, 1, "", "to_dict"], [71, 11, 1, "", "use_meta_recipe"]], "tensorrt_llm.llmapi.RequestOutput": [[71, 12, 1, "", "__init__"], [71, 11, 1, "", "context_logits"], [71, 11, 1, "", "finished"], [71, 11, 1, "", "outputs"], [71, 13, 1, "id6", "prompt"], [71, 11, 1, "", "prompt_token_ids"], [71, 11, 1, "", "request_id"]], "tensorrt_llm.llmapi.SamplingParams": [[71, 12, 1, "", "__init__"], [71, 11, 1, "", "add_special_tokens"], [71, 11, 1, "", "additional_model_outputs"], [71, 11, 1, "", "apply_batched_logits_processor"], [71, 11, 1, "", "bad"], [71, 11, 1, "", "bad_token_ids"], [71, 11, 1, "", "beam_search_diversity_rate"], [71, 11, 1, "", "beam_width_array"], [71, 11, 1, "", "best_of"], [71, 11, 1, "", "detokenize"], [71, 11, 1, "", "early_stopping"], [71, 11, 1, "", "embedding_bias"], [71, 11, 1, "", "end_id"], [71, 11, 1, "", "exclude_input_from_output"], [71, 11, 1, "", "frequency_penalty"], [71, 11, 1, "", "guided_decoding"], [71, 11, 1, "", "ignore_eos"], [71, 11, 1, "", "include_stop_str_in_output"], [71, 11, 1, "", "length_penalty"], [71, 11, 1, "", "logits_processor"], [71, 11, 1, "", "logprobs"], [71, 11, 1, "", "lookahead_config"], [71, 11, 1, "", "max_tokens"], [71, 11, 1, "", "min_p"], [71, 11, 1, "", "min_tokens"], [71, 11, 1, "", "n"], [71, 11, 1, "", "no_repeat_ngram_size"], [71, 11, 1, "", "pad_id"], [71, 11, 1, "", "presence_penalty"], [71, 11, 1, "", "prompt_logprobs"], [71, 11, 1, "", "repetition_penalty"], [71, 11, 1, "", "return_context_logits"], [71, 11, 1, "", "return_encoder_output"], [71, 11, 1, "", "return_generation_logits"], [71, 11, 1, "", "return_perf_metrics"], [71, 11, 1, "", "seed"], [71, 11, 1, "", "skip_special_tokens"], [71, 11, 1, "", "spaces_between_special_tokens"], [71, 11, 1, "", "stop"], [71, 11, 1, "", "stop_token_ids"], [71, 11, 1, "", "temperature"], [71, 11, 1, "", "top_k"], [71, 11, 1, "", "top_p"], [71, 11, 1, "", "top_p_decay"], [71, 11, 1, "", "top_p_min"], [71, 11, 1, "", "top_p_reset_ids"], [71, 11, 1, "", "truncate_prompt_tokens"], [71, 11, 1, "", "use_beam_search"]], "tensorrt_llm.llmapi.SchedulerConfig": [[71, 15, 1, "", "capacity_scheduler_policy"], [71, 15, 1, "", "context_chunking_policy"], [71, 15, 1, "", "dynamic_batch_config"], [71, 11, 1, "", "model_config"]], "tensorrt_llm.llmapi.TorchCompileConfig": [[71, 15, 1, "", "enable_fullgraph"], [71, 15, 1, "", "enable_inductor"], [71, 15, 1, "", "enable_piecewise_cuda_graph"], [71, 15, 1, "", "enable_userbuffers"], [71, 11, 1, "", "model_config"]], "tensorrt_llm.llmapi.TorchLlmArgs": [[71, 15, 1, "", "allreduce_strategy"], [71, 15, 1, "", "attn_backend"], [71, 15, 1, "", "build_config"], [71, 15, 1, "", "checkpoint_format"], [71, 15, 1, "", "checkpoint_loader"], [71, 16, 1, "", "convert_load_format"], [71, 15, 1, "", "cuda_graph_config"], [71, 11, 1, "", "decoding_config"], [71, 15, 1, "", "disable_overlap_scheduler"], [71, 15, 1, "", "enable_autotuner"], [71, 15, 1, "", "enable_iter_perf_stats"], [71, 15, 1, "", "enable_iter_req_stats"], [71, 15, 1, "", "enable_layerwise_nvtx_marker"], [71, 15, 1, "", "enable_min_latency"], [71, 15, 1, "", "enable_mixed_sampler"], [71, 15, 1, "", "enable_trtllm_sampler"], [71, 13, 1, "", "extra_resource_managers"], [71, 11, 1, "id18", "field_name"], [71, 15, 1, "", "force_dynamic_quantization"], [71, 15, 1, "", "garbage_collection_gen0_threshold"], [71, 12, 1, "", "get_pytorch_backend_config"], [71, 16, 1, "", "init_backend"], [71, 15, 1, "", "load_format"], [71, 11, 1, "", "max_cpu_loras"], [71, 11, 1, "", "max_lora_rank"], [71, 11, 1, "", "max_loras"], [71, 11, 1, "", "model_config"], [71, 12, 1, "", "model_post_init"], [71, 15, 1, "", "moe_config"], [71, 11, 1, "id16", "msg"], [71, 15, 1, "", "print_iter_log"], [71, 13, 1, "", "quant_config"], [71, 15, 1, "", "stream_interval"], [71, 16, 1, "", "sync_quant_config_with_kv_cache_config_dtype"], [71, 15, 1, "", "torch_compile_config"], [71, 16, 1, "", "validate_checkpoint_format"], [71, 16, 1, "", "validate_cuda_graph_config"], [71, 16, 1, "", "validate_load_balancer"], [71, 16, 1, "", "validate_stream_interval"], [71, 11, 1, "id17", "wrapped_property"]], "tensorrt_llm.llmapi.TrtLlmArgs": [[71, 11, 1, "", "auto_parallel"], [71, 13, 1, "", "auto_parallel_config"], [71, 11, 1, "", "auto_parallel_world_size"], [71, 15, 1, "", "build_config"], [71, 15, 1, "", "calib_config"], [71, 11, 1, "", "decoding_config"], [71, 15, 1, "", "embedding_parallel_mode"], [71, 15, 1, "", "enable_build_cache"], [71, 15, 1, "", "enable_prompt_adapter"], [71, 15, 1, "", "enable_tqdm"], [71, 15, 1, "", "extended_runtime_perf_knob_config"], [71, 15, 1, "", "fast_build"], [71, 11, 1, "id33", "field_name"], [71, 16, 1, "", "init_calib_config"], [71, 11, 1, "", "max_cpu_loras"], [71, 11, 1, "", "max_lora_rank"], [71, 11, 1, "", "max_loras"], [71, 15, 1, "", "max_prompt_adapter_token"], [71, 11, 1, "", "model_config"], [71, 12, 1, "", "model_post_init"], [71, 11, 1, "id31", "msg"], [71, 15, 1, "", "quant_config"], [71, 16, 1, "", "setup_embedding_parallel_mode"], [71, 16, 1, "", "validate_auto_parallel"], [71, 16, 1, "", "validate_enable_build_cache"], [71, 16, 1, "", "validate_kv_cache_dtype"], [71, 16, 1, "", "validate_quant_config"], [71, 15, 1, "", "workspace"], [71, 11, 1, "id32", "wrapped_property"]], "tensorrt_llm.llmapi.UserProvidedDecodingConfig": [[71, 11, 1, "", "decoding_type"], [71, 15, 1, "", "drafter"], [71, 12, 1, "", "from_dict"], [71, 11, 1, "", "model_config"], [71, 15, 1, "", "resource_manager"]], "tensorrt_llm.models": [[85, 10, 1, "", "BaichuanForCausalLM"], [85, 10, 1, "", "BertForQuestionAnswering"], [85, 10, 1, "", "BertForSequenceClassification"], [85, 10, 1, "", "BertModel"], [85, 10, 1, "", "BloomForCausalLM"], [85, 10, 1, "", "BloomModel"], [85, 10, 1, "", "CLIPVisionTransformer"], [85, 10, 1, "", "ChatGLMConfig"], [85, 10, 1, "", "ChatGLMForCausalLM"], [85, 10, 1, "", "ChatGLMModel"], [85, 10, 1, "", "CogVLMConfig"], [85, 10, 1, "", "CogVLMForCausalLM"], [85, 10, 1, "", "CohereForCausalLM"], [85, 10, 1, "", "DbrxConfig"], [85, 10, 1, "", "DbrxForCausalLM"], [85, 10, 1, "", "DecoderModel"], [85, 10, 1, "", "DeepseekForCausalLM"], [85, 10, 1, "", "DeepseekV2ForCausalLM"], [85, 10, 1, "", "DiT"], [85, 10, 1, "", "EagleForCausalLM"], [85, 10, 1, "", "EncoderModel"], [85, 10, 1, "", "FalconConfig"], [85, 10, 1, "", "FalconForCausalLM"], [85, 10, 1, "", "FalconModel"], [85, 10, 1, "", "GPTConfig"], [85, 10, 1, "", "GPTForCausalLM"], [85, 10, 1, "", "GPTJConfig"], [85, 10, 1, "", "GPTJForCausalLM"], [85, 10, 1, "", "GPTJModel"], [85, 10, 1, "", "GPTModel"], [85, 10, 1, "", "GPTNeoXForCausalLM"], [85, 10, 1, "", "GPTNeoXModel"], [85, 10, 1, "", "GemmaConfig"], [85, 10, 1, "", "GemmaForCausalLM"], [85, 10, 1, "", "LLaMAConfig"], [85, 10, 1, "", "LLaMAForCausalLM"], [85, 10, 1, "", "LLaMAModel"], [85, 10, 1, "", "LlavaNextVisionConfig"], [85, 10, 1, "", "LlavaNextVisionWrapper"], [85, 10, 1, "", "MLLaMAForCausalLM"], [85, 10, 1, "", "MPTForCausalLM"], [85, 10, 1, "", "MPTModel"], [85, 10, 1, "", "MambaForCausalLM"], [85, 10, 1, "", "MedusaConfig"], [85, 10, 1, "", "MedusaForCausalLm"], [85, 10, 1, "", "OPTForCausalLM"], [85, 10, 1, "", "OPTModel"], [85, 10, 1, "", "Phi3ForCausalLM"], [85, 10, 1, "", "Phi3Model"], [85, 10, 1, "", "PhiForCausalLM"], [85, 10, 1, "", "PhiModel"], [85, 10, 1, "", "PretrainedConfig"], [85, 10, 1, "", "PretrainedModel"], [85, 10, 1, "", "ReDrafterForLLaMALM"], [85, 10, 1, "", "ReDrafterForQWenLM"], [85, 10, 1, "", "RecurrentGemmaForCausalLM"], [85, 11, 1, "", "RobertaForQuestionAnswering"], [85, 11, 1, "", "RobertaForSequenceClassification"], [85, 11, 1, "", "RobertaModel"], [85, 10, 1, "", "SD3Transformer2DModel"], [85, 10, 1, "", "SpeculativeDecodingMode"], [85, 10, 1, "", "WhisperEncoder"]], "tensorrt_llm.models.BaichuanForCausalLM": [[85, 11, 1, "", "config_class"], [85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "quantize"]], "tensorrt_llm.models.BertForQuestionAnswering": [[85, 12, 1, "", "forward"]], "tensorrt_llm.models.BertForSequenceClassification": [[85, 12, 1, "", "forward"]], "tensorrt_llm.models.BertModel": [[85, 12, 1, "", "forward"]], "tensorrt_llm.models.BloomModel": [[85, 12, 1, "", "forward"]], "tensorrt_llm.models.CLIPVisionTransformer": [[85, 12, 1, "", "forward"]], "tensorrt_llm.models.ChatGLMConfig": [[85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "to_dict"]], "tensorrt_llm.models.ChatGLMForCausalLM": [[85, 11, 1, "", "config_class"], [85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "prepare_inputs"], [85, 12, 1, "", "quantize"]], "tensorrt_llm.models.ChatGLMModel": [[85, 12, 1, "", "forward"]], "tensorrt_llm.models.CogVLMConfig": [[85, 12, 1, "", "to_dict"]], "tensorrt_llm.models.CogVLMForCausalLM": [[85, 11, 1, "", "config_class"], [85, 12, 1, "", "default_plugin_config"], [85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "quantize"]], "tensorrt_llm.models.CohereForCausalLM": [[85, 11, 1, "", "config_class"], [85, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.DbrxConfig": [[85, 12, 1, "", "to_dict"]], "tensorrt_llm.models.DbrxForCausalLM": [[85, 11, 1, "", "config_class"]], "tensorrt_llm.models.DecoderModel": [[85, 12, 1, "", "check_config"], [85, 12, 1, "", "forward"], [85, 12, 1, "", "precompute_relative_attention_bias"], [85, 12, 1, "", "prepare_inputs"], [85, 12, 1, "", "use_lora"]], "tensorrt_llm.models.DeepseekForCausalLM": [[85, 11, 1, "", "config_class"], [85, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.DeepseekV2ForCausalLM": [[85, 11, 1, "", "config_class"], [85, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.DiT": [[85, 12, 1, "", "check_config"], [85, 12, 1, "", "forward"], [85, 12, 1, "", "forward_with_cfg"], [85, 12, 1, "", "forward_without_cfg"], [85, 12, 1, "", "prepare_inputs"], [85, 12, 1, "", "unpatchify"]], "tensorrt_llm.models.EagleForCausalLM": [[85, 11, 1, "", "config_class"], [85, 12, 1, "", "forward"], [85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "prepare_inputs"]], "tensorrt_llm.models.EncoderModel": [[85, 12, 1, "", "check_config"], [85, 12, 1, "", "forward"], [85, 12, 1, "", "precompute_relative_attention_bias"], [85, 12, 1, "", "prepare_inputs"], [85, 12, 1, "", "use_lora"], [85, 12, 1, "", "use_prompt_tuning"]], "tensorrt_llm.models.FalconConfig": [[85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "to_dict"]], "tensorrt_llm.models.FalconForCausalLM": [[85, 12, 1, "", "check_config"], [85, 11, 1, "", "config_class"], [85, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.FalconModel": [[85, 12, 1, "", "forward"]], "tensorrt_llm.models.GPTConfig": [[85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "from_nemo"], [85, 12, 1, "", "to_dict"]], "tensorrt_llm.models.GPTForCausalLM": [[85, 11, 1, "", "config_class"], [85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "from_nemo"], [85, 12, 1, "", "quantize"], [85, 12, 1, "", "use_lora"]], "tensorrt_llm.models.GPTJConfig": [[85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "to_dict"]], "tensorrt_llm.models.GPTJForCausalLM": [[85, 11, 1, "", "config_class"], [85, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.GPTJModel": [[85, 12, 1, "", "forward"]], "tensorrt_llm.models.GPTModel": [[85, 12, 1, "", "forward"]], "tensorrt_llm.models.GPTNeoXModel": [[85, 12, 1, "", "forward"]], "tensorrt_llm.models.GemmaConfig": [[85, 11, 1, "", "GEMMA2_ADDED_FIELDS"], [85, 11, 1, "", "GEMMA3_ADDED_FIELDS"], [85, 11, 1, "", "GEMMA_ADDED_FIELDS"], [85, 11, 1, "", "VERBATIM"], [85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "gemma2_config"], [85, 12, 1, "", "gemma3_config"], [85, 12, 1, "", "get_hf_config"], [85, 13, 1, "", "is_gemma_2"], [85, 13, 1, "", "is_gemma_3"], [85, 12, 1, "", "to_dict"]], "tensorrt_llm.models.GemmaForCausalLM": [[85, 11, 1, "", "NATIVE_QUANT_FLOW"], [85, 12, 1, "", "assert_valid_quant_algo"], [85, 11, 1, "", "config_class"], [85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "quantize"], [85, 12, 1, "", "use_lora"]], "tensorrt_llm.models.LLaMAConfig": [[85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "from_meta_ckpt"], [85, 12, 1, "", "to_dict"]], "tensorrt_llm.models.LLaMAForCausalLM": [[85, 11, 1, "", "config_class"], [85, 12, 1, "", "default_plugin_config"], [85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "from_meta_ckpt"], [85, 12, 1, "", "quantize"], [85, 12, 1, "", "use_lora"]], "tensorrt_llm.models.LLaMAModel": [[85, 12, 1, "", "forward"]], "tensorrt_llm.models.LlavaNextVisionConfig": [[85, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.LlavaNextVisionWrapper": [[85, 12, 1, "", "forward"], [85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "prepare_inputs"], [85, 12, 1, "", "save_checkpoint"]], "tensorrt_llm.models.MLLaMAForCausalLM": [[85, 11, 1, "", "config_class"], [85, 12, 1, "", "forward"], [85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "prepare_inputs"], [85, 12, 1, "", "use_lora"]], "tensorrt_llm.models.MPTForCausalLM": [[85, 12, 1, "", "check_config"]], "tensorrt_llm.models.MPTModel": [[85, 12, 1, "", "forward"]], "tensorrt_llm.models.MambaForCausalLM": [[85, 11, 1, "", "config_class"], [85, 12, 1, "", "forward"], [85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "prepare_inputs"]], "tensorrt_llm.models.MedusaConfig": [[85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "to_dict"]], "tensorrt_llm.models.MedusaForCausalLm": [[85, 11, 1, "", "config_class"], [85, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.OPTForCausalLM": [[85, 12, 1, "", "check_config"]], "tensorrt_llm.models.OPTModel": [[85, 12, 1, "", "forward"]], "tensorrt_llm.models.Phi3ForCausalLM": [[85, 11, 1, "", "config_class"], [85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "use_lora"]], "tensorrt_llm.models.Phi3Model": [[85, 12, 1, "", "forward"]], "tensorrt_llm.models.PhiForCausalLM": [[85, 12, 1, "", "check_config"], [85, 11, 1, "", "config_class"], [85, 12, 1, "", "from_hugging_face"], [85, 12, 1, "", "use_lora"]], "tensorrt_llm.models.PhiModel": [[85, 12, 1, "", "forward"]], "tensorrt_llm.models.PretrainedConfig": [[85, 12, 1, "", "create_runtime_defaults"], [85, 12, 1, "", "for_each_rank"], [85, 12, 1, "", "from_checkpoint"], [85, 12, 1, "", "from_dict"], [85, 12, 1, "", "from_json_file"], [85, 12, 1, "", "get_config_group"], [85, 12, 1, "", "has_config_group"], [85, 13, 1, "", "kv_dtype"], [85, 13, 1, "", "quant_algo"], [85, 13, 1, "", "quant_mode"], [85, 12, 1, "", "set_if_not_exist"], [85, 12, 1, "", "set_rank"], [85, 12, 1, "", "to_dict"], [85, 12, 1, "", "to_json_file"], [85, 12, 1, "", "to_layer_quant_config"]], "tensorrt_llm.models.PretrainedModel": [[85, 12, 1, "", "check_config"], [85, 12, 1, "", "from_checkpoint"], [85, 12, 1, "", "from_config"], [85, 12, 1, "", "load"], [85, 12, 1, "", "prepare_inputs"], [85, 12, 1, "", "quantize"], [85, 12, 1, "", "release"], [85, 12, 1, "", "save_checkpoint"]], "tensorrt_llm.models.RecurrentGemmaForCausalLM": [[85, 12, 1, "", "forward"], [85, 12, 1, "", "prepare_inputs"], [85, 12, 1, "", "prepare_recurrent_inputs"]], "tensorrt_llm.models.SD3Transformer2DModel": [[85, 13, 1, "", "attn_processors"], [85, 11, 1, "", "config_class"], [85, 12, 1, "", "disable_forward_chunking"], [85, 12, 1, "", "enable_forward_chunking"], [85, 12, 1, "", "forward"], [85, 12, 1, "", "from_pretrained"], [85, 12, 1, "", "fuse_qkv_projections"], [85, 12, 1, "", "load"], [85, 12, 1, "", "prepare_inputs"], [85, 12, 1, "", "set_attn_processor"], [85, 12, 1, "", "unfuse_qkv_projections"]], "tensorrt_llm.models.SpeculativeDecodingMode": [[85, 11, 1, "", "DRAFT_TOKENS_EXTERNAL"], [85, 11, 1, "", "EAGLE"], [85, 11, 1, "", "EXPLICIT_DRAFT_TOKENS"], [85, 11, 1, "", "LOOKAHEAD_DECODING"], [85, 11, 1, "", "MEDUSA"], [85, 11, 1, "", "NGRAM"], [85, 11, 1, "", "NONE"], [85, 11, 1, "", "USER_PROVIDED"], [85, 12, 1, "", "from_arguments"]], "tensorrt_llm.models.WhisperEncoder": [[85, 12, 1, "", "forward"], [85, 12, 1, "", "precompute_relative_attention_bias"], [85, 12, 1, "", "prepare_inputs"]], "tensorrt_llm.plugin": [[86, 10, 1, "", "PluginConfig"]], "tensorrt_llm.plugin.PluginConfig": [[86, 12, 1, "", "to_legacy_setting"]], "tensorrt_llm.quantization": [[87, 10, 1, "", "QuantAlgo"], [87, 10, 1, "", "QuantMode"], [87, 14, 1, "", "quantize_and_export"]], "tensorrt_llm.runtime": [[88, 10, 1, "", "ChatGLMGenerationSession"], [88, 10, 1, "", "EncDecModelRunner"], [88, 10, 1, "", "GenerationSequence"], [88, 10, 1, "", "GenerationSession"], [88, 10, 1, "", "KVCacheManager"], [88, 10, 1, "", "LogitsProcessor"], [88, 10, 1, "", "LogitsProcessorList"], [88, 10, 1, "", "ModelConfig"], [88, 10, 1, "", "ModelRunner"], [88, 10, 1, "", "ModelRunnerCpp"], [88, 10, 1, "", "MultimodalModelRunner"], [88, 10, 1, "", "QWenForCausalLMGenerationSession"], [88, 10, 1, "", "SamplingConfig"], [88, 10, 1, "", "Session"], [88, 10, 1, "", "StoppingCriteria"], [88, 10, 1, "", "StoppingCriteriaList"], [88, 10, 1, "", "TensorInfo"], [88, 14, 1, "", "decode_words_list"]], "tensorrt_llm.runtime.EncDecModelRunner": [[88, 12, 1, "", "encoder_run"], [88, 12, 1, "", "from_engine"], [88, 12, 1, "", "generate"], [88, 12, 1, "", "process_input"]], "tensorrt_llm.runtime.GenerationSequence": [[88, 12, 1, "", "get_batch_idx"], [88, 12, 1, "", "get_seq_idx"]], "tensorrt_llm.runtime.GenerationSession": [[88, 11, 1, "", "batch_size"], [88, 11, 1, "", "buffer_allocated"], [88, 13, 1, "", "context_mem_size"], [88, 13, 1, "", "conv_kernel"], [88, 13, 1, "", "cross_attention"], [88, 11, 1, "", "cuda_graph_mode"], [88, 12, 1, "", "cuda_stream_guard"], [88, 11, 1, "", "debug_mode"], [88, 11, 1, "", "debug_tensors_to_save"], [88, 12, 1, "", "decode"], [88, 12, 1, "", "decode_batch"], [88, 12, 1, "", "decode_regular"], [88, 12, 1, "", "decode_stream"], [88, 11, 1, "", "device"], [88, 13, 1, "", "dtype"], [88, 12, 1, "", "dump_debug_buffers"], [88, 12, 1, "", "early_stop_criteria"], [88, 13, 1, "", "engine_inspector"], [88, 12, 1, "", "filter_medusa_logits"], [88, 12, 1, "", "finalize_decoder"], [88, 12, 1, "", "find_best_medusa_path"], [88, 13, 1, "", "first_layer"], [88, 13, 1, "", "gather_context_logits"], [88, 13, 1, "", "gather_generation_logits"], [88, 13, 1, "", "gemm_allreduce_plugin"], [88, 12, 1, "", "get_next_medusa_tokens"], [88, 12, 1, "", "get_num_heads_kv"], [88, 12, 1, "", "handle_per_step"], [88, 13, 1, "", "has_position_embedding"], [88, 13, 1, "", "has_token_type_embedding"], [88, 13, 1, "", "head_size"], [88, 13, 1, "", "hidden_size"], [88, 13, 1, "", "is_medusa_mode"], [88, 13, 1, "", "is_redrafter_mode"], [88, 13, 1, "", "kv_cache_type"], [88, 13, 1, "", "last_layer"], [88, 12, 1, "", "locate_accepted_draft_tokens"], [88, 11, 1, "", "mapping"], [88, 13, 1, "", "max_draft_tokens"], [88, 13, 1, "", "max_prompt_embedding_table_size"], [88, 12, 1, "", "medusa_decode_and_verify"], [88, 11, 1, "", "medusa_paths"], [88, 11, 1, "", "medusa_position_offsets"], [88, 11, 1, "", "medusa_temperature"], [88, 11, 1, "", "medusa_topks"], [88, 11, 1, "", "medusa_tree_ids"], [88, 12, 1, "", "next_medusa_input_ids"], [88, 11, 1, "", "num_draft_tokens"], [88, 13, 1, "", "num_heads"], [88, 13, 1, "", "num_layers"], [88, 13, 1, "", "num_medusa_heads"], [88, 13, 1, "", "paged_kv_cache"], [88, 13, 1, "", "paged_state"], [88, 12, 1, "", "pp_communicate_final_output_ids"], [88, 12, 1, "", "pp_communicate_new_tokens"], [88, 12, 1, "", "process_logits_including_draft"], [88, 13, 1, "", "profiler"], [88, 13, 1, "", "quant_mode"], [88, 13, 1, "", "remove_input_padding"], [88, 12, 1, "", "reorder_kv_cache_for_beam_search"], [88, 13, 1, "", "rnn_conv_dim_size"], [88, 13, 1, "", "rnn_head_size"], [88, 13, 1, "", "rnn_hidden_size"], [88, 11, 1, "", "runtime"], [88, 12, 1, "", "setup"], [88, 13, 1, "", "state_dtype"], [88, 13, 1, "", "state_size"], [88, 13, 1, "", "tokens_per_block"], [88, 12, 1, "", "update_output_ids_by_offset"], [88, 13, 1, "", "use_gemm_allreduce_plugin"], [88, 13, 1, "", "use_gpt_attention_plugin"], [88, 13, 1, "", "use_kv_cache"], [88, 13, 1, "", "use_lora_plugin"], [88, 13, 1, "", "use_mamba_conv1d_plugin"], [88, 13, 1, "", "vocab_size"]], "tensorrt_llm.runtime.KVCacheManager": [[88, 12, 1, "", "add_sequence"], [88, 12, 1, "", "get_block_offsets"], [88, 12, 1, "", "step"]], "tensorrt_llm.runtime.ModelConfig": [[88, 11, 1, "", "conv_kernel"], [88, 11, 1, "", "cross_attention"], [88, 11, 1, "", "dtype"], [88, 11, 1, "", "gather_context_logits"], [88, 11, 1, "", "gather_generation_logits"], [88, 11, 1, "", "gemm_allreduce_plugin"], [88, 11, 1, "", "gpt_attention_plugin"], [88, 11, 1, "", "gpu_weights_percent"], [88, 11, 1, "", "has_position_embedding"], [88, 11, 1, "", "has_token_type_embedding"], [88, 11, 1, "", "head_size"], [88, 11, 1, "", "hidden_size"], [88, 11, 1, "", "kv_cache_type"], [88, 11, 1, "", "language_adapter_config"], [88, 11, 1, "", "layer_types"], [88, 11, 1, "", "lora_plugin"], [88, 11, 1, "", "lora_target_modules"], [88, 11, 1, "", "mamba_conv1d_plugin"], [88, 11, 1, "", "max_batch_size"], [88, 11, 1, "", "max_beam_width"], [88, 11, 1, "", "max_medusa_tokens"], [88, 11, 1, "", "max_prompt_embedding_table_size"], [88, 11, 1, "", "model_name"], [88, 11, 1, "", "num_heads"], [88, 11, 1, "", "num_kv_heads"], [88, 11, 1, "", "num_kv_heads_per_cross_attn_layer"], [88, 11, 1, "", "num_kv_heads_per_layer"], [88, 11, 1, "", "num_layers"], [88, 11, 1, "", "num_medusa_heads"], [88, 11, 1, "", "paged_state"], [88, 11, 1, "", "quant_mode"], [88, 11, 1, "", "redrafter_draft_len_per_beam"], [88, 11, 1, "", "redrafter_num_beams"], [88, 11, 1, "", "remove_input_padding"], [88, 11, 1, "", "rnn_conv_dim_size"], [88, 11, 1, "", "rnn_head_size"], [88, 11, 1, "", "rnn_hidden_size"], [88, 11, 1, "", "skip_cross_attn_blocks"], [88, 11, 1, "", "skip_cross_kv"], [88, 11, 1, "", "state_dtype"], [88, 11, 1, "", "state_size"], [88, 11, 1, "", "tokens_per_block"], [88, 11, 1, "", "trtllm_modules_to_hf_modules"], [88, 11, 1, "", "vocab_size"]], "tensorrt_llm.runtime.ModelRunner": [[88, 13, 1, "", "dtype"], [88, 12, 1, "", "from_dir"], [88, 12, 1, "", "from_engine"], [88, 13, 1, "", "gather_context_logits"], [88, 13, 1, "", "gather_generation_logits"], [88, 12, 1, "", "generate"], [88, 13, 1, "", "hidden_size"], [88, 13, 1, "", "mapping"], [88, 13, 1, "", "max_prompt_embedding_table_size"], [88, 13, 1, "", "max_sequence_length"], [88, 13, 1, "", "num_heads"], [88, 13, 1, "", "num_layers"], [88, 13, 1, "", "remove_input_padding"], [88, 12, 1, "", "serialize_engine"], [88, 13, 1, "", "use_lora_plugin"], [88, 13, 1, "", "vocab_size"], [88, 13, 1, "", "vocab_size_padded"]], "tensorrt_llm.runtime.ModelRunnerCpp": [[88, 13, 1, "", "dtype"], [88, 12, 1, "", "from_dir"], [88, 13, 1, "", "gather_context_logits"], [88, 13, 1, "", "gather_generation_logits"], [88, 12, 1, "", "generate"], [88, 13, 1, "", "hidden_size"], [88, 13, 1, "", "max_prompt_embedding_table_size"], [88, 13, 1, "", "max_sequence_length"], [88, 13, 1, "", "num_heads"], [88, 13, 1, "", "num_layers"], [88, 13, 1, "", "remove_input_padding"], [88, 13, 1, "", "vocab_size"], [88, 13, 1, "", "vocab_size_padded"]], "tensorrt_llm.runtime.MultimodalModelRunner": [[88, 13, 1, "", "audio_engine_dir"], [88, 13, 1, "", "cpp_e2e"], [88, 13, 1, "", "cpp_llm_only"], [88, 12, 1, "", "generate"], [88, 12, 1, "", "get_audio_features"], [88, 12, 1, "", "get_rope_index"], [88, 12, 1, "", "get_visual_features"], [88, 12, 1, "", "init_audio_encoder"], [88, 12, 1, "", "init_image_encoder"], [88, 12, 1, "", "init_llm"], [88, 12, 1, "", "init_processor"], [88, 12, 1, "", "init_tokenizer"], [88, 13, 1, "", "llm_engine_dir"], [88, 12, 1, "", "load_test_audio"], [88, 12, 1, "", "load_test_data"], [88, 12, 1, "", "prepare_position_ids_for_cogvlm"], [88, 12, 1, "", "preprocess"], [88, 12, 1, "", "ptuning_setup"], [88, 12, 1, "", "ptuning_setup_fuyu"], [88, 12, 1, "", "ptuning_setup_llava_next"], [88, 12, 1, "", "ptuning_setup_phi3"], [88, 12, 1, "", "ptuning_setup_pixtral"], [88, 13, 1, "", "python_e2e"], [88, 12, 1, "", "run"], [88, 12, 1, "", "setup_fake_prompts"], [88, 12, 1, "", "setup_fake_prompts_qwen2vl"], [88, 12, 1, "", "setup_fake_prompts_vila"], [88, 12, 1, "", "setup_inputs"], [88, 12, 1, "", "split_prompt_by_images"], [88, 12, 1, "", "tokenizer_image_token"], [88, 12, 1, "", "video_preprocess"], [88, 13, 1, "", "visual_engine_dir"]], "tensorrt_llm.runtime.QWenForCausalLMGenerationSession": [[88, 12, 1, "", "generate"]], "tensorrt_llm.runtime.SamplingConfig": [[88, 11, 1, "", "bad_words_list"], [88, 11, 1, "", "beam_search_diversity_rate"], [88, 11, 1, "", "early_stopping"], [88, 11, 1, "", "end_id"], [88, 11, 1, "", "frequency_penalty"], [88, 11, 1, "", "length_penalty"], [88, 11, 1, "", "max_attention_window_size"], [88, 11, 1, "", "max_new_tokens"], [88, 11, 1, "", "min_length"], [88, 11, 1, "", "min_p"], [88, 11, 1, "", "no_repeat_ngram_size"], [88, 11, 1, "", "num_beams"], [88, 11, 1, "", "num_return_sequences"], [88, 11, 1, "", "output_cum_log_probs"], [88, 11, 1, "", "output_log_probs"], [88, 11, 1, "", "output_sequence_lengths"], [88, 11, 1, "", "pad_id"], [88, 11, 1, "", "presence_penalty"], [88, 11, 1, "", "random_seed"], [88, 11, 1, "", "repetition_penalty"], [88, 11, 1, "", "return_dict"], [88, 11, 1, "", "sink_token_length"], [88, 11, 1, "", "stop_words_list"], [88, 11, 1, "", "temperature"], [88, 11, 1, "", "top_k"], [88, 11, 1, "", "top_p"], [88, 11, 1, "", "top_p_decay"], [88, 11, 1, "", "top_p_min"], [88, 11, 1, "", "top_p_reset_ids"], [88, 12, 1, "", "update"], [88, 11, 1, "", "use_beam_hyps"]], "tensorrt_llm.runtime.Session": [[88, 13, 1, "", "context"], [88, 13, 1, "", "context_mem_size"], [88, 13, 1, "", "engine"], [88, 12, 1, "", "from_engine"], [88, 12, 1, "", "from_serialized_engine"], [88, 12, 1, "", "infer_shapes"], [88, 12, 1, "", "run"], [88, 13, 1, "", "runtime"], [88, 12, 1, "", "set_shapes"]], "tensorrt_llm.runtime.TensorInfo": [[88, 11, 1, "", "dtype"], [88, 11, 1, "", "name"], [88, 12, 1, "", "numel"], [88, 11, 1, "", "shape"], [88, 12, 1, "", "squeeze"], [88, 12, 1, "", "view"]], "trtllm-bench": [[33, 17, 1, "cmdoption-trtllm-bench-log_level", "--log_level"], [33, 17, 1, "cmdoption-trtllm-bench-m", "--model"], [33, 17, 1, "cmdoption-trtllm-bench-model_path", "--model_path"], [33, 17, 1, "cmdoption-trtllm-bench-w", "--workspace"], [33, 17, 1, "cmdoption-trtllm-bench-m", "-m"], [33, 17, 1, "cmdoption-trtllm-bench-w", "-w"]], "trtllm-bench-build": [[33, 17, 1, "cmdoption-trtllm-bench-build-dataset", "--dataset"], [33, 17, 1, "cmdoption-trtllm-bench-build-max_batch_size", "--max_batch_size"], [33, 17, 1, "cmdoption-trtllm-bench-build-max_num_tokens", "--max_num_tokens"], [33, 17, 1, "cmdoption-trtllm-bench-build-max_seq_len", "--max_seq_len"], [33, 17, 1, "cmdoption-trtllm-bench-build-no_weights_loading", "--no_weights_loading"], [33, 17, 1, "cmdoption-trtllm-bench-build-pp", "--pp_size"], [33, 17, 1, "cmdoption-trtllm-bench-build-q", "--quantization"], [33, 17, 1, "cmdoption-trtllm-bench-build-target_input_len", "--target_input_len"], [33, 17, 1, "cmdoption-trtllm-bench-build-target_output_len", "--target_output_len"], [33, 17, 1, "cmdoption-trtllm-bench-build-tp", "--tp_size"], [33, 17, 1, "cmdoption-trtllm-bench-build-trust_remote_code", "--trust_remote_code"], [33, 17, 1, "cmdoption-trtllm-bench-build-pp", "-pp"], [33, 17, 1, "cmdoption-trtllm-bench-build-q", "-q"], [33, 17, 1, "cmdoption-trtllm-bench-build-tp", "-tp"]], "trtllm-bench-latency": [[33, 17, 1, "cmdoption-trtllm-bench-latency-backend", "--backend"], [33, 17, 1, "cmdoption-trtllm-bench-latency-beam_width", "--beam_width"], [33, 17, 1, "cmdoption-trtllm-bench-latency-concurrency", "--concurrency"], [33, 17, 1, "cmdoption-trtllm-bench-latency-dataset", "--dataset"], [33, 17, 1, "cmdoption-trtllm-bench-latency-engine_dir", "--engine_dir"], [33, 17, 1, "cmdoption-trtllm-bench-latency-ep", "--ep"], [33, 17, 1, "cmdoption-trtllm-bench-latency-iteration_log", "--iteration_log"], [33, 17, 1, "cmdoption-trtllm-bench-latency-kv_cache_free_gpu_mem_fraction", "--kv_cache_free_gpu_mem_fraction"], [33, 17, 1, "cmdoption-trtllm-bench-latency-max_input_len", "--max_input_len"], [33, 17, 1, "cmdoption-trtllm-bench-latency-max_seq_len", "--max_seq_len"], [33, 17, 1, "cmdoption-trtllm-bench-latency-medusa_choices", "--medusa_choices"], [33, 17, 1, "cmdoption-trtllm-bench-latency-modality", "--modality"], [33, 17, 1, "cmdoption-trtllm-bench-latency-num_requests", "--num_requests"], [33, 17, 1, "cmdoption-trtllm-bench-latency-pp", "--pp"], [33, 17, 1, "cmdoption-trtllm-bench-latency-report_json", "--report_json"], [33, 17, 1, "cmdoption-trtllm-bench-latency-tp", "--tp"], [33, 17, 1, "cmdoption-trtllm-bench-latency-warmup", "--warmup"]], "trtllm-bench-throughput": [[33, 17, 1, "cmdoption-trtllm-bench-throughput-backend", "--backend"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-beam_width", "--beam_width"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-cluster_size", "--cluster_size"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-concurrency", "--concurrency"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-dataset", "--dataset"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-enable_chunked_context", "--enable_chunked_context"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-engine_dir", "--engine_dir"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-eos_id", "--eos_id"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-ep", "--ep"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-extra_llm_api_options", "--extra_llm_api_options"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-iteration_log", "--iteration_log"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-kv_cache_free_gpu_mem_fraction", "--kv_cache_free_gpu_mem_fraction"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-max_batch_size", "--max_batch_size"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-max_input_len", "--max_input_len"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-max_num_tokens", "--max_num_tokens"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-max_seq_len", "--max_seq_len"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-modality", "--modality"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-num_requests", "--num_requests"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-output_json", "--output_json"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-pp", "--pp"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-report_json", "--report_json"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-request_json", "--request_json"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-scheduler_policy", "--scheduler_policy"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-streaming", "--streaming"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-target_input_len", "--target_input_len"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-target_output_len", "--target_output_len"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-tp", "--tp"], [33, 17, 1, "cmdoption-trtllm-bench-throughput-warmup", "--warmup"]], "trtllm-serve-disaggregated": [[35, 17, 1, "cmdoption-trtllm-serve-disaggregated-c", "--config_file"], [35, 17, 1, "cmdoption-trtllm-serve-disaggregated-l", "--log_level"], [35, 17, 1, "cmdoption-trtllm-serve-disaggregated-m", "--metadata_server_config_file"], [35, 17, 1, "cmdoption-trtllm-serve-disaggregated-r", "--request_timeout"], [35, 17, 1, "cmdoption-trtllm-serve-disaggregated-t", "--server_start_timeout"], [35, 17, 1, "cmdoption-trtllm-serve-disaggregated-c", "-c"], [35, 17, 1, "cmdoption-trtllm-serve-disaggregated-l", "-l"], [35, 17, 1, "cmdoption-trtllm-serve-disaggregated-m", "-m"], [35, 17, 1, "cmdoption-trtllm-serve-disaggregated-r", "-r"], [35, 17, 1, "cmdoption-trtllm-serve-disaggregated-t", "-t"]], "trtllm-serve-disaggregated_mpi_worker": [[35, 17, 1, "cmdoption-trtllm-serve-disaggregated_mpi_worker-c", "--config_file"], [35, 17, 1, "cmdoption-trtllm-serve-disaggregated_mpi_worker-log_level", "--log_level"], [35, 17, 1, "cmdoption-trtllm-serve-disaggregated_mpi_worker-c", "-c"]], "trtllm-serve-serve": [[35, 17, 1, "cmdoption-trtllm-serve-serve-backend", "--backend"], [35, 17, 1, "cmdoption-trtllm-serve-serve-cluster_size", "--cluster_size"], [35, 17, 1, "cmdoption-trtllm-serve-serve-ep_size", "--ep_size"], [35, 17, 1, "cmdoption-trtllm-serve-serve-extra_llm_api_options", "--extra_llm_api_options"], [35, 17, 1, "cmdoption-trtllm-serve-serve-gpus_per_node", "--gpus_per_node"], [35, 17, 1, "cmdoption-trtllm-serve-serve-host", "--host"], [35, 17, 1, "cmdoption-trtllm-serve-serve-kv_cache_free_gpu_memory_fraction", "--kv_cache_free_gpu_memory_fraction"], [35, 17, 1, "cmdoption-trtllm-serve-serve-log_level", "--log_level"], [35, 17, 1, "cmdoption-trtllm-serve-serve-max_batch_size", "--max_batch_size"], [35, 17, 1, "cmdoption-trtllm-serve-serve-max_beam_width", "--max_beam_width"], [35, 17, 1, "cmdoption-trtllm-serve-serve-max_num_tokens", "--max_num_tokens"], [35, 17, 1, "cmdoption-trtllm-serve-serve-max_seq_len", "--max_seq_len"], [35, 17, 1, "cmdoption-trtllm-serve-serve-metadata_server_config_file", "--metadata_server_config_file"], [35, 17, 1, "cmdoption-trtllm-serve-serve-num_postprocess_workers", "--num_postprocess_workers"], [35, 17, 1, "cmdoption-trtllm-serve-serve-port", "--port"], [35, 17, 1, "cmdoption-trtllm-serve-serve-pp_size", "--pp_size"], [35, 17, 1, "cmdoption-trtllm-serve-serve-reasoning_parser", "--reasoning_parser"], [35, 17, 1, "cmdoption-trtllm-serve-serve-server_role", "--server_role"], [35, 17, 1, "cmdoption-trtllm-serve-serve-tokenizer", "--tokenizer"], [35, 17, 1, "cmdoption-trtllm-serve-serve-tp_size", "--tp_size"], [35, 17, 1, "cmdoption-trtllm-serve-serve-trust_remote_code", "--trust_remote_code"], [35, 17, 1, "cmdoption-trtllm-serve-serve-arg-MODEL", "MODEL"]]}, "objnames": {"0": ["c", "macro", "C macro"], "1": ["cpp", "type", "C++ type"], "2": ["cpp", "class", "C++ class"], "3": ["cpp", "function", "C++ function"], "4": ["cpp", "functionParam", "C++ function parameter"], "5": ["cpp", "member", "C++ member"], "6": ["cpp", "enum", "C++ enum"], "7": ["cpp", "enumerator", "C++ enumerator"], "8": ["cpp", "templateParam", "C++ template parameter"], "9": ["py", "module", "Python module"], "10": ["py", "class", "Python class"], "11": ["py", "attribute", "Python attribute"], "12": ["py", "method", "Python method"], "13": ["py", "property", "Python property"], "14": ["py", "function", "Python function"], "15": ["py", "pydantic_field", "Python field"], "16": ["py", "pydantic_validator", "Python validator"], "17": ["std", "cmdoption", "program option"]}, "objtypes": {"0": "c:macro", "1": "cpp:type", "2": "cpp:class", "3": "cpp:function", "4": "cpp:functionParam", "5": "cpp:member", "6": "cpp:enum", "7": "cpp:enumerator", "8": "cpp:templateParam", "9": "py:module", "10": "py:class", "11": "py:attribute", "12": "py:method", "13": "py:property", "14": "py:function", "15": "py:pydantic_field", "16": "py:pydantic_validator", "17": "std:cmdoption"}, "terms": {"": [0, 1, 2, 3, 4, 6, 7, 8, 13, 15, 16, 17, 18, 19, 20, 21, 22, 24, 25, 27, 28, 29, 30, 31, 32, 34, 36, 45, 47, 48, 51, 52, 56, 66, 68, 71, 72, 74, 76, 78, 79, 80, 81, 83, 84, 85, 88, 89, 90, 92, 93, 95, 96, 97, 99, 100, 101, 106], "0": [0, 1, 2, 3, 5, 6, 7, 9, 10, 13, 14, 16, 17, 18, 20, 21, 23, 24, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 38, 39, 40, 41, 42, 43, 44, 45, 47, 48, 49, 50, 51, 52, 54, 55, 56, 57, 58, 59, 60, 62, 63, 65, 66, 67, 68, 70, 71, 72, 73, 74, 75, 76, 80, 81, 82, 83, 84, 85, 88, 89, 91, 92, 94, 95, 98, 99, 105, 107], "00": [17, 27, 53, 54, 55, 74, 75, 76, 95], "000": [21, 74], "0000": [74, 76], "0007503032684326172": 35, "0012": 74, "0017": 75, "003": 75, "0047": 95, "005": 75, "0070": 95, "0071": 95, "0096": 95, "00978": 93, "01": [26, 27, 53, 54, 55, 59, 74, 75, 92, 96], "0105": 21, "014": 24, "0158": 76, "016": 75, "0162": 78, "0165": 80, "017": 75, "02": [75, 96], "021": 75, "022": 75, "0235": 95, "0260": 95, "0273": 95, "028": 75, "0294": 95, "03": [80, 95, 96], "032": 27, "0339": 75, "03762": 83, "03961": 4, "03x": 28, "04": [68, 75, 96, 98, 103], "043": 75, "0449": 95, "045471": 30, "0461": 21, "0463": 75, "05": [75, 83, 84, 85, 94, 95, 96], "05100": 83, "0523": 95, "055": 75, "0554": 76, "0560": 95, "0563": 75, "06": [27, 74, 75, 83, 84], "0630": 95, "0669": 21, "0675": 21, "068": 75, "0682": 95, "0689e": 74, "07": [26, 27, 75, 96], "0704": 76, "0713": 95, "0723": 95, "0732": 95, "0772": 21, "0776": 95, "08": [27, 75, 80], "0804": 95, "081947": 30, "082": 75, "0838": [21, 75], "0881": 81, "089": 75, "09": [27, 95], "0903": 95, "0910": 95, "092": 75, "092314": 30, "092623": 30, "093256": 30, "09353": 10, "0964": 75, "09685": 10, "097": 75, "09f": [0, 1], "0e": 6, "0f": [0, 6, 71], "0rc1": 74, "0rc4": [67, 89], "0u": 1, "0x": 23, "0x0000000000000000": 96, "1": [0, 1, 2, 3, 5, 6, 7, 9, 10, 13, 14, 16, 18, 20, 22, 23, 24, 25, 26, 27, 28, 29, 31, 33, 34, 35, 38, 40, 41, 42, 43, 44, 45, 47, 48, 49, 50, 51, 52, 53, 54, 56, 57, 58, 59, 60, 62, 63, 65, 67, 68, 71, 73, 74, 76, 77, 78, 80, 82, 83, 84, 85, 87, 88, 89, 90, 91, 94, 95, 97, 103, 104, 105, 106], "10": [0, 9, 10, 13, 21, 26, 27, 28, 30, 31, 35, 41, 43, 52, 59, 65, 68, 71, 74, 75, 76, 78, 81, 83, 92, 94, 95], "100": [0, 9, 12, 21, 30, 35, 43, 54, 57, 73, 74, 76, 89], "1000": [0, 32, 73, 74, 75, 76], "10000": [83, 84, 85], "1003": 96, "100gb": 29, "101": 9, "101029": 30, "101978": 75, "102": [9, 23], "1024": [1, 6, 16, 21, 24, 26, 30, 32, 34, 41, 57, 71, 74, 75, 76, 80, 83, 84, 95], "102415": 74, "103": [9, 30], "104": 96, "10438": 93, "1045": 95, "1047": 74, "1050": 95, "1051": 76, "1059": 74, "106563": 75, "1072": 95, "107501": 75, "10774": 0, "1079": 20, "108": 75, "1082": 95, "10858": 41, "109": 30, "10b": [83, 96], "10m": 23, "11": [0, 10, 13, 21, 24, 26, 30, 31, 65, 74, 75, 78, 83, 94, 95], "11023": 74, "110804": 75, "110b": 96, "111": [23, 27], "111302": 75, "111618": 75, "111668": 75, "1118": 96, "1123": 96, "1134": 92, "113420": 30, "1135": 95, "114": 30, "1141": 95, "114688": 21, "1148": 96, "11489": 21, "11490": 74, "115": 30, "1151": 21, "115378": 30, "115716": 75, "1160": [35, 42], "117": 75, "1178": 74, "1181": 96, "1183": 96, "119": [30, 74], "11943": 74, "11947": 41, "1196": 21, "119648": 30, "11b": [94, 96], "11x": 31, "12": [0, 10, 16, 23, 27, 30, 31, 32, 41, 65, 68, 74, 75, 78, 80, 83, 95, 103], "120": 30, "1212": 95, "121847": 74, "1219": 21, "122": 74, "1225": 83, "12288": 74, "123": [35, 43, 44], "1234": [71, 85], "1239": 96, "1242": 96, "1248": 96, "125": [30, 74], "1252": [20, 74], "1256": 96, "1257": 21, "125m": [13, 16], "126": 74, "1267": 96, "127": 83, "1272": 95, "128": [0, 1, 5, 9, 10, 14, 17, 21, 22, 23, 24, 25, 26, 27, 30, 35, 41, 43, 44, 54, 71, 74, 75, 85, 96], "1284": 96, "1287": 78, "128798": 71, "128799": 71, "128e": 32, "129": 30, "1290": 95, "1291504": 76, "1293": 20, "12945": 21, "129498": 21, "13": [5, 10, 25, 29, 30, 31, 65, 74, 75, 76, 83, 95], "1300": 47, "131072": [74, 76], "13195": 74, "132": [74, 75], "1323": 96, "1328": 96, "1329": 96, "133": 96, "13368": 74, "1337": 96, "1341": 21, "1343": 96, "1344": 96, "13525": 74, "13598": 74, "137": 74, "1378": 95, "138": 30, "139": 75, "1392": 96, "13b": 23, "14": [10, 16, 26, 30, 31, 65, 74, 75, 78, 80, 81, 95], "140g": 20, "141": 24, "1418": 74, "141gb": [22, 75], "142": [29, 30], "1424": 96, "1436": [21, 96], "1437": 95, "144": 78, "1446": 96, "1447": 96, "14480": 74, "1449": 96, "145": [80, 81], "1459": 95, "146": [80, 81], "1467": 96, "147": [76, 78, 80, 81], "1480": 96, "1486": 96, "149": [95, 96], "15": [10, 27, 30, 31, 32, 65, 74, 75, 81, 83, 95], "150": 73, "1500": 75, "15043": 41, "1514": 96, "152": [30, 74], "1529": 96, "1534": 96, "1535": 96, "1536": 21, "1537": 96, "1539": 96, "154": 27, "1552": 96, "1556": 95, "15585": 74, "1562": 96, "1564": [76, 80, 81], "158": 21, "1583": 96, "1584": 21, "1585": 76, "1589": 96, "1590": 96, "1597": 78, "15u": 29, "16": [0, 5, 10, 11, 13, 17, 21, 23, 26, 27, 30, 31, 35, 38, 40, 53, 54, 55, 65, 66, 74, 75, 76, 77, 83, 84, 85, 92, 93, 95], "160": [30, 96], "1607": 74, "161": [35, 42, 74], "162": 30, "1625": 78, "1626": 96, "163": 22, "1637": 96, "16384": [78, 80], "164": [27, 30], "1642": 96, "1650": 96, "1660": 96, "1669": 96, "167": [74, 75], "1672": 95, "1674": 96, "1675": 96, "167507": 30, "1676": 96, "168": 27, "16e": 94, "16x": [28, 92], "17": [0, 10, 21, 30, 32, 65, 74, 75, 80, 95, 98], "1706": 83, "171": 30, "1721": 95, "1723": 96, "172321": 21, "17233": 21, "173": 27, "1732": 96, "17323": 93, "1738": 96, "174": 75, "1741966075": 89, "1742": 96, "17453": 34, "17453v3": 1, "1748018634": 32, "175": 75, "175b": 24, "176": 74, "1762": 96, "1799": 96, "17b": [32, 94], "18": [10, 29, 30, 65, 72, 74, 75, 95], "180": [27, 92], "180000000": 0, "1806": 21, "180b": [26, 74], "1815": 96, "181540": 21, "182": 75, "1822": 41, "183": 75, "1834": 96, "184": 75, "185": [23, 74], "1851": 96, "18527": 41, "18563": 74, "1861": 81, "1866": 81, "187": 30, "1885": 76, "1886": 96, "1897": 96, "19": [21, 30, 65, 75, 81, 95], "1909": 96, "191": 75, "192": [22, 30], "1926": 96, "1937": 96, "1939": 96, "1944": 80, "1950": 30, "1953": 96, "1959": 74, "1963": 30, "198": 27, "1985": 96, "1987": 96, "1993": 95, "1999": 96, "1_405b": 17, "1_70b": 17, "1b": [31, 35, 38, 40, 43, 45, 47, 48, 49, 50, 51, 52, 56, 57, 58, 60, 62, 68, 70, 89], "1d": [5, 83, 88], "1e": [16, 83, 84, 85], "1e20f": 1, "1g": 95, "1gb": 2, "1k": [21, 27, 28, 29], "1m": 81, "1st": [23, 83, 92], "1u": [0, 1], "1x": 27, "1xh200": 22, "1xtep": 31, "1ytic": 96, "2": [0, 1, 3, 5, 6, 7, 8, 9, 10, 11, 13, 14, 16, 17, 20, 22, 23, 24, 26, 27, 28, 29, 31, 35, 50, 51, 52, 53, 54, 55, 56, 57, 65, 68, 71, 74, 75, 77, 78, 80, 81, 83, 85, 88, 90, 93, 94, 95, 97, 106], "20": [1, 6, 13, 14, 29, 30, 31, 35, 58, 60, 62, 63, 74, 75, 76, 80, 83, 88, 95], "200": [24, 30, 32, 52, 71, 88], "2000": [29, 75], "20000": [71, 75], "200mb": 29, "2017": 80, "2018": 96, "202": 30, "2023": [22, 95], "2024": [27, 103], "2025": [21, 27, 74], "2028": 96, "203": 75, "2033": 81, "2039": 96, "204": [27, 75], "2040": 96, "2042": 21, "2044": [80, 81], "2045": 80, "2048": [16, 21, 22, 24, 25, 29, 33, 34, 71, 74, 75, 76, 78, 79, 80, 81, 85, 88, 95, 96], "205": 30, "2056": 96, "206": 75, "20627": 41, "20685": 74, "2079": 95, "208": 75, "2081": [78, 80, 96], "2087": 96, "2089": 75, "209": [30, 75], "20b": 96, "21": [13, 21, 26, 27, 30, 75, 80, 95, 96], "2101": 4, "2102": 75, "2106": 10, "2107": 95, "210g": 20, "211": 27, "2113": 96, "212": 30, "2135": 96, "2152": 96, "2158": 75, "2168": 21, "2169": 96, "21747": 74, "2176": 75, "21764": 74, "2182": 96, "2191": 96, "22": [29, 30, 37, 75, 83, 95], "22000": 75, "22056": 74, "221": 74, "2210": 93, "2211": [83, 93], "2219": 96, "22213": 74, "2225": 95, "2232": 96, "224": 84, "2243": 96, "2263": 96, "227": 25, "2288": 96, "2294": 96, "22x": 28, "23": [30, 74, 75, 95, 96], "2305": 95, "2306": 93, "2309": [1, 34], "232": [25, 30], "234": 30, "2352": 96, "2357": 96, "236": 27, "2366": 96, "2370": 96, "2373": 96, "2379": 96, "2388": 96, "239": 27, "2397": 74, "24": [0, 30, 68, 74, 75, 95, 96, 98], "240": 75, "2401": 0, "2402": 10, "24189": 75, "2419": 96, "242": 75, "2425": 96, "243": 30, "2439": 96, "245": 27, "2458": 96, "246": 30, "2461": 80, "2466": 80, "2473": 96, "2474": [78, 80], "2484": 96, "2485": 96, "2487": 75, "249": 27, "24mib": 30, "25": [25, 27, 30, 31, 74, 75, 94, 96], "250": [21, 27, 30], "2500": 75, "25032": 74, "251": 30, "252u": 29, "253": [27, 75], "2552": 96, "256": [1, 21, 22, 25, 29, 30, 71, 74, 75, 83, 95, 96], "25603": 74, "2573": 96, "2581": [78, 80], "2590780": 74, "259840": 92, "26": [30, 74, 75, 78, 89], "260": 75, "2602": 41, "2628": [80, 81], "263": [22, 41], "2640": 81, "2649": 95, "2671": 21, "2677": 96, "26778": 74, "2679": 78, "2685": 96, "2691": 96, "27": [75, 96], "270": 75, "2712": 96, "274": [21, 96], "2742": 76, "275": 96, "2755": 21, "276": 75, "2766684": 21, "278": [41, 75], "2782": 96, "2787": 96, "2796": 96, "28": [27, 74, 75, 95], "2820": 95, "28390": 74, "287113": 74, "288": [30, 96], "29": [75, 92], "290": 30, "292": 75, "2939": 95, "294": 75, "297": 41, "29892": 41, "299": [27, 74], "29962": 41, "2998": 95, "2b": [20, 65, 74], "2cta": 29, "2d": [13, 83, 84, 93], "2k": [21, 27, 28, 29], "2m": 81, "2nd": 83, "2u": 1, "2x": [23, 24, 31], "2xdep": 31, "3": [0, 1, 