TensorRT-LLMs/searchindex.js

Search.setIndex({"docnames": ["_cpp_gen/executor", "_cpp_gen/runtime", "advanced/batch-manager", "advanced/expert-parallelism", "advanced/gpt-attention", "advanced/gpt-runtime", "advanced/graph-rewriting", "advanced/inference-request", "advanced/lora", "advanced/weight-streaming", "architecture/add-model", "architecture/checkpoint", "architecture/core-concepts", "architecture/model-weights-loader", "architecture/overview", "architecture/workflow", "blogs/Falcon180B-H200", "blogs/H100vsA100", "blogs/H200launch", "blogs/XQA-kernel", "blogs/quantization-in-TRT-LLM", "commands/trtllm-build", "executor", "index", "installation/build-from-source-linux", "installation/build-from-source-windows", "installation/linux", "installation/windows", "key-features", "kv_cache_reuse", "llm-api-examples/customization", "llm-api-examples/index", "llm-api-examples/llm_api_examples", "llm-api-examples/llm_auto_parallel", "llm-api-examples/llm_generate", "llm-api-examples/llm_generate_async", "llm-api-examples/llm_generate_async_streaming", "llm-api-examples/llm_generate_distributed", "llm-api-examples/llm_quantization", "llm-api/index", "overview", "performance/perf-analysis", "performance/perf-best-practices", "performance/perf-overview", "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/memory", "reference/precision", "reference/support-matrix", "reference/troubleshooting", "release-notes", "speculative_decoding"], "filenames": ["_cpp_gen/executor.rst", "_cpp_gen/runtime.rst", "advanced/batch-manager.md", "advanced/expert-parallelism.md", "advanced/gpt-attention.md", "advanced/gpt-runtime.md", "advanced/graph-rewriting.md", "advanced/inference-request.md", "advanced/lora.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/Falcon180B-H200.md", "blogs/H100vsA100.md", "blogs/H200launch.md", "blogs/XQA-kernel.md", "blogs/quantization-in-TRT-LLM.md", "commands/trtllm-build.rst", "executor.md", "index.rst", "installation/build-from-source-linux.md", "installation/build-from-source-windows.md", "installation/linux.md", "installation/windows.md", "key-features.md", "kv_cache_reuse.md", "llm-api-examples/customization.md", "llm-api-examples/index.md", "llm-api-examples/llm_api_examples.rst", "llm-api-examples/llm_auto_parallel.rst", "llm-api-examples/llm_generate.rst", "llm-api-examples/llm_generate_async.rst", "llm-api-examples/llm_generate_async_streaming.rst", "llm-api-examples/llm_generate_distributed.rst", "llm-api-examples/llm_quantization.rst", "llm-api/index.rst", "overview.md", "performance/perf-analysis.md", "performance/perf-best-practices.md", "performance/perf-overview.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/memory.md", "reference/precision.md", "reference/support-matrix.md", "reference/troubleshooting.md", "release-notes.md", "speculative_decoding.md"], "titles": ["Executor", "Runtime", "The Batch Manager in TensorRT-LLM", "Expert Parallelism in TensorRT-LLM", "Multi-Head, Multi-Query, and Group-Query Attention", "C++ GPT Runtime", "Graph Rewriting Module", "Inference Request", "Run gpt-2b + LoRA using GptManager / cpp runtime", "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", "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", "trtllm-build", "Executor API", "Welcome to TensorRT-LLM\u2019s Documentation!", "Building from Source Code on Linux", "Building from Source Code on Windows", "Installing on Linux", "Installing on Windows", "Key Features", "KV cache reuse", "Common Customizations", "LLM Examples Introduction", "Examples", "LLM Auto Parallel", "LLM Generate", "LLM Generate Async", "LLM Generate Async Streaming", "LLM Generate Distributed", "LLM Quantization", "API Reference", "Overview", "Performance Analysis", "Best Practices for Tuning the Performance of TensorRT-LLM", "Overview", "Functionals", "Layers", "Models", "Plugin", "Quantization", "Runtime", "Quick Start Guide", "Memory Usage of TensorRT-LLM", "Numerical Precision", "Support Matrix", "Troubleshooting", "Release Notes", "Speculative Sampling"], "terms": {"namespac": [0, 1, 2, 46], "tensorrt_llm": [0, 1, 2, 4, 5, 6, 8, 9, 10, 12, 13, 15, 22, 24, 25, 26, 27, 30, 31, 33, 34, 35, 36, 37, 38, 39, 44, 45, 46, 47, 48, 49, 50, 54, 55, 56], "function": [0, 1, 2, 4, 9, 10, 12, 14, 15, 22, 37, 39, 41, 42, 47, 49, 51, 52, 53, 54, 55], "char": [0, 1], "const": [0, 1, 2, 22], "version": [0, 1, 4, 5, 11, 13, 15, 22, 24, 25, 26, 27, 30, 43, 44, 50, 54, 55], "noexcept": [0, 1], "trt": [0, 2, 3, 4, 5, 6, 8, 12, 13, 17, 25, 29, 34, 39, 44, 46, 48, 49, 51, 54, 55], "llm": [0, 1, 4, 5, 6, 8, 10, 12, 16, 19, 21, 22, 26, 27, 28, 29, 30, 32, 39, 41, 43, 44, 46, 48, 52, 54], "variabl": [0, 1, 2, 5, 13, 18, 25, 54, 55], "sizetype32": [0, 1], "kdefaultiterstatsmaxiter": 0, "1000": [0, 43], "kdefaultrequeststatsmaxiter": 0, "0": [0, 1, 2, 4, 5, 6, 7, 8, 9, 11, 12, 13, 15, 17, 18, 20, 21, 22, 23, 25, 27, 29, 30, 31, 33, 34, 35, 36, 37, 38, 39, 41, 42, 43, 44, 45, 46, 49, 50, 51, 54, 56], "class": [0, 1, 2, 4, 5, 6, 7, 9, 10, 12, 13, 15, 20, 21, 24, 29, 30, 31, 34, 39, 44, 45, 46, 47, 48, 49, 54, 55], "samplingconfig": [0, 5, 22, 30, 49, 55], "includ": [0, 1, 2, 4, 5, 7, 8, 11, 12, 13, 14, 16, 17, 19, 21, 22, 24, 25, 26, 29, 30, 31, 38, 39, 40, 42, 50, 52, 55, 56], "sampl": [0, 1, 4, 7, 12, 14, 22, 28, 34, 35, 36, 37, 38, 39, 41, 43, 44, 49, 55], "configur": [0, 1, 2, 3, 4, 7, 13, 14, 18, 21, 22, 25, 26, 39, 42, 46, 49, 51, 54, 55, 56], "public": [0, 1, 20, 25, 38], "explicit": [0, 1, 41, 44, 55, 56], "beamwidth": [0, 1, 2, 5, 39, 55], "1": [0, 1, 2, 4, 5, 6, 7, 8, 9, 11, 13, 15, 16, 17, 18, 19, 20, 21, 22, 23, 25, 26, 27, 29, 30, 31, 33, 34, 35, 36, 37, 38, 39, 41, 42, 43, 44, 45, 46, 49, 50, 53, 54, 56], "std": [0, 1, 2, 22], "option": [0, 1, 5, 6, 7, 10, 15, 17, 21, 23, 25, 26, 27, 29, 30, 39, 43, 44, 47, 49, 51, 54, 55, 56], "topk": [0, 1, 3, 5, 7, 44, 56], "nullopt": [0, 1], "floattyp": [0, 1], "topp": [0, 1, 5, 7, 55], "toppmin": [0, 1, 5, 39], "tokenidtyp": [0, 1], "toppresetid": [0, 1, 5], "toppdecai": [0, 1, 5], "randomseedtyp": 0, "seed": [0, 5, 39, 48, 55], "temperatur": [0, 1, 5, 7, 30, 31, 33, 34, 35, 36, 37, 38, 39, 49, 50, 55], "mintoken": [0, 55], "beamsearchdiversityr": [0, 1, 5], "repetitionpenalti": [0, 1, 5, 7], "presencepenalti": [0, 1, 5, 7], "frequencypenalti": [0, 1, 5, 7], "lengthpenalti": [0, 1, 5, 7], "earlystop": [0, 1, 5, 7], "norepeatngrams": [0, 1, 5, 7], "constructor": [0, 1, 2, 9, 31], "see": [0, 1, 2, 4, 5, 7, 12, 13, 16, 18, 19, 20, 31, 41, 42, 43, 44, 45, 46, 51, 52, 54, 55, 56], "descript": [0, 1, 5, 7, 8, 23, 43, 44], "paramet": [0, 1, 3, 4, 8, 9, 11, 12, 13, 15, 21, 22, 29, 39, 42, 44, 45, 46, 49, 51, 55, 56], "below": [0, 1, 2, 4, 5, 6, 7, 8, 18, 19, 20, 31, 43, 56], "bool": [0, 1, 2, 6, 7, 9, 11, 39, 44, 45, 46, 49], "oper": [0, 1, 2, 4, 5, 6, 11, 12, 13, 22, 42, 43, 44, 50, 51, 53], "other": [0, 1, 3, 4, 5, 12, 13, 15, 16, 22, 24, 27, 29, 30, 40, 42, 44, 47, 51, 55, 56], "getbeamwidth": 0, "gettopk": 0, "gettopp": 0, "gettoppmin": 0, "gettoppresetid": 0, "gettoppdecai": 0, "getse": 0, "getrandomse": 0, "gettemperatur": 0, "getmintoken": 0, "getminlength": 0, "getbeamsearchdiversityr": 0, "getrepetitionpenalti": 0, "getpresencepenalti": 0, "getfrequencypenalti": 0, "getlengthpenalti": 0, "getearlystop": 0, "getnorepeatngrams": 0, "void": [0, 1, 2, 12, 22], "setbeamwidth": 0, "settopk": 0, "settopp": 0, "settoppmin": 0, "settoppresetid": 0, "settoppdecai": 0, "setse": 0, "setrandomse": 0, "randomse": [0, 1, 5, 7, 55], "settemperatur": 0, "setmintoken": 0, "setminlength": 0, "minlength": [0, 1, 5, 7, 55], "setbeamsearchdiversityr": 0, "setrepetitionpenalti": 0, "setpresencepenalti": 0, "setfrequencypenalti": 0, "setlengthpenalti": 0, "setearlystop": 0, "setnorepeatngrams": 0, "privat": [0, 1, 5], "member": [0, 1, 2, 5, 6, 9, 12, 38, 39, 44], "mbeamwidth": [0, 1], "The": [0, 1, 3, 4, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 20, 21, 23, 24, 25, 27, 29, 30, 31, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 49, 50, 51, 53, 54, 55, 56], "beam": [0, 1, 2, 5, 7, 14, 19, 21, 23, 30, 39, 44, 49, 51, 54, 55, 56], "width": [0, 1, 2, 4, 5, 7, 39, 49, 51, 55], "default": [0, 1, 2, 3, 4, 5, 7, 11, 13, 15, 21, 22, 24, 25, 27, 29, 30, 39, 42, 44, 46, 49, 50, 51, 52, 54, 55], "i": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 18, 19, 20, 21, 22, 24, 25, 27, 29, 30, 31, 33, 34, 35, 36, 37, 38, 39, 40, 42, 43, 44, 45, 46, 47, 49, 50, 52, 53, 54, 55, 56], "which": [0, 1, 2, 3, 4, 5, 6, 8, 11, 12, 13, 15, 16, 20, 22, 24, 25, 27, 29, 39, 41, 42, 44, 46, 47, 49, 50, 51, 52, 55, 56], "disabl": [0, 1, 2, 4, 5, 9, 13, 21, 39, 42, 44, 47, 49, 51, 55, 56], "search": [0, 1, 5, 14, 19, 21, 23, 27, 30, 39, 44, 55, 56], "mtopk": 0, "control": [0, 2, 4, 5, 6, 22, 30, 39, 42, 44, 49, 52], "number": [0, 1, 2, 3, 4, 5, 7, 12, 19, 21, 22, 39, 42, 43, 44, 45, 51, 52, 55, 56], "logit": [0, 1, 5, 7, 39, 44, 46, 49, 54, 55, 56], "from": [0, 1, 2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18, 20, 21, 22, 23, 27, 29, 30, 33, 34, 35, 36, 37, 38, 39, 40, 42, 43, 44, 45, 46, 48, 49, 50, 51, 54, 55], "all": [0, 1, 2, 3, 4, 5, 6, 7, 8, 12, 13, 15, 18, 22, 24, 25, 26, 27, 39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 55, 56], "mtopp": 0, "top": [0, 4, 5, 12, 14, 39, 44, 55, 56], "p": [0, 5, 7, 14, 39, 44, 46, 49, 55, 56], "probabl": [0, 1, 5, 7, 29, 39, 44, 55, 56], "f": [0, 4, 5, 7, 25, 31, 33, 34, 35, 36, 37, 38, 39, 44, 50, 54, 56], "mtoppmin": 0, "decai": [0, 5, 39], "algorithm": [0, 4, 5, 11, 12, 15, 20, 39, 44, 55, 56], "lower": [0, 1, 5, 6, 8, 19, 20, 29, 30, 39, 42, 43, 44, 51], "bound": [0, 5, 10, 12, 18, 39, 44, 49, 51], "e": [0, 1, 4, 8, 13, 25, 27, 29, 39, 41, 42, 44, 47, 49, 52, 54, 55], "6": [0, 1, 5, 8, 9, 18, 20, 29, 39, 43, 44, 53, 54, 55, 56], "mtoppresetid": 0, "indic": [0, 1, 2, 4, 5, 11, 22, 39, 42, 44, 45, 51, 56], "where": [0, 1, 2, 4, 5, 7, 11, 12, 16, 20, 29, 30, 39, 43, 44, 49, 51, 52, 55, 56], "reset": [0, 1, 5, 39, 49], "mtoppdecai": 0, "valu": [0, 1, 2, 4, 5, 7, 8, 9, 11, 12, 13, 16, 17, 21, 29, 30, 39, 41, 42, 44, 46, 47, 48, 49, 51, 52, 54, 55, 56], "mseed": 0, "random": [0, 5, 39, 43, 44, 55], "us": [0, 1, 2, 3, 4, 5, 7, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 29, 30, 31, 36, 39, 40, 41, 42, 43, 44, 45, 46, 47, 49, 50, 52, 54, 55], "gener": [0, 1, 2, 5, 7, 11, 12, 13, 15, 16, 17, 19, 21, 22, 23, 25, 29, 31, 32, 33, 38, 39, 40, 41, 42, 43, 44, 46, 49, 50, 51, 53, 54, 55, 56], "mtemperatur": 0, "modul": [0, 1, 2, 4, 5, 10, 11, 12, 13, 21, 23, 24, 27, 39, 45, 46, 49, 54, 55], "when": [0, 1, 2, 3, 4, 5, 7, 8, 12, 13, 15, 19, 20, 21, 22, 23, 24, 25, 29, 30, 39, 42, 43, 44, 45, 46, 49, 50, 51, 52, 54, 55, 56], "new": [0, 1, 2, 4, 5, 6, 7, 8, 9, 15, 17, 18, 22, 23, 25, 26, 27, 29, 33, 34, 35, 36, 37, 39, 40, 44, 49, 51, 55, 56], "token": [0, 1, 2, 3, 4, 5, 7, 12, 16, 19, 20, 21, 22, 29, 39, 41, 43, 44, 45, 46, 49, 50, 51, 52, 55, 56], "It": [0, 1, 2, 4, 5, 6, 8, 10, 12, 13, 14, 16, 19, 20, 21, 22, 24, 30, 39, 40, 42, 43, 44, 50, 52, 54, 56], "can": [0, 1, 2, 3, 4, 5, 6, 7, 9, 12, 13, 14, 15, 16, 17, 19, 20, 21, 22, 23, 24, 25, 26, 30, 31, 34, 38, 39, 41, 42, 43, 44, 46, 47, 49, 50, 51, 52, 54, 56], "have": [0, 1, 2, 3, 4, 5, 7, 8, 11, 13, 15, 16, 18, 20, 22, 27, 29, 39, 40, 41, 42, 43, 44, 50, 51, 54, 56], "0f": [0, 5, 39], "mmintoken": 0, "effect": [0, 2, 5, 21, 25, 39, 42, 56], "mbeamsearchdiversityr": 0, "divers": [0, 5, 39, 41], "mrepetitionpenalti": 0, "penal": [0, 5, 39], "base": [0, 1, 2, 10, 13, 14, 15, 16, 17, 20, 21, 22, 25, 29, 35, 36, 39, 40, 41, 42, 44, 45, 46, 47, 48, 49, 51, 53, 55, 56], "how": [0, 2, 5, 10, 12, 13, 15, 22, 23, 31, 39, 41, 44, 50, 51, 52, 54, 56], "often": [0, 16, 20, 22, 39, 44, 56], "thei": [0, 1, 4, 5, 7, 8, 12, 13, 15, 22, 24, 25, 27, 39, 42, 44, 46, 50, 52, 54], "appear": [0, 2, 4, 5, 39, 44, 54, 56], "sequenc": [0, 1, 2, 4, 5, 6, 7, 12, 16, 17, 18, 19, 22, 29, 39, 40, 43, 44, 45, 49, 51, 55, 56], "ani": [0, 2, 6, 13, 15, 22, 25, 27, 31, 39, 40, 43, 44, 46, 49, 54, 56], "encourag": [0, 5, 7, 15, 39], "repetit": [0, 5, 39, 44, 56], "discourag": [0, 5, 7, 39], "mpresencepenalti": 0, "alreadi": [0, 4, 6, 14, 25, 29, 39, 42, 44, 51, 55], "present": [0, 1, 39, 43, 52, 55], "irrespect": [0, 5, 39], "mfrequencypenalti": 0, "depend": [0, 2, 4, 5, 6, 11, 18, 22, 25, 26, 27, 39, 44, 51, 54, 55, 56], "mlengthpenalti": 0, "longer": [0, 5, 29, 39, 43], "mearlystop": 0, "whether": [0, 1, 2, 4, 21, 39, 44, 45, 49], "process": [0, 1, 2, 4, 5, 11, 12, 15, 21, 22, 39, 40, 41, 42, 43, 44, 49, 55, 56], "finish": [0, 1, 5, 15, 30, 31, 39, 40, 49, 56], "onc": [0, 2, 4, 5, 6, 12, 14, 22, 24, 39, 41, 44, 51, 56], "sentenc": [0, 5, 39], "ar": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 18, 19, 20, 21, 22, 24, 25, 27, 29, 31, 33, 34, 35, 37, 39, 40, 41, 42, 43, 44, 45, 46, 47, 49, 50, 51, 52, 53, 54, 55, 56], "end": [0, 1, 2, 4, 5, 7, 12, 38, 39, 40, 41, 42, 44, 50, 55], "end_token": [0, 39], "mnorepeatngrams": 0, "mani": [0, 2, 4, 12, 15, 29, 38, 39, 42, 44, 53, 54, 56], "repeat": [0, 4, 39, 41, 44], "ngram": [0, 5, 39, 56], "size": [0, 1, 2, 4, 5, 7, 8, 9, 17, 18, 20, 21, 29, 30, 39, 43, 44, 45, 46, 49, 54, 55, 56], "accept": [0, 1, 2, 24, 30, 34, 35, 36, 37, 39, 44, 55, 56], "30": [0, 39, 43, 51, 56], "static": [0, 1, 22, 41, 43, 44, 45, 46, 49, 55, 56], "checkbeamwidth": 0, "checktopk": 0, "checktopp": 0, "checktoppmin": 0, "checktoppresetid": 0, "checktoppdecai": 0, "checktemperatur": 0, "checkrepetitionpenalti": 0, "penalti": [0, 55], "checkmintoken": 0, "checknorepeatngrams": 0, "checkbeamsearchdiversityr": 0, "friend": [0, 1], "outputconfig": [0, 22, 30, 55], "output": [0, 1, 2, 4, 5, 6, 7, 8, 12, 16, 17, 18, 19, 20, 21, 22, 29, 30, 31, 33, 34, 35, 36, 37, 38, 39, 41, 42, 43, 44, 45, 49, 50, 54, 55, 56], "result": [0, 1, 2, 3, 4, 12, 16, 17, 18, 20, 23, 24, 30, 39, 41, 42, 44, 45, 55, 56], "returnlogprob": 0, "fals": [0, 1, 2, 4, 5, 6, 7, 11, 21, 22, 29, 39, 44, 45, 46, 47, 49, 54, 55, 56], "returncontextlogit": 0, "returngenerationlogit": 0, "excludeinputfromoutput": 0, "returnencoderoutput": 0, "should": [0, 1, 2, 6, 7, 8, 15, 22, 24, 25, 29, 30, 33, 34, 35, 37, 39, 42, 43, 44, 45, 47, 49, 51, 54, 55, 56], "contain": [0, 1, 2, 4, 5, 6, 7, 8, 11, 12, 13, 14, 15, 21, 22, 26, 27, 39, 40, 44, 46, 49, 50, 52, 53, 55, 56], "log": [0, 1, 2, 4, 7, 21, 38, 39, 44, 50, 51, 55, 56], "context": [0, 1, 2, 3, 7, 20, 21, 23, 28, 29, 39, 41, 44, 49, 51, 54, 55], "input": [0, 1, 2, 5, 6, 7, 8, 12, 13, 16, 17, 18, 19, 20, 21, 22, 23, 29, 30, 31, 39, 43, 44, 45, 46, 49, 51, 54, 55, 56], "encod": [0, 1, 4, 5, 17, 21, 39, 44, 49, 52, 53, 55], "hidden": [0, 1, 3, 4, 5, 8, 27, 39, 44, 45, 51, 55, 56], "state": [0, 1, 2, 3, 4, 6, 22, 29, 31, 33, 34, 35, 36, 37, 38, 39, 43, 44, 50, 56], "onli": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 12, 13, 15, 20, 21, 22, 23, 24, 27, 29, 30, 38, 39, 42, 43, 44, 45, 47, 49, 51, 53, 55, 56], "decod": [0, 1, 4, 5, 7, 10, 15, 22, 39, 41, 44, 49, 53, 55], "model": [0, 1, 2, 3, 4, 7, 8, 9, 11, 15, 16, 17, 18, 19, 20, 21, 22, 23, 26, 27, 29, 30, 33, 34, 35, 36, 37, 38, 39, 40, 43, 44, 47, 48, 49, 51, 52], "externaldrafttokensconfig": [0, 1, 39], "specul": [0, 1, 22, 28, 39, 44, 55], "extern": [0, 6, 13, 49, 51], "draft": [0, 1, 7, 21, 55], "allow": [0, 1, 2, 4, 5, 11, 16, 19, 21, 22, 29, 40, 41, 42, 44, 47, 50, 51, 55, 56], "specifi": [0, 1, 2, 4, 5, 6, 7, 8, 13, 15, 21, 22, 24, 25, 27, 30, 31, 41, 42, 43, 44, 46, 47, 50, 51, 55, 56], "threshold": [0, 44], "vectoken": 0, "acceptancethreshold": 0, "gettoken": 0, "getlogit": 0, "getacceptancethreshold": 0, "mtoken": 0, "mlogit": 0, "expect": [0, 2, 4, 5, 7, 10, 12, 13, 15, 18, 30, 39, 43, 44, 53], "shape": [0, 1, 2, 4, 6, 7, 8, 11, 12, 39, 44, 46, 49, 51, 52, 54, 55], "num_draft_token": [0, 7, 44, 49], "vocab_s": [0, 7, 11, 13, 39, 45, 46, 49], "macceptancethreshold": 0, "must": [0, 1, 2, 3, 4, 5, 7, 8, 12, 14, 22, 25, 29, 37, 39, 42, 44, 45, 47, 49, 52, 54, 56], "prompttuningconfig": [0, 39], "prompt": [0, 5, 7, 10, 21, 22, 25, 29, 30, 31, 33, 34, 35, 36, 37, 38, 39, 45, 49, 50, 55, 56], "tune": [0, 7, 17, 20, 21, 22, 23, 39, 45, 46, 49, 50, 51, 55, 56], "embeddingt": [0, 1], "vectokenextraid": [0, 1], "inputtokenextraid": 0, "getembeddingt": 0, "getinputtokenextraid": 0, "membeddingt": 0, "embed": [0, 7, 10, 21, 29, 39, 44, 55], "tabl": [0, 5, 7, 17, 20, 21, 29, 39, 42, 43, 44, 45, 49, 53, 55], "task": [0, 1, 7, 8, 10, 11, 29, 35, 36, 45, 49, 52, 55, 56], "hidden_s": [0, 6, 11, 13, 44, 45, 46, 49, 54], "data": [0, 1, 4, 5, 7, 12, 13, 16, 17, 18, 19, 20, 21, 39, 42, 43, 44, 46, 53, 54, 55, 56], "match": [0, 1, 3, 6, 23, 44, 49, 50, 55, 56], "weight": [0, 1, 2, 3, 7, 8, 15, 16, 17, 20, 21, 23, 39, 40, 43, 44, 45, 46, 49, 50, 55], "minputtokenextraid": 0, "extra": [0, 4, 11, 26, 27, 29, 49, 54, 55, 56], "id": [0, 1, 2, 7, 22, 29, 30, 36, 39, 41, 43, 45, 49], "kv": [0, 2, 8, 12, 15, 16, 20, 21, 23, 28, 30, 40, 41, 43, 44, 49, 50, 55, 56], "cach": [0, 1, 2, 5, 7, 8, 12, 15, 20, 21, 23, 28, 30, 39, 40, 41, 43, 44, 49, 50, 52, 54, 55, 56], "reus": [0, 2, 28, 44, 49, 51, 55, 56], "enabl": [0, 1, 2, 4, 5, 6, 7, 8, 9, 12, 13, 17, 18, 19, 20, 21, 23, 24, 30, 33, 36, 39, 42, 43, 44, 45, 46, 47, 49, 50, 51, 52, 54, 55, 56], "loraconfig": [0, 8, 39, 46, 55], "lora": [0, 1, 2, 7, 22, 23, 28, 39, 44, 45, 46, 49, 55], "idtyp": [0, 22], "taskid": [0, 1], "config": [0, 1, 4, 7, 9, 10, 13, 15, 16, 29, 38, 39, 44, 45, 46, 47, 49, 51, 55, 56], "gettaskid": 0, "getweight": 0, "getconfig": 0, "mtaskid": 0, "mweight": 0, "document": [0, 4, 5, 7, 8, 10, 11, 12, 14, 15, 17, 18, 20, 24, 25, 28, 29, 30, 41, 42, 43, 44, 51, 52, 54, 55], "mconfig": [0, 1], "detail": [0, 2, 4, 10, 12, 21, 22, 23, 30, 31, 42, 43, 44, 46, 51, 54, 55, 56], "struct": [0, 1], "lookaheaddecodingconfig": [0, 1], "windows": 0, "ngramsiz": 0, "verificationsets": 0, "inlin": [0, 1], "tupl": [0, 1, 44, 45, 49, 56], "get": [0, 1, 4, 6, 8, 9, 13, 19, 24, 25, 26, 30, 31, 40, 41, 42, 44, 46, 49, 50, 55, 56], "getwindows": 0, "getngrams": 0, "getverificationsets": 0, "calculatespeculativeresourc": 0, "return": [0, 1, 2, 6, 7, 8, 10, 12, 13, 15, 22, 30, 39, 44, 45, 46, 49, 51, 54, 55, 56], "maxdecodingtoken": [0, 1], "maxpathlen": [0, 1], "maxdrafttoken": [0, 1], "maxdraftpathlen": [0, 1], "isl": [0, 16, 17, 18, 19, 43], "true": [0, 1, 2, 5, 6, 7, 11, 22, 25, 29, 30, 33, 36, 39, 44, 45, 46, 47, 49, 51, 54, 55, 56], "thi": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 18, 20, 21, 22, 24, 25, 26, 27, 28, 29, 30, 31, 39, 40, 41, 42, 43, 44, 46, 47, 49, 50, 51, 52, 54, 55, 56], "execut": [0, 1, 5, 8, 12, 14, 15, 22, 23, 25, 26, 27, 40, 42, 44, 49, 50, 51], "resourc": [0, 4, 15, 56], "defin": [0, 1, 2, 4, 6, 11, 12, 13, 14, 15, 18, 21, 22, 38, 40, 42, 44, 45, 52, 54, 55, 56], "isleg": 0, "combin": [0, 6, 18, 42, 43, 45, 55, 56], "valid": [0, 1, 7, 25, 43, 44, 49, 56], "mwindows": 0, "mngramsiz": 0, "mverificationsets": 0, "contextphaseparam": 0, "firstgentoken": 0, "getfirstgentoken": 0, "popfirstgentoken": 0, "getstat": 0, "releasest": 0, "stateptr": 0, "unique_ptr": [0, 1], "decltyp": [0, 1], "delet": [0, 1, 43, 47, 54], "mfirstgentoken": 0, "first": [0, 1, 2, 4, 5, 6, 7, 8, 14, 18, 20, 21, 22, 25, 27, 29, 41, 42, 44, 51, 55, 56], "mstate": [0, 1], "nullptr": [0, 1], "phase": [0, 1, 2, 6, 7, 16, 19, 21, 23, 41, 42, 43, 44, 51, 55, 56], "request": [0, 4, 5, 8, 12, 17, 19, 21, 23, 29, 39, 40, 41, 42, 43, 44, 50, 51, 55, 56], "A": [0, 1, 2, 4, 5, 7, 8, 11, 12, 15, 20, 22, 39, 43, 44, 49, 55, 56], "hold": [0, 1, 2, 3, 6, 8, 22, 29, 45, 51, 56], "inform": [0, 1, 2, 4, 5, 7, 8, 11, 12, 16, 19, 22, 23, 25, 40, 41, 43, 53, 55, 56], "about": [0, 1, 15, 16, 17, 19, 20, 22, 23, 38, 50, 51, 55, 56], "inputtokenid": 0, "maxtoken": [0, 2, 51, 55], "stream": [0, 1, 2, 5, 7, 12, 21, 22, 30, 31, 32, 39, 49, 51, 54, 55], "endid": [0, 1], "padid": [0, 1], "vector": [0, 1, 4, 5, 22, 44], "positionid": [0, 1], "list": [0, 1, 2, 4, 5, 6, 7, 11, 12, 13, 14, 22, 24, 25, 28, 30, 39, 40, 43, 44, 45, 46, 49, 53, 55, 56], "badword": 0, "stopword": 0, "embeddingbia": [0, 1], "ptuningconfig": 0, "lookaheadconfig": 0, "string": [0, 1, 2, 11, 22, 39, 44, 49], "logitspostprocessornam": 0, "encoderinputtokenid": 0, "clientid": 0, "returnallgeneratedtoken": [0, 22], "prioritytyp": 0, "prioriti": [0, 1, 13, 29], "kdefaultprior": 0, "requesttyp": [0, 1], "request_type_context_and_gener": 0, "encoderinputfeatur": 0, "encoderoutputlength": 0, "numreturnsequ": [0, 22], "maximum": [0, 1, 2, 4, 5, 18, 21, 22, 39, 43, 44, 49, 51, 54, 56], "respons": [0, 23, 30, 39, 44], "pad": [0, 1, 2, 5, 6, 7, 8, 21, 23, 39, 40, 44, 45, 51, 55], "posit": [0, 1, 7, 44, 49, 55, 56], "bad": [0, 7, 22, 39, 55], "word": [0, 1, 4, 7, 22, 44, 49, 55], "each": [0, 1, 2, 3, 4, 5, 6, 7, 8, 11, 12, 21, 22, 29, 30, 41, 42, 43, 44, 45, 47, 49, 51, 52, 56], "compos": [0, 1, 5], "multipl": [0, 1, 2, 3, 4, 5, 6, 7, 12, 13, 21, 22, 29, 40, 44, 45, 49, 50, 54, 55, 56], "stop": [0, 1, 2, 5, 6, 7, 22, 39, 41, 49, 55, 56], "bia": [0, 1, 2, 7, 11, 12, 22, 39, 44, 45, 46, 54, 55], "kfp32": [0, 39], "postprocessor": [0, 39], "name": [0, 1, 2, 5, 6, 7, 8, 11, 22, 31, 33, 34, 35, 36, 37, 38, 39, 41, 43, 44, 47, 49, 50, 55, 56], "correspond": [0, 1, 2, 3, 4, 6, 8, 13, 15, 26, 39, 41, 44, 45, 49, 52, 55, 56], "one": [0, 1, 2, 3, 4, 5, 6, 7, 11, 12, 13, 15, 16, 21, 22, 25, 27, 29, 31, 39, 42, 43, 44, 47, 49, 50, 51, 54, 55, 56], "provid": [0, 1, 2, 3, 4, 5, 6, 10, 11, 14, 15, 16, 17, 20, 21, 22, 24, 27, 29, 30, 38, 39, 40, 41, 42, 43, 44, 49, 51, 53, 54, 56], "executorconfig": [0, 9, 39], "full": [0, 2, 3, 4, 5, 7, 8, 17, 18, 29, 40, 41, 49, 50, 51, 54, 56], "just": [0, 1, 41, 51, 56], "newli": [0, 1, 2], "after": [0, 1, 2, 4, 6, 8, 12, 13, 21, 22, 24, 25, 29, 31, 41, 42, 43, 44, 45, 47, 51, 54, 55, 56], "everi": [0, 13, 22, 49], "step": [0, 1, 2, 4, 6, 11, 12, 14, 15, 16, 23, 25, 27, 29, 40, 42, 43, 44, 49, 54, 56], "set": [0, 1, 2, 3, 4, 5, 6, 7, 9, 11, 13, 14, 15, 21, 22, 24, 25, 26, 27, 30, 37, 40, 41, 42, 43, 44, 45, 46, 47, 49, 50, 51, 54, 55, 56], "featur": [0, 2, 4, 5, 6, 8, 11, 12, 13, 15, 20, 21, 23, 24, 42, 44, 47, 49, 53, 56], "multimod": [0, 21, 49, 55], "length": [0, 1, 2, 4, 7, 16, 17, 18, 19, 20, 21, 29, 42, 43, 44, 49, 51, 54, 55, 56], "differ": [0, 1, 2, 3, 4, 5, 10, 11, 12, 13, 15, 20, 21, 25, 29, 31, 40, 42, 44, 46, 49, 51, 52, 55, 56], "due": [0, 1, 15, 18, 37, 42, 49, 56], "convolut": [0, 49], "down": [0, 2, 8, 16, 22, 25, 40, 44, 49], "etc": [0, 1, 49, 51], "disaggreg": 0, "serv": [0, 2, 4, 12, 14, 19, 20, 42, 56], "mode": [0, 1, 2, 3, 4, 6, 12, 13, 21, 25, 39, 44, 45, 49, 51, 52, 55, 56], "getinputtokenid": 0, "getmaxtoken": 0, "getmaxnewtoken": 0, "getstream": [0, 1], "getsamplingconfig": [0, 1], "getoutputconfig": 0, "getendid": 0, "getpadid": 0, "getpositionid": 0, "getbadword": 0, "getstopword": 0, "getembeddingbia": 0, "getexternaldrafttokensconfig": 0, "getprompttuningconfig": 0, "getloraconfig": 0, "getlookaheadconfig": 0, "getlogitspostprocessornam": 0, "getencoderinputtokenid": 0, "getclientid": 0, "getprior": 0, "getreturnallgeneratedtoken": 0, "getcontextphaseparam": 0, "getencoderinputfeatur": 0, "getencoderoutputlength": 0, "getrequesttyp": 0, "getnumreturnsequ": 0, "setstream": 0, "setsamplingconfig": 0, "setoutputconfig": 0, "setendid": 0, "setpadid": 0, "setpositionid": 0, "setbadword": 0, "setstopword": 0, "setembeddingbia": 0, "setexternaldrafttokensconfig": 0, "setprompttuningconfig": 0, "setloraconfig": 0, "setlookaheadconfig": 0, "setlogitspostprocessornam": 0, "setencoderinputtokenid": 0, "setclientid": 0, "setprior": 0, "setreturnallgeneratedtoken": 0, "setrequesttyp": 0, "setcontextphaseparam": 0, "setencoderinputfeatur": 0, "setencoderoutputlength": 0, "setnumreturnsequ": 0, "attribut": [0, 1, 6, 13, 15, 22, 49], "constexpr": [0, 1], "5": [0, 1, 7, 8, 9, 11, 16, 17, 18, 20, 21, 25, 26, 27, 29, 31, 39, 43, 44, 46, 53, 54, 55, 56], "auto": [0, 1, 2, 4, 5, 9, 12, 31, 32, 39, 44, 46, 47, 55], "kbatchedpostprocessornam": [0, 22], "batch": [0, 1, 7, 8, 9, 12, 14, 17, 18, 20, 21, 22, 23, 28, 29, 39, 41, 43, 44, 49, 50, 51, 54, 55, 56], "dispatch": [0, 3, 15, 30], "impl": 0, "mimpl": 0, "isfin": [0, 22], "final": [0, 1, 2, 8, 21, 30, 44], "beamtoken": [0, 2, 22], "outputtokenid": [0, 22], "veclogprob": 0, "cumlogprob": [0, 1, 2], "cumul": [0, 1, 7, 44], "beamsiz": 0, "logprob": [0, 1, 2, 30], "outputlen": 0, "contextlogit": [0, 1], "promptlen": 0, "vocabsizepad": [0, 1, 2], "generationlogit": [0, 1], "maxnewtoken": [0, 1, 55, 56], "non": [0, 2, 4, 9, 12, 15, 20, 44, 55], "allgeneratedtoken": 0, "encoderoutput": 0, "encoderlen": 0, "hiddens": [0, 1, 5], "finishreason": [0, 1, 55], "reason": [0, 4, 5, 12, 15, 44], "why": [0, 12, 44, 51], "current": [0, 1, 2, 4, 5, 8, 20, 21, 25, 27, 30, 42, 43, 44, 49, 51, 55, 56], "support": [0, 1, 2, 3, 4, 8, 9, 11, 14, 15, 16, 17, 18, 19, 20, 22, 23, 25, 28, 29, 30, 42, 43, 44, 47, 50, 54, 55, 56], "batchingtyp": [0, 39], "kinflight": 0, "param": [0, 1, 7, 13, 34, 35, 36, 37, 38, 39, 44, 45, 46, 49], "decodingit": 0, "iter": [0, 1, 2, 4, 7, 13, 22, 23, 39, 40, 42, 49, 55, 56], "take": [0, 1, 2, 4, 5, 6, 11, 15, 25, 29, 40, 42, 44, 45], "sequenceindex": [0, 22], "index": [0, 1, 13, 22, 23, 26, 27, 30, 41, 44, 54, 56], "issequencefin": [0, 22], "given": [0, 1, 2, 5, 7, 8, 13, 15, 18, 22, 31, 39, 41, 44, 45, 46, 49, 51, 52, 55], "either": [0, 1, 2, 14, 22, 34, 39, 44, 51, 54, 55], "an": [0, 1, 2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 18, 20, 22, 24, 26, 27, 29, 30, 31, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 48, 49, 51, 52, 54, 55], "error": [0, 2, 7, 8, 15, 21, 22, 23, 24, 26, 27, 38, 51, 55, 56], "requestid": [0, 7, 22], "errormsg": 0, "getrequestid": 0, "wa": [0, 1, 4, 5, 11, 22, 42, 43, 45, 52, 54, 55], "haserror": [0, 22], "ha": [0, 1, 2, 4, 7, 8, 11, 12, 13, 15, 16, 20, 21, 22, 24, 29, 42, 43, 44, 49, 51, 52, 55, 56], "geterrormsg": 0, "msg": [0, 1], "Will": 0, "throw": [0, 1], "except": [0, 4, 5, 15, 21, 22, 27, 44, 55], "getresult": [0, 22], "hasresult": 0, "schedulerconfig": [0, 2, 39, 55], "schedul": [0, 2, 8, 21, 22, 29, 39, 41, 43, 51, 55], "capacityschedulerpolici": [0, 2, 39, 42, 55], "kguaranteed_no_evict": [0, 2], "contextchunkingpolici": [0, 39, 55], "getcapacityschedulerpolici": 0, "getcontextchunkingpolici": 0, "mcapacityschedulerpolici": 0, "capac": [0, 1, 16, 18, 20], "polici": [0, 1, 2, 43, 51], "mcontextchunkingpolici": 0, "chunk": [0, 2, 23, 28, 44, 49, 51, 55], "kvcacheconfig": [0, 1, 2, 4, 29, 30, 39, 51, 56], "enableblockreus": [0, 2, 29, 56], "maxattentionwindowvec": 0, "sinktokenlength": [0, 1], "freegpumemoryfract": [0, 2, 51, 55], "size_t": [0, 1], "hostcaches": [0, 2, 29], "onboardblock": 0, "getenableblockreus": 0, "getmaxattentionwindowvec": 0, "getsinktokenlength": 0, "getfreegpumemoryfract": 0, "gethostcaches": 0, "getonboardblock": 0, "setenableblockreus": 0, "setmaxtoken": 0, "setmaxattentionwindowvec": 0, "setsinktokenlength": 0, "setfreegpumemoryfract": 0, "sethostcaches": 0, "setonboardblock": 0, "menableblockreus": 0, "block": [0, 1, 2, 4, 5, 12, 29, 30, 37, 41, 42, 44, 49, 51, 55], "mmaxtoken": 0, "store": [0, 1, 2, 4, 7, 8, 12, 17, 29, 31, 39, 42, 43, 44, 46, 51, 52], "If": [0, 1, 2, 3, 4, 5, 6, 7, 8, 11, 12, 13, 15, 20, 21, 22, 24, 25, 26, 27, 29, 39, 40, 42, 43, 44, 46, 49, 51, 53, 54, 55, 56], "both": [0, 2, 3, 4, 6, 8, 12, 13, 17, 20, 21, 31, 42, 43, 44, 45, 51, 52, 55, 56], "mfreegpumemoryfract": 0, "memori": [0, 1, 2, 3, 4, 5, 8, 12, 13, 15, 16, 17, 19, 20, 23, 25, 30, 41, 43, 44, 49, 54], "minimum": [0, 2, 4, 44, 49, 51, 56], "alloc": [0, 1, 2, 4, 29, 30, 42, 44, 49, 51, 54], "mmaxattentionwindowvec": 0, "attent": [0, 1, 2, 5, 8, 10, 12, 13, 16, 23, 29, 44, 49, 50, 51, 54, 55, 56], "window": [0, 1, 2, 23, 44, 49, 53, 55, 56], "last": [0, 1, 2, 4, 8, 10, 22, 42, 44, 46, 56], "mmaxattentionwindow": [0, 1], "layer": [0, 1, 2, 3, 4, 5, 6, 8, 10, 11, 12, 13, 42, 44, 50, 51, 52, 54, 55, 56], "mai": [0, 1, 2, 4, 5, 11, 12, 13, 15, 21, 22, 24, 25, 26, 27, 29, 40, 41, 42, 43, 44, 47, 50, 51, 53, 54, 55, 56], "max": [0, 1, 2, 7, 8, 16, 17, 18, 41, 43, 44, 51, 56], "element": [0, 1, 4, 5, 8, 44, 52], "less": [0, 4, 5, 12, 17, 22, 43, 44], "than": [0, 1, 4, 5, 6, 12, 16, 17, 18, 20, 21, 22, 29, 40, 42, 44, 49, 51, 54, 55, 56], "time": [0, 1, 2, 4, 7, 8, 9, 12, 18, 20, 21, 22, 23, 24, 25, 27, 29, 33, 34, 35, 36, 37, 40, 42, 44, 49, 54, 55, 56], "msinktokenlength": [0, 1], "sink": [0, 1, 4, 49], "alwai": [0, 1, 4, 5, 11, 12, 15, 29, 44], "keep": [0, 1, 4, 5, 15, 41, 42, 44, 55], "fraction": [0, 2, 44, 49], "gpu": [0, 1, 3, 4, 5, 8, 11, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 26, 29, 30, 37, 38, 43, 44, 46, 49, 50, 53, 54, 55, 56], "90": [0, 24, 41, 42, 43, 51], "mhostcaches": 0, "secondari": [0, 51], "pool": [0, 1, 2, 4, 23, 44, 49], "byte": [0, 1, 2, 29, 49], "increas": [0, 1, 2, 4, 12, 17, 18, 29, 41, 42, 44, 50, 55, 56], "potenti": [0, 1, 2, 7, 41, 56], "monboardblock": 0, "offload": [0, 9, 21], "onboard": [0, 29, 51], "back": [0, 2, 29, 34, 55, 56], "primari": [0, 1, 20, 51], "befor": [0, 1, 2, 4, 6, 7, 11, 12, 13, 22, 24, 27, 29, 40, 44, 46, 49, 51, 54, 55], "being": [0, 2, 4, 5, 12, 15, 29, 39, 43, 55], "extendedruntimeperfknobconfig": 0, "runtim": [0, 2, 4, 7, 9, 14, 21, 23, 26, 27, 40, 41, 43, 44, 45, 46, 50, 54, 55, 56], "perf": [0, 44], "knob": [0, 42, 44], "multiblockmod": 0, "enablecontextfmhafp32acc": 0, "getmultiblockmod": 0, "getenablecontextfmhafp32acc": 0, "setmultiblockmod": 0, "setenablecontextfmhafp32acc": 0, "mmultiblockmod": 0, "multi": [0, 3, 5, 8, 11, 14, 15, 16, 21, 22, 23, 24, 25, 29, 37, 44, 46, 51, 52, 55, 56], "menablecontextfmhafp32acc": 0, "fmha": [0, 44, 49, 51, 55], "runner": [0, 11, 49], "fp32": [0, 4, 23, 44, 49, 50, 53, 55], "accumul": [0, 4, 5, 44, 49, 50], "debugconfig": 0, "debug": [0, 21, 23, 24, 49, 51, 55], "dumpinputtensor": 0, "dumpouputtensor": 0, "stringvec": 0, "debugtensornam": 0, "getdumpinputtensor": 0, "getdumpoutputtensor": 0, "getdebugtensornam": 0, "setdumpinputtensor": 0, "setdumpouputtensor": 0, "setdebugtensornam": 0, "mdumpinputtensor": 0, "dump": [0, 24, 26], "mdumpouputtensor": 0, "mdebugtensornam": 0, "empti": [0, 1, 2, 22, 30, 39, 44, 56], "orchestratorconfig": 0, "isorchestr": 0, "workerexecutablepath": 0, "shared_ptr": [0, 1, 2], "mpi": [0, 1, 2, 5, 14, 15, 21, 41, 44, 54, 55], "mpicomm": 0, "orchleadercomm": 0, "spawnprocess": 0, "getisorchestr": 0, "getworkerexecutablepath": 0, "getorchleadercomm": 0, "getspawnprocess": 0, "setisorchestr": 0, "setworkerexecutablepath": 0, "setorchleadercomm": 0, "setspawnprocess": 0, "misorchestr": 0, "mworkerexecutablepath": 0, "morchleadercomm": 0, "mspawnprocess": 0, "parallelconfig": 0, "parallel": [0, 2, 4, 5, 11, 12, 16, 18, 19, 22, 23, 31, 32, 39, 43, 44, 45, 46, 51, 55], "commtyp": 0, "communicationtyp": 0, "kmpi": 0, "communicationmod": 0, "commmod": 0, "kleader": 0, "deviceid": [0, 1], "participantid": 0, "commun": [0, 2, 5, 12, 25, 38, 40, 44, 55], "involv": [0, 1, 12, 20, 45, 56], "particip": [0, 38, 44], "rank": [0, 1, 2, 3, 5, 8, 15, 21, 22, 23, 44, 46, 49, 51], "consid": [0, 1, 2, 7, 8, 