3, 5, 7, 9, 10, 18, 22, 23, 24, 26, 27, 28, 29, 45, 48, 50, 56, 58, 59, 65, 68, 70, 71, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 88, 89, 91, 95, 96, 99, 102, 104, 105], "30": [0, 13, 21, 27, 31, 32, 71, 75, 76, 78, 81, 83, 92], "300": [25, 30, 74], "3000": [74, 75], "30000": 75, "30065": 74, "3019": 74, "3021": 21, "3022": 74, "303": 24, "3031": 80, "304": 41, "3040": [76, 80, 81], "306": 41, "3072": 21, "30990": 74, "30b": 26, "30x": 26, "31": [11, 75, 76, 80, 81], "311": 75, "3132": 74, "315": [27, 75], "318": 75, "32": [1, 5, 9, 11, 21, 23, 24, 30, 31, 34, 41, 71, 74, 75, 76, 83, 84, 85, 88, 89, 92, 93, 95, 96], "3201": 76, "321": 74, "322": 41, "3276": [76, 80, 81], "32768": 83, "3291": 95, "32b": 96, "32k": 96, "32x": 26, "33": [75, 95], "332": 75, "3328": 95, "332826": 21, "3338": 76, "338": [27, 41], "3389": 78, "339447": 30, "339981": 30, "33x": 28, "34": [21, 30, 75], "340": [27, 75], "341": [24, 30], "3442": 95, "3445": 95, "3452": [74, 95], "3476": 21, "348gib": 30, "349": 24, "34b": 96, "35": [0, 71, 75], "3504": 30, "351": 75, "3555": 95, "357": 75, "36": [27, 30, 75, 77, 78], "36384": 21, "3671": 74, "367714": 30, "368": 27, "37": [30, 74], "370": 75, "371": 75, "374": 75, "375": 75, "3763": 27, "379": 75, "38": [74, 75], "381": 30, "384": [21, 75], "3863": 75, "387": 75, "387b12598a9e": 74, "3887": 95, "39": [27, 75], "3914": 75, "3936": 74, "3977": 95, "399": 75, "3_1": 94, "3_3": 94, "3b": [35, 39, 44, 61], "3d": [5, 83, 88], "3rd": 83, "3u": 1, "3x": [26, 27, 29], "4": [0, 1, 2, 7, 9, 10, 11, 13, 17, 20, 24, 26, 27, 28, 29, 30, 31, 35, 41, 53, 54, 55, 57, 65, 71, 74, 75, 76, 78, 79, 80, 81, 82, 83, 85, 88, 89, 92, 93, 94, 95, 96, 97, 103], "40": [6, 58, 75, 78, 83, 96], "400": [29, 30], "4000": 29, "403": 96, "405b": [74, 77], "4060": 92, "4066": 41, "408": 75, "408348": 30, "4089": 81, "4096": [22, 29, 41, 74, 75, 78, 83, 84, 88], "40b": 26, "40gb": 34, "40x": 26, "41": 75, "41020": 74, "411": 74, "4117e": 74, "4133": 81, "41375": 74, "414": 21, "41607": 74, "4168": 21, "4192": 95, "42": [30, 74, 75], "420": 33, "4224": 75, "4248": 78, "4265": 74, "427": [74, 75], "4280": 27, "43": [75, 89, 92], "43146": 21, "433": 75, "437": 75, "438": 75, "4384": 30, "44": [30, 75, 92], "4408": 41, "442": 75, "4439": 74, "4456": 75, "447": 75, "448": 75, "449": 96, "4493": [80, 81], "4495": 30, "4497": 75, "44x": 26, "45": [9, 30, 75, 94, 96], "450": 75, "45000000000": 9, "453": 75, "4548": 21, "4566": 75, "458676": 30, "459": 75, "46": 26, "4600": 29, "461014": 30, "462": 75, "463": 75, "464": 30, "4653": 41, "4656": 75, "466": 75, "4667": 75, "47": [26, 30, 78], "4701": 74, "471": 75, "472": 41, "475": 75, "477": 75, "478": 96, "47x": 26, "48": [30, 75, 78, 92, 96], "480gb": 30, "481": [23, 75], "482": 96, "488": 75, "49": [30, 75, 78], "491": 30, "49152": 21, "495": 75, "496": 11, "4963": 74, "4963654": 90, "498043": 30, "49b": 94, "4b": 96, "4bit": 22, "4gb": 29, "4u": 1, "4x": [22, 23, 24, 31], "5": [0, 1, 9, 10, 13, 14, 16, 22, 23, 24, 26, 27, 28, 29, 30, 31, 35, 39, 44, 47, 58, 61, 71, 74, 75, 80, 83, 85, 88, 94, 95, 96, 105], "50": [0, 26, 30, 31, 47, 57, 58, 71, 74, 75, 96], "500": [27, 29, 75], "5000": 75, "500000": 85, "5007": 41, "500m": 26, "50272": 16, "505143404006958": 35, "5064": 75, "5073": 95, "50m": 30, "51": 75, "512": [1, 10, 14, 21, 24, 25, 33, 57, 71, 74, 75, 78, 80, 85], "5120": 21, "512mb": 2, "514": 75, "518": [41, 75], "51b": [94, 96], "51x": 26, "52": 30, "52269": 75, "524": 75, "525": 75, "526": [75, 96], "52667": 75, "529": 75, "529514": 30, "5299": 78, "53": [30, 74, 80, 81], "5305": 78, "531": 75, "535": 32, "537602": 30, "5393": 21, "54": [26, 75], "540": 74, "543": 75, "544": 75, "5443839": 21, "54576": 21, "5496": 78, "5497": 75, "55": [26, 74, 75], "5500": 75, "5510": 74, "5514": 74, "552": 32, "5530": 75, "554": 75, "557": 75, "559": 75, "56": [26, 30, 75], "560": 22, "562": [10, 14], "564": 30, "56401920000": 35, "564272": 30, "565": 75, "567": 75, "568": [74, 75], "57": [30, 74, 75], "570": 30, "571": 75, "572": 75, "5739": 21, "5742": [78, 80], "579": 75, "58": [27, 30, 75, 80], "580": 75, "5821": 75, "5830": 95, "5874": 95, "5877": 78, "5879": 95, "588": 75, "58x": 27, "59": [30, 74], "590": [41, 75], "5918": 95, "5957": 95, "5976": 78, "598": 75, "5980": 78, "5b": 96, "5th": [29, 83], "5u": 1, "5x": [23, 26, 27, 31], "6": [0, 1, 6, 9, 10, 13, 24, 26, 27, 28, 29, 30, 31, 35, 71, 75, 83, 88, 94, 95, 96], "60": [0, 30, 75], "600": 36, "6000": 74, "602": 75, "6049": 78, "6059": 74, "6064": 95, "608": 75, "61": 75, "610": 75, "6100": 21, "612328": 30, "6157": 95, "618": 75, "61954812": 91, "62": [27, 75, 80], "623219": 30, "6255": 95, "626": 41, "6299": 95, "63": [66, 74, 75, 80, 85, 92], "630": 75, "63266": 76, "63307": 76, "63308": 76, "63331": 76, "63374": 76, "634": 75, "63456": 76, "6345624": 76, "6372": 78, "6376": 21, "639": 96, "64": [0, 1, 5, 6, 16, 21, 23, 24, 30, 34, 35, 39, 44, 56, 61, 74, 75, 80, 83, 84, 85, 92, 96], "640": [22, 75], "640gb": 29, "6452": 81, "6475": 80, "649": 96, "64x": 27, "65": [68, 75], "65024": 95, "65100": 21, "651199": 30, "6523": 81, "653": 75, "654": 24, "6550": 78, "6554": 80, "656": 75, "657": 75, "659": 75, "6591": 74, "66": [27, 75], "661": 75, "6628": [80, 81], "6678": 92, "6684": 81, "6695": 92, "67": [26, 27, 30, 75], "671": 21, "67108864": [32, 66], "671b": 28, "673": 96, "675": 74, "6753e": 74, "6769": 80, "679": 23, "68": [26, 27, 75, 81], "682": 75, "6825": 74, "683": 75, "684": 27, "685": 75, "6852": [78, 80], "686": 75, "6862": 74, "6890": 95, "69": [26, 27, 30, 75, 81, 89], "6925": 74, "6938": 41, "695": 96, "696": 75, "697": 29, "6975": 78, "6976": [76, 80, 81], "698": 75, "6a": 22, "6b": [23, 74, 83, 96], "6x": [24, 31], "7": [0, 1, 9, 10, 22, 23, 26, 27, 28, 29, 30, 31, 58, 65, 66, 68, 74, 75, 76, 83, 88, 95], "70": [0, 26, 30, 81, 92], "700": 36, "7000": 74, "701": 96, "7031": 78, "704": 75, "705": [29, 96], "706": 75, "7063": 74, "707": 75, "7072": 75, "709": 74, "7090": 95, "70b": [5, 20, 24, 26, 76, 78, 79, 80, 81, 82, 94, 96], "70g": 20, "71": [27, 74, 75], "711": 75, "712": 75, "7134": 95, "7136": 76, "714": 75, "7144": 95, "7168": [21, 27, 29], "717": 75, "717498": 30, "7187": 75, "7188": 21, "72": [30, 75, 77], "7206": 21, "722": 75, "727": 75, "728516": 30, "72b": [94, 96], "73": [27, 75], "732": 75, "734": 75, "736": 75, "737": 75, "7382": 75, "739": 96, "73x": 31, "74": [27, 75], "741": [75, 96], "742": 75, "745": 75, "7456": 21, "74561": 21, "747": 75, "7480": 76, "75": [26, 30, 32, 74, 96], "750": [24, 75], "7502": 76, "7520": 21, "755": 36, "7584": 21, "75903": 75, "76": 75, "7607": 80, "7621": 75, "7638": [76, 80, 81], "7657": 21, "767": 75, "768": [16, 84], "77": [30, 75], "772": 75, "7743": 76, "7770": 76, "78": [27, 75, 78], "780": 74, "7842": 78, "78509": 75, "7876": 80, "79": [74, 92], "7900": 95, "791": 30, "792": 30, "7933": 80, "794": [75, 96], "7949": 95, "7977": 78, "7a": 22, "7b": [10, 13, 14, 26, 35, 63, 74, 75, 89, 94, 96], "7x": [23, 27, 31], "8": [0, 1, 5, 9, 10, 11, 16, 17, 20, 21, 22, 24, 25, 26, 27, 28, 29, 30, 31, 32, 34, 35, 41, 42, 45, 48, 49, 50, 51, 52, 53, 54, 55, 57, 58, 65, 68, 71, 74, 75, 76, 77, 78, 82, 83, 84, 85, 89, 92, 93, 95, 97, 105], "80": [0, 6, 24, 27, 29, 66, 75, 96], "800": [22, 75, 96], "8000": [31, 32, 35, 38, 39, 40, 42, 43, 44, 60, 61, 62, 63, 89], "8001": 31, "8002": [31, 74], "8003": 31, "8004": 31, "8005": 75, "803": 22, "8048": 74, "80gb": [23, 26, 34, 75, 76, 78, 79], "81": [27, 30, 75, 78], "810": 75, "8140": 21, "8149": 95, "8179": 95, "819": 24, "8192": [34, 71, 74, 75, 76, 80, 83, 84, 95, 96], "82": [27, 75, 78], "820": 74, "8212": 1, "8218": 95, "822": 75, "8225": 78, "825": 96, "8259": 74, "83": 75, "8307": 81, "8351": 74, "838": 75, "84": [27, 75], "840": 75, "841": 75, "8441": 74, "85": [21, 26, 57, 74, 75, 96], "850": 75, "851": 75, "854": 75, "86": [66, 75], "863": 74, "866": 75, "867": 75, "8672": 95, "87": [26, 30, 75], "8779": 95, "88": [75, 78, 81], "8804": 76, "880676": 30, "88226": 74, "8828": 95, "8841": 78, "89": [26, 27, 66, 75, 94], "893": 75, "8932": 74, "8958": 81, "896": [21, 75], "8a": 25, "8b": [45, 48, 59, 68, 70, 74, 89, 94, 104, 105], "8bit": 23, "8tb": 24, "8x": [29, 31, 32], "8x7b": [4, 74, 94, 96], "8xb200": [27, 32], "8xgpu": 29, "8xh100": 25, "8xh200": 22, "9": [0, 1, 10, 13, 20, 23, 27, 28, 30, 31, 58, 65, 75, 78, 83, 91, 95], "90": [0, 12, 21, 30, 58, 66, 71, 74, 75, 76, 78, 82, 92], "9007": 21, "9028": 95, "907": 23, "9087": 81, "91": 75, "910": 75, "9101": 75, "911": 75, "9115": 81, "912656": 21, "913": 75, "9184": 78, "9197": 21, "92": [27, 75], "920": 75, "9203": 78, "9214": 75, "924": 16, "925": 75, "9263": 21, "9274": 76, "93": [21, 30, 75], "935": 96, "9353e": 76, "9379": 21, "94": 75, "94022": 75, "941": [22, 25], "944": 75, "946": 22, "947": 75, "948": 30, "9494": 80, "95": [35, 42, 45, 48, 49, 50, 51, 52, 57, 58, 68, 75, 76, 82, 89], "9521": 95, "953": 75, "9537": 78, "954": 29, "955200": 30, "956": 75, "957": 75, "96": [22, 27, 29, 75, 78, 96], "960": 22, "9606": 29, "960gb": 30, "961": 75, "9613": 29, "9623": 80, "9629": 29, "963": 75, "9639": 75, "96583": 75, "967": 96, "9692": 95, "97": [29, 74, 75, 78], "970": 75, "976442": 30, "98": 75, "983": 96, "987": 96, "9898": 21, "99": [9, 27, 30, 36, 75], "990": 75, "991": 75, "992": 96, "9928": 81, "9938": 21, "9982": [80, 81], "9f": 0, "9x": [24, 25], "A": [0, 1, 2, 3, 5, 6, 8, 10, 13, 16, 17, 20, 21, 26, 27, 30, 32, 52, 53, 54, 55, 56, 70, 71, 73, 74, 75, 83, 88, 90, 96, 97, 99, 101], "AND": 83, "And": [13, 20, 28, 29, 30, 83, 84, 92], "As": [4, 5, 7, 10, 13, 17, 19, 28, 30, 31, 41, 66, 78, 81, 82, 83, 92, 93, 95, 101, 106], "At": [15, 29, 56, 78, 84, 92, 103], "Being": 90, "But": [5, 8, 30, 72], "By": [0, 1, 2, 6, 12, 13, 27, 29, 30, 31, 41, 66, 71, 74, 78, 81, 83, 91, 95, 101], "For": [0, 1, 2, 3, 5, 6, 7, 8, 9, 10, 12, 13, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 34, 35, 41, 45, 53, 54, 55, 64, 66, 70, 74, 75, 76, 77, 78, 80, 81, 82, 83, 88, 89, 90, 92, 95, 96, 97, 99, 100, 101, 106, 107], "If": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 16, 17, 18, 20, 26, 28, 30, 32, 33, 34, 35, 36, 37, 52, 66, 67, 68, 70, 71, 72, 74, 76, 77, 78, 80, 81, 82, 83, 85, 88, 89, 91, 92, 94, 95, 96, 99, 101, 106, 107], "In": [0, 1, 7, 8, 11, 13, 17, 18, 20, 21, 23, 26, 27, 28, 29, 30, 31, 32, 37, 41, 56, 65, 66, 67, 74, 75, 76, 77, 78, 80, 81, 83, 89, 91, 92, 93, 94, 95, 96, 101, 105, 106, 107], "It": [0, 1, 3, 5, 6, 7, 10, 13, 15, 17, 18, 19, 21, 22, 25, 26, 27, 28, 29, 30, 33, 34, 41, 52, 56, 58, 66, 70, 71, 72, 74, 75, 78, 79, 80, 81, 82, 83, 89, 91, 93, 95, 97, 99, 100, 101, 107], "Its": [5, 83, 101], "NO": 102, "NOT": 83, "No": [0, 2, 9, 30, 56, 74, 76, 102], "Not": [1, 26], "ON": [74, 78, 80, 81], "OR": 83, "Of": [27, 96], "On": [5, 9, 21, 30, 66, 68, 73, 77, 81, 83, 96], "One": [16, 17, 30, 80, 83, 95, 100, 102], "Or": [83, 88, 104], "That": [3, 5, 6, 9, 17, 72, 78, 83, 90], "The": [0, 1, 2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 26, 27, 28, 29, 31, 32, 33, 34, 35, 41, 45, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 65, 66, 68, 70, 71, 73, 74, 75, 76, 77, 78, 80, 81, 82, 83, 84, 85, 86, 88, 89, 90, 91, 92, 94, 95, 96, 97, 98, 99, 100, 101, 103, 104, 105, 106, 107], "Their": [29, 32], "Then": [10, 20, 28, 30, 35, 36, 70, 74, 76, 83, 99, 106], "There": [2, 5, 6, 7, 8, 9, 10, 16, 20, 24, 27, 28, 29, 30, 31, 41, 66, 68, 70, 83, 86, 89, 92, 93, 95, 96, 100, 101, 106, 107], "These": [2, 13, 20, 22, 24, 25, 27, 29, 30, 31, 41, 74, 76, 77, 84, 86, 89, 91, 96], "To": [3, 5, 9, 10, 12, 13, 14, 17, 18, 19, 20, 21, 24, 27, 28, 30, 31, 32, 66, 70, 71, 72, 73, 74, 75, 78, 80, 81, 82, 83, 89, 90, 92, 93, 96, 98, 99, 101, 103, 106, 107], "WITH": 58, "Will": 0, "With": [5, 6, 13, 17, 30, 31, 36, 41, 65, 74], "_": [0, 3, 18, 86], "__all__": 99, "__call__": 52, "__init__": [7, 15, 17, 18, 52, 71, 74, 95, 96, 99, 101, 107], "__main__": [45, 47, 48, 49, 50, 51, 52, 56, 57, 58, 59, 68, 70, 76, 78, 81, 82, 89, 96, 99], "__name__": [45, 47, 48, 49, 50, 51, 52, 56, 57, 58, 59, 68, 76, 78, 81, 82, 89, 96, 99], "__post_init__": 96, "__repr__": 96, "__version__": [67, 89], "_autodeploi": 33, "_capac": 1, "_context_logits_auto_en": 71, "_cpp_gen": 3, "_create_tensor": 17, "_explicitly_disable_gemm_plugin": 86, "_generation_logits_auto_en": 71, "_handl": 1, "_mark_output": 95, "_mpi_sess": 71, "_note": 5, "_path": 21, "_postproc_param": 71, "_postprocess_result": 71, "_return_log_prob": 71, "_run": 95, "_runtim": 88, "_static": 17, "_str_to_trt_dtype_dict": 83, "_torch": [71, 74, 96, 98, 99, 101, 104], "_torchllm": 71, "_unsign": 1, "_util": 83, "a10": 34, "a100": [6, 20, 34, 90], "a100x": 90, "a10g": 34, "a2": 96, "a30": 34, "a40": 34, "a8": 93, "a_": 83, "a_1": 83, "a_2": 83, "a_n": 83, "a_sf": 83, "aarch64": 94, "ab": [10, 34, 83, 93], "abbrevi": 35, "abc": 28, "abcd": 28, "abi": [66, 96], "abil": [72, 74], "abl": [5, 23, 27, 30, 68, 74, 80, 83, 96], "ablat": [28, 29], "abnorm": [30, 96], "abort": [71, 96], "about": [0, 1, 3, 20, 21, 22, 23, 25, 26, 29, 30, 31, 56, 58, 65, 74, 76, 78, 79, 81, 83, 89, 92, 95, 96], "abov": [10, 11, 17, 20, 21, 26, 29, 30, 31, 32, 41, 66, 68, 74, 75, 76, 78, 81, 91, 92], "absenc": [6, 31], "absorb": 27, "abstract": [81, 84], "ac": 96, "acc": 83, "acceler": [5, 11, 13, 23, 24, 25, 26, 30, 34, 72], "accept": [0, 1, 13, 21, 30, 32, 33, 41, 45, 48, 49, 50, 51, 66, 68, 70, 71, 76, 78, 83, 88, 89, 90, 94, 96, 101], "accept_length": 88, "acceptancelength": 0, "acceptancer": 0, "acceptancethreshold": 0, "acceptedlen": 1, "acceptedlengthscumsum": 1, "acceptedpath": 1, "acceptedpathid": 1, "acceptedtoken": 1, "acceptedtokenslen": 1, "access": [3, 30, 32, 37, 47, 71, 74, 76, 83, 89, 91, 96], "accessor": 1, "accommod": [4, 31, 100, 106], "accomplish": 77, "accord": [5, 18, 32, 83, 84, 101], "accordingli": 18, "account": [17, 21, 31, 36, 53, 54, 55, 66], "accumul": [0, 5, 6, 30, 34, 52, 71, 83, 88, 89], "accur": [2, 22, 28, 47, 74, 76, 96], "accuraci": [21, 22, 27, 29, 34, 78, 82, 83, 93, 96], "achiev": [13, 21, 22, 26, 27, 29, 30, 31, 66, 75, 76, 78, 80, 82, 99], "across": [4, 5, 6, 7, 17, 18, 24, 27, 30, 31, 32, 35, 75, 77, 78, 80, 81, 83, 88, 90, 97], "act": [27, 30, 31], "act_fn": 84, "act_typ": [17, 83], "activ": [0, 1, 5, 7, 17, 22, 23, 26, 27, 29, 30, 31, 34, 77, 83, 93, 94, 96, 107], "activation_scaling_factor": 16, "activationtyp": [17, 83], "active_request": 107, "actual": [7, 8, 13, 21, 26, 27, 28, 30, 32, 33, 34, 78, 80, 81, 82, 96, 97, 106], "ad": [1, 5, 6, 7, 9, 13, 14, 20, 21, 28, 29, 31, 37, 65, 73, 77, 80, 81, 83, 85, 88, 96, 98, 100], "ada": [5, 26, 66, 72, 78, 94, 96], "adalayernorm": 84, "adalayernormcontinu": 84, "adalayernormzero": 84, "adalayernormzerosingl": 84, "adapt": [0, 10, 28, 30, 33, 46, 71, 83, 84, 96, 99], "adapter_s": 10, "adapters": 1, "add": [1, 3, 5, 7, 10, 15, 16, 17, 20, 28, 36, 37, 66, 70, 71, 74, 76, 78, 81, 83, 88, 90, 91, 95, 96, 99, 106], "add_activ": 17, "add_argu": 57, "add_bias_linear": 85, "add_generation_prompt": 27, "add_input": 83, "add_output": 83, "add_padding_request": 106, "add_prefix_spac": 52, "add_qkv_bia": 85, "add_rmsnorm": 27, "add_sequ": 88, "add_special_token": [27, 52, 71, 88, 96], "addcumlogprob": 96, "added_kv_proj_dim": 84, "added_proj_bia": 84, "addit": [0, 5, 6, 10, 13, 17, 20, 24, 28, 29, 30, 31, 35, 41, 47, 66, 71, 74, 75, 77, 78, 80, 83, 84, 93, 94, 95, 96, 101, 106], "addition": [2, 74, 76, 78, 81, 99, 101], "additional_model_output": 71, "additional_opt": 55, "additionalmodeloutput": [0, 3, 71], "additionaloutput": [0, 3], "addr": 0, "address": [1, 18, 21, 26, 27, 29, 30, 70, 81, 92, 96], "addresswiths": 1, "adequ": 84, "adher": 47, "adjust": [30, 31, 32, 52, 53, 71, 74, 76, 92, 107], "admin": 68, "adopt": [6, 20, 30], "advanc": [13, 17, 25, 27, 28, 29, 30, 31, 34, 45, 48, 49, 51, 68, 70, 83, 89, 96, 101], "advantag": [6, 30, 31, 72], "advers": [22, 34], "advertis": 74, "affect": [11, 20, 21, 34, 76, 78, 80, 81, 92], "affin": 84, "aforement": [30, 91], "after": [0, 1, 2, 3, 5, 7, 8, 9, 10, 13, 17, 18, 27, 28, 29, 30, 32, 33, 34, 35, 36, 66, 70, 71, 74, 78, 80, 81, 82, 83, 84, 86, 89, 90, 91, 92, 96, 97, 101, 107], "again": [17, 30, 76, 78, 81, 95], "against": [66, 74], "agent": 24, "agentdesc": 0, "agentnam": 0, "agentst": 0, "aggreg": [29, 30, 31], "aggress": [16, 28, 78, 82], "agre": [70, 89], "agreement": 70, "ahead": [0, 5, 13, 32], "ai": [21, 23, 27, 30, 32, 35, 42, 45, 48, 49, 50, 51, 52, 57, 59, 68, 72, 73, 76, 82, 83, 89, 94, 96], "aidc": 96, "aim": [4, 16, 21, 27, 30, 72, 74, 76, 78, 96], "ainsli": 22, "air": 96, "aka": 83, "akhoroshev": 96, "al": 22, "albeit": 13, "alessionetti": 96, "algo": 59, "algorithm": [0, 5, 6, 13, 16, 17, 20, 26, 27, 28, 29, 30, 33, 59, 71, 74, 78, 83, 96], "alia": [71, 84, 85], "alibi": 83, "alibi_bias_max": [83, 84], "alibi_scal": 83, "alibi_slop": 83, "alibi_with_scal": 83, "align": [74, 96, 107], "align_corn": 83, "all": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 13, 17, 18, 20, 21, 24, 27, 28, 29, 30, 31, 32, 33, 53, 54, 55, 56, 57, 58, 66, 67, 68, 71, 72, 74, 75, 76, 77, 78, 80, 81, 82, 83, 84, 86, 88, 89, 90, 92, 93, 94, 95, 96, 97, 101, 106, 107], "all2al": 30, "all_reduce_param": [83, 84], "allbitset": [0, 1], "allgath": [17, 29, 34, 81, 83, 96], "allgeneratedtoken": 0, "alllayersdrafttokenid": 1, "alllayersdrafttokenidspredecessor": 1, "alllayersscor": 1, "alloc": [0, 1, 2, 5, 8, 9, 32, 35, 41, 71, 82, 83, 88, 92, 95, 96, 97, 100, 101, 106, 107], "allocateipcmemori": 1, "allocnewblock": 0, "allocnewblocksperrequest": 0, "alloctotalblock": 0, "alloctotalblocksperrequest": 0, "allot": 0, "allottedtimem": [0, 96], "allow": [0, 1, 3, 5, 6, 9, 13, 16, 22, 25, 29, 30, 31, 34, 70, 71, 72, 73, 74, 75, 76, 77, 78, 80, 81, 83, 86, 91, 95, 96, 100, 103, 107], "allreduc": [17, 27, 29, 34, 71, 81, 83, 96], "allreduce_gemm": 12, "allreduce_strategi": [11, 71], "allreducebuff": 1, "allreducefusionkernel": 27, "allreducefusionop": 83, "allreduceparam": [83, 84], "allreducestrategi": [11, 83], "almost": [17, 29, 30, 78, 80, 92], "alon": 4, "along": [5, 13, 19, 28, 66, 83, 96], "alongsid": 30, "alpaca": 10, "alpha": [71, 83, 84, 96], "alphabet": 83, "alreadi": [0, 5, 7, 9, 19, 21, 27, 28, 29, 30, 31, 71, 78, 80, 82, 83, 96, 99, 106], "also": [0, 3, 5, 7, 13, 16, 17, 18, 19, 20, 21, 24, 25, 26, 27, 28, 29, 30, 31, 34, 35, 41, 52, 66, 67, 68, 70, 71, 74, 75, 76, 77, 78, 79, 80, 83, 84, 89, 90, 91, 92, 93, 96, 99, 100, 101, 106], "altair": 96, "alter": [3, 7], "altern": [3, 12, 27, 66, 74, 90, 99, 100], "although": [7, 17, 31, 74, 78, 81], "alwai": [0, 1, 3, 5, 6, 9, 16, 17, 20, 29, 30, 71, 80, 81, 83, 95], "always_share_across_beam": 88, "am": [45, 48, 49, 51, 68, 76, 82, 88, 89], "ambigu": 1, "amd": 96, "amen": [0, 3, 71], "among": [31, 37, 83], "amongst": 83, "amount": [0, 9, 17, 29, 30, 34, 71, 74, 80, 82, 88, 92, 95], "amper": [23, 66, 72, 94, 96], "an": [0, 1, 2, 3, 5, 6, 7, 9, 10, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 24, 26, 27, 28, 29, 30, 31, 33, 34, 35, 41, 45, 47, 48, 49, 50, 51, 52, 66, 68, 70, 71, 72, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 88, 89, 90, 91, 92, 93, 95, 96, 99, 100, 101, 106, 107], "analog": 91, "analys": 30, "analysi": [7, 27, 28, 29, 30, 31, 32, 65, 92], "analysispatternmanag": 7, "analyt": 23, "analyz": [7, 52, 76], "andlength": 33, "ani": [0, 1, 3, 7, 8, 13, 18, 20, 21, 28, 29, 30, 35, 66, 71, 72, 74, 75, 80, 81, 82, 83, 85, 88, 90, 91, 95, 99, 100, 101], "announc": [21, 22, 23, 25], "anoth": [0, 1, 5, 7, 10, 20, 23, 27, 28, 29, 30, 31, 32, 35, 80, 83, 89, 95, 101, 107], "answer": [28, 47, 52, 57], "antialia": 83, "antonin": [45, 68, 89], "anybitset": [0, 1], "anymor": 30, "anyth": [56, 75], "aotman": 96, "apart": 41, "api": [2, 6, 9, 13, 15, 16, 17, 19, 21, 28, 29, 30, 31, 32, 33, 41, 42, 45, 46, 54, 55, 65, 66, 72, 73, 74, 75, 78, 79, 81, 82, 83, 92, 95, 98, 99], "api_kei": [35, 60, 61, 62, 63], "app": [66, 96], "appar": [2, 72], "appear": [0, 5, 6, 68, 71, 83, 95, 96], "append": [28, 73, 83, 107], "append_paged_kv_cach": 101, "appl": 96, "appli": [0, 2, 3, 5, 7, 10, 13, 16, 17, 18, 27, 28, 29, 30, 34, 66, 71, 72, 74, 83, 84, 88, 91, 93, 96, 101], "applic": [9, 13, 23, 26, 27, 29, 30, 31, 32, 35, 38, 39, 40, 68, 70, 72, 73, 89, 91, 95, 96, 97, 107], "apply_batched_logits_processor": 71, "apply_chat_templ": [27, 47], "apply_llama3_sc": 83, "apply_query_key_layer_sc": [84, 85], "apply_residual_connection_post_layernorm": 85, "apply_rotary_pos_emb": 83, "apply_rotary_pos_emb_chatglm": 83, "apply_rotary_pos_emb_cogvlm": 83, "apply_silu": 83, "applybiasropeupdatekvcach": 96, "applyrop": 27, "appreci": 29, "approach": [0, 4, 7, 9, 11, 13, 27, 28, 29, 30, 31, 74, 82, 89], "appropri": [26, 31, 41, 90, 95], "approxim": [29, 30, 66, 84], "apt": [21, 36, 66, 68], "ar": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 38, 39, 45, 47, 48, 49, 51, 52, 53, 54, 55, 56, 60, 61, 66, 67, 68, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 88, 89, 90, 91, 92, 93, 95, 96, 97, 99, 100, 101, 104, 105, 106, 107], "arang": 83, "arbitrag": 74, "arbitrari": [18, 96], "arbitrary_types_allow": 71, "architectur": [2, 4, 6, 9, 16, 23, 28, 29, 30, 31, 66, 72, 85, 88, 94, 96, 98], "arctic": [94, 96], "area": [29, 30], "aresult": 41, "arg": [0, 7, 20, 33, 35, 57, 71, 84, 85, 88, 96], "arglist": 7, "argmax": 83, "argpars": 57, "argument": [2, 3, 21, 35, 41, 59, 66, 71, 74, 77, 83, 90, 92, 96, 97, 101], "argumentpars": 57, "aris": 66, "arithmet": 17, "arm": 90, "around": [1, 16, 20, 72, 76, 81], "arrai": [0, 1, 71, 83, 88, 90], "arrayview": [0, 1], "arriv": [0, 4], "arrivaltim": 0, "arrow": 83, "art": [21, 27, 30, 31], "articl": [5, 13, 27, 28], "artifact": [66, 91], "artifici": [32, 58, 72], "arxiv": [0, 1, 4, 10, 34, 83, 93], "as_dtyp": 83, "as_lay": 7, "as_shap": 83, "ascii": 83, "asciichar": 1, "ask": [56, 95], "aspect": 5, "assembl": [17, 19], "assert": [7, 63, 83, 95, 96, 107], "assert_valid_quant_algo": 85, "assign": [0, 20, 30, 74, 84, 86, 99], "assist": [6, 32, 35, 38, 39, 47, 60, 61, 70, 89], "assistant_model": 6, "associ": [1, 3, 4, 10, 29, 31, 66, 76, 83, 91], "asssembl": 13, "assum": [1, 3, 9, 10, 13, 14, 21, 28, 29, 30, 71, 74, 83, 88], "assumpt": [13, 31, 34], "assur": 30, "async": [41, 49, 50, 71, 74, 88], "asynchron": [1, 3, 30, 41, 46, 71], "asynchroni": 30, "asyncio": [49, 50], "asyncllmengin": 96, "atom": 1, "attach": [21, 89], "attempt": [0, 2, 75, 76, 78, 91, 97], "attend": 82, "attent": [0, 1, 2, 6, 8, 9, 10, 13, 15, 17, 18, 21, 22, 30, 31, 34, 65, 71, 83, 88, 89, 92, 95, 96, 97, 98, 99, 102, 106], "attention_backend": [99, 101], "attention_head_s": [83, 84], "attention_mask": [83, 84, 85, 88, 101], "attention_mask_param": 85, "attention_mask_typ": 84, "attention_multipli": 85, "attention_output": 95, "attention_output_orig_quant_scal": 83, "attention_output_sf_scal": 83, "attention_packed_mask": [83, 84], "attention_param": [84, 85], "attention_qk_half_accumul": 96, "attention_window_s": 8, "attentionconfig": 0, "attentionheads": 1, "attentionmask": 101, "attentionmaskparam": 84, "attentionmasktyp": [83, 84], "attentionmetadata": 99, "attentionparam": [84, 85], "attentiontyp": 0, "attn_backend": [71, 101], "attn_bia": 85, "attn_dens": [10, 34], "attn_forward_funcnam": 84, "attn_k": [10, 34, 74], "attn_logit_softcap": 85, "attn_logit_softcapping_scal": 83, "attn_metadata": 99, "attn_processor": 85, "attn_q": [10, 34, 74], "attn_qkv": [10, 34], "attn_v": [10, 34, 74], "attribut": [0, 1, 3, 7, 18, 20, 71, 88], "audienc": 52, "audio": [88, 96], "audio_engine_dir": 88, "audio_featur": 88, "audio_path": 88, "authent": [70, 76, 89], "authorized_kei": [36, 37], "auto": [0, 1, 3, 5, 6, 11, 14, 17, 30, 33, 71, 74, 81, 83, 85, 86, 87, 91, 96], "auto_deploi": 96, "auto_parallel": [34, 71, 96], "auto_parallel_config": 71, "auto_parallel_world_s": 71, "auto_quantize_bit": 87, "autoawq": 96, "autodeploi": 96, "autogptq": 96, "autom": [31, 47, 52, 90, 96], "automat": [0, 3, 7, 11, 17, 18, 27, 30, 35, 41, 70, 72, 74, 76, 83, 90, 92, 93, 96], "autonom": 32, "autoparallelconfig": 71, "autopp": 96, "autoq": 96, "autoregress": [0, 13, 101, 106], "autotoken": 41, "autotun": [71, 96], "aux": 92, "auxiliari": 13, "avaiable_block": 107, "avail": [0, 1, 3, 7, 9, 12, 17, 22, 24, 30, 31, 35, 41, 45, 48, 49, 51, 58, 66, 67, 68, 72, 74, 80, 81, 82, 88, 89, 91, 92, 93, 96, 98, 101, 105, 106], "averag": [0, 13, 21, 28, 30, 31, 33, 71, 74, 75, 76, 78, 80, 81], "avg": [74, 76, 83], "avg_pool2d": 83, "avgnumdecodedtokensperit": 0, "avgpool2d": 84, "avoid": [1, 20, 27, 28, 29, 30, 66, 70, 88, 92, 96], "awai": [71, 80, 81], "await": [0, 3, 41, 49, 50], "awaitcontextrespons": 0, "awaitgenerationrespons": 0, "awaitrespons": [0, 3], "awar": [2, 5, 22, 31, 95], "awq": [26, 41, 65, 94, 96], "awq_block_s": 87, "ax": 83, "axi": [25, 30, 83], "b": [1, 7, 10, 17, 22, 23, 24, 25, 73, 83, 85, 88, 90, 96], "b200": [28, 29, 30, 32, 75, 96], "b6261862419c33d6ce2313aff1e7116067d6037d": 21, "b_sf": 83, "back": [0, 9, 11, 13, 30, 68, 75, 96], "backbon": 72, "backend": [0, 3, 13, 17, 19, 21, 28, 29, 30, 32, 33, 35, 42, 46, 47, 58, 65, 70, 71, 73, 74, 75, 89, 90, 96, 100, 104, 105, 106, 107], "backend_token": [0, 3], "backendagentdesc": 0, "backendtyp": [0, 2], "background": 30, "backlog": 90, "backu": [0, 3, 71], "backward": 20, "bad": [0, 3, 71, 96, 105], "bad_token_id": 71, "bad_words_data": 88, "bad_words_list": 88, "badword": 0, "badwordslen": 1, "badwordslist": 1, "badwordsptr": 1, "baichuan": [93, 94, 96], "baichuan2": 94, "baichuanconfig": 85, "baichuanforcausallm": 85, "balanc": [4, 6, 13, 17, 29, 31, 58, 71, 80, 82], "band": 47, "bandwidth": [2, 6, 17, 22, 23, 24, 26, 29, 30, 47], "bangbang": 23, "bantoken": 0, "banword": 0, "bar": 71, "bare": [96, 98], "barissglc": 56, "bart": [94, 96], "base": [0, 1, 3, 9, 10, 11, 13, 15, 18, 19, 20, 21, 22, 23, 26, 27, 29, 30, 31, 34, 49, 50, 52, 66, 71, 72, 74, 80, 82, 83, 84, 85, 86, 87, 88, 91, 92, 94, 96, 97, 98, 99, 100, 106, 107], "base64": 61, "base_model": 10, "base_s": 84, "base_url": [35, 60, 61, 62, 63], "baseagentconfig": 0, "basecheckpointload": 71, "basekvcachemanag": 0, "baselin": [26, 27, 28, 29, 76, 80, 81, 101], "baseline_fp8_engin": 78, "basellmarg": 71, "basemodel": 71, "baseresourcemanag": [100, 106], "basetransferag": 0, "bash": [17, 35, 37, 38, 39, 40, 42, 43, 44, 53, 54, 55, 73, 89], "basi": 31, "basic": [15, 73, 83], "basic_string_view": 0, "batch": [0, 1, 6, 9, 10, 11, 13, 14, 17, 19, 21, 23, 24, 26, 27, 28, 29, 30, 32, 33, 34, 35, 65, 69, 71, 74, 75, 76, 78, 79, 81, 82, 83, 84, 88, 89, 92, 95, 96, 97, 99, 100, 101, 103, 106, 107], "batch_beam_s": [5, 83], "batch_dim": 83, "batch_idx": 88, "batch_input_id": 88, "batch_manag": [0, 1, 106], "batch_schedul": 96, "batch_siz": [5, 7, 14, 16, 21, 22, 25, 57, 71, 75, 83, 84, 87, 88, 92, 101], "batchdon": 1, "batched_logits_processor": 71, "batchedlogitsprocessor": 71, "batchidx": 1, "batchindex": 1, "batching_typ": 71, "batchingtyp": [0, 71], "batchsiz": [0, 1, 6, 23], "batchsizelimit": 0, "batchsizet": 0, "batchslot": 1, "batchslotshostcopi": 1, "bc": 83, "beam": [0, 1, 6, 13, 19, 25, 33, 34, 35, 41, 58, 65, 71, 83, 88, 92, 95, 96], "beam_search_diversity_r": [71, 88], "beam_width": [5, 6, 33, 41, 83, 88, 96], "beam_width_arrai": 71, "beamhypothes": 1, "beamsearch": 0, "beamsearchbuff": 1, "beamsearchdiversityr": [0, 1, 6], "beamsiz": 0, "beamtoken": [0, 3], "beamwidth": [0, 1, 2, 3, 6, 71, 96], "beamwidtharrai": [0, 1, 6], "beauti": 58, "becam": 0, "becaus": [0, 3, 9, 26, 27, 28, 29, 30, 34, 41, 56, 67, 70, 74, 75, 76, 77, 78, 80, 82, 83, 89, 92], "becom": [5, 6, 7, 9, 10, 17, 18, 26, 27, 29, 30, 72], "been": [0, 3, 4, 5, 20, 21, 23, 24, 27, 29, 30, 37, 56, 66, 67, 68, 71, 74, 78, 80, 83, 89, 95, 96], "befor": [0, 1, 2, 3, 5, 7, 9, 10, 11, 16, 17, 18, 27, 28, 30, 32, 33, 52, 53, 54, 55, 65, 66, 68, 70, 71, 72, 73, 77, 78, 80, 82, 83, 85, 88, 92, 95, 96, 99, 100, 101, 106, 107], "beforehand": 76, "begin": [13, 72, 77, 96, 99], "begin_thinking_phase_token": 71, "behav": [0, 71, 92], "behavior": [2, 5, 75, 80, 83, 88, 91, 92, 96], "behaviour": [0, 30, 83], "behind": [23, 29], "being": [0, 5, 9, 17, 20, 29, 32, 56, 71, 80, 95, 96, 97, 101], "believ": [30, 74], "belong": 80, "below": [0, 5, 6, 7, 8, 10, 21, 24, 25, 26, 28, 29, 30, 31, 32, 36, 37, 66, 74, 75, 78, 80, 81, 89, 90, 95], "bench": [21, 28, 30, 46, 56, 74, 75, 79, 96], "benchmark": [2, 27, 28, 30, 31, 32, 33, 54, 65, 66, 73, 78, 79, 81, 89, 96], "benchmark_2nod": 35, "benefici": [29, 31, 74, 80, 81], "benefit": [7, 9, 11, 24, 26, 28, 29, 30, 31, 34, 52, 57, 72, 80, 96], "bert": [34, 83, 93, 94, 96], "bert_attent": 83, "bert_attention_plugin": 34, "bert_context_fmha_fp32_acc": 34, "bertattent": 84, "bertattentionplugin": 83, "bertbas": 85, "bertforquestionansw": 85, "bertforsequenceclassif": [85, 94], "bertmodel": 85, "besid": 100, "best": [5, 17, 27, 28, 29, 30, 31, 65, 71, 73, 74, 77, 79, 80, 89, 96], "best_of": [71, 96], "best_path": 88, "best_path_len": 88, "best_path_length": 88, "best_perf_practice_on_deepseek": [27, 96], "bestpathindic": 1, "bestpathlength": 1, "beta": [35, 83], "beta_fast": 83, "beta_slow": 83, "better": [0, 2, 5, 6, 9, 11, 18, 20, 25, 27, 28, 29, 30, 31, 34, 52, 53, 54, 55, 57, 71, 75, 77, 78, 81, 82, 96, 103], "between": [0, 2, 5, 6, 8, 9, 12, 13, 17, 18, 20, 27, 28, 29, 30, 31, 33, 35, 39, 61, 71, 73, 75, 77, 81, 82, 83, 84, 92, 95, 96, 99], "beyond": [1, 23, 78], "bf16": [1, 5, 11, 18, 20, 21, 27, 29, 32, 65, 78, 81, 94, 96], "bfloat16": [5, 17, 34, 74, 76, 86, 93, 94, 96], "bhuvanesh09": 96, "bi": 5, "bia": [0, 3, 16, 17, 29, 71, 83, 84, 85, 96], "bias": [16, 83], "bidirect": [83, 84], "bidirectionalglm": 83, "big": 52, "bigger": 9, "biggest": 9, "billion": 21, "bin": [16, 17, 18, 21, 35, 38, 39, 40, 42, 43, 44, 53, 54, 55, 73, 95, 96], "binari": [13, 17, 73, 83], "bind": [30, 65, 71, 82, 88, 92, 96, 100, 106, 107], "bindcapacityschedul": 107, "bindf": 91, "bit": [0, 1, 5, 23, 30, 56, 83, 93], "bitmask": 96, "bl": [13, 31], "black": 7, "blackwel": [21, 28, 30, 65, 68, 77, 78, 94, 96], "blip": [93, 96], "blip2": [93, 94, 96], "blob": 27, "block": [0, 1, 2, 5, 6, 9, 17, 29, 30, 31, 34, 41, 65, 70, 71, 80, 83, 88, 92, 96, 106], "block_controlnet_hidden_st": 85, "block_num": 83, "block_siz": [83, 84, 88], "block_sparse_block_s": 83, "block_sparse_homo_head_pattern": 83, "block_sparse_num_local_block": 83, "block_sparse_param": 84, "block_sparse_vertical_strid": 83, "blockhash": 0, "blockidx": 1, "blockptr": 1, "blocksiz": 0, "blockspars": 83, "blocksparseattnparam": 84, "blog": [21, 22, 25, 26, 27, 28, 29, 30, 31, 96, 103], "bloodeagle40234": 96, "bloom": [6, 18, 93, 94, 96], "bloom_dict": 18, "bloomforcausallm": 85, "bloommodel": 85, "bm": 1, "bmm": 17, "board": 81, "bodi": 17, "book": 56, "bool": [0, 1, 7, 14, 16, 52, 71, 83, 84, 85, 86, 88, 101], "boolean": [1, 3, 10, 83, 85, 86], "boost": [21, 27, 29, 30, 32, 52, 78, 80, 81], "boost_factor": 52, "boost_val": 52, "born": [15, 17, 95], "borrow": [41, 74], "bos_token": 52, "bos_token_ad": 52, "bos_token_id": [52, 88], "bot": 90, "both": [0, 2, 4, 5, 7, 8, 10, 13, 17, 18, 21, 23, 26, 27, 28, 29, 30, 31, 32, 34, 45, 58, 71, 74, 75, 77, 80, 82, 83, 84, 90, 92, 93, 96, 100, 101], "bottleneck": [4, 11, 21, 26, 30, 77, 80], "bottom": 37, "bound": [0, 6, 15, 17, 24, 27, 28, 29, 71, 74, 83, 88, 92], "boundari": [6, 17, 29, 30, 71, 83, 85, 87, 92], "box": [7, 21, 90], "bpru": 96, "brahma": 74, "branch": [13, 22, 25, 30, 32, 71], "breadth": 13, "break": [13, 27, 30, 74, 81, 96, 107], "breakdown": [73, 74, 75, 76], "breviti": 21, "bridg": 30, "brief": [85, 88, 90, 101], "briefli": [35, 39, 61], "brife": 0, "bright": 52, "bring": [26, 27, 28, 29, 30, 99], "broad": 70, "broadcast": [3, 27, 83], "broadcast_help": 83, "broader": [5, 70, 96], "broadli": 29, "broken": [72, 80, 96], "brought": 30, "bsz": 84, "bu": 66, "budget": [14, 80], "buffer": [0, 1, 2, 3, 8, 9, 30, 34, 35, 65, 71, 83, 96, 106], "buffer_0": 1, "buffer_1": 1, "buffer_2": 1, "buffer_alloc": 88, "buffercast": 1, "buffercastornul": 1, "bufferdatatyp": 1, "buffermanag": 92, "buffermanagertest": 1, "bufferptr": 1, "bufferrang": 1, "buffers": 1, "bufferview": 0, "bug": [29, 90, 96], "build": [2, 3, 5, 6, 7, 9, 10, 12, 13, 14, 15, 17, 19, 56, 65, 71, 72, 73, 77, 78, 79, 80, 82, 85, 86, 89, 91, 92, 95, 96], "build_config": [20, 34, 41, 56, 71, 78, 80, 81, 85], "build_dir": 66, "build_engin": 17, "build_flags_multiple_profil": 81, "build_serialized_network": 17, "build_wheel": [12, 21, 66, 73], "buildcacheconfig": 71, "buildconfig": [14, 20, 41, 56, 71, 78, 80, 81, 96], "builder": [14, 17, 20, 71, 96], "builder_force_num_profil": 96, "builder_opt": 96, "built": [3, 6, 9, 17, 20, 29, 31, 34, 65, 66, 68, 70, 74, 75, 76, 81, 82, 83, 89, 91, 92, 95, 96], "bulk": 30, "bump": 1, "bumptaskinprogress": 1, "burden": 77, "busi": [0, 31, 52], "button": 96, "buvnswrn": 96, "bw": 96, "bypass": [31, 91], "byt5": [94, 96], "byte": [0, 1, 11, 71, 88], "bytestostr": 1, "c": [0, 1, 5, 7, 13, 17, 19, 21, 28, 29, 31, 32, 35, 36, 37, 41, 53, 54, 55, 65, 71, 72, 73, 80, 83, 85, 89, 96, 100, 102, 105, 106, 107], "c2c": 30, "c4dep4_g1dep4": 31, "cach": [0, 1, 2, 3, 6, 10, 17, 20, 26, 27, 28, 29, 32, 33, 34, 35, 41, 57, 65, 69, 71, 72, 74, 75, 76, 80, 83, 88, 89, 91, 93, 96, 98, 99, 100, 101, 102, 107], "cache_indir": 88, "cache_indir_t": 83, "cache_indirect": [5, 83, 84, 88, 95], "cache_root": 71, "cache_transceiver_config": 71, "cachehitr": 0, "cacheindirect": 1, "cachelevel": 0, "cachelevelupd": 0, "caches": 0, "cachest": 0, "cachetransceiv": 0, "cachetransceiverconfig": [0, 2, 71], "cachetyp": 106, "cachevalu": 1, "calcul": [0, 22, 23, 25, 28, 29, 30, 31, 71, 74, 82, 83, 88, 92, 96], "calculate_speculative_resourc": 71, "calculatespeculativeresourc": 0, "calculatespeculativeresourcetupl": 0, "calib_batch": [71, 78, 85], "calib_batch_s": [71, 78, 85], "calib_config": [71, 78], "calib_dataset": [71, 85, 87], "calib_max_seq_length": [71, 78, 85, 87], "calib_s": [74, 87], "calibconfig": [71, 78], "calibr": [18, 26, 29, 30, 34, 71, 78, 96], "call": [0, 1, 3, 4, 5, 6, 7, 12, 17, 18, 20, 28, 29, 30, 31, 41, 52, 71, 73, 76, 78, 83, 85, 87, 88, 89, 92, 96, 97, 99, 100, 101, 106], "callabl": [18, 71, 85], "callback": [3, 71], "campaign": 52, "can": [0, 1, 2, 3, 4, 5, 6, 7, 8, 11, 12, 13, 14, 17, 18, 19, 20, 21, 22, 23, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 41, 45, 52, 53, 54, 55, 56, 59, 65, 66, 67, 68, 70, 71, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 85, 86, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 104, 106, 107], "canaccessp": 1, "cancel": [0, 3, 71, 74, 96], "cancelrequest": [0, 3], "candid": [0, 6, 11, 13, 17, 27, 28, 71], "canenqueu": 0, "canenqueuerequest": 0, "cannot": [1, 6, 17, 18, 27, 29, 30, 31, 70, 71, 80, 81, 82, 83, 92, 95, 96, 107], "cap": [33, 76], "capabl": [22, 27, 30, 31, 47, 66, 72, 73, 78], "capac": [0, 1, 22, 24, 26, 30, 71, 107], "capacitor_schedul": 107, "capacity_scheduler_polici": [71, 82], "capacityschedul": [100, 106, 107], "capacityschedulerpolici": [0, 71, 82, 96], "capit": [45, 48, 49, 50, 51, 57, 59, 68, 76, 82, 89], "caption": 84, "captur": [28, 29, 30, 71, 101], "card": 56, "care": [30, 31], "carefulli": [21, 30], "case": [0, 1, 2, 5, 6, 8, 9, 10, 13, 21, 23, 26, 27, 28, 29, 30, 31, 34, 41, 70, 74, 75, 76, 78, 79, 81, 83, 91, 93, 96], "cast": [29, 83], "cast_to_dtyp": 83, "castsiz": 1, "cat": [21, 28, 30, 35, 54], "catalog": [66, 67, 89], "categor": [13, 29, 83], "categori": 86, "categorical_sampl": 83, "caus": [2, 3, 18, 20, 30, 34, 71, 81, 95, 96], "causal": [28, 83, 84, 101], "cautiou": 20, "caveat": 78, "cd": [15, 16, 21, 28, 32, 66, 74, 89, 95, 104], "ceil": [1, 85], "ceil_mod": [83, 84], "ceildiv": 1, "center": [23, 24, 31], "central": 86, "certain": [7, 16, 30, 31, 68, 72, 83], "cg": 85, "chain": [28, 52], "challeng": [27, 30, 31, 72], "chanc": [9, 30, 34, 82], "chang": [2, 5, 6, 8, 9, 10, 18, 20, 21, 22, 24, 25, 28, 29, 30, 59, 66, 71, 72, 74, 81, 83, 85, 88, 90, 92, 95, 97, 98, 106], "channel": [30, 34, 83, 93, 96], "char": [0, 1], "charact": 90, "characterist": 31, "charg": [6, 17, 101], "chart": 23, "chat": [13, 24, 31, 32, 40, 43, 45, 47, 48, 49, 50, 51, 52, 56, 57, 58, 62, 64, 68, 70, 89, 96], "chatbot": 56, "chatcmpl": [32, 89], "chatglm": [83, 93, 94, 96], "chatglm2": [94, 96], "chatglm3": [85, 94, 96], "chatglm_vers": 85, "chatglmconfig": 85, "chatglmforcausallm": 85, "chatglmgenerationsess": 88, "chatglmmodel": 85, "check": [2, 3, 30, 32, 45, 66, 68, 71, 75, 77, 78, 80, 81, 83, 88, 89, 91, 92, 95, 96, 99, 103], "check_accuraci": 16, "check_config": 85, "check_gpt_mem_usag": 92, "checkbeamsearchdiversityr": 0, "checkbeamwidth": 0, "checkbeamwidtharrai": 0, "checkearlystop": 0, "checklengthpenalti": 0, "checkminp": 0, "checkmintoken": 0, "checknorepeatngrams": 0, "checknumreturnsequ": 0, "checkpoint": [15, 18, 19, 20, 21, 27, 28, 29, 32, 33, 34, 35, 45, 48, 65, 68, 70, 71, 74, 76, 78, 87, 88, 89, 93, 95, 96, 99], "checkpoint_dir": [10, 14, 15, 16, 17, 20, 34, 74, 89, 95], "checkpoint_format": 71, "checkpoint_load": 71, "checkposteriorvalu": 0, "checkremotedesc": 0, "checkrepetitionpenalti": 0, "checktemperatur": 0, "checktopk": 0, "checktopp": 0, "checktoppdecai": 0, "checktoppmin": 0, "checktoppresetid": 0, "chef": 95, "chmod": 36, "choic": [0, 13, 26, 28, 30, 32, 34, 57, 58, 59, 74, 77, 83, 88, 89, 101], "choos": [17, 20, 27, 29, 30, 31, 78, 83, 96], "chose": 30, "chosen": [29, 92, 105, 107], "chrome": 73, "chrono": 0, "chunk": [0, 8, 29, 33, 34, 65, 69, 71, 81, 83, 88, 92, 96, 102], "chunk_dim": 84, "chunk_length": 96, "chunk_scan": 83, "chunk_siz": [83, 85], "chunkedcontextnexttoken": 1, "chunkedcontextnexttokenshost": 1, "ci": [1, 65, 91], "circular": 5, "citi": 89, "ckpt": [74, 89], "ckpt_dir": [17, 20, 85], "ckpt_llama_3": 17, "cl": [15, 20], "claim": [1, 18], "claimpag": 1, "claimpageswithevict": 1, "clamp": [71, 96], "clamp_val": 71, "class": [0, 1, 5, 6, 7, 8, 14, 15, 17, 18, 20, 26, 34, 41, 52, 66, 70, 71, 77, 78, 81, 83, 84, 85, 86, 87, 88, 95, 96, 99, 100, 101, 105, 107], "class_dropout_prob": 84, "class_label": 84, "classic": [17, 30, 65], "classifi": [84, 85], "classmethod": [15, 20, 71, 84, 85, 88], "classvar": 71, "clean": [21, 30, 66, 73, 95], "clear": [30, 80, 88], "clearli": [30, 82], "cli": [16, 21, 41, 65, 74, 77, 78, 80, 81, 89], "click": [36, 37, 58, 59], "client": [0, 3, 31, 35, 64, 75, 97], "client_id": 52, "clientid": 0, "clip": 83, "clip_before_cast": 83, "clip_qkv": [84, 85], "clip_vision_model": 85, "clipvisiontransform": 85, "clock": 27, "clone": [10, 21, 66, 70, 76, 89, 95, 104], "clone_input": 7, "close": [5, 20, 21, 30, 31, 34, 81, 92], "closur": 83, "cloud": [23, 36, 37], "cls_token": 84, "cluster": [6, 17, 27, 30, 32, 33, 34, 35, 68, 71, 96], "cluster_info": 96, "cluster_kei": [34, 96], "cluster_s": [33, 35], "cmake": [66, 96], "cnn_dailymail": [71, 85], "co": [0, 10, 21, 28, 29, 30, 35, 39, 61, 70, 83, 84, 89, 95], "coast": 89, "code": [5, 7, 8, 11, 12, 13, 17, 20, 26, 27, 29, 32, 33, 35, 41, 53, 54, 55, 65, 70, 71, 72, 73, 74, 83, 91, 93, 94, 95, 96, 99, 106, 107], "codebas": [8, 99], "codellama": 96, "codepath": 96, "codeqwen": 96, "coderham": 96, "cogvlm": [94, 96], "cogvlmattent": 84, "cogvlmconfig": 85, "cogvlmforcausallm": 85, "coher": [6, 96], "cohereconfig": 85, "cohereforcausallm": 85, "cold": 30, "collabor": [6, 27, 29, 30, 31, 83], "collect": [1, 7, 11, 13, 17, 27, 29, 31, 71, 75, 83, 99], "collect_and_bia": 84, "collector": 30, "color": [56, 80], "column": [10, 83, 93], "columnlinear": [10, 15, 84], "com": [17, 20, 21, 27, 32, 52, 66, 83, 89, 90, 91, 95, 96, 104], "combin": [0, 7, 13, 24, 27, 28, 29, 30, 31, 32, 34, 53, 54, 55, 58, 74, 75, 78, 80, 84, 85, 91, 96, 98, 101, 107], "combinedtimesteplabelembed": 84, "combinedtimesteptextprojembed": 84, "come": [6, 10, 23, 30, 31, 76, 77, 80, 82, 92, 95], "comm": 71, "comma": [83, 88], "command": [9, 10, 12, 15, 16, 17, 20, 21, 31, 32, 33, 35, 36, 37, 53, 54, 55, 58, 59, 66, 67, 73, 74, 76, 81, 86, 89, 90, 91, 92, 95, 96, 104], "commandr": 96, "comment": [90, 96], "commit": [21, 29, 32, 90, 91], "commmod": 0, "common": [0, 5, 8, 9, 13, 21, 29, 30, 33, 45, 70, 71, 83, 91, 92, 106], "commonli": [7, 27, 35, 96], "commstat": 0, "commtyp": 0, "commun": [0, 2, 6, 11, 17, 29, 31, 34, 70, 71, 72, 78, 83, 94, 96], "communicationmod": [0, 2], "communicationtyp": 0, "compani": [32, 52], "compar": [1, 18, 21, 23, 24, 26, 28, 29, 30, 31, 78, 80, 81, 82, 83, 101], "comparison": [6, 23, 27, 28, 74], "compat": [13, 20, 28, 30, 31, 32, 33, 35, 66, 81, 84, 89, 94, 96, 99], "compbin": 10, "compet": 30, "compil": [6, 11, 12, 19, 32, 65, 68, 71, 72, 73, 74, 83, 95], "complet": [0, 1, 3, 6, 8, 9, 13, 30, 32, 38, 39, 41, 58, 60, 61, 64, 66, 71, 72, 74, 75, 76, 80, 81, 89, 96, 103, 106, 107], "complete_sent": 52, "completion_token": [32, 89], "completionoutput": [41, 71], "complex": [7, 8, 13, 17, 27, 30, 52, 89], "compli": 35, "complic": [28, 29, 30, 99], "compon": [3, 5, 17, 19, 26, 27, 28, 29, 30, 33, 65, 93, 100], "compos": [0, 6, 30, 65, 74], "comprehens": [21, 33, 35, 72], "compress": [22, 29], "compris": [26, 31], "comput": [0, 1, 4, 5, 6, 9, 13, 17, 22, 23, 24, 26, 27, 28, 29, 30, 31, 32, 34, 45, 48, 49, 51, 52, 68, 71, 73, 74, 77, 78, 82, 83, 89, 92, 95, 96, 99, 100, 101, 103, 106], "compute_relative_bia": 84, "computecontextlogit": 1, "computegenerationlogit": 1, "computenumpackedmask": 1, "concat": [15, 27, 83], "concat_kvcach": 27, "concaten": [5, 10, 18, 27, 83, 99], "concept": [17, 31, 74, 79, 96, 106], "conceptu": 1, "concern": [17, 30, 92], "conclud": 30, "conclus": 79, "concret": [30, 99], "concurr": [1, 2, 13, 21, 23, 27, 28, 29, 30, 31, 33, 74, 96, 97, 103], "concurrency_list": 97, "cond_proj_dim": 84, "conda": 96, "condit": [0, 1, 3, 6, 7, 13, 30, 31, 74, 83, 84, 90, 96], "condition": [83, 91], "conditioning_embed": 84, "conditioning_embedding_dim": 84, "conduct": [2, 5, 31, 74], "config": [0, 1, 5, 9, 10, 14, 15, 18, 20, 21, 22, 28, 29, 32, 33, 35, 42, 71, 74, 80, 84, 85, 86, 88, 95, 96, 97, 99, 106], "config_class": 85, "config_dir": 85, "config_fil": [35, 71, 85, 97], "configdict": 71, "configur": [0, 1, 2, 4, 5, 8, 12, 13, 18, 19, 21, 24, 31, 32, 33, 34, 35, 46, 47, 56, 65, 66, 68, 71, 74, 75, 76, 79, 80, 82, 85, 88, 90, 92, 95, 96, 97, 101, 103], "configuration_llama": 99, "configuration_mymodel": 99, "configuration_util": 99, "confirm": [45, 68, 89], "conform": 71, "congest": 30, "conjunct": 80, "connect": [0, 2, 11, 17, 30, 32, 76, 77, 79], "connectioninfo": 0, "connectioninfotyp": 0, "connectionmanag": 0, "connectremoteag": 0, "consecut": 6, "consequ": [2, 26, 77, 81], "conserv": [0, 82, 90], "consid": [0, 1, 10, 13, 21, 26, 30, 31, 32, 56, 58, 71, 75, 80, 83, 99, 107], "consider": [20, 26, 30, 31, 41], "consist": [7, 20, 23, 27, 71, 72, 74, 76, 83, 93, 95, 101], "consol": 36, "consolid": [13, 30], "const": [0, 1, 3], "const_iter": 1, "constant": [1, 5, 30, 83, 92], "constant_to_tensor_": 83, "constantli": [45, 48, 49, 51, 68, 89], "constants_to_tensors_": 83, "constantthreshold": 1, "constexpr": [0, 1], "constitut": 31, "constpointercast": 1, "constrain": [6, 26], "constraint": [0, 5, 6, 26, 30, 31, 83], "construct": [0, 1, 3, 13, 17, 31, 74, 83, 96, 101], "constructor": [0, 14, 56, 70, 89, 101], "consult": [13, 66, 73], "consum": [0, 7, 29, 30, 71, 83, 90], "consumpt": [5, 23, 28, 34], "contact": 83, "contain": [0, 1, 3, 5, 6, 7, 8, 10, 11, 16, 17, 18, 19, 20, 27, 30, 32, 33, 34, 35, 37, 53, 54, 55, 65, 68, 71, 72, 74, 75, 83, 85, 88, 90, 93, 94, 96, 97, 98, 100, 101], "container_id": [32, 89], "container_imag": [53, 54, 55], "container_img": 35, "content": [1, 10, 20, 32, 35, 36, 38, 39, 40, 47, 60, 61, 65, 71, 83, 89, 91, 92, 96], "context": [0, 2, 4, 9, 26, 28, 29, 30, 31, 34, 65, 69, 71, 74, 79, 83, 88, 92, 95, 96, 97, 101, 105, 106, 107], "context_and_gener": 71, "context_chunking_polici": [71, 82], "context_fmha": [10, 34], "context_fmha_fp32_acc": 96, "context_fmha_typ": [5, 92], "context_init": 107, "context_len": [88, 101], "context_length": [83, 84, 88, 95], "context_logit": [71, 88], "context_mem_s": 88, "context_onli": 71, "context_parallel_s": 71, "context_phas": 5, "context_pre_onli": 84, "context_request": 107, "context_serv": 31, "contextchunkingpolici": [0, 71, 82, 