20, 38, 42, 43, 44, 56], "leader": 0, "getcommunicationtyp": 0, "getcommunicationmod": 0, "getdeviceid": 0, "getparticipantid": 0, "getorchestratorconfig": 0, "setcommunicationtyp": 0, "setcommunicationmod": 0, "setdeviceid": 0, "setparticipantid": 0, "setorchestratorconfig": 0, "mcommtyp": 0, "protocol": 0, "mcommmod": 0, "mdeviceid": [0, 1], "devic": [0, 1, 2, 25, 41, 44, 46, 48, 49, 54], "mparticipantid": 0, "exampl": [0, 1, 2, 4, 5, 6, 7, 9, 10, 12, 14, 15, 16, 18, 20, 23, 24, 25, 26, 29, 30, 33, 34, 35, 36, 37, 38, 42, 43, 44, 49, 50, 51, 52, 53, 54, 55, 56], "morchestratorconfig": 0, "orchestr": [0, 56], "peftcacheconfig": [0, 39], "peftcachemanag": 0, "numhostmodulelay": [0, 2], "numdevicemodulelay": [0, 2], "optimaladapters": [0, 1, 2], "8": [0, 1, 2, 4, 8, 11, 15, 16, 18, 19, 20, 21, 23, 25, 26, 29, 30, 31, 33, 34, 35, 36, 37, 38, 39, 41, 43, 44, 45, 46, 50, 51, 52, 54, 56], "maxadapters": [0, 2], "64": [0, 1, 2, 4, 5, 11, 17, 18, 21, 25, 43, 44, 45, 46, 49, 51, 55], "numputwork": [0, 2], "numensurework": [0, 2], "numcopystream": [0, 1, 2], "maxpagesperblockhost": [0, 2], "24": [0, 2, 43, 53, 54, 55, 56], "maxpagesperblockdevic": [0, 2], "float": [0, 1, 5, 7, 9, 11, 12, 17, 39, 42, 44, 46, 49, 52], "devicecacheperc": [0, 2], "getnumhostmodulelay": 0, "getnumdevicemodulelay": 0, "getoptimaladapters": 0, "getmaxadapters": 0, "getnumputwork": 0, "getnumensurework": 0, "getnumcopystream": [0, 1], "getmaxpagesperblockhost": 0, "getmaxpagesperblockdevic": 0, "getdevicecacheperc": 0, "mnumhostmodulelay": 0, "mnumdevicemodulelay": 0, "moptimaladapters": 0, "mmaxadapters": 0, "mnumputwork": 0, "mnumensurework": 0, "mnumcopystream": [0, 1], "mmaxpagesperblockhost": 0, "mmaxpagesperblockdevic": 0, "mdevicecacheperc": 0, "decodingconfig": [0, 1, 39], "decodingmod": [0, 1, 55], "medusachoic": [0, 1], "setdecodingmod": 0, "some": [0, 1, 2, 3, 4, 5, 6, 9, 11, 12, 15, 21, 25, 29, 40, 42, 43, 44, 47, 50, 51, 55, 56], "requir": [0, 1, 2, 4, 5, 7, 8, 12, 13, 15, 16, 20, 24, 25, 26, 27, 29, 37, 42, 43, 44, 45, 50, 51, 53, 54, 55, 56], "own": [0, 1, 2, 11, 12, 13, 14, 15, 24, 29, 30, 56], "setter": [0, 5], "getdecodingmod": [0, 1], "setlookaheaddecod": 0, "lookahead": [0, 1, 55], "getlookaheaddecodingconfig": 0, "setmedusachoic": 0, "medusa": [0, 1, 21, 44, 46, 49, 55], "getmedusachoic": [0, 1], "mdecodingmod": [0, 1], "mlookaheaddecodingconfig": 0, "mmedusachoic": 0, "logitspostprocessorconfig": [0, 22, 55], "logitspostprocessormap": 0, "processormap": 0, "logitspostprocessorbatch": 0, "processorbatch": 0, "replic": [0, 22, 44], "getprocessormap": 0, "getprocessorbatch": 0, "getrepl": 0, "setprocessormap": 0, "setprocessorbatch": 0, "setrepl": [0, 22], "mprocessormap": 0, "map": [0, 1, 2, 4, 6, 7, 10, 11, 12, 13, 15, 22, 39, 44, 45, 46, 49, 50], "post": [0, 11, 17, 20, 38, 39, 40, 41, 44, 55], "processor": [0, 4, 49, 55], "mprocessorbatch": 0, "singl": [0, 1, 2, 3, 4, 5, 7, 10, 12, 15, 18, 19, 22, 23, 25, 39, 42, 43, 44, 46, 51, 52, 55, 56], "mreplic": 0, "run": [0, 1, 2, 4, 5, 7, 10, 11, 12, 16, 20, 21, 22, 23, 24, 26, 27, 29, 35, 36, 39, 40, 41, 42, 44, 46, 49, 51, 52, 54, 55, 56], "tp": [0, 3, 5, 8, 16, 17, 18, 19, 20, 43, 44, 55, 56], "pp": [0, 1, 5, 8, 16, 19, 43, 44, 55], "maxbeamwidth": [0, 1, 2, 22, 55], "enablechunkedcontext": [0, 2], "normalizelogprob": [0, 1], "iterstatsmaxiter": 0, "requeststatsmaxiter": 0, "maxbatchs": [0, 1, 5], "maxnumtoken": [0, 1], "gpuweightsperc": [0, 1, 9], "maxqueues": 0, "recvpollperiodm": 0, "uint64_t": [0, 1, 2, 7], "maxseqidlemicrosecond": 0, "180000000": 0, "getmaxbeamwidth": [0, 1], "getschedulerconfig": 0, "getkvcacheconfig": 0, "getenablechunkedcontext": 0, "getnormalizelogprob": [0, 1], "getiterstatsmaxiter": 0, "getrequeststatsmaxiter": 0, "getbatchingtyp": 0, "getmaxbatchs": [0, 1], "getmaxnumtoken": [0, 1], "getparallelconfig": 0, "getpeftcacheconfig": 0, "getlogitspostprocessorconfig": 0, "getdecodingconfig": 0, "getgpuweightsperc": [0, 9], "getmaxqueues": 0, "getextendedruntimeperfknobconfig": 0, "getdebugconfig": 0, "getrecvpollperiodm": 0, "getmaxseqidlemicrosecond": 0, "setmaxbeamwidth": [0, 1], "setmaxbatchs": [0, 1], "setmaxnumtoken": [0, 1], "setschedulerconfig": 0, "setkvcacheconfig": 0, "setenablechunkedcontext": 0, "setnormalizelogprob": 0, "setiterstatsmaxiter": 0, "setrequeststatsmaxiter": 0, "setbatchingtyp": 0, "setparallelconfig": 0, "setpeftcacheconfig": 0, "setlogitspostprocessorconfig": 0, "setdecodingconfig": 0, "setgpuweightsperc": [0, 9], "setmaxqueues": 0, "setextendedruntimeperfknobconfig": 0, "setdebugconfig": 0, "setrecvpollperiodm": 0, "setmaxseqidlemicrosecond": 0, "mmaxbeamwidth": [0, 1], "sent": [0, 2, 56], "mschedulerconfig": 0, "mkvcacheconfig": 0, "menablechunkedcontext": 0, "mnormalizelogprob": [0, 1], "normal": [0, 5, 9, 20, 29, 39, 44, 51, 55, 56], "miterstatsmaxiter": 0, "statist": [0, 22, 39, 43, 56], "mrequeststatsmaxiter": 0, "per": [0, 1, 2, 4, 5, 15, 16, 18, 19, 22, 41, 44, 51, 52, 55, 56], "mbatchingtyp": 0, "strategi": [0, 20, 30, 44, 46, 51, 55, 56], "mmaxbatchs": [0, 1], "mmaxnumtoken": [0, 1], "mparallelconfig": 0, "mpeftcacheconfig": 0, "mlogitspostprocessorconfig": 0, "mdecodingconfig": 0, "mgpuweightsperc": 0, "percent": [0, 2, 9], "mmaxqueues": 0, "queue": [0, 2, 22, 40], "reject": [0, 2], "mextendedruntimeperfknobconfig": 0, "mdebugconfig": 0, "mrecvpollperiodm": 0, "m": [0, 2, 17, 25, 44, 51, 52, 54], "between": [0, 1, 2, 4, 5, 12, 13, 15, 25, 29, 41, 42, 43, 44, 51, 55, 56], "poll": 0, "busi": [0, 56], "loop": [0, 1, 2, 5, 12, 13, 22, 42], "mmaxseqidlemicrosecond": 0, "microsecond": 0, "remain": [0, 6, 9, 29, 43, 44, 51, 56], "idl": 0, "termin": [0, 2, 22, 25, 29, 43, 55], "3": [0, 1, 4, 6, 7, 8, 9, 13, 16, 17, 18, 20, 21, 22, 23, 25, 26, 27, 29, 31, 36, 43, 44, 49, 50, 53, 54, 55, 56], "minut": [0, 20], "receiv": [0, 1, 2, 3, 22, 44, 55, 56], "send": [0, 1, 12, 44, 50, 55, 56], "infer": [0, 1, 5, 8, 12, 14, 15, 16, 17, 18, 21, 23, 25, 26, 42, 43, 44, 49, 52, 54, 55], "filesystem": [0, 1], "path": [0, 1, 2, 4, 11, 13, 21, 22, 24, 25, 27, 30, 31, 34, 35, 36, 37, 39, 43, 44, 49, 55, 56], "modelpath": 0, "modeltyp": [0, 2, 9], "folder": [0, 5, 15, 22, 25, 27, 52, 53, 55], "comm": 0, "inter": [0, 54, 55], "encodermodelpath": 0, "decodermodelpath": 0, "bufferview": 0, "enginebuff": [0, 1], "jsonconfigstr": 0, "managedweight": 0, "encoderenginebuff": 0, "encoderjsonconfigstr": 0, "decoderenginebuff": 0, "decoderjsonconfigstr": 0, "encodermodel": [0, 46], "decodermodel": [0, 46], "enqueuerequest": [0, 22], "enqueu": [0, 2, 12, 22, 49, 51, 55], "uniqu": [0, 2, 4, 5, 7, 8, 11, 21, 39, 56], "identifi": [0, 2, 5, 8, 12, 44, 56], "awaitrespons": [0, 22], "chrono": 0, "millisecond": 0, "timeout": [0, 30], "await": [0, 22, 30, 35, 36], "readi": [0, 25, 26, 50], "overload": [0, 1, 39], "In": [0, 1, 6, 7, 12, 13, 15, 17, 20, 22, 23, 24, 25, 26, 30, 41, 43, 44, 50, 51, 52, 54, 55, 56], "particular": [0, 22, 24, 31, 50], "sever": [0, 1, 2, 4, 6, 11, 30, 44, 51, 54, 56], "been": [0, 2, 3, 4, 7, 15, 17, 18, 22, 29, 42, 54, 55], "method": [0, 1, 4, 5, 9, 11, 12, 15, 16, 22, 25, 30, 49, 52, 56], "without": [0, 1, 2, 4, 12, 13, 20, 22, 24, 30, 40, 42, 43, 44, 46, 51, 55], "order": [0, 4, 13, 16, 25, 42, 43, 44, 51], "guarante": [0, 2, 5, 15, 29, 42, 43], "wait": [0, 1, 2, 15, 30, 40], "behav": [0, 51], "were": [0, 1, 11, 15, 16, 20, 43, 56], "invok": [0, 1, 2, 6, 22], "same": [0, 1, 2, 4, 5, 6, 7, 8, 9, 12, 15, 17, 22, 29, 41, 42, 43, 44, 45, 47, 49, 51, 55, 56], "behaviour": [0, 44], "appli": [0, 4, 6, 8, 11, 12, 13, 21, 22, 40, 44, 49, 52, 53, 55, 56], "hang": [0, 55], "unless": [0, 25, 30, 39, 42], "getnumresponsesreadi": 0, "cancelrequest": [0, 22], "cancel": [0, 22, 55], "shutdown": 0, "signal": [0, 2], "server": [0, 12, 14, 17, 23, 26, 29, 43, 55], "call": [0, 1, 2, 3, 4, 5, 6, 12, 13, 15, 22, 30, 41, 42, 44, 46, 48, 49, 50, 51, 55], "reach": [0, 1, 4, 11, 42], "dequ": [0, 1], "iterationstat": 0, "getlatestiterationstat": [0, 22], "comput": [0, 1, 2, 3, 4, 5, 12, 16, 17, 18, 20, 21, 29, 33, 34, 35, 37, 41, 42, 44, 51, 55, 56], "sinc": [0, 3, 4, 6, 9, 15, 24, 29, 30, 44, 46, 51, 56], "most": [0, 1, 5, 12, 15, 16, 17, 18, 20, 27, 33, 34, 35, 37, 41, 42, 44, 51, 55], "stat": [0, 2, 55], "requeststatsperiter": 0, "getlatestrequeststat": 0, "group": [0, 3, 5, 12, 16, 23, 44, 45, 52, 55], "canenqueuerequest": 0, "jsonseri": 0, "util": [0, 1, 2, 4, 5, 12, 16, 31, 40, 41, 42, 43, 51, 55, 56], "json": [0, 1, 2, 11, 22, 55, 56], "tojsonstr": 0, "convert": [0, 1, 2, 8, 9, 10, 11, 12, 13, 15, 40, 50, 54, 55], "requeststatsperit": 0, "requeststat": 0, "deserializesamplingconfig": 0, "istream": [0, 1], "ostream": [0, 1], "o": [0, 1, 6, 8, 15, 19], "serializeds": 0, "deserializeoutputconfig": 0, "deserializeexternaldrafttokensconfig": 0, "deserializeprompttuningconfig": 0, "deserializeloraconfig": 0, "kv_cach": 0, "commstat": 0, "deserializecommst": 0, "socketst": 0, "deserializesocketst": 0, "cachest": 0, "deserializecachest": 0, "contextphasest": 0, "deserializecontextphasest": 0, "deserializecontextphaseparam": 0, "deserializerequest": 0, "deserializetensor": 0, "deserializeresult": 0, "deserializerespons": 0, "buffer": [0, 1, 2, 22, 23, 29, 44, 55], "deserializekvcacheconfig": 0, "deserializeschedulerconfig": 0, "deserializeextendedruntimeperfknobconfig": 0, "deserializeparallelconfig": 0, "deserializepeftcacheconfig": 0, "deserializeorchestratorconfig": 0, "deserializedecodingmod": 0, "deserializelookaheaddecodingconfig": 0, "deserializedecodingconfig": 0, "deserializedebugconfig": 0, "deserializeexecutorconfig": 0, "kvcachestat": 0, "deserializekvcachestat": 0, "staticbatchingstat": 0, "deserializestaticbatchingstat": 0, "inflightbatchingstat": 0, "deserializeinflightbatchingstat": 0, "deserializeiterationstat": 0, "iterstat": 0, "deserializestr": 0, "deserializebool": 0, "deserializemodeltyp": 0, "common": [0, 4, 29, 31, 44, 51, 56], "arrayview": [0, 1], "dimtype64": [0, 1], "typenam": [0, 1, 12], "remove_cv_t": 0, "value_typ": 0, "size_typ": [0, 1], "initializer_list": [0, 1], "dim": [0, 1, 44, 46], "cudastreamptr": [0, 1], "cudastream": 0, "copytocpu": 0, "copytopin": 0, "copytopooledpin": 0, "copytomanag": 0, "copytogpu": 0, "getdata": 0, "pointer": [0, 1, 2, 5, 13, 44, 49, 55], "underli": [0, 1, 2, 6, 37, 56], "arrai": [0, 1, 44, 49], "datatyp": [0, 1, 5, 12, 44, 49], "getdatatyp": [0, 1], "memorytyp": [0, 1], "getmemorytyp": [0, 1], "getshap": [0, 1], "dimens": [0, 1, 4, 5, 8, 42, 44, 45, 46, 51], "getsiz": [0, 1], "getsizeinbyt": [0, 1], "setzero": [0, 1], "entir": [0, 2, 8, 12, 16, 22, 40, 43, 44, 51], "zero": [0, 1, 2, 13, 44, 45, 52], "cuda": [0, 1, 2, 4, 5, 12, 24, 25, 26, 27, 38, 41, 46, 49, 51, 54, 55], "setfrom": 0, "copi": [0, 1, 2, 25, 27, 29, 42, 44, 51, 56], "anoth": [0, 1, 4, 6, 8, 15, 17, 44, 54], "rh": [0, 1], "cpu": [0, 1, 2, 8, 9, 12, 21, 29, 41, 42, 44, 51, 54], "templat": [0, 1, 12, 13], "t": [0, 1, 2, 4, 12, 15, 25, 30, 41, 44, 46, 51, 56], "pin": [0, 1, 29, 41], "pooledpin": 0, "manag": [0, 1, 4, 5, 8, 12, 14, 23, 30, 40, 42, 47, 49, 51, 55, 56], "uvm": [0, 1], "wrap": [0, 1, 2, 12, 44, 47, 49, 55], "ownership": 0, "itensor": [0, 44], "copyto": 0, "mtensor": 0, "getruntimetyp": 0, "toitensor": 0, "ofitensor": 0, "typedef": [0, 1], "int64_t": [0, 1], "typetrait": 0, "int8_t": [0, 1], "kint8": [0, 1], "int32_t": [0, 1, 2, 7, 44], "kint32": [0, 1], "kint64": [0, 1], "uint8_t": [0, 1], "kuint8": [0, 1], "tensorptr": [0, 1, 2], "iterationtyp": 0, "streamptr": [0, 1, 22], "logitspostprocessor": [0, 2], "unordered_map": [0, 1, 22], "reference_wrapp": [0, 1, 22], "basic_string_view": 0, "enum": [0, 1], "enumer": [0, 1, 36, 39, 44, 46, 48], "kbool": [0, 1], "kbf16": 0, "kfp8": 0, "kfp16": 0, "kunknown": 0, "request_type_context_onli": 0, "request_type_generation_onli": 0, "kcpu": [0, 1], "kcpu_pin": 0, "kcpu_pinnedpool": 0, "kgpu": [0, 1], "kuvm": [0, 1], "kdecoder_onli": [0, 9], "kencoder_onli": 0, "kencoder_decod": 0, "kstatic": 0, "refer": [0, 1, 2, 4, 5, 6, 7, 8, 12, 14, 15, 22, 24, 25, 30, 31, 37, 40, 42, 43, 44, 50, 53, 55, 56], "tradit": [0, 2], "scheme": [0, 2], "lockstep": [0, 2], "until": [0, 1, 2, 5, 22, 29, 42, 56], "them": [0, 1, 2, 3, 6, 9, 40, 41, 42, 44, 49, 51, 56], "complet": [0, 1, 2, 5, 7, 22, 25, 29, 30, 39, 40, 43, 50, 56], "up": [0, 2, 4, 8, 17, 18, 25, 27, 55, 56], "inflight": [0, 4, 7, 8, 28, 44, 55, 56], "arriv": [0, 2, 3], "dynam": [0, 2, 44, 46, 49, 51], "incorpor": [0, 2, 40], "under": [0, 2, 20, 21, 24, 27, 43, 54, 55], "soon": [0, 2, 16, 17, 18, 19, 20, 30], "condit": [0, 2, 5, 6, 22, 42, 44, 55, 56], "met": [0, 2, 22, 56], "select": [0, 2, 3, 5, 14, 20, 25, 27, 42, 44, 51, 56], "subset": [0, 2, 5, 12, 15, 22, 44], "avail": [0, 1, 2, 6, 12, 16, 18, 22, 24, 29, 30, 33, 34, 35, 37, 40, 42, 49, 50, 51, 52], "kmax_util": [0, 2], "max_util": [0, 2, 39, 42], "pack": [0, 1, 2, 5, 23, 42, 44, 46, 51], "engin": [0, 1, 2, 4, 5, 6, 8, 9, 14, 15, 19, 21, 22, 23, 25, 30, 34, 39, 42, 44, 46, 49, 51, 54, 55], "inflightbatch": [0, 2], "while": [0, 1, 2, 3, 6, 7, 15, 16, 17, 19, 20, 25, 29, 40, 44, 51, 52, 56], "maxim": [0, 2, 16, 18, 42], "throughput": [0, 2, 4, 16, 17, 18, 23, 42, 55], "might": [0, 2, 12, 15, 20, 21, 22, 24, 27, 49, 51, 54, 55], "paus": [0, 2, 42], "restart": [0, 2, 27], "peak": [0, 2, 16, 17, 43], "guaranteed_no_evict": [0, 2, 39, 42, 56], "more": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 16, 17, 18, 20, 22, 24, 25, 30, 31, 38, 40, 42, 43, 44, 50, 51, 55, 56], "conserv": [0, 2, 42], "start": [0, 1, 2, 4, 6, 21, 26, 27, 29, 31, 40, 41, 42, 44, 46, 51, 56], "evict": [0, 1, 2, 7, 8, 29, 40, 43], "kfirst_come_first_serv": 0, "sequenti": [0, 51], "unfinish": 0, "kequal_progress": 0, "through": [0, 1, 2, 4, 5, 6, 12, 13, 14, 21, 24, 40, 45, 50, 56], "attempt": 0, "its": [0, 1, 2, 4, 5, 6, 9, 11, 12, 13, 15, 16, 18, 27, 40, 42, 44, 51], "count": [0, 1, 2, 5, 41, 46, 50], "constraint": [0, 4, 5, 20, 44], "exceed": [0, 51], "korchestr": 0, "requeststag": 0, "repres": [0, 1, 16, 20, 44, 49, 56], "kqueu": 0, "yet": [0, 5, 15, 17, 44], "activ": [0, 1, 2, 4, 5, 6, 12, 16, 17, 20, 39, 41, 44, 52, 53, 55], "kencoder_in_progress": 0, "kcontext_in_progress": 0, "kgeneration_in_progress": 0, "kgeneration_complet": 0, "knot_finish": 0, "kend_id": 0, "becaus": [0, 20, 22, 29, 30, 42, 43, 44, 51], "kstop_word": 0, "klength": 0, "For": [0, 1, 2, 4, 5, 6, 8, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 24, 25, 29, 30, 31, 42, 43, 44, 49, 50, 51, 54, 55, 56], "c": [0, 1, 2, 4, 6, 7, 12, 14, 23, 26, 27, 30, 40, 41, 42, 44, 46, 50, 55, 56], "trtlmmdatatyp": 0, "half": [0, 1, 12, 44], "maxnumblock": 0, "freenumblock": 0, "free": [0, 1, 2, 8, 12, 13, 40, 41, 46, 49, 51], "usednumblock": 0, "tokensperblock": [0, 1, 5], "alloctotalblock": 0, "total": [0, 1, 2, 3, 4, 5, 7, 11, 13, 21, 41, 42, 43, 51, 56], "allocnewblock": 0, "reusedblock": 0, "numscheduledrequest": 0, "numcontextrequest": [0, 1], "stage": [0, 4, 6, 43, 51, 55], "numctxtoken": 0, "numgentoken": 0, "emptygenslot": 0, "unus": 0, "slot": [0, 1, 2], "numgenrequest": 0, "numpausedrequest": 0, "microbatchid": [0, 1], "mirco": 0, "avgnumdecodedtokensperit": 0, "averag": [0, 43, 56], "timestamp": [0, 2, 41], "doubl": [0, 17], "iterlatencym": 0, "latenc": [0, 2, 4, 17, 18, 20, 29, 42, 43, 44, 55, 56], "newactiverequestsqueuelatencym": 0, "spent": 0, "becam": 0, "numactiverequest": 0, "numqueuedrequest": [0, 55], "queu": [0, 43], "numcompletedrequest": 0, "maxnumactiverequest": 0, "gpumemusag": 0, "usag": [0, 4, 6, 12, 15, 16, 19, 21, 23, 25, 31, 42, 44, 55, 56], "cpumemusag": 0, "pinnedmemusag": 0, "specif": [0, 1, 2, 3, 5, 6, 7, 8, 11, 15, 17, 20, 24, 41, 43, 44, 50, 55, 56], "crosskvcachestat": 0, "cross": [0, 8, 44, 55], "contextprefillposit": 0, "prefil": 0, "numgeneratedtoken": 0, "so": [0, 1, 2, 4, 6, 7, 8, 14, 15, 22, 24, 25, 27, 30, 39, 42, 44, 45, 46, 51, 53, 54, 55, 56], "far": [0, 2, 22], "lack": 0, "exhaust": [0, 14], "underlyingtyp": [0, 1], "uint32_t": [0, 1, 44], "usetemperatur": 0, "usetemp": 0, "useoccurrencepenalti": 0, "usepenalti": 0, "usepresencepenalti": 0, "userepetitionpenalti": 0, "usefrequencypenalti": 0, "useminlength": 0, "useminlen": 0, "usebantoken": 0, "bantoken": 0, "usebanword": 0, "banword": 0, "usenorepeatngrams": 0, "usestopword": 0, "usemaxlengthstop": 0, "maxlengthstop": 0, "useexpliciteosstop": 0, "expliciteosstop": 0, "isauto": 0, "istopk": 0, "istopp": 0, "istopkortopp": 0, "istopkandtopp": 0, "isbeamsearch": 0, "ismedusa": [0, 1], "islookahead": 0, "isexplicitdrafttoken": [0, 1], "isusetemperatur": 0, "isusepresencepenalti": 0, "isusefrequencypenalti": 0, "isuserepetitionpenalti": 0, "isuseminlength": 0, "isuseoccurrencepenalti": 0, "isusepenalti": 0, "isusebanword": 0, "isusenorepeatngrams": 0, "isusebantoken": 0, "isusestopword": 0, "isusemaxlengthstop": 0, "isuseexpliciteosstop": 0, "isusestopcriteria": 0, "No": [0, 29, 43, 51], "determin": [0, 1, 4, 15, 42, 44, 46, 52], "topktopp": [0, 5], "beamsearch": 0, "otherwis": [0, 1, 2, 4, 5, 30, 44, 49, 54], "explicitdrafttoken": [0, 1], "anybitset": [0, 1], "bit": [0, 1, 2, 4, 17, 25, 44, 52], "allbitset": [0, 1], "setbitto": 0, "x": [0, 1, 5, 7, 8, 9, 22, 44, 45, 46, 52], "kuserepetitionpenalti": 0, "1u": [0, 1], "kusefrequencypenalti": 0, "kusepresencepenalti": 0, "2": [0, 1, 2, 4, 5, 6, 7, 8, 9, 11, 15, 16, 17, 18, 20, 21, 22, 23, 25, 29, 31, 33, 36, 37, 38, 39, 41, 42, 43, 44, 46, 49, 52, 54, 55, 56], "kusetemperatur": 0, "kuseminlength": 0, "4": [0, 1, 6, 8, 15, 18, 20, 21, 23, 25, 29, 30, 42, 43, 44, 46, 50, 51, 52, 53, 54, 55, 56], "kusebanword": 0, "kusestopword": 0, "kusemaxlengthstop": 0, "7": [0, 1, 7, 8, 16, 17, 20, 23, 25, 29, 43, 44, 54, 56], "kuseexpliciteosstop": 0, "kusenorepeatngrams": 0, "9": [0, 1, 2, 7, 8, 15, 17, 23, 38, 43, 44, 54, 56], "kstandardstopcriteria": 0, "kuseoccurrencepenalti": 0, "kusepenalti": 0, "kusebantoken": 0, "knumflag": 0, "10": [0, 8, 20, 23, 25, 26, 27, 29, 30, 39, 41, 43, 44, 51, 53, 54, 56], "kauto": 0, "ktopk": 0, "ktopp": 0, "kbeamsearch": 0, "kmedusa": [0, 1], "klookahead": 0, "kexplicitdrafttoken": [0, 1], "ktopktopp": 0, "helper": [1, 44], "host": [1, 2, 8, 24, 25, 26, 44], "type": [1, 2, 4, 5, 6, 7, 8, 11, 12, 17, 20, 21, 22, 39, 43, 44, 46, 49, 52, 53, 54, 55, 56], "ibufferptr": 1, "uniqueptr": 1, "itensorptr": 1, "cudamempoolptr": 1, "cudamempool": 1, "trimpool": 1, "construct": [1, 12, 22, 44, 56], "de": 1, "destructor": [1, 2], "nvinfer1": 1, "kbyte_typ": 1, "cudamallocasync": 1, "emptybuff": 1, "creat": [1, 2, 6, 7, 9, 10, 12, 14, 15, 22, 25, 26, 29, 30, 31, 33, 34, 35, 36, 37, 38, 40, 41, 43, 44, 46, 49, 50, 51, 55, 56], "resiz": 1, "later": [1, 2, 8, 12, 15, 18, 25, 31, 34, 51, 54, 56], "emptytensor": 1, "reshap": [1, 44], "setmem": 1, "content": [1, 7, 8, 15, 44, 51, 55], "src": [1, 12, 44], "dst": 1, "srctype": 1, "dsttype": 1, "copyfrom": 1, "memorypoolreserv": [1, 51], "reserv": [1, 2, 42, 51, 56], "memorypoolus": 1, "memorypoolfre": [1, 51], "memorypooltrimto": 1, "try": [1, 2, 10, 15, 22, 42, 43, 50, 51, 54], "trim": 1, "synchron": [1, 2, 12, 22, 39, 54, 55], "implicitli": 1, "gpusync": 1, "cudamalloc": 1, "pinnedpool": 1, "mstream": 1, "mpool": 1, "mtrimpool": 1, "buffermanagertest": 1, "fmt_dim": 1, "lorataskidtyp": 1, "tokenextraidtyp": 1, "vecuniquetoken": 1, "uniquetoken": 1, "stringptrmap": 1, "tokenid": 1, "tokenextraid": 1, "cudaevent_t": 1, "unsign": [1, 2], "int": [1, 5, 7, 10, 11, 12, 15, 36, 39, 44, 45, 46, 49], "flag": [1, 4, 15, 19, 22, 23, 25, 30, 42, 44, 51, 55, 56], "cudaeventdisabletim": 1, "event": 1, "destroi": [1, 51], "creation": [1, 44, 51], "By": [1, 5, 25, 30, 44, 56], "ownsev": 1, "pass": [1, 2, 4, 6, 8, 12, 13, 30, 41, 44, 45, 46, 49, 51, 55, 56], "exist": [1, 5, 8, 13, 15, 21, 25, 27, 29, 49, 55, 56], "object": [1, 5, 7, 10, 12, 13, 15, 22, 29, 30, 39, 44, 45, 46, 47, 49, 50, 51], "associ": [1, 2, 3, 7, 8, 22, 24, 44], "element_typ": 1, "remove_pointer_t": 1, "eventptr": 1, "mevent": 1, "mownsev": 1, "cudastreamnonblock": 1, "cudastreamcreatewithflag": 1, "higher": [1, 2, 4, 5, 8, 13, 16, 17, 19, 29, 40, 42, 51, 55, 56], "cudadevicegetstreampriorityrang": 1, "meaning": [1, 56], "cudastream_t": 1, "ownsstream": 1, "getdevic": 1, "record": [1, 6, 39], "mdevic": 1, "mownsstream": 1, "assum": [1, 2, 8, 9, 29, 44, 46, 56], "immut": 1, "whatev": 1, "initi": [1, 13, 39, 43, 51, 54, 55, 56], "tensorconstptr": 1, "sharedconstptr": 1, "sharedptr": 1, "maxlength": 1, "maxattentionwindow": [1, 2], "batchsiz": [1, 5, 17], "batchslot": 1, "we": [1, 2, 3, 5, 6, 8, 9, 11, 15, 19, 20, 22, 27, 31, 33, 34, 35, 37, 38, 41, 44, 50, 54, 55, 56], "python": [1, 4, 5, 6, 8, 9, 10, 12, 14, 15, 23, 25, 26, 27, 30, 31, 35, 36, 42, 43, 50, 52, 54, 55, 56], "describ": [1, 2, 4, 5, 7, 8, 10, 12, 13, 14, 19, 24, 26, 29, 41, 43, 44, 52, 54, 56], "http": [1, 3, 8, 15, 24, 25, 26, 27, 31, 33, 34, 35, 36, 37, 38, 44, 50, 52, 54, 55], "arxiv": [1, 3, 8, 44, 52], "org": [1, 3, 8, 27, 44, 52, 54], "html": [1, 37, 44, 54], "2309": 1, "17453v3": 1, "maxstopwordslen": 1, "stopwordslen": 1, "tensor": [1, 2, 5, 7, 11, 12, 13, 16, 17, 18, 19, 22, 23, 39, 43, 44, 45, 46, 49, 52, 54, 55], "maxbadwordslen": 1, "badwordslen": 1, "distribut": [1, 3, 4, 5, 12, 31, 32, 44, 49, 51], "over": [1, 2, 13, 17, 18, 20, 29, 41, 44, 56], "vocabulari": [1, 5, 7, 29, 43, 45, 56], "address": [1, 13, 20, 43, 51], "linear": [1, 8, 10, 11, 12, 44, 51, 52, 56], "seq": [1, 4, 51], "skip": [1, 6, 13, 25, 38, 39, 44], "sequencelimitlength": 1, "badwordslist": 1, "badwordsptr": 1, "badwordslength": 1, "stopwordslist": 1, "stopwordsptr": 1, "stopwordslength": 1, "cacheindirect": 1, "maxseqlen": 1, "k": [1, 4, 5, 8, 14, 44, 52, 54, 55, 56], "v": [1, 4, 5, 8, 16, 17, 20, 23, 25, 44, 46, 52, 54], "medusainput": 1, "explicitdrafttokensinput": 1, "lookaheadinput": 1, "nextdrafttoken": 1, "maxnumpath": 1, "nextflattoken": 1, "nextdraftindic": 1, "nextdraftprob": 1, "vocabs": [1, 5], "lastdrafttoken": 1, "lastdraftindic": 1, "mask": [1, 4, 44, 45, 46, 49, 56], "packedpositionid": 1, "bestpathlength": 1, "bestpathindic": 1, "nextgenerationlength": 1, "lastpositionidsbas": 1, "lastgenerationlength": 1, "maxgenlengthdevic": 1, "seqslot": 1, "tokensperstep": 1, "medusapath": 1, "maxtokensperstep": 1, "maxmedusahead": 1, "medusatreeid": 1, "medusalogit": 1, "maxaccepteddrafttokensperstep": 1, "medusacurtokensperstep": 1, "medusatargettokensperstep": 1, "batch_manag": [1, 2], "gatheredid": 1, "newtokensstep": 1, "newtoken": 1, "newtokensvec": 1, "finishedsum": 1, "parentid": 1, "beamhypothes": 1, "speculativedecodingoutput": 1, "lookaheaddecodingbuff": 1, "lookaheadoutput": 1, "knegativeinfin": 1, "1e20f": 1, "maxsequencelength": [1, 51], "releas": [1, 2, 4, 5, 15, 16, 19, 20, 23, 25, 26, 27, 43, 44, 46, 50, 51, 52], "init": [1, 24, 25], "slice": [1, 3, 13, 44], "batchindex": 1, "outputidscba": 1, "logprobscba": 1, "sequencelengthscba": 1, "cumlogprobscba": 1, "normedscorescba": 1, "numbeamscba": 1, "minnormedscorescba": 1, "batchdon": 1, "nextdrafttokenslen": 1, "prevdrafttokenslen": 1, "acceptedtokenslen": 1, "acceptedlengthscumsum": 1, "pathsoffset": 1, "bufferptr": 1, "tensormap": 1, "executor": [1, 2, 5, 9, 29, 39, 49, 51, 55, 56], "tllmruntim": [1, 5], "numctxsequ": 1, "numgensequ": 1, "setfrominput": 1, "decoderbuff": 1, "contextpositionid": 1, "insertinputtensor": 1, "inputbuff": 1, "outputbuff": 1, "engineinput": 1, "engineoutput": 1, "scantempstoragebyt": 1, "scantempstorag": 1, "cumsumgenerationlength": 1, "draftbuff": 1, "explicitdrafttokensmodul": 1, "requesttypesdevic": 1, "numsequ": 1, "positionoffset": 1, "nextpositionoffset": 1, "maxgentoken": 1, "totalgentoken": 1, "subclass": [1, 15], "maxnumsequ": [1, 55], "positionidsbas": 1, "generationlength": 1, "randomdatasampl": 1, "randomdatavalid": 1, "maxpathdraftlen": 1, "drafttoken": [1, 56], "draftindic": 1, "draftprob": 1, "packedmask": 1, "ceil": [1, 46], "32": [1, 9, 17, 18, 29, 30, 39, 43, 44, 46, 51, 52, 55, 56], "maxgenlengthhost": 1, "generationlengthshost": 1, "ttensor": 1, "genericgenerationinput": 1, "mark": [1, 2, 6, 44, 54], "aka": [1, 7, 44], "eo": [1, 5], "": [1, 2, 3, 5, 6, 10, 11, 12, 13, 14, 15, 16, 18, 19, 22, 24, 25, 40, 42, 44, 45, 46, 49, 51, 52, 54, 55, 56], "50": [1, 20, 43], "256": [1, 9, 16, 19, 39, 41, 43, 44, 55], "gpt2": [1, 46, 54], "257": [1, 43], "fill": [1, 13, 33, 34, 35, 37, 44], "greater": [1, 4, 19, 20, 21, 44], "equal": [1, 3, 21, 22, 30, 42, 44, 45, 51, 56], "That": [1, 2, 4, 5, 12, 29, 40, 44], "maxinputlength": 1, "respect": [1, 3, 30, 42, 44, 49, 51, 52, 54, 56], "sessionconfig": 1, "numtoken": 1, "sum": [1, 6, 10, 44], "instanc": [1, 2, 5, 6, 12, 22, 30, 31, 39, 49, 51, 56], "futur": [1, 2, 4, 13, 15, 20, 21, 23, 24, 25, 31, 33, 34, 35, 36, 37, 38, 42, 43, 44, 50, 51, 52, 55, 56], "session": [1, 4, 23, 49], "made": [1, 40], "flexibl": [1, 15, 24, 30, 56], "automat": [1, 2, 6, 12, 13, 22, 25, 27, 30, 33, 40, 43, 44, 51, 52, 55, 56], "embeddingbiasopt": 1, "point": [1, 2, 4, 12, 14, 17, 20, 31, 42, 43, 44, 50, 52, 54], "add": [1, 4, 6, 10, 11, 12, 15, 24, 25, 27, 39, 44, 49, 54, 55], "dure": [1, 2, 4, 5, 6, 9, 12, 19, 25, 27, 39, 41, 42, 49, 51, 56], "project": [1, 4, 8, 24, 38], "argument": [1, 2, 22, 24, 26, 30, 39, 42, 44, 51, 55], "integ": [1, 4, 42, 44, 52, 55], "ban": 1, "Its": [1, 2, 4, 44], "explain": [1, 5, 12, 14, 42, 44, 51, 52], "trigger": [1, 4, 6, 12, 30, 31, 38, 41, 42], "let": [1, 6, 10, 11, 13, 30, 40, 44], "three": [1, 11, 20, 22, 42, 44, 52, 56], "represent": [1, 6, 12], "those": [1, 4, 5, 11, 12, 14, 21, 22, 41, 42, 43, 44, 45, 52], "second": [1, 2, 7, 8, 16, 18, 19, 22, 29, 43, 44, 56], "third": [1, 2, 22], "row": [1, 2, 7, 8, 44, 52], "inclus": [1, 2, 44], "prefix": [1, 11, 44, 47, 54, 56], "shown": [1, 7, 18, 24, 44], "follow": [1, 2, 5, 6, 8, 10, 11, 12, 13, 20, 22, 24, 25, 27, 29, 30, 31, 35, 36, 42, 43, 44, 50, 52, 53, 54, 55, 56], "diagram": [1, 56], "case": [1, 2, 4, 5, 8, 17, 20, 21, 29, 30, 41, 42, 43, 44, 52, 55, 56], "inner": [1, 44], "instead": [1, 6, 12, 15, 16, 24, 29, 30, 39, 44, 51, 55, 56], "8212": 1, "genericgenerationoutput": 1, "maxseqlength": [1, 2], "shorter": [1, 4, 42, 43], "ad": [1, 4, 5, 6, 7, 9, 15, 23, 25, 29, 41, 44, 46, 49, 55, 56], "note": [1, 2, 6, 8, 12, 18, 20, 21, 22, 23, 24, 26, 29, 30, 31, 39, 42, 43, 44, 47, 49, 50, 51, 52, 53, 56], "tensorrt": [1, 4, 5, 6, 8, 9, 10, 16, 19, 21, 22, 26, 27, 28, 30, 33, 34, 35, 36, 37, 38, 41, 43, 44, 49, 52, 53, 54], "previou": [1, 2, 3, 15, 17, 56], "prob": [1, 2, 7, 44], "like": [1, 2, 4, 5, 6, 7, 11, 12, 14, 15, 20, 22, 25, 29, 30, 31, 33, 34, 35, 36, 37, 38, 40, 42, 43, 44, 50, 51, 52, 55], "chang": [1, 4, 13, 15, 16, 18, 19, 23, 24, 25, 29, 40, 42, 43, 44, 46, 49, 50, 51], "remove_input_pad": [1, 4, 8, 21, 42, 44, 45, 49, 54, 56], "packeds": 1, "built": [1, 2, 5, 12, 15, 22, 24, 25, 29, 31, 38, 39, 42, 43, 44, 50, 51, 54, 55, 56], "gather_context_logit": [1, 2, 21, 39, 46, 49], "gather_all_token_logit": [1, 2, 21, 55], "you": [1, 2, 3, 4, 5, 6, 11, 12, 14, 15, 20, 21, 22, 23, 24, 25, 26, 27, 29, 30, 31, 34, 38, 42, 43, 44, 49, 50, 51, 54, 55, 56], "acquisit": 1, "pleas": [1, 2, 4, 6, 10, 16, 18, 19, 20, 24, 26, 27, 30, 39, 42, 54, 55, 56], "gptsessionbenchmark": [1, 41, 55], "cpp": [1, 2, 4, 5, 7, 12, 22, 23, 24, 25, 43, 44, 54, 55], "import": [1, 13, 15, 16, 20, 23, 25, 26, 27, 30, 31, 33, 34, 35, 36, 37, 38, 43, 50, 53, 55, 56], "out": [1, 7, 8, 15, 16, 17, 18, 19, 25, 27, 31, 41, 43, 44, 50, 51], "impact": [1, 16, 20, 42, 56], "perform": [1, 2, 4, 5, 6, 7, 8, 12, 13, 14, 15, 16, 18, 19, 21, 22, 24, 30, 40, 43, 44, 50, 53, 55], "languag": [1, 5, 12, 14, 16, 26, 40, 41, 44, 52, 56], "head": [1, 5, 12, 16, 23, 38, 44, 51, 55, 56], "lm": [1, 56], "matrix": [1, 4, 12, 19, 23, 40, 44, 50], "maxoutputlen": 1, "gather_generation_logit": [1, 2, 21, 39, 46, 49, 56], "also": [1, 2, 4, 6, 9, 11, 12, 13, 14, 15, 18, 19, 20, 22, 24, 25, 26, 30, 41, 42, 43, 44, 50, 51, 52, 55, 56], "obtain": [1, 2, 14, 22, 26, 42, 44], "ontokengener": 1, "callback": [1, 22], "caller": 1, "continu": [1, 2, 4, 18, 20, 21, 22, 40, 49, 56], "implement": [1, 2, 4, 5, 11, 12, 14, 15, 16, 23, 40, 42, 43, 44, 50, 52, 53, 56], "boolean": [1, 2, 22, 44, 46, 47], "getdefaultbatchslot": 1, "produc": [1, 2, 6, 12, 22, 25, 30, 42, 44, 55], "do": [1, 2, 6, 13, 15, 20, 23, 25, 30, 41, 44, 50], "explicitli": [1, 6, 12, 13, 21, 26, 30, 55, 56], "igptdecod": 1, "virtual": [1, 45], "setup": [1, 4, 21, 25, 39, 49, 50, 51], "decoder_batch": 1, "forwardasync": 1, "forwardsync": 1, "gathertre": 1, "acceptdrafttokensbyid": 1, "targettokenid": 1, "drafttokenid": 1, "contextlength": 1, "numdrafttoken": 1, "sequencelength": 1, "finishedvec": 1, "finishedfin": 1, "acceptdrafttokensbylogit": 1, "draftlogit": 1, "targetlogit": 1, "targetprob": 1, "userandomacceptthreshold": 1, "randomacceptthreshold": 1, "curandstate_t": 1, "curandst": 1, "dtype": [1, 6, 8, 9, 10, 11, 12, 15, 21, 39, 43, 44, 45, 46, 47, 48, 49, 54, 56], "overrid": [1, 2, 13, 15, 30, 49], "mmanag": 1, "dynamicdecodelay": 1, "mdynamicdecodelay": 1, "decodinglayerworkspac": 1, "mdecodinglayerworkspac": 1, "mlogprobstil": 1, "msamplingconfig": 1, "gpt": [1, 2, 4, 7, 12, 14, 17, 20, 23, 31, 44, 51, 52, 53, 54, 55, 56], "flight": [1, 14, 22, 23, 43, 50, 51, 55], "forwardtyp": 1, "kasync": 1, "ksync": 1, "forward": [1, 2, 6, 10, 12, 42, 45, 46, 54, 56], "setupexplicitdrafttoken": 1, "setuplookahead": 1, "newbatch": 1, "newrequest": 1, "tokenptr": 1, "thread": [1, 2, 4, 30, 49], "getfinish": 1, "getfinishreason": 1, "finishedst": 1, "getid": 1, "batchidx": 1, "ungath": 1, "getgatheredid": 1, "gather": [1, 21, 25, 35, 36, 44], "getparentid": 1, "parent": [1, 13, 15], "collect": [1, 2, 6, 12, 43, 44, 56], "getcumlogprob": 1, "getlogprob": 1, "getallnewtoken": 1, "getnewtoken": 1, "within": [1, 4, 12, 25, 44, 56], "getnbstep": 1, "getnbfinish": 1, "getnextdrafttoken": 1, "predict": [1, 4, 56], "next": [1, 2, 8, 12, 15, 17, 23, 40, 49, 51, 53, 55, 56], "getprevdrafttokenslength": 1, "getnextdrafttokenslength": 1, "getacceptedlengthscumsum": 1, "exclus": [1, 5, 52], "getacceptedpackedpath": 1, "gptdecoderptr": 1, "decodinginputptr": 1, "decodingoutputptr": 1, "postprocessrequest": 1, "allocatespeculativedecodingbuff": 1, "setupspeculativedecod": 1, "newrequestspeculativedecod": 1, "intern": [1, 2, 4, 15, 51, 54], "newrequestdrafttokensextern": 1, "sp": 1, "newrequestmedusa": 1, "newrequestlookahead": 1, "newrequestexplicitdrafttoken": 1, "updatefinish": 1, "updat": [1, 12, 13, 15, 18, 24, 25, 26, 39, 42, 44, 49, 56], "setexplicitdrafttokensinput": 1, "forwarddispatch": 1, "forwarddecod": 1, "whole": [1, 39, 40, 44, 51], "mvocabs": 1, "mvocabsizepad": 1, "mruntimestream": 1, "mdecoderstream": 1, "mbuffermanag": 1, "mforwardtoken": 1, "mforwardev": 1, "mdecod": 1, "mjointdecodinginput": 1, "mjointdecodingoutput": 1, "macceptbylogit": 1, "mnumdrafttoken": 1, "mcurandst": 1, "mnbstep": 1, "mfinish": 1, "mfinishedsum": 1, "mmaxnewtoken": 1, "mnumdecodingenginetoken": 1, "mfinishedstep": 1, "mdraftprob": 1, "mtargetprob": 1, "mdrafttokenid": 1, "mdraftlogit": 1, "mbatchslotssetup": 1, "mbatchslotsdecod": 1, "mbatchslotsaccepttoken": 1, "mbatchslotsacceptlogit": 1, "mtargetlogitsptr": 1, "mmaxsequencelength": 1, "mactualbatchs": 1, "mmaxdecodingdecodertoken": 1, "mmaxdecodingenginetoken": 1, "mspeculativedecodingmod": 1, "moutputbeamhypothes": 1, "mcumlogprobstmp": 1, "mnumsm": 1, "precis": [1, 5, 13, 16, 20, 23, 42, 43, 47, 50, 51, 53], "tensorparallel": [1, 5], "pipelineparallel": [1, 5], "gpuspernod": [1, 5], "getmodelconfig": 1, "getmodelconfigmut": 1, "getnam": 1, "getvers": 1, "getprecis": 1, "gettensorparallel": 1, "getpipelineparallel": 1, "getgpuspernod": 1, "getworlds": 1, "enginefilenam": 1, "pars": 1, "mname": 1, "mversion": 1, "mprecis": 1, "mtensorparallel": 1, "mpipelineparallel": 1, "mgpuspernod": 1, "mmodelconfig": 1, "kv_cache_manag": 1, "loggerptr": 1, "ilogg": 1, "logger": 1, "environ": [1, 2, 5, 24, 25, 26, 27, 54, 55, 56], "compil": [1, 5, 14, 23, 24, 40, 44], "engines": 1, "enginefil": 1, "getlogg": 1, "getbuffermanag": 1, "getruntimestreamptr": 1, "getworldconfig": 1, "iengineinspector": 1, "getengineinspector": 1, "getlogitdatatyp": 1, "generationprofil": 1, "read": [1, 2, 4, 10, 12, 13, 21, 27, 55, 56], "popul": [1, 2, 4, 12, 38, 44], "product": [1, 3, 4, 12, 18, 26, 40, 44, 50, 56], "pseudo": [1, 4, 44, 52], "code": [1, 2, 4, 6, 12, 15, 20, 23, 30, 40, 44, 52, 53, 54, 55, 56], "look": [1, 7, 15, 19, 22, 24, 40, 41], "simpl": [1, 6, 12, 24, 31, 40, 50, 56], "allfinish": 1, "limit": [1, 4, 5, 6, 12, 15, 20, 25, 30, 40, 42, 44, 47, 49, 51, 53], "computelogit": 1, "generatetokensfromlogit": 1, "setlayerprofil": 1, "layerprofil": 1, "getlayerprofileinfo": 1, "print": [1, 4, 25, 27, 30, 31, 33, 34, 35, 36, 37, 38, 41, 43, 50, 51, 54], "profil": [1, 21, 23, 44, 49, 51, 55], "kvcachemanag": [1, 4, 29, 49], "tokengeneratedcallback": 1, "usecudagraph": 1, "generatebatch": 1, "microbatchesoutput": 1, "microbatchesinput": 1, "createcontext": 1, "createbuff": 1, "nummicrobatch": 1, "createdecod": 1, "logitstyp": 1, "decoderperrequest": 1, "createkvcachemanag": 1, "createcustomallreduceworkspac": 1, "executecontextstep": 1, "generationbatchesinput": 1, "generationbatchesoffset": 1, "executegenerationstep": 1, "microbatchoffset": 1, "microbatchesfinish": 1, "decoderstepasync": 1, "decoderstep": 1, "shouldstopsync": 1, "shouldstop": 1, "asynchron": [1, 22, 30, 35, 39], "access": [1, 2, 22, 25, 27, 44, 55], "kvcacheaddsequ": 1, "firstbatchidx": 1, "initdecod": 1, "outputid": [1, 2], "createontokengeneratedcallback": 1, "shouldusekvcachemanag": 1, "mworldconfig": 1, "ncclcommun": 1, "mpipelinecomm": 1, "mcommstream": 1, "mcommev": 1, "allreducebuff": 1, "mallreducebuff": 1, "mdecodermaxsequencelength": 1, "mdecodermaxattentionwindowvec": 1, "mdecodermaxattentionwindow": 1, "mdecodersinktokenlength": 1, "mlogger": 1, "mruntim": 1, "mkvcachemanag": 1, "microbatchconfig": 1, "mmicrobatchconfig": 1, "runtimebuff": 1, "mbuffer": 1, "mreceivedev": 1, "mcudagraphmod": 1, "cudagraphexecutor": 1, "mcudagraphinst": 1, "trtgptmodelv1": [1, 55], "smaller": [1, 21, 41, 42, 44, 51, 55, 56], "divid": [1, 13, 44, 55], "micro": [1, 2, 42, 51], "cudagraphmod": 1, "ctxmicrobatchs": 1, "genmicrobatchs": 1, "enginepath": 1, "hasinst": 1, "clear": [1, 49], "preparenextgraph": 1, "nextcontextid": 1, "launch": [1, 2, 12, 23, 25, 26, 29, 54, 55, 56], "cudagraph_t": 1, "graph": [1, 12, 23, 44, 49, 50, 51, 54], "uploadtostream": 1, "cudagraphexec_t": 1, "minstanc": 1, "getstart": 1, "getend": 1, "getelapsedtimem": 1, "cudaeventdefault": 1, "numctxpergen": 1, "getgengraphid": 1, "flipflopid": 1, "generationbatchid": 1, "flip": [1, 44], "flop": 1, "numctxbatch": 1, "numgenbatch": 1, "ctxbatchsiz": 1, "genbatchs": 1, "loadengin": 1, "memorytypestr": 1, "kpin": 1, "kpinnedpool": 1, "datatypetrait": 1, "kfloat": [1, 12], "sizeof": 1, "khalf": 1, "int8": [1, 11, 13, 15, 20, 21, 23, 39, 44, 51, 53, 55], "int32": [1, 4, 21, 44, 47], "int64": [1, 5, 44], "uint32": 1, "uint64": [1, 29], "kunsign": 1, "uint8": 1, "trtdatatyp": 1, "bufferdatatyp": 1, "kernel": [1, 4, 5, 12, 16, 21, 29, 40, 41, 42, 43, 44, 49, 50, 51, 54, 55], "kvcacheindex": 1, "pointerelementtyp": 1, "remove_reference_t": 1, "remove_const_t": 1, "constpointercast": 1, "ptr": 1, "d": [1, 2, 7, 8, 25, 44, 55], "buffercast": 1, "constant": [1, 4, 44, 51], "buffercastornul": 1, "retriev": [1, 13, 26, 43, 44, 50], "null": [1, 11], "possibli": 1, "share": [1, 2, 4, 6, 8, 15, 20, 22, 24, 25, 29, 39, 44, 45, 55, 56], "optionalbufferptr": 1, "doesn": [1, 4, 30], "kdatatyp": 1, "kisunsign": 1, "kispoint": 1, "wrapper": [1, 6, 15], "around": [1, 11, 15, 40], "_unsign": 1, "ispoint": 1, "isunsign": 1, "ktrtpointertyp": 1, "mdatatyp": 1, "munsign": 1, "mpointer": 1, "kunderlyingtyp": 1, "uniqueconstptr": 1, "getcapac": 1, "getdatatypenam": 1, "getmemorytypenam": 1, "newsiz": 1, "op": [1, 6, 44], "Not": [1, 20, 54], "offset": [1, 7, 44, 49, 52, 55], "view": [1, 44], "tconstptr": 1, "enable_if_t": 1, "is_const_v": 1, "independ": [1, 22, 44, 56], "cannot": [1, 5, 12, 13, 42, 44, 51, 54, 55], "beyond": [1, 17, 26, 42], "protect": 1, "tobyt": 1, "bufferrang": 1, "u": [1, 6, 26, 33, 34, 35, 36, 37, 38], "actual": [1, 2, 6, 20, 21, 44, 55, 56], "predicteddraftlogit": 1, "explicitdrafttokenslastinput": 1, "reshapebuff": 1, "declar": [1, 5, 6, 15], "avoid": [1, 15, 24, 26, 51, 55], "ambigu": 1, "implicit": [1, 4, 44, 56], "convers": [1, 13, 19, 20, 23, 50, 55], "optionaltensorptr": 1, "n": [1, 4, 8, 11, 33, 34, 35, 36, 37, 38, 41, 42, 44, 46, 51, 52, 54, 56], "getdimens": 1, "th": [1, 11, 44], "neg": [1, 2, 7, 42, 44], "nbdim": 1, "todo": [1, 44], "replac": [1, 3, 6, 12, 13, 15, 42, 44, 51, 56], "move": [1, 15, 25, 40, 54, 55], "20": [1, 9, 43, 44, 49, 54, 56], "volum": [1, 24], "squeez": [1, 44], "remov": [1, 2, 4, 5, 6, 12, 13, 21, 24, 25, 26, 43, 44, 51, 55], "unit": [1, 13, 23, 24, 25, 31, 33, 34, 35, 36, 37, 38, 50], "unsqueez": [1, 44], "shapeequ": 1, "volumenonneg": 1, "stride": [1, 44, 45], "dimems": 1, "w": [1, 19, 46, 52, 53, 55, 56], "r": [1, 7, 8, 26, 31, 33, 34, 35, 36, 37, 38, 44, 50, 54, 56], "offsetdim": 1, "whenev": 1, "overflow": 1, "rest": [1, 4], "omit": [1, 7, 15, 22, 44], "flattenn": 1, "slicen": 1, "flatten": [1, 8, 19, 44], "mean": [1, 3, 4, 5, 11, 13, 15, 17, 18, 29, 41, 42, 43, 44, 47, 49, 51, 56], "makeshap": 1, "conveni": [1, 10, 15], "tostr": 1, "lh": 1, "compar": [1, 5, 13, 17, 18, 20, 42, 44], "castsiz": 1, "ipcmemori": 1, "buffers": 1, "openipc": 1, "getcommptr": 1, "flags_siz": 1, "max_all_reduce_block": 1, "allocateipcmemori": 1, "destroyipcmemori": 1, "mtprank": 1, "mcommptr": 1, "mopenipc": 1, "mallreducecommptr": 1, "mipcmemoryhandl": 1, "maxdecodingdrafttoken": 1, "setexecutionconfig": 1, "getexecutionconfig": 1, "mexecutionconfig": 1, "to_str": 1, "tasklayermoduleconfig": 1, "loraexpectedexcept": 1, "runtime_error": 1, "loracachefullexcept": 1, "loracachepagemanag": 1, "page": [1, 2, 5, 18, 21, 23, 29, 31, 44, 50, 51, 55], "pre": [1, 4, 11, 14, 25, 26, 40, 44, 50, 51, 54, 55], "safe": [1, 2, 6], "claimpag": 1, "numpag": 1, "claim": [1, 13], "pageid": 1, "numavailablepag": 1, "releasepag": 1, "blockptr": 1, "blockidx": 1, "pageptr": 1, "pageidx": 1, "mutablepageptr": 1, "mutabl": 1, "mpageblock": 1, "mfreepageid": 1, "mispagefre": 1, "lru": [1, 29, 44], "put": [1, 2, 11, 40], "progress": [1, 39, 44], "done": [1, 12, 29, 40, 42, 44, 47], "optim": [1, 2, 5, 6, 12, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 26, 29, 40, 44, 50, 51, 53, 55, 56], "numslot": 1, "pagewidth": 1, "conceptu": 1, "smallest": [1, 44], "ceildiv": 1, "num": [1, 43, 56], "taskidtyp": 1, "tasklayermoduleconfiglistptr": 1, "pagemanagerconfig": 1, "load": [1, 2, 8, 10, 11, 12, 15, 19, 21, 27, 31, 34, 42, 43, 46, 48, 49, 50, 51, 55], "loadweight": 1, "design": [1, 12, 13, 15, 20, 42, 56], "taslid": 1, "isload": 1, "place": [1, 37, 41, 42, 44, 56], "isdon": 1, "necessarili": [1, 12, 51], "bump": 1, "make": [1, 4, 6, 7, 8, 12, 15, 20, 23, 24, 26, 27, 40, 42, 44, 50, 54, 55, 56], "recent": [1, 2, 3, 4, 17], "marktaskdon": 1, "markalldon": 1, "determinenumpag": 1, "need": [1, 2, 4, 5, 6, 9, 10, 11, 12, 13, 14, 15, 22, 24, 25, 29, 30, 40, 41, 42, 43, 44, 46, 47, 49, 51, 54, 55, 56], "fit": [1, 2, 4, 16, 17], "copytask": 1, "devicecach": 1, "markdon": 1, "othercach": 1, "getnumpag": 1, "getpageptr": 1, "copytopag": 1, "moduleidtomodel": 1, "modelidtomodel": 1, "splittransposecpu": 1, "tpsize": 1, "tprank": 1, "split": [1, 3, 4, 5, 8, 12, 44, 51, 55], "part": [1, 3, 6, 12, 13, 15, 23, 24, 39, 40, 42, 43, 44, 51], "write": [1, 13, 21, 23, 29, 44, 56], "valuestatu": 1, "kvalue_status_miss": 1, "kvalue_status_process": 1, "kvalue_status_load": 1, "taskvalueptr": 1, "taskvalu": 1, "cachevalu": 1, "bumptaskinprogress": 1, "getstatu": 1, "claimpageswithevict": 1, "pair": [1, 16, 44], "copytaskmappag": 1, "targettaskvalu": 1, "sourcetaskvalu": 1, "targetpageid": 1, "targetcach": 1, "insid": [1, 13, 15, 24, 37, 44, 51, 56], "mpagemanagerconfig": 1, "mutex": 1, "mpagesmutex": 1, "mcachepagemanag": 1, "mcachemutex": 1, "mcachemap": 1, "minprogresstask": 1, "mdonetask": 1, "mdevicebuffermanag": 1, "mmoduleidtomodul": 1, "splittransposecpuinn": 1, "slotidx": 1, "insiz": 1, "outsiz": 1, "moduleid": [1, 8], "layerid": [1, 8], "adapters": 1, "weightsinpoint": 1, "weightsoutpoint": 1, "inprogress": 1, "loadinprogress": 1, "concurr": [1, 2, 17, 42, 55, 56], "doc": [1, 15, 19, 44, 54, 55], "memtyp": 1, "totalnumpag": 1, "maxpagesperblock": 1, "slotsperpag": 1, "setmemorytyp": 1, "setdatatyp": 1, "gettotalnumpag": 1, "settotalnumpag": 1, "getmaxpagesperblock": 1, "setmaxpagesperblock": 1, "getslotsperpag": 1, "setslotsperpag": 1, "getpagewidth": 1, "setpagewidth": 1, "getinittozero": 1, "setinittozero": 1, "inittozero": 1, "setnumcopystream": 1, "mmemorytyp": 1, "mtotalnumpag": 1, "mmaxpagesperblock": 1, "mslotsperpag": 1, "mpagewidth": 1, "minittozero": 1, "moduletyp": 1, "kinvalid": 1, "kattn_qkv": 1, "kattn_q": 1, "kattn_k": 1, "kattn_v": 1, "kattn_dens": 1, "kmlp_h_to_4h": 1, "kmlp_4h_to_h": 1, "kmlp_gate": 1, "kcross_attn_qkv": 1, "kcross_attn_q": 1, "kcross_attn_k": 1, "kcross_attn_v": 1, "kcross_attn_dens": 1, "kmoe_h_to_4h": 1, "kmoe_4h_to_h": 1, "kmoe_gat": 1, "kmoe_rout": 1, "kmlp_router": 1, "indim": 1, "outdim": 1, "indimfirst": 1, "outdimfirst": 1, "intpsplitdim": 1, "outtpsplitdim": 1, "flattenedinouts": 1, "localins": 1, "localouts": 1, "localindim": 1, "localoutdim": 1, "localinadapters": 1, "localoutadapters": 1, "localinouts": 1, "string_view": 1, "createloramodul": 1, "loramodulenam": 1, "mlphiddens": 1, "numattentionhead": 1, "numkvattentionhead": 1, "attentionheads": 1, "numexpert": 1, "tomoduletyp": 1, "tomodulenam": 1, "mtype": 1, "mindim": 1, "moutdim": 1, "mindimfirst": 1, "moutdimfirst": 1, "mintpsplitdim": 1, "mouttpsplitdim": 1, "maxacceptedtoken": 1, "initmedusatensorsfromchoic": 1, "choic": [1, 20, 21, 44, 49, 56], "generationinputlength": 1, "treeid": 1, "totalpath": 1, "computepathsandmask": 1, "medusatreenod": 1, "tree": [1, 33, 34, 35, 36, 37, 38, 54], "copypackedmask": 1, "srcidx": 1, "dstidx": 1, "setonepackedmask": 1, "col": 1, "computeprefix": 1, "vec": 1, "len": [1, 44, 49, 56], "dumpchoic": 1, "mdefaultmedusachoic": 1, "prefix_chunk_size_bit": 1, "prefix_max_valu": 1, "16": [1, 8, 17, 20, 43, 44, 45, 46, 51, 52, 54, 56], "nodeid": 1, "depth": [1, 56], "parentlinearidx": 1, "linearidx": 1, "childlinearindic": 1, "difftyp": 1, "ptrdiff_t": 1, "getgpu": 1, "getcpu": 1, "getpin": 1, "getuvm": 1, "getpinnedpool": 1, "getgpudiff": 1, "getcpudiff": 1, "getpinneddiff": 1, "getuvmdiff": 1, "getpinnedpooldiff": 1, "dealloc": 1, "getinst": 1, "bytestostr": 1, "atom": 1, "mgpu": 1, "mcpu": 1, "mpin": 1, "muvm": 1, "mpinnedpool": 1, "mgpudiff": 1, "mcpudiff": 1, "mpinneddiff": 1, "muvmdiff": 1, "mpinnedpooldiff": 1, "modelvari": 1, "kgpt": 1, "kchatglm": 1, "kglm": 1, "kmamba": 1, "krecurrentgemma": 1, "kencdec": 1, "layertyp": [1, 6], "kattent": 1, "krecurr": 1, "kvcachetyp": [1, 39, 49], "kcontinu": 1, "kpage": 1, "kdisabl": 1, "manageweightstyp": 1, "kenabl": 1, "nbattentionlay": 1, "nbrnnlayer": 1, "nbhead": 1, "getvocabs": 1, "getvocabsizepad": 1, "worldsiz": 1, "getnbattentionlay": 1, "getnbrnnlay": 1, "getnbhead": 1, "getnbkvhead": 1, "setnbkvhead": 1, "nbkvhead": 1, "gethiddens": 1, "getencoderhiddens": 1, "setencoderhiddens": 1, "encoderhiddens": 1, "getsizeperhead": 1, "setsizeperhead": 1, "sizeperhead": 1, "usegptattentionplugin": [1, 5], "usemambaconv1dplugin": 1, "usepackedinput": 1, "inputpack": [1, 5], "usepagedst": 1, "pagedst": 1, "gettokensperblock": 1, "settokensperblock": 1, "quantmod": [1, 4, 5, 23, 39, 44, 45, 46, 48, 49], "getquantmod": 1, "setquantmod": 1, "supportsinflightbatch": 1, "getmaxinputlen": 1, "setmaxinputlen": 1, "maxinputlen": [1, 5], "getmaxsequencelen": 1, "setmaxsequencelen": 1, "maxsequencelen": [1, 5], "getmaxencoderlen": 1, "setmaxencoderlen": 1, "maxencoderlen": 1, "useprompttun": 1, "getmaxpromptembeddingtables": 1, "setmaxpromptembeddingtables": 1, "maxpromptembeddingtables": 1, "computecontextlogit": 1, "computegenerationlogit": 1, "getmodelvari": 1, "setmodelvari": 1, "getmaxdecodingdrafttoken": 1, "getmaxdecodingtoken": 1, "setcontextfmha": 1, "contextfmha": 1, "getcontextfmha": 1, "setpagedcontextfmha": 1, "pagedcontextfmha": 1, "getpagedcontextfmha": 1, "usexqa": 1, "useloraplugin": 1, "getloramodul": 1, "setloramodul": 1, "getmlphiddens": 1, "setmlphiddens": 1, "iskvcacheen": 1, "ispagedkvcach": 1, "iscontinuouskvcach": 1, "getkvcachetyp": 1, "setkvcachetyp": 1, "usecrossattent": 1, "setusecrossattent": 1, "usepositionembed": 1, "setusepositionembed": 1, "usetokentypeembed": 1, "setusetokentypeembed": 1, "getmaxlorarank": 1, "setmaxlorarank": 1, "maxlorarank": 1, "setspeculativedecodingmod": 1, "hasspeculativedecodingmodul": 1, "getspeculativedecodingmodul": 1, "getspeculativedecodingmoduleptr": 1, "setspeculativedecodingmodul": 1, "getkvdatatyp": 1, "istransformerbas": 1, "hasrnnconfig": 1, "rnnconfig": 1, "getrnnconfig": 1, "setrnnconfig": 1, "isrnnbas": 1, "getlayertyp": 1, "setlayertyp": 1, "getspeculativedecodingmod": 1, "setlogitsdtyp": 1, "inputdtyp": 1, "getlogitsdtyp": 1, "setuseshapeinfer": 1, "useshapeinfer": 1, "getmanageweightstyp": 1, "setmanageweightstyp": 1, "manageweighttyp": 1, "getmodelnam": 1, "setmodelnam": 1, "modelnam": 1, "kvcachetypefromstr": 1, "getoptprofilessplitpoint": 1, "kopt_profiles_split_point": 1, "128": [1, 4, 8, 9, 16, 17, 18, 19, 20, 29, 30, 39, 41, 43, 55], "512": [1, 8, 9, 18, 19, 39, 43, 46], "1024": [1, 5, 11, 18, 20, 21, 30, 44, 45, 56], "mnbattentionlay": 1, "mnbrnnlayer": 1, "mnbhead": 1, "mnbkvhead": 1, "mhiddens": 1, "msizeperhead": 1, "musegptattentionplugin": 1, "musemambaconv1dplugin": 1, "minputpack": 1, "mpagedst": 1, "mtokensperblock": 1, "mquantmod": 1, "mmaxinputlen": 1, "mmaxsequencelen": 1, "mcomputecontextlogit": 1, "mcomputegenerationlogit": 1, "mmodelvari": 1, "mmaxpromptembeddingtables": 1, "mcontextfmha": 1, "mpagedcontextfmha": 1, "musexqa": 1, "museloraplugin": 1, "mloramodul": 1, "mmlphiddens": 1, "mmaxlorarank": 1, "mrnnconfig": 1, "mkvcachetyp": 1, "mmaxencoderlen": 1, "mencoderhiddens": 1, "musecrossattent": 1, "musepositionembed": 1, "musetokentypeembed": 1, "mlayertyp": 1, "mspeculativedecodingmodul": 1, "mlogitsdtyp": 1, "museshapeinfer": 1, "mmanageweightstyp": 1, "mmodelnam": 1, "states": 1, "convkernel": 1, "rnnhiddens": 1, "rnnheadsiz": 1, "rnnconvdims": 1, "genericprompttuningparam": 1, "prompttuningen": 1, "filltaskstensor": 1, "taskshost": 1, "reqbeamwidth": 1, "reqpromptlength": 1, "packedinput": 1, "filepath": 1, "addresswiths": 1, "hostmemori": 1, "engineaddr": 1, "ihostmemori": [1, 12, 49], "gettyp": 1, "getpath": 1, "getpathopt": 1, "setpath": 1, "getmanagedweightsmapopt": 1, "setmanagedweightsmap": 1, "managedweightsmap": 1, "getaddress": 1, "gethostmemori": 1, "mengineaddr": 1, "mengines": 1, "menginepath": 1, "anonym": 1, "menginebuff": 1, "mmanagedweightsmap": 1, "inputlen": 1, "generatedtokensperenginestep": 1, "lookaheadruntimeconfig": 1, "set_from_opt": 1, "varnam": 1, "vartyp": 1, "optvec": 1, "outputlogprob": 1, "draftacceptancethreshold": 1, "topkmedusahead": 1, "validatevec": 1, "min": [1, 17, 44], "fusevalu": 1, "ci": 1, "accessor": 1, "defaultvalu": 1, "isnon": 1, "isdrafttokensextern": 1, "islookaheaddecod": 1, "updatespositionid": 1, "requiresattentionmask": 1, "predictsdrafttoken": 1, "needskvcacherewind": 1, "variabledraftlength": 1, "hasdraftlogit": 1, "needsdecoderprologu": 1, "none": [1, 5, 6, 10, 13, 15, 21, 30, 39, 44, 45, 46, 47, 48, 49, 54, 56], "drafttokensextern": 1, "lookaheaddecod": 1, "knone": 1, "0u": 1, "kdrafttokensextern": 1, "2u": 1, "klookaheaddecod": 1, "3u": 1, "4u": 1, "getmaxdraftpathlen": 1, "getmaxpathlen": 1, "grow": [1, 42, 56], "getnumpackedmask": 1, "getmaxnumpath": 1, "setmaxdrafttoken": 1, "setmaxdraftpathlen": 1, "setmaxnumpath": 1, "computenumpackedmask": 1, "mmaxdraftpathlen": 1, "mmaxdecodingdrafttoken": 1, "mmaxnumpath": 1, "mmaxnumpackedmask": 1, "asciichar": 1, "getlevel": 1, "setlevel": 1, "level": [1, 2, 4, 8, 10, 11, 13, 15, 21, 22, 30, 41, 51, 55], "kdefaultgpuspernod": 1, "istensorparallel": 1, "ispipelineparallel": 1, "getrank": 1, "getgpuspergroup": 1, "getdeviceof": 1, "getpipelineparallelrank": 1, "gettensorparallelrank": 1, "getlocalrank": 1, "getnoderank": 1, "getnoderankof": 1, "isfirstpipelineparallelrank": 1, "islastpipelineparallelrank": 1, "my": [1, 31, 33, 34, 35, 36, 37, 38, 50], "pipelin": [1, 2, 5, 12, 16, 19, 22, 51, 55], "isfirsttensorparallelrank": 1, "getlastrank": 1, "getpipelineparallelgroup": 1, "gettensorparallelgroup": 1, "validmpiconfig": 1, "mrank": 1, "lookaheadruntimebuff": 1, "decoderlookaheadbuff": 1, "packedmasksdevic": 1, "generationlengthsdevic": 1, "positionoffsetsdevic": 1, "positionidsdevic": 1, "packedmaskhost": 1, "positionoffsetshost": 1, "positionidshost": 1, "packedmaskhostcopi": 1, "generationlengthshostcopi": 1, "positionoffsetshostcopi": 1, "positionidshostcopi": 1, "batchslotshostcopi": 1, "reli": [2, 4, 6, 15, 41, 52], "compon": [2, 4, 12, 14, 20, 22, 52], "known": [2, 4, 12, 23, 27, 44, 53, 56], "techniqu": [2, 4, 6, 12, 16, 40, 42, 52, 55, 56], "aim": [2, 3, 11, 40, 42, 55], "reduc": [2, 3, 4, 12, 16, 19, 22, 24, 29, 40, 43, 44, 51, 54, 55, 56], "elimin": [2, 40, 55], "via": [2, 7, 24, 25, 44, 56], "expos": [2, 5, 12, 24, 42, 55], "hook": 2, "user": [2, 4, 5, 6, 8, 12, 13, 14, 15, 19, 20, 22, 24, 25, 29, 41, 42, 43, 44, 46, 51, 52, 54, 55], "regist": [2, 23, 54], "deprec": [2, 5, 21, 29, 39, 42, 51, 55], "favor": [2, 5, 55], "softwar": [2, 4, 5, 22, 23, 40, 55], "client": [2, 22, 43], "text": [2, 4, 5, 22, 29, 30, 31, 33, 34, 35, 36, 37, 38, 39, 40, 43, 50, 54], "interact": [2, 22, 25, 40, 54, 56], "two": [2, 3, 4, 5, 6, 7, 8, 9, 11, 12, 15, 17, 22, 24, 25, 27, 29, 31, 42, 43, 44, 45, 47, 56], "Their": 2, "signatur": [2, 6, 44], "h": [2, 4, 13, 21, 22, 44, 46, 55, 56], "file": [2, 3, 4, 6, 11, 12, 13, 21, 22, 29, 41, 43, 49, 50, 55, 56], "These": [2, 15, 16, 18, 19, 25, 30, 43, 47, 50, 56], "regular": [2, 4, 44], "interv": 2, "varieti": [2, 55], "entri": [2, 8, 44, 54], "getinferencerequestscallback": 2, "inferencerequest": [2, 7, 8, 55], "unbound": 2, "deliv": [2, 16, 19, 43], "sendresponsecallback": [2, 7], "conform": 2, "messag": [2, 43, 44, 51, 55], "encount": [2, 13, 22, 54], "properli": [2, 13, 25, 27, 42], "handl": [2, 3, 13, 15, 16, 42, 44, 45, 50], "pollstopsignalcallback": 2, "unordered_set": 2, "ensur": [2, 3, 6, 15, 47], "report": [2, 41, 51, 55], "returnbatchmanagerstatscallback": 2, "packag": [2, 22, 24, 25, 27, 54], "field": [2, 5, 11, 15, 29, 30, 39, 40, 46, 47, 52, 55, 56], "put_tim": 2, "tm": 2, "y": [2, 19, 22, 24, 25, 26, 27, 44, 46, 52, 54, 56], "counter": [2, 41], "global": [2, 4, 7, 12, 55], "monoton": 2, "addit": [2, 4, 5, 12, 15, 18, 22, 24, 25, 30, 41, 42, 44, 45, 52, 53, 56], "across": [2, 3, 4, 5, 6, 12, 13, 18, 29, 42, 44, 49], "microbatch": [2, 41], "v1": [2, 31, 33, 34, 35, 36, 37, 38, 42, 50, 53, 56], "alter": [2, 6, 22], "network": [2, 3, 4, 6, 12, 14, 15, 21, 22, 44, 50, 51, 52, 54, 55], "attach": 2, "requestidtyp": 2, "tstream": 2, "fourth": [2, 22], "altern": [2, 22], "howev": [2, 4, 15, 16, 22, 40, 42, 51, 53, 55, 56], "slow": [2, 22, 29, 40], "logic": [2, 13, 15, 22, 45, 55, 56], "isn": [2, 25], "moment": [2, 22], "trtenginepath": 2, "directori": [2, 10, 11, 12, 13, 15, 21, 22, 24, 25, 39, 43, 46, 49, 50, 55], "inflightfusedbatch": 2, "improv": [2, 4, 5, 12, 16, 17, 18, 19, 20, 29, 33, 34, 35, 37, 40, 42, 43, 50, 55], "leverag": [2, 7, 16, 50, 56], "fusion": [2, 6, 23, 40, 51, 52], "opportun": 2, "strictli": 2, "superior": 2, "trtgptmodeloptionalparam": [2, 29, 42, 55], "encapsul": [2, 4, 5, 12, 29, 44], "unspecifi": [2, 21, 44], "well": [2, 4, 5, 12, 14, 17, 30, 41, 42, 43, 52, 53], "attend": [2, 42], "slide": [2, 23, 42, 44, 49], "streamingllm": [2, 21, 23, 55], "mha": [2, 4, 16, 42, 44, 49], "mqa": [2, 4, 16, 19, 42, 44, 55], "previous": [2, 16, 29], "enabletrtoverlap": 2, "partit": [2, 4, 8, 42], "hide": [2, 42], "thank": [2, 55], "work": [2, 4, 5, 6, 12, 15, 24, 25, 27, 30, 38, 40, 42, 43, 44, 49, 52, 53, 55], "significantli": [2, 20, 51], "therefor": [2, 9, 15, 42, 43, 44, 54], "recommend": [2, 4, 5, 10, 13, 14, 17, 20, 25, 27, 42, 54, 55, 56], "doe": [2, 4, 5, 15, 16, 21, 25, 29, 42, 44, 49, 51, 55], "give": [2, 40, 46], "notic": [2, 4], "hurt": [2, 42], "possibl": [2, 4, 5, 12, 21, 24, 29, 30, 40, 42, 44, 51, 54, 56], "turn": [2, 4, 24, 29, 42, 49, 51, 55], "peftcachemanagerconfig": 2, "use_lora_plugin": [2, 49], "build": [2, 4, 5, 6, 8, 9, 10, 14, 23, 27, 29, 31, 39, 40, 46, 47, 50, 51, 55], "adapter_s": [2, 7, 8], "typic": [2, 6, 10, 12, 15, 20, 47, 51], "adapt": [2, 7, 8], "fix": [2, 8, 51, 56], "exactli": 2, "least": [2, 4, 15, 22, 49], "larg": [2, 4, 12, 14, 15, 16, 20, 26, 29, 40, 41, 42, 44, 51, 55, 56], "enough": [2, 4, 29, 42, 51], "worker": [2, 21, 51], "h2d": 2, "05": [2, 43, 44, 45, 46, 54, 55, 56], "peft": [2, 39], "1g": [2, 54], "inputid": 2, "promptlength": 2, "dummi": [2, 55], "outputlength": 2, "gptmanagerbenchmark": [2, 29, 41, 55], "rememb": 2, "To": [2, 4, 7, 8, 9, 12, 13, 14, 15, 18, 23, 24, 25, 29, 31, 40, 41, 43, 44, 50, 51, 52, 54, 55, 56], "redund": [2, 56], "much": [2, 12, 29, 43, 51], "max_batch_s": [2, 4, 8, 9, 11, 15, 21, 30, 39, 44, 46, 49, 51, 55, 56], "max_beam_width": [2, 4, 21, 22, 30, 39, 44, 46, 49, 51, 56], "max_input_len": [2, 8, 9, 11, 21, 39, 42, 46, 49, 51, 56], "max_seq_len": [2, 8, 9, 11, 21, 39, 44, 45, 46, 49, 51, 55, 56], "close": [2, 4, 15, 21, 25, 27, 51], "integr": [2, 55, 56], "item": [2, 49], "style": [2, 4, 55], "autoregress": 2, "architectur": [2, 3, 5, 11, 17, 24, 25, 29, 40, 42, 43, 46, 49, 53, 55], "spawn": 2, "persist": [2, 20, 31], "intend": [2, 25, 51], "system": [2, 12, 17, 23, 24, 25, 27, 29, 43, 53, 55], "retir": 2, "notifi": 2, "final_respons": 2, "relat": [2, 3, 13, 23, 24, 41, 44, 47, 51, 54, 55], "freed": 2, "regress": [2, 4, 5, 12], "batchmanag": 2, "pathtotrtengin": 2, "trtgptmodeltyp": 2, "getinferencerequestscb": 2, "abov": [2, 8, 12, 15, 20, 24, 27, 30, 31, 41, 43, 51], "sendresponsecb": 2, "pollstopsignalcb": 2, "returnbatchmanagerstatscb": 2, "help": [2, 4, 6, 12, 22, 24, 42, 43, 55], "adjust": [2, 42, 51], "aggress": [2, 11, 42], "risk": [2, 12, 42], "short": [2, 4], "resum": 2, "visibl": 2, "adopt": [2, 5, 15], "approach": [2, 3, 6, 29, 42], "know": [2, 23, 41, 42], "suffici": [2, 25], "even": [2, 4, 5, 12, 15, 20, 42, 44, 51], "worst": 2, "consumpt": [2, 4, 17, 42], "node": [2, 5, 14, 21, 23, 44, 52, 54, 55], "cuda_visible_devic": 2, "care": 2, "taken": [2, 13, 16, 17, 44], "backend": [2, 12, 14, 42, 50, 55, 56], "broadcast": [2, 44], "seen": [2, 56], "ident": [2, 21, 22, 29, 44], "mechan": [2, 12], "good": [2, 12], "wide": 3, "mistral": [3, 31, 43, 52, 53, 55], "mixtral": [3, 8, 31, 43, 52, 53, 55], "8x7b": [3, 43, 55], "structur": [3, 5, 6, 7, 51, 55, 56], "feedforward": 3, "neural": [3, 6, 12, 50, 55], "ffn": 3, "dens": [3, 4, 8, 11, 13, 44], "router": [3, 8, 55], "As": [3, 4, 6, 8, 12, 14, 30, 42, 43, 44, 51, 52, 54, 56], "switch": [3, 17, 20, 24, 25, 29, 51, 55], "transform": [3, 4, 10, 11, 12, 13, 21, 30, 46, 50, 51, 54, 56], "pdf": [3, 8], "2101": 3, "03961": 3, "necessari": [3, 24, 44, 56], "accommod": 3, "kind": [3, 4, 6], "pattern": [3, 23, 44, 55], "hybrid": 3, "evenli": 3, "partial": [3, 12, 29], "portion": [3, 44, 51], "matric": 3, "ep": [3, 44, 45], "further": [3, 4, 12, 16, 20, 22], "balanc": [3, 5, 12, 42, 56], "workload": [3, 21, 25, 41, 42], "enhanc": [3, 5, 40, 42, 51, 56], "effici": [3, 4, 5, 9, 12, 14, 29, 33, 34, 35, 37, 42, 43, 51, 56], "likelihood": [3, 29, 56], "bottleneck": [3, 20, 42], "alon": 3, "moe_tp_siz": 3, "moe_ep_s": 3, "convert_coneckpoint": 3, "py": [3, 4, 6, 8, 9, 10, 11, 12, 13, 15, 24, 25, 33, 34, 35, 36, 37, 38, 42, 43, 44, 47, 49, 50, 54, 55, 56], "tp_size": [3, 8, 11, 13, 15, 43, 44, 45, 48, 54, 55, 56], "num_experts_per_tok": 3, "num_local_expert": 3, "found": [3, 4, 5, 6, 12, 14, 17, 22, 24, 27, 42, 52, 54, 56], "gqa": [4, 16, 19, 42, 44, 55], "quick": [4, 23, 40], "remind": 4, "matmul": [4, 12, 42, 44, 52], "softmax": [4, 12, 44], "articl": [4, 56], "variant": [4, 15, 16, 22, 31, 44, 50, 55], "fewer": [4, 16, 42, 56], "gpt_attent": [4, 6, 19, 44, 50, 55], "discuss": [4, 55], "faster": [4, 15, 17, 18, 21, 43, 44], "plugin": [4, 5, 6, 9, 11, 23, 24, 25, 39, 44, 46, 50, 51, 52, 54, 55], "max_sequence_length": [4, 49], "excess": 4, "unneed": [4, 42], "variou": [4, 14, 25, 56], "surround": 4, "overcom": [4, 12], "problem": [4, 24], "togeth": [4, 5, 8, 12, 14, 16, 22, 27, 42, 49, 52, 55], "1d": [4, 44], "context_fmha_typ": [4, 51], "intermedi": [4, 12, 54], "q": [4, 5, 8, 16, 23, 44, 54], "slowest": 4, "footprint": [4, 16, 51], "signific": [4, 18, 56], "quadrat": [4, 51], "enabled_with_fp32_acc": 4, "forc": [4, 21], "vanilla": 4, "larger": [4, 5, 9, 17, 18, 20, 29, 42, 43, 44, 49, 51, 55, 56], "flash": [4, 12], "flashattent": [4, 12, 50], "fast": [4, 56], "exact": [4, 51], "io": [4, 37, 51, 55, 56], "awar": [4, 16, 54], "better": [4, 5, 13, 15, 19, 29, 42, 55, 56], "plan": [4, 25], "overal": [4, 29, 40, 56], "quantiz": [4, 5, 12, 13, 16, 17, 21, 23, 28, 31, 32, 39, 40, 42, 43, 44, 45, 46, 49, 50, 53, 55], "acceler": [4, 17, 18, 19, 20, 40, 56], "use_fp8_context_fmha": [4, 21, 42, 55, 56], "workflow": [4, 5, 10, 11, 23, 30, 43, 44, 50, 55], "use_paged_context_fmha": [4, 21, 29, 56], "experiment": [4, 5, 13, 25, 42, 52, 53, 55], "hopper": [4, 16, 17, 20, 23, 24, 29, 40, 42, 43, 53, 55], "decreas": [4, 16, 17, 42], "accuraci": [4, 16, 42, 44, 52, 55], "abl": [4, 17, 44, 55], "fly": [4, 44, 52], "dequant": [4, 23, 44], "ia3": 4, "special": [4, 8, 12, 13, 16, 39, 55], "occup": [4, 51], "low": [4, 10, 15, 20, 44, 55], "13": [4, 8, 19, 23, 27, 41, 43, 44, 54], "multi_block_mod": [4, 49, 55], "test": [4, 5, 20, 23, 24, 25, 42, 55], "scenario": [4, 11, 18, 20, 42, 43, 55, 56], "small": [4, 12, 20, 29, 44, 51, 55, 56], "definit": [4, 14, 15, 23, 40, 44, 50], "hard": 4, "rule": [4, 54], "thumb": [4, 54], "worth": 4, "batch_siz": [4, 6, 9, 11, 16, 19, 44, 45, 48, 49, 51], "num_head": [4, 13, 44, 46, 49], "suggest": [4, 20], "evolv": [4, 15, 40, 52], "research": [4, 33, 34, 35, 37, 52], "conduct": 4, "immedi": [4, 40, 54, 56], "There": [4, 5, 6, 8, 11, 15, 18, 24, 29, 30, 31, 42, 43, 44, 47, 51, 52, 54], "becom": [4, 5, 6, 12, 13, 20, 29, 40, 42], "heurist": [4, 44, 55], "proport": 4, "warn": [4, 21, 43, 44, 51], "still": [4, 13, 15, 40, 44, 49, 51], "llama2": [4, 8, 16, 17, 55], "70b": [4, 15, 18, 20, 43, 55], "fp16": [4, 8, 9, 11, 13, 16, 17, 20, 23, 42, 43, 44, 50, 53, 54, 55, 56], "bf16": [4, 13, 15, 23, 42, 53, 55], "disable_xqa": 4, "decid": [4, 11, 41, 52], "want": [4, 15, 24, 26, 41, 42, 44, 54, 55, 56], "trtllm_force_xqa": 4, "shouldus": 4, "decoderxqarunn": 4, "decodermaskedmultiheadattent": 4, "With": [4, 5, 12, 23, 30, 56], "purpos": [4, 24], "interleav": [4, 12], "go": [4, 5, 42, 55], "s0": 4, "s1": 4, "s2": 4, "relax": 4, "ineffici": 4, "origin": [4, 6, 8, 44, 55], "behavior": [4, 5, 43, 44, 49, 51, 55], "wai": [4, 6, 14, 25, 27, 31, 40, 44, 51], "best": [4, 12, 23, 24, 41, 50, 55, 56], "practic": [4, 12, 17, 18, 23, 50, 51, 55], "past": 4, "monolith": 4, "max_seqlen": [4, 44], "hidden_dim_per_head": [4, 44], "lot": [4, 12, 14, 29, 42], "decompos": 4, "track": 4, "recycl": 4, "simplifi": [4, 15, 44, 55], "bfloat16": [4, 21, 47, 52, 53, 55], "kv_cache_quant_mod": [4, 44], "int8_kv_cach": [4, 52, 55], "fp8_kv_cach": [4, 52], "kv_cache_scaling_factor": [4, 11], "invers": 4, "multipli": [4, 13, 44], "fp_valu": 4, "quantized_valu": 4, "treat": [4, 44], "circular": 4, "max_attention_window_s": [4, 42, 44, 49, 56], "generationsess": [4, 49, 51], "summar": [4, 9, 10, 11, 18, 20, 42, 43, 51, 56], "overwrit": [4, 26], "surpass": 4, "window_s": 4, "deal": [4, 6], "veri": [4, 11, 12, 14, 20, 42, 55], "long": [4, 20, 41, 51, 55], "simpli": [4, 40, 43, 54, 56], "torch": [4, 13, 24, 25, 27, 38, 39, 44, 49, 54], "save": [4, 15, 21, 29, 31, 34, 39, 42, 43, 51, 55, 56], "_note": 4, "stabl": [4, 13, 26, 27, 37, 44], "similar": [4, 5, 6, 16, 18, 25, 30, 41, 44, 56], "kept": [4, 15, 44], "sink_token_length": [4, 39, 49], "But": [4, 40], "self": [4, 6, 10, 12, 13, 39, 44, 46, 49, 54], "offici": 4, "distanc": [4, 44], "rather": [4, 6, 40, 56], "reconstruct": [4, 44], "correct": [4, 8, 22, 54, 56], "cache_indirect": [4, 44, 45, 49, 54], "beam_width": [4, 5, 7, 30, 39, 42, 44, 49], "si": 4, "bi": 4, "ti": 4, "concaten": [4, 8, 13, 44], "along": [4, 14, 44, 55, 56], "3d": [4, 44], "batch_beam_s": [4, 44], "hidden_dim": [4, 44], "num_token": [4, 44], "context_phas": 4, "generation_phas": 4, "rotary_embedding_dim": [4, 44], "fuse": [4, 12, 44, 50, 55, 56], "neox": [4, 5, 52, 53, 55], "j": [4, 5, 17, 20, 31, 44, 52, 53, 55], "form": [4, 22, 44, 50, 56], "position_embedding_typ": [4, 11, 44, 45, 46], "positionembeddingtyp": [4, 44, 45, 46], "rope_gpt_neox": [4, 44, 46], "rope_gptj": [4, 44], "slope": [4, 44], "norm_factor": 4, "q_scale": [4, 44, 45, 46], "sqrt": [4, 44], "head_siz": [4, 44, 46, 49, 55], "On": [4, 24, 25, 29, 42, 44, 55], "broader": [4, 55], "aspect": [4, 42], "issu": [4, 12, 15, 23, 27, 54], "accord": [4, 13, 44, 45, 56], "lightweight": 4, "popular": [4, 11, 15, 20, 31], "t5": [4, 5, 52, 53, 55], "famili": [4, 13, 53, 55], "ahead": [4, 56], "ii": [4, 44], "suit": [4, 43], "too": 4, "max_dist": [4, 44, 45], "api": [5, 10, 11, 12, 14, 23, 24, 29, 30, 31, 33, 34, 35, 36, 37, 38, 40, 41, 42, 44, 51, 54, 56], "section": [5, 7, 8, 12, 13, 15, 22, 24, 25, 31, 40, 42, 44, 50, 53, 55], "mention": [5, 15, 30], "restrict": [5, 24, 44], "bloom": [5, 13, 26, 52, 53, 55], "llama": [5, 8, 9, 13, 15, 17, 18, 20, 31, 42, 50, 52, 53, 55, 56], "now": [5, 11, 13, 16, 25, 40, 42, 47, 50, 51, 55, 56], "enc_dec": 5, "modelconfig": [5, 49, 55], "worldconfig": [5, 49], "come": [5, 8, 17, 25, 50, 51], "famou": [5, 38], "mpi_comm_world": 5, "getter": 5, "numlay": 5, "numhead": 5, "numkvhead": 5, "queri": [5, 12, 16, 23, 44, 51, 56], "pagedkvcach": 5, "relev": [5, 24, 