96], "contextexecutor": 2, "contextfmha": 1, "contextidx": 0, "contextlogit": 0, "contextmanag": 70, "contextparallel": 1, "contextphaseparam": [0, 71], "contextpositionid": 1, "contextprefillposit": 0, "contextrequest": 1, "contigu": [2, 8, 77, 83, 96], "continu": [1, 3, 5, 13, 24, 26, 31, 34, 65, 66, 71, 72, 78, 80, 88, 107], "contract": 74, "contrast": [6, 13, 101], "contrib": 22, "contribut": [20, 28, 29, 30, 74, 83, 96], "contributor": [27, 30, 31, 92], "control": [0, 2, 5, 6, 7, 12, 32, 41, 46, 58, 71, 73, 74, 76, 82, 83, 84, 88, 93, 96], "conv": 83, "conv1d": [34, 83, 84], "conv2d": [83, 84], "conv3d": [83, 84], "conv_bia": 83, "conv_kernel": 88, "conv_stat": 85, "conv_state_or_ptr": 83, "conv_transpose2d": 83, "conv_weight": 83, "conveni": [1, 15, 20, 66], "convent": [20, 83], "convers": [1, 18, 25, 26, 31, 56, 65, 89, 96], "convert": [0, 1, 10, 14, 15, 16, 17, 18, 20, 30, 52, 72, 74, 76, 78, 89, 95, 96, 101], "convert_and_load_weights_into_trtllm_llama": 20, "convert_checkpoint": [10, 14, 15, 16, 17, 20, 76, 77, 89, 95, 96], "convert_coneckpoint": 4, "convert_hf_mpt_legaci": 96, "convert_load_format": 71, "convert_util": 96, "convert_weights_from_custom_training_checkpoint": 20, "convkernel": 1, "convolut": [0, 88], "convtranspose2d": 84, "coordin": [13, 30, 65, 83], "copi": [0, 1, 2, 9, 13, 30, 34, 37, 71, 78, 83, 92, 96, 101], "copy_on_partial_reus": 71, "copyfrom": 1, "copyonpartialreus": 0, "copytask": 1, "copytaskmappag": 1, "copyto": 0, "copytocpu": 0, "copytogpu": 0, "copytomanag": 0, "copytopag": 1, "copytopin": 0, "copytopooledpin": 0, "core": [6, 7, 10, 14, 17, 20, 22, 23, 25, 29, 66, 71, 74, 77, 89, 95, 96, 97, 100], "corner": 29, "coroutin": [49, 50, 71], "correct": [3, 5, 10, 13, 28, 96], "correctli": [9, 83, 96, 99], "correspond": [0, 1, 4, 5, 7, 8, 10, 13, 18, 20, 28, 30, 31, 35, 67, 71, 73, 81, 83, 84, 88, 89, 93, 95, 96, 99], "correspondingli": 30, "corrupt": 30, "cost": [9, 17, 27, 28, 29, 30, 52, 74, 77, 92, 96], "costli": 27, "could": [0, 7, 8, 9, 16, 30, 45, 48, 49, 50, 51, 68, 71, 76, 89, 92, 95, 96], "couldn": 80, "count": [0, 1, 6, 30, 35, 43, 44, 52, 70, 74, 89], "count_include_pad": [83, 84], "countlocallay": 1, "countlowerranklay": 1, "cours": 13, "court": [45, 68, 89], "cover": [21, 30, 78, 79, 81, 90], "coverag": [30, 71], "cp312": 66, "cp_config": 71, "cp_group": [83, 84], "cp_rank": [83, 84], "cp_size": [83, 84, 87, 96], "cp_split_plugin": 83, "cpp": [3, 5, 6, 12, 17, 21, 29, 35, 54, 65, 66, 73, 74, 75, 76, 95, 96], "cpp_e2e": 88, "cpp_extens": 68, "cpp_llm_onli": 88, "cpp_onli": 66, "cpu": [0, 1, 8, 9, 10, 14, 17, 27, 28, 30, 34, 35, 68, 71, 83, 92, 95, 96, 101, 103], "cpumemusag": [0, 71], "crash": 96, "creat": [1, 3, 7, 8, 9, 13, 14, 15, 17, 19, 20, 27, 32, 35, 36, 41, 45, 48, 49, 50, 51, 52, 60, 61, 62, 63, 66, 68, 71, 72, 74, 75, 76, 80, 81, 83, 84, 85, 88, 89, 91, 92, 96, 97, 99, 100, 101, 107], "create_allreduce_plugin": 83, "create_attention_const_param": 84, "create_builder_config": 14, "create_cuda_graph_metadata": 101, "create_execution_context": 88, "create_fake_weight": 83, "create_network": 17, "create_pytorch_model_based_executor": [106, 107], "create_runtime_default": 85, "create_sinusoidal_posit": 83, "create_sinusoidal_positions_for_attention_plugin": 83, "create_sinusoidal_positions_for_cogvlm_attention_plugin": 83, "create_sinusoidal_positions_long_rop": 83, "create_sinusoidal_positions_long_rope_for_attention_plugin": 83, "create_sinusoidal_positions_yarn": 83, "createloramodul": 1, "creation": [1, 71, 83, 92], "creativ": [6, 58], "criteria": [88, 103], "critic": [27, 30, 31, 74, 95], "crop": 84, "cropped_pos_emb": 84, "cross": [0, 10, 11, 27, 28, 30, 71, 83, 88, 96], "cross_attent": [84, 88], "cross_attention_dim": 84, "cross_attention_mask": [84, 88], "cross_attention_mask_for_context": 88, "cross_attention_mask_for_gen": 88, "cross_attention_norm": 84, "cross_attention_norm_num_group": 84, "cross_attention_packed_mask": 84, "cross_attn_dens": [10, 34], "cross_attn_k": [10, 34], "cross_attn_q": [10, 34], "cross_attn_qkv": [10, 34], "cross_attn_v": [10, 34], "cross_kv": 83, "cross_kv_cache_block_offset": [84, 88], "cross_kv_cache_fract": [71, 88], "cross_kv_cache_gen": [84, 85], "cross_kv_length": 83, "cross_kv_reus": [84, 85], "crossattentionmask": 0, "crosskvcachefract": [0, 96], "crosskvcachestat": 0, "crucial": [13, 17, 26, 100], "csv": 33, "ctor": 83, "ctx": [0, 21, 31], "ctx1dep4": 31, "ctx_batch_siz": 97, "ctx_enable_attention_dp": 97, "ctx_gpu": 97, "ctx_max_num_token": 97, "ctx_param": 31, "ctx_request_id": 71, "ctx_tp_size": 97, "ctxenginepath": 0, "ctxexecutorconfig": 0, "ctxreqrat": 31, "cu": [17, 27], "cu12": 96, "cu128": 68, "cuassert": 95, "cubla": 29, "cublaslt": [34, 81], "cublasltmatmul": 29, "cublasscaledmm": 29, "cuda": [0, 1, 2, 5, 11, 17, 21, 28, 29, 30, 32, 52, 57, 66, 68, 71, 73, 74, 85, 88, 92, 95, 96, 101, 102, 106], "cuda_arch": 66, "cuda_architectur": [12, 21, 66], "cuda_graph": 57, "cuda_graph_batch_s": 71, "cuda_graph_cache_s": 71, "cuda_graph_config": [21, 28, 29, 30, 57, 71, 75], "cuda_graph_inst": 95, "cuda_graph_mod": [71, 88, 95], "cuda_hom": 68, "cuda_launch_block": 95, "cuda_stream": 95, "cuda_stream_guard": 88, "cuda_stream_sync": 83, "cudadevicegetstreampriorityrang": 1, "cudaevent_t": 1, "cudaeventdisabletim": 1, "cudagraph": 96, "cudagraphcaches": 0, "cudagraphconfig": [57, 71], "cudagraphlaunch": 95, "cudagraphmod": 0, "cudamalloc": [1, 2], "cudamallocasync": [1, 2], "cudamempool": 1, "cudamempoolptr": 1, "cudaprofilerapi": 73, "cudart": 95, "cudastream": 0, "cudastream_t": 1, "cudastreamcreatewithflag": 1, "cudastreamnonblock": 1, "cudastreamptr": [0, 1], "cudeviceptr": 1, "cudnn": 96, "cufil": 0, "cumemgenericallocationhandl": 1, "cumlogprob": [0, 1], "cumlogprobscba": 1, "cumsum": [83, 96], "cumsumgenerationlength": 1, "cumsumlastdim": 83, "cumsumlength": 1, "cumul": [0, 1, 58, 71, 83], "cumulative_logprob": [41, 71], "curand": 96, "curl": [32, 35, 64, 89], "currenc": 74, "current": [0, 1, 2, 3, 5, 10, 13, 21, 26, 27, 28, 29, 30, 31, 34, 41, 47, 56, 66, 67, 71, 74, 78, 80, 81, 82, 83, 88, 89, 91, 92, 94, 96, 98, 100, 101, 106, 107], "current_image_tag": 91, "current_stream": 95, "currentexpandindic": 1, "curv": [25, 31], "custom": [6, 17, 20, 22, 27, 28, 30, 31, 34, 45, 52, 58, 66, 70, 72, 78, 81, 83, 88, 91, 96, 100, 101], "custom_all_reduc": 96, "custom_mask": 83, "customallreduc": 96, "customized_key_dict": 18, "customized_preprocess": 18, "customizedmodulea": 18, "customizedmoduleb": 18, "cutedsl": 71, "cutlass": [12, 29, 71, 96], "cutlass_kernel": 12, "cxx11": 66, "cyclic": [65, 83, 88], "d": [1, 10, 12, 32, 35, 36, 38, 39, 40, 53, 54, 55, 56, 74, 83, 84, 89, 95, 96], "d0": 27, "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b": 74, "d_": 28, "d_6": 28, "dangl": 7, "data": [0, 1, 2, 5, 6, 8, 11, 17, 18, 22, 23, 24, 25, 26, 27, 30, 31, 33, 34, 52, 61, 71, 74, 75, 76, 83, 85, 91, 94, 95, 96, 99, 102], "data_path": 54, "data_typ": [14, 16], "datacontext": 0, "dataset": [27, 28, 29, 32, 35, 39, 54, 61, 71, 73, 78, 96], "dataset_fil": 75, "dataset_path": 74, "datatyp": [0, 1, 6, 17, 83, 88, 93, 95], "datatypetrait": 1, "date": 20, "datetim": 71, "db": 90, "dbrx": [93, 94, 96], "dbrxconfig": 85, "dbrxforcausallm": 85, "dconv": 83, "de": 1, "deactiv": 41, "dead": 96, "deal": [5, 7, 95], "dealloc": [1, 8, 107], "death": [45, 68, 89], "debug": [0, 8, 30, 33, 34, 35, 65, 66, 88, 92, 96], "debug_buff": 95, "debug_mod": [88, 95], "debug_tensors_to_sav": 88, "debugconfig": 0, "debuginputtensor": 0, "debugoutputtensor": 0, "debugtensor": 0, "debugtensornam": 0, "debugtensorsmaxiter": 0, "debugtensorsperiter": 0, "dec": [34, 88, 96], "decai": [0, 6, 71], "decid": [5, 16, 30, 65, 74, 79, 80, 93, 100, 107], "decilmforcausallm": 94, "decis": [30, 56, 83], "declar": [1, 6, 7, 20, 100, 106], "decltyp": [0, 1], "decod": [0, 1, 2, 5, 6, 15, 20, 27, 29, 30, 31, 32, 35, 46, 58, 65, 70, 71, 74, 83, 85, 88, 94, 96, 99, 102, 103, 105, 106], "decode_batch": 88, "decode_duration_m": 71, "decode_regular": 88, "decode_retention_prior": 71, "decode_stream": 88, "decode_words_list": 88, "decode_wrapp": 101, "decodedurationm": 0, "decoder_batch": 1, "decoder_input_id": [85, 88], "decoder_language_adapter_rout": 88, "decoder_lay": 99, "decoder_start_token_id": 34, "decoderbuff": 1, "decoderenginebuff": 0, "decoderetentionprior": 0, "decoderjsonconfigstr": 0, "decoderlay": 99, "decoderlayerlist": 15, "decoderlookaheadbuff": 1, "decodermaskedmultiheadattent": 5, "decodermodel": [0, 85, 99], "decodermodelforcausallm": [15, 20, 85, 99], "decodermodelpath": 0, "decoderst": 96, "decoderxqarunn": 5, "decoding_config": 71, "decoding_typ": [21, 28, 32, 71], "decodingbaseconfig": 71, "decodingconfig": [0, 1], "decodinginputptr": 1, "decodingit": 0, "decodinglayerworkspac": 1, "decodingmod": [0, 1, 96], "decodingoutputptr": 1, "decompos": [5, 30], "decor": 99, "decoupl": [12, 27, 30, 31, 92], "decreas": [22, 23, 78], "dedic": [27, 29, 30, 31, 95], "deduc": [30, 34, 35, 96], "deep": [17, 23, 24, 32, 73, 83, 96], "deepep": 30, "deeper": 28, "deepgemm": 21, "deeplearn": [17, 83, 95], "deepli": 30, "deepseek": [30, 35, 59, 64, 73, 75, 94, 96], "deepseek_v1": 96, "deepseek_v2": 96, "deepseek_v3": [27, 96], "deepseekforcausallm": 85, "deepseekv1config": 85, "deepseekv2": 83, "deepseekv2attent": 84, "deepseekv2config": 85, "deepseekv2forcausallm": 85, "deepseekv3forcausallm": 94, "deepseekv3routingimpl": 29, "deepspe": 16, "def": [7, 15, 17, 18, 20, 45, 47, 48, 49, 50, 51, 52, 56, 57, 58, 59, 68, 76, 78, 81, 82, 89, 95, 99, 107], "default": [0, 1, 2, 3, 4, 5, 6, 9, 12, 16, 18, 20, 28, 29, 33, 34, 35, 36, 41, 52, 57, 58, 59, 65, 66, 67, 71, 73, 75, 78, 79, 80, 81, 82, 83, 85, 88, 89, 90, 91, 92, 93, 95, 96, 99, 101, 103], "default_net": 83, "default_plugin_config": 85, "default_trtnet": 17, "defaultvalu": 1, "defer": 83, "defin": [0, 1, 3, 5, 7, 13, 16, 17, 18, 19, 20, 21, 24, 30, 33, 34, 72, 74, 81, 83, 84, 90, 91, 93, 96, 97, 99, 101], "definit": [3, 5, 8, 19, 20, 27, 65, 72, 83, 95], "deftruth": 96, "degrad": [0, 34, 78], "degre": [30, 45, 48, 49, 51, 68, 75, 78, 81, 89, 91], "delai": [30, 31, 75, 96], "deleg": [83, 101], "delet": [0, 1, 30, 86, 95], "deliv": [21, 22, 25, 27, 28, 75], "delta": [0, 27, 28, 83, 84], "delta_bia": 83, "delta_softplu": 83, "delv": 29, "demand": [27, 29, 30, 31, 52], "demo": [27, 35, 39, 58, 61], "demo_prompt": 58, "demonstr": [3, 18, 23, 27, 30, 31, 57, 58, 70, 76, 78, 80, 81], "demonstrate_beam_search": 58, "demonstrate_combined_sampl": 58, "demonstrate_greedy_decod": 58, "demonstrate_multiple_sequ": 58, "demonstrate_temperature_sampl": 58, "demonstrate_top_k_sampl": 58, "demonstrate_top_p_sampl": 58, "demonstrate_with_logprob": 58, "denois": 84, "denot": 13, "dens": [4, 5, 10, 16, 18, 83], "dense_4h_to_h": 18, "dense_bia": 84, "dense_h_to_4h": 18, "densiti": 26, "dep": 66, "dep4": 31, "dep8": 31, "depend": [0, 3, 5, 6, 7, 12, 13, 16, 24, 30, 31, 32, 35, 68, 71, 75, 76, 78, 81, 83, 92, 95, 96, 106], "deploi": [13, 16, 30, 35, 65, 68, 72], "deplot": [94, 96], "deploy": [26, 27, 30, 31, 32, 70, 72, 74, 78, 89, 96], "deprec": [12, 34, 71, 72, 74, 96], "deprecationwarn": 74, "depriorit": 12, "depriv": 7, "depth": 13, "dequ": [0, 1], "dequant": [5, 11, 65, 83], "deregistermemori": 0, "deriv": [17, 18, 83, 92, 100], "desc": 0, "descendli": 6, "describ": [0, 5, 6, 8, 9, 10, 13, 15, 17, 18, 19, 21, 25, 30, 31, 35, 37, 39, 58, 61, 66, 68, 74, 75, 81, 83, 90, 93, 95, 101], "descript": [0, 1, 6, 10, 33, 35, 57, 65, 74, 75, 81, 83, 101], "descriptor": 71, "deseri": [0, 20], "deserializeadditionalmodeloutput": 0, "deserializeadditionaloutput": 0, "deserializeagentst": 0, "deserializebool": 0, "deserializecachest": 0, "deserializecachetransceiverconfig": 0, "deserializecommst": 0, "deserializecontextphaseparam": 0, "deserializedatatransceiverst": 0, "deserializedebugconfig": 0, "deserializedecodingconfig": 0, "deserializedecodingmod": 0, "deserializedisservingrequeststat": 0, "deserializedynamicbatchconfig": 0, "deserializeeagleconfig": 0, "deserializeexecutorconfig": 0, "deserializeextendedruntimeperfknobconfig": 0, "deserializeexternaldrafttokensconfig": 0, "deserializeguideddecodingconfig": 0, "deserializeguideddecodingparam": 0, "deserializeinflightbatchingstat": 0, "deserializeiterationstat": 0, "deserializeiterationstatsvec": 0, "deserializekvcacheconfig": 0, "deserializekvcacheretentionconfig": 0, "deserializekvcachestat": 0, "deserializelookaheaddecodingconfig": 0, "deserializeloraconfig": 0, "deserializemodeltyp": 0, "deserializemropeconfig": 0, "deserializemultimodalinput": 0, "deserializeorchestratorconfig": 0, "deserializeoutputconfig": 0, "deserializeparallelconfig": 0, "deserializepeftcacheconfig": 0, "deserializeprompttuningconfig": 0, "deserializerequest": 0, "deserializerequestperfmetr": 0, "deserializerequeststag": 0, "deserializerequeststat": 0, "deserializerequeststatsperiter": 0, "deserializerequeststatsperiterationvec": 0, "deserializerespons": 0, "deserializeresult": 0, "deserializesamplingconfig": 0, "deserializeschedulerconfig": 0, "deserializesocketst": 0, "deserializespecdecfastlogitsinfo": 0, "deserializespecdecodingstat": 0, "deserializespeculativedecodingconfig": 0, "deserializestaticbatchingstat": 0, "deserializestr": 0, "deserializetensor": 0, "deserializetimepoint": 0, "deserializetokenrangeretentionconfig": 0, "design": [1, 11, 13, 17, 18, 20, 21, 26, 27, 28, 29, 31, 33, 70, 76, 89, 100, 101, 106], "desir": [3, 33, 75, 83, 89, 91, 101, 105], "destin": [53, 54, 55], "destroi": [1, 92], "destroyipcmemori": 1, "destructor": 1, "detach": 32, "detail": [0, 3, 5, 11, 13, 15, 17, 21, 27, 29, 30, 31, 34, 35, 41, 45, 47, 65, 74, 75, 76, 78, 82, 83, 85, 89, 90, 91, 92, 95, 96, 100, 101, 106], "detect": [0, 3, 30, 33, 35, 71, 83, 91, 96], "detect_format": 18, "determin": [0, 1, 5, 6, 10, 20, 28, 30, 31, 71, 77, 78, 82, 83, 85, 93, 97, 100, 106, 107], "determinenumpag": 1, "determinist": [58, 81, 96], "detoken": [71, 96, 100], "detokenizedgenerationresultbas": 71, "dev": [30, 32, 65, 68, 96], "dev_container_imag": 91, "devcontain": 91, "devel": [36, 37, 66], "develop": [15, 16, 17, 20, 27, 28, 30, 31, 32, 36, 45, 48, 49, 51, 65, 66, 68, 72, 76, 83, 89, 90, 91, 94, 96, 99], "deviat": [30, 33, 75], "devic": [0, 1, 30, 31, 52, 71, 78, 83, 85, 87, 88, 95], "device_id": 88, "device_map": 87, "device_memory_size_v2": 92, "device_num_expert": 83, "device_request_typ": 85, "deviceallocationnvl": 1, "devicecach": 1, "devicecacheperc": 0, "deviceid": [0, 1, 2], "dgx": [6, 17, 21, 29, 90], "di": [28, 30, 31], "diagon": 83, "diagram": [13, 29, 31], "diamond": [27, 29], "dict": [15, 18, 20, 71, 83, 85, 88, 96, 99, 106], "dict_kei": 95, "dictat": 80, "dictionari": [16, 18, 71, 84], "didn": 80, "differ": [0, 1, 2, 4, 5, 6, 8, 9, 11, 15, 16, 17, 18, 20, 21, 26, 28, 29, 30, 31, 33, 34, 35, 39, 58, 61, 66, 71, 72, 74, 76, 78, 80, 81, 83, 85, 88, 92, 93, 96, 97, 101, 105], "differenti": 83, "difftyp": 1, "diffus": [35, 39, 61, 84, 96], "diffusersattent": 84, "digit": 72, "dilat": [83, 84], "dim": [0, 1, 83, 84, 85, 88, 95], "dim0": 83, "dim1": 83, "dim_head": 84, "dim_in": 84, "dim_out": 84, "dim_rang": 83, "dimems": 1, "dimens": [0, 1, 5, 6, 10, 29, 30, 83, 84, 85, 92, 95, 96, 99], "dimension": 83, "diminish": 30, "dimrang": 83, "dimtype64": [0, 1], "dir": [33, 41, 66, 74], "direct": [0, 2, 11, 20, 31, 68, 95], "directli": [0, 2, 6, 7, 13, 17, 20, 28, 29, 30, 31, 37, 41, 66, 70, 74, 81, 82, 83, 89, 96, 97, 101, 107], "directori": [0, 3, 15, 16, 17, 18, 20, 30, 33, 34, 53, 54, 55, 66, 70, 71, 74, 75, 76, 85, 88, 89, 96, 97, 99], "disabl": [0, 1, 5, 6, 9, 14, 18, 30, 33, 34, 71, 74, 78, 81, 82, 83, 86, 88, 91, 92, 96, 103], "disable_forward_chunk": 85, "disable_kv_cach": 88, "disable_overlap_schedul": [29, 59, 71, 103], "disable_weight_only_quant_plugin": 85, "disable_xqa": 5, "disablelookahead": 1, "disablelookaheaddecod": 1, "disableseamlesslookaheaddecod": 1, "disadvantag": [20, 77], "disagg_config": 31, "disagg_executor": 0, "disaggexecutororchestr": 0, "disaggreg": [0, 65, 71, 96, 102], "disaggregated_mpi_work": 97, "disaggregated_param": 71, "disaggregatedparam": 71, "disaggserverbenchmark": 96, "discard": 78, "disclaim": [28, 76, 78, 80, 81], "disclosur": 96, "disconnect": 96, "discourag": [0, 6, 52, 71], "discov": [17, 58, 68], "discoveri": 91, "discrep": [31, 66, 99], "discuss": [5, 28, 30, 76, 78, 81, 82, 96], "disk": [3, 20, 66], "dispatch": [0, 4, 20, 27, 30, 31, 41], "displai": [30, 71], "disservingrequeststat": 0, "disservingstat": 0, "dist": [21, 54, 68, 73, 74, 75, 76], "distanc": [5, 83], "distil": 96, "distinct": [8, 10, 13, 27, 31, 83], "distinguish": 9, "distribut": [1, 4, 5, 6, 17, 27, 30, 33, 46, 53, 70, 74, 83, 88, 92, 97], "distserv": 2, "dit": [85, 96], "div": 83, "dive": [28, 72, 73], "divers": [0, 6, 73], "diversity_penalti": 6, "divid": [18, 28, 30, 83, 96], "divup": 83, "dl": 26, "dlsym": 0, "do": [1, 2, 7, 18, 20, 21, 26, 27, 28, 29, 30, 31, 33, 41, 65, 68, 71, 76, 78, 81, 83, 89, 90, 95, 99, 101], "do_cross_attent": [83, 84], "do_layer_norm_befor": 16, "do_sampl": 6, "doc": [1, 17, 21, 25, 27, 30, 37, 78, 81, 83, 95, 96], "docker": [21, 53, 54, 55, 65, 89, 95, 96], "docker_run_arg": 21, "dockerfil": [36, 66], "document": [0, 2, 5, 6, 8, 9, 10, 13, 15, 16, 17, 19, 20, 23, 24, 26, 28, 30, 31, 33, 35, 38, 39, 40, 41, 42, 43, 44, 47, 60, 61, 62, 63, 66, 67, 68, 69, 73, 75, 76, 82, 83, 89, 92, 93, 95, 100, 101], "doe": [0, 2, 5, 6, 10, 13, 20, 21, 22, 29, 30, 34, 63, 67, 71, 74, 75, 81, 83, 88, 89, 90, 91, 92, 94, 96, 99, 107], "doesn": [1, 5, 27, 36, 41, 59, 74, 80, 81], "dollar": 74, "domain": [11, 30], "domin": [27, 30, 96], "don": [13, 20, 29, 30, 36, 77, 81, 83], "done": [1, 9, 17, 21, 29, 30, 31, 32, 72, 74, 78, 80, 83, 86, 99], "dongjiyingdji": 96, "dora": [34, 83, 84], "dora_plugin": [10, 34, 83], "dot": [18, 27, 83], "doubl": [0, 23, 79, 81, 95], "down": [0, 3, 10, 22, 28, 29, 30, 56, 72, 77, 83, 88], "down_proj": 18, "download": [19, 53, 54, 55, 56, 59, 66, 68, 70, 74, 76, 89, 95, 96], "downscale_freq_shift": 84, "downsid": 81, "downstream": 93, "dp": [21, 22, 25, 27, 29, 31, 96, 97], "dp8": [27, 29], "dprank": 0, "dpsize": 0, "dq": 65, "draft": [0, 1, 27, 28, 32, 34, 65, 71, 85, 88, 96], "draft_len": 85, "draft_path": 88, "draft_target": [59, 71], "draft_target_model": 13, "draft_token": [71, 85], "draft_tokens_extern": [34, 85], "draftacceptancethreshold": 1, "draftbuff": 1, "drafter": [13, 71], "draftindic": 1, "draftlen": 1, "draftlogit": 1, "draftoverhead": 0, "draftparticipantid": 0, "draftpath": 1, "draftpathshost": 1, "draftprob": 1, "draftrequestid": 0, "drafttargetdecodingconfig": 71, "drafttoken": [0, 1], "drafttokenid": 1, "drafttokensextern": 1, "dram": [0, 17, 71], "drastic": 29, "dreamgenx": 96, "drive": [17, 52, 74], "driven": [30, 72], "driver": [30, 92, 96], "drop": [21, 28, 29, 78, 80, 82], "dropout": 84, "dropout_prob": 84, "dry_run": [34, 71, 96], "dst": 1, "dstate": 83, "dstdesc": 0, "dsttype": 1, "dt_proj": 83, "dt_rank": 83, "dtype": [1, 7, 10, 14, 15, 16, 17, 20, 71, 74, 76, 77, 83, 84, 85, 86, 87, 88, 95, 96, 106], "dual": 66, "due": [0, 12, 13, 20, 21, 24, 27, 29, 30, 32, 66, 74, 76, 80, 82, 88, 90, 91, 96, 101, 105], "dummi": [33, 71, 76, 96], "dump": [0, 3, 30, 66, 71], "dump_debug_buff": 88, "duplic": [29, 96], "duplicate_data": 83, "durat": [0, 30, 76], "duration_m": 71, "durationm": 0, "dure": [0, 1, 2, 5, 6, 7, 11, 12, 13, 14, 17, 25, 27, 28, 29, 30, 31, 34, 66, 71, 73, 74, 81, 82, 88, 90, 92, 95, 101, 106], "dynam": [0, 2, 27, 28, 30, 31, 34, 71, 74, 83, 85, 88, 92, 96, 107], "dynamic_batch_config": 71, "dynamic_batch_moving_average_window": 71, "dynamic_quant_bf16tonvfp4": 27, "dynamic_tree_max_topk": 71, "dynamicbatchconfig": [0, 71], "dynamicbatchmovingaveragewindow": 0, "dynamicbatchsizeconfig": 0, "dynamicdecodelay": 1, "dynamicqu": 27, "dynamictreemaxtopk": 0, "dynamictreemaxtopkhost": 1, "dynamo": [13, 70], "dynlibload": 0, "e": [0, 2, 3, 5, 8, 9, 10, 11, 18, 28, 29, 32, 35, 36, 53, 54, 55, 66, 67, 70, 71, 73, 74, 83, 86, 88, 89, 91, 93, 95, 96, 97, 99, 103], "e2": [29, 31, 65], "e4m3": [11, 23], "e5m2": 23, "e752184d1181494c940579c007ab2c5f": 32, "each": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 16, 17, 21, 27, 28, 29, 30, 31, 33, 34, 35, 41, 52, 53, 54, 55, 58, 71, 74, 75, 76, 77, 80, 81, 82, 83, 84, 86, 88, 90, 92, 93, 95, 96, 97, 100, 101, 106, 107], "eager": [29, 72, 96], "eagl": [0, 1, 32, 34, 65, 71, 85, 88, 96, 102, 105], "eagle3": [13, 59, 71], "eagle3_one_model": [59, 71], "eagle_choic": [71, 88], "eagle_dynamic_tree_max_top_k": 88, "eagle_posterior_threshold": 88, "eagle_temperatur": 85, "eagle_use_dynamic_tre": 88, "eaglechoic": [0, 1], "eagleconfig": [0, 1, 85], "eagledecodingconfig": [59, 71], "eagleforcausallm": 85, "eagleinput": 1, "eaglenetctxcontextlengthshost": 1, "eaglenetctxpastkeyvaluelengthshost": 1, "eaglenetctxrequesttypeshost": 1, "eaglenetgencontextlengthshost": 1, "eaglenetgenpastkeyvaluelengthshost": 1, "eaglenetgenrequesttypeshost": 1, "ealge2": 28, "earli": [88, 95, 96], "earlier": [0, 16, 78, 95], "early_stop": [6, 71, 88, 96], "early_stop_criteria": 88, "earlystop": [0, 1, 6], "eas": [19, 30, 31, 72, 75], "easi": [26, 30, 70, 76], "easier": [17, 20, 21, 28, 30, 74], "easili": [18, 19, 21, 27, 30, 72, 83, 89], "east": [15, 17, 95], "eastern": 89, "ebnf": [0, 3, 71], "echo": [32, 35, 36, 37, 54, 55], "ecosystem": 70, "eddi": 96, "edg": 23, "edit": [13, 66, 91], "ef648e7489c040679d87ed12db5d3214": 89, "effect": [0, 2, 6, 11, 13, 27, 28, 29, 34, 52, 58, 68, 71, 78, 80, 81], "effici": [4, 5, 6, 9, 13, 17, 19, 27, 28, 29, 30, 31, 34, 35, 39, 45, 48, 49, 51, 61, 68, 89, 90, 92, 94, 98, 100, 101, 106], "effort": [13, 16, 28, 29, 30, 31, 78, 96], "eg": 75, "eight": [21, 22], "einop": 83, "einstein": 83, "einsum": 83, "einsum_eq": 83, "either": [0, 1, 3, 19, 27, 29, 70, 71, 83, 90, 92, 95, 96], "element": [0, 1, 5, 6, 10, 11, 30, 71, 83, 84, 90, 93], "element_typ": 1, "elementwis": [7, 83], "elementwise_affin": 84, "elementwise_binari": 83, "elementwise_sub": 7, "elementwise_sum": 7, "elementwiseoper": [7, 83], "eleutherai": 74, "elif": [58, 59, 107], "elimin": [2, 13, 27, 29, 34, 72, 74, 78, 80, 96], "ellipsi": 83, "els": [0, 17, 18, 20, 41, 52, 59, 83, 95, 107], "emb": [17, 61, 84], "embark": 72, "embed": [0, 9, 15, 28, 34, 71, 74, 83, 88, 96, 99, 101], "embed_dim": 84, "embed_posit": 84, "embed_positions_for_gpt_attent": 84, "embed_positions_for_gpt_attention_loc": 84, "embed_positions_loc": 84, "embed_token": [18, 99], "embedding_bia": 71, "embedding_dim": 84, "embedding_multipli": 85, "embedding_parallel_mod": 71, "embedding_scal": 85, "embedding_sharding_dim": [16, 85], "embeddingbia": [0, 1], "embeddingt": [0, 1], "emerg": [26, 27, 30], "emit": 71, "emot": 58, "emphasi": 16, "empir": 30, "emploi": [13, 30, 31, 100, 107], "employe": 52, "empow": 27, "empti": [0, 1, 13, 41, 83, 96, 107], "emptybuff": 1, "emptygenslot": 0, "emptytensor": 1, "emul": [83, 96], "en": 96, "enabl": [0, 2, 3, 5, 6, 7, 10, 11, 12, 13, 14, 17, 18, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 41, 50, 51, 52, 57, 58, 65, 66, 71, 74, 76, 80, 82, 83, 84, 85, 86, 88, 89, 91, 93, 95, 96, 97, 99, 101, 103, 105, 106], "enable_allreduc": 83, "enable_attention_dp": [21, 30, 32, 35, 54, 71], "enable_autotun": 71, "enable_batch_size_tun": 71, "enable_block_reus": [32, 35, 57, 71], "enable_build_cach": [71, 96], "enable_chunked_context": [33, 88, 96], "enable_chunked_prefil": [71, 96], "enable_context_fmha_fp32_acc": [71, 88], "enable_debug_output": [34, 71, 95], "enable_forward_chunk": 85, "enable_fp8": 11, "enable_fullgraph": 71, "enable_if_t": 1, "enable_inductor": 71, "enable_iter_perf_stat": [35, 71], "enable_iter_req_stat": 71, "enable_kv_cache_reus": 9, "enable_layerwise_nvtx_mark": 71, "enable_lora": [56, 71], "enable_max_num_tokens_tun": [71, 96], "enable_min_lat": 71, "enable_mixed_sampl": 71, "enable_multi_devic": 96, "enable_overlap_schedul": 35, "enable_pad": [21, 29, 57, 71, 75], "enable_partial_reus": 71, "enable_pdl": 97, "enable_piecewise_cuda_graph": 71, "enable_prompt_adapt": [71, 96], "enable_qkv": 84, "enable_tqdm": 71, "enable_trt_overlap": 96, "enable_trtllm_sampl": [71, 105], "enable_ucx": 96, "enable_userbuff": 71, "enable_xqa": 96, "enableattentiondp": [0, 1], "enablebatchsizetun": 0, "enableblockreus": [0, 9], "enablechunkedcontext": 0, "enablecontextfmhafp32acc": 0, "enabled_with_fp32_acc": 5, "enablelookaheaddecod": 1, "enablemaxnumtokenstun": 0, "enablepartialreus": 0, "enableseamlesslookaheaddecod": [0, 1], "enabletrtoverlap": 0, "enc": [34, 88, 96], "enc_dec": 6, "encapsul": [5, 6, 17, 83], "encdecmodelrunn": 88, "encod": [0, 5, 6, 23, 27, 34, 52, 71, 83, 88, 93, 94, 96], "encode_base64_content_from_url": 61, "encoded_vocab": [0, 3], "encodedvocab": [0, 3], "encoder_hidden_st": [84, 85], "encoder_input_featur": 88, "encoder_input_id": 88, "encoder_input_len_rang": 96, "encoder_input_length": [83, 84, 88], "encoder_language_adapter_rout": 88, "encoder_max_input_length": [84, 88], "encoder_output": [84, 85, 88], "encoder_output_length": 88, "encoder_run": 88, "encoderenginebuff": 0, "encoderhiddens": 1, "encoderinputfeatur": 0, "encoderinputtokenid": 0, "encoderjsonconfigstr": 0, "encoderlen": 0, "encodermodel": [0, 85], "encodermodelpath": 0, "encoderoutput": 0, "encoderoutputlength": 0, "encount": [18, 21, 32, 68, 95], "encourag": [0, 6, 20, 30, 52, 71], "end": [0, 1, 5, 6, 17, 28, 33, 34, 52, 71, 72, 74, 78, 81, 82, 83, 89, 96, 106], "end_dim": 83, "end_id": [71, 88, 96], "end_thinking_phase_token": 71, "end_token": [0, 71], "endeavor": [27, 30, 31], "endid": [0, 1], "endpoint": [32, 43, 44, 71, 89, 96, 97], "endswith": 18, "enforc": [76, 83], "engin": [0, 1, 2, 3, 5, 6, 7, 10, 13, 14, 19, 20, 25, 27, 28, 29, 30, 31, 33, 34, 35, 41, 56, 65, 68, 75, 77, 78, 80, 81, 82, 83, 85, 88, 92, 95, 96, 102], "engine_buff": 88, "engine_dir": [14, 15, 16, 17, 20, 33, 74, 76, 88, 89, 95], "engine_inspector": 88, "engine_llama_3": 17, "engine_nam": 88, "engine_output": 34, "engineaddr": 1, "enginebuff": [0, 1], "enginefilenam": 1, "engineinput": 1, "engineoutput": 1, "enginepath": 1, "engines": 1, "enhanc": [4, 6, 13, 21, 27, 28, 29, 30, 31, 33, 52, 72, 82, 92, 98, 101], "enjoi": [37, 45, 48, 49, 51, 68, 89], "enough": [5, 9, 21, 28, 80, 92, 100, 107], "enqueu": [0, 3, 17, 88, 92, 96], "enqueuecontext": 0, "enqueuegener": 0, "enqueuerequest": [0, 3], "ensembl": 31, "ensur": [2, 3, 4, 7, 12, 20, 28, 30, 32, 33, 66, 71, 74, 80, 86, 99, 106], "enter": [7, 36, 66, 75, 80, 106], "enterpris": 47, "entir": [0, 3, 10, 17, 22, 27, 30, 72, 74, 75, 83, 92, 106], "entri": [0, 10, 33, 51, 66, 74, 83, 90, 96, 97], "entrypoint": [36, 70, 76], "enum": [0, 1], "enumer": [0, 1, 50, 52, 57, 58], "env": [35, 38, 39, 40, 42, 43, 44, 74, 91], "envelop": 30, "environ": [6, 11, 13, 21, 27, 30, 31, 35, 39, 53, 54, 55, 61, 63, 65, 66, 68, 73, 74, 76, 78, 80, 81, 95, 96, 97, 98, 101], "environment": 18, "eo": [6, 33, 52, 71], "eof": [21, 28, 30, 35, 54], "eos_id": [30, 33], "eos_token": 52, "eos_token_id": [3, 52, 88], "ep": [4, 21, 27, 28, 31, 33, 35, 74, 83, 84], "ep2": 27, "ep2tp4": 27, "ep32": 30, "ep4": 30, "ep4tp2": 27, "ep8": [29, 30], "ep8tp8": 27, "ep_load_balanc": 30, "ep_siz": [30, 32, 35, 42], "epsilon": [0, 83], "eq": 83, "equal": [0, 1, 3, 4, 29, 30, 34, 41, 77, 83, 84, 92], "equal_progress": [71, 82], "equat": [25, 83], "equip": 19, "equival": [27, 29, 78, 83, 89, 99], "equvili": 34, "erenup": 96, "err": [53, 54, 55], "error": [0, 2, 3, 10, 20, 29, 32, 33, 34, 35, 65, 66, 68, 71, 76, 80, 91, 92, 96], "errorcod": 70, "errormsg": 0, "especi": [2, 7, 28, 30, 31, 34, 45, 48, 49, 51, 68, 77, 80, 89, 106], "essenti": [13, 30, 74], "establish": [2, 29, 30, 31], "estim": [30, 74, 96, 107], "et": 22, "etc": [0, 1, 13, 30, 70, 71, 73, 74, 78, 81, 88, 92, 95, 99], "ethnzhng": 96, "eval": 47, "evalu": [11, 21, 23, 24, 29, 31, 65, 96], "even": [5, 6, 17, 20, 26, 27, 30, 31, 34, 76, 80, 83, 91, 92], "evenli": [4, 27], "event": [0, 1, 65, 71], "event_buffer_max_s": 71, "eventbuffermaxs": 0, "eventid": 0, "eventptr": 1, "eventu": 12, "ever": [0, 81], "everi": [0, 3, 18, 27, 29, 30, 31, 52, 74, 76, 77, 83, 88, 90], "everyon": 28, "everyth": 17, "evict": [0, 1, 8, 9, 10, 28, 33, 72, 74, 76, 80], "evolv": [5, 20, 27, 72, 93, 106], "ex": [54, 55], "exact": [5, 21, 92], "exactli": 90, "exam": 27, "examin": [13, 30], "exampl": [0, 2, 5, 6, 7, 9, 12, 13, 14, 15, 19, 20, 22, 24, 26, 28, 30, 31, 35, 41, 47, 53, 58, 65, 66, 67, 71, 75, 76, 77, 78, 79, 80, 81, 82, 83, 88, 89, 90, 91, 92, 93, 94, 95, 96, 98, 99, 101, 104, 105, 107], "example_cuda_graph_config": 57, "example_kv_cache_config": 57, "exaon": [18, 94, 96], "exc": 50, "exce": [0, 71, 82, 83], "exceed": [0, 92], "except": [0, 3, 5, 6, 20, 27, 28, 30, 34, 52, 77, 83, 95, 96], "excess": [5, 30], "exchang": 71, "excit": [45, 48, 49, 50, 51, 68, 89], "exclud": [1, 71, 78, 83, 96], "exclude_input_from_output": 71, "exclude_modul": [16, 71, 96], "excludeinputfromoutput": 0, "exclus": [1, 6, 93, 96], "exec": [73, 89], "execut": [0, 3, 6, 10, 13, 17, 19, 20, 27, 29, 30, 31, 65, 71, 72, 73, 74, 80, 82, 83, 88, 89, 90, 91, 92, 97, 100, 107], "executor": [1, 2, 9, 13, 14, 19, 31, 41, 56, 65, 71, 72, 74, 82, 88, 92, 96, 100], "executor_config": 106, "executorconfig": [0, 2, 3, 14], "executorexamplefastlogit": 96, "exhaust": [0, 19, 31], "exist": [1, 6, 9, 10, 13, 18, 20, 27, 29, 30, 34, 63, 66, 71, 74, 88, 91, 96, 101], "exit": [30, 75, 88], "exp": 83, "expand": [0, 24, 26, 28, 83, 88, 96], "expand_dim": 83, "expand_dims_lik": 83, "expand_mask": 83, "expand_shap": 83, "expanded_idx_to_permuted_idx": 83, "expans": 83, "expect": [0, 5, 6, 11, 15, 17, 18, 20, 24, 28, 30, 31, 32, 34, 41, 53, 54, 55, 65, 71, 74, 76, 79, 83, 95, 96], "expens": [3, 13, 31, 72, 77, 78, 82], "experi": [12, 13, 25, 26, 27, 29, 30, 31, 52, 70, 72, 73, 74, 95, 97], "experiment": [5, 6, 13, 18, 28, 35, 53, 54, 55, 65, 74, 93, 96, 98], "expert": [10, 21, 33, 35, 51, 65, 71, 81, 96], "expert_scale_factor": 83, "expert_statist": 30, "expert_statistic_eplb": 30, "expert_statistic_iter_rang": 30, "expert_statistic_path": 30, "expertid": 30, "expertis": [27, 29, 30, 31], "expir": 0, "explain": [2, 6, 17, 19, 29, 80, 83, 90, 92, 93, 100, 101], "explan": [21, 29, 81, 88, 90, 92], "explicit": [0, 1, 13, 30, 83, 96], "explicit_draft_token": [13, 34, 85], "explicitdrafttoken": [0, 1], "explicitdrafttokensdtyp": 1, "explicitdrafttokensinput": 1, "explicitdrafttokensmodul": 1, "expliciteosstop": 0, "explicitli": [1, 2, 7, 13, 17, 18, 29, 30, 34, 35, 41, 71, 96], "explor": [13, 27, 29, 30, 72], "expon": 23, "exponenti": [13, 31], "export": [16, 20, 21, 27, 28, 30, 34, 35, 43, 44, 53, 54, 55, 74, 87, 88, 95, 96], "export_fmt": 104, "expos": [0, 6, 17, 32, 37, 66, 78, 89, 96], "express": [0, 3, 71, 83], "extend": [0, 3, 9, 17, 27, 28, 29, 30, 70, 71, 81, 83, 96], "extended_runtime_perf_knob_config": [71, 96], "extendedruntimeperfknobconfig": [0, 71], "extens": [16, 19, 31, 68, 72, 74, 90, 96], "extern": [0, 7, 8, 18, 88, 92], "external_checkpoint_dir": 18, "external_kei": 18, "external_weight": 18, "externaldrafttoken": 0, "externaldrafttokensconfig": [0, 1], "externaldrafttokensinput": 1, "externalstream": 52, "extra": [0, 2, 5, 9, 13, 16, 21, 27, 28, 34, 35, 42, 68, 71, 74, 75, 77, 78, 88, 90, 96, 103], "extra_arg": 54, "extra_bodi": 63, "extra_id": 9, "extra_llm_api_opt": [21, 28, 30, 32, 33, 35, 42, 54, 74, 75], "extra_llm_api_options_eplb": 30, "extra_resource_manag": 71, "extra_token": 84, "extract": [0, 3, 30, 33, 66, 73, 79, 83, 88], "extrapol": 83, "extrem": [17, 27, 30, 78, 80, 81], "f": [0, 5, 6, 32, 36, 45, 47, 48, 49, 50, 51, 52, 56, 57, 58, 59, 63, 68, 71, 73, 76, 82, 83, 89, 95], "face": [3, 10, 14, 19, 20, 30, 41, 71, 74, 85, 89, 96], "facilit": [7, 13, 30, 31, 89], "fact": [72, 74, 81], "factor": [26, 29, 30, 52, 77, 78, 83, 84, 92, 93], "factori": [20, 71, 88, 96], "factual": 6, "fail": [30, 32, 71, 88, 91, 92, 95, 107], "failur": [18, 30, 96], "fairli": 17, "fairseq": [94, 96], "fake": [9, 96], "fakebuff": 1, "falcon": [16, 26, 74, 93, 94, 96], "falconconfig": 85, "falconforcausallm": 85, "falconmodel": 85, "fall": [11, 68, 75, 96], "fallback": 18, "fals": [0, 1, 2, 3, 5, 6, 7, 9, 16, 27, 29, 32, 34, 35, 47, 52, 54, 71, 83, 84, 85, 86, 87, 88, 96, 97], "false_output_valu": 83, "false_valu": 83, "famili": [5, 18, 30, 90, 94, 96], "familiar": [6, 17, 70, 76, 77, 79, 89], "famou": 6, "faq": 65, "far": [0, 3, 28], "fast": [0, 5, 8, 13, 30, 32, 71, 74, 77, 96], "fast_build": [34, 71, 96], "fastapi": 96, "fastapi_serv": 96, "faster": [5, 20, 23, 24, 28, 29, 34, 75, 76, 83], "fastlogit": 0, "fault": [30, 96], "favor": 96, "favorit": 56, "fc": [16, 17, 18, 95], "fc_gate": 84, "fc_gate_dora": 84, "fc_gate_lora": 84, "fc_gate_plugin": 84, "featur": [0, 2, 3, 5, 7, 8, 10, 11, 13, 16, 17, 18, 20, 26, 27, 28, 29, 30, 31, 33, 34, 53, 54, 55, 65, 66, 70, 74, 78, 80, 81, 82, 83, 86, 88, 89, 90, 91, 94, 99, 101, 105], "feature_dim": 88, "februari": 29, "fed": [75, 85], "feed": 83, "feedback": [30, 96], "feedforward": 4, "feel": 56, "fetch": [0, 28, 35, 100], "few": [2, 9, 17, 20, 26, 28, 29, 30, 68, 80], "fewer": [5, 13, 22, 101], "ffn": [4, 27], "ffn_hidden_s": 84, "fhma": 96, "field": [0, 6, 11, 16, 20, 35, 37, 41, 71, 72, 74, 78, 85, 86, 93, 96, 101], "field_nam": 71, "fifo": 30, "figur": [27, 28, 30, 31], "file": [0, 3, 4, 5, 7, 9, 16, 17, 18, 20, 21, 28, 30, 32, 33, 34, 35, 43, 44, 73, 74, 75, 88, 89, 90, 91, 96, 99], "filenam": 33, "filepath": 1, "filesystem": [0, 1], "fill": [18, 37, 45, 68, 83, 89, 101], "fill_attention_const_params_for_long_rop": 84, "fill_attention_const_params_for_rop": 84, "fill_attention_param": 84, "fill_none_tensor_list": 84, "fill_valu": 83, "fillemptyfieldsfromruntimedefault": 0, "filloper": 83, "filltaskstensor": 1, "filter_medusa_logit": 88, "final": [0, 1, 10, 27, 28, 30, 31, 34, 35, 36, 41, 83, 107], "final_logit_softcap": 85, "final_output_id": 88, "finalize_decod": 88, "find": [21, 29, 30, 31, 65, 78, 83, 95, 96], "find_best_medusa_path": 88, "fine": [13, 21, 29, 30, 74, 81, 84], "finer": 7, "finetun": 27, "finish": [0, 1, 3, 6, 8, 20, 28, 30, 41, 71, 72, 74, 88, 100, 106], "finish_reason": [32, 71, 89, 96], "finishedst": 1, "finishedsum": 1, "finishreason": [0, 1, 96], "first": [0, 1, 2, 3, 5, 6, 7, 9, 10, 13, 19, 24, 26, 28, 29, 30, 31, 32, 34, 35, 36, 58, 66, 70, 71, 74, 75, 76, 78, 80, 81, 82, 83, 90, 92, 95, 96, 99, 101, 106, 107], "first_come_first_serv": [71, 82], "first_gen_token": 71, "first_lay": 88, "firstgentoken": 0, "firstit": 0, "firstli": [29, 30, 36, 80, 92], "firstscheduledtim": 0, "firsttokentim": 0, "fit": [1, 5, 22, 23, 71, 77, 78, 107], "fitting_request": 107, "fix": [8, 10, 13, 28, 29, 31, 74, 92], "fjosw": 96, "flag": [0, 1, 3, 5, 10, 20, 25, 30, 33, 35, 41, 65, 74, 78, 79, 80, 82, 83, 92, 96], "flags_siz": 1, "flan": [93, 94], "flash": [5, 17], "flashattent": [5, 17, 89], "flashinf": 101, "flashinferattent": 101, "flashmla": [28, 96], "flatten": [1, 10, 25, 30, 83, 84], "flattenedinouts": 1, "flattenn": 1, "flayer": 7, "flayerinfomemo": 7, "flexibl": [13, 20, 27, 30, 41, 66, 70], "flight": [1, 19, 65, 74, 80, 82, 89, 92, 96], "flip": 83, "flip_sin_to_co": 84, "float": [0, 1, 6, 14, 16, 17, 23, 52, 71, 82, 83, 84, 85, 88, 93], "float16": [7, 10, 14, 15, 16, 20, 34, 77, 83, 85, 86, 89, 95], "float2": 83, "float32": [0, 16, 34, 83, 84, 85, 86], "floattensor": 99, "floattyp": [0, 1], "floor_div": 83, "floordiv": 83, "flop": 29, "flow": [7, 20, 27, 29, 31, 76, 77, 78, 80, 81, 96, 100, 107], "fluctuat": 2, "fly": [5, 83, 93], "fmha": [0, 34, 71, 83, 88, 92, 96], "fmt_dim": 1, "focu": [7, 26, 27, 30, 52, 73], "focus": [13, 58, 74, 78, 79, 96], "fold": 92, "folder": [0, 3, 6, 20, 76, 91, 93, 94, 96], "folder_trt_llm": 17, "follow": [2, 3, 6, 7, 10, 12, 13, 15, 16, 17, 18, 20, 21, 26, 27, 28, 29, 30, 32, 34, 35, 37, 41, 49, 50, 53, 54, 55, 66, 68, 70, 74, 75, 76, 77, 78, 79, 80, 81, 83, 89, 90, 91, 93, 94, 96, 97, 99, 101, 104, 105, 106], "footprint": [5, 22, 29, 92], "for_each_rank": 85, "forbid": 71, "forc": [0, 5, 27, 30, 31, 71, 74, 91], "force_drop_id": 84, "force_dynamic_quant": 71, "force_multi_block_mod": 74, "force_nccl_all_reduce_strategi": 96, "force_num_profil": 71, "force_words_id": 6, "forecast": 13, "fork": 73, "form": [0, 3, 5, 13, 31, 71, 83, 89], "format": [0, 3, 11, 16, 18, 20, 23, 26, 28, 29, 32, 33, 44, 65, 66, 71, 72, 76, 78, 88, 89, 92, 95, 96, 101], "former": [17, 26], "formula": [29, 31, 83], "forth": 30, "forthcom": 32, "forum": 96, "forward": [0, 1, 7, 13, 15, 17, 28, 30, 31, 82, 83, 84, 85, 95, 96, 99, 100, 101, 106, 107], "forward_loop": 74, "forward_with_cfg": 85, "forward_without_cfg": 85, "forwardasync": 1, "forwarddispatch": 1, "forwardsync": 1, "found": [3, 4, 5, 6, 7, 13, 17, 19, 21, 23, 30, 52, 66, 68, 74, 76, 78, 81, 91, 93, 107], "foundat": 28, "four": [3, 7, 13, 16, 27, 28, 84], "fourth": 3, "fp": [93, 96], "fp16": [5, 10, 11, 14, 16, 18, 22, 23, 26, 34, 65, 74, 78, 81, 83, 89, 94, 95, 96], "fp32": [0, 5, 27, 29, 34, 65, 71, 83, 88, 89, 94, 95, 96], "fp4": [21, 28, 29, 30, 34, 59, 70, 96], "fp4_gemm": 12, "fp8": [11, 20, 22, 24, 25, 26, 27, 28, 29, 30, 32, 33, 34, 45, 48, 65, 68, 70, 71, 74, 79, 81, 83, 86, 89, 92, 94, 96, 101, 104, 105], "fp8_block_scal": 71, "fp8_blockscale_gemm": 96, "fp8_inputs_overrid": 83, "fp8_kv_cach": [5, 93], "fp8_per_channel_per_token": 71, "fp8_qdq": 93, "fp8_rowwise_gemm_plugin": 34, "fp_valu": 5, "fpa_intb": 96, "frac": 31, "fraction": [0, 31, 35, 71, 83, 84, 88, 97], "framework": [13, 15, 16, 19, 20, 72, 83, 96], "franc": [15, 17, 45, 48, 49, 50, 51, 57, 59, 68, 76, 82, 89, 95], "free": [0, 1, 8, 10, 17, 18, 29, 30, 35, 52, 72, 80, 84, 85, 88, 92, 106], "free_gpu_memory_fract": [35, 41, 57, 71, 82, 96], "free_resourc": [100, 106], "freed": 74, "freedom": 20, "freegpumemoryfract": [0, 92, 96], "freenumblock": 0, "freez": 29, "french": 89, "freq": 83, "frequenc": [74, 84], "frequency_penalti": [71, 88, 96], "frequencypenalti": [0, 1, 6], "frequent": [9, 71, 95], "friend": [0, 1, 74], "friendli": [30, 83], "from": [0, 1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 24, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 41, 45, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 65, 67, 68, 71, 72, 74, 75, 76, 77, 78, 80, 81, 82, 83, 84, 85, 87, 88, 89, 90, 91, 92, 95, 96, 97, 99, 100, 101, 103, 104, 105, 106, 107], "from_argu": 85, "from_checkpoint": [20, 85], "from_config": 85, "from_dict": [71, 85], "from_dir": 88, "from_engin": 88, "from_hugging_fac": [15, 18, 20, 85], "from_jax": 20, "from_json_fil": [71, 85], "from_kera": 20, "from_meta_ckpt": [20, 85], "from_nemo": [20, 85], "from_pretrain": 85, "from_prun": 85, "from_serialized_engin": 88, "from_str": 83, "fromfil": 17, "fruit": 29, "full": [0, 4, 5, 6, 9, 10, 13, 23, 24, 28, 29, 30, 31, 35, 52, 71, 72, 73, 74, 77, 83, 88, 89, 90, 92, 95], "full_stop_token": 52, "fulli": [29, 45, 90, 96], "funcnam": 0, "function": [0, 1, 3, 5, 14, 15, 17, 19, 20, 27, 28, 30, 57, 70, 71, 72, 73, 81, 85, 86, 88, 92, 93, 94, 95, 96, 106, 107], "functiont": 0, "further": [3, 4, 5, 13, 17, 22, 26, 28, 29, 30, 31, 32, 34, 74, 78, 81, 101], "furthermor": [13, 27, 30, 31, 78], "fuse": [5, 13, 17, 27, 29, 34, 81, 83, 89, 96, 99, 101], "fuse_a": [27, 29], "fuse_fp4_qu": 34, "fuse_qkv_project": 85, "fuseattentionwithbiaspass": 7, "fused_gate_up_dora": 84, "fused_gate_up_lora": 84, "fused_mo": 71, "fusedgatedmlp": [83, 84], "fusevalu": 1, "fusion": [7, 29, 34, 65, 72, 80, 92, 93, 96, 101], "fusion_op": 83, "futur": [2, 5, 6, 8, 12, 13, 18, 20, 26, 30, 34, 45, 47, 48, 49, 50, 51, 52, 57, 58, 59, 66, 68, 71, 72, 74, 76, 82, 83, 89, 92, 93, 96, 98], "fuyu": [94, 96], "g": [3, 8, 11, 18, 28, 29, 35, 53, 54, 55, 67, 71, 74, 80, 88, 89, 91, 97, 99, 103], "g1": 80, "g2": 80, "gain": [30, 77, 80], "game": 32, "gamma": 83, "gap": 31, "garbag": 71, "garbage_collection_gen0_threshold": 71, "gate": [10, 18, 34, 76, 83, 96], "gate_a": 83, "gate_a_bia": 83, "gate_bia": 83, "gate_proj": 18, "gate_x": 83, "gate_x_bia": 83, "gatedmlp": [83, 84], "gather": [0, 1, 34, 49, 50, 71, 83, 88], "gather_all_token_logit": [34, 96], "gather_context_logit": [34, 71, 85, 88], "gather_dim": [17, 83], "gather_generation_logit": [34, 71, 85, 88], "gather_last_token_logit": 83, "gather_nd": 83, "gather_output": 84, "gathercontext": [0, 96], "gatheredid": 1, "gatherel": 83, "gathergenerationlogit": 0, "gathermod": 83, "gathertre": 1, "gatherv2": 83, "gb": [2, 24, 29, 66, 71, 74], "gb200": [29, 31, 94, 96], "gcc": 66, "gd": 0, "geforc": 96, "gegelu": 83, "gegelu_limit": 84, "geglu": 83, "gelu": [83, 85], "gelu_pytorch_tanh": 96, "gelu_tanh": 84, "gemm": [7, 29, 30, 34, 80, 83, 89, 92, 96], "gemm_allreduc": 83, "gemm_allreduce_plugin": [34, 88], "gemm_fc1": 27, "gemm_plugin": [10, 14, 16, 17, 34, 74, 78, 81, 84, 89], "gemm_swiglu": 83, "gemm_swiglu_plugin": [34, 78, 86], "gemma": [20, 93, 94, 96], "gemma2": 94, "gemma2_added_field": 85, "gemma2_config": 85, "gemma3": 96, "gemma3_added_field": 85, "gemma3_config": 85, "gemma_added_field": 85, "gemma_config_kwarg": 85, "gemmaconfig": 85, "gemmaforcausallm": 85, "gen": [31, 71, 96], "gen2dep4": 31, "gen4": 31, "gen8": 31, "gen_batch_s": 97, "gen_enable_attention_dp": 97, "gen_gpu_memory_fract": 97, "gen_max_num_token": 97, "gen_tp_siz": 97, "genai": [26, 35, 64], "genattent": 27, "genenginepath": 0, "gener": [0, 1, 3, 6, 9, 13, 16, 17, 18, 20, 21, 22, 23, 25, 27, 28, 29, 31, 33, 34, 45, 46, 57, 58, 59, 65, 67, 68, 70, 71, 72, 73, 74, 75, 76, 77, 79, 80, 81, 82, 83, 85, 88, 89, 91, 92, 94, 95, 96, 97, 99, 100, 101, 104, 105, 106, 107], "generate_alibi_bias": 83, "generate_alibi_slop": 83, "generate_async": [41, 49, 50, 71, 96], "generate_eplb_config": 30, "generate_logn_sc": 83, "generate_tllm_weight": 18, "generated_text": [56, 76, 82], "generatedtokensperenginestep": 1, "generation_complet": 107, "generation_in_progress": 107, "generation_logit": [71, 88], "generation_onli": 71, "generation_phas": 5, "generation_request": 107, "generation_serv": 31, "generation_to_complet": 107, "generationexecutor": [2, 96], "generationlength": 1, "generationlengthsdevic": 1, "generationlengthshost": 1, "generationlengthshostcopi": 1, "generationlogit": 0, "generationmixin": 85, "generationresult": 71, "generationsequ": 88, "generationsess": [5, 88, 92], "generationstep": 1, "genericprompttuningparam": 1, "genert": 2, "genexecutorconfig": 0, "genidx": 0, "genlengthlogitsprocessor": 52, "genlenthlogitsprocesor": 52, "genreqr": 31, "genrequest": 1, "get": [0, 1, 3, 5, 7, 10, 14, 18, 25, 28, 29, 30, 32, 35, 36, 37, 41, 58, 63, 66, 68, 71, 72, 73, 76, 78, 83, 88, 89, 95, 96, 104, 107], "get_1d_sincos_pos_embed_from_grid": 84, "get_2d_sincos_pos_emb": 84, "get_2d_sincos_pos_embed_from_grid": 84, "get_audio_featur": 88, "get_batch_cache_indic": 106, "get_batch_idx": 88, "get_block_offset": 88, "get_buff": 106, "get_build_config_default": 71, "get_comm": 71, "get_config_group": 85, "get_context_phase_param": 71, "get_draft_model_prompt": 71, "get_first_past_key_valu": 84, "get_hf_config": 85, "get_input": 7, "get_kv_cache_ev": 71, "get_kv_cache_events_async": 71, "get_max_resource_count": [106, 107], "get_needed_resource_to_complet": [106, 107], "get_next_medusa_token": 88, "get_num_free_block": 106, "get_num_heads_kv": 88, "get_output": [7, 17], "get_par": [7, 83], "get_pytorch_backend_config": 71, "get_request_typ": 71, "get_rope_index": 88, "get_seq_idx": 88, "get_shap": 18, "get_slic": 18, "get_stat": [71, 96], "get_stats_async": 71, "get_timestep_embed": 84, "get_us": [7, 83], "get_visual_featur": 88, "get_vocab": [0, 3], "get_weight": 84, "getacceptancethreshold": 0, "getacceptedlengthscumsum": 1, "getacceptedpackedpath": 1, "getadditionalmodeloutput": 0, "getadditionaloutputnam": 0, "getaddr": 0, "getaddress": 1, "getagentst": 0, "getallnewtoken": 1, "getallottedtimem": 0, "getattentionconfig": 0, "getattr": 52, "getbackend": 0, "getbackendagentdesc": 0, "getbackendtyp": 0, "getbadword": 0, "getbatchingtyp": 0, "getbatchsizet": 0, "getbeamsearchbuff": 1, "getbeamsearchdiversityr": 0, "getbeamwidth": 0, "getbeamwidtharrai": 0, "getbuffermanag": 1, "getcacheindirectioninput": 1, "getcacheindirectionoutput": 1, "getcachest": 