25], "numer": [5, 23, 50, 53], "familiar": [5, 12], "lmm": 5, "main": [5, 7, 16, 19, 22, 26, 30, 33, 34, 35, 36, 37, 38, 39, 41, 44, 51, 54], "thing": [5, 33, 34, 35, 37], "locat": [5, 6, 12, 24, 25, 27, 38, 43, 44, 54, 56], "cluster": [5, 21], "collabor": [5, 38, 44], "bandwidth": [5, 12, 16, 17, 18, 20], "presenc": [5, 12], "nvlink": [5, 55], "consecut": 5, "happen": [5, 12, 22, 29, 51, 54], "boundari": [5, 12, 51], "harder": 5, "absenc": 5, "advantag": [5, 40], "interconnect": 5, "a100": [5, 15, 21, 43], "dgx": [5, 12], "comparison": [5, 17, 56], "hf": [5, 8, 9, 13, 21, 34, 35, 36, 37, 39, 43, 49, 54, 56], "assist": 5, "assistant_model": 5, "prompt_lookup_num_token": 5, "num_beam": [5, 49], "do_sampl": 5, "multinomi": 5, "constrain": [5, 20], "force_words_id": 5, "contrast": [5, 56], "penalty_alpha": 5, "top_k": [5, 39, 49, 55], "num_beam_group": 5, "greedi": [5, 7], "rang": [5, 29, 41, 44, 46, 51, 52, 53, 56], "infti": 5, "min_length": [5, 7, 39, 49], "repetition_penalti": [5, 7, 39, 49, 55], "occur": [5, 7, 29], "no_repeat_ngram_s": [5, 7, 39, 49], "onto": 5, "mutual": [5, 52], "top_p": [5, 31, 33, 34, 35, 36, 37, 38, 39, 49, 50], "0e": 5, "highest": [5, 6, 17, 18], "probil": 5, "candid": [5, 12, 56], "sort": [5, 44], "descendli": 5, "largest": [5, 16, 17, 18, 44], "factual": 5, "open": [5, 16, 25, 27, 38, 40, 54], "diversity_penalti": 5, "length_penalti": [5, 39, 49], "early_stop": [5, 7, 39, 49, 55], "score": 5, "lengthlengthpenalti": 5, "scalar": [5, 44], "gptsession": [5, 24, 29, 51, 55], "gptsessiontest": 5, "charg": [5, 12], "gptdecod": 5, "directli": [5, 6, 12, 15, 24, 25, 30, 31, 42, 44, 50], "custom": [5, 12, 15, 16, 21, 31, 40, 42, 44, 49, 55], "satisfi": [5, 13, 42, 55, 56], "separ": [5, 24, 41, 42, 43, 44, 49, 56], "biggest": [5, 29], "individu": 5, "revisit": 5, "maintain": [5, 8, 16, 17, 20, 52, 56], "develop": [5, 10, 11, 12, 15, 24, 25, 33, 34, 35, 37, 40, 44, 55], "could": [5, 6, 11, 27, 29, 34, 35, 36, 37, 39, 42, 51, 54, 55], "rebuild": 5, "pytorch": [6, 11, 14, 27, 44, 54, 55, 56], "ilay": [6, 12], "inetworkdefinit": [6, 12, 44], "gw": 6, "manipul": 6, "modifi": [6, 22, 27, 42, 56], "facilit": [6, 56], "modif": [6, 12], "gemm": [6, 50, 51, 55], "smoothquant": [6, 20, 23, 53, 55], "finer": 6, "grain": 6, "ideal": [6, 55], "would": [6, 7, 42, 43, 56], "lead": [6, 12, 29, 42, 56], "nest": 6, "flow": [6, 15], "scatter": [6, 44], "core": [6, 8, 12, 15, 16, 17, 19, 24, 25, 26, 55], "get_par": [6, 44], "get_us": [6, 44], "consum": [6, 44], "replace_all_uses_with": [6, 44], "miss": [6, 55], "especi": [6, 33, 34, 35, 37, 42, 56], "opaqu": 6, "world": [6, 21, 40, 43, 44], "wise": [6, 44, 55], "singleton": [6, 44], "flayerinfomemo": 6, "replace_input_with": 6, "replace_output_uses_with": 6, "redirect": [6, 39], "consist": [6, 15, 17, 40, 44, 52, 54], "patternrewrit": 6, "match_and_rewrit": 6, "complex": [6, 12, 56], "patternanalyz": 6, "analysi": [6, 23, 51], "analyz": [6, 41], "rewritepatternmanag": 6, "label": [6, 44, 46], "benefit": [6, 18, 20, 29, 40, 42, 55], "privileg": 6, "analysispatternmanag": 6, "vital": [6, 20], "certain": [6, 11, 40, 44, 53], "manner": 6, "routin": 6, "subtract": 6, "test_graph_rewrit": 6, "naivepatternrewriter_replaceaddwithsub": 6, "def": [6, 10, 12, 13, 15, 33, 35, 36, 37, 54, 56], "__init__": [6, 10, 12, 13, 39, 54], "super": [6, 10, 13, 15, 54], "replace_add_with_sub": 6, "root_lay": 6, "elementwis": [6, 44], "separate_match_rewrit": 6, "enter": [6, 43], "as_lay": 6, "elementwiseoper": [6, 44], "here": [6, 8, 9, 10, 11, 13, 15, 17, 18, 22, 24, 25, 30, 31, 41, 44, 49, 50, 51, 52, 54, 56], "elementwise_sum": 6, "net_guard": 6, "subgraph": [6, 44], "b": [6, 8, 12, 16, 17, 18, 19, 42, 44, 46, 49, 55], "get_input": 6, "get_output": [6, 12], "old": [6, 26, 29], "insert": [6, 12, 44], "elementwise_sub": 6, "dangl": 6, "prune": [6, 44, 56], "mark_as_remov": 6, "unnecessari": [6, 55], "illustr": [6, 14, 56], "four": [6, 11, 45, 56], "nearli": [6, 17], "never": [6, 42], "depriv": 6, "commonli": [6, 55], "gptattentionpluginremovepaddingrewritepass": 6, "gpt_attention_plugin_remove_pad": 6, "plugin_v2": 6, "plugin_namespac": 6, "plugin_typ": 6, "gptattent": 6, "flayer": 6, "assert": [6, 44, 55], "although": [6, 42], "black": 6, "box": 6, "tensor_input": 6, "qkv": [6, 8, 11, 13, 23, 44, 54, 55], "arg": [6, 15, 39, 46, 49, 55], "in_len": 6, "new_input": 6, "clone_input": 6, "arglist": 6, "float16": [6, 7, 8, 9, 10, 11, 15, 21, 43, 46, 47, 50, 54, 56], "new_out": 6, "replace_outputs_uses_with": 6, "quit": 6, "focu": [6, 20, 41], "real": [6, 24, 25, 44], "fuseattentionwithbiaspass": 6, "graph_rewrit": 6, "gptmanag": [7, 23, 29, 42, 55, 56], "mandatori": [7, 11, 22], "request_output_len": 7, "input_id": [7, 10, 29, 46, 49, 54], "num_input_token": 7, "suppli": [7, 14, 25], "applic": [7, 17, 20, 29, 40, 41, 54, 55, 56], "runtime_top_k": 7, "runtime_top_p": 7, "len_penalti": 7, "presence_penalti": [7, 39, 49, 55], "frequency_penalti": [7, 39, 49, 55], "random_se": [7, 39, 46, 49], "end_id": [7, 39, 49, 55], "pad_id": [7, 39, 49], "embedding_bia": [7, 39], "leav": [7, 42], "unchang": [7, 44, 56], "bad_words_list": [7, 49], "num_bad_word": 7, "scan": 7, "henc": 7, "bad_word_list": 7, "stop_words_list": [7, 49], "num_stop_word": 7, "prompt_embedding_t": [7, 45, 46, 49], "prompt_vocab_s": [7, 46, 49], "vocab": [7, 44, 49], "lora_task_id": [7, 8], "lora_weight": [7, 8], "lora_config": [7, 8, 39, 46], "subsequ": [7, 8, 29, 56], "oldest": [7, 8], "space": [7, 8, 24, 51], "ones": [7, 8], "num_lora_modules_lay": [7, 8], "hi": [7, 8, 56], "ho": [7, 8], "2b": [7, 23], "module_id": [7, 8], "layer_idx": [7, 8, 10, 44, 49], "return_log_prob": [7, 39], "return_context_logit": [7, 39], "return_generation_logit": [7, 39], "draft_input_id": 7, "draft_logit": 7, "format": [7, 11, 13, 15, 17, 20, 23, 24, 31, 40, 49, 50, 51, 54], "show": [7, 17, 22, 31, 43, 50, 51, 53], "output_id": [7, 49], "num_output_token": 7, "sequence_length": [7, 44, 45, 49, 54], "output_log_prob": [7, 49], "cum_log_prob": 7, "context_logit": [7, 39, 49], "generation_logit": [7, 49], "git": [8, 24, 25, 26, 27, 31, 50, 54, 56], "lf": [8, 24, 26, 31, 56], "clone": [8, 24, 25, 26, 27, 31, 50, 54], "huggingfac": [8, 10, 11, 13, 15, 31, 39, 43, 50, 54, 55], "co": [8, 31, 44, 50, 54], "qychen": 8, "luotuo": 8, "7b": [8, 9, 20, 43, 50, 55, 56], "kunish": 8, "japanes": 8, "alpaca": 8, "v0": [8, 16, 17, 18, 19, 27, 42, 43, 55], "base_model": 8, "convert_checkpoint": [8, 9, 10, 11, 15, 42, 50, 54, 55, 56], "model_dir": [8, 9, 10, 11, 13, 15, 46, 48, 50, 54, 56], "output_dir": [8, 9, 10, 11, 15, 21, 46, 48, 50, 54, 56], "tmp": [8, 9, 43, 56], "llama_7b": [8, 9], "trt_ckpt": [8, 9, 11, 54], "trtllm": [8, 9, 10, 11, 15, 27, 29, 30, 31, 42, 43, 50, 51, 54, 55, 56], "checkpoint_dir": [8, 9, 10, 11, 15, 21, 50, 54, 56], "llama_7b_with_lora_qkv": 8, "trt_engin": [8, 9, 11, 54], "gpt_attention_plugin": [8, 21, 42, 45, 49, 54, 55, 56], "context_fmha": [8, 21, 42, 56], "paged_kv_cach": [8, 21, 42, 49, 56], "gemm_plugin": [8, 9, 11, 21, 42, 45, 50, 56], "lora_plugin": [8, 21, 44, 49], "562": [8, 9], "lora_dir": [8, 21, 49], "max_lora_rank": [8, 21], "lora_target_modul": [8, 21, 46, 49], "attn_q": [8, 21], "attn_k": [8, 21], "attn_v": [8, 21], "script": [8, 10, 15, 24, 25, 27, 43, 47, 52, 54, 55, 56], "hug": [8, 9, 14, 15, 30, 46, 50, 55], "face": [8, 9, 14, 15, 30, 46, 50, 55], "numpi": [8, 44], "python3": [8, 9, 11, 24, 26, 27, 50, 54, 56], "hf_lora_convert": 8, "storag": [8, 39], "tensorrtllm_backend": [8, 50, 55, 56], "triton": [8, 12, 14, 23, 26, 29, 40, 55], "loraweight": 8, "lorataskid": 8, "attn_qkv": [8, 21], "num_lora_module_lay": 8, "layer1": 8, "hidden_size_in": 8, "hidden_size_out": 8, "2106": 8, "09685": 8, "paper": [8, 17, 52, 56], "compbin": 8, "attn_dens": [8, 21], "mlp_h_to_4h": [8, 21], "gate": [8, 13, 44], "mlp": [8, 10, 12, 13, 44, 54, 55], "rmsnorm": [8, 44, 45, 46, 55], "mlp_4h_to_h": [8, 21], "mlp_gate": [8, 21], "cross_attn_qkv": [8, 21], "cross_attn_q": [8, 21], "cross_attn_k": [8, 21], "cross_attn_v": [8, 21], "11": [8, 18, 20, 23, 24, 25, 42, 43, 44, 54, 56], "cross_attn_dens": [8, 21], "12": [8, 11, 17, 23, 25, 26, 27, 30, 41, 43, 44, 54], "moe_h_to_4h": [8, 21], "expert": [8, 23, 55], "moe_4h_to_h": [8, 21], "14": [8, 11, 20, 41, 43, 54], "moe_gat": [8, 21], "15": [8, 43, 54, 55], "moe_rout": [8, 21], "mlp_router": [8, 21], "17": [8, 43, 54], "qwen2": [8, 53, 55], "moe": [8, 13, 23, 46, 55], "idea": 8, "resid": [8, 38, 54], "distinct": [8, 44, 56], "percentag": [8, 9, 43], "rowlinear": [8, 45, 54], "columnlinear": [8, 10, 45, 54], "Then": [8, 15, 44, 54], "column": [8, 44, 52], "lora_rank": [8, 44], "budget": 9, "gpu_weights_perc": [9, 49], "weight_stream": [9, 21, 39], "engine_dir": [9, 10, 11, 15, 39, 43, 49, 50, 54, 56], "test_trt_llm": [9, 10, 11, 56], "hf_model_dir": [9, 10, 11, 15, 46, 56], "data_typ": [9, 11, 56], "benchmark": [9, 23, 25, 41, 42, 50, 55], "input_output_len": 9, "csv": [9, 41], "log_level": [9, 21, 56], "verbos": [9, 21, 56], "builder": [9, 12, 15, 21, 55], "buildconfig": [9, 15, 30, 39, 55], "create_builder_config": 9, "tle": 9, "model_path": 9, "concat": [10, 42, 44], "basic": [10, 26, 43, 44], "layernorm": [10, 42, 44, 45, 55], "high": [10, 12, 15, 16, 20, 22, 30, 42, 44, 51, 55], "decodermodelforcausallm": [10, 15, 46], "my_model": 10, "mydecoderlay": 10, "pretrainedconfig": [10, 15, 39, 46, 47], "input_layernorm": [10, 11, 13], "post_layernorm": [10, 11, 13, 44, 54], "hidden_st": [10, 44, 45, 46, 49, 54], "mymodel": 10, "vocab_embed": [10, 13], "decoderlayerlist": 10, "ln_f": [10, 13], "mymodelforcausallm": 10, "lm_head": [10, 13, 42], "sourc": [10, 11, 13, 15, 16, 19, 21, 23, 33, 34, 35, 36, 37, 38, 39, 40, 44, 45, 46, 47, 48, 49, 55, 56], "framework": [10, 11, 14, 15, 40, 44, 56], "classmethod": [10, 15, 39, 45, 46, 49], "from_hugging_fac": [10, 13, 15, 46], "cl": [10, 15], "checkpoint": [10, 13, 14, 15, 21, 23, 39, 48, 49, 50, 52, 54, 55], "dict": [10, 13, 15, 39, 44, 46, 49], "offlin": [10, 18, 31, 43], "At": [10, 25, 45, 51], "command": [10, 11, 15, 24, 25, 27, 29, 31, 42, 47, 51, 54, 55, 56], "cd": [10, 11, 24, 25, 26, 50, 54, 56], "tllm_ckpt_dir": 10, "tllm_engine_dir": 10, "tokenizer_dir": [10, 50, 54, 56], "input_text": [10, 49, 50, 56], "born": [10, 54], "north": [10, 54], "east": [10, 54], "franc": [10, 31, 33, 34, 35, 36, 37, 38, 50, 54], "soyer": [10, 54], "train": [10, 11, 14, 15, 17, 20, 54, 56], "md": [10, 42, 44, 55], "earlier": [11, 26, 54], "timelin": 11, "emphasi": 11, "unifi": [11, 15, 20, 55], "rich": 11, "team": [11, 15, 55], "effort": [11, 38, 56], "cli": [11, 23, 30, 50], "tool": [11, 23, 25, 27, 31, 42, 55, 56], "nemo": [11, 14, 21, 40, 49, 52, 53, 55], "modelopt": [11, 15, 48, 55], "modelrunn": [11, 49, 55], "jax": [11, 15], "deepspe": 11, "nvidia": [11, 12, 14, 15, 16, 17, 18, 20, 23, 24, 25, 26, 27, 33, 34, 35, 36, 37, 38, 40, 42, 44, 50, 51, 53, 54, 55, 56], "microsoft": [11, 25, 27], "One": [11, 12, 44, 54], "hyper": [11, 25], "dictionari": [11, 13, 45], "logits_dtyp": [11, 21, 46], "float32": [11, 21, 44, 45, 46, 47], "max_position_embed": [11, 42, 44, 45, 46], "num_hidden_lay": [11, 46], "num_attention_head": [11, 44, 45, 46], "num_key_value_head": [11, 46], "hidden_act": [11, 45, 46], "intermediate_s": [11, 46], "norm_epsilon": [11, 46], "1e": [11, 44, 45, 46], "learned_absolut": [11, 44, 45, 46], "world_siz": [11, 15, 33, 44, 55], "pp_size": [11, 48, 55, 56], "quant_algo": [11, 13, 15, 30, 38, 39, 46], "str": [11, 15, 35, 36, 39, 44, 45, 46, 49], "kv_cache_quant_algo": [11, 38, 39], "group_siz": [11, 39, 44], "has_zero_point": [11, 39], "pre_quant_scal": [11, 39], "exclude_modul": [11, 39, 55], "sub": [11, 15, 43, 44], "optforcausallm": [11, 46], "w8a16": [11, 20, 23, 39, 46], "w4a16": [11, 20, 23, 39, 46], "w4a16_awq": [11, 15, 30, 38, 39], "w4a8_awq": [11, 15, 39], "w4a16_gptq": [11, 39], "w8a8_sq_per_channel": [11, 39], "extens": [11, 14, 40, 55], "opt": [11, 20, 22, 44, 52, 53, 55], "do_layer_norm_befor": 11, "falcon": [11, 20, 31, 52, 53, 55], "new_decoder_architectur": [11, 46], "parallel_attent": [11, 46], "hierarch": 11, "whose": [11, 29, 45], "bias": [11, 44], "fc": [11, 12, 13, 54], "proj": [11, 13, 54], "activation_scaling_factor": 11, "weights_scaling_factor": [11, 13], "prequant_scaling_factor": 11, "out_featur": [11, 12, 45], "in_featur": [11, 12, 45], "wherea": 11, "out_fatur": 11, "transpos": [11, 44], "deploi": [11, 23, 24, 27, 40, 56], "125m": [11, 56], "rank0": 11, "safetensor": [11, 13, 54, 55], "rank1": 11, "768": [11, 43], "50272": 11, "2048": [11, 16, 18, 19, 21, 43, 46, 49, 56], "relu": [11, 12, 44, 54], "use_parallel_embed": [11, 42, 46], "embedding_sharding_dim": [11, 42, 46], "share_embedding_t": [11, 39, 46], "export": [11, 15, 21, 25, 48, 49, 55, 56], "usr": [11, 24], "local": [11, 12, 24, 25, 26, 27, 34, 35, 36, 37, 39, 40, 43, 55], "bin": [11, 13, 26, 41, 54, 55], "924": [11, 43], "mpirun": [11, 41, 54, 55], "root": [11, 24, 25, 39, 44, 50], "check_accuraci": 11, "tensorrt_llm_rouge1_threshold": 11, "power": [12, 18, 20, 29, 40], "deep": [12, 17, 18, 41, 44], "concept": 12, "proceed": 12, "create_network": 12, "iactivationlay": 12, "act_typ": [12, 44], "activationtyp": [12, 44], "default_trtnet": 12, "add_activ": 12, "trt_tensor": [12, 44], "_create_tensor": 12, "easier": [12, 15], "few": [12, 15, 20, 29, 43], "standard": [12, 14, 16, 43, 44, 56], "deriv": [12, 13, 51], "sigmoid": [12, 44], "assembl": [12, 14], "advanc": [12, 19, 24, 25, 33, 34, 35, 37, 44, 55, 56], "silu": [12, 44], "travers": 12, "build_engin": 12, "build_serialized_network": 12, "everyth": 12, "binari": [12, 41, 44, 56], "sweep": [12, 17], "choos": [12, 15, 44, 55], "crucial": [12, 20, 56], "amount": [12, 29, 39, 42, 49, 51, 54], "movement": 12, "overhead": [12, 22, 55], "extrem": 12, "speed": [12, 17, 55], "discov": 12, "highli": [12, 41, 56], "emb": [12, 45], "tensorrt_llm_gpt": 12, "fromfil": 12, "refit": [12, 21, 55], "refit_engin": 12, "kei": [12, 16, 20, 22, 23, 29, 39, 43, 46, 49, 54], "transfer": [12, 55], "dram": 12, "multiprocessor": 12, "cost": [12, 29, 51, 55], "classic": [12, 23], "usual": [12, 15, 25, 42, 43, 44, 54], "preced": [12, 44], "written": [12, 44, 56], "again": [12, 54], "suboptim": 12, "twice": 12, "almost": [12, 51], "infinit": [12, 43], "multihead": [12, 16], "arithmet": 12, "bmm": 12, "stand": [12, 43], "trivial": 12, "someth": [12, 30], "polyhedr": 12, "uncommon": 12, "inevit": 12, "offer": [12, 14, 20, 40], "interfac": [12, 15, 49], "extend": [12, 29, 42, 44], "guid": [12, 20, 23, 40, 41, 44, 54], "fairli": 12, "quantizetensorplugin": 12, "inputdesc": 12, "invokequant": 12, "els": [12, 13, 15, 30, 38, 41, 44, 54, 56], "cu": 12, "quantizedkernel": 12, "grid": 12, "role": 12, "drive": 12, "bodi": 12, "primit": [12, 40, 50], "nccl": [12, 44, 54, 55], "librari": [12, 14, 24, 25, 40, 54, 55], "connect": 12, "nvswitch": 12, "ncclplugin": 12, "allreduc": [12, 42, 44, 55], "allgath": [12, 44], "gather_dim": [12, 44], "tgt": [12, 44], "recv": [12, 44], "former": [12, 20], "sibl": 12, "incur": 12, "term": [12, 31, 42, 44, 50], "easili": [13, 14, 40, 44], "g": [13, 25, 27, 41, 42, 49, 56], "embed_token": 13, "down_proj": 13, "inter_s": 13, "gate_proj": 13, "up_proj": 13, "post_attention_layernorm": 13, "self_attn": 13, "q_proj": 13, "k_proj": 13, "v_proj": 13, "o_proj": 13, "external_kei": 13, "external_weight": 13, "tllm_kei": [13, 45], "tllm_weight": 13, "target": [13, 21, 24, 30, 42, 56], "dot": [13, 44], "keyword": [13, 51], "tllm_to_externel_key_dict": 13, "modelweightsload": [13, 55], "accordingli": 13, "qweight": 13, "qzero": 13, "scale": [13, 42, 44, 52, 55], "customized_key_dict": 13, "norm": [13, 43, 44, 55], "arbitrari": [13, 55], "tp_dim": 13, "tp_rank": [13, 44, 45], "load_tensor": 13, "shard_map": 13, "ptr_idx": 13, "shard": [13, 42, 44, 45], "modelweightsformat": 13, "get_slic": 13, "tensor_shap": 13, "get_shap": 13, "slice_shap": 13, "detect_format": 13, "pth": [13, 55], "preload": 13, "stack": [13, 24, 44], "customizedmodulea": 13, "inherit": [13, 15, 44], "kwarg": [13, 15, 39, 45, 46, 49, 55], "proc": 13, "customizedmoduleb": 13, "endswith": 13, "proccessed_weight": 13, "proccessed_zero": 13, "model_weights_load": 13, "external_checkpoint_dir": 13, "generate_tllm_weight": 13, "trtllm_model": 13, "calibr": [13, 20, 39, 55], "llava": [13, 52, 53, 55], "llava_dict": 13, "language_model": 13, "exaon": [13, 53, 55], "llamaforcausallm": [13, 15, 46], "bloom_dict": 13, "word_embed": 13, "ln_emb": 13, "word_embeddings_layernorm": 13, "self_attent": 13, "query_key_valu": 13, "dense_h_to_4h": 13, "dense_4h_to_h": 13, "update_key_map": 13, "_": [13, 47], "tqdm": [13, 39, 55], "named_paramet": 13, "callabl": [13, 39, 46], "preprocess": [13, 49, 52, 56], "customized_preprocess": 13, "demonstr": [13, 17, 22], "wo": [13, 55], "int4": [13, 15, 20, 21, 23, 30, 53, 55], "qwen": [13, 31, 52, 53, 55], "qwenforcausallm": 13, "xxx": [13, 15], "failur": [13, 55], "caus": [13, 15, 21, 27, 55], "workaround": [13, 55], "environment": 13, "trtllm_disable_unified_convert": 13, "fallback": 13, "legaci": [13, 47], "toolkit": [14, 15, 20, 25, 26, 27], "solut": [14, 54], "web": 14, "servic": [14, 38, 56], "your": [14, 15, 20, 21, 24, 25, 26, 27, 29, 30, 40, 41, 42, 50, 54, 56], "outsid": [14, 15, 56], "scope": [14, 55], "download": [14, 25, 27, 31, 50, 54, 55], "hub": [14, 50, 55], "equip": 14, "recreat": 14, "eas": [14, 40], "hand": [14, 29, 56], "onlin": [14, 18, 31, 42], "pull": [14, 24, 50, 55], "pretrain": 14, "repositori": [14, 25, 27, 31, 50, 56], "major": [15, 38, 40, 51], "convent": [15, 44], "shall": [15, 51], "had": 15, "migrat": [15, 47, 55], "ship": [15, 54], "disadvantag": 15, "lib": [15, 25, 27], "quickli": [15, 50], "date": 15, "thu": [15, 29, 44, 51], "And": [15, 25, 44, 45, 51, 56], "hoc": [15, 49], "mitig": 15, "refactor": [15, 55], "sit": 15, "ongo": [15, 38], "topmodelmixin": [15, 46], "introduc": [15, 17, 24, 52, 55], "direct": [15, 54], "hierarchi": [15, 44], "rais": [15, 54, 55], "notimplementederror": 15, "greatli": [15, 29], "affect": [15, 51], "simplic": 15, "save_checkpoint": [15, 46], "save_config": [15, 46], "disk": [15, 24, 31, 34], "intention": 15, "slower": 15, "meta": [15, 31, 43, 50], "from_meta_ckpt": [15, 46], "don": [15, 44, 56], "from_jax": 15, "from_nemo": [15, 46], "from_kera": 15, "factori": [15, 39, 49, 55], "gemma": [15, 31, 52, 53, 55], "kera": 15, "contribut": [15, 44, 55], "freedom": 15, "read_config_from_the_custom_training_checkpoint": 15, "weights_dict": 15, "convert_weights_from_custom_training_checkpoint": 15, "assign": [15, 45, 47, 56], "convert_and_load_weights_into_trtllm_llama": 15, "though": [15, 51], "pitfal": [15, 29], "fp8": [15, 16, 18, 19, 20, 21, 23, 38, 39, 43, 44, 47, 51, 53, 55, 56], "smooth": [15, 55], "quant": [15, 55], "standalon": 15, "pretrainedmodel": [15, 46, 51], "quant_config": [15, 30, 38, 39, 46], "quantconfig": [15, 30, 38, 39, 46, 55], "quanticonfig": 15, "use_modelopt_quant": 15, "nativ": [15, 17, 42, 55], "140g": 15, "70g": 15, "210g": 15, "h100": [15, 20, 21, 40, 43, 56], "program": [15, 25, 27, 33, 34, 35, 37, 42, 50, 56], "cautiou": 15, "mpi_barri": 15, "quant_mod": [15, 39, 45, 46, 49], "from_checkpoint": [15, 46], "build_config": [15, 21, 30, 39, 46], "backward": 15, "compat": [15, 53, 55, 56], "older": [15, 27, 29], "trace": 15, "thin": 15, "deseri": 15, "ckpt_dir": [15, 46, 56], "promis": 15, "unstabl": 15, "instal": [15, 24, 25, 31, 40, 50, 55, 56], "mismatch": [15, 54], "github": [15, 24, 25, 26, 31, 33, 34, 35, 36, 37, 38, 40, 44, 50, 55], "com": [15, 24, 25, 26, 27, 33, 34, 35, 36, 37, 38, 44, 50, 54, 55], "1293": 15, "1252": 15, "1079": 15, "txt": [15, 26, 50, 55, 56], "natur": 15, "sure": [15, 24, 26, 27, 42, 44, 54, 55], "gradual": 15, "span": 15, "accur": [16, 55], "141gb": [16, 43], "eight": 16, "800": [16, 55], "tok": [16, 18, 19], "retain": [16, 18], "great": [16, 56], "preliminari": [16, 18, 19], "measur": [16, 18, 19, 20, 23], "subject": [16, 18, 19, 20, 31, 44, 50], "tp1": [16, 17, 18, 56], "7a": 16, "1xh200": 16, "advers": 16, "4x": [16, 17, 18], "lin": 16, "et": 16, "al": 16, "2023": [16, 41, 54], "compress": 16, "4bit": 16, "rel": [16, 29, 44, 55], "capabl": [16, 24, 40, 41], "performantli": 16, "achiev": [16, 20, 42, 43, 56], "803": [16, 43], "941": [16, 19, 43], "163": [16, 43], "4096": [16, 30, 43, 49], "946": [16, 43], "263": [16, 30, 43], "8xh200": 16, "dp": [16, 19], "960": [16, 43], "192": 16, "560": [16, 43], "96": [16, 43, 55], "640": 16, "6a": 16, "ainsli": 16, "publish": [16, 19, 55], "branch": [16, 19, 26], "announc": [16, 17, 19], "blog": [16, 19, 20, 26, 55], "calcul": [16, 17, 19, 42, 44, 51, 55], "out_tp": [16, 19], "output_seqlen": [16, 19], "total_lat": [16, 19], "glossari": [16, 19], "osl": [16, 17, 18, 19, 43], "oom": [16, 19, 51], "bangbang": 17, "h200": [17, 43], "learn": [17, 18, 20, 33, 34, 35, 37, 44, 50], "sec": [17, 43], "13b": 17, "evalu": [17, 18, 23, 55], "amper": [17, 24, 40, 43, 53, 55], "1st": [17, 44, 51], "10m": 17, "sxm": [17, 21], "80gb": [17, 20, 21, 43], "success": [17, 43], "6b": [17, 43, 44, 55], "907": 17, "102": [17, 29], "185": 17, "679": [17, 43], "481": 17, "111": 17, "speedup": [17, 19, 20], "0x": 17, "7x": 17, "behind": 17, "chart": 17, "stai": [17, 20], "highlight": [17, 20], "5x": [17, 20], "2x": [17, 18], "center": [17, 18], "ai": [17, 31, 33, 34, 35, 36, 37, 38, 40, 44, 50], "hpc": 17, "analyt": 17, "cloud": 17, "edg": 17, "workstat": [17, 40], "halv": [17, 44], "e4m3": 17, "expon": 17, "mantissa": 17, "e5m2": 17, "gradient": 17, "perceiv": 17, "w8a8": [17, 20, 23], "8bit": 17, "loudspeak": 18, "819": [18, 43], "9x": [18, 19], "hbm3e": 18, "llama_13b": 18, "750": 18, "349": [18, 43], "llama_70b": 18, "014": 18, "654": [18, 43], "341": 18, "303": [18, 43], "v9": 18, "tp8": 18, "chat": [18, 31, 33, 34, 35, 36, 37, 38, 50, 55], "agent": 18, "80": [18, 24, 43, 55], "200": [18, 43, 49], "gpt3": 18, "175b": 18, "hgx": 18, "6x": 18, "vari": 18, "swept": 18, "newest": 18, "portfolio": 18, "8tb": 18, "expand": [18, 20, 44, 55], "141": 18, "gigabyt": 18, "gb": [18, 24, 25, 39], "experi": [19, 20, 27, 40, 41, 56], "curv": 19, "equat": [19, 44], "tpot": 19, "axi": [19, 44], "8xh100": 19, "8a": 19, "227": [19, 43], "232": [19, 43], "25": [19, 43, 54], "300": 19, "deploy": [20, 26, 40, 50], "imped": 20, "emerg": 20, "overview": [20, 22, 23, 24, 41], "appropri": [20, 30, 42, 54], "tailor": 20, "dl": 20, "genai": 20, "hardwar": [20, 23, 24, 30, 55], "easi": 20, "mind": [20, 42], "line": [20, 25, 29, 51, 55], "ptq": [20, 42, 55], "impos": 20, "v2": [20, 43, 52, 55], "500m": 20, "notabl": 20, "3x": 20, "sq": [20, 52, 55], "40x": 20, "44x": 20, "30x": 20, "51x": 20, "47x": 20, "32x": 20, "mmlu": 20, "baselin": 20, "loss": 20, "180b": 20, "70": [20, 43, 51], "68": [20, 43], "56": [20, 43], "awq": [20, 23, 30, 53, 55], "69": [20, 43], "85": [20, 43, 55], "40b": 20, "55": [20, 41, 43], "89": [20, 24, 25, 43, 53], "54": [20, 43], "07": [20, 43, 53, 55], "87": [20, 43], "67": [20, 43], "75": [20, 43, 53, 55], "01": [20, 43, 51], "mpt": [20, 52, 53, 55], "30b": [20, 56], "47": [20, 43], "21": [20, 43, 54, 56], "46": [20, 43], "compris": 20, "consider": [20, 30], "prefer": [20, 24], "densiti": 20, "factor": [20, 42, 44, 51, 52], "consequ": 20, "speicfic": 20, "priorit": 20, "meet": 20, "gptq": [20, 23, 53, 55], "toler": 20, "tradeoff": 20, "our": [20, 25, 33, 34, 35, 37, 41, 55], "medium": [20, 54, 55], "ten": [20, 56], "w4a8": 20, "ll": [20, 25, 42], "occupi": [20, 51], "neglig": [20, 29], "re": [20, 25, 27, 40, 42, 55, 56], "ada": [20, 24, 38, 40, 43, 53, 55], "latter": [20, 42, 55], "machin": [20, 25, 29, 55], "bring": 20, "upcom": 20, "model_config": [21, 49], "model_cls_fil": 21, "model_cls_nam": 21, "max_num_token": [21, 30, 39, 46, 51, 55], "opt_num_token": [21, 39, 46], "max_encoder_input_len": [21, 39, 46], "max_prompt_embedding_table_s": [21, 39, 49, 55], "kv_cache_typ": [21, 39, 49], "input_timing_cach": [21, 39], "output_timing_cach": [21, 39], "builder_opt": [21, 39], "profiling_verbos": [21, 39], "layer_names_onli": [21, 39], "builder_force_num_profil": 21, "strip_plan": 21, "weight_spars": [21, 39], "fast_build": [21, 55], "internal_error": 21, "info": [21, 41, 51, 54], "enable_debug_output": [21, 39, 54], "visualize_network": [21, 39, 55], "dry_run": [21, 39, 55], "lora_ckpt_sourc": [21, 49], "speculative_decoding_mod": [21, 39, 56], "draft_tokens_extern": [21, 46, 56], "lookahead_decod": [21, 46, 56], "explicit_draft_token": [21, 46, 56], "max_draft_len": [21, 39, 46, 48, 56], "auto_parallel": [21, 33, 39, 55], "gpus_per_nod": 21, "cluster_kei": 21, "40gb": 21, "pcie": 21, "h20": 21, "v100": [21, 55], "16gb": 21, "32gb": 21, "a40": 21, "a30": 21, "a10": 21, "a10g": 21, "l40": [21, 43], "l20": 21, "l4": 21, "l2": 21, "bert_attention_plugin": [21, 42], "gemm_swiglu_plugin": [21, 42, 43, 47], "fp8_rowwise_gemm_plugin": 21, "nccl_plugin": 21, "lookup_plugin": [21, 42, 44], "moe_plugin": 21, "mamba_conv1d_plugin": [21, 49], "low_latency_gemm_plugin": [21, 45], "bert_context_fmha_fp32_acc": 21, "reduce_fus": [21, 42], "enable_xqa": 21, "tokens_per_block": [21, 29, 42, 49, 55], "multiple_profil": [21, 42, 55], "paged_st": [21, 49], "use_fused_mlp": [21, 39, 42, 43, 55], "serial": [21, 44, 46, 49], "engine_output": 21, "max_decoder_seq_len": 21, "deduc": [21, 55], "8192": [21, 42, 43, 55], "enc": [21, 55], "dec": [21, 55], "decoder_start_token_id": 21, "max_multimodal_len": 21, "equvili": 21, "ignor": [21, 44], "inspect": [21, 51], "tactic": 21, "strip": [21, 55], "assumpt": [21, 56], "sparsiti": 21, "degrad": 21, "incompat": 21, "onnx": [21, 44], "prior": 21, "workspac": [21, 25, 39, 44, 51], "spec": 21, "_cpp_gen": 22, "rst": 22, "neither": [22, 44, 51], "side": 22, "expens": [22, 40, 42, 56], "infeas": 22, "properti": [22, 39, 44, 46, 47, 49], "what": [22, 23, 41, 42], "check": [22, 25, 26, 27, 31, 44, 49, 50, 51, 54, 55], "reconfigur": 22, "itself": [22, 49], "prematur": 22, "interpret": [22, 24], "prerequisit": [23, 27], "linux": [23, 25, 53], "docker": [23, 26, 50, 54, 55, 56], "imag": [23, 26, 49, 55, 56], "bind": [23, 39, 49, 51, 55], "link": [23, 29, 55], "bare": 23, "metal": 23, "prepar": [23, 44, 46, 52, 55, 56], "verifi": [23, 25, 27, 44, 55, 56], "cyclic": [23, 44, 49], "roll": 23, "rewrit": [23, 44, 55], "mixtur": [23, 55], "reproduc": [23, 42, 55], "dataset": [23, 55, 56], "coordin": [23, 44, 56], "nsight": [23, 25], "ifb": [23, 55, 56], "troubleshoot": [23, 55], "cudnn": [23, 25, 27, 55], "e2": 23, "tip": 23, "dq": 23, "technic": 23, "understand": [23, 24, 41, 50], "faq": 23, "instruct": [24, 50, 55, 56], "gnu": 24, "abi": 24, "platform": [24, 33, 34, 35, 37], "apt": [24, 26, 56], "submodul": [24, 25], "recurs": [24, 25], "approxim": 24, "63": [24, 41, 43, 46, 51], "release_build": 24, "cuda_arch": 24, "cmake": [24, 25, 56], "release_run": [24, 50], "local_us": [24, 50], "account": 24, "app": [24, 55], "tag": [24, 27], "devel": [24, 26], "latest": [24, 25, 26, 27, 50], "dockerfil": [24, 25], "rm": [24, 26, 44, 54, 56], "ipc": [24, 26], "ulimit": [24, 54], "memlock": [24, 54], "67108864": 24, "pwd": [24, 56], "workdir": 24, "bu": [24, 26], "build_wheel": [24, 25], "trt_root": [24, 25], "pip": [24, 25, 26, 27, 50, 54], "whl": [24, 25, 27, 54], "increment": 24, "clean": [24, 41, 54], "semicolon": 24, "cuda_architectur": 24, "86": [24, 43], "wheel": [24, 25], "consult": [24, 41, 56], "cpp_onli": 24, "particularli": [24, 25], "dual": 24, "gcc": 24, "overridden": 24, "build_dir": 24, "libtensorrt_llm": 24, "against": [24, 25], "libnvinfer_plugin_tensorrt_llm": 24, "27": [25, 43], "visual": [25, 27, 55], "studio": [25, 27], "2022": [25, 27], "unzip": 25, "26": [25, 43], "right": [25, 40, 44], "click": 25, "icon": 25, "trai": 25, "bottom": 25, "taskbar": 25, "tab": 25, "uncheck": 25, "wsl": 25, "cp": [25, 56], "mount": 25, "manual": [25, 26, 30, 49, 54], "12g": 25, "dll": [25, 27], "nvtx": [25, 41], "asset": 25, "drop": [25, 42], "deselect": 25, "setup_build_env": 25, "ps1": [25, 27], "powershel": [25, 27], "administr": [25, 27], "trtpath": 25, "skipcmak": 25, "skipvsbuildtool": 25, "skiptrt": 25, "reopen": 25, "userprofil": [25, 27], "bash": [25, 26, 27, 41], "pick": [25, 27], "uninstal": [25, 26, 27, 54], "tensorrt_lib": [25, 27], "tensorrt_bind": [25, 27, 44], "cubla": [25, 27], "cu12": [25, 27, 55], "nvrtc": [25, 27], "__version__": 25, "x86": [25, 29], "buildtool": 25, "common7": 25, "vsdevshel": 25, "arch": 25, "amd64": 25, "gui": 25, "path_to_trt_root": 25, "geforc": [25, 40], "40": [25, 43, 55], "seri": 25, "card": 25, "enable_multi_devic": 25, "impli": 25, "wish": 25, "exp": [25, 44], "stub": 25, "nvinfer_plugin_tensorrt_llm": 25, "th_common": 25, "thop": 25, "append": [25, 38, 44], "appdata": [25, 27], "python310": [25, 27], "site": [25, 27], "entrypoint": 26, "ubuntu22": 26, "04": [26, 43], "openmpi": [26, 55], "libopenmpi": 26, "dev": 26, "preview": [26, 55], "pip3": [26, 56], "url": [26, 27, 54, 56], "pypi": [26, 27, 54], "upgrad": [26, 50, 54], "beta": [27, 44], "setup_env": 27, "skipcuda": 27, "skippython": 27, "ex": 27, "navig": 27, "express": [27, 44], "conda": [27, 55], "forg": 27, "pyarrow": 27, "_util": [27, 44], "trt_version": 27, "oserror": [27, 55], "violat": [27, 55], "0x0000000000000000": [27, 55], "outdat": 27, "redistribut": 27, "msvc": 27, "retri": 27, "system32": 27, "mscv": 27, "winerror": 27, "126": [27, 43], "fbgemm": 27, "resolv": [27, 54], "enable_kv_cache_reus": [29, 56], "string_valu": 29, "obsolet": 29, "fake": 29, "incorrect": [29, 56], "distinguish": 29, "correctli": [29, 42, 55], "vocaburlai": 29, "100": [29, 50], "99": [29, 43], "101": [29, 43], "103": [29, 43], "extra_id": 29, "bigger": 29, "realiz": [29, 56], "seem": 29, "reusabl": 29, "propag": [29, 55], "frequent": 29, "chanc": [29, 42], "matter": 29, "trade": 29, "off": [29, 41, 51], "vice": [29, 38], "versa": 29, "grace": 29, "yield": [29, 30], "net": [29, 54], "unlik": [29, 56], "kv_host_cache_byt": 29, "45000000000": 29, "45": [29, 43], "gib": [29, 51], "substanti": [29, 56], "kv_cache_host_memory_byt": 29, "upon": [29, 43, 54, 56], "hlapi": [30, 38, 39, 55], "quantalgo": [30, 38, 39, 46, 48], "dir": [30, 31, 54], "samplingparam": [30, 31, 33, 34, 35, 36, 37, 38, 39, 50, 55], "sampling_param": [30, 31, 33, 34, 35, 36, 37, 38, 39, 50], "llama_model_path": 30, "apart": 30, "borrow": 30, "runtime_config": 30, "peft_cache_config": [30, 39], "kv_cache_config": [30, 39], "free_gpu_memory_fract": [30, 39, 55], "autotoken": 30, "my_faster_on": 30, "skip_tokenizer_init": [30, 39], "generate_async": [30, 35, 36, 39, 55], "requestoutput": [30, 39, 55], "request_id": [30, 39], "prompt_token_id": [30, 39], "15043": 30, "29892": 30, "590": [30, 43], "338": [30, 43], "completionoutput": [30, 39], "token_id": 30, "518": 30, "10858": 30, "4408": 30, "29962": 30, "322": 30, "306": 30, "626": [30, 43], "20627": 30, "472": [30, 43], "6938": 30, "1822": 30, "5007": 30, "304": [30, 43], "4653": 30, "4066": 30, "297": [30, 43], "278": [30, 43], "11947": 30, "18527": 30, "2602": 