0, "getcachetransceiverconfig": 0, "getcapac": 1, "getcapacityschedulerpolici": 0, "getclientid": 0, "getcommptr": 1, "getcommst": 0, "getcommunicationmod": 0, "getcommunicationtyp": 0, "getconfig": 0, "getconnect": 0, "getconnectioninfo": 0, "getcontextchunkingpolici": 0, "getcontextexecutor": 0, "getcontextfmha": 1, "getcontextparallel": 1, "getcontextparallelgroup": 1, "getcontextparallelrank": 1, "getcontextphaseparam": 0, "getcopyonpartialreus": 0, "getcpu": 1, "getcpudiff": 1, "getcrossattentionmask": 0, "getcrosskvcachefract": 0, "getcudagraphcaches": 0, "getcudagraphmod": 0, "getcumlogprob": 1, "getdata": 0, "getdatatyp": [0, 1], "getdatatypenam": 1, "getdebugconfig": 0, "getdebuginputtensor": 0, "getdebugoutputtensor": 0, "getdebugtensornam": 0, "getdebugtensorsmaxiter": 0, "getdecodedurationm": 0, "getdecoderetentionprior": 0, "getdecoderstream": 1, "getdecodingconfig": 0, "getdecodingmod": 0, "getdefaultbatchslot": 1, "getdefaulteaglechoic": 1, "getdesc": 0, "getdevic": 1, "getdevicecacheperc": 0, "getdeviceid": 0, "getdeviceof": 1, "getdimens": 1, "getdirectori": 0, "getdrafttoken": 0, "getdstdesc": 0, "getdynamicbatchconfig": 0, "getdynamicbatchmovingaveragewindow": 0, "getdynamictreemaxtopk": 0, "geteaglebuff": 1, "geteaglechoic": 0, "geteagleconfig": 0, "getearlystop": 0, "getembeddingbia": 0, "getembeddingt": 0, "getenablebatchsizetun": 0, "getenableblockreus": 0, "getenablechunkedcontext": 0, "getenablecontextfmhafp32acc": 0, "getenablemaxnumtokenstun": 0, "getenablepartialreus": 0, "getenabletrtoverlap": 0, "getencodedvocab": 0, "getencoderhiddens": 1, "getencoderinputfeatur": 0, "getencoderinputtokenid": 0, "getencoderoutputlength": 0, "getendid": 0, "geterrormsg": 0, "geteventbuffermaxs": 0, "getexecutionconfig": 1, "getexplicitdrafttokensbuff": 1, "getextendedruntimeperfknobconfig": 0, "getexternaldrafttokensconfig": 0, "getfastlogit": 0, "getfinishedstep": 1, "getfinishedsum": 1, "getfinishreason": 1, "getfirstgentoken": 0, "getfirstlocallay": 1, "getfreegpumemoryfract": 0, "getfrequencypenalti": 0, "getfunctionpoint": 0, "getgatheredid": 1, "getgathergenerationlogit": 0, "getgemmallreducedtyp": 1, "getgenerationstep": 1, "getgenexecutor": 0, "getgpu": 1, "getgpudiff": 1, "getgpuspergroup": 1, "getgpuspernod": 1, "getgpuweightsperc": [0, 14], "getguid": 0, "getguideddecodingconfig": 0, "getguideddecodingparam": 0, "getguidetyp": 0, "gethandl": 0, "gethiddens": 1, "gethostcaches": 0, "gethostmemori": 1, "getid": 1, "getinittozero": 1, "getinputtokenextraid": 0, "getinputtokenid": 0, "getinst": [0, 1], "getipcunicastpoint": 1, "getisorchestr": 0, "getiterstatsmaxiter": 0, "getjointdecodinginput": 1, "getjointdecodingoutput": 1, "getkvcacheconfig": 0, "getkvcacheconfigref": 0, "getkvcacheeventmanag": 0, "getkvcacheretentionconfig": 0, "getkvcachetyp": 1, "getkvdatatyp": 1, "getlanguageadapteruid": 0, "getlastrank": 1, "getlatestdebugtensor": 0, "getlatestev": 0, "getlatestiterationstat": [0, 3], "getlatestrequeststat": 0, "getlayertyp": 1, "getlen": 0, "getlengthpenalti": 0, "getlevel": 1, "getlocalagentdesc": 0, "getlocalrank": 1, "getlogit": 0, "getlogitsdtyp": 1, "getlogitspostprocessor": 0, "getlogitspostprocessorconfig": 0, "getlogitspostprocessornam": 0, "getlogprob": 1, "getlookaheadbuff": 1, "getlookaheadconfig": 0, "getlookaheaddecodingconfig": 0, "getlookaheaddecodingmaxnumrequest": 0, "getloraconfig": 0, "getloramodul": 1, "getloraprefetchdir": 0, "getmanagedweightsmapopt": 1, "getmanageweightstyp": 1, "getmaxadapters": 0, "getmaxattentionwindowvec": 0, "getmaxbatchs": [0, 1], "getmaxbeamwidth": [0, 1], "getmaxdecodingdecodertoken": 1, "getmaxdecodingdrafttoken": 1, "getmaxdecodingenginetoken": 1, "getmaxdecodingtoken": 1, "getmaxdraftpathlen": 1, "getmaxencoderlen": 1, "getmaxinputlen": 1, "getmaxlorarank": 1, "getmaxnonleafnodesperlay": 1, "getmaxnumpath": 1, "getmaxnumtoken": [0, 1], "getmaxpagesperblock": 1, "getmaxpagesperblockdevic": 0, "getmaxpagesperblockhost": 0, "getmaxpathlen": 1, "getmaxpositionembed": 1, "getmaxpromptembeddingtables": 1, "getmaxqueues": 0, "getmaxseqidlemicrosecond": 0, "getmaxsequencelen": 1, "getmaxsequencelength": 1, "getmaxtoken": 0, "getmaxtokensinbuff": 0, "getmedusachoic": [0, 1], "getmemorytyp": [0, 1], "getmemorytypenam": 1, "getminp": 0, "getmintoken": 0, "getmlphiddens": 1, "getmodelconfig": [0, 1], "getmodelconfigmut": 1, "getmodelnam": 1, "getmodelvari": 1, "getmpist": 0, "getmropeconfig": 0, "getmropepositiondelta": 0, "getmroperotarycossin": 0, "getmultiblockmod": 0, "getmulticastpoint": 1, "getmultimodalembed": 0, "getmultimodalhash": 0, "getmultimodalinput": 0, "getmultimodallength": 0, "getmultimodalposit": 0, "getnam": [0, 1], "getnbattentionlay": 1, "getnbhead": 1, "getnbkvhead": 1, "getnblay": 1, "getnbrnnlay": 1, "getnextdrafttoken": 1, "getnextdrafttokenslength": 1, "getngrams": 0, "getnoderank": 1, "getnoderankof": 1, "getnorepeatngrams": 0, "getnormalizelogprob": 0, "getnotifiedsyncmessag": 0, "getnumcopystream": [0, 1], "getnumdecodingenginetoken": 1, "getnumdevicemodulelay": 0, "getnumensurework": 0, "getnumhostmodulelay": 0, "getnumkvheadsforgivenlay": 1, "getnumkvheadsperlay": 1, "getnumkvheadsperlayerlocalrang": 1, "getnumlanguag": 1, "getnumnod": 0, "getnumpackedmask": 1, "getnumpag": 1, "getnumputwork": 0, "getnumresponsesreadi": 0, "getnumreturnbeam": [0, 1], "getnumreturnsequ": 0, "getnumtransformerlay": 1, "getonboardblock": 0, "getop": 0, "getoptimaladapters": 0, "getoptprofilessplitpoint": 1, "getorchestratorconfig": 0, "getorchleadercomm": 0, "getoutputconfig": 0, "getpadid": 0, "getpagedcontextfmha": 1, "getpageptr": 1, "getpagewidth": 1, "getparallelconfig": 0, "getparentid": 1, "getparticipantid": 0, "getpath": 1, "getpathopt": 1, "getpeftcacheconfig": 0, "getperblockretentionprioritydur": 0, "getpin": 1, "getpinneddiff": 1, "getpinnedpool": 1, "getpinnedpooldiff": 1, "getpipelineparallel": 1, "getpipelineparallelgroup": 1, "getpipelineparallelrank": 1, "getpositionid": 0, "getposteriorthreshold": 0, "getppreducescatt": 1, "getprecis": 1, "getpresencepenalti": 0, "getprevdrafttokenslength": 1, "getprior": 0, "getprocessorbatch": 0, "getprocessormap": 0, "getprompttableoffload": 0, "getprompttuningconfig": 0, "getquantmod": 1, "getrank": 1, "getrecvpollperiodm": 0, "getremotenam": 0, "getrepetitionpenalti": 0, "getrepl": 0, "getreqid": 0, "getrequestid": 0, "getrequeststatsmaxiter": 0, "getrequesttyp": 0, "getresult": [0, 3], "getreturnallgeneratedtoken": 0, "getrnnconfig": 1, "getrotaryembeddingdim": 1, "getruntimedefault": 1, "getruntimetyp": 0, "getsamplingconfig": [0, 1], "getschedulerconfig": 0, "getschedulerconfigref": 0, "getse": 0, "getsecondaryoffloadminprior": 0, "getselfidx": 0, "getsequencelength": 1, "getserializedst": 0, "getshap": [0, 1], "getsinktokenlength": 0, "getsiz": [0, 1], "getsizeinbit": 1, "getsizeinbyt": [0, 1], "getsizeperhead": 1, "getskipcrossattnblock": 0, "getslotsperpag": 1, "getsocketst": 0, "getspawnprocess": 0, "getspecdecconfig": 0, "getspeculativedecodingmod": 1, "getspeculativedecodingmodul": 1, "getspeculativedecodingmoduleptr": 1, "getsrcdesc": 0, "getstat": 0, "getstatu": 1, "getstoptokenid": 0, "getstopword": 0, "getstream": [0, 1], "getsyncmessag": 0, "gettag": 0, "gettaskid": 0, "gettemperatur": 0, "gettensorparallel": 1, "gettensorparallelgroup": 1, "gettensorparallelrank": 1, "getter": 6, "gettoken": 0, "gettokenizerstr": 0, "gettokenrangeretentionconfig": 0, "gettokensperblock": 1, "gettopk": 0, "gettopp": 0, "gettoppdecai": 0, "gettoppmin": 0, "gettoppresetid": 0, "gettotalnumpag": 1, "gettransfermod": 0, "gettyp": [0, 1], "getunderlyingdecod": 1, "getunicastpoint": 1, "getusegpudirectstorag": 0, "getuseuvm": 0, "getuvm": 1, "getuvmdiff": 1, "getverificationsets": 0, "getvers": 1, "getvocabs": 1, "getvocabsizepad": 1, "getweight": 0, "getwindows": 0, "getworkerexecutablepath": 0, "getworlds": 1, "gh200": [90, 96], "ghz": 47, "gib": [9, 92], "gid": [0, 91], "gigabyt": 24, "git": [10, 21, 32, 66, 70, 89, 91, 95, 104], "github": [20, 21, 27, 30, 32, 33, 52, 66, 67, 72, 89, 96, 104], "give": [3, 28, 29, 72, 78, 80, 85, 105], "given": [0, 1, 3, 6, 10, 18, 20, 21, 24, 30, 71, 73, 79, 80, 83, 84, 85, 87, 88, 90, 92, 93, 96, 106], "givyboi": 56, "glm": [83, 94, 96], "glm4": 96, "glob": 90, "global": [0, 5, 8, 17, 27, 29, 96], "global_max_input_length": 88, "global_max_output_length": 88, "globalrequestid": 0, "glossari": [22, 25], "gm": 95, "gnu": 66, "go": [5, 6, 77, 96], "goal": [30, 82], "goe": [28, 70, 74], "good": [3, 17, 21, 29, 30, 74, 77, 80, 81], "got": [0, 45, 47, 48, 49, 50, 51, 52, 56, 68, 70, 74, 89, 95], "gpqa": [27, 29], "gpt": [1, 5, 13, 17, 19, 23, 26, 34, 65, 74, 83, 90, 92, 93, 94, 95, 96], "gpt2": [85, 95], "gpt3": 24, "gpt_attent": [5, 7, 25, 83, 89, 96], "gpt_attention_plugin": [10, 17, 34, 74, 84, 88, 95, 96], "gpt_attention_plugin_remove_pad": 7, "gpt_ib_ptun": 90, "gpt_variant": [85, 96], "gptattent": 7, "gptattentionpluginremovepaddingrewritepass": 7, "gptconfig": 85, "gptdecod": 6, "gptdecoderbatch": 96, "gptdecoderptr": 1, "gptforcausallm": 85, "gptj": 85, "gptjconfig": 85, "gptjforcausallm": 85, "gptjmodel": 85, "gptlmheadmodel": 95, "gptmanag": 96, "gptmanagerbenchmark": [9, 66, 96], "gptmodel": 85, "gptmodelconfig": 96, "gptneoxforcausallm": 85, "gptneoxmodel": 85, "gptq": [26, 65, 94, 96], "gptsession": 96, "gptsessionbenchmark": 96, "gpu": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11, 13, 16, 19, 20, 23, 24, 25, 26, 28, 31, 32, 34, 35, 41, 53, 54, 55, 57, 65, 66, 68, 70, 71, 75, 76, 77, 78, 81, 83, 85, 88, 89, 90, 94, 95, 96, 97, 100, 101, 103], "gpu_typ": 90, "gpu_weights_perc": [14, 88], "gpudirect": 0, "gpumemusag": [0, 35], "gpus_per_nod": [34, 35, 71], "gpuspernod": [1, 6], "gpusync": 1, "gpuweightsperc": [0, 14], "gqa": [5, 8, 22, 25, 34, 83, 96, 101], "grace": [9, 30, 68, 94], "gradient": 23, "gradual": [12, 20], "grain": [7, 30], "gram": 13, "grammar": [0, 3, 71], "granit": [94, 96], "graph": [0, 17, 21, 28, 29, 30, 57, 65, 71, 73, 74, 83, 88, 89, 92, 95, 96, 101, 102, 106], "graph_rewrit": 7, "graphic": 32, "gratitud": 28, "gre": 35, "great": [22, 30, 32], "greater": [0, 2, 5, 25, 26, 27, 30, 34, 83], "greatli": [9, 20, 28, 78, 81], "greedi": [0, 6, 58, 100], "greedy_sampl": 71, "greedysampl": 0, "greedysamplinghost": 1, "grid": [17, 78, 80, 83, 84], "grid_search_engin": 76, "grid_siz": 84, "grok": [94, 96], "groovi": 90, "ground": 73, "groundbreak": 72, "group": [0, 3, 4, 6, 8, 17, 22, 29, 30, 65, 71, 83, 84, 93, 96, 101], "group_cl": 85, "group_norm": 83, "group_siz": [16, 71, 83], "groupedrmsnorm": 27, "groupgemm": [29, 30], "groupnorm": [83, 84], "grow": [1, 13, 31, 80], "gsm8k": 29, "gt": 83, "gtc": [21, 27], "guarante": [0, 6, 9, 20, 30, 74, 75, 76, 78, 82], "guaranteed_no_evict": [0, 33, 71, 74, 82], "guaranteednoevictschedul": 107, "guard": 76, "guid": [0, 17, 21, 26, 32, 46, 65, 70, 71, 72, 73, 75, 76, 77, 78, 81, 83, 95, 96, 101, 102], "guidanc": [13, 35, 81, 84, 85], "guided_decod": [47, 71], "guided_decoding_backend": [47, 71], "guideddecodingbackend": 0, "guideddecodingconfig": [0, 3], "guideddecodingparam": [0, 3, 47, 71], "guidelin": 77, "guidetyp": [0, 3], "gw": 7, "h": [3, 5, 13, 18, 28, 32, 34, 35, 38, 39, 40, 76, 83, 85, 89, 96], "h0": 28, "h1": 83, "h100": [20, 26, 32, 34, 72, 75, 76, 78, 79, 80, 90, 96], "h20": 34, "h200": [23, 34, 75, 96], "ha": [0, 1, 3, 5, 9, 10, 11, 16, 17, 18, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 34, 37, 52, 66, 67, 71, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 88, 89, 92, 93, 95, 96, 100, 106, 107], "habitu": 90, "had": [20, 21, 29, 78, 80], "half": [0, 1, 17, 29, 76, 83], "halv": [23, 83], "hand": [9, 13, 19, 77, 90], "handl": [0, 1, 2, 4, 8, 18, 20, 22, 27, 31, 76, 78, 80, 81, 82, 83, 84, 99, 100], "handle_per_step": 88, "hang": [0, 30, 70, 95, 96], "happen": [3, 6, 9, 17, 30, 68, 92, 95], "happi": 88, "har": 29, "hard": [5, 71], "harder": 6, "hardwar": [8, 26, 29, 32, 41, 65, 66, 90, 96], "has_affin": 83, "has_bia": 83, "has_config_group": 85, "has_position_embed": 88, "has_scal": 83, "has_token_type_embed": 88, "has_zero_point": [16, 71], "hascontextawaitthread": 0, "hasdraftlogit": 1, "haserror": [0, 3], "hasgenawaitthread": 0, "hash": [0, 71], "hasresult": 0, "hasrnnconfig": 1, "hasspeculativedecodingmodul": 1, "hattizai": 96, "have": [0, 1, 3, 4, 5, 6, 9, 10, 12, 13, 16, 17, 18, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32, 34, 36, 53, 54, 55, 56, 59, 68, 70, 71, 72, 73, 74, 76, 77, 78, 79, 80, 81, 82, 83, 88, 89, 92, 94, 95, 96, 99], "hbm3": 75, "hbm3e": 24, "head": [1, 6, 8, 13, 17, 22, 28, 29, 34, 65, 74, 83, 84, 96, 101], "head_dim": [101, 106], "head_siz": [5, 83, 85, 88, 96], "header": 2, "headsiz": 83, "headsperlay": 1, "health": [32, 35, 56, 97], "healthi": 97, "heat": 6, "heavi": [81, 90], "heavier": 77, "heavili": 30, "height": [44, 84, 88], "hello": [45, 48, 49, 50, 51, 53, 56, 57, 68, 76, 82, 89, 104, 105], "help": [3, 5, 7, 17, 27, 28, 30, 31, 34, 35, 38, 39, 47, 52, 57, 58, 59, 60, 61, 66, 71, 73, 74, 75, 76, 79, 80, 81, 82, 83, 89, 96, 100], "helper": [1, 83, 90], "henc": 99, "here": [3, 7, 10, 14, 15, 16, 17, 18, 20, 21, 23, 24, 28, 29, 30, 35, 37, 41, 45, 47, 52, 66, 68, 71, 73, 76, 77, 78, 80, 81, 83, 88, 89, 92, 93, 95, 98, 101, 106, 107], "heterogen": 2, "heurist": [5, 29, 33, 74, 83, 91, 96], "hf": [6, 10, 14, 18, 33, 34, 35, 45, 48, 49, 50, 51, 53, 54, 55, 63, 68, 74, 75, 76, 88, 89, 94, 95, 104], "hf_config_or_dir": 85, "hf_home": 91, "hf_lora_convert": 10, "hf_model": [74, 85], "hf_model_dir": [14, 15, 16, 20, 85], "hf_model_nam": 74, "hf_model_or_dir": 85, "hf_quant_config": 74, "hf_token": 74, "hfconfigordir": 85, "hgx": 24, "hi": 10, "hidden": [0, 3, 4, 5, 6, 10, 13, 27, 28, 71, 83, 84, 96], "hidden_act": [16, 84, 85], "hidden_dim": [0, 5, 83], "hidden_dim_per_head": [5, 83], "hidden_dtyp": 84, "hidden_s": [0, 7, 16, 18, 83, 84, 85, 88, 99, 101], "hidden_size_in": 10, "hidden_size_out": 10, "hidden_size_per_head": 83, "hidden_st": [15, 83, 84, 85, 88, 95, 99], "hidden_states_for_emb": 85, "hiddens": [0, 1, 6], "hide": [27, 29], "hierarch": 16, "hierarchi": [20, 65, 83], "high": [3, 13, 15, 17, 20, 22, 26, 27, 28, 29, 31, 32, 70, 74, 82, 83, 92, 96], "higher": [0, 1, 5, 6, 9, 10, 13, 18, 22, 23, 25, 29, 30, 31, 58, 72, 75, 82, 92, 96, 99], "highest": [6, 7, 23, 24], "highli": [13, 17, 29, 30, 73, 78], "highlight": [23, 26, 78, 80], "hin": 28, "hint": [74, 83], "histori": 29, "hit": [0, 29, 71, 75, 80, 81, 96], "hk": 13, "ho": 10, "hoc": [20, 88], "hold": [0, 1, 3, 4, 7, 8, 9, 10, 13, 30, 71, 77, 84, 92, 100], "home": [21, 74, 91], "home_dir": 91, "homo_head_pattern": 84, "homogen": 2, "hood": 70, "hope": [27, 30, 31], "hopper": [5, 9, 22, 23, 26, 28, 29, 30, 34, 65, 66, 68, 72, 78, 94, 96], "horizont": [29, 34], "host": [1, 10, 29, 31, 32, 35, 37, 42, 55, 65, 66, 68, 71, 81, 83, 96], "host_cache_s": 71, "host_context_length": [83, 84, 85, 88, 95], "host_context_progress": [83, 84, 95], "host_cross_kv_cache_block_offset": [84, 88], "host_cross_kv_cache_pool_map": 84, "host_cross_kv_cache_pool_point": 84, "host_kv_cache_block_offset": [83, 84, 88, 95], "host_kv_cache_block_point": 95, "host_kv_cache_pool_map": [83, 84, 95], "host_kv_cache_pool_point": [83, 84, 95], "host_max_attention_window_s": [83, 84, 95], "host_past_key_value_length": [83, 84, 95], "host_request_typ": [83, 84, 85, 95], "host_runtime_perf_knob": [83, 84, 95], "host_sink_token_length": [83, 84, 95], "hostcaches": [0, 9], "hostmemori": 1, "hostnam": [31, 35], "hot": 30, "hottest": 30, "hour": 76, "hous": [30, 77], "how": [0, 2, 3, 13, 15, 17, 18, 20, 30, 31, 34, 37, 45, 53, 65, 71, 73, 76, 78, 79, 81, 83, 89, 90, 92, 93, 95, 98, 100, 101], "howev": [3, 5, 13, 20, 21, 22, 27, 28, 29, 30, 35, 74, 77, 78, 80, 81, 82, 92, 96, 99, 100], "hpc": 23, "html": [1, 17, 33, 83, 95], "http": [0, 1, 4, 10, 17, 20, 21, 27, 32, 33, 34, 35, 38, 39, 40, 52, 60, 61, 62, 63, 66, 68, 70, 83, 89, 90, 91, 93, 95, 96, 103, 104], "http_code": 32, "hub": [19, 32, 56, 71, 74, 89, 96, 104], "hug": [3, 10, 14, 19, 20, 41, 71, 74, 85, 89, 96], "huggingfac": [0, 10, 15, 16, 18, 20, 21, 33, 35, 39, 56, 61, 70, 74, 75, 76, 89, 91, 94, 95, 96, 99], "huggingface_exampl": 104, "huggingface_hub": 56, "huggingface_model_card": 104, "human": [27, 74], "hundr": 30, "hurt": [29, 30, 81], "hw": [27, 29, 30], "hybrid": [4, 96], "hyper": 16, "hypothesi": 13, "i": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 38, 40, 41, 45, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 62, 66, 67, 68, 70, 71, 72, 74, 75, 76, 78, 79, 80, 81, 82, 83, 84, 85, 86, 88, 89, 90, 91, 93, 94, 95, 96, 97, 98, 99, 100, 101, 104, 105, 106, 107], "ia3": 5, "iactivationlay": 17, "ib": 90, "ibrahimamin1": 96, "ibufferptr": 1, "iconstantlay": 83, "icudaengin": [88, 92], "id": [0, 1, 3, 9, 28, 30, 32, 33, 41, 50, 52, 70, 71, 74, 75, 83, 84, 88, 89, 101, 106], "idea": [10, 29, 30, 81], "ideal": [7, 30, 31, 78, 80, 96], "ident": [3, 9, 29, 34, 83, 105], "identifi": [0, 6, 10, 13, 17, 30, 31, 74, 80, 83], "idl": [0, 103], "idtyp": [0, 3], "idx": 88, "ieee": 93, "ieinsumlay": 83, "ielementwiselay": 83, "iexecutioncontext": [88, 92], "ifb": [13, 31, 96], "ifilllay": 83, "igatherlay": 83, "ignor": [34, 71, 74, 83, 88, 91], "ignore_eo": [71, 96], "igptdecod": 1, "ihostmemori": [1, 17, 88], "ii": [5, 83], "ij": 83, "ijk": 83, "ijl": 83, "ik": 83, "ikl": 83, "ilay": [7, 17], "illustr": [7, 13, 19, 27, 28, 30, 31], "ilogg": 1, "ilooplay": 83, "imag": [33, 35, 39, 44, 53, 54, 55, 61, 65, 68, 74, 84, 88, 96], "image64": 61, "image_grid_thw": 88, "image_patches_indic": 88, "image_path": 88, "image_s": 85, "image_tag": [67, 89], "image_token_index": 88, "image_url": [35, 39, 61], "imatrixmultiplylay": 83, "imb": 30, "imbal": [30, 80], "imbalanc": 30, "immedi": [5, 13, 72, 76, 95], "immut": 1, "impact": [11, 13, 22, 26, 27, 28, 29, 30, 35, 56, 77, 78, 80, 81, 82], "imped": [26, 30], "impl": [0, 107], "implement": [2, 3, 5, 6, 8, 12, 13, 16, 17, 19, 20, 22, 29, 31, 32, 33, 52, 65, 72, 83, 84, 85, 89, 93, 94, 95, 96, 99, 100, 106, 107], "implicit": [1, 5, 13, 83], "implicitli": 1, "import": [11, 13, 18, 20, 22, 26, 28, 29, 32, 35, 41, 45, 47, 48, 49, 50, 51, 52, 56, 57, 58, 59, 60, 61, 62, 63, 65, 68, 76, 78, 80, 81, 82, 89, 90, 94, 96, 98, 99, 100, 104, 105, 106], "importantli": [30, 91], "impos": 26, "improv": [5, 9, 11, 17, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 34, 45, 48, 49, 51, 52, 57, 65, 68, 72, 74, 75, 76, 78, 79, 80, 81, 89, 96, 98, 101, 103], "in_channel": 84, "in_featur": [16, 17, 84], "in_hidden_s": 83, "in_len": 7, "in_point": 83, "in_progress": 88, "includ": [0, 1, 3, 5, 6, 9, 10, 12, 13, 16, 17, 18, 19, 22, 23, 25, 28, 29, 30, 31, 33, 34, 35, 41, 47, 66, 68, 70, 71, 72, 74, 78, 81, 83, 89, 90, 93, 95, 96, 97, 100, 101, 106, 107], "include_stop_str_in_output": 71, "inclus": [2, 83], "incompat": [34, 96, 98], "incorpor": [0, 27, 30, 72, 96], "incorrect": [9, 13, 96], "increas": [0, 5, 9, 13, 17, 21, 23, 24, 27, 28, 29, 30, 31, 34, 52, 73, 74, 76, 78, 81, 82, 83, 90, 96, 107], "incred": 72, "increment": [30, 66, 96], "incur": [2, 17, 27, 31], "inde": 92, "independ": [0, 1, 2, 3, 13, 31, 83], "index": [0, 1, 3, 8, 13, 18, 27, 32, 41, 65, 68, 71, 83, 88, 89, 90, 96, 101], "index_select": 83, "indic": [0, 1, 3, 5, 6, 13, 16, 31, 71, 82, 83, 84, 88, 92, 106], "indim": 1, "indimfirst": 1, "indirect": 1, "individu": [27, 30, 31, 90, 96], "indivis": 96, "inductor": 71, "industri": 74, "ineffici": [5, 27], "inetworkdefinit": [7, 17, 83], "inevit": 17, "infeas": 3, "infer": [0, 2, 6, 10, 13, 17, 19, 20, 21, 22, 23, 24, 27, 29, 34, 39, 61, 65, 70, 73, 75, 76, 77, 78, 79, 81, 82, 83, 88, 93, 95, 96, 100], "infer_shap": 88, "inferencerequest": 96, "infin": 37, "infinit": [17, 74, 75], "inflat": 27, "inflight": [0, 5, 10, 13, 35, 69, 71, 74, 79, 80, 83, 96, 101, 107], "inflight_request_id": 107, "inflightbatch": 0, "inflightbatchingstat": [0, 35], "influenc": [27, 81], "info": [0, 30, 33, 34, 35, 74, 92, 95], "inform": [0, 1, 2, 3, 5, 6, 8, 13, 16, 17, 22, 25, 27, 28, 30, 31, 33, 35, 58, 65, 66, 68, 72, 74, 76, 94, 95, 96], "infti": 6, "inher": 30, "inherit": [18, 20, 83, 99, 100, 106, 107], "init": [1, 21, 29, 32, 66, 96], "init_audio_encod": 88, "init_backend": 71, "init_build_config": 71, "init_calib_config": 71, "init_image_encod": 88, "init_llm": 88, "init_processor": 88, "init_token": 88, "initi": [1, 2, 13, 18, 27, 30, 31, 32, 71, 74, 78, 80, 81, 91, 92, 95, 96, 99, 101, 107], "initial_global_assign": 30, "initialis": 71, "initializecommand": 91, "initializer_list": [0, 1], "initmemorypool": 92, "inittozero": 1, "inlin": [0, 1], "inner": 83, "inner_layernorm": [84, 85], "innov": [29, 30, 32], "inp": 83, "inpaint": [35, 39, 61], "inprogress": 1, "input": [0, 1, 3, 6, 7, 9, 10, 11, 13, 17, 18, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 33, 34, 35, 41, 43, 44, 54, 61, 65, 71, 73, 74, 75, 76, 77, 79, 81, 82, 83, 84, 85, 88, 92, 94, 95, 96, 97, 99, 100, 101, 107], "input_1": 83, "input_1_": 83, "input_audio": 88, "input_featur": 85, "input_fil": 96, "input_id": [9, 15, 27, 74, 83, 85, 88, 95, 99], "input_imag": 88, "input_layernorm": [15, 16, 18, 99], "input_length": [83, 84, 85, 88], "input_list": 83, "input_n": 83, "input_n_": 83, "input_text": [15, 17, 88, 89], "input_timing_cach": [34, 71], "input_token": 71, "input_token_extra_id": 88, "inputbuff": 1, "inputdesc": 17, "inputdtyp": 1, "inputgentokenshost": 1, "inputlen": 1, "inputpack": [1, 6], "inputs_emb": 99, "inputtokenextraid": 0, "inputtokenid": 0, "insert": [7, 17, 30, 74, 83], "insertinputtensor": 1, "insid": [1, 13, 18, 20, 21, 28, 29, 66, 83, 89, 92, 101], "insight": [27, 30, 31], "insiz": 1, "inspect": [34, 73, 92], "inspir": 28, "instal": [20, 32, 35, 36, 53, 54, 55, 66, 70, 76, 96, 99], "instanc": [0, 2, 3, 6, 7, 8, 13, 17, 27, 30, 31, 41, 52, 70, 71, 88, 92, 96, 101], "instance_idx": 95, "instanti": [76, 82, 106], "instead": [7, 9, 13, 17, 20, 21, 22, 30, 33, 41, 66, 68, 71, 81, 82, 83, 90, 92, 96], "instruct": [13, 21, 29, 31, 32, 35, 39, 44, 45, 48, 59, 61, 66, 67, 68, 74, 75, 76, 77, 81, 82, 89, 94, 96, 99, 104, 105], "instrument": 29, "int": [0, 1, 6, 15, 16, 17, 20, 50, 52, 71, 80, 83, 84, 85, 88, 99, 101, 106, 107], "int32": [1, 5, 34, 83, 86, 95], "int32_t": [0, 1, 83], "int4": [18, 20, 26, 30, 34, 41, 65, 94, 96], "int4_weight": 93, "int64": [1, 6, 83, 95], "int64_t": [0, 1], "int8": [1, 16, 18, 20, 26, 30, 33, 34, 65, 71, 78, 83, 92, 94, 96], "int8_kv_cach": [5, 93, 96], "int8_t": [0, 1], "int8_weight": 93, "int8awq": 78, "int_clip": 83, "integ": [5, 33, 71, 74, 83, 93, 96], "integr": [13, 30, 31, 33, 65, 70, 96, 100, 101, 106, 107], "intellig": [32, 58, 72], "intend": [66, 91, 92], "intens": [29, 30], "intent": 76, "intention": 20, "intenum": 83, "inter": [2, 30, 76, 77, 78, 80, 81, 95, 96], "inter_layernorm": 85, "inter_s": 18, "interact": [3, 13, 30, 31, 72, 89, 95], "interchang": 8, "interconect": 77, "interconnect": [6, 76, 77, 78, 80, 81], "interest": [30, 74], "interfac": [17, 20, 70, 76, 88, 96, 99, 100], "interfer": [30, 31, 95], "interleav": [5, 17, 29], "intermedi": [5, 17, 29, 33, 95], "intermediate_s": [16, 85], "intern": [1, 3, 5, 8, 12, 20, 21, 27, 29, 76, 79, 91, 92, 95, 106], "internal_cutlass_kernel": 12, "internal_error": [33, 34, 35], "internlm": [93, 94, 96], "internlm2": [93, 94, 96], "internvl2": 96, "interpol": 83, "interpolation_scal": 84, "interpret": [3, 66, 80, 90], "intersect": 2, "intertwin": 81, "interv": 71, "intflag": [85, 87], "intpsplitdim": 1, "intra": 77, "introduc": [20, 21, 23, 27, 28, 30, 31, 37, 93, 96, 103], "introduct": [79, 89, 96], "inttensor": [88, 99], "intuit": [29, 72, 79], "inv": 83, "inv_freq": 83, "invalid": [30, 59, 95, 96], "invalidateremoteag": 0, "inventori": 74, "invers": 5, "invest": 74, "investig": [21, 96], "invoc": 96, "invok": [0, 3, 7, 30, 70, 90, 95, 107], "invokequant": 17, "involv": [0, 1, 2, 13, 17, 26, 28, 29, 31, 84, 100, 101, 106], "io": [5, 32, 33, 36, 37, 92, 96], "ip": [0, 96], "ipc": [32, 66], "ipc_uc_handl": 1, "ipc_uc_ptr": 1, "ipc_uc_va": 1, "ipcmemori": 1, "ipcnvl": 1, "ipcnvlsalloc": 1, "ipcnvlsfre": 1, "ipcnvlshandl": 1, "ipcnvlssupport": 1, "ipluginv3lay": 83, "ireducelay": 83, "irrespect": [0, 6, 71], "is_alibi": 83, "is_caus": 84, "is_const_v": 1, "is_cuda_graph": 101, "is_cutlass_min_lat": 83, "is_def": 83, "is_dora": 10, "is_dynam": 83, "is_enc_dec": 88, "is_expert": 84, "is_gated_activ": 83, "is_gemma_2": 85, "is_gemma_3": 85, "is_keep_al": [59, 71], "is_loc": 84, "is_medusa_mod": 88, "is_mla_en": 83, "is_mla_enabled_flag": 83, "is_module_excluded_from_quant": 71, "is_mrop": 83, "is_network_input": 83, "is_orchestrator_mod": 88, "is_public_pool": [59, 71], "is_qkv": 84, "is_redrafter_mod": 88, "is_rop": 83, "is_trt_wrapp": 83, "is_use_oldest": [59, 71], "is_valid": [83, 84], "is_valid_cross_attn": 84, "isagentst": 0, "isauto": 0, "isbeamsearch": 0, "iscomplet": 0, "iscontextparallel": 1, "iscontinuouskvcach": 1, "iscrossattent": 1, "isdon": 1, "isdora": 1, "isdrafttokensextern": 1, "iseagl": [0, 1], "iselectlay": 83, "isexplicitdrafttoken": [0, 1], "isexternaldrafttoken": 0, "isfin": [0, 3], "isfirstcontextparallelrank": 1, "isfirstpipelineparallelrank": 1, "isfirsttensorparallelrank": 1, "isgreedysampl": 0, "ishufflelay": 83, "iskvcacheen": 1, "isl": [0, 22, 23, 24, 25, 27, 28, 29, 30, 74, 75, 81, 97], "isl8192": 31, "islastpipelineparallelrank": 1, "isleg": 0, "islicelay": 83, "isload": 1, "islookahead": 0, "islookaheaddecod": 1, "ismedusa": [0, 1], "ismpist": 0, "ismultimod": 1, "isn": [30, 95], "isnon": 1, "isoftmaxlay": 83, "isorchestr": 0, "ispagedkvcach": 1, "isparticip": [0, 96], "ispipelineparallel": 1, "ispoint": 1, "isrnnbas": 1, "issequencefin": [0, 3], "issocketst": 0, "issu": [5, 17, 20, 28, 30, 32, 56, 65, 66, 68, 70, 74, 75, 76, 83, 91, 95], "istensorparallel": 1, "isthreadsaf": 0, "istopk": 0, "istopkandtopp": 0, "istopkortopp": 0, "istopp": 0, "istransformerbas": 1, "istream": [0, 1], "isunsign": 1, "isusebantoken": 0, "isusebanword": 0, "isuseexpliciteosstop": 0, "isusefrequencypenalti": 0, "isusemaxlengthstop": 0, "isuseminlength": 0, "isuseminp": 0, "isusenorepeatngrams": 0, "isuseoccurrencepenalti": 0, "isusepenalti": 0, "isusepresencepenalti": 0, "isuserepetitionpenalti": 0, "isusestopcriteria": 0, "isusestopword": 0, "isusetemperatur": 0, "isusevariablebeamwidthsearch": 0, "iswhisp": 1, "ite": 88, "item": [0, 3, 29, 88], "itensor": [0, 83], "itensorbind": 1, "itensorptr": 1, "iter": [0, 1, 3, 5, 13, 18, 27, 28, 30, 33, 35, 71, 72, 74, 76, 80, 81, 82, 88, 96, 97], "iter_stats_max_iter": 71, "iteration_log": 33, "iterationresult": 71, "iterationstat": 0, "iterationtyp": 0, "iterlatencym": [0, 35], "iterlatencymillisec": 96, "iterstat": 0, "iterstatsmaxiter": 0, "iterstatsvec": 0, "ith": 83, "itl": [30, 78, 81, 96], "its": [0, 1, 3, 5, 6, 7, 8, 14, 16, 17, 18, 20, 22, 24, 27, 28, 30, 31, 47, 70, 72, 74, 77, 79, 80, 81, 83, 90, 92, 100, 101, 107], "itself": [3, 29, 30, 88], "itsuji": 74, "iunarylay": 83, "j": [5, 6, 23, 26, 28, 53, 54, 55, 74, 83, 93, 94, 96], "jacobi": 13, "jai": 96, "jamesthez": 96, "janpetrov": 96, "japanes": [10, 74], "jax": [16, 20], "jenkin": [65, 91], "ji": 83, "jit": [21, 68, 96], "jj": 83, "jk": 83, "jl749": 96, "job": [17, 54, 55, 90, 97], "join": 31, "joint": 29, "joint_attention_kwarg": 85, "joint_attn_forward": 84, "joke": 58, "journei": [27, 72], "jpg": 74, "json": [0, 1, 3, 16, 30, 32, 33, 35, 38, 39, 40, 43, 44, 47, 71, 73, 74, 89, 91, 96], "json_object": 71, "jsonconfigstr": 0, "jsonl": [33, 74], "jsonseri": 0, "judgement": 30, "just": [0, 1, 13, 28, 29, 30, 52, 53, 54, 55, 56, 66, 68, 74, 76, 82, 88, 92], "justic": [45, 56, 68, 89], "k": [1, 5, 6, 10, 13, 19, 27, 28, 29, 58, 71, 83, 93, 95, 96, 99, 101, 105], "k_b_proj_tran": 83, "k_dim": 83, "k_proj": [18, 74, 99], "kattent": 1, "kattn_dens": 1, "kattn_k": 1, "kattn_q": 1, "kattn_qkv": 1, "kattn_v": 1, "kauto": 0, "kbatchedpostprocessornam": [0, 3], "kbeamsearch": 0, "kbf16": 0, "kblk": 0, "kbool": [0, 1], "kbyte_typ": 1, "kc_cache_retention_config": 96, "kcancel": 0, "kchatglm": 1, "kcontext": 1, "kcontext_in_progress": 0, "kcontinu": 1, "kcpu": [0, 1], "kcpu_pin": 0, "kcpu_pinnedpool": 0, "kcross_attn_dens": 1, "kcross_attn_k": 1, "kcross_attn_q": 1, "kcross_attn_qkv": 1, "kcross_attn_v": 1, "kdatatyp": 1, "kdecoder_onli": [0, 14], "kdefault": 0, "kdefault_num_tokens_per_block": 1, "kdefaultbatchsizet": 0, "kdefaultdynamicbatchmovingaveragewindow": 0, "kdefaultgpumemfract": 0, "kdefaultgpuspernod": 1, "kdefaultiterstatsmaxiter": 0, "kdefaultlookaheaddecodingngram": 0, "kdefaultlookaheaddecodingverificationset": 0, "kdefaultlookaheaddecodingwindow": 0, "kdefaultmaxadapters": 0, "kdefaultmaxpagesperblockdevic": 0, "kdefaultmaxpagesperblockhost": 0, "kdefaultmaxseqidlemicrosecond": 0, "kdefaultoptimaladapters": 0, "kdefaultprior": 0, "kdefaultrequeststatsmaxiter": 0, "kdefaultretentionprior": 0, "kdisabl": 1, "kdrafttokensextern": 1, "kdram": 0, "kdynamicpostprocessornameprefix": 0, "keagl": [0, 1], "kebnf_grammar": [0, 3], "keep": [0, 5, 6, 12, 20, 27, 29, 30, 71, 75, 82, 83, 90, 96], "keepdim": 83, "kei": [0, 3, 9, 17, 22, 26, 28, 29, 30, 33, 65, 74, 75, 80, 85, 88, 95, 100, 101, 106], "kenabl": 1, "kencdec": 1, "kencoder_decod": 0, "kencoder_in_progress": 0, "kencoder_onli": 0, "kend_id": 0, "kept": [5, 20, 30, 71, 83], "kequal_progress": 0, "kera": 20, "kernel": [1, 5, 9, 12, 17, 22, 28, 29, 31, 34, 57, 68, 72, 73, 78, 81, 83, 88, 89, 92, 95, 96], "kernel_s": [83, 84], "kexplicitdrafttoken": [0, 1], "kexternaldrafttoken": 0, "key_length": [83, 84], "keyvaluecacheparam": [84, 85], "keyword": [18, 71, 83, 92], "kfile": 0, "kfirst_come_first_serv": 0, "kfloat": [1, 17], "kfp16": 0, "kfp32": [0, 71], "kfp8": 0, "kgener": 1, "kgeneration_complet": 0, "kgeneration_in_progress": 0, "kglm": 1, "kgpt": 1, "kgpu": [0, 1], "kguaranteed_no_evict": 0, "khalf": 1, "kick": 90, "kill": [32, 97], "kind": [4, 5, 7, 27, 30, 107], "kinflight": 0, "kint32": [0, 1], "kint64": [0, 1], "kint8": [0, 1], "kinvalid": 1, "kispoint": 1, "kisunsign": 1, "kj": 83, "kjson": [0, 3], "kjson_schema": [0, 3], "kleader": [0, 2], "klength": 0, "klinear": 1, "kllguidanc": 0, "klookahead": 0, "klookaheaddecod": 1, "kmamba": 1, "kmax_util": 0, "kmaxretentionprior": 0, "kmedusa": [0, 1], "kminretentionprior": 0, "kmla": 0, "kmlp_4h_to_h": 1, "kmlp_gate": 1, "kmlp_gate_up": 1, "kmlp_h_to_4h": 1, "kmlp_router": 1, "kmoe_4h_to_h": 1, "kmoe_gat": 1, "kmoe_h_to_4h": 1, "kmoe_rout": 1, "kmpi": 0, "knegativeinfin": 1, "knob": [0, 71, 82, 83], "knone": 1, "knoop": 1, "knot_finish": 0, "know": [6, 73, 82, 83], "knowledg": 65, "known": [5, 12, 13, 17, 28, 30, 65, 68, 83, 90, 94], "knumflag": 0, "kobj": 0, "kopt_profiles_split_point": 1, "korchestr": [0, 2], "kosmo": [94, 96], "kpage": 1, "kpin": 1, "kpinnedpool": 1, "kqueu": 0, "kread": 0, "krecurr": 1, "krecurrentgemma": 1, "kregex": [0, 3], "kstatic": 0, "kstatic_batch": 0, "kstop_word": 0, "kstructural_tag": 0, "ktimed_out": 0, "ktopk": 0, "ktopktopp": 0, "ktopp": 0, "ktrtpointertyp": 1, "kubernet": 31, "kuint8": [0, 1], "kunderlyingtyp": 1, "kunish": 10, "kunknown": 0, "kunsign": 1, "kusebantoken": 0, "kusebanword": 0, "kuseexpliciteosstop": 0, "kusefrequencypenalti": 0, "kusemaxlengthstop": 0, "kuseminlength": 0, "kuseminp": 0, "kusenorepeatngrams": 0, "kuseoccurrencepenalti": 0, "kusepenalti": 0, "kusepresencepenalti": 0, "kuserepetitionpenalti": 0, "kusestandardstopcriteria": 0, "kusestopword": 0, "kusetemperatur": 0, "kusevariablebeamwidthsearch": 0, "kuvm": [0, 1], "kv": [0, 1, 2, 3, 10, 17, 20, 22, 26, 28, 29, 32, 33, 34, 35, 41, 57, 65, 69, 71, 72, 74, 75, 76, 80, 83, 88, 89, 96, 98, 99, 100, 101, 102, 107], "kv_b_proj": 83, "kv_cach": [0, 57], "kv_cache_block_offset": [83, 84, 88, 95], "kv_cache_block_point": 95, "kv_cache_config": [35, 41, 57, 71, 82, 106], "kv_cache_dtyp": [21, 74, 78, 87, 106], "kv_cache_enable_block_reus": [88, 96], "kv_cache_free_gpu_mem_fract": [21, 30, 33, 75, 82], "kv_cache_free_gpu_memory_fract": [31, 32, 35, 42, 88, 96], "kv_cache_host_memory_byt": 9, "kv_cache_manag": [0, 96, 100, 101, 106, 107], "kv_cache_param": [84, 85, 101], "kv_cache_quant_algo": [16, 71, 74, 78], "kv_cache_quant_mod": [5, 83], "kv_cache_retention_config": 71, "kv_cache_scaling_factor": [5, 16], "kv_cache_typ": [17, 34, 71, 88, 96], "kv_dtype": 85, "kv_head": 84, "kv_host_cache_byt": 9, "kv_lora_rank": [83, 84], "kv_orig_quant_scal": 83, "kv_quant_orig_scal": 83, "kvalue_status_load": 1, "kvalue_status_miss": 1, "kvalue_status_process": 1, "kvcach": [0, 2, 27, 96], "kvcacheblock": 8, "kvcacheblockpool": 8, "kvcacheconfig": [0, 5, 9, 41, 57, 71, 82, 92], "kvcachecreateddata": [0, 71], "kvcacheev": 0, "kvcacheeventdata": 0, "kvcacheeventdiff": 0, "kvcacheeventmanag": [0, 65], "kvcachehitr": 0, "kvcachehitrateperrequest": 0, "kvcacheindex": 1, "kvcachemanag": [0, 5, 9, 88, 101, 106], "kvcachemetr": 0, "kvcacheparam": 101, "kvcacheremoveddata": [0, 71], "kvcacheretentionconfig": [0, 71], "kvcaches": 0, "kvcachestat": [0, 35], "kvcachestoredblockdata": 0, "kvcachestoreddata": [0, 71], "kvcachetransferend": 0, "kvcachetransferm": 0, "kvcachetransfermod": [0, 71], "kvcachetransferstart": 0, "kvcachetyp": [1, 71, 88], "kvcachetypefromstr": 1, "kvcacheupdateddata": [0, 71], "kvfactor": 0, "kvheadnum": 83, "kvram": 0, "kwarg": [18, 20, 71, 83, 84, 85, 88, 96, 99], "kwrite": 0, "kxgrammar": 0, "l": [13, 35, 53, 54, 55, 74, 94], "l0_a100": 90, "l0_mergerequest": 90, "l0_sanity_check": 90, "l0_test": 90, "l2": 34, "l20": 34, "l304": 27, "l345": 27, "l4": 34, "l40": 34, "l440": 27, "l506": 27, "l546": 27, "l823": 27, "lab": 74, "label": [7, 83, 84, 85], "labelembed": 84, "lack": [0, 1], "lai": 28, "lambda": [0, 3], "lamportinitializeal": 1, "languag": [0, 6, 13, 17, 19, 22, 27, 30, 31, 72, 73, 83, 93, 94, 96, 100, 103], "language_adapt": [88, 96], "language_adapter_config": 88, "language_adapter_rout": [85, 88], "language_adapter_uid": 88, "language_model": 18, "languageadapterconfig": 88, "languageadapteruid": 0, "larg": [5, 9, 11, 13, 17, 19, 20, 21, 22, 26, 27, 29, 31, 32, 34, 35, 39, 61, 71, 72, 73, 74, 77, 78, 80, 81, 83, 92, 94, 95, 96, 100, 103], "larger": [0, 5, 6, 9, 13, 14, 21, 23, 24, 26, 29, 31, 71, 74, 75, 83, 88, 92, 96], "largest": [6, 22, 23, 24, 83], "last": [0, 1, 3, 5, 10, 11, 13, 15, 27, 28, 30, 32, 52, 71, 80, 82, 83, 85], "last_lay": 88, "last_process_for_ub": 83, "last_token_id": [83, 85, 95], "last_token_ids_for_logit": 85, "last_tokens_id": 83, "lastdraftindic": 1, "lastdraftlen": 1, "lastdraftpath": 1, "lastdrafttoken": 1, "lastgenerationlength": 1, "lastit": 0, "lastpositionidsbas": 1, "lasttokentim": 0, "late": 56, "latenc": [0, 5, 9, 13, 23, 24, 26, 28, 29, 30, 31, 34, 65, 71, 75, 80, 81, 82, 83, 96], "latent": [29, 84, 85], "later": [0, 1, 6, 10, 13, 17, 20, 24, 32, 78, 81, 88, 92, 95, 98], "latest": [0, 17, 21, 29, 32, 36, 66, 89, 96], "latter": [3, 26, 91, 96], "launch": [2, 9, 17, 29, 30, 31, 35, 53, 54, 55, 57, 65, 68, 70, 76, 95, 96, 97, 98, 103], "launch_llama_3": 17, "layer": [0, 1, 2, 4, 5, 6, 7, 8, 10, 13, 15, 16, 17, 18, 28, 30, 31, 34, 71, 77, 83, 88, 89, 92, 93, 95, 96, 99, 101, 106], "layer1": 10, "layer_idx": [10, 15, 83, 88, 99, 101], "layer_names_onli": [34, 71], "layer_norm": [83, 84], "layer_quant_mod": 71, "layer_typ": 88, "layer_updates_per_it": 30, "layerid": [1, 10], "layeridx": 1, "layernorm": [15, 34, 81, 83, 84, 96], "layernorm_shar": 84, "layernorm_typ": 84, "layernormpositiontyp": 83, "layernormtyp": [83, 84], "layertyp": [1, 7], "layerwis": 71, "layout": [80, 96], "lead": [7, 9, 13, 17, 30, 31, 34, 56, 66, 74, 75, 76, 78, 80, 81], "leader": [0, 32, 88], "learn": [23, 24, 26, 30, 32, 45, 48, 49, 51, 68, 78, 83, 89], "learned_absolut": [16, 83, 84, 85], "least": [0, 3, 5, 20, 21, 30, 35, 56, 80, 88], "leav": [31, 80, 81, 82], "left": [31, 71, 75, 80, 82, 83], "legaci": [18, 82, 86, 96], "len": [0, 1, 52, 74, 83, 88, 107], "length": [0, 1, 5, 9, 21, 22, 23, 24, 25, 26, 27, 28, 29, 31, 33, 34, 35, 52, 71, 74, 75, 76, 79, 81, 82, 83, 88, 92, 95, 96, 97, 101, 106], "length_penalti": [6, 71, 88], "lengthlengthpenalti": 6, "lengthpenalti": [0, 1, 6], "less": [0, 3, 5, 6, 17, 23, 28, 30, 71, 75, 83], "let": [7, 15, 16, 18, 27, 30, 36, 41, 72, 74, 80, 83], "letter": 83, "level": [0, 1, 3, 5, 8, 10, 12, 15, 16, 18, 20, 28, 29, 31, 33, 34, 35, 70, 73, 74, 92, 96, 97, 99], "leverag": [13, 22, 27, 28, 30, 31, 32, 78, 89], "lf": [10, 21, 32, 66, 70], "lfz941": 96, "lh": 1, "lib": [20, 68, 74], "libnam": 0, "libnvinfer_plugin_tensorrt_llm": 66, "libopenmpi": 68, "librari": [12, 17, 19, 30, 31, 33, 66, 70, 72, 95, 96, 101], "libtensorrt_llm": 66, "licens": [70, 89], "life": 56, "lifecycl": 8, "lightweight": [5, 30], "like": [0, 3, 5, 6, 7, 9, 13, 16, 17, 19, 20, 26, 27, 28, 29, 30, 31, 32, 34, 41, 45, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 67, 68, 71, 72, 74, 76, 77, 78, 80, 81, 82, 83, 89, 90, 91, 92, 93, 95, 96, 98, 99, 100, 106], "likelihood": [4, 9, 13, 52], "limit": [0, 2, 3, 5, 6, 7, 17, 20, 26, 27, 28, 29, 30, 31, 32, 33, 41, 68, 70, 71, 72, 76, 80, 82, 83, 86, 88, 92, 94, 101], "lin": 22, "line": [9, 21, 26, 31, 33, 52, 74, 76, 78, 81, 90, 91, 92, 96, 106, 107], "linear": [1, 10, 13, 15, 16, 17, 29, 83, 92, 93, 96, 99, 101], "linearactiv": 84, "linearapproximategelu": 84, "linearbas": 84, "lineargeglu": 84, "lineargelu": 84, "linearli": 92, "linearswiglu": 84, "link": [9, 21, 27, 36, 37, 90, 96], "linspac": 83, "linux": [65, 89, 91, 94, 96], "linux_x86_64": 66, "list": [0, 1, 3, 5, 6, 7, 16, 17, 18, 19, 28, 30, 41, 52, 66, 69, 71, 72, 74, 75, 76, 83, 84, 85, 88, 90, 91, 94, 95, 96, 97, 101, 106, 107], "list_siz": 84, "liter": 71, "littl": [28, 30, 81], "live": [90, 92], "livecodebench": 27, "lkm2835": 96, "ll": [26, 28, 35], "ll128": 30, "llama": [6, 10, 13, 14, 18, 20, 23, 24, 26, 32, 34, 45, 48, 59, 63, 68, 70, 76, 77, 79, 80, 82, 85, 89, 93, 94, 96, 98, 99, 104, 105], "llama2": [5, 10, 22, 23, 96], "llama3": [59, 83], "llama4": [30, 71], "llama4forconditionalgener": 94, "llama_13b": 24, "llama_70b": 24, "llama_7b": [10, 14], "llama_7b_with_lora_qkv": 10, "llama_model_path": 41, "llamaconfig": [85, 99], "llamaforcausallm": [18, 20, 85, 94], "llamamodel": 85, "llava": [18, 93, 94, 96], "llava_dict": 18, "llavallamamodel": 94, "llavanextforconditionalgener": 94, "llavanextvisionconfig": 85, "llavanextvisionwrapp": 85, "llguidanc": [0, 47, 71], "llm": [0, 2, 3, 5, 6, 7, 8, 9, 10, 11, 15, 17, 22, 25, 27, 29, 33, 34, 35, 38, 39, 40, 42, 43, 44, 47, 48, 49, 50, 52, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 67, 68, 69, 71, 73, 75, 77, 78, 79, 81, 82, 83, 85, 87, 88, 90, 91, 93, 95, 97, 98, 99, 100, 101, 104, 105, 106, 107], "llm_advanc": 57, "llm_arg": [71, 75], "llm_engine_dir": 88, "llm_id": 71, "llm_inference_distribut": 70, "llm_mgmn_": 96, "llm_models_root": 63, "llm_option": 75, "llm_ptq": 104, "llm_sampl": 58, "llmapi": [3, 30, 35, 41, 47, 53, 54, 55, 56, 57, 59, 71, 75, 78, 96], "llmarg": [11, 71, 75, 96], "llmrequest": [1, 106, 107], "llmrequestptr": 1, "llmrequestst": 107, "lm": 13, "lm_head": [15, 18, 74, 96], "lmm": [6, 74], "lmsy": 103, "ln_emb": 18, "ln_f": [15, 18], "load": [0, 1, 10, 15, 16, 17, 20, 25, 27, 29, 31, 32, 33, 34, 68, 70, 71, 74, 75, 76, 81, 82, 85, 87, 88, 89, 92, 96], "load_balanc": [30, 71], "load_format": 71, "load_model_on_cpu": 85, "load_tensor": 18, "load_test_audio": 88, "load_test_data": 88, "load_weight": 99, "loaded_weight": 84, "loader": [71, 96], "loadformat": 71, "loadinprogress": 1, "loadremoteag": 0, "loadweight": 1, "local": [16, 17, 21, 27, 30, 34, 45, 48, 49, 50, 51, 53, 54, 55, 59, 66, 67, 68, 71, 74, 75, 78, 89, 91, 96, 106], "local_build": 91, "local_in_featur": 84, "local_layer_idx": 84, "local_model": [53, 54, 55], "local_out_featur": 84, "local_path_to_model": 70, "local_us": [21, 66, 89], "localhost": [31, 32, 35, 38, 39, 40, 42, 43, 44, 60, 61, 62, 63, 89], "localinadapters": 1, "localindim": 1, "localinouts": 1, "localins": 1, "localoutadapters": 1, "localoutdim": 1, "localouts": 1, "localreduct": 27, "localscaless": 1, "localtotals": 1, "locat": [6, 7, 17, 29, 30, 66, 74, 75, 83, 89, 90, 95, 101], "locate_accepted_draft_token": 88, "lock": [30, 74], "lockstep": 0, "log": [0, 1, 5, 8, 33, 34, 35, 36, 53, 54, 55, 58, 71, 74, 83, 89, 92, 96, 97, 105], "log_level": [33, 34, 35], "log_path": 97, "log_softmax": 83, "logic": [3, 8, 18, 20, 31, 52, 84, 85, 91, 96, 99, 100, 107], "login": [36, 89], "logit": [0, 1, 6, 13, 27, 28, 46, 71, 74, 83, 88, 95, 96, 102, 105], "logits_dtyp": [16, 34, 85], "logits_processor": [52, 71, 88], "logits_processor_map": 88, "logits_processor_nam": 88, "logitspostprocessor": 0, "logitspostprocessorbatch": [0, 3], "logitspostprocessorconfig": [0, 3, 96], "logitspostprocessormap": 0, "logitspostprocessornam": 0, "logitsprocessor": [52, 71, 88, 96], "logitsprocessorlist": 88, "logitsvec": 1, "logn": [83, 96], "logn_scal": 83, "logprob": [0, 1, 32, 41, 58, 71, 89], "logprobs_diff": 71, "logprobscba": 1, "logprobstil": 1, "london": 95, "long": [5, 26, 30, 31, 34, 73, 74, 76, 77, 78, 80, 81, 92, 96], "long_factor": 83, "long_mscal": [83, 84], "long_rop": 83, "long_rope_embed_posit": 84, "long_rope_embed_positions_for_gpt_attent": 84, "long_rope_rotary_cos_sin": 83, "long_rope_rotary_inv_freq": [83, 84], "longer": [0, 6, 9, 27, 29, 30, 32, 71, 75, 80, 83, 107], "longest": [28, 80, 83], "longrop": 83, "longtensor": [52, 88], "look": [0, 3, 20, 25, 30, 66, 72, 74, 96], "lookahead": [0, 1, 65, 71, 96], "lookahead_config": [71, 88], "lookahead_decod": [34, 85], "lookaheadalgoconfig": 1, "lookaheadconfig": 0, "lookaheaddecod": 1, "lookaheaddecodingbuff": 1, "lookaheaddecodingconfig": [0, 1, 71], "lookaheadinput": 1, "lookaheadoutput": 1, "lookaheadprompt": 1, "lookaheadruntimebuff": 1, "lookaheadruntimeconfig": 1, "lookup": [83, 84, 90, 96], "lookup_plugin": 83, "loop": [0, 3, 6, 17, 18, 71, 82, 97], "lopuhin": 96, "lora": [0, 1, 3, 33, 46, 64, 65, 69, 71, 83, 84, 85, 88, 96], "lora_0": 74, "lora_ckpt_sourc": [34, 88], "lora_config": [56, 71, 74, 85], "lora_dir": [10, 34, 56, 74, 88], "lora_dir1": 56, "lora_dir2": 56, "lora_dir3": 56, "lora_hidden_st": 84, "lora_int_id": [63, 74], "lora_layer_param": 84, "lora_manag": [56, 71, 88, 96], "lora_nam": [63, 74], "lora_param": 85, "lora_path": [63, 74], "lora_plugin": [10, 34, 83, 88], "lora_rank": [10, 83], "lora_request": [56, 63, 71, 74], "lora_runtime_param": 84, "lora_target_modul": [10, 34, 74, 85, 88], "lora_task_uid": 88, "lora_uid": 88, "lora_weights_point": 83, "loracachefullexcept": 1, "loracachepagemanag": 1, "loraconfig": [0, 10, 56, 71, 85, 96], "loraexpectedexcept": 1, "loraid": 0, "loramanag": 88, "loramodulenam": 1, "loraparam": 85, "loraprefetchdir": 0, "lorarequest": [56, 71], "loraruntimeparam": 84, "lorataskidtyp": [0, 1], "loraweight": 10, "loss": [26, 78], "lot": [5, 9, 17, 19, 28], "loudspeak": 24, "love": 32, "lovelac": [72, 94, 96], "low": [5, 15, 20, 21, 26, 27, 28, 29, 30, 31, 34, 65, 83, 96], "low_latency_gemm": [12, 83], "low_latency_gemm_plugin": [34, 74, 78, 84], "low_latency_gemm_swiglu": 83, "low_latency_gemm_swiglu_plugin": [34, 78, 86], "low_rank": 83, "lower": [0, 1, 2, 6, 7, 9, 10, 25, 26, 29, 31, 58, 71, 75, 78, 83, 92], "lowprecis": [11, 71, 83], "loyalti": 52, "lpddr5x": 30, "lru": [1, 9, 83], "lt": 83, "lunch": 30, "luotuo": [10, 63], "m": [0, 21, 23, 27, 30, 31, 33, 35, 43, 44, 47, 56, 74, 75, 76, 78, 80, 81, 83, 92, 93], "macceptancethreshold": 0, "machin": [9, 21, 26, 32, 96, 97], "macro": 12, "madditionalmodeloutput": 0, "maddr": 0, "made": [67, 72, 96, 107], "magentnam": 0, "magic": 30, "mahmoudashraf97": 96, "mai": [0, 1, 3, 5, 6, 9, 10, 11, 12, 13, 16, 17, 18, 20, 21, 27, 28, 30, 31, 32, 34, 36, 53, 54, 55, 66, 70, 73, 74, 75, 76, 81, 82, 83, 84, 86, 91, 92, 95, 96, 99, 100, 101, 106], "main": [3, 6, 8, 22, 25, 27, 28, 30, 32, 33, 35, 39, 41, 45, 47, 48, 49, 50, 51, 52, 56, 57, 58, 59, 61, 68, 70, 71, 73, 76, 78, 81, 82, 83, 89, 92, 95, 97, 99], "mainli": [28, 30], "mainstream": 31, "maintain": [10, 12, 22, 23, 26, 30, 74, 78, 93], "major": [20, 27, 72, 75, 92], "make": [1, 2, 5, 7, 10, 12, 17, 20, 21, 26, 27, 28, 30, 32, 36, 37, 56, 65, 66, 70, 72, 74, 76, 82, 83, 89, 95, 96], "make_causal_mask": 84, "make_env": 