30, "cumulative_logprob": 30, "deactiv": 30, "async": [30, 31, 32, 49], "aresult": 30, "tinyllama": [31, 33, 34, 35, 36, 37, 38, 50], "hello": [31, 33, 34, 35, 36, 37, 38, 50], "presid": [31, 33, 34, 35, 36, 37, 38, 50], "capit": [31, 33, 34, 35, 36, 37, 38, 50], "95": [31, 33, 34, 35, 36, 37, 38, 42, 43, 50], "1b": [31, 33, 34, 35, 36, 37, 38, 50], "generated_text": [31, 50], "fulli": [31, 55], "internlm": [31, 52, 53, 55], "starcod": [31, 53, 55], "santacod": [31, 52, 53], "phi": [31, 44, 52, 53, 55], "chatglm": [31, 44, 52, 53, 55], "glm": [31, 44, 53, 55], "10b": [31, 44, 55], "chatglm2": [31, 53, 55], "chatglm3": [31, 46, 53, 55], "glm4": [31, 55], "baichuan": [31, 52, 53, 55], "interchang": 31, "repo": [31, 40, 50, 56], "8b": [31, 43, 50], "path_to_meta_llama_from_hf": 31, "licens": [31, 50], "agre": [31, 50], "authent": [31, 50], "begin": [31, 40, 56], "readm": [31, 43, 55, 56], "path_to_trt_engin": 31, "reload": 31, "llm_auto_parallel": 33, "got": [33, 34, 35, 36, 37, 38], "njane": [33, 34, 35, 36, 37], "smith": [33, 34, 35, 36, 37, 38], "am": [33, 34, 35, 37, 38, 49], "student": [33, 34, 35, 37], "pursu": [33, 34, 35, 37], "degre": [33, 34, 35, 37], "scienc": [33, 34, 35, 37], "univers": [33, 34, 35, 37], "enjoi": [33, 34, 35, 37], "technologi": [33, 34, 35, 37], "nomin": [33, 34, 35, 36, 37], "suprem": [33, 34, 35, 37], "court": [33, 34, 35, 37], "justic": [33, 34, 35, 37], "seat": [33, 34, 35, 37], "vacat": [33, 34, 35, 37], "death": [33, 34, 35, 37], "antonin": [33, 34, 35, 37], "scalia": [33, 34, 35, 37], "senat": [33, 34, 35, 37], "vote": [33, 34, 35, 37], "confirm": [33, 34, 35, 37], "pari": [33, 34, 35, 36, 37, 38], "excit": [33, 34, 35, 36, 37], "constantli": [33, 34, 35, 37], "__name__": [33, 37], "__main__": [33, 37], "llm_gener": 34, "tempfil": 34, "mkdtemp": 34, "llm_generate_async": 35, "asyncio": [35, 36], "coroutin": [35, 36], "llm_generate_async_stream": 36, "exc": 36, "nj": 36, "llm_generate_distribut": 37, "tensor_parallel_s": [37, 39], "mpi4pi": [37, 54, 55], "readthedoc": 37, "en": 37, "mpipoolexecutor": 37, "llm_quantiz": 38, "minor": [38, 55], "get_device_cap": 38, "post_ada": 38, "jane": 38, "citi": 38, "tell": [38, 41], "me": 38, "area": 38, "estim": 38, "million": 38, "home": 38, "artist": 38, "picasso": 38, "invit": 38, "nour": 38, "pretrainedtokenizerbas": 39, "tokenizerbas": 39, "revis": 39, "tokenizer_revis": 39, "union": [39, 44], "detoken": 39, "tokenzier_revis": 39, "calib_config": 39, "calibconfig": 39, "embedding_parallel_mod": 39, "sharding_along_vocab": 39, "decoding_config": 39, "logits_post_processor_map": 39, "scheduler_config": 39, "normalize_log_prob": [39, 56], "iter_stats_max_iter": 39, "request_stats_max_iter": 39, "batching_typ": 39, "enable_build_cach": [39, 55], "buildcacheconfig": 39, "enable_tqdm": 39, "displai": 39, "bar": 39, "use_tqdm": 39, "lora_request": 39, "lorarequest": 39, "promptinput": [39, 55], "generation_result": 39, "generationresult": 39, "handle_respons": 39, "max_token": 39, "max_new_token": [39, 49, 51], "bad_token_id": 39, "stop_token_id": 39, "include_stop_str_in_output": 39, "external_draft_tokens_config": 39, "prompt_tuning_config": 39, "logits_post_processor_nam": 39, "top_p_min": [39, 49], "top_p_reset_id": [39, 49], "top_p_decai": [39, 49], "min_token": 39, "beam_search_diversity_r": [39, 49], "exclude_input_from_output": 39, "return_encoder_output": [39, 49], "add_special_token": [39, 49, 55], "exclud": [39, 44, 55], "pybind11_object": 39, "enable_block_reus": 39, "max_attention_window": [39, 55], "host_cache_s": 39, "onboard_block": 39, "capacity_scheduler_polici": 39, "context_chunking_polici": 39, "static_batch": 39, "opt_batch_s": [39, 46], "strongly_typ": [39, 55], "force_num_profil": 39, "modeling_util": 39, "speculativedecodingmod": [39, 46, 55], "use_refit": 39, "lora_manag": [39, 49, 55], "auto_parallel_config": 39, "autoparallelconfig": 39, "plugin_config": [39, 44, 46], "pluginconfig": [39, 47], "use_strip_plan": 39, "from_dict": [39, 46], "from_json_fil": [39, 46], "config_fil": [39, 46], "to_dict": [39, 46], "update_from_dict": 39, "update_kv_cache_typ": 39, "model_architectur": 39, "smoothquant_v": 39, "clamp_val": 39, "serializ": 39, "get_modelopt_kv_cache_dtyp": 39, "get_modelopt_qformat": 39, "requires_calibr": 39, "requires_modelopt_quant": 39, "use_plugin_sq": 39, "strenum": [39, 48], "fp8_per_channel_per_token": 39, "w8a8_sq_per_channel_per_tensor_plugin": [39, 46], "w8a8_sq_per_channel_per_token_plugin": [39, 46], "w8a8_sq_per_tensor_per_token_plugin": [39, 46], "w8a8_sq_per_tensor_plugin": [39, 46], "cache_root": 39, "max_record": 39, "max_cache_storage_gb": 39, "revolution": 40, "artifici": 40, "intellig": 40, "digit": 40, "organ": 40, "challeng": 40, "appar": 40, "fact": 40, "comprehens": 40, "intuit": 40, "broken": [40, 55], "groundbreak": 40, "abil": 40, "lovelac": [40, 53, 55], "ture": [40, 53], "volta": [40, 53], "enthusiast": 40, "pc": 40, "rtx": 40, "backbon": 40, "modular": 40, "eager": 40, "dive": [40, 41], "explor": [40, 56], "embark": 40, "journei": 40, "unlock": 40, "incred": 40, "driven": 40, "metric": [41, 55, 56], "middl": 41, "ground": 41, "outlin": 41, "toggl": 41, "region": 41, "extract": [41, 44, 49], "log_iteration_data": 41, "stdout": [41, 43], "metadata": 41, "249": 41, "231": [41, 43], "2448": 41, "28784": 41, "540173600": 41, "239": 41, "6904": 41, "tllm_gptm_profile_start_stop": 41, "nsy": 41, "tllm_gpts_profile_start_stop": 41, "sai": 41, "cudaprofilerapi": 41, "captur": 41, "127": [41, 44], "resolut": 41, "pmi_rank": 41, "mpich": 41, "slurm_procid": 41, "srun": [41, 54], "ompi_comm_world_local_rank": 41, "eq": [41, 44], "nsys_mpi_store_teams_per_rank": 41, "frequenc": 41, "100000": 41, "fi": 41, "profile_rank_0": 41, "env": 41, "strongli": 42, "regard": [42, 44], "max_output_len": [42, 49, 50, 54, 55, 56], "bulid": 42, "firstli": [42, 51], "secondli": 42, "realist": 42, "benefici": 42, "plateau": 42, "satur": 42, "residualadd": [42, 55], "domin": [42, 55], "look_up": 42, "aforement": 42, "lookup": [42, 44, 45], "use_embedding_shar": 42, "downsid": 42, "slight": 42, "reduct": [42, 44, 56], "discard": 42, "cublaslt": 42, "inferenc": 42, "tweak": 42, "inflight_batch": 42, "inflight_fused_batch": [42, 56], "max_tokens_in_paged_kv_cach": [42, 49, 55, 56], "kv_cache_free_gpu_mem_fract": [42, 43, 56], "tend": 42, "translat": [42, 55], "left": [42, 44, 51], "unset": 42, "clearli": 42, "goal": 42, "therebi": 42, "did": 42, "max_input_length": [42, 44, 45, 46, 49], "max_output_length": 42, "exce": [42, 44], "enable_chunked_context": [42, 49, 55, 56], "methodologi": 43, "observ": 43, "swiglu": [43, 44, 55], "fed": [43, 46], "rate": [43, 55], "delai": 43, "hbm3": 43, "gh200": 43, "120gb": 43, "sxm4": 43, "gptj": [43, 46], "533": 43, "22": [43, 44, 54], "368": 43, "318": 43, "61": 43, "936": 43, "964": 43, "19": [43, 54], "688": 43, "44": [43, 51], "375": 43, "588": 43, "73": 43, "829": 43, "91": 43, "931": 43, "215": 43, "88": 43, "842": 43, "82": 43, "048": 43, "59": 43, "662": 43, "81": 43, "955": 43, "28": 43, "041": 43, "06": [43, 44, 45], "118": 43, "980": 43, "23": [43, 54], "770": 43, "520": 43, "37": 43, "698": 43, "08": 43, "479": 43, "48": [43, 51, 55], "650": 43, "09": [43, 54], "746": 43, "5000": 43, "500": 43, "791": 43, "39": 43, "449": [43, 55], "623": 43, "818": 43, "436": 43, "413": 43, "33": 43, "2000": 43, "60": 43, "565": 43, "62": 43, "149": [43, 55], "65": 43, "030": 43, "03": [43, 54, 55], "673": [43, 55], "538": 43, "465": 43, "580": 43, "078": 43, "797": 43, "531": 43, "57": 43, "637": 43, "42": 43, "998": 43, "060": 43, "285": 43, "845": 43, "83": [43, 56], "753": 43, "v3": [43, 52, 55], "125": 43, "045": 43, "147": 43, "647": 43, "687": 43, "548": 43, "989": 43, "497": 43, "79": [43, 51], "221": 43, "02": [43, 55], "882": 43, "918": 43, "53": 43, "988": 43, "077": 43, "856": 43, "462": 43, "054": 43, "625": 43, "357": 43, "859": 43, "796": 43, "000": 43, "823": 43, "76": 43, "217": 43, "276": 43, "74": 43, "788": 43, "66": 43, "872": 43, "382": 43, "77": 43, "996": 43, "834": 43, "929": 43, "911": 43, "435": 43, "355": 43, "41": 43, "411": 43, "43": [43, 50, 51], "160": [43, 55], "92": 43, "592": 43, "648": 43, "072": 43, "97": 43, "850": 43, "851": 43, "152": 43, "269": 43, "78": 43, "055": 43, "20000": 43, "634": 43, "98": 43, "595": 43, "316": 43, "940": 43, "117": 43, "156": 43, "489": 43, "656": 43, "734": 43, "228": 43, "417": 43, "209": 43, "901": 43, "967": [43, 55], "004": 43, "93": 43, "94": 43, "351": 43, "889": 43, "455": 43, "053": 43, "631": 43, "339": 43, "476": 43, "050": 43, "836": 43, "186": 43, "279": 43, "668": 43, "792": 43, "860": 43, "31": 43, "725": 43, "241": 43, "218": 43, "816": 43, "899": 43, "990": 43, "201": 43, "049": 43, "371": 43, "617": 43, "097": 43, "255": 43, "852": 43, "251": 43, "549": 43, "298": 43, "238": 43, "396": 43, "675": 43, "438": 43, "607": 43, "985": 43, "807": 43, "566": 43, "397": 43, "310": 43, "628": 43, "575": 43, "35": 43, "957": 43, "821": 43, "392": 43, "064": 43, "18": [43, 54], "157": 43, "619": 43, "570": 43, "250": 43, "419": 43, "624": 43, "366": 43, "347": 43, "044": 43, "717": 43, "51": 43, "188": 43, "408": 43, "58": 43, "896": 43, "825": [43, 55], "208": 43, "431": 43, "277": 43, "193": 43, "693": 43, "38": 43, "641": 43, "738": 43, "29": [43, 51], "672": 43, "711": 43, "863": 43, "676": 43, "742": 43, "528": 43, "774": 43, "321": 43, "437": 43, "905": 43, "49": 43, "671": 43, "715": 43, "740": 43, "369": 43, "502": 43, "893": 43, "00": [43, 54], "890": 43, "401": 43, "358": 43, "904": 43, "035": 43, "962": 43, "494": 43, "168": 43, "088": 43, "52": 43, "620": 43, "362": 43, "84": 43, "213": 43, "281": 43, "794": [43, 55], "972": 43, "747": 43, "599": 43, "320": 43, "170": 43, "271": 43, "299": 43, "609": 43, "324": 43, "405b": 43, "039": 43, "144": 43, "454": 43, "459": 43, "259": 43, "067": 43, "447": 43, "923": 43, "72": 43, "839": 43, "340": 43, "969": 43, "655": 43, "677": 43, "426": 43, "434": 43, "643": 43, "491": 43, "365": 43, "36": 43, "503": 43, "343": 43, "344": 43, "068": 43, "146": 43, "801": 43, "498": 43, "377": 43, "460": 43, "748": 43, "947": 43, "892": 43, "148": 43, "314": 43, "302": 43, "268": 43, "059": 43, "501": 43, "056": 43, "660": 43, "180": [43, 51], "393": 43, "699": 43, "705": [43, 55], "372": 43, "211": 43, "689": 43, "280": 43, "690": 43, "323": 43, "143": 43, "047": 43, "015": 43, "016": 43, "167": 43, "061": 43, "273": 43, "539": 43, "534": 43, "283": 43, "112": 43, "943": 43, "337": 43, "897": 43, "224": 43, "115": 43, "383": 43, "329": 43, "361": 43, "235": 43, "795": 43, "758": 43, "083": 43, "063": 43, "652": 43, "34": 43, "423": 43, "090": 43, "378": 43, "441": 43, "139": 43, "790": 43, "728": 43, "572": 43, "223": 43, "880": 43, "737": 43, "451": 43, "612": 43, "553": 43, "731": 43, "113": 43, "121": 43, "013": 43, "120": 43, "611": 43, "161": 43, "407": 43, "432": 43, "108": 43, "864": 43, "948": 43, "220": 43, "855": 43, "527": 43, "262": 43, "598": 43, "177": 43, "414": 43, "958": 43, "187": 43, "140": 43, "793": 43, "359": 43, "122": 43, "388": 43, "551": 43, "205": 43, "618": 43, "678": 43, "857": 43, "424": 43, "703": 43, "627": 43, "490": 43, "333": 43, "519": 43, "346": 43, "353": 43, "071": 43, "862": 43, "878": 43, "802": 43, "876": 43, "458": 43, "171": 43, "875": 43, "906": 43, "199": 43, "602": 43, "311": 43, "633": 43, "370": 43, "71": 43, "552": 43, "632": 43, "697": 43, "210": 43, "694": 43, "692": 43, "022": 43, "976": 43, "542": 43, "158": 43, "379": 43, "442": 43, "384": 43, "326": 43, "853": 43, "483": 43, "225": 43, "763": 43, "074": 43, "293": 43, "109": 43, "356": 43, "683": 43, "325": 43, "412": 43, "760": 43, "665": 43, "159": 43, "517": 43, "540": 43, "164": 43, "040": 43, "879": 43, "453": 43, "606": 43, "547": 43, "732": 43, "155": 43, "894": 43, "610": 43, "162": 43, "405": 43, "571": 43, "391": 43, "222": 43, "854": 43, "480": 43, "826": 43, "181": 43, "927": 43, "394": 43, "252": 43, "336": 43, "031": 43, "865": 43, "420": 43, "766": 43, "487": 43, "404": 43, "335": 43, "775": 43, "757": 43, "869": 43, "098": 43, "536": 43, "274": [43, 55], "686": 43, "446": 43, "831": 43, "684": 43, "354": 43, "385": 43, "506": 43, "782": 43, "400": 43, "328": 43, "745": 43, "457": 43, "308": 43, "138": 43, "330": 43, "270": 43, "755": 43, "009": 43, "348": 43, "561": 43, "364": 43, "020": 43, "885": 43, "212": 43, "759": 43, "837": 43, "386": 43, "546": 43, "709": 43, "019": 43, "716": 43, "402": 43, "292": 43, "629": 43, "387": 43, "429": 43, "951": 43, "012": 43, "789": 43, "260": 43, "104": [43, 55], "739": [43, 55], "706": 43, "736": 43, "425": 43, "557": 43, "817": 43, "866": 43, "511": 43, "543": 43, "798": 43, "767": 43, "226": 43, "702": 43, "891": 43, "492": 43, "135": 43, "395": 43, "309": 43, "784": 43, "116": 43, "496": 43, "938": 43, "603": 43, "332": 43, "475": 43, "427": 43, "312": 43, "254": 43, "065": 43, "992": [43, 55], "261": 43, "081": 43, "921": 43, "237": 43, "559": 43, "244": 43, "848": 43, "997": 43, "630": 43, "877": 43, "466": 43, "773": 43, "886": 43, "478": [43, 55], "908": 43, "153": 43, "597": 43, "954": 43, "644": 43, "154": 43, "289": 43, "046": 43, "291": 43, "307": 43, "461": 43, "741": [43, 55], "017": 43, "870": 43, "448": 43, "535": 43, "550": 43, "488": 43, "977": 43, "191": 43, "593": 43, "999": 43, "195": 43, "367": 43, "583": 43, "086": 43, "301": 43, "982": 43, "586": 43, "579": 43, "106": 43, "653": 43, "synthet": 43, "prepare_dataset": 43, "model_nam": [43, 49], "dist": 43, "num_request": 43, "stdev": 43, "dataset_fil": 43, "bench": 43, "eg": 43, "seq_len": [43, 44, 45], "randomli": 43, "uniform": [43, 44], "deviat": 43, "hit": [43, 55], "steadi": 43, "exit": [43, 49], "30000": 43, "2176": 43, "3000": 43, "4224": 43, "1500": 43, "5500": 43, "2500": 43, "22000": 43, "max_seq_length": 43, "tp_1_pp_1": 43, "rapid": [43, 50, 56], "patch": 43, "4098": 43, "req": 43, "680275266452667e": 43, "23405": 43, "927228471104": 43, "182": 43, "8588064724305": 43, "406100739": 43, "anyth": 43, "allreduceconfig": 44, "intflag": [44, 46, 48], "customallreducekernel": 44, "sync": [44, 49], "push_mod": 44, "use_memcpi": 44, "allreducefusionop": 44, "residual_rms_norm": 44, "allreducefusionparam": [44, 45], "fusion_op": 44, "residu": [44, 54], "norm_weight": 44, "has_affin": 44, "has_bia": 44, "allreducestrategi": 44, "intenum": 44, "oneshot": 44, "twoshot": 44, "attentionmasktyp": [44, 45], "bidirect": [44, 45], "bidirectionalglm": 44, "blockspars": 44, "causal": [44, 45], "custom_mask": 44, "sliding_window_caus": 44, "condition": 44, "input_1_": 44, "add_input": 44, "input_1": 44, "input_n_": 44, "input_n": 44, "true_output_valu": 44, "false_output_valu": 44, "add_output": 44, "true_valu": 44, "false_valu": 44, "dimrang": 44, "ctor": 44, "layernormpositiontyp": 44, "pre_layernorm": 44, "layernormtyp": [44, 45], "groupnorm": [44, 45], "mlptype": 44, "fusedgatedmlp": [44, 45], "gatedmlp": [44, 45], "alibi": 44, "alibi_with_scal": 44, "from_str": 44, "is_alibi": 44, "is_rop": 44, "long_rop": 44, "ropeembeddingutil": 44, "apply_llama3_sc": 44, "inv_freq": 44, "ndarrai": [44, 45], "rope_scaling_config": 44, "apply_rotary_pos_emb": 44, "position_embed": [44, 45], "pos_emb_typ": 44, "apply_rotary_pos_emb_chatglm": 44, "attention_head_s": [44, 45], "rotary_embedding_scal": 44, "apply_rotary_pos_emb_cogvlm": 44, "create_sinusoidal_posit": 44, "num_po": 44, "theta": 44, "10000": [44, 45, 46], "create_sinusoidal_positions_for_attention_plugin": 44, "scale_typ": 44, "rotaryscalingtyp": 44, "create_sinusoidal_positions_for_cogvlm_attention_plugin": 44, "vision_start": 44, "vision_length": 44, "1225": 44, "create_sinusoidal_positions_long_rop": 44, "num_orig_po": 44, "scaling_short_factor": 44, "scaling_long_factor": 44, "short_mscal": [44, 45], "long_mscal": [44, 45], "rotate_every_two": 44, "rotate_half": 44, "llama3": 44, "longrop": 44, "dim_rang": 44, "is_network_input": 44, "tensorloc": 44, "ab": [44, 52], "cast": 44, "start_dim": 44, "end_dim": 44, "is_dynam": 44, "is_trt_wrapp": 44, "differenti": 44, "physic": [44, 51], "mark_output": 44, "keepdim": 44, "ndim": 44, "permut": 44, "new_tensor": 44, "undefin": 44, "split_size_or_sect": 44, "dim0": 44, "dim1": 44, "unbind": 44, "zero_is_placehold": 44, "unaryoper": 44, "closur": 44, "round": 44, "sin": 44, "iunarylay": 44, "unari": 44, "tanh": 44, "mul": 44, "prod": 44, "div": 44, "floordiv": 44, "floor_div": 44, "gt": 44, "lt": 44, "op_and": 44, "AND": 44, "op_or": 44, "OR": 44, "pow": 44, "ielementwiselay": 44, "amongst": 44, "section_s": 44, "deeplearn": [44, 54], "reduce_fusion_param": [44, 45], "deleg": 44, "arang": 44, "ifilllay": 44, "filloper": 44, "linspac": 44, "_str_to_trt_dtype_dict": 44, "argmax": 44, "blob": 44, "ye": [44, 51], "avg_pool2d": 44, "kernel_s": [44, 45], "ceil_mod": [44, 45], "count_include_pad": [44, 45], "bert_attent": 44, "input_length": [44, 45, 46, 49], "relative_attent": [44, 45], "relative_attention_bia": 44, "bert": [44, 52, 53, 55], "1706": 44, "03762": 44, "2d": [44, 52], "sum_of_token": 44, "bertattentionplugin": 44, "num_bucket": [44, 45], "broadcast_help": 44, "categorical_sampl": 44, "rand_data": 44, "equival": 44, "categor": [44, 56], "rand": 44, "split_siz": 44, "clip": 44, "alpha": [44, 45, 55], "upper": [44, 51], "inp": 44, "jj": 44, "iconstantlay": 44, "constant_to_tensor_": 44, "to_arrai": 44, "constants_to_tensors_": 44, "upcast": 44, "conv1d": [44, 45], "dilat": [44, 45], "conv2d": [44, 45], "conv_transpose2d": 44, "output_pad": [44, 45], "create_allreduce_plugin": 44, "cumsum": [44, 55], "prefer_plugin": 44, "ilooplay": 44, "cumsumlastdim": 44, "einsum": 44, "einsum_eq": 44, "ieinsumlay": 44, "summat": 44, "einstein": 44, "ascii": 44, "letter": 44, "comma": [44, 49], "subscript": 44, "diagon": 44, "ax": 44, "alphabet": 44, "arrow": 44, "ij": 44, "jk": 44, "ik": 44, "ellipsi": 44, "syntax": 44, "rubric": 44, "ji": 44, "kj": 44, "ijk": 44, "ikl": 44, "ijl": 44, "elementwise_binari": 44, "tp_group": [44, 45, 54], "sharding_dim": [44, 45], "per_token_scal": 44, "among": 44, "transposit": 44, "default_net": 44, "igatherlay": 44, "tg_group": 44, "expand_shap": 44, "expans": 44, "islicelay": 44, "shrunk": 44, "expand_dim": 44, "shape_cast_dtyp": 44, "ishufflelay": 44, "new_shap": 44, "shuffl": 44, "expand_dims_lik": 44, "expand_mask": 44, "tgt_len": [44, 45], "src_seq_len": 44, "tgt_seq_len": 44, "3rd": 44, "2nd": 44, "dimension": 44, "revers": 44, "gatherel": 44, "gather_last_token_logit": 44, "last_token_id": [44, 46, 54], "last_tokens_id": 44, "longest": 44, "gather_nd": 44, "batch_dim": 44, "onnx__gathernd": 44, "gathermod": 44, "nd": 44, "gegelu": 44, "geglu": 44, "gelu": [44, 46], "gemm_swiglu": 44, "scale_d0": 44, "scale_d1": 44, "scale_output": 44, "channel": [44, 52, 55], "generate_alibi_bias": 44, "key_length": [44, 45], "2211": [44, 52], "05100": 44, "generate_alibi_slop": 44, "alibi_scal": 44, "alibi_bias_max": [44, 45], "past_key_valu": [44, 45], "context_fmha_custom_mask": 44, "host_past_key_value_length": [44, 45, 54], "host_max_attention_window_s": [44, 45, 54], "host_sink_token_length": [44, 45, 54], "context_length": [44, 45, 49, 54], "host_request_typ": [44, 45, 46, 54], "num_kv_head": [44, 45, 49], "hidden_size_per_head": 44, "qk_tanh_scal": 44, "rotary_embedding_bas": [44, 45], "rotary_embedding_scale_typ": 44, "rotary_embedding_short_m_scal": 44, "rotary_embedding_long_m_scal": 44, "rotary_embedding_max_posit": 44, "rotary_embedding_original_max_posit": 44, "rotary_inv_freq": [44, 45], "rotary_cos_sin": 44, "kv_orig_quant_scal": 44, "kv_quant_orig_scal": 44, "attention_output_orig_quant_scal": 44, "max_context_length": [44, 45, 49, 51], "mask_typ": 44, "block_sparse_block_s": 44, "block_sparse_homo_head_pattern": 44, "block_sparse_num_local_block": 44, "block_sparse_vertical_strid": 44, "alibi_slop": 44, "kv_cache_block_offset": [44, 45, 49], "host_kv_cache_block_offset": [44, 45, 49], "host_kv_cache_pool_point": [44, 45], "host_kv_cache_pool_map": [44, 45], "do_cross_attent": [44, 45], "cross_qkv": 44, "cross_qkv_length": 44, "encoder_input_length": [44, 45, 49], "host_context_length": [44, 45, 46, 49, 54], "qkv_bia": [44, 55], "use_cach": [44, 45, 46], "spec_decoding_is_generation_length_vari": [44, 45, 46], "spec_decoding_max_generation_length": [44, 45], "spec_decoding_generation_length": [44, 45, 46], "spec_decoding_position_offset": [44, 45, 46], "spec_decoding_packed_mask": [44, 45, 46], "host_runtime_perf_knob": [44, 45], "layer_idx_in_cache_pool": [44, 45], "hint": 44, "merg": 44, "qkv_dim": 44, "contigu": [44, 55], "max_block": 44, "num_tokens_per_block": 44, "max_kv_seqlen": 44, "cache_indir_t": 44, "grok": [44, 53, 55], "rope": [44, 55], "rotari": 44, "inv": 44, "freq": 44, "float2": 44, "spars": [44, 55, 56], "vertic": 44, "num_lay": [44, 45, 46, 49], "max_blocks_per_sequ": 44, "redraft": [44, 49, 55], "divup": 44, "group_norm": 44, "num_group": [44, 45], "index_select": 44, "5th": 44, "int_clip": 44, "interpol": 44, "scale_factor": 44, "nearest": 44, "align_corn": 44, "recompute_scale_factor": 44, "antialia": 44, "is_gated_activ": 44, "layer_norm": 44, "normalized_shap": [44, 45], "use_diff_of_squar": 44, "simplest": 44, "gamma": 44, "formula": 44, "varianc": 44, "squar": 44, "var": 44, "epsilon": 44, "log_softmax": 44, "nn": 44, "safer": 44, "in_hidden_s": 44, "out_hidden_s": 44, "transa": 44, "transb": 44, "max_low_rank": 44, "lora_weights_point": 44, "weight_index": 44, "low_rank": 44, "in_point": 44, "out_point": 44, "low_latency_gemm": 44, "mat2": 44, "strict_dtyp": [44, 45], "mamba_conv1d": 44, "conv_state_or_ptr": 44, "conv_weight": 44, "conv_bia": 44, "dconv": 44, "pre_strid": 44, "post_strid": 44, "slot_map": [44, 46], "apply_silu": 44, "conv": 44, "Or": [44, 49], "masked_scatt": 44, "masked_scatter_": 44, "masked_select": [44, 55], "nonzero": 44, "gatherv2": 44, "use_fp32_acc": 44, "imatrixmultiplylay": 44, "decis": 44, "ireducelay": 44, "reduceoper": 44, "avg": 44, "modulo": 44, "non_gated_vers": 44, "find": [44, 54], "not_op": 44, "NOT": 44, "outer": 44, "vec2": 44, "quick_gelu": 44, "desir": [44, 50], "p2p": 44, "ncclrecv": 44, "repeat_interleav": 44, "rg_lru": 44, "state_or_ptr": 44, "block_siz": [44, 45, 49], "y_bia": 44, "gate_bia": 44, "gate_x": 44, "gate_x_bia": 44, "gate_a": 44, "gate_a_bia": 44, "dstate": 44, "block_num": 44, "rms_norm": 44, "weig": 44, "scatter_nd": 44, "selective_scan": 44, "delta": 44, "delta_bia": 44, "bc": 44, "dt_rank": 44, "delta_softplu": 44, "z": 44, "nhead": 44, "ngroup": 44, "chunk_siz": 44, "mamba_vers": 44, "mamba1": 44, "ssm": 44, "mamba": [44, 52, 53, 55], "mamba2": [44, 55], "dt_proj": 44, "softplu": 44, "chunk_scan": 44, "ncclsend": 44, "cast_to_dtyp": 44, "clip_before_cast": 44, "samplemod": 44, "emul": [44, 55], "strict_bound": 44, "isoftmaxlay": 44, "revert": 44, "ith": 44, "squared_relu": 44, "contact": 44, "a_1": 44, "a_2": 44, "a_n": 44, "a_": 44, "untouch": 44, "enforc": 44, "iselectlay": 44, "mish": 45, "local_layer_idx": 45, "apply_query_key_layer_sc": [45, 46], "qk_layernorm": [45, 46], "layernorm_typ": 45, "inner_layernorm": [45, 46], "attention_mask_typ": 45, "rotary_embedding_sc": 45, "rotary_embedding_percentag": 45, "rope_scaling_short_factor": 45, "rope_scaling_long_factor": 45, "rope_scaling_short_mscal": 45, "rope_scaling_long_mscal": 45, "original_max_position_embed": 45, "cross_attent": [45, 49], "dense_bia": 45, "clip_qkv": [45, 46], "skip_cross_qkv": [45, 49], "max_attn_valu": 45, "block_sparse_param": 45, "use_implicit_relative_attent": 45, "reorder": 45, "create_attention_const_param": 45, "model_cl": 45, "fill_attention_param": 45, "attention_param": [45, 46], "attention_mask": [45, 46, 49], "spec_decoding_param": [45, 46], "kv_cache_param": [45, 46], "encoder_output": [45, 46, 49], "norm_before_bmm1": [45, 46], "lora_layer_param": 45, "cross_kv_cache_gen": [45, 46], "cross_qkv_reus": [45, 46], "postprocess": [45, 56], "set_rel_attn_t": 45, "precomputed_relative_attent": 45, "attentionparam": [45, 46], "encoder_max_input_length": [45, 49], "fill_attention_const_params_for_long_rop": 45, "embed_positions_short_factor": 45, "embed_positions_long_factor": 45, "embed_positions_short_factors_for_attention_plugin": 45, "embed_positions_long_factors_for_attention_plugin": 45, "short_inv_freq": 45, "long_inv_freq": 45, "fill_attention_const_params_for_rop": 45, "embed_posit": 45, "embed_positions_for_gpt_attent": 45, "is_valid": 45, "use_kv_cach": [45, 49], "is_valid_cross_attn": 45, "bertattent": 45, "cp_group": 45, "cp_size": [45, 55], "blocksparseattnparam": 45, "homo_head_pattern": 45, "num_local_block": 45, "vertical_strid": 45, "cogvlmattent": 45, "vision_token_mask": 45, "keyvaluecacheparam": [45, 46], "past_key_value_length": 45, "cross_kv_cache_block_offset": [45, 49], "host_cross_kv_cache_block_offset": [45, 49], "host_cross_kv_cache_pool_point": 45, "host_cross_kv_cache_pool_map": 45, "fill_none_tensor_list": 45, "list_siz": 45, "get_first_past_key_valu": 45, "specdecodingparam": 45, "compute_relative_bia": 45, "query_length": 45, "rel_attn_t": 45, "make_causal_mask": 45, "bsz": 45, "past_key_values_length": 45, "output_dtyp": 45, "in_channel": 45, "out_channel": 45, "padding_mod": 45, "convtranspose2d": 45, "output_s": 45, "num_embed": 45, "embedding_dim": 45, "weight_load": 45, "loaded_weight": 45, "prompttuningembed": 45, "fine": [45, 56], "supplementari": 45, "adequ": 45, "task_vocab_s": 45, "num_task": 45, "num_tokens_per_task": 45, "alia": [45, 46], "gather_output": [45, 54], "share_weight": 45, "pad_lda": 45, "prefer_managed_weight": 45, "is_qkv": 45, "linearbas": 45, "collect_and_bia": 45, "tp_split_dim": 45, "local_in_featur": 45, "local_out_featur": 45, "abstract": 45, "lora_runtime_param": 45, "loraruntimeparam": 45, "lora_hidden_st": 45, "get_weight": 45, "multiply_and_lora": 45, "use_fp8": 45, "multiply_collect": 45, "weight_is_kn": 45, "is_expert": 45, "ffn_hidden_s": [45, 54], "fc_gate": 45, "fc_gate_plugin": 45, "gegelu_limit": 45, "fc_gate_lora": 45, "num_channel": 45, "affin": 45, "elementwise_affin": 45, "avgpool2d": 45, "baichuanforcausallm": 46, "config_class": 46, "baichuanconfig": 46, "hf_model_or_dir": 46, "calib_dataset": [46, 48], "cnn_dailymail": 46, "calib_batch": 46, "calib_batch_s": 46, "calib_max_seq_length": [46, 48], "1234": 46, "tokenizer_max_seq_length": [46, 48], "bertforquestionansw": 46, "type_vocab_s": 46, "pad_token_id": [46, 49], "is_roberta": 46, "num_label": 46, "token_type_id": [46, 49], "position_id": [46, 49, 54], "bertforsequenceclassif": 46, "bertmodel": 46, "bloomforcausallm": 46, "bloommodel": 46, "prompt_task": [46, 49], "chatglmconfig": 46, "chatglm_vers": 46, "add_bias_linear": 46, "add_qkv_bia": 46, "apply_residual_connection_post_layernorm": 46, "rotary_pct": 46, "rotary_bas": 46, "rotary_sc": 46, "hf_config_or_dir": 46, "chatglmforcausallm": 46, "prepare_input": [46, 51], "chatglmmodel": 46, "cogvlmconfig": 46, "mlp_bia": 46, "attn_bia": 46, "cogvlmforcausallm": 46, "default_plugin_config": 46, "to_trt": 46, "dbrxconfig": 46, "500000": 46, "moeconfig": 46, "dbrxforcausallm": 46, "check_config": 46, "decoder_input_id": [46, 49], "cross_attention_mask": [46, 49], "lora_param": 46, "loraparam": 46, "precompute_relative_attention_bia": 46, "max_decoder_input_len": 46, "brief": [46, 49], "use_lora": 46, "deepseekforcausallm": 46, "hf_model": 46, "override_field": 46, "dit": [46, 55], "latent": 46, "timestep": 46, "forward_with_cfg": 46, "classifi": 46, "guidanc": [46, 56], "forward_without_cfg": 46, "unpatchifi": 46, "prompt_embedding_table_s": 46, "use_prompt_tun": [46, 55], "falconconfig": 46, "falconforcausallm": 46, "falconmodel": 46, "gptconfig": 46, "gpt_variant": 46, "embedding_scal": 46, "nemo_ckpt_dir": 46, "gptforcausallm": 46, "gptjconfig": 46, "rotary_dim": 46, "gptjforcausallm": 46, "gptjmodel": 46, "gptmodel": 46, "gptneoxforcausallm": 46, "gptneoxmodel": 46, "gemmaconfig": 46, "liter": 46, "query_pre_attn_scalar": 46, "final_logit_softcap": 46, "attn_logit_softcap": 46, "gemma2_added_field": 46, "gemma_added_field": 46, "inter_layernorm": 46, "verbatim": 46, "hfconfigordir": 46, "gemma2_config": 46, "is_gemma_2": 46, "gemmaforcausallm": 46, "native_quant_flow": 46, "assert_valid_quant_algo": 46, "load_model_on_cpu": 46, "gemma_config_kwarg": 46, "quantize_kwarg": 46, "llamaconfig": 46, "residual_mlp": 46, "disable_weight_only_quant_plugin": 46, "remove_duplicated_kv_head": 46, "meta_ckpt_dir": 46, "llamamodel": 46, "mptforcausallm": 46, "mptmodel": 46, "mambaforcausallm": 46, "conv_stat": 46, "ssm_state": 46, "last_token_ids_for_logit": 46, "speculative_decoding_draft_tokens_extern": 46, "medusaconfig": 46, "num_medusa_head": [46, 48, 49], "num_medusa_lay": [46, 48], "medusaforcausallm": 46, "optmodel": 46, "phi3forcausallm": 46, "phi3config": 46, "phi3model": 46, "phiforcausallm": 46, "phiconfig": 46, "phimodel": 46, "for_each_rank": 46, "get_config_group": 46, "group_cl": 46, "cg": 46, "has_config_group": 46, "kv_dtype": 46, "set_if_not_exist": 46, "set_rank": 46, "to_json_fil": 46, "generationmixin": 46, "preprocess_weights_hook": 46, "from_config": 46, "from_prun": 46, "position_encoding_2d": 46, "redrafterforcausallm": 46, "max_gen_token": 46, "nb": 46, "bl": [46, 56], "device_request_typ": 46, "draft_token": 46, "draft_indic": 46, "draft_prob": 46, "packed_length": 46, "redrafter_inverted_temperatur": 46, "rand_data_sampl": 46, "rand_data_valid": 46, "tricki": 46, "recurrentgemmaforcausallm": 46, "rnn_state": 46, "prepare_recurrent_input": 46, "num_profil": 46, "from_argu": 46, "whisperencod": 46, "input_featur": 46, "categori": 47, "xxx_plugin": 47, "pluginconfigmeta": 47, "to_legacy_set": 47, "central": 47, "quantize_and_export": 48, "qformat": 48, "kv_cache_dtyp": 48, "calib_s": 48, "awq_block_s": 48, "medusa_hidden_act": 48, "medusa_model_dir": 48, "quant_medusa_head": 48, "chatglmgenerationsess": 49, "engine_buff": 49, "debug_mod": [49, 54], "debug_tensors_to_sav": 49, "cuda_graph_mod": [49, 54], "encdecmodelrunn": 49, "engine_nam": 49, "lora_task_uid": 49, "skip_encod": 49, "enable_context_fmha_fp32_acc": 49, "encoder_run": 49, "from_engin": 49, "encoder_input_id": 49, "eos_token_id": 49, "bos_token_id": 49, "return_dict": 49, "time_encod": 49, "process_input": 49, "generationsequ": 49, "seq_idx": 49, "batch_idx": 49, "get_batch_idx": 49, "idx": 49, "get_seq_idx": 49, "buffer_alloc": 49, "context_mem_s": 49, "conv_kernel": 49, "cuda_stream_guard": 49, "sampling_config": 49, "output_sequence_length": 49, "stopping_criteria": 49, "stoppingcriteria": [49, 55], "logits_processor": 49, "logitsprocessor": [49, 55], "decode_batch": 49, "decode_regular": 49, "scfg": 49, "ite": 49, "sequence_limit_length": 49, "stop_words_data": 49, "bad_words_data": 49, "decode_stream": 49, "dump_debug_buff": 49, "early_stop_criteria": 49, "should_stop": 49, "engine_inspector": 49, "filter_medusa_logit": 49, "best_path": 49, "best_path_length": 49, "medusa_logit": 49, "nmh": 49, "nmt": [49, 53, 55], "finalize_decod": 