91, "makeshap": 1, "maketransferag": 0, "mallotedtim": 0, "mallreducecommptr": 1, "mamba": [34, 83, 93, 94, 96], "mamba1": 83, "mamba2": [83, 96], "mamba_conv1d": 83, "mamba_conv1d_plugin": [34, 88], "mamba_vers": 83, "mambaconfig": 85, "mambaforcausallm": 85, "manag": [0, 1, 2, 5, 13, 17, 29, 30, 31, 34, 41, 52, 65, 68, 70, 76, 82, 86, 88, 89, 92, 96, 98, 100, 101], "managedweight": 0, "managedweightsmap": 1, "manageweightstyp": 1, "manageweighttyp": 1, "mandatori": [1, 3, 16], "mani": [0, 5, 8, 9, 13, 17, 20, 28, 29, 30, 32, 34, 37, 71, 75, 78, 80, 82, 83, 94, 95], "manipul": 7, "manner": [7, 30], "mantissa": 23, "manual": [29, 30, 41, 68, 70, 71, 88, 90, 95], "manufactur": 74, "map": [0, 1, 3, 5, 7, 11, 15, 16, 17, 18, 20, 27, 30, 31, 32, 75, 83, 84, 85, 88, 89, 90, 106], "mard1no": 96, "margin": [74, 80], "mark": [1, 7, 80, 83, 90, 95], "mark_as_remov": 7, "mark_output": [3, 83], "markalldon": 1, "markdon": 1, "marker": [71, 90], "market": 52, "marks101": 96, "marktaskdon": 1, "mask": [0, 1, 5, 13, 27, 28, 83, 84, 85, 88, 101], "mask_typ": 83, "masked_scatt": 83, "masked_scatter_": 83, "masked_select": [83, 96], "massiv": 21, "master": [77, 78, 79], "mat2": 83, "match": [0, 4, 7, 13, 28, 31, 65, 71, 74, 83, 84, 88, 89, 90, 95, 96], "match_and_rewrit": 7, "materi": 3, "math": [27, 29, 94], "matichon": 96, "matmul": [5, 17, 34, 78, 83, 93], "matric": 4, "matrix": [5, 17, 25, 29, 65, 72, 74, 77, 83, 89, 98, 101], "mattentionconfig": 0, "mattentiontyp": 0, "matter": 9, "matur": 35, "maverick": 13, "max": [0, 1, 10, 22, 23, 24, 29, 30, 33, 65, 71, 76, 78, 79, 81, 83, 88, 92, 95, 97, 101], "max_all_reduce_block": 1, "max_attention_window": [71, 82, 96], "max_attention_window_s": [5, 82, 83, 88], "max_attn_valu": 84, "max_batch_s": [5, 10, 14, 16, 17, 20, 21, 28, 32, 33, 34, 35, 41, 42, 57, 71, 74, 78, 80, 81, 83, 85, 88, 92, 95, 96, 106], "max_beam_width": [3, 5, 34, 35, 41, 71, 83, 85, 88, 92], "max_block": [83, 107], "max_blocks_per_seq": 88, "max_blocks_per_sequ": 83, "max_boost_slid": 74, "max_cache_storage_gb": 71, "max_context_length": [83, 84, 88, 92], "max_cpu_lora": 71, "max_decoder_input_len": 85, "max_decoder_seq_len": 34, "max_dist": [5, 83, 84], "max_draft_len": [32, 34, 59, 71, 85, 87], "max_draft_token": 88, "max_encoder_input_len": [34, 71, 85], "max_gen_token": 85, "max_input_len": [10, 14, 16, 17, 33, 34, 71, 74, 85, 88, 92], "max_input_length": [83, 84, 85, 88], "max_kv_seqlen": 83, "max_lora": 71, "max_lora_rank": [10, 34, 56, 71, 74], "max_low_rank": 83, "max_matching_ngram_s": [59, 71], "max_medusa_token": 88, "max_multimodal_len": 34, "max_new_token": [88, 92], "max_ngram_s": 71, "max_non_leaves_per_lay": 71, "max_num_request": [101, 106, 107], "max_num_token": [21, 33, 34, 35, 41, 42, 71, 74, 78, 80, 81, 85, 92, 96, 101], "max_output_len": [17, 88, 89, 95, 96], "max_period": 84, "max_position_embed": [16, 83, 84, 85], "max_position_embedding_len": 83, "max_power_limit": 74, "max_prompt_adapter_token": 71, "max_prompt_embedding_table_s": [34, 71, 88, 96], "max_record": 71, "max_seq_len": [10, 14, 16, 17, 32, 33, 34, 35, 57, 71, 74, 82, 83, 84, 85, 88, 92, 96, 106], "max_seqlen": [5, 83], "max_seqlen_for_logn_sc": 84, "max_sequence_length": [5, 88], "max_token": [32, 35, 38, 39, 40, 47, 52, 57, 58, 59, 60, 61, 62, 63, 71, 82, 89], "max_token_count": 52, "max_tokens_in_buff": 71, "max_tokens_in_paged_kv_cach": [82, 88, 96], "max_util": [0, 33, 71, 82], "max_verification_set_s": 71, "max_window_s": 71, "maxaccepteddrafttokensperstep": 1, "maxacceptedtoken": 1, "maxadapters": 0, "maxattentionwindow": 1, "maxattentionwindowvec": [0, 1], "maxbadwordslen": 1, "maxbatchs": [0, 1, 6], "maxbatchsizeruntim": 0, "maxbatchsizeruntimeupperbound": 0, "maxbatchsizestat": 0, "maxbatchsizetunerrecommend": 0, "maxbeamwidth": [0, 1, 3, 96], "maxdecoderstep": 1, "maxdecodingdrafttoken": 1, "maxdecodingtoken": [0, 1], "maxdraftpathlen": [0, 1], "maxdrafttoken": [0, 1], "maxencoderlen": 1, "maxgenerationlength": 1, "maxgenlengthdevic": 1, "maxgenlengthhost": 1, "maxgentoken": 1, "maxim": [0, 22, 24, 27, 29, 74, 82, 103], "maximum": [0, 1, 2, 3, 5, 6, 21, 24, 30, 33, 34, 35, 71, 74, 75, 78, 83, 84, 88, 92, 95, 96, 106], "maxinputlen": [1, 6], "maxinputlength": 1, "maxlength": 1, "maxlengthstop": 0, "maxlorarank": 1, "maxmedusahead": 1, "maxnewtoken": [1, 96], "maxnonleafnodesperlay": 1, "maxnumactiverequest": 0, "maxnumblock": 0, "maxnumpath": 1, "maxnumsequ": [1, 96], "maxnumtoken": [0, 1], "maxnumtokensruntim": 0, "maxnumtokensstat": 0, "maxnumtokenstunerrecommend": 0, "maxoutputlength": 3, "maxpagesperblock": 1, "maxpagesperblockdevic": 0, "maxpagesperblockhost": 0, "maxpathdraftlen": 1, "maxpathlen": [0, 1], "maxpositionembed": [0, 1], "maxpromptembeddingtables": 1, "maxqueues": 0, "maxseqidlemicrosecond": 0, "maxseqlen": 1, "maxsequencelen": [1, 6], "maxsequencelength": 1, "maxstopwordslen": 1, "maxtoken": [0, 92, 96], "maxtokensinbuff": 0, "maxtokensperenginestep": 1, "maxtokensperstep": 1, "mb": [71, 92], "mbackend": 0, "mbackendagentdesc": 0, "mbackendtyp": 0, "mbart": [94, 96], "mbatchingtyp": 0, "mbatchsizet": 0, "mbeamsearchbuff": 1, "mbeamsearchdiversityr": 0, "mbeamwidth": 0, "mbeamwidtharrai": 0, "mbp": 47, "mbuffer": 1, "mbuffermanag": 1, "mc_handl": 1, "mc_ptr": 1, "mc_va": 1, "mcachemap": 1, "mcachemutex": 1, "mcachepagemanag": 1, "mcachest": 0, "mcachetransceiverconfig": 0, "mcapacityschedulerpolici": 0, "mcommmod": 0, "mcommptr": 1, "mcommstat": 0, "mcommtyp": 0, "mcomputecontextlogit": 1, "mcomputegenerationlogit": 1, "mconfig": [0, 1], "mconnectioninfo": 0, "mcontextchunkingpolici": 0, "mcontextfmha": 1, "mcontextparallel": 1, "mcopyonpartialreus": 0, "mcpu": 1, "mcpudiff": 1, "mcrosskvcachefract": 0, "mcudagraphcaches": 0, "mcudagraphmod": 0, "mcumlogprobstmp": 1, "md": [13, 15, 27, 83, 89, 96, 100], "mdatatyp": [0, 1], "mdebugconfig": 0, "mdebuginputtensor": 0, "mdebugoutputtensor": 0, "mdebugtensornam": 0, "mdebugtensorsmaxiter": 0, "mdecod": 1, "mdecodedurationm": 0, "mdecoderetentionprior": 0, "mdecoderstream": 1, "mdecodingconfig": 0, "mdecodinglayerworkspac": 1, "mdecodingmod": [0, 1], "mdefaulteaglechoic": 1, "mdefaultmedusachoic": 1, "mdefaultposteriorthreshold": 1, "mdesc": 0, "mdevic": 1, "mdevicebuffermanag": 1, "mdevicecacheperc": 0, "mdeviceid": [0, 1], "mdirectori": 0, "mdllmutex": 0, "mdogreedysampl": 1, "mdonetask": 1, "mdprank": 0, "mdpsize": 0, "mdrafttoken": 0, "mdstdesc": 0, "mdynamicbatchconfig": 0, "mdynamicbatchmovingaveragewindow": 0, "mdynamicdecodelay": 1, "mdynamictreemaxtopk": 0, "me": [35, 39, 56, 58, 61, 89], "meaglechoic": 0, "meagleconfig": 0, "mean": [1, 4, 5, 6, 9, 13, 16, 18, 20, 21, 23, 24, 28, 29, 30, 31, 33, 35, 43, 44, 54, 56, 71, 73, 74, 75, 76, 77, 82, 83, 86, 88, 92], "meaning": [1, 21, 29, 78, 81], "meant": [71, 79, 97], "mearlystop": 0, "measur": [0, 2, 22, 24, 25, 26, 28, 29, 30, 65, 74, 76, 96], "mechan": [3, 17, 30, 31, 91, 106, 107], "media": [74, 96], "media_path": 74, "medium": [26, 95, 96], "medusa": [0, 1, 33, 34, 65, 71, 83, 85, 88, 96], "medusa_choic": [13, 33, 71, 74, 88], "medusa_decode_and_verifi": 88, "medusa_hidden_act": 87, "medusa_logit": 88, "medusa_model_dir": 87, "medusa_output_token": 88, "medusa_path": 88, "medusa_position_offset": 88, "medusa_temperatur": [13, 88], "medusa_topk": 88, "medusa_tree_id": 88, "medusachoic": [0, 1], "medusaconfig": 85, "medusacurtokensperstep": 1, "medusadecodingconfig": 71, "medusaforcausallm": 85, "medusainput": 1, "medusalogit": 1, "medusapath": 1, "medusatargettokensperstep": 1, "medusatreeid": 1, "meet": [26, 30, 31, 83], "membeddingt": 0, "member": [0, 1, 6, 7, 14, 17, 83], "memlock": [32, 66, 95], "memori": [0, 1, 2, 4, 5, 6, 8, 10, 17, 18, 20, 22, 23, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 41, 65, 71, 74, 75, 76, 80, 81, 83, 88, 95, 96, 97, 101, 106], "memorydesc": 0, "memorypoolfre": [1, 92], "memorypoolreserv": [1, 92], "memorypooltrimto": 1, "memorypoolus": 1, "memorytyp": [0, 1], "memorytypestr": 1, "memtyp": 1, "memusagechang": 92, "menableattentiondp": [0, 1], "menablebatchsizetun": 0, "menableblockreus": 0, "menablechunkedcontext": 0, "menablecontextfmhafp32acc": 0, "menablemaxnumtokenstun": 0, "menablepartialreus": 0, "menabletrtoverlap": 0, "mencodedvocab": 0, "mencoderhiddens": 1, "mengineaddr": 1, "menginebuff": 1, "menginepath": 1, "mengines": 1, "mental": 56, "mention": [6, 20, 21, 41, 78], "menu": [36, 37], "merg": [27, 30, 83, 91], "meshgrid": 83, "meshgrid2d": 83, "messag": [11, 27, 32, 35, 38, 39, 60, 61, 68, 71, 75, 83, 89, 92, 96], "met": [0, 1, 3, 13], "meta": [20, 59, 70, 71, 74, 75, 76, 82, 89, 94], "meta_ckpt_dir": 85, "metadata": [8, 31, 35, 74, 99, 101], "metadata_server_config_fil": 35, "metal": [96, 98], "meth": 70, "method": [0, 1, 3, 5, 6, 12, 13, 14, 16, 17, 20, 22, 28, 29, 30, 31, 41, 52, 68, 71, 74, 88, 91, 93, 95, 96, 99, 100, 106, 107], "metric": [0, 29, 30, 31, 71, 73, 74, 75, 76, 78, 80, 81, 96], "mevent": 1, "meventbuffermaxs": 0, "mexecutionconfig": 1, "mextendedruntimeperfknobconfig": 0, "mfastlogit": 0, "mfinishedstep": 1, "mfirstgentoken": 0, "mflagptr": 1, "mfreegpumemoryfract": 0, "mfreepageid": 1, "mfrequencypenalti": 0, "mfuntowicz": 96, "mgathergenerationlogit": 0, "mgemmallreducedtyp": 1, "mgmn": 30, "mgpu": 1, "mgpudiff": 1, "mgpuspernod": 1, "mgpuweightsperc": 0, "mgreedysampl": 0, "mguid": 0, "mguideddecodingconfig": 0, "mguidetyp": 0, "mh": 13, "mh1": 13, "mha": [5, 8, 22, 29, 34, 83, 88, 101], "mhandler": 0, "mhiddens": 1, "mhostcaches": 0, "mi": 93, "mib": 92, "micro": [0, 92], "microbatchid": 0, "microbatchschedul": [100, 107], "microsecond": 0, "microsoft": 16, "middl": 73, "might": [0, 3, 17, 20, 21, 26, 30, 34, 66, 72, 74, 76, 77, 81, 88, 92, 95, 96, 106], "migrat": [20, 86, 96], "million": 74, "millisecond": 0, "millisecondstyp": 0, "mimpl": 0, "min": [0, 1, 6, 23, 27, 28, 29, 33, 71, 74, 76, 81, 83, 95], "min_lat": 83, "min_length": [6, 88], "min_p": [0, 6, 71, 88], "min_token": 71, "mind": [26, 70, 82], "mindim": 1, "mindimfirst": 1, "mini": 96, "minim": [27, 30, 31, 80, 89], "minimum": [0, 5, 6, 33, 71, 74, 75, 78, 83, 88, 92], "minitron": [94, 96], "minittozero": 1, "minlat": [11, 71], "minlength": [1, 6, 96], "minnormedscorescba": 1, "minor": 96, "minp": [0, 1, 6], "minprogresstask": 1, "minputpack": 1, "minputtokenextraid": 0, "mintoken": [0, 96], "mintpsplitdim": 1, "minut": [0, 26, 32, 76], "mip": 0, "mipcmemoryhandl": 1, "mirco": 0, "mish": 84, "mismatch": [20, 95], "misorchestr": 0, "mispagefre": 1, "miss": [0, 7, 74, 96], "missedblock": 0, "missedblocksperrequest": 0, "mission": [27, 30, 31], "mistral": [4, 74, 78, 81, 93, 94, 96], "mistralai": [74, 94], "mistralforcausallm": 94, "misus": 96, "miterstatsmaxiter": 0, "mitig": [20, 27, 30], "mix": [2, 29, 77, 81, 96], "mixed_precis": 71, "mixer": 96, "mixtral": [4, 10, 74, 78, 81, 93, 94, 96], "mixtralforcausallm": 94, "mixtur": [29, 30, 65, 81, 96], "mjointdecodinginput": 1, "mjointdecodingoutput": 1, "mkdir": 36, "mkvcacheconfig": 0, "mkvcachetyp": 1, "mkvfactor": 0, "ml": [83, 96], "mla": [27, 28, 83, 96], "mlayertyp": 1, "mlen": 0, "mlengthpenalti": 0, "mllama": [94, 96], "mllamaconfig": 85, "mllamaforcausallm": 85, "mllamaforconditionalgener": 94, "mlogit": 0, "mlogitsdtyp": 1, "mlogitspostprocessorconfig": 0, "mlookaheaddecodingconfig": 0, "mlookaheaddecodingmaxnumrequest": 0, "mloramodul": 1, "mloraprefetchdir": 0, "mlp": [10, 15, 17, 18, 34, 83, 95, 96, 99], "mlp_4h_to_h": [10, 34], "mlp_bia": 85, "mlp_gate": [10, 34], "mlp_gate_up": [10, 34], "mlp_h_to_4h": [10, 34], "mlp_output": 95, "mlp_router": [10, 34], "mlphiddens": 1, "mlptype": 83, "mm": 96, "mm_data": 74, "mm_embedding_offload": 88, "mma": [29, 83], "mmanag": 1, "mmanagedweightsmap": 1, "mmanageweightstyp": 1, "mmaxadapters": 0, "mmaxattentionwindow": 0, "mmaxattentionwindowvec": 0, "mmaxbatchs": [0, 1], "mmaxbeamwidth": [0, 1], "mmaxdecodingdecodertoken": 1, "mmaxdecodingdrafttoken": 1, "mmaxdecodingenginetoken": 1, "mmaxdraftpathlen": 1, "mmaxencoderlen": 1, "mmaxinputlen": 1, "mmaxlorarank": 1, "mmaxnonleafnodesperlay": 1, "mmaxnumpackedmask": 1, "mmaxnumpath": 1, "mmaxnumtoken": [0, 1], "mmaxpagesperblock": 1, "mmaxpagesperblockdevic": 0, "mmaxpagesperblockhost": 0, "mmaxpositionembed": 1, "mmaxpromptembeddingtables": 1, "mmaxqueues": 0, "mmaxseqidlemicrosecond": 0, "mmaxsequencelen": 1, "mmaxsequencelength": 1, "mmaxtoken": 0, "mmaxtokensinbuff": 0, "mmedusachoic": 0, "mmemorytyp": 1, "mmha": [83, 96], "mminp": 0, "mmintoken": 0, "mmlphiddens": 1, "mmlu": [26, 27, 96], "mmlu_llmapi": 96, "mmmu": 74, "mmodelconfig": [0, 1], "mmodelnam": 1, "mmodelvari": 1, "mmoduleidtomodul": 1, "mmropepositiondelta": 0, "mmroperotarycossin": 0, "mmultiblockmod": 0, "mmultimodalhash": 0, "mmultimodallength": 0, "mmultimodalposit": 0, "mname": [0, 1], "mnbattentionlay": 1, "mnbhead": 1, "mnbkvheadsperlay": 0, "mnblayer": 1, "mnbrnnlayer": 1, "mngramsiz": 0, "mnnvl": [11, 30, 71, 83], "mnorepeatngrams": 0, "mnormalizelogprob": 0, "mnumcopystream": [0, 1], "mnumdecodingenginetoken": 1, "mnumdevicemodulelay": 0, "mnumensurework": 0, "mnumhostmodulelay": 0, "mnumkvheadsperattentionlay": 1, "mnumkvheadspercrossattentionlay": 1, "mnumlanguag": 1, "mnumnod": 0, "mnumputwork": 0, "mnumreturnbeam": 0, "mnumreturnsequ": 0, "mnumsm": 1, "mnumtransformerslay": 1, "modal": [33, 93], "mode": [0, 1, 4, 5, 7, 17, 18, 29, 32, 33, 34, 35, 47, 53, 54, 55, 71, 82, 83, 84, 88, 91, 92, 93, 96, 99], "model": [0, 1, 2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 20, 22, 23, 24, 25, 26, 29, 30, 31, 32, 33, 34, 35, 38, 39, 40, 41, 45, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 65, 68, 71, 72, 73, 76, 79, 82, 83, 84, 86, 87, 88, 92, 93, 97, 98, 101, 102, 103, 104, 105, 106, 107], "model_architectur": 71, "model_cl": 84, "model_cls_fil": 34, "model_cls_nam": 34, "model_config": [34, 71, 88, 99], "model_dir": [10, 14, 15, 16, 17, 18, 20, 28, 53, 74, 77, 85, 87, 89, 95], "model_engin": [100, 106], "model_nam": [30, 54, 75, 88, 97], "model_path": [14, 30, 33, 54, 58, 73, 74], "model_post_init": 71, "model_qu": 74, "model_weights_load": [18, 96], "modelconfig": [0, 6, 88, 96, 99], "modelengin": [100, 106], "modelidtomodel": 1, "modeling_deepseekv3": [27, 29], "modeling_llama": 99, "modeling_mymodel": 99, "modeling_opt": 99, "modeling_util": [71, 99], "modelnam": 1, "modelopt": [16, 20, 68, 74, 75, 87, 96], "modelopt_cuda_ext": 68, "modelpath": 0, "modelrunn": [16, 88, 96], "modelrunnercpp": [88, 96], "modelrunnermixin": 88, "modeltyp": [0, 14], "modelvari": 1, "modelweightsformat": 18, "modelweightsload": [18, 96], "moder": [31, 58], "modern": 88, "modif": [7, 17], "modifi": [3, 7, 66, 74, 78, 81, 82, 95, 96, 97], "modul": [0, 1, 5, 6, 15, 16, 17, 18, 27, 30, 31, 34, 65, 66, 71, 81, 83, 84, 85, 87, 88, 95, 96, 99], "modular": [30, 70, 72], "modularli": 31, "module1": 27, "module10": 27, "module11": 27, "module12": 27, "module13": 27, "module2": 27, "module3": 27, "module4": 27, "module5": 27, "module6": 27, "module7": 27, "module8": 27, "module9": 27, "module_id": 10, "moduleid": [1, 10], "moduleidtomodel": 1, "modulelist": 99, "moduletyp": 1, "modulo": 83, "moe": [10, 18, 27, 28, 30, 34, 51, 65, 71, 81, 83, 85, 96], "moe_4h_to_h": [10, 34], "moe_cluster_parallel_s": 71, "moe_config": [21, 28, 30, 71], "moe_ep_s": 4, "moe_expert_parallel_s": [51, 71], "moe_finalize_allreduce_residual_rms_norm": 83, "moe_gat": [10, 34], "moe_gemm": 12, "moe_h_to_4h": [10, 34], "moe_load_balanc": 30, "moe_plugin": 34, "moe_rout": [10, 34], "moe_shared_": 30, "moe_tensor_parallel_s": [51, 71], "moe_tp_siz": 4, "moeallreduceparam": 83, "moeconfig": [71, 85], "moetopk": 96, "moment": 3, "monboardblock": 0, "monitor": [8, 31, 34], "monitor_memori": [34, 71], "monolith": 5, "monost": 0, "month": 74, "mop": 0, "mopenipc": 1, "moptimaladapters": 0, "morchestratorconfig": 0, "morchleadercomm": 0, "more": [0, 1, 2, 3, 4, 5, 6, 7, 8, 13, 15, 16, 17, 22, 23, 24, 26, 27, 28, 29, 30, 31, 33, 34, 35, 41, 45, 52, 58, 66, 70, 71, 72, 74, 75, 76, 78, 80, 81, 82, 83, 89, 90, 91, 92, 95, 96, 97, 99, 101, 105, 107], "most": [0, 1, 6, 8, 13, 17, 20, 22, 23, 24, 26, 27, 29, 31, 45, 48, 49, 51, 58, 68, 71, 73, 79, 81, 82, 83, 89, 90, 91, 92, 95, 96, 105], "mostli": 30, "mount": [35, 53, 54, 55, 65, 66], "mount_dest": [53, 54, 55], "mount_dir": [53, 54, 55], "moutdim": 1, "moutdimfirst": 1, "moutputbeamhypothes": 1, "mouttpsplitdim": 1, "move": [0, 1, 8, 20, 30, 71, 72, 83, 95, 96], "movement": [8, 17], "mownsev": 1, "mownsstream": 1, "mp4": [35, 39, 61], "mpageblock": 1, "mpagedcontextfmha": 1, "mpagedst": 1, "mpagemanagerconfig": 1, "mpagesmutex": 1, "mpagewidth": 1, "mparallelconfig": 0, "mparticipantid": 0, "mpeftcacheconfig": 0, "mpi": [0, 1, 2, 6, 17, 19, 20, 31, 34, 35, 53, 54, 55, 68, 71, 73, 74, 76, 83, 95, 96, 97], "mpi4pi": [70, 76, 95, 96], "mpi_abort": 70, "mpi_barri": 20, "mpi_comm_world": [6, 70], "mpi_group_barri": 1, "mpicomm": 0, "mpicommsess": 71, "mpin": 1, "mpinneddiff": 1, "mpinnedpool": 1, "mpinnedpooldiff": 1, "mpipelineparallel": [0, 1], "mpirun": [16, 17, 70, 76, 95, 96], "mpisess": 71, "mpistat": 0, "mpointer": 1, "mpool": 1, "mport": 0, "mposteriorthreshold": 0, "mppreducescatt": 1, "mprecis": 1, "mpresencepenalti": 0, "mprocessorbatch": 0, "mprocessormap": 0, "mprompttableoffload": 0, "mpt": [26, 93, 94, 96], "mptforcausallm": 85, "mptmodel": 85, "mqa": [5, 8, 22, 25, 27, 34, 83, 96, 101], "mquantmod": 1, "mrank": [0, 1], "mrecvpollperiodm": 0, "mremotenam": 0, "mrepetitionpenalti": 0, "mreplic": 0, "mreqid": 0, "mrequeststatsmaxiter": 0, "mrnnconfig": 1, "mrope": [0, 83], "mrope_param": [84, 88], "mrope_position_delta": [83, 84, 88], "mrope_rotary_cos_sin": [83, 84], "mrope_rotary_cos_sin_s": 85, "mropeconfig": 0, "mropeparam": [84, 88], "mropepositiondelta": 0, "mroperoratysinco": 0, "mrotaryembeddingdim": 1, "mruntimedefault": 1, "mruntimestream": 1, "msamplingconfig": 1, "mscale": 83, "mscale_all_dim": 83, "mschedulerconfig": 0, "msecondaryofflineminprior": [0, 71], "msecondaryoffloadminprior": 0, "mseed": 0, "mselfidx": 0, "msg": [0, 1, 27, 71], "msinktokenlength": 0, "msizeperhead": [0, 1], "mskipcrossattnblock": 1, "msl": 1, "mslotsperpag": 1, "mspawnprocess": 0, "mspeculativedecodingconfig": 0, "mspeculativedecodingmod": 1, "mspeculativedecodingmodul": 1, "msrcdesc": 0, "mstate": [0, 1], "mstoptokenid": 0, "mstream": 1, "msyncmessag": 0, "mt5": 94, "mtag": 0, "mtaskid": 0, "mtemperatur": 0, "mtensor": 0, "mtensorparallel": [0, 1], "mtoken": 0, "mtokenizerstr": 0, "mtokenrangeretentionconfig": 0, "mtokensperblock": [0, 1], "mtopk": 0, "mtopp": 0, "mtoppdecai": 0, "mtoppmin": 0, "mtoppresetid": 0, "mtotalnumpag": 1, "mtp": [21, 30, 31, 59, 71, 96, 102, 105], "mtp3": 31, "mtp3_autoregress": 27, "mtp3_top1": 27, "mtp3_top10": 27, "mtp3_top15": 27, "mtp3_vanilla": 27, "mtpdecodingconfig": [59, 71], "mtprank": 1, "mtransfermod": 0, "mtrimpool": 1, "mtype": [0, 1], "much": [9, 17, 28, 30, 73, 75, 80, 92], "mul": 83, "multi": [0, 2, 3, 4, 6, 9, 10, 13, 16, 19, 20, 22, 28, 29, 30, 34, 39, 53, 54, 55, 61, 65, 66, 70, 71, 76, 83, 85, 92, 93, 96, 101], "multi_block_mod": [5, 71, 88, 96], "multi_round": 97, "multiblockmod": 0, "multidimension": 83, "multihead": [17, 22], "multimod": [0, 33, 34, 64, 70, 74, 88, 94, 96], "multimodalembed": 0, "multimodalhash": 0, "multimodalinput": 0, "multimodallength": 0, "multimodalmodelrunn": 88, "multimodalposit": 0, "multinod": 77, "multinomi": 6, "multipl": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 13, 17, 18, 27, 28, 29, 30, 31, 32, 34, 46, 58, 71, 72, 76, 77, 78, 80, 83, 84, 88, 89, 90, 95, 96, 97, 101], "multiple_profil": [34, 74, 78, 81, 96], "multipli": [5, 18, 29, 83], "multiply_and_lora": 84, "multiply_collect": 84, "multiprocessor": 17, "munsign": 1, "musecrossattent": 1, "musedynamictre": 0, "musegemmallreduceplugin": 1, "musegptattentionplugin": 1, "musegpudirectstorag": 0, "museloraplugin": 1, "musemambaconv1dplugin": 1, "musemrop": 1, "musepositionembed": 1, "museshapeinfer": 1, "musetokentypeembed": 1, "museuvm": 0, "must": [0, 1, 2, 3, 4, 5, 6, 9, 10, 13, 17, 19, 30, 31, 34, 35, 37, 47, 68, 71, 78, 83, 84, 86, 88, 93, 95], "mutabl": [0, 1], "mutablepageptr": 1, "mutex": [0, 1], "mutual": [6, 93], "muvm": 1, "muvmdiff": 1, "mverificationsets": 0, "mversion": 1, "mvocabs": 1, "mvocabsizepad": 1, "mweight": 0, "mwindows": 0, "mworkerexecutablepath": 0, "mworldconfig": 1, "my": [1, 45, 48, 49, 50, 51, 57, 68, 74, 89, 104, 105], "my_faster_on": 41, "my_model": 15, "my_profile_export": [35, 43, 44], "my_test": 90, "myattent": 99, "myconfig": 99, "mydecoderlay": [15, 99], "mymodel": [15, 99], "mymodelforcausallm": [15, 99], "n": [1, 5, 10, 13, 16, 17, 28, 29, 32, 35, 45, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 68, 70, 71, 74, 76, 80, 83, 84, 85, 89, 92, 93, 95, 96, 103], "n1": [32, 52, 57], "n2": [32, 52], "n3": 52, "n4": 52, "n_worker": 71, "na": [74, 96], "naiv": 81, "naivepatternrewriter_replaceaddwithsub": 7, "name": [0, 1, 3, 6, 7, 10, 12, 16, 17, 33, 35, 36, 45, 48, 49, 50, 51, 54, 57, 58, 59, 65, 68, 70, 71, 74, 75, 76, 83, 85, 86, 87, 88, 89, 95, 96, 97, 99, 104, 105], "named_network_output": 95, "named_paramet": 18, "namespac": [0, 1, 70, 85], "nanoflow": 103, "nation": 74, "nationwid": 74, "nativ": [20, 23, 29, 30, 33, 70, 96, 99], "native_quant_flow": 85, "natur": [20, 29, 30, 35, 39, 61, 76], "naur": [0, 3, 71], "nbattentionlay": [0, 1], "nbdim": 1, "nbhead": 1, "nbkvhead": [0, 1], "nbkvheadperlay": 0, "nblayer": 1, "nbrnnlayer": 1, "nccl": [11, 17, 27, 30, 34, 71, 83, 95, 96], "nccl_p2p_level": 96, "nccl_plugin": 34, "ncclplugin": 17, "ncclrecv": [30, 83], "ncclsend": [30, 83], "ncuda_graph_config": 32, "nd": [74, 83], "ndarrai": [83, 84, 88], "ndim": 83, "nearest": [29, 71, 83], "nearli": [7, 23, 29], "necess": 13, "necessari": [1, 4, 13, 27, 29, 30, 56, 78, 83, 91, 96, 105, 106], "necessarili": [1, 17, 92], "necessit": 30, "need": [1, 2, 3, 5, 6, 7, 9, 13, 14, 15, 16, 17, 18, 19, 20, 21, 27, 28, 29, 30, 31, 32, 33, 35, 36, 41, 47, 51, 53, 54, 55, 56, 66, 68, 70, 71, 72, 74, 75, 76, 77, 78, 80, 81, 82, 83, 85, 86, 88, 90, 92, 95, 96, 97, 99, 100, 101, 106, 107], "needed_block": 107, "needsdecoderprologu": 1, "needskvcacherewind": 1, "neg": [1, 52, 71, 82, 83], "neglig": [9, 26, 80], "neither": [3, 83, 92], "nemo": [16, 19, 34, 72, 76, 88, 93, 94, 96], "nemo_ckpt_dir": 85, "nemo_prompt_convert": 88, "nemotron": [94, 96], "nemotron_na": 96, "nemotronforcausallm": 94, "nemotronna": [94, 96], "nemotronnasforcausallm": 94, "nenable_autotun": 32, "nenable_min_lat": 32, "neox": [5, 6, 93, 94, 96], "nest": 7, "net": [9, 71, 95], "net_guard": 7, "network": [3, 4, 5, 7, 11, 17, 19, 20, 29, 30, 34, 47, 83, 89, 92, 93, 95, 96], "neural": [4, 7, 17, 89, 96], "neva": [94, 96], "never": [7, 74, 82], "nevertheless": 30, "new": [0, 1, 3, 5, 6, 7, 9, 10, 13, 14, 20, 23, 24, 27, 28, 30, 35, 36, 38, 40, 45, 48, 49, 50, 51, 52, 60, 62, 65, 66, 68, 70, 71, 72, 80, 81, 83, 88, 89, 96, 98, 100, 106], "new_decoder_architectur": [16, 85], "new_generated_id": 88, "new_input": 7, "new_line_token": 52, "new_out": 7, "new_shap": 83, "new_tensor": 83, "new_token": 88, "new_workflow": 96, "newactiverequestsqueuelatencym": [0, 35], "newer": [94, 96], "newest": [24, 71], "newli": [0, 28, 30, 71, 80], "newlin": 90, "newsiz": 1, "newtoken": 1, "newtokensstep": 1, "newtokensvec": 1, "newvalu": 0, "next": [1, 10, 13, 17, 20, 23, 28, 30, 65, 66, 72, 77, 78, 80, 81, 82, 88, 92, 94, 96, 103], "next_logit": 88, "next_medusa_input_id": 88, "next_medusa_logit": 88, "next_step_buff": 88, "next_step_tensor": 88, "nextdraftindic": 1, "nextdraftlen": 1, "nextdraftpath": 1, "nextdraftprob": 1, "nextdrafttoken": 1, "nextdrafttokenslen": 1, "nextflattoken": 1, "nextgenerationlength": 1, "nextn": 28, "nextpositionoffset": 1, "ngc": [65, 66, 68, 89, 91, 96, 98], "ngoanpv": 96, "ngram": [0, 6, 59, 65, 71, 85], "ngramdecodingconfig": [59, 71], "ngramsiz": 0, "ngroup": 83, "nhead": 83, "nhere": 47, "ni": [47, 93], "nic": 30, "nice": 30, "nine": 89, "nixl": [0, 31, 71], "nj": 50, "njane": [45, 48, 49, 50, 51, 68, 89], "njason": 56, "nkv_cache_config": 32, "nmh": 88, "nmt": [88, 94, 96], "nn": [83, 99], "no_quant": 71, "no_repeat_ngram_s": [6, 71, 88], "no_schedule_after_st": 107, "no_schedule_until_st": 107, "no_weights_load": 33, "noauxtckernel": 27, "node": [0, 2, 6, 11, 19, 28, 29, 30, 31, 32, 34, 53, 54, 55, 65, 70, 71, 73, 76, 77, 83, 88, 93, 95, 96, 97], "noexcept": [0, 1], "nomin": [45, 50, 68, 89], "non": [0, 2, 5, 8, 14, 17, 20, 26, 27, 28, 29, 30, 34, 71, 83, 95, 96], "non_block": 52, "non_gated_vers": 83, "none": [1, 6, 7, 15, 18, 20, 34, 35, 41, 52, 56, 58, 59, 71, 74, 76, 80, 83, 84, 85, 86, 87, 88, 95, 96, 99, 101], "nonetyp": [71, 88], "nonzero": 83, "nor": [30, 92], "norepeatngrams": [0, 1, 6], "norm": [18, 21, 29, 54, 73, 74, 75, 76, 83, 96, 99], "norm_before_bmm1": [84, 85], "norm_elementwise_affin": 84, "norm_ep": 84, "norm_epsilon": [16, 85], "norm_factor": 5, "norm_num_group": 84, "norm_pre_residual_weight": 83, "norm_quant_fus": 34, "norm_typ": 84, "norm_weight": 83, "normal": [0, 6, 9, 10, 14, 26, 27, 28, 29, 30, 33, 71, 74, 83, 92, 96], "normalize_log_prob": 71, "normalize_weight": 10, "normalized_shap": [83, 84], "normalizelogprob": [0, 1], "normedscorescba": 1, "north": [15, 17, 95], "northeastern": 89, "not_op": 83, "notabl": 26, "notat": 28, "note": [1, 2, 7, 9, 10, 11, 12, 13, 17, 21, 24, 26, 27, 28, 29, 30, 32, 34, 37, 41, 53, 54, 55, 65, 66, 70, 71, 74, 75, 78, 80, 82, 83, 86, 88, 90, 92, 93, 94, 95, 98, 99, 106], "notic": 56, "notifysyncmessag": 0, "notimplementederror": 20, "nougat": [93, 94, 96], "now": [6, 12, 13, 16, 18, 22, 27, 28, 30, 72, 74, 80, 86, 89, 92, 96], "np": 83, "npy": 88, "npytorch_backend_config": 35, "nsight": 65, "nspeculative_config": 32, "nsy": [73, 97], "ntask": [17, 35, 53, 54, 55], "nucleu": 58, "null": [1, 16, 32, 74, 89], "nullopt": [0, 1], "nullptr": [0, 1], "num": [0, 1, 21, 33, 54, 65, 71, 73, 74, 75, 76, 78, 79, 81], "num_attention_head": [16, 83, 84, 85], "num_aud_token": 88, "num_beam": [6, 88], "num_beam_group": 6, "num_block": [88, 106], "num_bucket": [83, 84], "num_channel": [84, 85], "num_class": 84, "num_context": 101, "num_ctx_serv": 97, "num_ctx_token": 101, "num_draft_token": [0, 83, 88], "num_eagle_lay": 71, "num_embed": 84, "num_experts_per_tok": 4, "num_extra_kv_token": 71, "num_gen_serv": 97, "num_gener": 101, "num_group": [83, 84], "num_head": [5, 18, 83, 88, 101], "num_hidden_lay": [16, 85, 99, 106], "num_imag": 88, "num_img_token": 88, "num_inst": 31, "num_key_value_head": [16, 85, 106], "num_kv_head": [8, 83, 84, 88, 101, 106], "num_kv_heads_origin": 83, "num_kv_heads_per_cross_attn_lay": 88, "num_kv_heads_per_lay": 88, "num_lay": [83, 84, 88, 106], "num_ln_in_parallel_attn": 85, "num_local_block": 84, "num_local_expert": 4, "num_lora_module_lay": 10, "num_lora_modules_lay": 10, "num_medusa_head": [71, 85, 87, 88], "num_medusa_lay": [85, 87], "num_multimodal_token": 0, "num_nextn_predict_lay": [21, 28, 59, 71], "num_nextn_predict_layers_from_model_config": 71, "num_orig_po": 83, "num_po": 83, "num_postprocess_work": [35, 71], "num_profil": 85, "num_q_head": 27, "num_request": [21, 28, 33, 74, 75], "num_return_sequ": [88, 96], "num_sampl": 73, "num_slot": 30, "num_task": 84, "num_token": [5, 27, 83, 101], "num_tokens_per_block": [83, 106], "num_tokens_per_task": 84, "num_video": 88, "numa": [11, 30], "numacceptedtoken": 0, "numactiverequest": 0, "numactl": 30, "numattentionhead": 1, "numavailablepag": 1, "numbeamscba": 1, "number": [0, 1, 2, 3, 4, 5, 6, 8, 13, 17, 21, 25, 27, 28, 29, 30, 31, 32, 33, 34, 35, 53, 54, 55, 71, 74, 75, 76, 77, 78, 80, 81, 82, 83, 84, 88, 90, 92, 93, 95, 96, 97, 99, 101, 106], "numblockspercachelevel": 0, "numcompletedrequest": 0, "numcontextrequest": [0, 1], "numcopystream": [0, 1], "numctxgpu": 31, "numctxsequ": 1, "numctxtoken": 0, "numdevicemodulelay": 0, "numdrafttoken": [0, 1], "numdrafttokenshost": 1, "numeaglelay": 1, "numel": 88, "numensurework": 0, "numer": [6, 11, 27, 65, 74, 89, 94, 97], "numexpert": 1, "numgeneratedtoken": 0, "numgengpu": 31, "numgenrequest": 0, "numgensequ": 1, "numgentoken": [0, 1], "numhead": 6, "numhostmodulelay": 0, "numkvattentionhead": 1, "numkvhead": 6, "numlanguag": 1, "numlay": 6, "nummissedblock": 0, "numnewactiverequest": 0, "numnewallocatedblock": 0, "numnewtokenscumsum": 96, "numnod": [0, 96], "numpag": 1, "numpausedrequest": 0, "numpi": [10, 83, 88], "numputwork": 0, "numqueuedrequest": [0, 96], "numrequestswithdrafttoken": 0, "numreturnbeam": 0, "numreturnsequ": [0, 1, 3], "numreusedblock": 0, "numscheduledrequest": 0, "numsequ": 1, "numslot": 1, "numtoken": 1, "numtotalallocatedblock": 0, "numtransformerslay": 1, "nvbugspro": 90, "nvcc": 21, "nvcr": 96, "nvfp4": [27, 30, 33, 34, 65, 71, 74, 96, 104], "nvidia": [16, 17, 19, 20, 21, 22, 23, 24, 26, 28, 30, 31, 32, 33, 34, 36, 38, 39, 40, 42, 43, 44, 45, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 65, 66, 67, 68, 70, 72, 74, 75, 76, 81, 83, 89, 90, 91, 92, 94, 95, 96, 104, 105], "nvila": [94, 96], "nvinfer1": [0, 1], "nvl": [1, 34, 96], "nvl36": 77, "nvl72": [29, 77, 94], "nvlink": [6, 11, 30, 31, 76, 77, 79, 96], "nvswitch": [17, 27], "nvtx": 71, "nyou": 47, "n\u7b54\u6848": 63, "o": [0, 1, 7, 10, 20, 25, 27, 29, 32, 53, 54, 55, 63, 73, 95], "o_proj": 18, "oai": [35, 39, 61], "obei": 95, "object": [0, 1, 3, 9, 15, 17, 18, 20, 32, 41, 47, 52, 71, 83, 84, 85, 86, 88, 89, 92, 100, 105], "observ": [2, 29, 31, 75], "obtain": [19, 31, 67, 75, 83], "obviou": [21, 29], "occas": 95, "occasion": 96, "occup": [5, 92, 103], "occupi": [26, 29, 30, 92], "occur": [6, 9, 31, 106, 107], "ocean": 58, "off": [9, 12, 29, 31, 73, 78, 80, 81, 90, 92, 96], "offer": [17, 19, 26, 27, 31, 72, 91, 101], "offic": 47, "officenetsecur": 47, "offici": [5, 21, 28, 74], "offlin": [15, 24, 29, 45, 74, 75, 96], "offload": [0, 8, 14, 30, 34, 65, 71, 96], "offset": [1, 83, 88, 93, 96], "offsetdim": 1, "ofitensor": 0, "often": [0, 3, 8, 13, 22, 26, 27, 30, 31, 71, 77, 78, 83], "ok": 95, "old": [7, 10, 28, 95], "older": [9, 20, 66, 94], "oldest": [10, 71], "oldvalu": 0, "omit": [1, 3, 20, 67, 83, 89], "ompi": [68, 95], "onboard": [0, 9, 71, 92], "onboard_block": 71, "onboardblock": 0, "onc": [0, 3, 5, 6, 7, 17, 19, 28, 30, 31, 32, 58, 66, 68, 70, 71, 78, 83, 90, 92], "one": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 11, 13, 16, 17, 18, 20, 22, 27, 28, 29, 31, 33, 34, 35, 36, 56, 71, 74, 76, 77, 78, 81, 82, 83, 84, 86, 88, 91, 92, 95, 96, 97, 99, 103, 107], "ones": [0, 10], "oneshot": [11, 27, 71, 83], "oneshotallreduc": 27, "oneshotar": 27, "onevis": [94, 96], "ongo": [20, 30], "onli": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 12, 13, 14, 15, 17, 18, 20, 21, 26, 28, 29, 30, 31, 33, 34, 35, 41, 52, 58, 65, 68, 70, 71, 74, 75, 76, 77, 78, 80, 81, 82, 83, 84, 86, 88, 90, 92, 94, 96, 100, 107], "onlin": [19, 24, 45], "only_cross_attent": 84, "onnx": [34, 83], "onnx__gathernd": 83, "onto": 6, "oom": [21, 22, 25, 29, 92], "ootb": [29, 96], "op": [0, 1, 7, 29, 71, 83, 96], "op_and": 83, "op_or": 83, "op_xor": 83, "opaqu": 7, "opaque_st": 71, "open": [6, 12, 22, 27, 29, 30, 72, 73, 89, 95, 96], "openai": [31, 32, 35, 64, 89, 96], "openipc": 1, "openmpi": 96, "opensora": 96, "openssh": 36, "oper": [0, 1, 3, 5, 6, 7, 11, 13, 16, 17, 18, 27, 29, 30, 31, 34, 57, 71, 74, 77, 78, 81, 83, 89, 92, 94, 96, 100, 101, 106], "opportun": 74, "opposit": 52, "opt": [3, 16, 26, 29, 36, 83, 93, 94, 95, 96], "opt_batch_s": [71, 85], "opt_num_token": [34, 71, 85], "optforcausallm": [16, 85], "optim": [1, 3, 6, 7, 8, 11, 12, 13, 17, 19, 20, 22, 23, 24, 25, 26, 30, 32, 33, 34, 45, 48, 52, 57, 66, 68, 72, 74, 75, 77, 78, 79, 83, 89, 92, 94, 95, 96, 98, 100, 101, 103, 104, 106], "optimaladapters": [0, 1], "option": [0, 1, 3, 6, 7, 8, 11, 12, 13, 15, 20, 23, 28, 33, 34, 35, 41, 52, 54, 56, 58, 59, 65, 67, 68, 71, 73, 74, 75, 76, 77, 79, 80, 83, 86, 88, 89, 90, 91, 92, 95, 96, 97, 99, 101, 105, 106], "optionalbufferptr": 1, "optionaltensorptr": 1, "optmodel": 85, "optvec": 1, "orchestr": [0, 13, 30, 31, 95, 96, 97], "orchestratorconfig": 0, "orchleadercomm": 0, "order": [0, 2, 5, 8, 18, 22, 71, 74, 75, 78, 82, 83, 84, 89, 91, 92, 97, 105], "org": [0, 1, 4, 10, 34, 68, 83, 93, 103], "organ": [8, 72, 90, 106], "orient": [29, 30, 31], "origin": [0, 5, 7, 10, 11, 28, 29, 30, 52, 83, 96, 99], "original_max_po": 83, "original_max_position_embed": [83, 84], "originaltemperatur": 1, "oserror": 96, "osl": [22, 23, 24, 25, 27, 28, 29, 30, 74, 75, 81, 97], "osl256": 31, "oss": 12, "ostream": [0, 1], "other": [0, 1, 2, 3, 4, 5, 6, 9, 11, 12, 13, 17, 18, 20, 22, 27, 28, 29, 30, 31, 32, 34, 41, 53, 54, 55, 66, 70, 71, 72, 75, 76, 77, 78, 80, 81, 82, 83, 86, 90, 92, 95, 96, 101, 107], "other_audio_input": 88, "other_decoder_input": 88, "other_vision_input": 88, "othercach": 1, "otherwis": [0, 1, 3, 5, 6, 41, 71, 74, 83, 88, 95, 101], "our": [21, 26, 27, 28, 29, 30, 45, 47, 48, 49, 51, 68, 74, 75, 78, 80, 81, 83, 89, 94, 95, 96, 99], "out": [0, 1, 2, 10, 20, 22, 23, 24, 25, 27, 28, 29, 30, 32, 45, 53, 54, 55, 70, 73, 75, 78, 80, 81, 83, 89, 90, 91, 92, 96], "out_bia": 84, "out_channel": 84, "out_context_dim": 84, "out_dim": 84, "out_fatur": 16, "out_featur": [16, 17, 84], "out_hidden_s": 83, "out_of_tree_exampl": 99, "out_point": 83, "out_tp": [22, 25], "outdim": 1, "outdimfirst": 1, "outer": 83, "outlin": 73, "outperform": 31, "output": [0, 1, 5, 6, 7, 9, 10, 13, 17, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 33, 34, 35, 41, 43, 44, 45, 47, 48, 49, 50, 51, 52, 54, 56, 57, 58, 59, 68, 71, 73, 75, 76, 77, 78, 79, 81, 82, 83, 84, 88, 89, 95, 96, 97, 100, 101, 107], "output_ctx0": 31, "output_ctx1": 31, "output_cum_log_prob": 88, "output_dim": 84, "output_dir": [10, 14, 15, 16, 17, 20, 34, 74, 77, 85, 87, 89, 95], "output_dtyp": [83, 84], "output_gen0": 31, "output_gen1": 31, "output_generation_logit": 88, "output_id": 88, "output_json": 33, "output_log_prob": 88, "output_multiplier_scal": 85, "output_pad": [83, 84], "output_path": 30, "output_s": 84, "output_seqlen": [22, 25], "output_sequence_length": 88, "output_timing_cach": [34, 71], "output_token": 74, "outputbuff": 1, "outputconfig": [0, 3, 41, 96], "outputidscba": 1, "outputlen": 0, "outputlogprob": 1, "outputtokenid": [0, 3], "outsid": [13, 19, 20, 89, 101], "outsiz": 1, "outstand": 28, "outtpsplitdim": 1, "outweigh": 77, "over": [0, 1, 9, 13, 18, 21, 23, 24, 26, 27, 29, 31, 32, 37, 58, 71, 73, 74, 77, 80, 81, 83, 96], "overal": [3, 5, 9, 11, 13, 21, 28, 29, 30, 31, 72, 77, 78, 80, 81, 82, 99], "overcom": [5, 17, 27], "overflow": 1, "overhead": [0, 2, 3, 17, 27, 28, 29, 31, 57, 71, 77, 96, 101, 103], "overiew": 74, "overlap": [0, 2, 13, 21, 27, 28, 29, 30, 71, 96, 98, 102, 107], "overlap_schedul": 59, "overload": [0, 1], "overrid": [1, 18, 20, 41, 65, 71, 83, 88], "overridden": [66, 91], "override_field": 85, "overshadow": 77, "oversubscrib": [70, 76], "overus": 90, "overview": [2, 3, 8, 21, 26, 30, 65, 66, 73, 74, 76, 98, 100], "overwhelm": 56, "overwrit": [5, 33, 35], "own": [0, 1, 9, 13, 16, 17, 18, 19, 20, 21, 28, 30, 32, 41, 66, 99], "ownership": 0, "ownsev": 1, "ownsstream": 1, "p": [0, 6, 13, 19, 32, 36, 52, 53, 54, 55, 58, 71, 85, 88, 96, 105], "p2p": [30, 83], "p50": [74, 75], "p90": [74, 75, 76], "p95": [74, 75, 76], "p99": [74, 75, 76], "p_max": 0, "p_x": 0, "pack": [0, 1, 6, 34, 65, 82, 83, 85, 92, 99], "packag": [3, 66, 68, 74, 76, 95, 96], "packed_length": 85, "packedinput": 1, "packedmask": 1, "packedmaskhost": 1, "packedmaskhostcopi": 1, "packedmasksdevic": 1, "packedpositionid": 1, "pad": [0, 1, 6, 7, 10, 29, 34, 35, 65, 71, 72, 83, 84, 88, 92, 96], "pad_id": [71, 88], "pad_lda": 84, "pad_ldc": 84, "pad_token_id": 88, "padding_2d": 83, "padding_back": 83, "padding_bottom": 83, "padding_front": 83, "padding_left": 83, "padding_mod": 84, "padding_right": 83, "padding_top": 83, "padid": 0, "page": [1, 2, 6, 9, 17, 24, 34, 65, 74, 76, 78, 83, 89, 90, 92, 96, 101], "paged_context_fmha": [78, 96], "paged_kv_cach": [10, 34, 74, 88], "paged_st": [34, 88], "pagedcontextfmha": 1, "pagedkvcach": 6, "pagedst": 1, "pageid": 1, "pageidx": 1, "pagemanagerconfig": 1, "pageptr": 1, "pagewidth": 1, "paid": 30, "pair": [0, 1, 22, 28, 71, 78, 81, 83], "paper": [2, 10, 13, 23, 28, 29, 31, 93, 101], "par": [80, 81], "parallel": [0, 1, 2, 3, 5, 6, 13, 16, 17, 21, 22, 24, 25, 28, 31, 32, 33, 35, 51, 65, 70, 71, 75, 78, 79, 83, 84, 85, 92, 96, 97, 99, 102, 107], "parallel_attent": [16, 85], "parallelconfig": [0, 96], "param": [0, 1, 18, 45, 48, 49, 50, 51, 68, 71, 83, 84, 88, 89], "paramet": [0, 1, 3, 4, 5, 8, 9, 10, 13, 14, 16, 17, 18, 20, 21, 29, 31, 32, 33, 34, 35, 52, 53, 58, 71, 74, 77, 78, 79, 82, 83, 84, 85, 88, 90, 91, 92, 96, 97, 101, 105], "parametr": 88, "parent": [0, 1, 18, 20, 74], "parenthash": 0, "parentid": 1, "pareto": 31, "pari": [45, 48, 49, 50, 51, 68, 89], "pars": [1, 33, 71], "parse_arg": 57, "parser": [35, 57, 64, 71], "part": [1, 3, 4, 7, 17, 18, 20, 29, 65, 66, 70, 71, 72, 75, 80, 81, 82, 83, 88, 90, 92], "part2": 96, "parti": 96, "partial": [0, 4, 9, 17, 27, 71, 77, 90], "particip": [0, 83, 96], "participantid": [0, 2], "particular": [0, 3, 79, 80, 81, 89, 91], "particularli": [27, 29, 30, 31, 66, 81, 106], "partit": [5, 10, 17, 53, 54, 55], "pass": [0, 1, 3, 5, 7, 9, 10, 13, 17, 18, 30, 33, 41, 52, 56, 70, 71, 73, 74, 76, 78, 80, 81, 83, 84, 85, 88, 90, 92, 96, 99, 100, 101, 104, 105, 107], "past": [0, 5, 28, 30, 31], "past_key_valu": [83, 84], "past_key_value_length": 84, "past_key_values_length": 84, "past_kv_length": 88, "past_sequence_length": 88, "patch": [84, 88], "patch_siz": [84, 85], "path": [0, 1, 3, 5, 12, 13, 16, 18, 21, 28, 30, 32, 33, 34, 35, 41, 45, 48, 49, 50, 51, 53, 54, 55, 58, 59, 63, 66, 68, 70, 71, 73, 74, 75, 76, 78, 83, 88, 89, 91, 96, 97], "path_to_llama_from_hf": 100, "pathlib": [63, 71], "pathlik": 85, "pathorn": 96, "pathsoffset": 1, "pattern": [4, 27, 29, 30, 65, 71, 83, 90, 96], "patternanalyz": 7, "patternrewrit": 7, "paus": [0, 30, 82, 107], "paused_request": 107, "pcie": [11, 30, 34], "pd": 30, "pdf": [0, 4, 10], "pdl": [27, 96], "peak": [0, 21, 22, 23, 27, 75], "peer": 30, "peft": 71, "peft_cache_config": [41, 71], "peftcacheconfig": [0, 71], "peftcachemanag": [0, 96], "penal": [0, 6, 71], "penalti": [96, 105], "penalty_alpha": 6, "pend": 107, "pending_request": 107, "per": [0, 1, 3, 5, 6, 8, 11, 13, 17, 20, 21, 22, 24, 25, 27, 28, 29, 30, 31, 32, 33, 34, 35, 53, 54, 55, 71, 74, 75, 76, 77, 78, 83, 84, 92, 93, 96], "per_channel": 93, "per_group": 93, "per_token": 93, "per_token_scal": 83, "perceiv": 23, "percent": [0, 14], "percentag": [10, 14, 33, 74, 75, 76], "percentil": [74, 96], "perf": [0, 21, 29, 31, 35, 64, 71, 83, 96], "perf_best_practic": 96, "perfect": [30, 31], "perfectli": 30, "perform": [0, 1, 2, 3, 5, 6, 7, 10, 12, 17, 18, 19, 20, 22, 24, 25, 28, 29, 34, 35, 41, 57, 66, 70, 71, 72, 74, 75, 77, 80, 82, 83, 88, 89, 94, 96, 99, 101, 106], "performantli": 22, "period": 30, "permut": 83, "persimmon": 96, "persist": 26, "person": [36, 52, 56], "phase": [0, 2, 7, 13, 22, 25, 27, 28, 29, 30, 31, 34, 65, 74, 79, 80, 81, 82, 83, 92, 96, 97, 101, 106], "phi": [83, 93, 94, 96], "phi3config": 85, "phi3forcausallm": 85, "phi3model": 85, "phiconfig": 85, "phiforcausallm": 85, "phimodel": 85, "physic": [83, 92], "pick": 80, "pickl": 96, "piec": [30, 80], "piecewis": 71, "pin": [0, 1, 9], "ping": 96, "pinnedmemusag": 0, "pinnedpool": 1, "pip": [21, 35, 65, 66, 89, 96], "pip3": 68, "pipelin": [0, 1, 3, 6, 17, 22, 25, 33, 34, 35, 51, 65, 71, 74, 75, 79, 92, 96, 107], "pipeline_parallel_s": [51, 71, 77, 78], "pipelineparallel": [0, 1, 6], "pipelineparallelismrank": 1, "pitfal": [9, 20], "pixart": 84, "pixartalphatextproject": 84, "pixel_valu": 85, "pl": [68, 74], "place": [1, 30, 34, 68, 83, 96, 99], "placemen": 30, "placement": [27, 30], "plai": 80, "plan": [3, 5, 27, 30, 31, 66], "planner": 96, "platform": [30, 36, 37, 45, 48, 49, 51, 66, 68, 72, 74, 89, 96, 98], "pleas": [2, 5, 7, 11, 13, 15, 22, 24, 25, 26, 27, 29, 30, 31, 32, 37, 41, 47, 66, 67, 68, 70, 74, 75, 77, 79, 83, 95, 96, 98, 107], "plot": 31, "plu": [11, 30, 31, 88], "plugin": [5, 6, 7, 14, 16, 65, 66, 71, 80, 83, 85, 89, 92, 93, 95, 96], "plugin_config": [71, 78, 81, 83, 85], "plugin_namespac": 7, "plugin_typ": 7, "plugin_v2": 7, "plugin_v2_gemm_0": 95, "pluginconfig": [71, 86], "pluginconfigmeta": 86, "pluginfield": 96, "pluginv2build": 95, "pm": [21, 27, 74], "pmi": 95, "pmi2_init": 95, "pmix": [17, 35, 53, 54, 55, 95], "png": [35, 39, 44, 61], "po": 84, "point": [1, 5, 17, 19, 23, 26, 30, 31, 47, 51, 71, 75, 77, 82, 83, 89, 93, 95, 96, 97], "pointer": [0, 1, 6, 18, 30, 83, 88, 96], "pointerelementtyp": 1, "polar": 94, "polici": [0, 1, 30, 33, 71, 74, 76, 92], "poll": [0, 35], "polyhedr": 17, "pong": 96, "pool": [0, 1, 5, 29, 30, 31, 65, 71, 83, 88, 106, 107], "pooled_project": [84, 85], "pooled_projection_dim": 84, "pooledpin": 0, "popd": 95, "popfirstgentoken": 0, "popul": [1, 5, 17, 83], "popular": [5, 16, 20, 26, 28, 37, 70], "port": [0, 31, 32, 35, 37, 42, 89], "portfolio": 24, "portion": [4, 77, 83, 92], "pos_emb_typ": 83, "pos_embd_param": 101, "pos_embed_max_s": 84, "pos_embed_typ": 84, "pose": 81, "posit": [0, 1, 13, 27, 28, 71, 74, 83, 84, 88, 96, 101], "position_embed": [83, 84], "position_embedding_typ": [5, 16, 83, 84, 85], "position_encoding_2d": 85, "position_id": [85, 88, 95, 99, 101], "positionalembeddingparam": 101, "positionembeddingtyp": [5, 83, 84, 85], "positionid": [0, 1], "positionidsbas": 1, "positionidsdevic": 1, "positionidshost": 1, "positionidshostcopi": 1, "positionoffset": 1, "positionoffsetsdevic": 1, "positionoffsetshost": 1, "positionoffsetshostcopi": 1, "posix": 0, "posix_debug_fallback": 0, "possibl": [3, 5, 6, 9, 13, 17, 21, 28, 29, 30, 31, 34, 41, 66, 68, 71, 72, 73, 74, 75, 78, 80, 82, 83, 91, 92, 95, 96, 100], "possibli": [1, 8, 83], "post": [0, 16, 23, 26, 27, 28, 29, 30, 31, 72, 73, 83, 89, 96, 102], "post_act_fn": 84, "post_attention_layernorm": [18, 99], "post_input_id": 88, "post_layernorm": [15, 16, 18, 83, 95], "post_merg": 90, "post_pad": 83, "post_prompt": 88, "post_strid": 83, "posterior_threshold": 71, "posterioralpha": 1, "posterioralphahost": 1, "posteriorthreshold": [0, 1], "posteriorthresholdhost": 1, "postprocess": [35, 71, 84], "postprocess_tokenizer_dir": 71, "postprocessor": [0, 71], "postprocparam": 71, "potenti": [0, 1, 8, 13, 29, 30, 34, 73, 74, 78, 99], "pow": 83, "power": [9, 17, 24, 26, 27, 29, 30, 52, 72, 80, 96], "pp": [0, 2, 6, 10, 22, 25, 31, 33, 35, 74, 76, 83, 96], "pp2": [31, 74], "pp_communicate_final_output_id": 88, "pp_communicate_new_token": 88, "pp_reduce_scatt": [34, 81], "pp_size": [16, 17, 33, 35, 42, 74, 75, 77, 87, 96], "ppreducescatt": 1, "pr": [27, 30], "practic": [5, 8, 17, 23, 24, 27, 29, 30, 31, 65, 89, 92, 96], "pre": [0, 1, 3, 5, 16, 19, 30, 31, 65, 66, 68, 71, 72, 74, 83, 89, 90, 91, 92, 96, 101], "pre_input_id": 88, "pre_layernorm": 83, "pre_merg": 90, "pre_onli": 84, "pre_pad": 83, "pre_prompt": 88, "pre_quant_scal": [16, 71], "pre_strid": 83, "prebuilt": [66, 89], "preced": [17, 83], "precis": [1, 6, 18, 21, 22, 26, 30, 33, 34, 65, 74, 78, 81, 86, 89, 92, 94, 96], "precompute_relative_attention_bia": 85, "precomputed_relative_attent": 84, "predefin": [13, 99, 101], "predict": [1, 5, 13, 27, 28, 30, 96], "predictor": 13, "predictsdrafttoken": 1, "prefer": [12, 26, 66], "prefer_managed_weight": 84, "prefer_plugin": 83, "prefetch": 27, "prefil": [0, 29, 30, 31, 33, 71, 79, 102], "prefix": [3, 13, 16, 28, 70, 76, 83, 86, 90, 95], "prefix_token_ad": 52, "preliminari": [22, 24, 25, 30], "preload": 18, "premis": 28, "prepar": [0, 2, 27, 28, 30, 54, 65, 73, 80, 83, 85, 93, 96, 101, 105], "prepare_dataset": [21, 54, 73, 74, 75, 76], "prepare_input": [85, 92], "prepare_position_ids_for_cogvlm": 88, "prepare_recurrent_input": 85, "prepare_resourc": [100, 106], "prepend": 95, "preprocess": [18, 33, 88, 93], "preprocess_weights_hook": 85, "preprocessed_dataset": 33, "preprocessor": [31, 74], "preqrequisit": 68, "prequant_scaling_factor": 16, "prerequisit": [65, 68], "presenc": [6, 17], "presence_penalti": [71, 88, 96], "presencepenalti": [0, 1, 6], "present": [0, 30, 31, 71, 74, 80, 81, 93, 96], "preserv": 78, "presid": [45, 68, 76, 82, 89], "pressur": 30, "pretrain": 19, "pretrained_config": 99, "pretrained_model_name_or_path": 85, "pretrainedconfig": [15, 20, 71, 85, 86, 99], "pretrainedmodel": [20, 85, 92], "pretrainedtoken": 52, "pretrainedtokenizerbas": 71, "prevdrafttokenslen": 1, "prevent": [27, 29, 33, 65, 70], "preview": 96, "previou": [1, 3, 4, 12, 13, 20, 21, 23, 28, 30, 67, 74, 76, 77, 78, 80, 81, 82, 89, 96], "previous": [1, 12, 22, 78, 80, 82, 96], "prevscor": 1, "prewritten": 89, "price": 74, "primari": [0, 1, 8, 26, 30, 92, 107], "primarili": 101, "primit": [17, 29, 30, 72, 89], "principl": 30, "print": [1, 5, 33, 35, 41, 45, 47, 48, 49, 50, 51, 52, 56, 57, 58, 59, 60, 61, 62, 63, 68, 71, 74, 75, 76, 82, 89, 90, 92, 95], "print_iter_log": [21, 54, 71], "prior": [3, 34, 66, 68], "priorit": [26, 80, 82], "prioriti": [0, 1, 8, 9, 18, 71], "prioritytyp": 0, "priorityupd": 0, "privat": [0, 1, 6, 32, 71], "privileg": 7, "prm": 94, "pro": 27, "prob": [83, 105], "probabilist": 84, "probabl": [0, 1, 6, 9, 13, 27, 28, 58, 71, 83, 88, 96], "probil": 1, "problem": [5, 21, 29, 95], "proc": 18, "proccessed_weight": 18, "proccessed_zero": 18, "proce": 31, "procedur": 21, "proceed": 17, "process": [0, 1, 2, 3, 5, 6, 8, 11, 13, 16, 17, 20, 21, 27, 28, 29, 30, 31, 32, 33, 34, 47, 51, 52, 53, 54, 55, 70, 71, 72, 73, 74, 75, 76, 77, 80, 81, 82, 83, 88, 89, 91, 95, 96, 97, 99, 100, 101, 107], "process_input": 88, "process_logits_including_draft": 88, "processor": [0, 5, 31, 46, 71, 85, 88, 96, 102], "processorbatch": 0, "processormap": 0, "prod": 83, "produc": [0, 1, 3, 7, 17, 41, 74, 76, 78, 80, 81, 83, 96], "product": [4, 5, 13, 17, 24, 30, 31, 52, 72, 80, 81, 82, 83, 89, 101], "profession": 32, "profil": [34, 35, 43, 44, 65, 78, 80, 83, 88, 92, 95, 96, 97], "profiling_verbos": [34, 71], "profit": [13, 74], "program": [20, 45, 48, 49, 51, 68, 70, 82, 89, 95], "progress": [1, 27, 71, 74, 83], "proj": [16, 18, 95], "project": [5, 10, 29, 66, 83, 84, 99, 106], "projector_hidden_act": 85, "prologu": [53, 54, 55], "promin": 13, "promis": [13, 20, 28, 31], "prompt": [0, 3, 6, 9, 13, 15, 21, 31, 33, 34, 35, 40, 41, 45, 47, 48, 49, 50, 51, 52, 53, 56, 57, 58, 59, 62, 63, 68, 71, 74, 76, 80, 81, 82, 84, 88, 89, 96, 101, 105], "prompt_adapter_request": [71, 96], "prompt_embedding_t": [84, 85, 88], "prompt_embedding_table_s": 85, "prompt_id": 52, "prompt_len": 101, "prompt_logprob": 71, "prompt_lookup": 96, "prompt_lookup_num_token": 6, "prompt_tabl": 88, "prompt_task": [85, 88], "prompt_token": [32, 89], "prompt_token_id": [41, 71], "prompt_vocab_s": [85, 88], "promptadapterrequest": 71, "promptinput": [71, 96], "promptlen": 0, "promptli": 31, "prompttableoffload": 0, "prompttuningconfig": 0, "prompttuningembed": 84, "prompttuningen": 1, "pronounc": [13, 30], "proof": 106, "propag": [9, 96], "proper": [2, 33, 74], "properli": [18, 30, 32, 80, 82], "properti": [3, 47, 71, 83, 85, 86, 88, 91], "proport": 5, "propos": [0, 27], "protect": [1, 51, 70], "protocol": [0, 31, 35, 47], "proud": [27, 30, 31], "prove": [13, 29], "provid": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 12, 13, 15, 16, 19, 20, 21, 22, 23, 26, 27, 29, 30, 31, 32, 33, 34, 35, 36, 41, 47, 52, 66, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 83, 88, 90, 91, 92, 94, 95, 96, 99, 100, 101], "proxy_dispatch_result_thread": 74, "prune": [7, 13, 83], "pseudo": [5, 83, 93], "pth": [18, 96], "ptq": [26, 78, 96], "ptr": 1, "ptr_idx": 18, "ptrdiff_t": 1, "ptune": 90, "ptuning_setup": 88, "ptuning_setup_fuyu": 88, "ptuning_setup_llava_next": 88, "ptuning_setup_phi3": 88, "ptuning_setup_pixtr": 88, "ptuningconfig": 0, "public": [0, 1, 26, 37], "publish": [21, 22, 25, 67, 74, 75, 89, 96], "pull": [19, 21, 32, 66, 89, 90, 96], "puneeshkhanna": 96, "purchas": 74, "pure": 88, "purpos": [5, 8, 29, 30, 31, 66, 76, 78, 80, 81], "pursu": [45, 48, 49, 51, 68, 89], "push": [29, 30, 36], "pushd": 95, "put": [1, 16, 27, 53, 54, 55, 68, 70, 72, 80], "pwd": [21, 66], "py": [3, 4, 5, 7, 10, 12, 13, 14, 15, 16, 17, 18, 20, 21, 27, 28, 29, 30, 53, 54, 58, 66, 68, 70, 73, 74, 75, 76, 77, 78, 83, 86, 88, 89, 91, 95, 96, 99, 100, 106, 107], "py3": 96, "py_executor_cr": 107, "pybind": 96, "pybind11_object": 71, "pybindmirror": 71, "pydant": [71, 96], "pydantic_cor": 71, "pyexecutor": [96, 106, 107], "pynvml": 96, "pypi": [66, 89, 96], "pytest": 90, "python": [1, 5, 6, 7, 10, 13, 15, 17, 19, 20, 21, 28, 29, 31, 33, 35, 41, 49, 50, 58, 65, 68, 70, 71, 73, 74, 75, 76, 77, 89, 90, 93, 96, 97, 99, 100, 106, 107], "python3": [10, 12, 14, 16, 21, 53, 54, 66, 68, 73, 74, 89, 95], "python_bind": 21, "python_e2": 88, "python_plugin": 96, "pythonpath": [21, 54, 55], "pytorch": [7, 13, 16, 19, 21, 28, 29, 30, 31, 32, 33, 35, 42, 46, 58, 65, 66, 68, 70, 71, 75, 83, 90, 96, 100, 101, 104, 105, 106, 107], "pytorch_backend_config": 35, "pytorch_extra_arg": 54, "pytorch_model": 95, "pytorch_model_registri": 106, "pytorchconfig": [71, 101], "pytorchmodelengin": [100, 106], "pzzzzz5142": 96, "q": [2, 5, 6, 10, 22, 27, 29, 33, 65, 74, 83, 95, 99, 101], "q_b_proj": 83, "q_dim": 83, "q_lora_rank": [83, 84], "q_proj": [18, 74, 99], "q_scale": [5, 83, 84, 85], "qa": 13, "qformat": [74, 87], "qgmma": 96, "qingquansong": 96, "qk_layernorm": [84, 85], "qk_nope_head_dim": [83, 84], "qk_norm": 84, "qk_rope_head_dim": [83, 84], "qkv": [7, 10, 16, 18, 65, 83, 95, 96, 101], "qkv_bia": [83, 96], "qkv_dim": 83, "qkv_proj": 99, "qo_indptr": 101, "qpi": 11, "qserv": 96, "quadrat": [5, 92], "qualifi": 90, "qualiti": [28, 30, 78, 81], "qualnam": [71, 83, 85, 87], "quant": [20, 71, 74, 83, 96, 104], "quant_algo": [16, 18, 20, 41, 71, 74, 78, 85], "quant_config": [20, 41, 71, 78, 85, 101], "quant_medusa_head": 87, "quant_mod": [20, 71, 84, 85, 88], "quantalgo": [41, 71, 78, 85, 87], "quantconfig": [20, 41, 71, 78, 85, 96, 101], "quanticonfig": 20, "quantiz": [5, 6, 11, 17, 18, 21, 22, 23, 27, 29, 33, 34, 45, 48, 65, 68, 69, 70, 71, 72, 75, 76, 79, 83, 84, 85, 88, 89, 94, 96, 98, 99, 101], "quantizaton": 74, "quantize_and_export": 87, "quantize_kwarg": 85, "quantize_lm_head": [87, 96], "quantized_valu": 5, "quantizedkernel": 17, "quantizetensorplugin": 17, "quantmod": [1, 5, 6, 65, 71, 83, 84, 85, 87, 88], "quantmodewrapp": [71, 83], "queri": [3, 6, 8, 13, 17, 22, 29, 31, 32, 35, 57, 65, 74, 83, 92, 101, 106], "query_dim": 84, "query_key_valu": 18, "query_length": 84, "query_pre_attn_scalar": 85, "question": [30, 56, 74, 92, 95], "queu": [0, 75, 80], "queue": [0, 71, 72, 90, 100], "quick": [5, 65, 72, 74, 76, 101], "quick_gelu": 83, "quicker": 77, "quickli": [20, 89], "quickstart": [70, 76], "quickstart_advanc": [28, 53], "quit": [7, 70], "quot": 90, "qweight": 18, "qwen": [18, 35, 44, 74, 83, 85, 93, 94, 96], "qwen1": [94, 96], "qwen2": [10, 35, 39, 44, 61, 74, 94, 96], "qwen2_5_vlforconditionalgener": 94, "qwen2_audio_7b_instruct": 90, "qwen2audio": 96, "qwen2forcausallm": 94, "qwen2forprocessrewardmodel": 94, "qwen2forrewardmodel": 94, "qwen2forsequenceclassif": 96, "qwen2vl": 96, "qwen2vlforconditionalgener": 94, "qwen3": 30, "qwenforcausallm": [18, 85], "qwenforcausallmgenerationsess": 88, "qwenvl": 96, "qwq": 94, "qychen": 10, "qzero": 18, "r": [1, 10, 35, 45, 47, 48, 49, 50, 51, 52, 56, 68, 76, 82, 83, 89, 95, 96], "r1": [30, 35, 59, 64, 75, 96], "r1_in_tensorrt": [27, 96], "race": 96, "radix": 106, "rais": [20, 52, 59, 71, 76, 95, 96], "rand": [33, 74, 83], "rand_data": 83, "rand_data_valid": 85, "random": [0, 6, 33, 35, 43, 44, 58, 71, 75, 83, 96], "random_se": [71, 85, 88], "randomdatasampl": 1, "randomdatavalid": 1, "randomli": [74, 75], "randomse": [1, 6, 96], "randomseedtyp": 0, "rang": [0, 6, 9, 13, 31, 32, 33, 52, 70, 73, 74, 81, 83, 85, 92, 93, 94, 95, 99], "rank": [0, 1, 2, 3, 4, 6, 10, 20, 21, 29, 30, 34, 70, 74, 83, 85, 88, 92, 95, 96], "rank0": 16, "rank1": 16, "rapid": [13, 75, 89], "rate": [0, 21, 27, 28, 29, 31, 33, 35, 43, 44, 74, 75, 76, 96], "rather": [5, 7, 13, 29, 30, 68, 72, 97], "ratio": [29, 30, 31], "ration": 31, "rational": 29, "raw": 35, "raw_audio": 88, "raw_imag": 88, "rdma": [2, 31], "re": [21, 26, 30, 32, 71, 72, 96, 101], "reach": [0, 5, 16, 31, 70, 74, 78, 82], "reachabl": 91, "react": 30, "read": [0, 2, 3, 5, 13, 15, 17, 18, 21, 27, 28, 30, 34, 56, 71, 74, 96, 97], "read_config_from_the_custom_training_checkpoint": 20, "readabl": 74, "reader": 83, "readi": [0, 32, 89, 97], "readm": [13, 35, 70, 76, 96], "real": [7, 12, 21, 27, 30, 33, 66, 76, 78, 80, 81, 83, 95], "realiti": 80, "realiz": [9, 13], "rearrang": 83, "reason": [0, 5, 6, 17, 20, 27, 28, 30, 32, 35, 64, 71, 74, 77, 80, 81, 83, 90, 95], "reasoning_pars": [35, 42, 71], "rebalanc": 30, "rebuild": [81, 83, 91, 95], "receiv": [0, 1, 2, 3, 4, 11, 13, 30, 31, 78, 83, 96], "recent": [1, 4, 5, 12, 23, 27, 91], "recept": 31, "recip": [27, 29, 35, 71, 93], "reclaim": 0, "recogn": [13, 27, 30, 31, 74, 99], "recommend": [2, 5, 6, 13, 15, 18, 19, 21, 23, 26, 29, 30, 31, 35, 52, 66, 71, 74, 79, 80, 82, 95, 96, 99, 101], "recompute_scale_factor": 83, "reconfigur": [3, 68], "reconstruct": [5, 83], "record": [1, 7, 21, 27, 28, 30, 71], "recored": 0, "recreat": 19, "recurr": 13, "recurrentgemma": [93, 94, 96], "recurrentgemmaforcausallm": 85, "recurs": [21, 32, 66, 70], "recv": [0, 17, 30, 83], "recvconnect": 0, "recvpollperiodm": 0, "recycl": [5, 106], "redesign": 96, "redirect": [7, 71], "redistribut": 30, "redraft": [65, 83, 85, 88, 96], "redrafter_draft_len_per_beam": 88, "redrafter_num_beam": 88, "redrafterforllamalm": 85, "redrafterforqwenlm": 85, "redraftermixin": 85, "reduc": [2, 3, 4, 5, 9, 11, 13, 17, 21, 22, 25, 27, 28, 29, 30, 31, 32, 34, 52, 57, 66, 70, 71, 72, 73, 74, 75, 76, 77, 80, 82, 83, 90, 92, 95, 96, 101, 103], "reduce_fus": [34, 74, 78, 81], "reduce_scatt": 83, "reduceoper": 83, "reducescatt": [34, 81, 96], "reduct": [11, 13, 27, 82, 83], "redund": [13, 27, 30], "refactor": [20, 21, 96], "refer": [0, 1, 2, 3, 5, 6, 7, 8, 10, 13, 17, 19, 20, 21, 30, 31, 32, 35, 37, 38, 39, 40, 41, 42, 43, 44, 45, 52, 60, 61, 62, 63, 66, 67, 70, 72, 74, 75, 76, 77, 78, 79, 81, 83, 89, 94, 96, 99, 101], "referenc": 78, "reference_wrapp": [0, 3], "refin": 96, "refit": [17, 34, 96], "refit_engin": 17, "reflect": [2, 80], "refresh": [21, 74], "regard": 83, "regardless": 95, "regex": [3, 71], "region": 73, "regist": [30, 36, 65, 95, 96, 99], "register_auto_model": 99, "register_network_output": 95, "registerdesc": 0, "registermemori": 0, "regress": [5, 6, 17], "regular": [0, 3, 5, 27, 71, 83], "reinforc": 79, "reject": [0, 28], "rel": [9, 22, 30, 80, 82, 83, 96], "rel_attn_t": 84, "relat": [2, 4, 8, 18, 65, 67, 72, 73, 83, 86, 92, 95, 96, 98, 99, 106], "relationship": 92, "relative_attent": [83, 84], "relative_attention_bia": 83, "relax": [5, 30], "relaxed_delta": [27, 28, 59, 71], "relaxed_topk": [27, 28, 59, 71], "releas": [1, 5, 6, 8, 20, 22, 25, 26, 30, 31, 65, 66, 72, 83, 85, 89, 92, 93, 94], "release_build": [32, 66], "release_run": [66, 89], "releasepag": 1, "releasest": 0, "relev": [6, 66, 91, 106], "reli": [2, 5, 7, 20, 30, 31, 70, 73, 93], "reload": [3, 30], "relu": [16, 17, 83, 95], "remain": [0, 7, 9, 13, 14, 27, 30, 66, 75, 76, 78, 80, 81, 83, 90, 92, 96], "remaind": 78, "remark": [27, 28], "rememb": 30, "remind": [5, 101], "remot": [30, 33, 71], "remotenam": 0, "remov": [0, 1, 5, 6, 7, 8, 17, 18, 21, 28, 31, 34, 35, 66, 71, 72, 78, 83, 90, 92, 96, 99], "remove_const_t": 1, "remove_cv_t": 0, "remove_duplicated_kv_head": 85, "remove_input_pad": [5, 10, 34, 83, 84, 88], "remove_pointer_t": 1, "remove_reference_t": 1, "remove_sequ": 106, "renam": 96, "reopen": 91, "reorder": [83, 84], "reorder_kv_cache_for_beam_search": 88, "rep": 73, "repeat": [0, 5, 28, 29, 57, 71, 83], "repeat_interleav": 83, "repeatedli": 13, "repetit": [0, 6, 52, 71, 83], "repetition_penalti": [6, 71, 88, 96], "repetitionpenalti": [0, 1, 6], "replac": [1, 4, 7, 17, 18, 20, 21, 29, 32, 74, 76, 78, 82, 83, 92, 99], "replace_add_with_sub": 7, "replace_all_uses_with": [7, 83], "replace_input_with": 7, "replace_output_uses_with": 7, "replace_outputs_uses_with": 7, "replai": 30, "replic": [0, 3, 27, 30, 83], "replit": [93, 94, 96], "repo": [20, 72, 76, 95], "repo_id": 56, "report": [8, 28, 29, 30, 32, 33, 73, 74, 75, 92, 96], "report_json": 33, "report_load_statist": 30, "reportpluginerror": 95, "repositori": [13, 19, 21, 36, 66, 70, 89, 91], "repres": [0, 1, 8, 12, 13, 21, 22, 26, 27, 30, 47, 56, 71, 74, 80, 83, 88, 107], "represent": [7, 17], "reproduc": [33, 65, 74, 96], "req": [21, 74, 75, 76, 78, 80, 81], "req_id": 52, "req_stat": 107, "reqbeamwidth": 1, "reqid": 0, "reqpromptlength": 1, "request": [0, 2, 5, 6, 9, 10, 17, 21, 23, 25, 28, 29, 30, 31, 33, 34, 35, 43, 44, 54, 71, 72, 73, 74, 75, 76, 78, 80, 81, 82, 83, 89, 90, 92, 96, 100, 101, 106, 107], "request_id": [41, 71, 101], "request_json": 33, "request_perf_metr": 71, "request_stats_max_iter": 71, "request_timeout": 35, "request_typ": 71, "request_type_context_and_gener": 0, "request_type_context_onli": 0, "request_type_generation_onli": 0, "requesterror": 71, "requestid": [0, 2, 3], "requestidtyp": 0, "requestlist": 107, "requestoutput": [41, 71, 96], "requestperfmetr": [0, 71], "requestschedul": 107, "requeststag": 0, "requeststat": 0, "requeststatsmaxiter": 0, "requeststatsperit": 0, "requeststatsperiter": 0, "requeststatsvec": 0, "requesttoken": 3, "requesttyp": [0, 1, 71], "requesttypesdevic": 1, "requestvector": 1, "requir": [0, 2, 5, 6, 9, 10, 13, 17, 18, 20, 21, 22, 26, 27, 29, 30, 31, 33, 34, 35, 47, 56, 66, 68, 70, 71, 74, 75, 76, 77, 78, 81, 83, 84, 89, 90, 91, 92, 94, 95, 96, 106], "require_ln_f": 85, "requiresattentionmask": 1, "rerun": 81, "rescale_output_factor": 84, "research": [5, 28, 30, 37, 45, 48, 49, 51, 68, 89, 93], "reserv": [0, 1, 35, 71, 82, 88, 92, 107], "reserved_block": 107, "reset": [0, 1, 6, 71, 74, 88], "resetspeculativedecodingmodul": 1, "reshap": [1, 83], "reshapebuff": 1, "reshapecacheindirectionbuff": 1, "reshapespeculativedecodingbuff": 1, "resid": [10, 30], "residu": [83, 95], "residual_connect": 84, "residual_mlp": 85, "residual_multipli": 85, "residual_rms_norm": 83, "residual_rms_norm_out_quant_fp8": 83, "residual_rms_norm_out_quant_nvfp4": 83, "residual_rms_norm_quant_fp8": 83, "residual_rms_norm_quant_nvfp4": 83, "residual_rms_prepost_norm": 83, "residualadd": [34, 81, 96], "resiz": 1, "resolv": [31, 35, 39, 61, 95], "resourc": [0, 2, 5, 20, 27, 29, 31, 90, 97, 100, 106, 107], "resource_manag": 71, "respect": [4, 31, 32, 41, 82, 83, 88, 91, 92, 93, 99, 107], "respond": 97, "respons": [0, 2, 8, 31, 35, 41, 58, 59, 60, 61, 62, 63, 71, 74, 83, 97, 100, 103], "responsewithid": 0, "rest": [1, 5, 31, 78], "restart": 0, "restrict": [0, 2, 3, 6, 66, 71, 83, 90, 105], "result": [0, 1, 4, 5, 11, 13, 17, 22, 23, 24, 26, 28, 29, 30, 31, 33, 34, 41, 65, 66, 71, 74, 77, 78, 79, 80, 81, 83, 84, 90, 96, 99, 101, 105, 107], "retail": 74, "retain": [22, 24, 28], "retent": [0, 71], "retentionprior": 0, "retentionpriorityanddur": 0, "rethink": 13, "retri": 90, "retriev": [1, 18, 31, 71, 75, 83], "return": [0, 1, 3, 7, 10, 13, 15, 17, 18, 20, 31, 32, 41, 52, 58, 71, 74, 80, 83, 84, 85, 88, 92, 95, 96, 106, 107], "return_all_generated_token": 88, "return_context_logit": 71, "return_dict": 88, "return_encoder_output": [71, 88], "return_generation_logit": 71, "return_perf_metr": 71, "returnallgeneratedtoken": [0, 3], "returncontextlogit": 0, "returnencoderoutput": 0, "returngenerationlogit": 0, "returnlogprob": 0, "returnperfmetr": 0, "reus": [0, 2, 3, 8, 28, 34, 65, 69, 71, 83, 88, 90, 91, 92, 96, 99, 102, 106], "reusabl": [8, 9, 30], "reusedblock": 0, "reusedblocksperrequest": 0, "reveal": [27, 29], "revers": 83, "revert": 83, "review": [30, 74], "revis": 71, "revolution": 72, "rewind": [28, 96], "rewrit": [65, 83, 96, 99], "rewritepatternmanag": 7, "rewrt": 95, "rf": 95, "rg_lru": 83, "rgc": 74, "rh": [0, 1], "rich": 16, "right": [31, 72, 78, 83, 95], "rigor": 74, "risk": [2, 17, 78, 82], "rm": [66, 83, 94, 95, 99], "rms_norm": [27, 83, 99], "rmsnorm": [10, 27, 83, 84, 85, 96, 99], "rnn": [34, 96], "rnn_conv_dim_s": 88, "rnn_head_siz": 88, "rnn_hidden_s": 88, "rnn_state": 85, "rnnconfig": 1, "rnnconvdims": 1, "rnnheadsiz": 1, "rnnhiddens": 1, "ro": [21, 91], "roberta": [94, 96], "robertaforquestionansw": 85, "robertaforsequenceclassif": 85, "robertamodel": 85, "robin": 31, "robot": 58, "robust": [27, 30, 96], "rock": 83, "roi": 52, "role": [17, 31, 32, 35, 38, 39, 47, 60, 61, 80, 89], "roll": 65, "rooflin": 29, "root": [16, 21, 36, 66, 68, 70, 71, 76, 83, 89], "root_lay": 7, "rootless": 91, "rope": [27, 29, 83, 88, 96, 101], "rope_gpt_neox": [5, 83, 85], "rope_gptj": [5, 83], "rope_local_base_freq": 85, "rope_scaling_config": 83, "rope_scaling_long_factor": 84, "rope_scaling_long_mscal": 84, "rope_scaling_short_factor": 84, "rope_scaling_short_mscal": 84, "ropeembeddingutil": 83, "rotari": [0, 27, 83, 88, 99, 101], "rotary_bas": 85, "rotary_cos_sin": 83, "rotary_dim": 85, "rotary_embed": 99, "rotary_embedding_bas": [83, 84], "rotary_embedding_base_loc": 84, "rotary_embedding_beta_fast": 84, "rotary_embedding_beta_slow": 84, "rotary_embedding_dim": [5, 83, 85], "rotary_embedding_long_m_scal": 83, "rotary_embedding_max_posit": 83, "rotary_embedding_mscal": 84, "rotary_embedding_mscale_all_dim": 84, "rotary_embedding_origin_max_posit": 84, "rotary_embedding_original_max_posit": 83, "rotary_embedding_percentag": 84, "rotary_embedding_sc": 84, "rotary_embedding_scal": 83, "rotary_embedding_scale_typ": 83, "rotary_embedding_short_m_scal": 83, "rotary_inv_freq": [83, 84], "rotary_inv_freq_loc": 84, "rotary_pct": 85, "rotary_sc": [84, 85], "rotaryembed": 99, "rotaryembeddingdim": [0, 1], "rotaryscalingtyp": 83, "rotate_every_two": 83, "rotate_half": 83, "round": [31, 71, 83, 97], "round_robin": 31, "rout": [2, 29, 30, 31], "router": [4, 10, 29, 30, 31, 96], "router_gemm": 27, "routin": [7, 30], "routingkernel": 27, "row": [10, 80, 83, 93, 96], "rowlinear": [10, 84], "rowwis": 71, "rr": 96, "rslora": 96, "rst": 3, "rtx": 96, "rubric": 83, "rule": [5, 77, 95], "run": [0, 1, 2, 3, 5, 6, 9, 12, 13, 15, 16, 17, 22, 26, 27, 29, 31, 32, 33, 34, 35, 36, 37, 46, 49, 50, 57, 58, 65, 66, 68, 70, 71, 72, 77, 78, 80, 81, 82, 83, 88, 90, 91, 92, 93, 95, 96, 97, 99, 100, 101, 103, 106], "run_all_demonstr": 58, "run_dtm_ngram": 13, "run_eagle3": 59, "run_mtp": 59, "run_ngram": 59, "runner": [0, 16, 88], "runningleon": 96, "runpod": 36, "runtim": [0, 3, 5, 13, 14, 19, 27, 28, 30, 31, 33, 34, 35, 46, 52, 56, 65, 70, 71, 72, 73, 74, 76, 79, 80, 83, 84, 85, 89, 95, 96, 99, 101, 107], "runtime_config": 41, "runtime_default": 85, "runtime_error": 1, "runtime_rank": 88, "runtimedefault": [0, 85], "runtimedefaultsin": 85, "runtimeerror": [70, 71, 95], "runtimetensor": 88, "s0": 5, "s1": 5, "s2": 5, "sacrif": 27, "sad": 88, "saeyoonoh": 96, "safe": [1, 7, 29, 81], "safer": 83, "safetensor": [16, 18, 95, 96], "sage_attn": 83, "sage_attn_k_block_s": 83, "sage_attn_k_quant_s": 83, "sage_attn_q_block_s": 83, "sage_attn_q_quant_s": 83, "sage_attn_v_block_s": 83, "sage_attn_v_quant_s": 83, "sageattent": 83, "sai": [30, 73, 76, 80], "said": 78, "sake": 80, "sale": [52, 74], "same": [0, 1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 13, 14, 17, 20, 23, 28, 29, 30, 31, 33, 34, 53, 54, 55, 58, 66, 70, 71, 74, 75, 78, 81, 82, 83, 84, 86, 88, 90, 92, 96], "sampl": [0, 1, 3, 5, 17, 19, 21, 27, 28, 33, 45, 46, 48, 49, 50, 51, 52, 56, 65, 68, 69, 71, 73, 74, 75, 83, 84, 88, 89, 96, 98, 103], "sample_proj_bia": 84, "sample_weight_strip": 96, "samplemod": 83, "sampler": [71, 102], "sampling_config": 88, "sampling_param": [41, 45, 47, 48, 49, 50, 51, 52, 57, 58, 68, 71, 76, 82, 89, 96, 105], "samplingconfig": [0, 3, 6, 41, 88, 96], "samplingparam": [41, 45, 47, 48, 49, 50, 51, 52, 57, 58, 59, 68, 71, 76, 82, 89, 96, 105], "saniti": [68, 77, 78, 81], "santacod": [93, 94], "satfinit": 93, "satisfi": [6, 18, 30, 31, 96], "satur": 30, "save": [5, 9, 13, 20, 21, 28, 29, 30, 34, 36, 73, 74, 78, 81, 82, 92, 96], "save_checkpoint": [20, 85], "save_config": [20, 85], "saw": [78, 89], "sbatch": [17, 53, 54, 55, 97], "sbsa": [96, 98], "scaffold": [96, 99], "scalabl": 30, "scalar": [6, 11, 83], "scalartyp": 96, "scale": [0, 6, 10, 18, 29, 31, 34, 71, 78, 83, 84, 93, 96], "scale_d0": 83, "scale_d1": 83, "scale_factor": 83, "scale_output": 83, "scale_qk": 84, "scale_typ": 83, "scalia": [45, 68, 89], "scaling_factor": 83, "scaling_long_factor": 83, "scaling_short_factor": 83, "scalingvecpoint": 1, "scanreducetempstorag": 1, "scanreducetempstoragebyt": 1, "scantempstorag": 1, "scantempstoragebyt": 1, "scarc": 90, "scatter": [7, 30, 83], "scatter_nd": 83, "scenario": [5, 11, 13, 16, 21, 24, 26, 27, 29, 30, 31, 33, 34, 37, 74, 75, 76, 78, 80, 81, 96], "scfg": 88, "schedul": [0, 2, 3, 9, 10, 21, 28, 29, 30, 33, 34, 35, 71, 74, 76, 81, 92, 96, 98, 102], "schedule_request": 107, "scheduled_request": 107, "scheduler_config": [71, 82], "scheduler_polici": 33, "schedulerconfig": [0, 71, 82, 96], "schedulerpolici": 96, "schema": [0, 3, 47, 71, 74], "scheme": 0, "scicod": 27, "scienc": [45, 48, 49, 51, 68, 89], "scope": [19, 28, 96], "score": [6, 29], "scout": 94, "scratch": [30, 74, 76, 77, 81, 91], "script": [10, 12, 15, 17, 20, 21, 30, 31, 33, 36, 53, 54, 55, 66, 70, 73, 74, 75, 76, 86, 90, 91, 93, 95, 96, 99, 104], "sd3": 84, "sd35adalayernormzerox": 84, "sd3patchemb": 84, "sd3transformer2dmodel": 85, "sd3transformer2dmodelconfig": 85, "sdxl": 96, "seamless": 96, "seamlessli": 70, "search": [0, 1, 3, 6, 13, 19, 25, 33, 34, 35, 41, 65, 71, 78, 80, 83, 90, 96, 100], "seashor": [35, 39, 61], "seat": [45, 68, 89], "sec": [21, 23, 31, 74, 75, 76, 78, 80, 81], "second": [1, 3, 6, 9, 10, 13, 21, 22, 24, 25, 27, 30, 31, 32, 71, 80, 83], "secondari": [0, 8, 71, 92], "secondary_offload_min_prior": 71, "secondaryoffloadminprior": 0, "secondli": 80, "section": [3, 6, 17, 18, 20, 21, 28, 29, 30, 35, 66, 72, 74, 76, 78, 79, 80, 81, 83, 89, 90, 91, 94, 96, 101], "section_s": 83, "secur": [47, 96], "securityprotocol": 47, "see": [0, 1, 5, 6, 8, 13, 17, 18, 21, 22, 24, 25, 26, 28, 29, 30, 33, 35, 36, 37, 39, 45, 61, 66, 67, 68, 74, 75, 76, 78, 80, 81, 82, 83, 84, 85, 89, 90, 91, 92, 93, 95, 96, 106], "seed": [0, 6, 33, 35, 43, 44, 71, 87, 96], "seem": [9, 56, 74, 77], "seen": [13, 21, 30, 74], "segment": 96, "select": [0, 4, 6, 19, 26, 27, 29, 31, 34, 65, 74, 81, 83, 88, 90, 92, 100, 107], "selectcontextid": 0, "selectgenidx": 0, "selective_scan": 83, "self": [0, 5, 7, 15, 17, 18, 52, 71, 74, 83, 85, 88, 95, 99, 106, 107], "self_attent": 18, "self_attention_mask": 84, "self_attention_packed_mask": 84, "self_attn": [18, 99], "selfidx": 0, "sell": 74, "semicolon": 66, "senat": [45, 68, 89], "send": [0, 2, 17, 27, 30, 31, 35, 76, 77, 83, 89, 96], "sens": 78, "sensit": [27, 30, 78], "sent": [0, 13, 29, 30, 31, 35, 71], "sentenc": [0, 6, 52, 71, 89], "separ": [11, 13, 30, 31, 34, 66, 71, 74, 83, 88, 90, 97, 101], "separate_match_rewrit": 7, "seq": [1, 5, 74, 83], "seq_idx": 88, "seq_len": [75, 83, 84, 101], "seq_length": 83, "seq_lens_cuda": 101, "seqlen": [0, 83], "seqslot": 1, "sequenc": [0, 1, 3, 5, 6, 7, 8, 9, 13, 17, 21, 22, 23, 24, 25, 27, 28, 29, 30, 31, 33, 52, 58, 71, 72, 74, 75, 76, 79, 82, 83, 84, 88, 92, 96, 97, 101, 106], "sequence_length": [83, 84, 88, 95], "sequence_length_buff": 88, "sequence_limit_length": 88, "sequenceindex": [0, 3], "sequencelengthscba": 1, "sequencelimitlength": 1, "sequenti": [0, 2, 13, 28, 92], "seri": 96, "serial": [33, 34, 83, 85, 88], "serializ": 71, "serialize_engin": 88, "serializeds": 0, "serializedst": 0, "serv": [0, 2, 3, 5, 8, 17, 19, 25, 26, 30, 32, 38, 39, 40, 42, 43, 44, 46, 60, 61, 62, 63, 65, 71, 81, 96, 97, 100, 101, 102, 103], "server": [0, 9, 13, 17, 19, 23, 30, 36, 38, 39, 40, 42, 43, 44, 60, 61, 62, 63, 65, 96, 97], "server_rol": 35, "server_start_timeout": 35, "servic": [19, 31, 52, 65, 91], "session": [5, 70, 74, 88], "set": [0, 1, 2, 3, 4, 5, 6, 7, 8, 11, 12, 13, 14, 16, 18, 19, 20, 21, 27, 29, 30, 31, 32, 33, 34, 35, 41, 47, 53, 54, 55, 66, 68, 71, 72, 73, 75, 76, 78, 80, 81, 82, 83, 84, 85, 86, 88, 89, 90, 91, 92, 95, 96, 97, 103, 107], "set_attn_processor": 85, "set_default_max_input_len": 71, "set_from_opt": 1, "set_if_not_exist": 85, "set_input_shap": 88, "set_rank": 85, "set_rel_attn_t": 84, "set_runtime_knobs_from_build_config": 71, "set_shap": 88, "setadditionalmodeloutput": [0, 3], "setallottedtimem": 0, "setbackend": 0, "setbackendtyp": 0, "setbadword": 0, "setbatchingtyp": 0, "setbeamsearchdiversityr": 0, "setbeamwidth": 0, "setbeamwidtharrai": 0, "setbitto": 0, "setcachest": 0, "setcachetransceiverconfig": [0, 2], "setclientid": 0, "setcommst": 0, "setcommunicationmod": 0, "setcommunicationtyp": 0, "setcontextfmha": 1, "setcontextphaseparam": 0, "setcopyonpartialreus": 0, "setcrossattentionmask": 0, "setcrosskvcachefract": 0, "setcudagraphcaches": 0, "setcudagraphmod": 0, "setdatatyp": 1, "setdebugconfig": 0, "setdebuginputtensor": 0, "setdebugoutputtensor": 0, "setdebugtensornam": 0, "setdebugtensorsmaxiter": 0, "setdecodingconfig": 0, "setdecodingmod": 0, "setdeviceid": 0, "seteagleconfig": 0, "setearlystop": 0, "setembeddingbia": 0, "setenableblockreus": 0, "setenablechunkedcontext": 0, "setenablecontextfmhafp32acc": 0, "setenablepartialreus": 0, "setenabletrtoverlap": 0, "setencodedvocab": 0, "setencoderhiddens": 1, "setencoderinputfeatur": 0, "setencoderinputtokenid": 0, "setencoderoutputlength": 0, "setendid": 0, "seteventbuffermaxs": 0, "setexecutionconfig": 1, "setextendedruntimeperfknobconfig": 0, "setexternaldrafttokensconfig": 0, "setfreegpumemoryfract": 0, "setfrequencypenalti": 0, "setfrom": 0, "setfrominput": 1, "setgathergenerationlogit": 0, "setgemmallreducedtyp": 1, "setgenerationstep": 1, "setgpuweightsperc": [0, 14], "setguideddecodingconfig": 0, "setguideddecodingparam": 0, "sethostcaches": 0, "setinittozero": 1, "setisorchestr": 0, "setiterstatsmaxiter": 0, "setkvcacheconfig": 0, "setkvcacheretentionconfig": 0, "setkvcachetyp": 1, "setlanguageadapteruid": 0, "setlayertyp": 1, "setlengthpenalti": 0, "setlevel": 1, "setlogitsdtyp": 1, "setlogitspostprocessor": 0, "setlogitspostprocessorconfig": 0, "setlogitspostprocessornam": 0, "setlookaheadconfig": 0, "setlookaheaddecodingconfig": 0, "setloraconfig": 0, "setloramodul": 1, "setmanagedweightsmap": 1, "setmanageweightstyp": 1, "setmaxattentionwindowvec": 0, "setmaxbatchs": [0, 1], "setmaxbeamwidth": [0, 1], "setmaxdraftpathlen": 1, "setmaxdrafttoken": 1, "setmaxencoderlen": 1, "setmaxinputlen": 1, "setmaxlorarank": 1, "setmaxnumpath": 1, "setmaxnumtoken": [0, 1], "setmaxpagesperblock": 1, "setmaxpositionembed": 1, "setmaxpromptembeddingtables": 1, "setmaxqueues": 0, "setmaxseqidlemicrosecond": 0, "setmaxsequencelen": 1, "setmaxtoken": 0, "setmaxtokensinbuff": 0, "setmedusachoic": 0, "setmem": 1, "setmemorytyp": 1, "setminp": 0, "setmintoken": 0, "setmlphiddens": 1, "setmodelnam": 1, "setmodelvari": 1, "setmropeconfig": 0, "setmultiblockmod": 0, "setmultimodalembed": 0, "setmultimodalinput": 0, "setnbcrosskvhead": 1, "setnbkvhead": 1, "setnorepeatngrams": 0, "setnormalizelogprob": 0, "setnumcopystream": 1, "setnumdecodingenginetoken": 1, "setnumkvheadspercrosslay": 1, "setnumkvheadsperlay": 1, "setnumlanguag": 1, "setnumnod": 0, "setnumreturnsequ": 0, "setonboardblock": 0, "setorchestratorconfig": 0, "setorchleadercomm": 0, "setoutputconfig": 0, "setpadid": 0, "setpagedcontextfmha": 1, "setpagewidth": 1, "setparallelconfig": 0, "setparticipantid": 0, "setpath": 1, "setpeftcacheconfig": 0, "setpositionid": 0, "setppreducescatt": 1, "setpresencepenalti": 0, "setprior": 0, "setprocessorbatch": 0, "setprocessormap": 0, "setprompttableoffload": 0, "setprompttuningconfig": 0, "setquantmod": 1, "setrecvpollperiodm": 0, "setrepetitionpenalti": 0, "setrepl": [0, 3], "setrequeststatsmaxiter": 0, "setrequesttyp": 0, "setreturnallgeneratedtoken": 0, "setrnnconfig": 1, "setrotaryembeddingdim": 1, "setsamplingconfig": 0, "setschedulerconfig": 0, "setse": 0, "setsecondaryoffloadminprior": 0, "setsinktokenlength": 0, "setsizeperhead": 1, "setskipcrossattnblock": [0, 1], "setslotsperpag": 1, "setspawnprocess": 0, "setspecdecconfig": 0, "setspeculativedecodingmod": 1, "setspeculativedecodingmodul": 1, "setstoptokenid": 0, "setstopword": 0, "setstream": 0, "settemperatur": 0, "setter": [0, 6], "settokenizerstr": 0, "settokensperblock": 1, "settopk": 0, "settopp": 0, "settoppdecai": 0, "settoppmin": 0, "settoppresetid": 0, "settotalnumpag": 1, "setup": [1, 5, 31, 34, 47, 53, 54, 55, 68, 70, 77, 78, 88, 89, 92, 96], "setup_embedding_parallel_mod": 71, "setup_fake_prompt": 88, "setup_fake_prompts_qwen2vl": 88, "setup_fake_prompts_vila": 88, "setup_input": 88, "setupbuff": 1, "setupcacheindirect": 1, "setupcacheindirectionbuff": 1, "setupspeculativedecod": 1, "setupspeculativedecodingbuff": 1, "setuptool": 68, "setusecrossattent": 1, "setusegpudirectstorag": 0, "setusemrop": 1, "setusepositionembed": 1, "setuseshapeinfer": 1, "setusetokentypeembed": 1, "setuseuvm": 0, "setworkerexecutablepath": 0, "setzero": [0, 1], "sever": [0, 1, 5, 7, 13, 16, 30, 31, 32, 41, 78, 79, 80, 81, 83, 92, 95, 101], "sft": 56, "sglang": [30, 103], "sh": [17, 32, 36, 91, 96, 104], "shah": 96, "shall": [20, 92], "shape": [0, 1, 5, 7, 10, 16, 17, 27, 29, 71, 81, 83, 85, 88, 92, 93, 95, 96, 101, 106], "shape_cast_dtyp": 83, "shapeequ": 1, "shard": [18, 27, 33, 65, 74, 79, 83, 84, 90], "shard_map": 18, "sharding_along_vocab": 71, "sharding_dim": [83, 84], "share": [1, 2, 3, 5, 7, 8, 9, 10, 13, 20, 21, 26, 27, 28, 29, 30, 31, 32, 34, 66, 77, 78, 83, 84, 96], "share_embed": 96, "share_weight": 84, "shared_embedding_t": 96, "shared_expert_output": 83, "shared_fc1": 29, "shared_fc2": 29, "shared_ptr": [0, 1], "sharedconstptr": 1, "sharedptr": 1, "shelf": 96, "shell": [67, 89, 90, 91, 97], "sherlock113": 96, "shift": [11, 28, 30], "ship": 20, "shm": [30, 95], "short": [5, 30, 58, 74, 78, 80], "short_factor": 83, "short_mscal": [83, 84], "shorter": [5, 52, 75], "shot": 96, "should": [0, 1, 3, 7, 9, 10, 11, 20, 21, 29, 30, 33, 41, 45, 47, 53, 54, 55, 56, 57, 66, 68, 71, 74, 75, 76, 77, 81, 82, 83, 84, 86, 88, 89, 90, 92, 96, 99, 101, 106, 107], "should_stop": 88, "shouldus": 5, "show": [3, 17, 23, 27, 28, 29, 30, 31, 35, 45, 75, 76, 80, 81, 89, 90, 92, 94, 98], "showcas": [46, 78, 81, 89], "shown": [11, 24, 28, 30, 31, 35, 66, 74, 76, 78, 80, 81, 83], "shrunk": 83, "shuffl": 83, "shutdown": [0, 70, 71], "si": 5, "sibl": 17, "side": [3, 30, 83], "side_stream_id": 83, "sidestreamidtyp": 83, "sigh": 56, "sigmoid": [17, 83], "signal": 0, "signatur": [7, 83], "signifi": 80, "signific": [2, 3, 5, 8, 24, 28, 29, 30, 56, 77, 78, 80, 81], "significantli": [26, 27, 28, 29, 30, 31, 76, 77, 78, 80, 81, 92, 101, 103], "silicon": 29, "silu": [17, 83, 84], "similar": [0, 5, 6, 7, 13, 21, 22, 24, 28, 30, 41, 73, 74, 82, 83, 100, 107], "similarli": 13, "simpl": [7, 8, 13, 17, 30, 32, 45, 66, 70, 72, 75, 89, 98], "simpler": [13, 30], "simpleschedul": 107, "simplest": [67, 83], "simpli": [5, 13, 70, 72, 74, 75, 80, 89, 95, 99], "simplic": 20, "simplifi": [5, 20, 70, 74, 80, 83, 96], "simultan": [13, 80], "sin": [0, 83, 84], "sinc": [0, 1, 4, 5, 7, 9, 13, 14, 20, 21, 28, 29, 30, 33, 36, 41, 52, 66, 71, 74, 76, 77, 78, 80, 81, 83, 85, 92, 100, 106, 107], "sincer": 29, "sinco": 84, "singl": [0, 1, 2, 3, 4, 5, 6, 8, 13, 15, 17, 20, 21, 24, 25, 27, 28, 29, 30, 31, 32, 34, 35, 39, 61, 70, 71, 73, 74, 78, 81, 83, 85, 89, 92, 93, 96, 97, 99, 100, 101, 106], "singleton": [7, 83], "sink": [0, 1, 5, 71, 88], "sink_token_len": 88, "sink_token_length": [5, 71, 88], "sinktokenlength": [0, 1], "sinusoid": 84, "sit": [20, 56], "situaiton": 75, "situat": [13, 56, 65, 76, 80], "six": 28, "size": [0, 1, 2, 5, 6, 8, 9, 10, 11, 13, 14, 21, 23, 24, 26, 27, 28, 29, 30, 33, 34, 35, 41, 53, 54, 55, 65, 71, 73, 74, 75, 76, 77, 78, 79, 81, 83, 84, 85, 88, 95, 96, 97, 101, 107], "size_t": [0, 1], "size_typ": [0, 1], "sizeof": 1, "sizeperhead": [0, 1], "sizetype32": [0, 1], "sizetype64": [0, 1], "skip": [0, 1, 7, 18, 21, 37, 66, 71, 83, 90, 107], "skip_attn": [83, 84], "skip_cross_attn_block": [85, 88], "skip_cross_kv": [84, 88], "skip_encod": 88, "skip_special_token": [71, 96], "skip_tokenizer_init": [41, 71], "skipcrossattnblock": [0, 1], "sku": [76, 78, 80, 81], "skywork": [93, 94, 96], "sleep": 37, "slice": [1, 4, 18, 83, 96], "slice_shap": 18, "sliceinputtyp": 83, "slicen": 1, "slide": [0, 8, 65, 82, 83, 88, 96, 102], "slider": [21, 27, 74], "sliding_window": 85, "sliding_window_caus": 83, "sliding_window_pattern": 85, "slight": [21, 28, 29, 78, 80, 81], "slightli": [0, 10, 11, 35, 78, 81], "slope": [5, 83], "slot": [0, 1, 30, 96], "slot_map": [83, 85], "slotid": 30, "slotidx": 1, "slotsperpag": 1, "slow": [3, 9, 71, 72, 77], "slower": [8, 20, 29, 77], "slowest": 5, "slurm": [17, 30, 68, 70, 95, 96], "slurm_job_nodelist": 97, "slurm_tasks_per_nod": 97, "sm": [94, 96], "sm120": 96, "sm80": [94, 96], "sm86": [94, 96], "sm89": [94, 96], "sm90": [94, 96], "small": [5, 9, 11, 13, 17, 26, 27, 28, 29, 30, 52, 76, 78, 80, 81, 83, 92, 95, 96], "smaller": [1, 13, 21, 28, 34, 73, 74, 77, 80, 81, 82, 83, 92, 96], "smallest": [0, 1, 8, 83], "smart": [31, 83], "smaug": [94, 96], "smi": [21, 27, 32, 74, 92], "smile": 56, "smith": [45, 48, 49, 50, 51, 68, 89], "smooth": [20, 71, 96], "smoother": 21, "smoothquant": [7, 26, 65, 96], "smoothquant_v": 71, "snapshot": 74, "snapshot_download": 56, "snip": 74, "snippet": [74, 96, 107], "snshrivas10": 56, "so": [0, 3, 5, 7, 10, 13, 19, 20, 21, 27, 28, 29, 30, 36, 41, 66, 71, 74, 77, 78, 80, 81, 82, 83, 84, 85, 90, 92, 94, 96, 99, 106], "socketst": 0, "softmax": [5, 17, 28, 29, 83, 101], "softplu": 83, "softwar": [3, 5, 17, 29, 30, 65, 72, 96], "sol": 31, "solid": 79, "solut": [19, 30, 70, 95, 100], "some": [0, 2, 3, 4, 5, 6, 7, 9, 13, 14, 16, 17, 20, 21, 27, 28, 29, 30, 31, 34, 35, 37, 52, 56, 68, 70, 71, 72, 75, 78, 79, 81, 82, 83, 86, 89, 90, 91, 92, 95, 96, 99, 100, 107], "some_uri": 91, "someth": [17, 41], "sometim": [30, 31, 74, 90], "song": 74, "soon": [0, 22, 23, 24, 25, 26, 30, 41], "sora": [35, 39, 61], "sort": [0, 1, 3, 6, 83], "sota": 96, "sourc": [12, 15, 16, 18, 20, 21, 22, 25, 27, 29, 30, 33, 34, 35, 38, 39, 40, 42, 43, 44, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 65, 67, 71, 72, 83, 84, 85, 86, 87, 88, 89, 91, 96], "source_dir": 91, "source_root": [53, 54, 55], "sourcetaskvalu": 1, "soyer": [15, 17, 95], "space": [10, 30, 31, 66, 71, 80, 92, 97, 106], "spaces_between_special_token": [71, 96], "span": [20, 27, 28, 30, 31], "spars": [13, 29, 83, 96], "sparse_fc1": 29, "sparse_fc2": 29, "sparsiti": [30, 34], "spatial_norm_dim": 84, "spawn": [51, 70, 76, 95], "spawnprocess": [0, 2], "spec": [30, 34], "spec_config": 59, "spec_dec_mod": 71, "spec_decode_algo": 28, "spec_decode_nextn": 28, "spec_decoding_generation_length": [83, 84, 85], "spec_decoding_is_generation_length_vari": [83, 84, 85], "spec_decoding_max_generation_length": [83, 84], "spec_decoding_packed_mask": [83, 84, 85], "spec_decoding_param": [84, 85], "spec_decoding_position_offset": [83, 84, 85], "spec_decoding_us": [83, 84], "specdec": 0, "specdecconfig": 0, "specdecfastlogitsinfo": 0, "specdecodinggenerationlength": 1, "specdecodinggenerationlengthshost": 1, "specdecodingpackedmask": 1, "specdecodingparam": 84, "specdecodingpositionoffset": 1, "specdecodingstat": 0, "special": [2, 5, 10, 17, 18, 22, 28, 34, 71, 96], "specif": [0, 1, 4, 6, 7, 8, 10, 11, 12, 13, 16, 20, 23, 26, 27, 29, 30, 31, 32, 33, 35, 52, 58, 66, 68, 70, 74, 77, 78, 81, 83, 89, 90, 96, 99, 100], "specifi": [0, 1, 3, 5, 6, 7, 8, 10, 13, 18, 20, 21, 30, 33, 34, 35, 41, 47, 52, 56, 66, 70, 71, 73, 74, 75, 77, 78, 80, 82, 83, 85, 86, 88, 89, 90, 92, 95, 96, 97, 101], "specul": [0, 1, 3, 27, 30, 31, 32, 46, 65, 69, 70, 71, 74, 76, 83, 85, 96, 105], "speculative_config": [21, 27, 28, 59, 71], "speculative_decod": 96, "speculative_decoding_draft_tokens_extern": 85, "speculative_decoding_mod": [34, 71, 74], "speculative_model_dir": [32, 59, 71], "speculativedecod": 0, "speculativedecodingconfig": 0, "speculativedecodingfastlogitsinfo": 0, "speculativedecodingmetr": 0, "speculativedecodingmod": [71, 85, 96], "speculativedecodingmodul": 96, "speculativedecodingoutput": 1, "speed": [17, 23, 27, 28, 29, 30, 32, 34, 74, 75, 81, 96], "speedup": [21, 23, 25, 26, 27, 29, 31, 32], "spent": 0, "spirit": 30, "split": [1, 4, 5, 10, 17, 71, 74, 77, 78, 83, 92, 96], "split_input_id": 88, "split_prompt_by_imag": 88, "split_siz": 83, "split_size_or_sect": 83, "splittransposecpu": 1, "splittransposecpuinn": 1, "splitwis": 2, "spot": [30, 80], "sq": [26, 93, 96], "sqrt": [5, 83], "squar": [80, 83], "squared_relu": 83, "squeez": [1, 83, 88], "src": [1, 17, 83], "src_seq_len": 83, "srcdesc": 0, "srctype": 1, "srun": [17, 35, 53, 54, 55, 68, 95, 97], "ssd": 32, "ssh": 91, "sshd": 36, "ssid": 47, "ssm": 83, "ssm_state": 85, "stabil": [12, 27, 30], "stabl": [5, 18, 30, 34, 76, 80, 81, 83, 96], "stack": [18, 27, 32, 66, 83], "stackoverflow": 91, "stage": [0, 5, 7, 13, 28, 31, 32, 33, 65, 75, 92, 96, 101], "stage_list": 90, "stai": [23, 26, 30, 77, 81], "stall": 30, "stand": 17, "standalon": 20, "standard": [13, 17, 19, 22, 30, 32, 33, 75, 83], "starcod": [94, 96], "starcoder1": 93, "starcoder2": [93, 96], "starrickliu": 96, "start": [0, 3, 5, 7, 9, 21, 28, 30, 34, 36, 37, 38, 39, 40, 42, 43, 44, 55, 56, 60, 61, 62, 63, 66, 71, 72, 74, 75, 76, 77, 80, 82, 83, 85, 87, 88, 90, 91, 92, 96, 97], "start_dim": 83, "startup": [2, 95], "stat": [0, 71, 96], "state": [0, 1, 3, 4, 5, 7, 8, 9, 13, 21, 27, 28, 30, 31, 34, 45, 68, 71, 74, 75, 76, 80, 82, 83, 89, 96, 107], "state_dtyp": 88, "state_or_ptr": 83, "state_s": 88, "statement": 70, "stateptr": 0, "states": 1, "static": [0, 1, 3, 12, 13, 29, 34, 71, 83, 84, 85, 88, 96], "static_batch": [71, 82], "static_cast": 93, "staticbatchingstat": 0, "statist": [0, 3, 13, 32, 33, 35, 71, 74, 96], "statu": [30, 95], "std": [0, 1, 3, 30], "stddev": [35, 43, 44], "stdev": [21, 33, 54, 73, 74, 75, 76], "stdin": 33, "stdit": 96, "stdout": [21, 33, 54, 73, 74, 75, 76], "steadi": 75, "steady_clock": 0, "step": [0, 1, 5, 6, 7, 9, 13, 16, 17, 19, 20, 22, 27, 28, 37, 58, 65, 68, 71, 72, 74, 75, 76, 83, 88, 95, 100, 101, 103, 106, 107], "still": [5, 18, 20, 21, 27, 28, 29, 30, 31, 72, 74, 76, 78, 83, 88, 92, 96], "stop": [0, 1, 3, 6, 7, 13, 30, 52, 71, 74, 80, 88, 89, 96, 103, 105], "stop_reason": [32, 71, 89, 96], "stop_token_id": [3, 71], "stop_words_data": 88, "stop_words_list": 88, "stopping_criteria": 88, "stoppingcriteria": [88, 96], "stoppingcriterialist": 88, "stoptokenid": [0, 3], "stopword": [0, 6], "stopwordslen": 1, "stopwordslist": 1, "stopwordsptr": 1, "storag": [0, 8, 10, 32, 70, 71], "store": [0, 1, 5, 8, 9, 10, 17, 23, 27, 28, 30, 32, 33, 71, 74, 82, 83, 85, 90, 92, 93, 97, 99, 101, 106], "stori": [56, 58], "str": [16, 20, 49, 50, 52, 57, 58, 59, 63, 71, 83, 84, 85, 88], "straight": 66, "straightforward": 28, "strategi": [0, 11, 13, 21, 26, 28, 30, 31, 41, 65, 70, 71, 74, 79, 83, 85, 92, 96], "stream": [0, 1, 2, 3, 17, 29, 30, 33, 34, 35, 41, 43, 44, 46, 52, 71, 73, 83, 88, 92, 95, 96, 97], "stream_interv": 71, "stream_ptr": 52, "streaming_llm": 96, "streamingllm": [34, 65, 96], "streamlin": [70, 74, 89], "streamptr": [0, 1, 3], "street": 56, "strenum": [71, 87], "strict": [27, 28, 30], "strict_bound": 83, "strict_dtyp": [83, 84], "stricter": 27, "strictli": 74, "stride": [1, 83, 84], "strike": [13, 30], "string": [0, 1, 3, 16, 47, 71, 74, 83, 88, 90], "string_valu": 9, "string_view": 1, "stringptrmap": 1, "stringvec": 0, "strip": [34, 96], "strip_plan": 34, "strong": 30, "strongli": 78, "strongly_typ": [71, 96], "struct": [0, 1, 8], "structur": [0, 4, 7, 8, 13, 29, 71, 74, 83, 92, 96], "structural_tag": 71, "struggl": 56, "student": [45, 48, 49, 51, 68, 89], "studi": [29, 76, 78, 79, 81], "studio": 91, "style": [5, 13, 27, 96], "sub": [16, 20, 30, 83], "sub_fil": 97, "subclass": [1, 20, 52, 99], "subcommad": 74, "subcommand": [33, 75, 96], "subdirectori": [74, 97], "subgraph": [7, 83], "subject": [2, 22, 24, 25, 26, 83, 89, 98], "submiss": 74, "submit": [10, 71, 74], "submit_sync": 71, "submittransferrequest": 0, "submodul": [21, 32, 66, 99], "suboptim": 17, "subscript": 83, "subsequ": [9, 10, 13, 28, 66, 76, 90], "subset": [0, 3, 6, 17, 20, 28, 71, 74, 83, 105], "substanti": [2, 9, 13, 27, 29, 31], "substitut": 91, "substr": 90, "subsystem": 96, "subtract": 7, "succe": [92, 96], "succeed": 88, "success": [3, 23, 27, 75, 90], "successfulli": [13, 37, 78], "sudo": [21, 27, 68, 74], "suffer": [27, 30], "suffici": [77, 78], "suggest": [5, 26, 30, 52, 56, 78], "suit": [5, 30, 31, 74, 75], "suitabl": [30, 31, 91], "sum": [1, 7, 15, 83, 106], "sum_of_token": 83, "summar": [5, 13, 14, 15, 16, 24, 26, 30, 74, 75, 82, 92], "summari": [8, 13, 30, 65], "summat": 83, "sunjiabin17": 96, "sunset": 58, "super": [7, 15, 18, 20, 94, 95, 99, 107], "superchip": 94, "superjomn": 58, "supplementari": 84, "suppli": [10, 19, 52, 90], "support": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 16, 19, 20, 22, 23, 24, 25, 26, 27, 29, 30, 33, 34, 35, 36, 41, 47, 53, 54, 55, 56, 58, 65, 68, 69, 70, 71, 75, 76, 78, 80, 81, 82, 83, 84, 86, 89, 90, 91, 95, 96, 98, 99, 100, 101, 104, 105, 106, 107], "supports_backend": 71, "supportsinflightbatch": 1, "suppos": 99, "suprem": [45, 68, 89], "sure": [2, 20, 21, 28, 30, 32, 37, 66, 70, 74, 82, 83, 96], "surpass": 5, "surround": [5, 96], "swa": 8, "swap": [8, 30], "sweep": [17, 23, 31, 80, 97], "sweet": 80, "swept": 24, "swiftli": 30, "swiglu": [34, 83, 96], "switch": [4, 9, 11, 12, 23, 26, 27, 29, 31, 66, 82, 92, 96], "sxm": [23, 34, 76, 78, 79], "sy": 96, "symbol": 0, "sync": 88, "sync_quant_config_with_kv_cache_config_dtyp": 71, "synchron": [1, 3, 17, 30, 71, 95, 96], "syncmessag": 0, "syntax": [83, 89], "synthet": [21, 33, 35, 43, 44, 74, 75], "synthetic_128_128": 74, "synthetic_2048_2048": 76, "synthetic_2048_2048_1000": 76, "synthetic_lora_data": 74, "system": [8, 9, 17, 21, 23, 28, 29, 30, 32, 35, 38, 39, 47, 53, 54, 55, 60, 61, 65, 66, 68, 75, 77, 89, 90, 94, 96, 98, 103], "systemat": [27, 30, 31], "t": [0, 1, 5, 13, 17, 20, 27, 29, 30, 35, 36, 41, 52, 53, 54, 55, 59, 68, 71, 73, 74, 77, 80, 81, 83, 85, 88, 95], "t5": [5, 6, 93, 94, 96], "t_": 28, "t_2": 28, "t_5": 28, "tabl": [0, 6, 9, 23, 26, 34, 74, 75, 83, 84, 88, 94, 95, 96], "tackl": 29, "tactic": [29, 34], "tag": [0, 36, 66, 68, 71, 90, 91], "tailor": [26, 78, 81], "take": [0, 1, 2, 5, 6, 7, 9, 11, 16, 20, 28, 30, 31, 32, 56, 71, 72, 74, 76, 77, 80, 83, 84, 97, 106], "taken": [18, 22, 23, 30, 83], "talk": [30, 56], "tanh": [83, 84], "target": [0, 18, 21, 29, 30, 31, 33, 34, 41, 52, 65, 66, 74, 81, 82, 96], "target_input_len": 33, "target_isl": 74, "target_osl": 74, "target_output_len": 33, "targetcach": 1, "targetpageid": 1, "targetprob": 1, "targettaskvalu": 1, "tarot": 56, "task": [0, 1, 9, 10, 13, 15, 16, 30, 33, 49, 50, 52, 53, 54, 55, 71, 74, 84, 88, 93, 96, 103, 106], "task_id": [10, 74], "task_vocab_s": 84, "taskid": [0, 1], "taskidtyp": 1, "tasklayermoduleconfig": 1, "tasklayermoduleconfigbind": 1, "tasklayermoduleconfiglistptr": 1, "taskshost": 1, "taskvalu": 1, "taskvalueptr": 1, "taslid": 1, "tayef": 96, "tconstptr": 1, "tcp": 37, "team": [16, 20, 27, 28, 29, 30, 31, 37, 90, 94, 96], "tech": [28, 30, 31, 96], "technic": [8, 28, 29, 30, 65], "techniqu": [5, 7, 13, 17, 22, 27, 28, 29, 30, 31, 46, 72, 77, 78, 79, 82, 93, 96], "technologi": [27, 32, 45, 48, 49, 51, 52, 68, 89], "tediou": 90, "tekit_2025": 74, "tell": [35, 39, 56, 58, 61, 81, 89], "temb": 84, "temp": [58, 88], "temperatur": [0, 1, 6, 32, 35, 38, 39, 40, 41, 45, 48, 49, 50, 51, 52, 57, 58, 68, 71, 74, 76, 82, 88, 89, 96, 105], "templat": [0, 1, 17, 18, 90], "tempor": 88, "temporari": 2, "ten": [13, 26, 28, 30], "tend": 82, "tensor": [1, 6, 11, 16, 17, 18, 21, 22, 23, 24, 25, 27, 28, 29, 30, 32, 33, 35, 51, 52, 65, 71, 74, 75, 78, 79, 81, 83, 84, 85, 88, 93, 95, 96, 97, 99, 101], "tensor_dict": 88, "tensor_input": 7, "tensor_parallel_s": [51, 53, 54, 55, 71, 76, 77, 78, 81, 82], "tensor_shap": 18, "tensorconstptr": 1, "tensorinfo": 88, "tensorloc": 83, "tensormap": 1, "tensorparallel": [0, 1, 6], "tensorptr": [0, 1], "tensorrt": [1, 3, 5, 6, 7, 8, 11, 14, 15, 22, 25, 27, 29, 33, 34, 35, 38, 39, 40, 41, 42, 43, 44, 45, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 67, 68, 69, 70, 73, 75, 78, 79, 81, 82, 83, 88, 90, 91, 93, 95, 97, 98, 99, 100, 101, 104, 106, 107], "tensorrt_llm": [0, 1, 3, 5, 6, 7, 10, 12, 14, 15, 17, 18, 20, 21, 32, 35, 36, 37, 41, 45, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 66, 67, 68, 71, 74, 75, 76, 78, 81, 82, 83, 84, 85, 86, 87, 88, 89, 91, 95, 96, 98, 99, 100, 101, 104, 105, 106], "tensorrt_llm_gpt": 17, "tensorrt_llm_rouge1_threshold": 16, "tensorrtllm_backend": [10, 89, 96], "tensortrt": 66, "tep4": 31, "term": [17, 30, 31, 70, 82, 83, 89, 90], "termin": [0, 9, 37, 75, 89, 96], "test": [5, 26, 27, 28, 31, 33, 35, 39, 61, 65, 66, 68, 74, 75, 76, 78, 79, 80, 81, 82, 94, 96, 97, 106], "test_gpt_ib_ptun": 90, "test_graph_rewrit": 7, "test_list": 90, "test_llm_openai_triton_1gpu": 90, "test_llm_qwen2audio_single_gpu": 90, "test_openai": 90, "test_qwen2audio": 90, "test_triton": 90, "test_trt_llm": [14, 15, 16], "texec": [0, 2], "text": [0, 3, 5, 6, 9, 31, 33, 34, 35, 39, 41, 45, 46, 51, 57, 58, 59, 61, 68, 71, 72, 74, 75, 76, 82, 88, 89, 90, 94, 95, 96], "text_diff": 71, "text_hidden_s": 85, "text_to_token": 52, "textattack": 94, "textprompt": 71, "tg_group": 83, "tgt": [17, 83], "tgt_len": [83, 84], "tgt_seq_len": 83, "th": [1, 16, 28, 83], "than": [0, 1, 2, 3, 5, 6, 7, 9, 13, 17, 21, 22, 23, 24, 26, 27, 28, 29, 30, 31, 34, 66, 71, 72, 74, 75, 76, 77, 78, 80, 82, 83, 88, 92, 95, 96, 101], "thank": [28, 30, 96], "thecodewrangl": 96, "thei": [0, 1, 3, 5, 6, 10, 17, 18, 20, 27, 28, 29, 30, 66, 71, 74, 76, 78, 80, 81, 82, 83, 85, 90, 91, 93, 96], "them": [0, 3, 4, 7, 13, 14, 21, 27, 28, 29, 30, 31, 53, 54, 55, 58, 71, 72, 73, 74, 77, 79, 80, 82, 83, 88, 92, 99], "themselv": 90, "theoret": [30, 92], "theori": 82, "therebi": [2, 82], "therefor": [6, 14, 20, 75, 83, 95, 105, 106], "thermal": 74, "theta": 83, "thi": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 20, 21, 22, 23, 24, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 41, 45, 47, 52, 53, 54, 55, 56, 57, 58, 59, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 88, 89, 90, 91, 92, 93, 95, 96, 97, 98, 99, 100, 101, 103, 105, 106, 107], "thin": 20, "thing": [6, 31, 37, 45, 48, 49, 51, 68, 80, 81, 89], "think": [27, 28, 29, 79], "third": [3, 31, 90, 96], "thorough": 30, "those": [3, 5, 6, 16, 17, 19, 21, 27, 28, 29, 30, 34, 35, 73, 75, 76, 81, 83, 84, 90, 93], "though": [20, 28, 30, 31, 80, 92], "thread": [0, 1, 5, 11, 30, 41, 70, 74, 88], "three": [3, 16, 26, 27, 29, 31, 33, 82, 83, 93, 99, 100, 101], "threshold": [0, 27, 28, 71, 83, 88], "throttl": 74, "through": [0, 5, 6, 7, 11, 12, 13, 17, 18, 19, 21, 27, 30, 31, 32, 34, 35, 66, 72, 74, 76, 77, 78, 80, 81, 84, 89, 96, 97], "throughout": [76, 79], "throughput": [0, 3, 5, 22, 23, 24, 28, 30, 31, 32, 54, 57, 65, 73, 78, 80, 81, 82, 96, 101, 103], "throw": [0, 1, 71], "thu": [9, 20, 21, 27, 29, 30, 66, 83, 91, 92], "thumb": [5, 77, 95], "ti": [5, 28], "tiiuae": 74, "tile": 29, "time": [0, 1, 2, 3, 5, 9, 10, 11, 13, 14, 17, 21, 24, 26, 27, 28, 29, 30, 31, 33, 34, 45, 48, 49, 50, 51, 56, 65, 66, 68, 71, 72, 73, 74, 75, 76, 78, 79, 80, 82, 83, 88, 89, 95, 96, 103, 106], "time_embed_dim": 84, "time_encod": 88, "time_point": 0, "timedelta": 71, "timedout": 0, "timelin": [16, 31], "timeout": [0, 30, 35, 41, 71, 96], "timepoint": 0, "timestamp": 0, "timestep": [84, 85], "timestepembed": 84, "timingmetr": 0, "tini": 56, "tinyllama": [31, 35, 38, 40, 43, 45, 47, 48, 49, 50, 51, 52, 56, 57, 58, 60, 62, 68, 70, 89], "tip": 65, "titl": [35, 47], "tle": 14, "tllm": 102, "tllm_checkpoint_16gpu_tp8_pp2": 77, "tllm_ckpt_dir": 15, "tllm_engine_dir": 15, "tllm_kei": [18, 84], "tllm_llmapi_build_cach": 96, "tllm_llmapi_enable_nvtx": 73, "tllm_log_level": 95, "tllm_nvtx_debug": 73, "tllm_override_layer_num": 96, "tllm_profile_record_gc": 73, "tllm_profile_start_stop": 73, "tllm_to_externel_key_dict": 18, "tllm_torch_profile_trac": 73, "tllm_trace_model_forward": 96, "tllm_weight": 18, "tllmruntim": [1, 6, 95], "tlntin": 96, "tmp": [10, 14, 54, 73, 74, 77], "tmp9so41y3r": 74, "tmpowsrb_f4": 74, "tmpxhdvasex": 74, "to_arrai": 83, "to_dict": [71, 85], "to_json_fil": 85, "to_layer_quant_config": 85, "to_legacy_set": 86, "to_str": [0, 1, 3], "to_trt": 85, "tobyt": 1, "todo": [1, 58, 83], "togeth": [3, 5, 6, 10, 17, 19, 22, 27, 31, 32, 34, 58, 88, 93, 96, 97], "toggl": 73, "toi": 80, "toitensor": 0, "tojsonstr": 0, "tok": [22, 24, 25, 31, 81], "token": [0, 1, 3, 4, 5, 6, 8, 9, 13, 17, 21, 22, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 43, 44, 47, 52, 54, 58, 65, 71, 73, 74, 75, 76, 78, 79, 81, 83, 84, 88, 89, 92, 93, 96, 97, 99, 100, 101], "token_count": 52, "token_drop": 84, "token_end": 71, "token_id": [41, 71], "token_ids_diff": 71, "token_range_retention_config": 71, "token_start": 71, "token_type_id": [85, 88], "tokenend": 0, "tokenextraid": 1, "tokenextraidtyp": 1, "tokenid": 1, "tokenidtyp": [0, 1], "tokenization_utils_bas": 71, "tokenizer_dir": [15, 17, 89, 95], "tokenizer_image_token": 88, "tokenizer_max_seq_length": [71, 78, 85, 87], "tokenizer_mod": 71, "tokenizer_revis": 71, "tokenizer_str": [0, 3], "tokenizerbas": 71, "tokenizerstr": [0, 3], "tokenlogprob": 71, "tokenrangeretentionconfig": [0, 71], "tokenrangeretentionprior": 0, "tokens_per_block": [8, 9, 34, 88, 96, 106], "tokensperblock": [0, 1, 6], "tokensperstep": 1, "tokensprompt": 71, "tokenstart": 0, "tokyo": [35, 39, 61], "toler": [26, 30], "tomodulenam": 1, "tomoduletyp": 1, "tonylek": 96, "too": [3, 5, 21, 29, 30, 76, 80, 95], "took": 76, "tool": [16, 21, 29, 30, 33, 65, 74, 91, 96], "tool_cal": [32, 89], "toolkit": [19, 20, 26, 27, 32, 68, 100], "top": [0, 5, 6, 13, 17, 19, 28, 29, 30, 31, 58, 71, 83, 90, 96, 105], "top1": 27, "top_k": [6, 58, 71, 88, 96, 105], "top_k_valu": 58, "top_p": [6, 45, 48, 49, 50, 51, 52, 57, 58, 68, 71, 76, 82, 88, 89, 105], "top_p_decai": [71, 88], "top_p_min": [71, 88], "top_p_reset_id": [71, 88], "top_p_valu": 58, "topenkoff": 96, "topic": [30, 81], "topk": [0, 1, 4, 6, 13, 27, 29, 83, 96], "topk_logit": 3, "topklastdim": 83, "topklogit": 3, "topkmedusahead": 1, "topktopp": [0, 6], "topmodelmixin": [20, 85], "topn": 27, "topologi": 30, "topp": [0, 1, 6, 96], "toppdecai": [0, 1, 6], "toppmin": [0, 1, 6, 71], "toppresetid": [0, 1, 6], "torch": [5, 18, 52, 66, 68, 71, 74, 83, 88, 95, 99, 102], "torch_compile_config": 71, "torchaudio": 68, "torchcompileconfig": 71, "torchllm": 71, "torchllmarg": 71, "torchvis": 68, "tostr": [0, 1], "total": [0, 1, 4, 5, 6, 13, 16, 18, 21, 28, 30, 31, 33, 34, 35, 74, 75, 76, 77, 90, 92, 106], "total_lat": [22, 25], "total_token": [32, 89], "totalaccepteddrafttoken": 0, "totaldrafttoken": 0, "totalgentoken": 1, "totalnumpag": 1, "totensor": 0, "touch": [36, 99], "toward": [30, 103], "tp": [0, 2, 4, 6, 10, 17, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 33, 35, 54, 74, 75, 76, 83, 96], "tp1": [22, 23, 24], "tp2": [31, 74], "tp4": 27, "tp4ep2": 27, "tp8": [24, 27, 29], "tp8ep2": 27, "tp_1_pp_1": 74, "tp_dim": [18, 84], "tp_group": [83, 84], "tp_rank": [18, 83, 84], "tp_size": [4, 10, 16, 17, 18, 20, 32, 33, 35, 42, 53, 55, 74, 75, 77, 83, 84, 87, 96], "tp_split_dim": 84, "tpot": [25, 31, 75], "tprank": 1, "tpsize": 1, "tqdm": [18, 71, 96], "trace": [20, 30, 33, 34, 35, 73, 95], "track": [5, 8, 30, 71, 83, 91], "trade": [9, 29], "tradeoff": [26, 27, 28, 78], "tradit": 0, "traffic": [30, 31], "train": [13, 15, 16, 17, 19, 20, 23, 26, 28, 74, 83, 95, 99], "trait": 96, "transa": 83, "transb": 83, "transceiv": [0, 71], "transfer": [0, 2, 17, 29, 30, 31, 71, 96], "transfer_mod": 71, "transferdesc": 0, "transfermod": 0, "transferop": 0, "transferrequest": 0, "transferstatu": 0, "transform": [0, 4, 5, 13, 15, 16, 17, 18, 33, 34, 35, 41, 52, 71, 85, 89, 92, 94, 95, 96, 99, 100, 106], "translat": [82, 91, 96], "transmiss": [2, 11, 31], "transmit": [2, 11], "transpar": 30, "transpos": [1, 16, 83], "transposit": 83, "travers": 17, "treat": [5, 27, 83], "tree": [0, 33, 67, 74, 88, 89, 95, 106], "tri": [29, 107], "tricki": 85, "trigger": [5, 7, 17, 30, 34, 41, 65, 70, 71], "trigger_completion_at_end": 83, "trim": 1, "trimpool": 1, "triton": [9, 10, 13, 17, 19, 65, 72, 90, 96], "triton_serv": 90, "tritonserv": 96, "trivial": 17, "troubleshoot": [65, 96], "trt": [0, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 17, 18, 23, 33, 36, 74, 80, 83, 85, 87, 88, 92, 95, 96, 101], "trt_ckpt": [10, 14, 16, 95], "trt_engin": [10, 14, 16, 95], "trt_llm_data": 91, "trt_llm_disable_load_weights_in_parallel": 32, "trt_root": 21, "trt_tensor": [17, 83], "trtdatatyp": 1, "trtgptmodel": 92, "trtgptmodeloptionalparam": 96, "trtgptmodelv1": 96, "trtllm": [9, 10, 14, 15, 16, 17, 20, 21, 28, 30, 32, 38, 39, 40, 41, 42, 43, 44, 46, 53, 60, 61, 62, 63, 65, 71, 74, 75, 78, 79, 80, 81, 91, 92, 95, 96, 97], "trtllm_dg_jit_use_nvcc": 21, "trtllm_disable_kv_cache_transfer_overlap": 2, "trtllm_disable_unified_convert": 18, "trtllm_enable_kvcache_receive_parallel": 2, "trtllm_enable_mmha_multi_block_debug": 74, "trtllm_enable_pdl": [21, 27, 28, 32, 74], "trtllm_force_xqa": 5, "trtllm_kvcache_send_max_concurrency_num": 2, "trtllm_kvcache_transfer_buffer_s": 2, "trtllm_kvcache_transfer_use_async_buff": 2, "trtllm_mmha_blocks_per_sequ": 74, "trtllm_mmha_kernel_block_s": 74, "trtllm_model": 18, "trtllm_modules_to_hf_modul": [74, 88], "trtllm_parallel_cache_send": 2, "trtllm_pdl_overlap_ratio": 74, "trtllm_precompiled_loc": 66, "trtllm_prefetch_ratio": 74, "trtllm_request_kv_cache_concurr": 2, "trtllm_serv": 35, "trtllm_try_zcopy_for_kvcache_transf": 2, "trtllm_use_mpi_kvcach": 2, "trtllm_use_precompil": 66, "trtllm_use_ucx_kvcach": 2, "trtllmarg": 71, "trtllmattent": 101, "trtlmmdatatyp": 0, "true": [0, 1, 3, 6, 7, 9, 13, 16, 21, 27, 28, 29, 30, 32, 35, 41, 50, 52, 54, 56, 57, 58, 59, 71, 73, 74, 75, 78, 81, 83, 84, 85, 86, 88, 92, 95, 96, 97, 103, 105], "true_output_valu": 83, "true_valu": 83, "truncat": [71, 96], "truncate_prompt_token": [71, 96], "trust": [29, 33, 71], "trust_remote_cod": [32, 33, 35, 71, 96], "try": [0, 1, 3, 15, 20, 30, 32, 56, 67, 70, 75, 78, 80, 81, 82, 89, 92, 95, 98, 104], "tsuji": 74, "ttensor": 1, "ttft": [31, 75, 78, 80, 81, 82, 96], "ttim": 96, "ttl": 27, "tunabl": 79, "tune": [0, 3, 13, 23, 26, 27, 29, 30, 31, 33, 34, 65, 71, 74, 75, 78, 81, 84, 85, 88, 89, 92, 96], "tuner": 0, "tupl": [0, 1, 83, 84, 88, 107], "turn": [5, 6, 9, 13, 29, 31, 66, 78, 88, 92, 96], "turnaround": 90, "tushar": 96, "tweak": 82, "twice": 17, "two": [0, 3, 4, 5, 6, 7, 9, 10, 11, 13, 14, 16, 17, 20, 23, 27, 28, 29, 30, 31, 33, 34, 35, 39, 61, 66, 70, 74, 76, 78, 80, 82, 83, 84, 86, 89, 90, 96, 100, 102, 105, 106, 107], "twofold": 13, "twoshot": [11, 71, 83], "txt": [20, 21, 33, 54, 73, 74, 76, 89, 90, 96], "type": [1, 2, 3, 5, 6, 7, 10, 16, 17, 23, 26, 29, 31, 32, 33, 34, 35, 38, 39, 40, 43, 44, 47, 52, 57, 58, 59, 61, 71, 74, 78, 81, 83, 85, 87, 88, 89, 90, 93, 94, 95, 96, 99, 100, 101, 106], "typedef": [0, 1], "typenam": [0, 1, 17], "typetrait": 0, "typic": [0, 2, 7, 15, 17, 20, 26, 28, 29, 30, 31, 35, 70, 77, 78, 81, 82, 86, 88, 92, 96, 99], "typo": 96, "u": [1, 7, 29, 30, 31, 36, 45, 48, 49, 50, 51, 68, 74, 75, 89, 96], "ub": [11, 71, 83], "ub_oneshot": 74, "ub_tp_siz": 74, "ubuntu": [68, 96, 98], "uc_handl": 1, "uc_ptr": 1, "uc_va": 1, "ucx": [0, 31, 71, 96], "uid": [0, 88, 91], "uint16_t": 0, "uint32": 1, "uint32_t": [0, 1, 83], "uint64": [1, 9], "uint64_t": [0, 1], "uint8": 1, "uint8_t": [0, 1], "uintptr_t": [0, 1], "uk": 29, "uk_bgemm": 27, "ulimit": [32, 66, 95], "ultim": 77, "ulyss": 96, "unabl": [68, 80], "unaccept": 78, "unari": 83, "unaryoper": 83, "unbind": 83, "uncas": 94, "uncertainti": 13, "unchang": [13, 30, 81, 83, 90], "uncom": 91, "uncommon": 17, "undefin": 83, "under": [0, 26, 31, 34, 66, 70, 71, 74, 75, 90, 95, 96], "underli": [0, 1, 7, 13, 30, 31], "underlying_type_t": 1, "underlyingtyp": [0, 1], "underscor": 78, "understand": [30, 65, 66, 73, 90], "understood": [71, 80], "underutil": 13, "underwai": 31, "uneven": 96, "unevenli": 27, "unexpect": [95, 96], "unfinish": 0, "unfus": 83, "unfuse_qkv_project": 85, "ungath": 1, "unguid": 47, "unif": 96, "unifi": [16, 20, 26, 96], "uniform": [33, 74, 75, 83], "uniniti": 101, "union": [71, 83], "uniqu": [0, 5, 6, 8, 10, 13, 16, 34, 71, 74], "unique_ptr": [0, 1], "uniqueconstptr": 1, "uniqueptr": 1, "uniquetoken": 1, "unit": [1, 8, 18, 29, 32, 45, 65, 66, 68, 74, 76, 82, 89], "unittest": 90, "univers": [45, 48, 49, 51, 68, 89], "unknown": 33, "unless": [0, 41, 71, 77, 81, 82], "unlik": [9, 13, 28], "unlock": [30, 72], "unnecessari": [7, 96, 99, 107], "unneed": [5, 27], "unordered_map": [0, 1, 3], "unpatchifi": 85, "unschedul": 80, "unset": [30, 82], "unsign": 1, "unspecifi": [34, 35, 83], "unsqueez": [1, 83], "unstabl": 20, "unsupport": [90, 96], "untest": 102, "until": [0, 1, 3, 6, 9, 13, 30], "untouch": 83, "unus": [0, 74], "up": [0, 2, 5, 6, 10, 13, 21, 23, 24, 27, 28, 29, 30, 31, 32, 33, 34, 47, 52, 71, 74, 80, 81, 89, 96, 97, 106], "up_proj": 18, "upcast": 83, "upcast_attent": 84, "upcast_softmax": 84, "upcom": [26, 106], "updat": [0, 8, 13, 17, 18, 20, 21, 24, 28, 29, 30, 32, 34, 36, 66, 71, 83, 88, 95, 103, 106], "update_from_dict": 71, "update_from_model_config": 71, "update_key_map": 18, "update_kv_cache_typ": 71, "update_output_ids_by_offset": 88, "update_resourc": [100, 106], "update_strategi": 83, "updatenumreturnbeam": 0, "updatespositionid": 1, "upgrad": [68, 89], "uplift": [78, 80, 81], "upon": [13, 32, 75, 81, 95, 96], "upper": [59, 74, 83, 92], "uq_qr_gemm": 27, "url": [31, 35, 39, 43, 44, 61, 66, 68, 96], "us": [0, 1, 2, 3, 4, 5, 6, 8, 9, 11, 12, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 33, 34, 35, 36, 37, 41, 45, 46, 47, 50, 53, 54, 55, 56, 58, 65, 66, 67, 68, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 83, 84, 85, 86, 88, 89, 93, 95, 96, 97, 98, 99, 100, 101, 105, 106, 107], "usabl": 98, "usag": [0, 2, 5, 7, 8, 17, 20, 22, 25, 29, 31, 32, 33, 34, 35, 45, 65, 67, 70, 71, 74, 81, 82, 83, 89, 96, 97, 101], "use_beam_hyp": 88, "use_beam_search": [71, 96], "use_cach": [83, 84, 85], "use_context_fmha_for_gener": 96, "use_custom_all_reduc": 96, "use_diff_of_squar": 83, "use_dynamic_tre": 71, "use_embedding_shar": 96, "use_fp32_acc": 83, "use_fp8": 84, "use_fp8_context_fmha": [5, 34, 74, 96], "use_fused_mlp": [34, 74, 96], "use_gemm_allreduce_plugin": 88, "use_gpt_attention_plugin": 88, "use_gpu_direct_storag": 88, "use_implicit_relative_attent": 84, "use_kv_cach": [84, 88], "use_logn_sc": 84, "use_lora": 85, "use_lora_plugin": 88, "use_mamba_conv1d_plugin": 88, "use_meta_recip": 71, "use_modelopt_quant": 20, "use_mrop": 71, "use_mtp_vanilla": 71, "use_one_more_block": 88, "use_paged_context_fmha": [5, 9, 34, 74, 78, 81], "use_parallel_embed": [16, 17, 85], "use_preload": 85, "use_prompt_tun": [85, 96], "use_py_sess": 95, "use_refit": 71, "use_relaxed_acceptance_for_think": [27, 28, 59, 71], "use_runtime_default": 88, "use_safetensors_load": 85, "use_strip_plan": 71, "use_tqdm": 71, "use_uvm": 71, "use_variable_beam_width_search": 88, "usebantoken": 0, "usebanword": 0, "usecrossattent": 1, "usedefaultvalu": 1, "usednumblock": 0, "usedraftlogit": 1, "usedraftlogitshost": 1, "usedynamictre": 0, "usedynamictreehost": 1, "useexpliciteosstop": 0, "usefrequencypenalti": 0, "usegemmallreduceplugin": 1, "usegptattentionplugin": [1, 6], "usegpudirectstorag": 0, "uselanguageadapt": 1, "useloraplugin": 1, "usemambaconv1dplugin": 1, "usemaxlengthstop": 0, "useminlen": 0, "useminlength": 0, "useminp": 0, "usemrop": 1, "usenorepeatngrams": 0, "useoccurrencepenalti": 0, "usepackedinput": 1, "usepagedst": 1, "usepenalti": 0, "usepositionembed": 1, "usepresencepenalti": 0, "useprogthread": 0, "useprompttun": 1, "user": [0, 2, 3, 5, 6, 7, 9, 10, 11, 12, 17, 18, 19, 20, 21, 25, 26, 27, 28, 29, 30, 31, 32, 35, 36, 38, 39, 47, 60, 61, 66, 70, 71, 73, 74, 75, 80, 81, 82, 83, 85, 89, 91, 92, 93, 95, 96, 97], "user_buff": [34, 78], "user_provid": [71, 85], "userandomacceptancethreshold": 1, "userbuff": [71, 96], "userepetitionpenalti": 0, "usernam": 32, "userprovideddecodingconfig": 71, "userwarn": 68, "useshapeinfer": 1, "usespecdecod": 1, "usestopword": 0, "usetemp": 0, "usetemperatur": 0, "usetokentypeembed": 1, "useuvm": 0, "usevariablebeamwidthsearch": 0, "using_oss_cutlass_": 12, "using_oss_cutlass_low_latency_gemm": 12, "using_oss_cutlass_moe_gemm": 12, "usr": [16, 21, 35, 38, 39, 40, 42, 43, 44, 68, 74], "usual": [17, 20, 28, 68, 71, 75, 76, 81, 83, 106], "util": [0, 1, 5, 6, 13, 17, 21, 22, 27, 29, 30, 31, 32, 34, 45, 57, 68, 72, 73, 74, 78, 81, 82, 92, 96, 101, 103], "uv": 29, "uv_gemm": 27, "uvm": [0, 1, 71], "v": [1, 5, 6, 10, 21, 22, 23, 26, 27, 29, 32, 65, 83, 88, 91, 93, 94, 95, 99, 101], "v0": [10, 22, 23, 24, 25, 72, 74, 75, 94, 96, 103], "v1": [31, 32, 35, 38, 39, 40, 43, 45, 47, 48, 49, 50, 51, 52, 56, 57, 58, 60, 61, 62, 63, 68, 70, 89, 94, 96], "v10": 96, "v100": 96, "v12": 96, "v2": [26, 29, 93, 96], "v3": [28, 30, 35, 73, 93, 94, 96], "v9": 24, "v_dim": 83, "v_head_dim": [83, 84], "v_proj": [18, 74, 99], "vacat": [45, 68, 89], "valid": [0, 1, 3, 13, 28, 30, 71, 75, 83, 88], "validate_and_init_token": 71, "validate_auto_parallel": 71, "validate_build_config_remain": 71, "validate_build_config_with_runtime_param": 71, "validate_checkpoint_format": 71, "validate_cuda_graph_config": 71, "validate_cuda_graph_max_batch_s": 71, "validate_enable_build_cach": 71, "validate_kv_cache_dtyp": 71, "validate_load_balanc": 71, "validate_lora_config_consist": 71, "validate_model_format_misc": 71, "validate_parallel_config": 71, "validate_positive_valu": 71, "validate_quant_config": 71, "validate_runtime_arg": 71, "validate_speculative_config": 71, "validate_stream_interv": 71, "validatevec": 1, "validationerror": 71, "validmpiconfig": 1, "valu": [0, 1, 2, 5, 6, 8, 9, 10, 11, 14, 16, 17, 18, 21, 22, 23, 28, 29, 31, 33, 34, 35, 41, 52, 58, 71, 74, 76, 78, 80, 82, 83, 85, 86, 87, 88, 90, 92, 93, 95, 96, 101, 106, 107], "valuabl": [27, 30, 31], "value_typ": 0, "valueerror": 59, "valuestatu": 1, "vanilla": [5, 71, 101], "vanillaattent": 101, "var": 83, "vari": [24, 30, 31, 32, 80, 81, 106], "variabl": [0, 1, 6, 8, 18, 21, 24, 27, 30, 31, 53, 54, 55, 65, 68, 71, 73, 74, 91, 95, 96, 97], "variabledraftlength": 1, "varianc": [29, 78, 80, 81, 83], "variant": [0, 3, 5, 20, 22, 28, 29, 83, 89, 96, 101], "varieti": [74, 76, 96], "variou": [5, 13, 19, 30, 31, 33, 58, 66, 70, 74, 78, 80, 91, 96, 97], "varnam": 1, "vartyp": 1, "vboost": [21, 27, 74], "vbw": 96, "ve": [27, 56], "vec": [0, 1], "vec2": 83, "veclogprob": 0, "vectoken": 0, "vectokenextraid": [0, 1], "vector": [0, 1, 3, 5, 6, 8, 10, 29, 83], "vecuniquetoken": [0, 1], "vehicl": 32, "verbatim": 85, "verbos": [33, 34, 35, 74], "veri": [5, 16, 17, 19, 26, 28, 30, 32, 76, 77, 78, 96], "verif": [0, 13, 28, 71], "verifi": [13, 28, 32, 65, 81, 83, 90, 96], "verificationsets": 0, "versa": [9, 29], "version": [0, 1, 2, 5, 6, 16, 18, 20, 21, 27, 29, 30, 35, 41, 66, 67, 68, 74, 76, 83, 89, 91, 95, 96, 98], "vertic": 83, "vertical_strid": 84, "vgqa": 8, "via": [0, 2, 11, 12, 13, 27, 30, 31, 53, 54, 55, 56, 65, 66, 74, 78, 79, 81, 82, 83, 89, 90, 96, 97, 98], "vice": [9, 29], "vicuna": 13, "video": [33, 35, 39, 61, 74, 88, 94, 96], "video_grid_thw": 88, "video_path": 88, "video_preprocess": 88, "video_url": [35, 39, 61], "view": [1, 28, 30, 32, 83, 88], "vila": [35, 39, 61, 93, 94, 96], "vinyl": 74, "violat": 96, "virtual": [0, 1, 84], "vision": [33, 88, 93, 94, 96], "vision_grid_thw": 88, "vision_length": 83, "vision_model_typ": 85, "vision_start": 83, "vision_token_mask": 84, "visit": [13, 27, 96], "visual": [32, 80, 91, 96], "visual_engine_dir": 88, "visual_featur": 88, "visualize_network": [34, 71, 96], "vit": 96, "vital": [7, 26], "vl": [35, 39, 44, 61, 74, 94, 96], "vlm": [94, 96], "vocab": [83, 88], "vocab_embed": [15, 18], "vocab_s": [0, 16, 18, 71, 84, 85, 88, 99], "vocab_size_pad": 88, "vocabs": [1, 6], "vocabsizepad": [0, 1], "vocabulari": [0, 1, 6, 9, 13, 75, 84, 88], "void": [0, 1, 3, 17], "volta": 96, "volum": [1, 11, 65, 66, 74], "volumenonneg": 1, "vonjackustc": 96, "vote": [45, 68, 89], "vswa": 8, "vulner": 96, "vultureprim": 96, "w": [1, 21, 25, 27, 29, 32, 33, 35, 83, 85, 93, 94, 96], "w1": 83, "w4a": [93, 96], "w4a16": [16, 26, 33, 65, 71, 85], "w4a16_awq": [16, 20, 33, 41, 71], "w4a16_gptq": [16, 33, 71], "w4a8": [26, 96], "w4a8_awq": [16, 20, 33, 71], "w4a8_mxfp4_fp8": 71, "w4a8_qserve_per_channel": 71, "w4a8_qserve_per_group": 71, "w4aint8": 96, "w8a": 93, "w8a16": [16, 26, 33, 65, 71, 85], "w8a16_gptq": 71, "w8a8": [23, 26, 65], "w8a8_sq_per_channel": [16, 71], "w8a8_sq_per_channel_per_tensor_plugin": [71, 85], "w8a8_sq_per_channel_per_token_plugin": [71, 85], "w8a8_sq_per_tensor_per_token_plugin": [71, 85], "w8a8_sq_per_tensor_plugin": [71, 85], "wa": [0, 1, 3, 5, 6, 16, 28, 29, 30, 67, 68, 70, 74, 75, 76, 78, 80, 81, 82, 84, 89, 93, 95, 96, 99, 107], "wai": [5, 6, 7, 11, 19, 27, 28, 29, 30, 31, 51, 52, 67, 70, 72, 74, 76, 78, 83, 89, 92, 96], "wait": [0, 1, 3, 20, 29, 30, 41, 71, 72, 74, 83, 97, 103], "waiv": 65, "walk": [32, 35, 39, 56, 61, 76, 77, 78], "wang1120": 96, "wangkuiyi": 96, "want": [5, 13, 20, 27, 28, 30, 32, 37, 66, 68, 73, 74, 78, 80, 82, 83, 95, 96, 99], "war": 1, "warm": [2, 33, 106], "warmup": [21, 30, 33, 73, 74, 76, 96, 101, 106], "warn": [5, 33, 34, 35, 52, 71, 74, 75, 92], "warp": [11, 96], "wast": [29, 90], "watch": 81, "wdkv": 27, "wdq": 27, "we": [1, 2, 4, 6, 7, 10, 11, 12, 13, 14, 16, 20, 21, 25, 26, 27, 28, 29, 30, 31, 32, 35, 36, 37, 45, 48, 49, 51, 56, 66, 68, 73, 74, 75, 76, 77, 78, 80, 81, 83, 88, 89, 95, 96, 99], "web": [19, 37], "weig": 83, "weight": [0, 1, 4, 10, 20, 22, 23, 26, 27, 28, 30, 32, 33, 34, 35, 51, 65, 71, 72, 75, 76, 77, 78, 83, 84, 85, 88, 89, 96], "weight_index": 83, "weight_load": 84, "weight_only_groupwise_quant_matmul": 93, "weight_only_precis": 96, "weight_spars": [34, 71], "weight_stream": [14, 34, 71], "weightonlygroupwisequantmatmulplugin": 93, "weights_dict": 20, "weights_scaling_factor": [16, 18], "weightsinpoint": 1, "weightsoutpoint": 1, "welcom": 30, "well": [2, 5, 6, 17, 19, 23, 30, 41, 73, 80, 81, 93, 94, 105], "were": [0, 1, 12, 13, 16, 20, 22, 26, 29, 31, 75, 77, 80, 96], "weren": 68, "wget": 95, "what": [2, 3, 29, 30, 35, 39, 56, 58, 59, 61, 65, 66, 71, 73, 74, 76, 78, 80, 81, 90], "whatev": 1, "wheel": [66, 68, 89, 96], "when": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11, 13, 17, 18, 20, 21, 25, 26, 28, 29, 30, 31, 32, 33, 34, 36, 41, 52, 65, 66, 68, 71, 73, 74, 76, 78, 80, 81, 82, 83, 84, 85, 88, 89, 90, 91, 92, 93, 95, 96, 99, 101, 105, 106], "whenev": 1, "where": [0, 1, 2, 5, 6, 8, 9, 11, 12, 13, 16, 17, 22, 26, 27, 28, 29, 30, 31, 33, 35, 38, 40, 41, 56, 60, 62, 71, 74, 75, 78, 80, 82, 83, 88, 89, 93, 96, 107], "wherea": [0, 16, 31, 80], "whether": [0, 1, 3, 5, 10, 30, 31, 34, 71, 77, 78, 81, 83, 84, 88, 100, 101], "which": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 13, 16, 17, 18, 20, 22, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 52, 57, 58, 66, 68, 70, 71, 73, 74, 76, 78, 80, 81, 82, 83, 85, 86, 88, 89, 90, 91, 92, 93, 96, 97, 100, 101, 104, 105, 107], "while": [0, 1, 4, 7, 8, 9, 11, 12, 13, 17, 20, 21, 22, 23, 25, 26, 27, 28, 29, 30, 31, 32, 68, 70, 72, 74, 76, 77, 78, 79, 80, 81, 82, 83, 90, 92, 93, 96, 101], "whisper": [93, 94, 96], "whisperencod": 85, "whl": [21, 66, 68], "who": [28, 70], "whole": [1, 71, 72, 83], "whose": [2, 9, 16, 27, 30, 31, 58, 84, 90], "why": [0, 17, 29, 32, 71, 78, 80, 81, 83, 90, 92], "wide": [0, 4, 28, 32, 71, 76], "wideep": 71, "width": [0, 1, 5, 6, 44, 71, 84, 88, 92, 96], "wildcard": 90, "win": 71, "window": [0, 1, 8, 13, 34, 65, 71, 74, 83, 88, 96, 102], "window_s": 5, "windows": 0, "wip": [27, 102], "wireless": 47, "wirelessaccesspoint": 47, "wise": [7, 30, 71, 83, 96], "wish": 9, "with_ssh": 36, "within": [2, 5, 8, 11, 13, 17, 29, 30, 58, 71, 74, 77, 78, 80, 81, 83, 89, 97, 106], "without": [0, 1, 3, 5, 11, 13, 17, 18, 21, 26, 27, 30, 31, 34, 41, 52, 72, 74, 78, 81, 83, 85, 90, 96, 99, 101, 103], "wkr": 27, "wo": [18, 27, 96], "wo_gemm": 27, "won": [68, 77], "word": [0, 3, 5, 6, 71, 83, 88, 96, 105], "word_dict": 88, "word_embed": 18, "word_embeddings_layernorm": 18, "work": [5, 6, 7, 8, 11, 13, 17, 20, 21, 30, 33, 41, 53, 54, 55, 59, 66, 67, 68, 72, 75, 79, 83, 88, 89, 93, 95, 96, 97, 99], "work_dir": 97, "workaround": [18, 21, 96], "workdir": [35, 53, 54, 55, 66], "worker": [17, 31, 34, 35, 71, 74, 92, 96, 97], "workerexecutablepath": 0, "workflow": [5, 6, 15, 16, 21, 28, 30, 31, 41, 65, 70, 75, 76, 78, 79, 83, 89, 95, 96], "workload": [4, 11, 17, 29, 30, 31, 32, 34, 73, 74, 76, 78, 79, 80, 81], "workspac": [1, 30, 33, 34, 35, 71, 74, 83, 91, 92, 96], "workstat": 23, "world": [0, 2, 7, 21, 28, 30, 34, 53, 54, 55, 72, 74, 76, 77, 78, 83], "world_config": 88, "world_siz": [16, 20, 83, 96], "worldconfig": [0, 6, 88], "worldsiz": 1, "wors": [13, 34, 78], "worst": [30, 80, 81], "worth": [5, 8, 78, 81], "would": [0, 7, 13, 28, 30, 74, 76, 78, 80, 82, 83, 99], "wpa2": 47, "wqr": 27, "wrap": [0, 1, 17, 34, 70, 76, 83, 86, 88, 96], "wrapped_properti": 71, "wrapper": [1, 7, 20, 30, 101], "write": [0, 1, 9, 18, 27, 30, 34, 58, 65, 83, 95], "written": [17, 33, 74, 83], "wrong": [13, 96], "wsl": 96, "wuk": 27, "wuq": 27, "wuv": 27, "www": 96, "x": [0, 1, 3, 6, 10, 14, 30, 35, 66, 67, 74, 83, 84, 85, 89, 93, 96], "x86": 9, "x86_64": 94, "xcomposer2": 96, "xgrammar": [0, 3, 47, 71, 96], "xl": 96, "xml": 3, "xor": 83, "xqa": 96, "xxx": [18, 20, 95], "xxx_plugin": 86, "xy": 83, "y": [3, 21, 25, 30, 36, 66, 67, 68, 74, 83, 85, 89, 93], "y_bia": 83, "yaml": [30, 31, 32, 33, 35, 74, 75, 90, 97], "yarn": 83, "ye": [2, 83, 92, 102], "yeah": 56, "yelp": 94, "yen": 74, "yet": [0, 6, 20, 21, 23, 27, 30, 67, 83, 89, 105, 107], "yield": [9, 29, 41, 78, 80], "yiyixu": [35, 39, 61], "yml": [21, 28, 35, 42, 74, 75, 90, 91], "york": [35, 38, 40, 60, 62, 89], "you": [3, 4, 5, 6, 7, 9, 10, 12, 13, 16, 17, 19, 20, 21, 26, 27, 28, 29, 30, 31, 32, 34, 35, 36, 37, 38, 39, 41, 47, 53, 54, 55, 56, 59, 60, 61, 65, 66, 67, 68, 70, 71, 74, 75, 77, 78, 79, 80, 81, 82, 83, 88, 89, 90, 92, 95, 96, 97, 98, 99, 101, 104], "your": [9, 10, 11, 13, 19, 20, 21, 26, 28, 30, 34, 36, 37, 41, 56, 58, 66, 68, 70, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 89, 90, 95, 99, 101, 106], "your_data_path": [21, 28], "your_dockerhub_usernam": [36, 37], "your_model_dir": 28, "your_model_path": [21, 30], "your_public_kei": 37, "your_work_path": 21, "yourself": 104, "yuhuili": 59, "yyi": 95, "z": [66, 67, 83, 89], "zars19": 96, "zero": [0, 1, 3, 18, 70, 71, 83, 84, 93, 95, 103], "zero_is_placehold": 83, "zjli2013": 96, "zoo": [52, 96], "zoom": 30, "\u7f8e\u56fd\u7684\u9996\u90fd\u5728\u54ea\u91cc": 63}, "titles": ["Executor", "Runtime", "Disaggregated-Service (Experimental)", "Executor API", "Expert Parallelism in TensorRT-LLM", "Multi-Head, Multi-Query, and Group-Query Attention", "C++ GPT Runtime", "Graph Rewriting Module", "KV Cache Management: Pools, Blocks, and Events", "KV cache reuse", "Run gpt-2b + LoRA using Executor / cpp runtime", "Low-Precision-AllReduce", "<no title>", "Speculative Sampling", "Running With Weight Streaming to Reduce GPU Memory Consumption", "Adding a Model", "TensorRT-LLM Checkpoint", "Model Definition", "TensorRT-LLM Model Weights Loader", "TensorRT-LLM Architecture", "TensorRT-LLM Build Workflow", "How to get best performance on DeepSeek-R1 in TensorRT-LLM", "Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100", "H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token", "H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM", "New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget", "Speed up inference with SOTA quantization techniques in TRT-LLM", "Pushing Latency Boundaries: Optimizing DeepSeek-R1 Performance on NVIDIA B200 GPUs", "DeepSeek R1 MTP Implementation and Optimization", "Optimizing DeepSeek R1 Throughput on NVIDIA Blackwell GPUs: A Deep Dive for Developers", "Scaling Expert Parallelism in TensorRT-LLM (Part 1: Design and Implementation of Large-scale EP)", "Disaggregated Serving in TensorRT-LLM", "How to launch Llama4 Maverick + Eagle3 TensorRT-LLM server", "trtllm-bench", "trtllm-build", "trtllm-serve", "Build the TensorRT-LLM Docker Image", "Develop TensorRT-LLM on Runpod", "Curl Chat Client", "Curl Chat Client For Multimodal", "Curl Completion Client", "LLM Common Customizations", "Deepseek R1 Reasoning Parser", "Genai Perf Client", "Genai Perf Client For Multimodal", "LLM Examples Introduction", "LLM Examples", "Generate text with guided decoding", "Generate text", "Generate text asynchronously", "Generate text in streaming", "Distributed LLM Generation", "Control generated text using logits processor", "Run LLM-API with pytorch backend on Slurm", "Run trtllm-bench with pytorch backend on Slurm", "Run trtllm-serve with pytorch backend on Slurm", "Generate text with multiple LoRA adapters", "Runtime Configuration Examples", "Sampling Techniques Showcase", "Speculative Decoding", "OpenAI Chat Client", "OpenAI Chat Client for Multimodal", "OpenAI Completion Client", "Openai Completion Client For Lora", "Online Serving Examples", "Welcome to TensorRT-LLM\u2019s Documentation!", "Building from Source Code on Linux", "Pre-built release container images on NGC", "Installing on Linux via pip", "Key Features", "LLM API Introduction", "API Reference", "Overview", "Performance Analysis", "TensorRT-LLM Benchmarking", "Overview", "Benchmarking Default Performance", "Deciding Model Sharding Strategy", "FP8 Quantization", "Performance Tuning Guide", "Tuning Max Batch Size and Max Num Tokens", "Useful Build-Time Flags", "Useful Runtime Options", "Functionals", "Layers", "Models", "Plugin", "Quantization", "Runtime", "Quick Start Guide", "Continuous Integration Overview", "Using Dev Containers", "Memory Usage of TensorRT-LLM", "Numerical Precision", "Support Matrix", "Troubleshooting", "Release Notes", "Disaggregated Inference Benchmark Scripts", "PyTorch Backend", "Adding a New Model in PyTorch Backend", "Architecture Ovewiew", "Attention", "Feature Combination Matrix", "Overlap Scheduler", "Quantization", "Sampling", "KV Cache Manager", "Scheduler"], "titleterms": {"": [5, 23, 26, 65], "0": 96, "000": [23, 24], "0528": 21, "1": [15, 17, 21, 30, 32, 66, 70, 75, 92, 96], "10": [23, 96], "100m": 23, "1024": 31, "11": 96, "12": [24, 96], "1200": 31, "13": 96, "13b": 24, "14": 96, "15": 96, "16": 96, "17": 96, "18": 96, "180b": 22, "19": 96, "2": [15, 21, 25, 30, 32, 66, 70, 92, 96], "256": 31, "2b": 10, "3": [15, 17, 21, 30, 31, 32, 74, 75, 92, 94], "4": [15, 21, 23, 32], "405b": [17, 75], "4096": 31, "4400": 31, "4x": 25, "5": [21, 32], "6": [21, 22, 32], "6x": 23, "7": [32, 96], "70b": [17, 22, 25, 74, 75], "7x": 22, "8": 96, "8192": 31, "8b": 75, "9": 96, "A": 29, "As": 3, "For": [39, 44, 63], "In": [3, 5, 72], "It": 103, "Not": [21, 92], "One": [27, 66], "The": [3, 30, 93], "To": 76, "With": [14, 72], "a100": [22, 23], "about": [13, 35, 72, 77], "absorb": 29, "accept": [27, 28], "access": 36, "account": 37, "accuraci": [11, 26, 28], "achiev": [23, 24, 28], "acknowledg": [27, 28, 29, 30, 31], "activ": [84, 92], "ad": [15, 99], "adapt": [56, 74], "addit": 3, "adp": 29, "advanc": [65, 66], "algorithm": 11, "alibi": 5, "allreduc": 11, "altern": 32, "an": 8, "analysi": 73, "announc": 96, "api": [3, 7, 14, 20, 35, 53, 70, 71, 76, 89, 96, 100], "arbitrari": 3, "architectur": [19, 27, 65, 100], "argument": 34, "artifact": 32, "asynchron": 49, "asyncio": 41, "attent": [5, 16, 27, 28, 29, 72, 80, 81, 82, 84, 101], "attentionbackend": 101, "attentionmetadata": 101, "auto": 34, "autoregress": 27, "avoid": [76, 90], "awq": [16, 22, 93], "b200": [21, 27], "backend": [27, 31, 53, 54, 55, 94, 98, 99, 101], "background": [27, 28], "balanc": [27, 30], "base": [28, 41], "baselin": 78, "basic": [28, 46], "batch": [3, 5, 72, 80], "beam": [3, 5], "befor": [74, 76], "begin": 76, "behavior": 74, "bench": [33, 54, 73, 76], "benchmark": [21, 26, 35, 74, 75, 76, 97], "best": [21, 26, 90], "bf16": 93, "bia": 5, "bind": [3, 17, 66], "blackwel": [29, 93], "block": 8, "blockmanag": 8, "boost": 74, "boundari": 27, "budget": 25, "buffer": [5, 78, 92], "buffermanag": 1, "build": [16, 20, 21, 32, 33, 34, 36, 37, 41, 66, 74, 76, 81], "built": 67, "c": [3, 6, 30, 66, 92], "cach": [5, 8, 9, 16, 21, 31, 78, 82, 92, 106], "cachecommun": 0, "can": [9, 72], "capac": 82, "case": 80, "cast": 84, "caveat": 74, "chang": [14, 80, 96], "chat": [35, 38, 39, 60, 61], "checkpoint": 16, "choos": 26, "chunk": [5, 21, 80, 82], "ci": 90, "class": 3, "classic": 7, "cli": [20, 76], "client": [38, 39, 40, 43, 44, 60, 61, 62, 63], "clock": [21, 74], "clone": 32, "close": [22, 25], "code": 66, "collect": [30, 73], "combin": [21, 102], "come": 26, "command": 75, "common": [1, 41, 72], "commun": [27, 30, 77], "compil": [17, 21, 66, 89], "complet": [35, 40, 62, 63], "compon": [6, 98], "compos": 91, "conclus": [78, 80, 81], "config": [16, 34], "configur": [3, 6, 10, 27, 30, 37, 41, 57, 78, 81, 91, 99], "connect": 37, "consider": 11, "consumpt": 14, "contain": [21, 36, 66, 67, 89, 91], "content": [21, 27, 28, 29, 30, 79, 90, 99], "context": [3, 5, 21, 80, 81, 82], "contigu": 5, "continu": 90, "control": [3, 52], "conv": 84, "convers": [15, 20], "coordin": 73, "core": [30, 99], "cpp": 10, "creat": 37, "cross": 5, "cuda": 27, "cudaev": 1, "cudastream": 1, "curl": [38, 39, 40], "custom": [18, 41, 46, 106, 107], "cutlass": 27, "cyclic": 5, "data": 29, "dataset": [21, 30, 31, 33, 74, 75, 76], "datatransceiverst": 0, "debug": [2, 73, 95], "decid": 77, "decod": [3, 13, 28, 34, 47, 59, 92, 100], "decoderst": 1, "decodinginput": 1, "decodingoutput": 1, "decor": 7, "deep": 29, "deepseek": [21, 27, 28, 29, 31, 42], "default": [21, 27, 74, 76], "definit": [17, 89, 90, 99], "dens": 27, "depend": 27, "deploi": 89, "dequant": 93, "descript": [73, 97], "design": 30, "detail": [10, 93], "dev": 91, "develop": [29, 37, 98], "diagram": 27, "differ": 3, "disabl": [41, 90], "disaggr_torch": 97, "disaggreg": [2, 13, 31, 35, 97], "disaggregated_mpi_work": 35, "disaggserverutil": 0, "distribut": 51, "dive": 29, "do": 72, "docker": [32, 36, 37, 66, 91], "dockerhub": [36, 37], "document": [65, 96], "dora": 10, "download": [21, 32], "dq": 93, "draft": 13, "dynamo": 31, "e2": [30, 95], "eagl": [13, 28], "eagle3": [28, 32], "eaglebuff": 1, "eaglemodul": 1, "effect": 30, "embed": [5, 84], "enabl": [4, 9, 21, 36, 73, 78, 81], "endpoint": 35, "engin": [16, 17, 74, 76, 89, 100], "enhanc": 96, "environ": 2, "ep": [29, 30], "eplb": 30, "error": 95, "etp": 27, "evalu": [16, 28, 30], "event": 8, "everyth": 27, "exampl": [3, 10, 16, 17, 18, 45, 46, 57, 64, 70, 73, 74], "except": 92, "exchang": 31, "execut": 95, "executor": [0, 3, 10], "expand": 30, "expect": [9, 21], "experiment": 2, "expert": [4, 27, 29, 30], "explicitdrafttokensbuff": 1, "explor": 21, "extens": 30, "face": 70, "factor": [5, 16], "fail": 90, "falcon": 22, "faq": [2, 92], "fast": 90, "faster": 22, "featur": [21, 69, 73, 96, 98, 102], "file": [66, 97], "find": 90, "first": 23, "fix": 96, "flag": [81, 93], "flayerinfo": 7, "flight": [3, 5, 72], "flow": 74, "fmha": 5, "format": [10, 21], "fp16": [21, 93], "fp32": 93, "fp4": 75, "fp8": [5, 16, 21, 23, 72, 75, 78, 93], "fraction": 82, "free": 82, "from": [66, 70], "full": 66, "fulli": 18, "function": [7, 18, 83], "fuse_a_gemm": 27, "fusion": [17, 27, 78, 81], "futur": [27, 28, 29, 31, 41], "garbag": 73, "gate": 78, "gb200": 30, "gc": 73, "gemm": [27, 78, 81], "gen_yaml": 97, "genai": [43, 44], "gener": [2, 5, 30, 41, 47, 48, 49, 50, 51, 52, 56], "get": [21, 65], "gil": 73, "gpt": [6, 10], "gptdecod": 1, "gptdecoderbatch": 1, "gptjsonconfig": 1, "gptq": 93, "gpu": [14, 17, 21, 22, 27, 29, 30, 72, 74, 82, 92], "graph": [7, 27], "group": [5, 27], "gsm8k": 30, "guid": [3, 47, 79, 89, 98, 99], "h": [0, 1], "h100": [23, 24], "h200": [21, 22, 24, 25], "ha": 23, "hardwar": 94, "hbm": 24, "head": 5, "header": 66, "hierarchi": 8, "high": [7, 30], "hopper": [21, 93], "host": [9, 30], "how": [4, 9, 21, 27, 28, 29, 32, 74, 77, 80, 103], "hub": 70, "hug": 70, "i": [23, 77, 92], "ibuff": 1, "id": 10, "igptdecoderbatch": 1, "imag": [32, 36, 37, 66, 67, 89, 91], "implement": [15, 27, 28, 30, 101], "import": 5, "improv": 13, "increas": 25, "indic": 65, "infer": [3, 26, 28, 30, 31, 35, 72, 89, 92, 97], "inform": [7, 73, 89], "infrastructur": 96, "input": [5, 70], "instal": [21, 65, 68, 89, 95], "int4": [22, 93], "int8": [5, 93], "integr": 90, "interfac": [30, 106], "intern": 6, "introduct": [29, 30, 45, 70, 99, 106, 107], "ipcnvlsmemori": 1, "ipcutil": 1, "isl": [21, 31], "issu": [21, 92, 96, 98], "itensor": 1, "iter": 73, "jenkin": 90, "kei": [18, 27, 37, 69, 77, 96, 98], "kernel": [25, 27, 30], "knowledg": 79, "known": [66, 92, 96, 98], "kv": [5, 8, 9, 16, 21, 31, 78, 82, 92, 106], "kvcacheeventmanag": 8, "kvcachemanag": 100, "larg": 30, "latenc": [21, 25, 27, 33, 74, 76, 78], "latest": [24, 72], "launch": [27, 32, 73], "layer": [27, 29, 84], "layernorm": 16, "layout": [18, 31], "level": [7, 27, 30, 100], "limit": [13, 66, 74, 96], "linear": 84, "link": 66, "linux": [66, 68], "llama": [17, 22, 25, 74, 75, 78, 81], "llama2": 24, "llama4": 32, "llm": [4, 13, 16, 18, 19, 20, 21, 23, 24, 26, 28, 30, 31, 32, 36, 37, 41, 45, 46, 51, 53, 65, 66, 70, 72, 74, 76, 80, 89, 92, 94, 96], "load": [18, 30, 99], "loader": 18, "local": 70, "log": 32, "logic": 30, "logit": [3, 34, 52], "lookahead": 13, "lookaheadbuff": 1, "lookaheadmodul": 1, "lora": [10, 34, 56, 63, 74], "loracach": [1, 10], "loracachepagemanagerconfig": 1, "loramodul": 1, "low": [11, 74, 78], "machin": [30, 31], "make": 16, "manag": [7, 8, 74, 106], "map": [10, 74], "mark": 3, "marker": 73, "match": 17, "matrix": [93, 94, 102], "maverick": 32, "max": [21, 74, 80, 82], "maximum": 82, "measur": [31, 75], "medusa": [13, 74], "medusamodul": 1, "memori": [9, 14, 21, 24, 82, 92], "memorycount": 1, "merg": 90, "method": [7, 26], "methodologi": 31, "metric": 35, "min": 21, "miscellan": 30, "mix": 27, "mixtur": 4, "mla": [21, 29], "mlp": [16, 78, 84], "mlperf": 23, "modal": [74, 94], "mode": 74, "model": [6, 13, 15, 17, 18, 19, 21, 27, 28, 70, 74, 75, 77, 78, 81, 85, 89, 94, 95, 96, 99, 100], "modelconfig": 1, "modul": [7, 10, 28, 29], "moe": [4, 29], "moe_backend": 27, "monitor": 32, "more": [21, 25, 73], "motiv": [30, 31], "mount": 91, "mqa": 29, "mtp": [27, 28], "multi": [5, 17, 27, 31, 35, 72, 74, 94], "multimod": [35, 39, 44, 61], "multipl": [56, 81], "name": [18, 34, 90], "nativ": [18, 72], "nearli": 24, "network": 74, "new": [15, 25, 99, 101], "next": [26, 89], "ngc": [32, 67], "ngram": 13, "node": [17, 35, 72], "non": 74, "norm": [78, 81], "normal": 84, "note": [3, 5, 96], "nsight": 73, "num": 80, "numer": 93, "nvfp4": 93, "nvidia": [27, 29, 73], "nvtx": 73, "o": 92, "observ": 30, "obtain": 3, "offlin": 30, "offload": 9, "one": 30, "onli": [27, 66, 73, 93], "onlin": [30, 64], "openai": [60, 61, 62, 63], "optim": [5, 27, 28, 29, 31, 81], "option": [21, 32, 66, 78, 81, 82], "osl": [21, 31], "other": 74, "out": [21, 99], "output": [3, 74], "over": [22, 30], "overlap": [31, 103], "overrid": 91, "overview": [6, 16, 18, 20, 72, 75, 90, 97], "ovewiew": 100, "own": 107, "p": 9, "pack": 5, "pad": 5, "page": [5, 8, 72, 80, 81, 82], "parallel": [4, 10, 27, 29, 30, 34, 74, 77, 81], "paramet": 6, "parser": 42, "part": [15, 30], "pattern": [7, 17], "perf": [43, 44], "perform": [9, 11, 13, 21, 23, 26, 27, 30, 31, 32, 65, 73, 76, 78, 79, 81], "persist": 74, "phase": 5, "pip": 68, "pipelin": [77, 81, 90], "pitfal": 76, "plugin": [17, 34, 78, 81, 86], "pod": 37, "polici": 82, "pool": [8, 84, 92], "posit": 5, "post": [3, 90], "postprocess": 18, "power": 74, "practic": [26, 90], "pre": 67, "precis": [11, 27, 29, 93], "prepar": [16, 21, 32, 37, 74, 75, 76], "prepare_dataset": 33, "prerequisit": [21, 32, 66, 79, 89, 99], "prevent": 9, "processor": [3, 52], "profil": [27, 73, 81], "programmat": 27, "prompttuningparam": 1, "provid": 25, "push": [27, 32], "py": [33, 90, 97], "pyexecutor": 100, "python": [3, 30, 66, 92], "pytorch": [53, 54, 55, 73, 74, 94, 98, 99], "q": 93, "qkv": 5, "quantiz": [16, 20, 26, 41, 74, 78, 87, 93, 104], "quantmod": 93, "queri": 5, "quick": [70, 89, 98], "quickstart": 74, "qwen": 31, "r1": [21, 27, 28, 29, 31, 42], "rab": 5, "rank": 16, "rawengin": 1, "re": 27, "reason": 42, "recommend": [78, 81, 92], "record_signatur": 7, "redraft": 13, "reduc": [14, 78, 81], "refer": [15, 65, 71, 103], "regist": 15, "registr": 99, "registri": 32, "rel": 5, "relat": [7, 89], "relax": [27, 28], "releas": [32, 67, 96], "repositori": 32, "reproduc": [21, 27, 29, 30, 31, 75], "request": [1, 3, 32], "requir": [7, 11], "resourcemanag": 100, "respons": 3, "result": [3, 21, 73, 75, 76], "retriev": 7, "reus": 9, "revisit": 80, "rewrit": 7, "right": 26, "roll": 5, "rope": 5, "rotari": 5, "router": 27, "routergemm": 27, "run": [10, 14, 21, 28, 30, 53, 54, 55, 73, 74, 75, 76, 89], "run_benchmark": 97, "runpod": 37, "runtim": [1, 6, 10, 17, 29, 41, 57, 66, 82, 88, 92], "runtimedefault": 1, "same": 25, "sampl": [6, 13, 32, 41, 58, 105], "samplingconfig": 1, "save": 76, "scale": [5, 16, 30], "scatter": 81, "schedul": [80, 82, 100, 103, 107], "script": 97, "search": 5, "sec": 24, "select": 91, "send": 3, "serial": 0, "serv": [13, 31, 35, 55, 64, 73, 89], "server": [3, 31, 32, 35, 89], "servic": 2, "set": [74, 77], "sh": 97, "shard": 77, "shoot": 18, "showcas": 58, "singl": 22, "situat": 9, "size": [80, 82, 92], "slide": 5, "slurm": [35, 46, 53, 54, 55, 97], "smart": 27, "smoothquant": 93, "softwar": 94, "sota": 26, "sourc": 66, "spars": 27, "specif": 73, "specul": [13, 28, 34, 59], "speculativedecodingmod": 1, "speculativedecodingmodul": 1, "speed": 26, "speedup": 28, "ssh": [36, 37], "stage": 90, "start": [32, 35, 65, 70, 89, 98], "start_work": 97, "statist": 30, "step": [15, 21, 30, 31, 32, 66, 89, 99], "stop": 32, "strategi": [27, 29, 77], "stream": [14, 27, 50], "streamingllm": 5, "structur": 3, "studi": [28, 30, 31, 80], "style": 41, "subcommand": 74, "submit": 97, "summari": [74, 78, 81], "support": [17, 18, 21, 28, 31, 66, 72, 74, 93, 94], "swiglu": 78, "syntax": 35, "synthet": 31, "system": [27, 73], "tabl": [21, 27, 28, 29, 30, 65, 79, 90, 99], "tag": [32, 67, 89], "target": 13, "technic": 93, "techniqu": [26, 58], "templat": 37, "tensor": [0, 3, 4, 5, 7, 10, 77, 92], "tensorrt": [4, 13, 16, 17, 18, 19, 20, 21, 23, 24, 26, 28, 30, 31, 32, 36, 37, 65, 66, 72, 74, 76, 80, 89, 92, 94, 96], "test": [32, 90, 95], "test_to_stage_map": 90, "text": [47, 48, 49, 50, 52, 56], "think": 77, "thought": 30, "throughput": [21, 25, 29, 33, 74, 75, 76], "time": [81, 92], "tip": [32, 70, 76, 95], "tllmlogger": 1, "tok": 23, "token": [23, 24, 41, 80, 82], "token_norm_dist": 33, "token_unif_dist": 33, "tool": 20, "top": 100, "topic": 66, "topologi": 11, "tradeoff": 103, "transferag": 0, "transform": 31, "translat": [18, 30, 31], "tree": [13, 28, 99], "trigger": [8, 90], "triton": [3, 31, 89], "troubl": 18, "troubleshoot": [2, 32, 70, 76, 95], "trt": 26, "trtllm": [27, 31, 33, 34, 35, 54, 55, 73, 76, 89], "tune": [9, 21, 32, 79, 80], "type": [0, 8], "understand": [80, 92], "unit": [90, 95], "unnecessari": 90, "up": [22, 25, 26], "updat": 96, "upload": [36, 37], "us": [7, 10, 13, 32, 52, 70, 81, 82, 90, 91, 92], "usag": [11, 90, 92, 103], "user": 78, "v": [4, 24], "valid": 74, "vanilla": 28, "variabl": [2, 75], "verif": 27, "verifi": 15, "via": [68, 76], "visual": 73, "volum": 91, "w4a16": 93, "w8a16": 93, "w8a8": 93, "wai": 32, "waiv": 90, "weekli": 32, "weight": [14, 15, 16, 17, 18, 19, 29, 92, 93, 99], "welcom": 65, "what": [8, 23, 26, 72], "when": [7, 27], "width": 3, "window": [5, 72, 82], "windowblockmanag": 8, "wip": 21, "within": 25, "without": 66, "work": [27, 28, 29, 31, 74, 103], "workflow": [7, 18, 20, 73, 74, 97], "workload": 27, "world": 6, "worldconfig": 1, "write": 15, "xqa": [5, 25], "you": [72, 76], "your": [32, 107]}}) \ No newline at end of file diff --git a/latest/torch.html b/latest/torch.html index 40fc0c44dc..c98e18aebd 100644 --- a/latest/torch.html +++ b/latest/torch.html @@ -58,7 +58,7 @@ @@ -70,7 +70,7 @@ - + @@ -349,6 +349,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -384,6 +386,8 @@

    Command-Line Reference

    @@ -689,9 +693,9 @@ This feature is currently experimental, and the related API is subjected to chan
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/torch/adding_new_model.html b/latest/torch/adding_new_model.html index a1bfbd0d3d..099a908f94 100644 --- a/latest/torch/adding_new_model.html +++ b/latest/torch/adding_new_model.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -347,6 +347,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -382,6 +384,8 @@

    Command-Line Reference

    @@ -833,9 +837,9 @@
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/torch/arch_overview.html b/latest/torch/arch_overview.html index 240432870c..c2da5549c9 100644 --- a/latest/torch/arch_overview.html +++ b/latest/torch/arch_overview.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -347,6 +347,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -382,6 +384,8 @@

    Command-Line Reference

    @@ -529,7 +533,7 @@ Key components of the #

    The core component of PyExecutor is the ModelEngine, responsible for executing the model’s forward pass efficiently on the GPU. The key method of ModelEngine is forward, which handles the forward pass computation. -For the PyTorch backend, the derived class is PyTorchModelEngine, declared in pytorch_model_engine.py.

    +For the PyTorch backend, the derived class is PyTorchModelEngine, declared in model_engine.py.

    Decoder#

    @@ -699,9 +703,9 @@ The document
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/torch/attention.html b/latest/torch/attention.html index 560087de59..521f4d386f 100644 --- a/latest/torch/attention.html +++ b/latest/torch/attention.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -347,6 +347,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -382,6 +384,8 @@

    Command-Line Reference

    @@ -823,9 +827,9 @@ For example, the Flashinfer metadata fills
    -

    Last updated on July 14, 2025.

    +

    Last updated on July 19, 2025.

    -

    This page is generated by TensorRT-LLM commit cfcb97a.

    +

    This page is generated by TensorRT-LLM commit 69e9f6d.

    diff --git a/latest/torch/features/feature_combination_matrix.html b/latest/torch/features/feature_combination_matrix.html index de6b20d524..b3d2abb608 100644 --- a/latest/torch/features/feature_combination_matrix.html +++ b/latest/torch/features/feature_combination_matrix.html @@ -58,7 +58,7 @@ @@ -68,7 +68,7 @@ - + @@ -343,6 +343,8 @@
  • Control generated text using logits processor
  • Generate text with multiple LoRA adapters
  • Speculative Decoding
    • +
  • Runtime Configuration Examples
    • +
  • Sampling Techniques Showcase
  • Run LLM-API with pytorch backend on Slurm
  • Run trtllm-bench with pytorch backend on Slurm
  • Run trtllm-serve with pytorch backend on Slurm
    • @@ -378,6 +380,8 @@

    Command-Line Reference

    @@ -720,11 +724,11 @@

    Guided Decoding

    Yes

    Yes

    Yes

    No

    Yes

    Yes

    Untested

    Yes

    No

    No

    No