49, "in_progress": 49, "find_best_medusa_path": 49, "next_logit": 49, "temp": 49, "first_lay": 49, "get_next_medusa_token": 49, "next_medusa_logit": 49, "get_num_heads_kv": 49, "handle_per_step": 49, "next_step_tensor": 49, "runtimetensor": 49, "has_position_embed": 49, "has_token_type_embed": 49, "is_medusa_mod": 49, "is_redrafter_mod": 49, "last_lay": 49, "locate_accepted_draft_token": 49, "best_path_len": 49, "draft_path": 49, "max_draft_token": 49, "medusa_decode_and_verifi": 49, "medusa_path": 49, "medusa_position_offset": 49, "medusa_temperatur": [49, 56], "medusa_topk": 49, "medusa_tree_id": 49, "next_medusa_input_id": 49, "pp_communicate_final_output_id": 49, "final_output_id": 49, "pp_communicate_new_token": 49, "cache_indir": 49, "process_logits_including_draft": 49, "next_step_buff": 49, "earli": [49, 54, 55], "criteria": 49, "accept_length": 49, "new_token": 49, "past_sequence_length": 49, "medusa_output_token": 49, "sequence_length_buff": 49, "past_kv_length": 49, "reorder_kv_cache_for_beam_search": 49, "rnn_conv_dim_s": 49, "rnn_head_siz": 49, "rnn_hidden_s": 49, "_runtim": 49, "loramanag": 49, "lora_uid": 49, "medusa_choic": [49, 56], "state_dtyp": 49, "state_s": 49, "update_output_ids_by_offset": 49, "new_generated_id": 49, "use_gpt_attention_plugin": 49, "use_mamba_conv1d_plugin": 49, "num_block": 49, "max_blocks_per_seq": 49, "sink_token_len": 49, "use_one_more_block": 49, "add_sequ": 49, "context_len": 49, "always_share_across_beam": 49, "get_block_offset": 49, "logitsprocessorlist": 49, "trtllm_modules_to_hf_modul": 49, "max_medusa_token": 49, "layer_typ": 49, "redrafter_num_beam": 49, "redrafter_draft_len_per_beam": 49, "num_kv_heads_per_lay": 49, "modelrunnermixin": 49, "from_dir": 49, "disable_kv_cach": 49, "batch_input_id": 49, "prompt_tabl": 49, "parametr": 49, "npy": 49, "nemo_prompt_convert": 49, "uid": 49, "serialize_engin": 49, "vocab_size_pad": 49, "modelrunnercpp": [49, 55], "world_config": 49, "kv_cache_free_gpu_memory_fract": [49, 55], "lookahead_config": [49, 56], "kv_cache_enable_block_reus": [49, 55], "is_enc_dec": 49, "encoder_input_featur": 49, "encoder_output_length": 49, "output_cum_log_prob": 49, "input_token_extra_id": 49, "return_all_generated_token": 49, "feature_dim": 49, "multimodalmodelrunn": 49, "pre_prompt": 49, "post_prompt": 49, "warmup": 49, "get_visual_featur": 49, "init_image_encod": 49, "init_llm": 49, "init_token": 49, "load_test_imag": 49, "prepare_position_ids_for_cogvlm": 49, "ptuning_setup": 49, "ptuning_setup_fuyu": 49, "image_patches_indic": 49, "ptuning_setup_llava_next": 49, "visual_featur": 49, "ptuning_setup_phi3": 49, "num_img_token": 49, "input_imag": 49, "setup_fake_prompt": 49, "pre_input_id": 49, "post_input_id": 49, "setup_fake_prompts_vila": 49, "split_input_id": 49, "setup_input": 49, "raw_imag": 49, "split_prompt_by_imag": 49, "tokenizer_image_token": 49, "image_token_index": 49, "video_preprocess": 49, "video_path": 49, "qwenforcausallmgenerationsess": 49, "global_max_input_length": 49, "global_max_output_length": 49, "runtime_rank": 49, "use_beam_hyp": 49, "iexecutioncontext": [49, 51], "create_execution_context": 49, "icudaengin": [49, 51], "from_serialized_engin": 49, "infer_shap": 49, "tensorinfo": 49, "set_input_shap": 49, "fail": [49, 51, 54], "succeed": 49, "set_shap": 49, "tensor_dict": 49, "stoppingcriterialist": 49, "decode_words_list": 49, "word_dict": 49, "happi": 49, "sad": 49, "minim": 50, "login": 50, "ckpt": [50, 56], "prewritten": 50, "nine": 50, "french": 50, "ngc": [50, 55], "incub": 50, "appreci": 50, "patienc": 50, "introduct": [50, 55], "ran": 50, "showcas": 50, "question": 51, "contributor": 51, "chosen": 51, "live": 51, "device_memory_size_v2": 51, "explan": 51, "relationship": 51, "linearli": 51, "fold": 51, "decoupl": 51, "inde": 51, "nor": 51, "buffermanag": 51, "initmemorypool": 51, "driver": [51, 55], "smi": 51, "concern": 51, "theoret": 51, "6695": 51, "mib": 51, "memusagechang": 51, "1134": 51, "aux": 51, "6678": 51, "mb": 51, "4060": 51, "259840": 51, "succe": [51, 55], "check_gpt_mem_usag": 51, "16x": 51, "recip": 52, "ieee": 52, "satfinit": 52, "fp": [52, 55], "static_cast": 52, "mi": 52, "ni": 52, "10438": 52, "downstream": 52, "2210": 52, "17323": 52, "2306": 52, "00978": 52, "weightonlygroupwisequantmatmulplugin": 52, "weight_only_groupwise_quant_matmul": 52, "blip": [52, 55], "dbrx": [52, 53, 55], "flan": [52, 53], "internlm2": [52, 53, 55], "recurrentgemma": [52, 53, 55], "replit": [52, 53], "skywork": [52, 53, 55], "starcoder1": 52, "starcoder2": [52, 55], "whisper": [52, 53, 55], "blip2": [52, 53, 55], "vila": [52, 53, 55], "nougat": [52, 53, 55], "vision": [52, 53, 55], "modal": 52, "int4_weight": 52, "w4a": [52, 55], "int8_weight": 52, "w8a": 52, "a8": 52, "per_channel": 52, "per_token": 52, "per_group": 52, "fp8_qdq": 52, "arctic": [53, 55], "baichuan2": 53, "bart": [53, 55], "byt5": [53, 55], "fairseq": [53, 55], "gemma2": 53, "mbart": [53, 55], "nemotron": [53, 55], "mt5": 53, "qwen1": [53, 55], "vl": [53, 55], "roberta": [53, 55], "smaug": [53, 55], "cogvlm": [53, 55], "deplot": [53, 55], "fuyu": [53, 55], "kosmo": [53, 55], "neva": [53, 55], "video": [53, 55], "x86_64": 53, "sm90": [53, 55], "sm89": [53, 55], "sm80": [53, 55], "sm86": [53, 55], "sm75": 53, "sm70": 53, "sm": [53, 55], "obei": 54, "paradigm": 54, "interest": 54, "1062": 54, "rectifi": 54, "cu11": 54, "post12": 54, "dev5": 54, "cu121": 54, "register_network_output": 54, "gm": 54, "named_network_output": 54, "_mark_output": 54, "attention_output": 54, "mlp_output": 54, "rf": [54, 56], "pushd": 54, "pytorch_model": 54, "wget": 54, "popd": 54, "current_stream": 54, "cuda_stream": 54, "instance_idx": 54, "cuda_graph_inst": 54, "cuassert": 54, "cudart": 54, "cudagraphlaunch": 54, "ok": 54, "_run": 54, "runtimeerror": 54, "debug_buff": 54, "use_py_sess": 54, "dict_kei": 54, "kv_cache_block_point": 54, "host_kv_cache_block_point": 54, "0294": 54, "0260": 54, "0776": 54, "0560": 54, "0235": 54, "0273": 54, "0071": 54, "5879": 54, "1993": 54, "0449": 54, "6299": 54, "5957": 54, "8779": 54, "1050": 54, "7090": 54, "0910": 54, "0713": 54, "2939": 54, "1212": 54, "0903": 54, "5918": 54, "1045": 54, "3445": 54, "1082": 54, "0723": 54, "0732": 54, "6157": 54, "3452": 54, "2998": 54, "2649": 54, "7134": 54, "9692": 54, "1141": 54, "0096": 54, "9521": 54, "1437": 54, "2107": 54, "5874": 54, "8179": 54, "7900": 54, "6890": 54, "6064": 54, "4192": 54, "0047": 54, "3887": 54, "9028": 54, "0682": 54, "2820": 54, "7949": 54, "5073": 54, "1721": 54, "5830": 54, "1378": 54, "0070": 54, "0804": 54, "1272": 54, "6255": 54, "1072": 54, "0523": 54, "7144": 54, "3328": 54, "8828": 54, "3442": 54, "8149": 54, "0630": 54, "2305": 54, "2225": 54, "2079": 54, "1459": 54, "3555": 54, "1672": 54, "1135": 54, "1290": 54, "1556": 54, "3977": 54, "8218": 54, "3291": 54, "8672": 54, "chef": 54, "london": 54, "cuda_launch_block": 54, "statu": 54, "shm": 54, "gptlmheadmodel": 54, "plugin_v2_gemm_0": 54, "pluginv2build": 54, "reportpluginerror": 54, "slurm": 54, "interfer": 54, "pmi2_init": 54, "ompi": 54, "pmi": 54, "pmix": 54, "dedic": 54, "feedback": 55, "forum": 55, "speculative_decod": 55, "loader": 55, "indivis": 55, "openai": 55, "trust_remote_cod": 55, "curand": 55, "mixer": 55, "break": 55, "renam": 55, "1999": 55, "5b": 55, "2087": 55, "convert_util": 55, "2113": 55, "force_nccl_all_reduce_strategi": 55, "unexpect": 55, "truncat": 55, "race": 55, "1323": 55, "nvcr": [55, 56], "py3": [55, 56], "tritonserv": [55, 56], "ootb": 55, "1886": 55, "altair": 55, "1834": 55, "gelu_pytorch_tanh": 55, "ttim": 55, "1897": 55, "chunk_length": 55, "mahmoudashraf97": 55, "1909": 55, "use_custom_all_reduc": 55, "context_fmha_fp32_acc": 55, "wrong": [55, 56], "codeqwen": 55, "1953": 55, "typo": 55, "cluster_info": 55, "saeyoonoh": 55, "1987": 55, "duplic": 55, "hattizai": 55, "1937": 55, "segment": 55, "fault": 55, "akhoroshev": 55, "2039": 55, "2040": 55, "1985": 55, "fjosw": 55, "2056": 55, "tayef": 55, "shah": 55, "2028": 55, "lfz941": 55, "1939": 55, "2018": 55, "mini": 55, "distil": 55, "ibrahimamin1": 55, "1337": 55, "dreamgenx": 55, "1762": 55, "qgmma": 55, "xqa": [55, 56], "jit": 55, "codepath": 55, "iterlatencymillisec": 55, "zoo": 55, "matichon": 55, "vultureprim": 55, "1674": 55, "weight_only_precis": 55, "attention_qk_half_accumul": 55, "use_context_fmha_for_gener": 55, "tllm_hlapi_build_cach": 55, "fastapi_serv": 55, "unif": 55, "speculativedecodingmodul": 55, "jai": 55, "110b": 55, "20b": 55, "runningleon": 55, "1392": 55, "a2": 55, "1539": 55, "vonjackustc": 55, "1329": 55, "1486": 55, "pzzzzz5142": 55, "1328": 55, "526": 55, "pynvml": 55, "coderham": 55, "1537": 55, "1660": 55, "lopuhin": 55, "1650": 55, "32b": 55, "1589": 55, "tlntin": 55, "1637": 55, "trait": 55, "fpa_intb": 55, "jamesthez": 55, "1583": 55, "qwenvl": 55, "ngoanpv": 55, "1248": 55, "rslora": 55, "thecodewrangl": 55, "1669": 55, "1675": 55, "tushar": 55, "ml": 55, "1535": 55, "convert_hf_mpt_legaci": 55, "bloodeagle40234": 55, "1534": 55, "1723": 55, "pathorn": 55, "1742": 55, "1642": 55, "ac": 55, "rr": 55, "1732": 55, "bpru": 55, "1738": 55, "janpetrov": 55, "1676": 55, "autopp": 55, "detect": 55, "unsupport": 55, "1626": 55, "shared_embedding_t": 55, "1799": 55, "mfuntowicz": 55, "1815": 55, "marks101": 55, "comment": 55, "lkm2835": 55, "1851": 55, "occasion": 55, "invalid": 55, "1590": 55, "1424": 55, "1529": 55, "1562": 55, "1552": 55, "dead": 55, "deftruth": 55, "buvnswrn": 55, "sunjiabin17": 55, "482": 55, "investig": 55, "sample_weight_strip": 55, "applybiasropeupdatekvcach": 55, "cutlass": 55, "fall": 55, "ttft": 55, "itl": 55, "gptmodelconfig": 55, "schedulerpolici": 55, "batch_schedul": 55, "persimmon": 55, "1284": 55, "crash": 55, "1256": 55, "scalartyp": 55, "403": 55, "1436": 55, "72b": 55, "1344": 55, "1449": 55, "1467": 55, "1447": 55, "1446": 55, "mmha": 55, "1343": 55, "determinist": 55, "air": 55, "rewind": 55, "planner": 55, "percentil": 55, "gptdecoderbatch": 55, "asyncllmengin": 55, "generationexecutor": 55, "refin": 55, "streaming_llm": 55, "bug": 55, "encoder_input_len_rang": 55, "983": 55, "1003": 55, "987": 55, "1118": 55, "1123": 55, "1181": 55, "1148": 55, "1239": 55, "1242": 55, "1183": 55, "1267": 55, "input_fil": 55, "newer": 55, "reducescatt": 55, "275": 55, "32k": 55, "eddi": 55, "wang1120": 55, "erenup": 55, "new_workflow": 55, "abnorm": 55, "639": 55, "649": 55, "695": 55, "pickl": 55, "701": 55, "custom_all_reduc": 55, "935": 55, "enable_trt_overlap": 55, "ping": 55, "pong": 55, "perf_best_practic": 55, "sota": 55, "133": 55, "fhma": 55, "warp": 55, "288": 55, "codellama": 55, "situat": 56, "underutil": 56, "repeatedli": 56, "twofold": 56, "successfulli": 56, "cours": 56, "wors": 56, "auxiliari": 56, "recurr": 56, "drafter": 56, "forecast": 56, "prove": 56, "simpler": 56, "summari": 56, "furthermor": 56, "pronounc": 56, "act": 56, "essenti": 56, "verif": 56, "predefin": 56, "procedur": 56, "llmrequest": 56, "advis": 56, "draft_model_path": 56, "target_model_path": 56, "max_draft_length": 56, "common_command": 56, "3072": 56, "draft_command_fp16": 56, "target_command_fp16": 56, "draft_command_fp8": 56, "target_command_fp8": 56, "draft_nam": 56, "target_nam": 56, "draft_engine_path": 56, "target_engine_path": 56, "edit": 56, "40gib": 56, "80gib": 56, "draft_gpu_device_id": 56, "target_gpu_device_id": 56, "elsewis": 56, "gpu_device_id": 56, "visit": 56, "accumulate_token": 56, "tensorrtllm": 56, "batch_scheduler_polici": 56, "batching_strategi": 56, "bls_instance_count": 56, "decoding_mod": 56, "top_k_top_p": 56, "decoupled_mod": 56, "e2e_model_nam": 56, "ensembl": 56, "engine_path": 56, "exclude_input_in_output": 56, "max_queue_delay_microsecond": 56, "max_tokens_in_kv_cach": 56, "postprocessing_instance_count": 56, "preprocessing_instance_count": 56, "tensorrt_llm_draft_model_nam": 56, "tensorrt_llm_draft": 56, "tensorrt_llm_model_nam": 56, "tokenizer_path": 56, "tokenizer_typ": 56, "triton_grpc_port": 56, "8001": 56, "triton_http_port": 56, "8000": 56, "triton_max_batch_s": 56, "triton_metrics_port": 56, "8002": 56, "triton_repo": 56, "use_draft_logit": 56, "tritoncli": 56, "grpcio": 56, "all_model": 56, "inflight_batcher_llm": 56, "fill_templ": 56, "pbtxt": 56, "tensorrt_llm_bl": 56, "sed": 56, "triton_backend": 56, "launch_triton_serv": 56, "model_repo": 56, "triton_log": 56, "httpservic": 56, "grpcinferenceservic": 56, "input_data": 56, "jame": 56, "stori": 56, "speculative_decoding_test": 56, "localhost": 56, "kill": 56, "pkill": 56, "trtllmexecutorwork": 56, "emploi": 56, "consolid": 56, "simultan": 56, "albeit": 56, "recogn": 56, "exponenti": 56, "focus": 56, "strike": 56, "breadth": 56, "mh": 56, "l": 56, "denot": 56, "hk": 56, "mh1": 56, "examin": 56, "vicuna": 56, "phasem": 56, "predictor": 56, "promin": 56, "tutori": 56, "windows_s": 56, "ngram_siz": 56, "verification_set_s": 56, "specualtive_decoding_mod": 56, "ngran_siz": 56, "executor_lookahead_config": 56, "lifecycl": 56, "jacobi": 56, "degener": 56, "llmama": 56, "log_levelverbos": 56, "Be": 56, "afraid": 56, "cnn": 56, "daili": 56, "test_hf": 56}, "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"], [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, "_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_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, 2, 1, "_CPPv4N12tensorrt_llm8executor12BatchingTypeE", "tensorrt_llm::executor::BatchingType"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12BatchingType9kINFLIGHTE", "tensorrt_llm::executor::BatchingType::kINFLIGHT"], [0, 3, 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_llm8executor23CapacitySchedulerPolicyE", "tensorrt_llm::executor::CapacitySchedulerPolicy"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicy20kGUARANTEED_NO_EVICTE", "tensorrt_llm::executor::CapacitySchedulerPolicy::kGUARANTEED_NO_EVICT"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicy16kMAX_UTILIZATIONE", "tensorrt_llm::executor::CapacitySchedulerPolicy::kMAX_UTILIZATION"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor17CommunicationModeE", "tensorrt_llm::executor::CommunicationMode"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor17CommunicationMode7kLEADERE", "tensorrt_llm::executor::CommunicationMode::kLEADER"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor17CommunicationMode13kORCHESTRATORE", "tensorrt_llm::executor::CommunicationMode::kORCHESTRATOR"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor17CommunicationTypeE", "tensorrt_llm::executor::CommunicationType"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor17CommunicationType4kMPIE", "tensorrt_llm::executor::CommunicationType::kMPI"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicyE", "tensorrt_llm::executor::ContextChunkingPolicy"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicy15kEQUAL_PROGRESSE", "tensorrt_llm::executor::ContextChunkingPolicy::kEQUAL_PROGRESS"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicy24kFIRST_COME_FIRST_SERVEDE", "tensorrt_llm::executor::ContextChunkingPolicy::kFIRST_COME_FIRST_SERVED"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsE", "tensorrt_llm::executor::ContextPhaseParams"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokensPv", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsERK18ContextPhaseParams", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsERR18ContextPhaseParams", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::firstGenTokens"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokensPv", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::firstGenTokens"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokensPv", "tensorrt_llm::executor::ContextPhaseParams::ContextPhaseParams::state"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams8StatePtrE", "tensorrt_llm::executor::ContextPhaseParams::StatePtr"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams7deleterEPKv", "tensorrt_llm::executor::ContextPhaseParams::deleter"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams7deleterEPKv", "tensorrt_llm::executor::ContextPhaseParams::deleter::data"], [0, 5, 1, "_CPPv4NKR12tensorrt_llm8executor18ContextPhaseParams17getFirstGenTokensEv", "tensorrt_llm::executor::ContextPhaseParams::getFirstGenTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams8getStateEv", "tensorrt_llm::executor::ContextPhaseParams::getState"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParams8getStateEv", "tensorrt_llm::executor::ContextPhaseParams::getState"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams15mFirstGenTokensE", "tensorrt_llm::executor::ContextPhaseParams::mFirstGenTokens"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams6mStateE", "tensorrt_llm::executor::ContextPhaseParams::mState"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsaSERK18ContextPhaseParams", "tensorrt_llm::executor::ContextPhaseParams::operator="], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsaSERR18ContextPhaseParams", "tensorrt_llm::executor::ContextPhaseParams::operator="], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParamseqERK18ContextPhaseParams", "tensorrt_llm::executor::ContextPhaseParams::operator=="], [0, 5, 1, "_CPPv4NO12tensorrt_llm8executor18ContextPhaseParams17popFirstGenTokensEv", "tensorrt_llm::executor::ContextPhaseParams::popFirstGenTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams12releaseStateEv", "tensorrt_llm::executor::ContextPhaseParams::releaseState"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor8DataTypeE", "tensorrt_llm::executor::DataType"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8DataType5kBF16E", "tensorrt_llm::executor::DataType::kBF16"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8DataType5kBOOLE", "tensorrt_llm::executor::DataType::kBOOL"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8DataType5kFP16E", "tensorrt_llm::executor::DataType::kFP16"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8DataType5kFP32E", "tensorrt_llm::executor::DataType::kFP32"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8DataType4kFP8E", "tensorrt_llm::executor::DataType::kFP8"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8DataType6kINT32E", "tensorrt_llm::executor::DataType::kINT32"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8DataType6kINT64E", "tensorrt_llm::executor::DataType::kINT64"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8DataType5kINT8E", "tensorrt_llm::executor::DataType::kINT8"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8DataType6kUINT8E", "tensorrt_llm::executor::DataType::kUINT8"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor8DataType8kUNKNOWNE", "tensorrt_llm::executor::DataType::kUNKNOWN"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfigE", "tensorrt_llm::executor::DebugConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig11DebugConfigEbb9StringVec", "tensorrt_llm::executor::DebugConfig::DebugConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig11DebugConfigEbb9StringVec", "tensorrt_llm::executor::DebugConfig::DebugConfig::debugTensorNames"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig11DebugConfigEbb9StringVec", "tensorrt_llm::executor::DebugConfig::DebugConfig::dumpInputTensors"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig11DebugConfigEbb9StringVec", "tensorrt_llm::executor::DebugConfig::DebugConfig::dumpOuputTensors"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig9StringVecE", "tensorrt_llm::executor::DebugConfig::StringVec"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor11DebugConfig19getDebugTensorNamesEv", "tensorrt_llm::executor::DebugConfig::getDebugTensorNames"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor11DebugConfig19getDumpInputTensorsEv", "tensorrt_llm::executor::DebugConfig::getDumpInputTensors"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor11DebugConfig20getDumpOutputTensorsEv", "tensorrt_llm::executor::DebugConfig::getDumpOutputTensors"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig17mDebugTensorNamesE", "tensorrt_llm::executor::DebugConfig::mDebugTensorNames"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig17mDumpInputTensorsE", "tensorrt_llm::executor::DebugConfig::mDumpInputTensors"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig17mDumpOuputTensorsE", "tensorrt_llm::executor::DebugConfig::mDumpOuputTensors"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor11DebugConfigeqERK11DebugConfig", "tensorrt_llm::executor::DebugConfig::operator=="], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor11DebugConfigeqERK11DebugConfig", "tensorrt_llm::executor::DebugConfig::operator==::other"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig19setDebugTensorNamesERK9StringVec", "tensorrt_llm::executor::DebugConfig::setDebugTensorNames"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig19setDebugTensorNamesERK9StringVec", "tensorrt_llm::executor::DebugConfig::setDebugTensorNames::debugTensorNames"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig19setDumpInputTensorsEb", "tensorrt_llm::executor::DebugConfig::setDumpInputTensors"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig19setDumpInputTensorsEb", "tensorrt_llm::executor::DebugConfig::setDumpInputTensors::dumpInputTensors"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig19setDumpOuputTensorsEb", "tensorrt_llm::executor::DebugConfig::setDumpOuputTensors"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor11DebugConfig19setDumpOuputTensorsEb", "tensorrt_llm::executor::DebugConfig::setDumpOuputTensors::dumpOuputTensors"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfigE", "tensorrt_llm::executor::DecodingConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14DecodingConfigENSt8optionalI12DecodingModeEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI13MedusaChoicesEE", "tensorrt_llm::executor::DecodingConfig::DecodingConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14DecodingConfigENSt8optionalI12DecodingModeEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI13MedusaChoicesEE", "tensorrt_llm::executor::DecodingConfig::DecodingConfig::decodingMode"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14DecodingConfigENSt8optionalI12DecodingModeEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI13MedusaChoicesEE", "tensorrt_llm::executor::DecodingConfig::DecodingConfig::lookaheadDecodingConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14DecodingConfigENSt8optionalI12DecodingModeEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI13MedusaChoicesEE", "tensorrt_llm::executor::DecodingConfig::DecodingConfig::medusaChoices"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig15getDecodingModeEv", "tensorrt_llm::executor::DecodingConfig::getDecodingMode"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig26getLookaheadDecodingConfigEv", "tensorrt_llm::executor::DecodingConfig::getLookaheadDecodingConfig"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig16getMedusaChoicesEv", "tensorrt_llm::executor::DecodingConfig::getMedusaChoices"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig13mDecodingModeE", "tensorrt_llm::executor::DecodingConfig::mDecodingMode"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig24mLookaheadDecodingConfigE", "tensorrt_llm::executor::DecodingConfig::mLookaheadDecodingConfig"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14mMedusaChoicesE", "tensorrt_llm::executor::DecodingConfig::mMedusaChoices"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfigeqERK14DecodingConfig", "tensorrt_llm::executor::DecodingConfig::operator=="], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor14DecodingConfigeqERK14DecodingConfig", "tensorrt_llm::executor::DecodingConfig::operator==::other"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig15setDecodingModeERK12DecodingMode", "tensorrt_llm::executor::DecodingConfig::setDecodingMode"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig20setLookaheadDecodingERK23LookaheadDecodingConfig", "tensorrt_llm::executor::DecodingConfig::setLookaheadDecoding"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig20setLookaheadDecodingERK23LookaheadDecodingConfig", "tensorrt_llm::executor::DecodingConfig::setLookaheadDecoding::lookaheadDecodingConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14DecodingConfig16setMedusaChoicesERK13MedusaChoices", "tensorrt_llm::executor::DecodingConfig::setMedusaChoices"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12DecodingModeE", "tensorrt_llm::executor::DecodingMode"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode4AutoEv", "tensorrt_llm::executor::DecodingMode::Auto"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode10BeamSearchEv", "tensorrt_llm::executor::DecodingMode::BeamSearch"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12DecodingModeE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::DecodingMode"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12DecodingModeE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::DecodingMode::state"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode19ExplicitDraftTokensEv", "tensorrt_llm::executor::DecodingMode::ExplicitDraftTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode9LookaheadEv", "tensorrt_llm::executor::DecodingMode::Lookahead"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode6MedusaEv", "tensorrt_llm::executor::DecodingMode::Medusa"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode4TopKEv", "tensorrt_llm::executor::DecodingMode::TopK"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode8TopKTopPEv", "tensorrt_llm::executor::DecodingMode::TopKTopP"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode4TopPEv", "tensorrt_llm::executor::DecodingMode::TopP"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode14UnderlyingTypeE", "tensorrt_llm::executor::DecodingMode::UnderlyingType"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9allBitSetE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::allBitSet"], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9allBitSetE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::allBitSet::bits"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9anyBitSetE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::anyBitSet"], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9anyBitSetE14UnderlyingType", "tensorrt_llm::executor::DecodingMode::anyBitSet::bits"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode8getStateEv", "tensorrt_llm::executor::DecodingMode::getState"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isAutoEv", "tensorrt_llm::executor::DecodingMode::isAuto"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isBeamSearchEv", "tensorrt_llm::executor::DecodingMode::isBeamSearch"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode21isExplicitDraftTokensEv", "tensorrt_llm::executor::DecodingMode::isExplicitDraftTokens"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode11isLookaheadEv", "tensorrt_llm::executor::DecodingMode::isLookahead"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode8isMedusaEv", "tensorrt_llm::executor::DecodingMode::isMedusa"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isTopKEv", "tensorrt_llm::executor::DecodingMode::isTopK"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode13isTopKandTopPEv", "tensorrt_llm::executor::DecodingMode::isTopKandTopP"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isTopKorTopPEv", "tensorrt_llm::executor::DecodingMode::isTopKorTopP"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isTopPEv", "tensorrt_llm::executor::DecodingMode::isTopP"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseBanTokensEv", "tensorrt_llm::executor::DecodingMode::isUseBanTokens"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode13isUseBanWordsEv", "tensorrt_llm::executor::DecodingMode::isUseBanWords"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode20isUseExplicitEosStopEv", "tensorrt_llm::executor::DecodingMode::isUseExplicitEosStop"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode21isUseFrequencyPenaltyEv", "tensorrt_llm::executor::DecodingMode::isUseFrequencyPenalty"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode18isUseMaxLengthStopEv", "tensorrt_llm::executor::DecodingMode::isUseMaxLengthStop"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseMinLengthEv", "tensorrt_llm::executor::DecodingMode::isUseMinLength"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseNoRepeatNgramSizeEv", "tensorrt_llm::executor::DecodingMode::isUseNoRepeatNgramSize"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseOccurrencePenaltyEv", "tensorrt_llm::executor::DecodingMode::isUseOccurrencePenalty"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isUsePenaltyEv", "tensorrt_llm::executor::DecodingMode::isUsePenalty"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode20isUsePresencePenaltyEv", "tensorrt_llm::executor::DecodingMode::isUsePresencePenalty"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseRepetitionPenaltyEv", "tensorrt_llm::executor::DecodingMode::isUseRepetitionPenalty"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode17isUseStopCriteriaEv", "tensorrt_llm::executor::DecodingMode::isUseStopCriteria"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseStopWordsEv", "tensorrt_llm::executor::DecodingMode::isUseStopWords"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingMode16isUseTemperatureEv", "tensorrt_llm::executor::DecodingMode::isUseTemperature"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kAutoE", "tensorrt_llm::executor::DecodingMode::kAuto"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode11kBeamSearchE", "tensorrt_llm::executor::DecodingMode::kBeamSearch"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode20kExplicitDraftTokensE", "tensorrt_llm::executor::DecodingMode::kExplicitDraftTokens"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode10kLookaheadE", "tensorrt_llm::executor::DecodingMode::kLookahead"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode7kMedusaE", "tensorrt_llm::executor::DecodingMode::kMedusa"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode9kNumFlagsE", "tensorrt_llm::executor::DecodingMode::kNumFlags"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode21kStandardStopCriteriaE", "tensorrt_llm::executor::DecodingMode::kStandardStopCriteria"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kTopKE", "tensorrt_llm::executor::DecodingMode::kTopK"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode9kTopKTopPE", "tensorrt_llm::executor::DecodingMode::kTopKTopP"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kTopPE", "tensorrt_llm::executor::DecodingMode::kTopP"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseBanTokensE", "tensorrt_llm::executor::DecodingMode::kUseBanTokens"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12kUseBanWordsE", "tensorrt_llm::executor::DecodingMode::kUseBanWords"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode19kUseExplicitEosStopE", "tensorrt_llm::executor::DecodingMode::kUseExplicitEosStop"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode22kUseFrequencyPenaltiesE", "tensorrt_llm::executor::DecodingMode::kUseFrequencyPenalties"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode17kUseMaxLengthStopE", "tensorrt_llm::executor::DecodingMode::kUseMaxLengthStop"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseMinLengthE", "tensorrt_llm::executor::DecodingMode::kUseMinLength"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode21kUseNoRepeatNgramSizeE", "tensorrt_llm::executor::DecodingMode::kUseNoRepeatNgramSize"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode23kUseOccurrencePenaltiesE", "tensorrt_llm::executor::DecodingMode::kUseOccurrencePenalties"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUsePenaltiesE", "tensorrt_llm::executor::DecodingMode::kUsePenalties"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode21kUsePresencePenaltiesE", "tensorrt_llm::executor::DecodingMode::kUsePresencePenalties"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode23kUseRepetitionPenaltiesE", "tensorrt_llm::executor::DecodingMode::kUseRepetitionPenalties"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseStopWordsE", "tensorrt_llm::executor::DecodingMode::kUseStopWords"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode15kUseTemperatureE", "tensorrt_llm::executor::DecodingMode::kUseTemperature"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode6mStateE", "tensorrt_llm::executor::DecodingMode::mState"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingModeeqERK12DecodingMode", "tensorrt_llm::executor::DecodingMode::operator=="], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor12DecodingModeeqERK12DecodingMode", "tensorrt_llm::executor::DecodingMode::operator==::other"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode8setBitToE14UnderlyingTypeb", "tensorrt_llm::executor::DecodingMode::setBitTo"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode8setBitToE14UnderlyingTypeb", "tensorrt_llm::executor::DecodingMode::setBitTo::state"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode8setBitToE14UnderlyingTypeb", "tensorrt_llm::executor::DecodingMode::setBitTo::x"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useBanTokensEb", "tensorrt_llm::executor::DecodingMode::useBanTokens"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useBanTokensEb", "tensorrt_llm::executor::DecodingMode::useBanTokens::banTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode11useBanWordsEb", "tensorrt_llm::executor::DecodingMode::useBanWords"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode11useBanWordsEb", "tensorrt_llm::executor::DecodingMode::useBanWords::banWords"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode18useExplicitEosStopEb", "tensorrt_llm::executor::DecodingMode::useExplicitEosStop"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode18useExplicitEosStopEb", "tensorrt_llm::executor::DecodingMode::useExplicitEosStop::explicitEosStop"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode19useFrequencyPenaltyEb", "tensorrt_llm::executor::DecodingMode::useFrequencyPenalty"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode19useFrequencyPenaltyEb", "tensorrt_llm::executor::DecodingMode::useFrequencyPenalty::usePenalty"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode16useMaxLengthStopEb", "tensorrt_llm::executor::DecodingMode::useMaxLengthStop"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode16useMaxLengthStopEb", "tensorrt_llm::executor::DecodingMode::useMaxLengthStop::maxLengthStop"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useMinLengthEb", "tensorrt_llm::executor::DecodingMode::useMinLength"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useMinLengthEb", "tensorrt_llm::executor::DecodingMode::useMinLength::useMinLen"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useNoRepeatNgramSizeEb", "tensorrt_llm::executor::DecodingMode::useNoRepeatNgramSize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useNoRepeatNgramSizeEb", "tensorrt_llm::executor::DecodingMode::useNoRepeatNgramSize::noRepeatNgramSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode22useOccurrencePenaltiesEb", "tensorrt_llm::executor::DecodingMode::useOccurrencePenalties"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode22useOccurrencePenaltiesEb", "tensorrt_llm::executor::DecodingMode::useOccurrencePenalties::usePenalty"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode18usePresencePenaltyEb", "tensorrt_llm::executor::DecodingMode::usePresencePenalty"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode18usePresencePenaltyEb", "tensorrt_llm::executor::DecodingMode::usePresencePenalty::usePenalty"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useRepetitionPenaltyEb", "tensorrt_llm::executor::DecodingMode::useRepetitionPenalty"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useRepetitionPenaltyEb", "tensorrt_llm::executor::DecodingMode::useRepetitionPenalty::usePenalty"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useStopWordsEb", "tensorrt_llm::executor::DecodingMode::useStopWords"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useStopWordsEb", "tensorrt_llm::executor::DecodingMode::useStopWords::stopWords"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode14useTemperatureEb", "tensorrt_llm::executor::DecodingMode::useTemperature"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12DecodingMode14useTemperatureEb", "tensorrt_llm::executor::DecodingMode::useTemperature::useTemp"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8ExecutorE", "tensorrt_llm::executor::Executor"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::decoderEngineBuffer"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::decoderJsonConfigStr"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::decoderModel"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::decoderModelPath"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::encoderEngineBuffer"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::encoderJsonConfigStr"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::encoderModel"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::encoderModelPath"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor::engineBuffer"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::executorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor::jsonConfigStr"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor::managedWeights"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEERK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::model"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::modelPath"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE", "tensorrt_llm::executor::Executor::Executor::modelType"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::modelType"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::modelType"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig", "tensorrt_llm::executor::Executor::Executor::modelType"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERK6IdTypeRKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt6vectorI6IdTypeEERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERK6IdTypeRKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses::requestId"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt6vectorI6IdTypeEERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses::requestIds"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERK6IdTypeRKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses::timeout"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt6vectorI6IdTypeEERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses::timeout"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt8optionalINSt6chrono12millisecondsEEE", "tensorrt_llm::executor::Executor::awaitResponses::timeout"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor8Executor18canEnqueueRequestsEv", "tensorrt_llm::executor::Executor::canEnqueueRequests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Executor13cancelRequestE6IdType", "tensorrt_llm::executor::Executor::cancelRequest"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor13cancelRequestE6IdType", "tensorrt_llm::executor::Executor::cancelRequest::requestId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Executor14enqueueRequestERK7Request", "tensorrt_llm::executor::Executor::enqueueRequest"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor14enqueueRequestERK7Request", "tensorrt_llm::executor::Executor::enqueueRequest::request"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Executor15enqueueRequestsERKNSt6vectorI7RequestEE", "tensorrt_llm::executor::Executor::enqueueRequests"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Executor15enqueueRequestsERKNSt6vectorI7RequestEE", "tensorrt_llm::executor::Executor::enqueueRequests::requests"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Executor23getLatestIterationStatsEv", "tensorrt_llm::executor::Executor::getLatestIterationStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Executor21getLatestRequestStatsEv", "tensorrt_llm::executor::Executor::getLatestRequestStats"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor8Executor20getNumResponsesReadyERKNSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Executor::getNumResponsesReady"], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor8Executor20getNumResponsesReadyERKNSt8optionalI6IdTypeEE", "tensorrt_llm::executor::Executor::getNumResponsesReady::requestId"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8Executor5mImplE", "tensorrt_llm::executor::Executor::mImpl"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Executor8shutdownEv", "tensorrt_llm::executor::Executor::shutdown"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8ExecutorD0Ev", "tensorrt_llm::executor::Executor::~Executor"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfigE", "tensorrt_llm::executor::ExecutorConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::batchingType"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::debugConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::decodingConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::enableChunkedContext"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::extendedRuntimePerfKnobConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::gpuWeightsPercent"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::iterStatsMaxIterations"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::kvCacheConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::logitsPostProcessorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::maxBatchSize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::maxBeamWidth"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::maxNumTokens"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::maxQueueSize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::maxSeqIdleMicroseconds"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::normalizeLogProbs"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::parallelConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::peftCacheConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::recvPollPeriodMs"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::requestStatsMaxIterations"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t", "tensorrt_llm::executor::ExecutorConfig::ExecutorConfig::schedulerConfig"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getBatchingTypeEv", "tensorrt_llm::executor::ExecutorConfig::getBatchingType"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig14getDebugConfigEv", "tensorrt_llm::executor::ExecutorConfig::getDebugConfig"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig17getDecodingConfigEv", "tensorrt_llm::executor::ExecutorConfig::getDecodingConfig"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig23getEnableChunkedContextEv", "tensorrt_llm::executor::ExecutorConfig::getEnableChunkedContext"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig32getExtendedRuntimePerfKnobConfigEv", "tensorrt_llm::executor::ExecutorConfig::getExtendedRuntimePerfKnobConfig"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig20getGpuWeightsPercentEv", "tensorrt_llm::executor::ExecutorConfig::getGpuWeightsPercent"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getIterStatsMaxIterationsEv", "tensorrt_llm::executor::ExecutorConfig::getIterStatsMaxIterations"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig16getKvCacheConfigEv", "tensorrt_llm::executor::ExecutorConfig::getKvCacheConfig"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig28getLogitsPostProcessorConfigEv", "tensorrt_llm::executor::ExecutorConfig::getLogitsPostProcessorConfig"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxBatchSizeEv", "tensorrt_llm::executor::ExecutorConfig::getMaxBatchSize"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxBeamWidthEv", "tensorrt_llm::executor::ExecutorConfig::getMaxBeamWidth"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxNumTokensEv", "tensorrt_llm::executor::ExecutorConfig::getMaxNumTokens"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxQueueSizeEv", "tensorrt_llm::executor::ExecutorConfig::getMaxQueueSize"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getMaxSeqIdleMicrosecondsEv", "tensorrt_llm::executor::ExecutorConfig::getMaxSeqIdleMicroseconds"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig20getNormalizeLogProbsEv", "tensorrt_llm::executor::ExecutorConfig::getNormalizeLogProbs"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig17getParallelConfigEv", "tensorrt_llm::executor::ExecutorConfig::getParallelConfig"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig18getPeftCacheConfigEv", "tensorrt_llm::executor::ExecutorConfig::getPeftCacheConfig"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig19getRecvPollPeriodMsEv", "tensorrt_llm::executor::ExecutorConfig::getRecvPollPeriodMs"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig28getRequestStatsMaxIterationsEv", "tensorrt_llm::executor::ExecutorConfig::getRequestStatsMaxIterations"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig18getSchedulerConfigEv", "tensorrt_llm::executor::ExecutorConfig::getSchedulerConfig"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mBatchingTypeE", "tensorrt_llm::executor::ExecutorConfig::mBatchingType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig12mDebugConfigE", "tensorrt_llm::executor::ExecutorConfig::mDebugConfig"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15mDecodingConfigE", "tensorrt_llm::executor::ExecutorConfig::mDecodingConfig"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig21mEnableChunkedContextE", "tensorrt_llm::executor::ExecutorConfig::mEnableChunkedContext"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig30mExtendedRuntimePerfKnobConfigE", "tensorrt_llm::executor::ExecutorConfig::mExtendedRuntimePerfKnobConfig"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18mGpuWeightsPercentE", "tensorrt_llm::executor::ExecutorConfig::mGpuWeightsPercent"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mIterStatsMaxIterationsE", "tensorrt_llm::executor::ExecutorConfig::mIterStatsMaxIterations"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14mKvCacheConfigE", "tensorrt_llm::executor::ExecutorConfig::mKvCacheConfig"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig26mLogitsPostProcessorConfigE", "tensorrt_llm::executor::ExecutorConfig::mLogitsPostProcessorConfig"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxBatchSizeE", "tensorrt_llm::executor::ExecutorConfig::mMaxBatchSize"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxBeamWidthE", "tensorrt_llm::executor::ExecutorConfig::mMaxBeamWidth"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxNumTokensE", "tensorrt_llm::executor::ExecutorConfig::mMaxNumTokens"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxQueueSizeE", "tensorrt_llm::executor::ExecutorConfig::mMaxQueueSize"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mMaxSeqIdleMicrosecondsE", "tensorrt_llm::executor::ExecutorConfig::mMaxSeqIdleMicroseconds"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18mNormalizeLogProbsE", "tensorrt_llm::executor::ExecutorConfig::mNormalizeLogProbs"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15mParallelConfigE", "tensorrt_llm::executor::ExecutorConfig::mParallelConfig"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16mPeftCacheConfigE", "tensorrt_llm::executor::ExecutorConfig::mPeftCacheConfig"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17mRecvPollPeriodMsE", "tensorrt_llm::executor::ExecutorConfig::mRecvPollPeriodMs"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig26mRequestStatsMaxIterationsE", "tensorrt_llm::executor::ExecutorConfig::mRequestStatsMaxIterations"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16mSchedulerConfigE", "tensorrt_llm::executor::ExecutorConfig::mSchedulerConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setBatchingTypeE12BatchingType", "tensorrt_llm::executor::ExecutorConfig::setBatchingType"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setBatchingTypeE12BatchingType", "tensorrt_llm::executor::ExecutorConfig::setBatchingType::batchingType"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14setDebugConfigERK11DebugConfig", "tensorrt_llm::executor::ExecutorConfig::setDebugConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14setDebugConfigERK11DebugConfig", "tensorrt_llm::executor::ExecutorConfig::setDebugConfig::debugConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setDecodingConfigERK14DecodingConfig", "tensorrt_llm::executor::ExecutorConfig::setDecodingConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setDecodingConfigERK14DecodingConfig", "tensorrt_llm::executor::ExecutorConfig::setDecodingConfig::decodingConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23setEnableChunkedContextEb", "tensorrt_llm::executor::ExecutorConfig::setEnableChunkedContext"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23setEnableChunkedContextEb", "tensorrt_llm::executor::ExecutorConfig::setEnableChunkedContext::enableChunkedContext"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig32setExtendedRuntimePerfKnobConfigERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::ExecutorConfig::setExtendedRuntimePerfKnobConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig32setExtendedRuntimePerfKnobConfigERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::ExecutorConfig::setExtendedRuntimePerfKnobConfig::extendedRuntimePerfKnobConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setGpuWeightsPercentERKf", "tensorrt_llm::executor::ExecutorConfig::setGpuWeightsPercent"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setGpuWeightsPercentERKf", "tensorrt_llm::executor::ExecutorConfig::setGpuWeightsPercent::gpuWeightsPercent"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setIterStatsMaxIterationsE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setIterStatsMaxIterations"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setIterStatsMaxIterationsE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setIterStatsMaxIterations::iterStatsMaxIterations"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16setKvCacheConfigERK13KvCacheConfig", "tensorrt_llm::executor::ExecutorConfig::setKvCacheConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16setKvCacheConfigERK13KvCacheConfig", "tensorrt_llm::executor::ExecutorConfig::setKvCacheConfig::kvCacheConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setLogitsPostProcessorConfigERK25LogitsPostProcessorConfig", "tensorrt_llm::executor::ExecutorConfig::setLogitsPostProcessorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setLogitsPostProcessorConfigERK25LogitsPostProcessorConfig", "tensorrt_llm::executor::ExecutorConfig::setLogitsPostProcessorConfig::logitsPostProcessorConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBatchSizeE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxBatchSize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBatchSizeE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxBatchSize::maxBatchSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBeamWidthE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxBeamWidth"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBeamWidthE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxBeamWidth::maxBeamWidth"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxNumTokensE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxNumTokens"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxNumTokensE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setMaxNumTokens::maxNumTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxQueueSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ExecutorConfig::setMaxQueueSize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxQueueSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::ExecutorConfig::setMaxQueueSize::maxQueueSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setMaxSeqIdleMicrosecondsE8uint64_t", "tensorrt_llm::executor::ExecutorConfig::setMaxSeqIdleMicroseconds"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setMaxSeqIdleMicrosecondsE8uint64_t", "tensorrt_llm::executor::ExecutorConfig::setMaxSeqIdleMicroseconds::maxNumTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setNormalizeLogProbsEb", "tensorrt_llm::executor::ExecutorConfig::setNormalizeLogProbs"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setNormalizeLogProbsEb", "tensorrt_llm::executor::ExecutorConfig::setNormalizeLogProbs::normalizeLogProbs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setParallelConfigERK14ParallelConfig", "tensorrt_llm::executor::ExecutorConfig::setParallelConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setParallelConfigERK14ParallelConfig", "tensorrt_llm::executor::ExecutorConfig::setParallelConfig::parallelConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setPeftCacheConfigERK15PeftCacheConfig", "tensorrt_llm::executor::ExecutorConfig::setPeftCacheConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setPeftCacheConfigERK15PeftCacheConfig", "tensorrt_llm::executor::ExecutorConfig::setPeftCacheConfig::peftCacheConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19setRecvPollPeriodMsERK10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setRecvPollPeriodMs"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19setRecvPollPeriodMsERK10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setRecvPollPeriodMs::recvPollPeriodMs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setRequestStatsMaxIterationsE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setRequestStatsMaxIterations"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setRequestStatsMaxIterationsE10SizeType32", "tensorrt_llm::executor::ExecutorConfig::setRequestStatsMaxIterations::requestStatsMaxIterations"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setSchedulerConfigERK15SchedulerConfig", "tensorrt_llm::executor::ExecutorConfig::setSchedulerConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setSchedulerConfigERK15SchedulerConfig", "tensorrt_llm::executor::ExecutorConfig::setSchedulerConfig::schedulerConfig"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfigE", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig29ExtendedRuntimePerfKnobConfigEbb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::ExtendedRuntimePerfKnobConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig29ExtendedRuntimePerfKnobConfigEbb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::ExtendedRuntimePerfKnobConfig::enableContextFMHAFP32Acc"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig29ExtendedRuntimePerfKnobConfigEbb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::ExtendedRuntimePerfKnobConfig::multiBlockMode"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig27getEnableContextFMHAFP32AccEv", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::getEnableContextFMHAFP32Acc"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig17getMultiBlockModeEv", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::getMultiBlockMode"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig25mEnableContextFMHAFP32AccE", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::mEnableContextFMHAFP32Acc"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig15mMultiBlockModeE", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::mMultiBlockMode"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfigeqERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::operator=="], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfigeqERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::operator==::other"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig27setEnableContextFMHAFP32AccEb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setEnableContextFMHAFP32Acc"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig27setEnableContextFMHAFP32AccEb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setEnableContextFMHAFP32Acc::enableContextFMHAFP32Acc"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig17setMultiBlockModeEb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setMultiBlockMode"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig17setMultiBlockModeEb", "tensorrt_llm::executor::ExtendedRuntimePerfKnobConfig::setMultiBlockMode::multiBlockMode"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfigE", "tensorrt_llm::executor::ExternalDraftTokensConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig25ExternalDraftTokensConfigE9VecTokensNSt8optionalI6TensorEERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::ExternalDraftTokensConfig::ExternalDraftTokensConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig25ExternalDraftTokensConfigE9VecTokensNSt8optionalI6TensorEERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::ExternalDraftTokensConfig::ExternalDraftTokensConfig::acceptanceThreshold"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig25ExternalDraftTokensConfigE9VecTokensNSt8optionalI6TensorEERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::ExternalDraftTokensConfig::ExternalDraftTokensConfig::logits"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig25ExternalDraftTokensConfigE9VecTokensNSt8optionalI6TensorEERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::ExternalDraftTokensConfig::ExternalDraftTokensConfig::tokens"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig22getAcceptanceThresholdEv", "tensorrt_llm::executor::ExternalDraftTokensConfig::getAcceptanceThreshold"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig9getLogitsEv", "tensorrt_llm::executor::ExternalDraftTokensConfig::getLogits"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig9getTokensEv", "tensorrt_llm::executor::ExternalDraftTokensConfig::getTokens"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig20mAcceptanceThresholdE", "tensorrt_llm::executor::ExternalDraftTokensConfig::mAcceptanceThreshold"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig7mLogitsE", "tensorrt_llm::executor::ExternalDraftTokensConfig::mLogits"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig7mTokensE", "tensorrt_llm::executor::ExternalDraftTokensConfig::mTokens"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor12FinishReasonE", "tensorrt_llm::executor::FinishReason"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12FinishReason7kEND_IDE", "tensorrt_llm::executor::FinishReason::kEND_ID"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12FinishReason7kLENGTHE", "tensorrt_llm::executor::FinishReason::kLENGTH"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12FinishReason13kNOT_FINISHEDE", "tensorrt_llm::executor::FinishReason::kNOT_FINISHED"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12FinishReason11kSTOP_WORDSE", "tensorrt_llm::executor::FinishReason::kSTOP_WORDS"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor9FloatTypeE", "tensorrt_llm::executor::FloatType"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor6IdTypeE", "tensorrt_llm::executor::IdType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStatsE", "tensorrt_llm::executor::InflightBatchingStats"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats26avgNumDecodedTokensPerIterE", "tensorrt_llm::executor::InflightBatchingStats::avgNumDecodedTokensPerIter"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats12microBatchIdE", "tensorrt_llm::executor::InflightBatchingStats::microBatchId"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats18numContextRequestsE", "tensorrt_llm::executor::InflightBatchingStats::numContextRequests"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats12numCtxTokensE", "tensorrt_llm::executor::InflightBatchingStats::numCtxTokens"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats14numGenRequestsE", "tensorrt_llm::executor::InflightBatchingStats::numGenRequests"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats17numPausedRequestsE", "tensorrt_llm::executor::InflightBatchingStats::numPausedRequests"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats20numScheduledRequestsE", "tensorrt_llm::executor::InflightBatchingStats::numScheduledRequests"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14IterationStatsE", "tensorrt_llm::executor::IterationStats"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats11cpuMemUsageE", "tensorrt_llm::executor::IterationStats::cpuMemUsage"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats17crossKvCacheStatsE", "tensorrt_llm::executor::IterationStats::crossKvCacheStats"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats11gpuMemUsageE", "tensorrt_llm::executor::IterationStats::gpuMemUsage"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats21inflightBatchingStatsE", "tensorrt_llm::executor::IterationStats::inflightBatchingStats"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats4iterE", "tensorrt_llm::executor::IterationStats::iter"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats13iterLatencyMSE", "tensorrt_llm::executor::IterationStats::iterLatencyMS"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats12kvCacheStatsE", "tensorrt_llm::executor::IterationStats::kvCacheStats"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats20maxNumActiveRequestsE", "tensorrt_llm::executor::IterationStats::maxNumActiveRequests"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats31newActiveRequestsQueueLatencyMSE", "tensorrt_llm::executor::IterationStats::newActiveRequestsQueueLatencyMS"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats17numActiveRequestsE", "tensorrt_llm::executor::IterationStats::numActiveRequests"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats20numCompletedRequestsE", "tensorrt_llm::executor::IterationStats::numCompletedRequests"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats17numQueuedRequestsE", "tensorrt_llm::executor::IterationStats::numQueuedRequests"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats14pinnedMemUsageE", "tensorrt_llm::executor::IterationStats::pinnedMemUsage"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats19staticBatchingStatsE", "tensorrt_llm::executor::IterationStats::staticBatchingStats"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14IterationStats9timestampE", "tensorrt_llm::executor::IterationStats::timestamp"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor13IterationTypeE", "tensorrt_llm::executor::IterationType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerializationE", "tensorrt_llm::executor::JsonSerialization"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK12RequestStats", "tensorrt_llm::executor::JsonSerialization::toJsonStr"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK14IterationStats", "tensorrt_llm::executor::JsonSerialization::toJsonStr"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK24RequestStatsPerIteration", "tensorrt_llm::executor::JsonSerialization::toJsonStr"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK14IterationStats", "tensorrt_llm::executor::JsonSerialization::toJsonStr::iterationStats"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK12RequestStats", "tensorrt_llm::executor::JsonSerialization::toJsonStr::requestStats"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK24RequestStatsPerIteration", "tensorrt_llm::executor::JsonSerialization::toJsonStr::requestStatsPerIter"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfigE", "tensorrt_llm::executor::KvCacheConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEb", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEb", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::enableBlockReuse"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEb", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::freeGpuMemoryFraction"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEb", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::hostCacheSize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEb", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::maxAttentionWindowVec"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEb", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::maxTokens"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEb", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::onboardBlocks"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEb", "tensorrt_llm::executor::KvCacheConfig::KvCacheConfig::sinkTokenLength"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig19getEnableBlockReuseEv", "tensorrt_llm::executor::KvCacheConfig::getEnableBlockReuse"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig24getFreeGpuMemoryFractionEv", "tensorrt_llm::executor::KvCacheConfig::getFreeGpuMemoryFraction"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig16getHostCacheSizeEv", "tensorrt_llm::executor::KvCacheConfig::getHostCacheSize"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig24getMaxAttentionWindowVecEv", "tensorrt_llm::executor::KvCacheConfig::getMaxAttentionWindowVec"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig12getMaxTokensEv", "tensorrt_llm::executor::KvCacheConfig::getMaxTokens"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig16getOnboardBlocksEv", "tensorrt_llm::executor::KvCacheConfig::getOnboardBlocks"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig18getSinkTokenLengthEv", "tensorrt_llm::executor::KvCacheConfig::getSinkTokenLength"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig17mEnableBlockReuseE", "tensorrt_llm::executor::KvCacheConfig::mEnableBlockReuse"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig22mFreeGpuMemoryFractionE", "tensorrt_llm::executor::KvCacheConfig::mFreeGpuMemoryFraction"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig14mHostCacheSizeE", "tensorrt_llm::executor::KvCacheConfig::mHostCacheSize"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig22mMaxAttentionWindowVecE", "tensorrt_llm::executor::KvCacheConfig::mMaxAttentionWindowVec"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig10mMaxTokensE", "tensorrt_llm::executor::KvCacheConfig::mMaxTokens"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig14mOnboardBlocksE", "tensorrt_llm::executor::KvCacheConfig::mOnboardBlocks"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16mSinkTokenLengthE", "tensorrt_llm::executor::KvCacheConfig::mSinkTokenLength"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19setEnableBlockReuseEb", "tensorrt_llm::executor::KvCacheConfig::setEnableBlockReuse"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19setEnableBlockReuseEb", "tensorrt_llm::executor::KvCacheConfig::setEnableBlockReuse::enableBlockReuse"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setFreeGpuMemoryFractionE9FloatType", "tensorrt_llm::executor::KvCacheConfig::setFreeGpuMemoryFraction"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setFreeGpuMemoryFractionE9FloatType", "tensorrt_llm::executor::KvCacheConfig::setFreeGpuMemoryFraction::freeGpuMemoryFraction"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setHostCacheSizeE6size_t", "tensorrt_llm::executor::KvCacheConfig::setHostCacheSize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setHostCacheSizeE6size_t", "tensorrt_llm::executor::KvCacheConfig::setHostCacheSize::hostCacheSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setMaxAttentionWindowVecENSt6vectorI10SizeType32EE", "tensorrt_llm::executor::KvCacheConfig::setMaxAttentionWindowVec"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setMaxAttentionWindowVecENSt6vectorI10SizeType32EE", "tensorrt_llm::executor::KvCacheConfig::setMaxAttentionWindowVec::maxAttentionWindowVec"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig12setMaxTokensE10SizeType32", "tensorrt_llm::executor::KvCacheConfig::setMaxTokens"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig12setMaxTokensE10SizeType32", "tensorrt_llm::executor::KvCacheConfig::setMaxTokens::maxTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setOnboardBlocksEb", "tensorrt_llm::executor::KvCacheConfig::setOnboardBlocks"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setOnboardBlocksEb", "tensorrt_llm::executor::KvCacheConfig::setOnboardBlocks::onboardBlocks"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig18setSinkTokenLengthE10SizeType32", "tensorrt_llm::executor::KvCacheConfig::setSinkTokenLength"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig18setSinkTokenLengthE10SizeType32", "tensorrt_llm::executor::KvCacheConfig::setSinkTokenLength::sinkTokenLength"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStatsE", "tensorrt_llm::executor::KvCacheStats"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats14allocNewBlocksE", "tensorrt_llm::executor::KvCacheStats::allocNewBlocks"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats16allocTotalBlocksE", "tensorrt_llm::executor::KvCacheStats::allocTotalBlocks"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats13freeNumBlocksE", "tensorrt_llm::executor::KvCacheStats::freeNumBlocks"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12maxNumBlocksE", "tensorrt_llm::executor::KvCacheStats::maxNumBlocks"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12reusedBlocksE", "tensorrt_llm::executor::KvCacheStats::reusedBlocks"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats14tokensPerBlockE", "tensorrt_llm::executor::KvCacheStats::tokensPerBlock"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12KvCacheStats13usedNumBlocksE", "tensorrt_llm::executor::KvCacheStats::usedNumBlocks"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor19LogitsPostProcessorE", "tensorrt_llm::executor::LogitsPostProcessor"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor26LogitsPostProcessorBatchedE", "tensorrt_llm::executor::LogitsPostProcessorBatched"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfigE", "tensorrt_llm::executor::LogitsPostProcessorConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig25LogitsPostProcessorConfigENSt8optionalI22LogitsPostProcessorMapEENSt8optionalI26LogitsPostProcessorBatchedEEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::LogitsPostProcessorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig25LogitsPostProcessorConfigENSt8optionalI22LogitsPostProcessorMapEENSt8optionalI26LogitsPostProcessorBatchedEEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::LogitsPostProcessorConfig::processorBatched"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig25LogitsPostProcessorConfigENSt8optionalI22LogitsPostProcessorMapEENSt8optionalI26LogitsPostProcessorBatchedEEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::LogitsPostProcessorConfig::processorMap"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig25LogitsPostProcessorConfigENSt8optionalI22LogitsPostProcessorMapEENSt8optionalI26LogitsPostProcessorBatchedEEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::LogitsPostProcessorConfig::replicate"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig19getProcessorBatchedEv", "tensorrt_llm::executor::LogitsPostProcessorConfig::getProcessorBatched"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig15getProcessorMapEv", "tensorrt_llm::executor::LogitsPostProcessorConfig::getProcessorMap"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig12getReplicateEv", "tensorrt_llm::executor::LogitsPostProcessorConfig::getReplicate"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig17mProcessorBatchedE", "tensorrt_llm::executor::LogitsPostProcessorConfig::mProcessorBatched"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig13mProcessorMapE", "tensorrt_llm::executor::LogitsPostProcessorConfig::mProcessorMap"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig10mReplicateE", "tensorrt_llm::executor::LogitsPostProcessorConfig::mReplicate"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig19setProcessorBatchedERK26LogitsPostProcessorBatched", "tensorrt_llm::executor::LogitsPostProcessorConfig::setProcessorBatched"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig19setProcessorBatchedERK26LogitsPostProcessorBatched", "tensorrt_llm::executor::LogitsPostProcessorConfig::setProcessorBatched::processorBatched"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig15setProcessorMapERK22LogitsPostProcessorMap", "tensorrt_llm::executor::LogitsPostProcessorConfig::setProcessorMap"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig15setProcessorMapERK22LogitsPostProcessorMap", "tensorrt_llm::executor::LogitsPostProcessorConfig::setProcessorMap::processorMap"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig12setReplicateEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::setReplicate"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig12setReplicateEb", "tensorrt_llm::executor::LogitsPostProcessorConfig::setReplicate::replicate"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor22LogitsPostProcessorMapE", "tensorrt_llm::executor::LogitsPostProcessorMap"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfigE", "tensorrt_llm::executor::LookaheadDecodingConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::LookaheadDecodingConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigEv", "tensorrt_llm::executor::LookaheadDecodingConfig::LookaheadDecodingConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::LookaheadDecodingConfig::ngramSize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::LookaheadDecodingConfig::verificationSetSize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::LookaheadDecodingConfig::windowSize"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig28calculateSpeculativeResourceEv", "tensorrt_llm::executor::LookaheadDecodingConfig::calculateSpeculativeResource"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig3getEv", "tensorrt_llm::executor::LookaheadDecodingConfig::get"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig12getNgramSizeEv", "tensorrt_llm::executor::LookaheadDecodingConfig::getNgramSize"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig22getVerificationSetSizeEv", "tensorrt_llm::executor::LookaheadDecodingConfig::getVerificationSetSize"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig13getWindowSizeEv", "tensorrt_llm::executor::LookaheadDecodingConfig::getWindowSize"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig4isLEERK23LookaheadDecodingConfig", "tensorrt_llm::executor::LookaheadDecodingConfig::isLE"], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig4isLEERK23LookaheadDecodingConfig", "tensorrt_llm::executor::LookaheadDecodingConfig::isLE::that"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig7isLegalE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::isLegal"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig7isLegalE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::isLegal::ngramSize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig7isLegalE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::isLegal::verificationSetSize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig7isLegalE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::executor::LookaheadDecodingConfig::isLegal::windowSize"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig10mNgramSizeE", "tensorrt_llm::executor::LookaheadDecodingConfig::mNgramSize"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig20mVerificationSetSizeE", "tensorrt_llm::executor::LookaheadDecodingConfig::mVerificationSetSize"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig11mWindowSizeE", "tensorrt_llm::executor::LookaheadDecodingConfig::mWindowSize"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfigeqERK23LookaheadDecodingConfig", "tensorrt_llm::executor::LookaheadDecodingConfig::operator=="], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfigeqERK23LookaheadDecodingConfig", "tensorrt_llm::executor::LookaheadDecodingConfig::operator==::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfigE", "tensorrt_llm::executor::LoraConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig10LoraConfigE6IdTypeNSt8optionalI6TensorEENSt8optionalI6TensorEE", "tensorrt_llm::executor::LoraConfig::LoraConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig10LoraConfigE6IdTypeNSt8optionalI6TensorEENSt8optionalI6TensorEE", "tensorrt_llm::executor::LoraConfig::LoraConfig::config"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig10LoraConfigE6IdTypeNSt8optionalI6TensorEENSt8optionalI6TensorEE", "tensorrt_llm::executor::LoraConfig::LoraConfig::taskId"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig10LoraConfigE6IdTypeNSt8optionalI6TensorEENSt8optionalI6TensorEE", "tensorrt_llm::executor::LoraConfig::LoraConfig::weights"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor10LoraConfig9getConfigEv", "tensorrt_llm::executor::LoraConfig::getConfig"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor10LoraConfig9getTaskIdEv", "tensorrt_llm::executor::LoraConfig::getTaskId"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor10LoraConfig10getWeightsEv", "tensorrt_llm::executor::LoraConfig::getWeights"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig7mConfigE", "tensorrt_llm::executor::LoraConfig::mConfig"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig7mTaskIdE", "tensorrt_llm::executor::LoraConfig::mTaskId"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10LoraConfig8mWeightsE", "tensorrt_llm::executor::LoraConfig::mWeights"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor13MedusaChoicesE", "tensorrt_llm::executor::MedusaChoices"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor10MemoryTypeE", "tensorrt_llm::executor::MemoryType"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType4kCPUE", "tensorrt_llm::executor::MemoryType::kCPU"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType11kCPU_PINNEDE", "tensorrt_llm::executor::MemoryType::kCPU_PINNED"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType15kCPU_PINNEDPOOLE", "tensorrt_llm::executor::MemoryType::kCPU_PINNEDPOOL"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType4kGPUE", "tensorrt_llm::executor::MemoryType::kGPU"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType8kUNKNOWNE", "tensorrt_llm::executor::MemoryType::kUNKNOWN"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor10MemoryType4kUVME", "tensorrt_llm::executor::MemoryType::kUVM"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor9ModelTypeE", "tensorrt_llm::executor::ModelType"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor9ModelType13kDECODER_ONLYE", "tensorrt_llm::executor::ModelType::kDECODER_ONLY"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor9ModelType16kENCODER_DECODERE", "tensorrt_llm::executor::ModelType::kENCODER_DECODER"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor9ModelType13kENCODER_ONLYE", "tensorrt_llm::executor::ModelType::kENCODER_ONLY"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfigE", "tensorrt_llm::executor::OrchestratorConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb", "tensorrt_llm::executor::OrchestratorConfig::OrchestratorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb", "tensorrt_llm::executor::OrchestratorConfig::OrchestratorConfig::isOrchestrator"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb", "tensorrt_llm::executor::OrchestratorConfig::OrchestratorConfig::orchLeaderComm"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb", "tensorrt_llm::executor::OrchestratorConfig::OrchestratorConfig::spawnProcesses"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb", "tensorrt_llm::executor::OrchestratorConfig::OrchestratorConfig::workerExecutablePath"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getIsOrchestratorEv", "tensorrt_llm::executor::OrchestratorConfig::getIsOrchestrator"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getOrchLeaderCommEv", "tensorrt_llm::executor::OrchestratorConfig::getOrchLeaderComm"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getSpawnProcessesEv", "tensorrt_llm::executor::OrchestratorConfig::getSpawnProcesses"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig23getWorkerExecutablePathEv", "tensorrt_llm::executor::OrchestratorConfig::getWorkerExecutablePath"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mIsOrchestratorE", "tensorrt_llm::executor::OrchestratorConfig::mIsOrchestrator"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mOrchLeaderCommE", "tensorrt_llm::executor::OrchestratorConfig::mOrchLeaderComm"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mSpawnProcessesE", "tensorrt_llm::executor::OrchestratorConfig::mSpawnProcesses"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig21mWorkerExecutablePathE", "tensorrt_llm::executor::OrchestratorConfig::mWorkerExecutablePath"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setIsOrchestratorEb", "tensorrt_llm::executor::OrchestratorConfig::setIsOrchestrator"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setIsOrchestratorEb", "tensorrt_llm::executor::OrchestratorConfig::setIsOrchestrator::isOrchestrator"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setOrchLeaderCommERKNSt10shared_ptrIN3mpi7MpiCommEEE", "tensorrt_llm::executor::OrchestratorConfig::setOrchLeaderComm"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setOrchLeaderCommERKNSt10shared_ptrIN3mpi7MpiCommEEE", "tensorrt_llm::executor::OrchestratorConfig::setOrchLeaderComm::orchLeaderComm"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setSpawnProcessesEb", "tensorrt_llm::executor::OrchestratorConfig::setSpawnProcesses"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setSpawnProcessesEb", "tensorrt_llm::executor::OrchestratorConfig::setSpawnProcesses::spawnProcesses"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig23setWorkerExecutablePathERKNSt6stringE", "tensorrt_llm::executor::OrchestratorConfig::setWorkerExecutablePath"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig23setWorkerExecutablePathERKNSt6stringE", "tensorrt_llm::executor::OrchestratorConfig::setWorkerExecutablePath::workerExecutablePath"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfigE", "tensorrt_llm::executor::OutputConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbb", "tensorrt_llm::executor::OutputConfig::OutputConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbb", "tensorrt_llm::executor::OutputConfig::OutputConfig::excludeInputFromOutput"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbb", "tensorrt_llm::executor::OutputConfig::OutputConfig::returnContextLogits"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbb", "tensorrt_llm::executor::OutputConfig::OutputConfig::returnEncoderOutput"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbb", "tensorrt_llm::executor::OutputConfig::OutputConfig::returnGenerationLogits"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbb", "tensorrt_llm::executor::OutputConfig::OutputConfig::returnLogProbs"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig22excludeInputFromOutputE", "tensorrt_llm::executor::OutputConfig::excludeInputFromOutput"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig19returnContextLogitsE", "tensorrt_llm::executor::OutputConfig::returnContextLogits"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig19returnEncoderOutputE", "tensorrt_llm::executor::OutputConfig::returnEncoderOutput"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig22returnGenerationLogitsE", "tensorrt_llm::executor::OutputConfig::returnGenerationLogits"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12OutputConfig14returnLogProbsE", "tensorrt_llm::executor::OutputConfig::returnLogProbs"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfigE", "tensorrt_llm::executor::ParallelConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig::commMode"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig::commType"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig::deviceIds"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig::orchestratorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEE", "tensorrt_llm::executor::ParallelConfig::ParallelConfig::participantIds"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig20getCommunicationModeEv", "tensorrt_llm::executor::ParallelConfig::getCommunicationMode"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig20getCommunicationTypeEv", "tensorrt_llm::executor::ParallelConfig::getCommunicationType"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig12getDeviceIdsEv", "tensorrt_llm::executor::ParallelConfig::getDeviceIds"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig21getOrchestratorConfigEv", "tensorrt_llm::executor::ParallelConfig::getOrchestratorConfig"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig17getParticipantIdsEv", "tensorrt_llm::executor::ParallelConfig::getParticipantIds"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig9mCommModeE", "tensorrt_llm::executor::ParallelConfig::mCommMode"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig9mCommTypeE", "tensorrt_llm::executor::ParallelConfig::mCommType"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig10mDeviceIdsE", "tensorrt_llm::executor::ParallelConfig::mDeviceIds"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig19mOrchestratorConfigE", "tensorrt_llm::executor::ParallelConfig::mOrchestratorConfig"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig15mParticipantIdsE", "tensorrt_llm::executor::ParallelConfig::mParticipantIds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationModeE17CommunicationMode", "tensorrt_llm::executor::ParallelConfig::setCommunicationMode"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationModeE17CommunicationMode", "tensorrt_llm::executor::ParallelConfig::setCommunicationMode::mode"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationTypeE17CommunicationType", "tensorrt_llm::executor::ParallelConfig::setCommunicationType"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationTypeE17CommunicationType", "tensorrt_llm::executor::ParallelConfig::setCommunicationType::type"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig12setDeviceIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::setDeviceIds"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig12setDeviceIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::setDeviceIds::deviceIds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig21setOrchestratorConfigERK18OrchestratorConfig", "tensorrt_llm::executor::ParallelConfig::setOrchestratorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig21setOrchestratorConfigERK18OrchestratorConfig", "tensorrt_llm::executor::ParallelConfig::setOrchestratorConfig::orchestratorConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig17setParticipantIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::setParticipantIds"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14ParallelConfig17setParticipantIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::ParallelConfig::setParticipantIds::participantIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfigE", "tensorrt_llm::executor::PeftCacheConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::deviceCachePercent"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::hostCacheSize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::maxAdapterSize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::maxPagesPerBlockDevice"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::maxPagesPerBlockHost"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::numCopyStreams"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::numDeviceModuleLayer"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::numEnsureWorkers"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::numHostModuleLayer"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::numPutWorkers"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEE", "tensorrt_llm::executor::PeftCacheConfig::PeftCacheConfig::optimalAdapterSize"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getDeviceCachePercentEv", "tensorrt_llm::executor::PeftCacheConfig::getDeviceCachePercent"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig16getHostCacheSizeEv", "tensorrt_llm::executor::PeftCacheConfig::getHostCacheSize"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig17getMaxAdapterSizeEv", "tensorrt_llm::executor::PeftCacheConfig::getMaxAdapterSize"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig25getMaxPagesPerBlockDeviceEv", "tensorrt_llm::executor::PeftCacheConfig::getMaxPagesPerBlockDevice"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig23getMaxPagesPerBlockHostEv", "tensorrt_llm::executor::PeftCacheConfig::getMaxPagesPerBlockHost"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig17getNumCopyStreamsEv", "tensorrt_llm::executor::PeftCacheConfig::getNumCopyStreams"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig23getNumDeviceModuleLayerEv", "tensorrt_llm::executor::PeftCacheConfig::getNumDeviceModuleLayer"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig19getNumEnsureWorkersEv", "tensorrt_llm::executor::PeftCacheConfig::getNumEnsureWorkers"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getNumHostModuleLayerEv", "tensorrt_llm::executor::PeftCacheConfig::getNumHostModuleLayer"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig16getNumPutWorkersEv", "tensorrt_llm::executor::PeftCacheConfig::getNumPutWorkers"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getOptimalAdapterSizeEv", "tensorrt_llm::executor::PeftCacheConfig::getOptimalAdapterSize"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mDeviceCachePercentE", "tensorrt_llm::executor::PeftCacheConfig::mDeviceCachePercent"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig14mHostCacheSizeE", "tensorrt_llm::executor::PeftCacheConfig::mHostCacheSize"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15mMaxAdapterSizeE", "tensorrt_llm::executor::PeftCacheConfig::mMaxAdapterSize"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig23mMaxPagesPerBlockDeviceE", "tensorrt_llm::executor::PeftCacheConfig::mMaxPagesPerBlockDevice"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig21mMaxPagesPerBlockHostE", "tensorrt_llm::executor::PeftCacheConfig::mMaxPagesPerBlockHost"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15mNumCopyStreamsE", "tensorrt_llm::executor::PeftCacheConfig::mNumCopyStreams"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig21mNumDeviceModuleLayerE", "tensorrt_llm::executor::PeftCacheConfig::mNumDeviceModuleLayer"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig17mNumEnsureWorkersE", "tensorrt_llm::executor::PeftCacheConfig::mNumEnsureWorkers"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mNumHostModuleLayerE", "tensorrt_llm::executor::PeftCacheConfig::mNumHostModuleLayer"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig14mNumPutWorkersE", "tensorrt_llm::executor::PeftCacheConfig::mNumPutWorkers"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mOptimalAdapterSizeE", "tensorrt_llm::executor::PeftCacheConfig::mOptimalAdapterSize"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfigeqERK15PeftCacheConfig", "tensorrt_llm::executor::PeftCacheConfig::operator=="], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfigeqERK15PeftCacheConfig", "tensorrt_llm::executor::PeftCacheConfig::operator==::other"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor19PhonyNameDueToError5valueE", "tensorrt_llm::executor::PhonyNameDueToError::value"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor19PhonyNameDueToError5valueE", "tensorrt_llm::executor::PhonyNameDueToError::value"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor19PhonyNameDueToError5valueE", "tensorrt_llm::executor::PhonyNameDueToError::value"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor19PhonyNameDueToError5valueE", "tensorrt_llm::executor::PhonyNameDueToError::value"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor12PriorityTypeE", "tensorrt_llm::executor::PriorityType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfigE", "tensorrt_llm::executor::PromptTuningConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig18PromptTuningConfigE6TensorNSt8optionalI16VecTokenExtraIdsEE", "tensorrt_llm::executor::PromptTuningConfig::PromptTuningConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig18PromptTuningConfigE6TensorNSt8optionalI16VecTokenExtraIdsEE", "tensorrt_llm::executor::PromptTuningConfig::PromptTuningConfig::embeddingTable"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig18PromptTuningConfigE6TensorNSt8optionalI16VecTokenExtraIdsEE", "tensorrt_llm::executor::PromptTuningConfig::PromptTuningConfig::inputTokenExtraIds"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor18PromptTuningConfig17getEmbeddingTableEv", "tensorrt_llm::executor::PromptTuningConfig::getEmbeddingTable"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor18PromptTuningConfig21getInputTokenExtraIdsEv", "tensorrt_llm::executor::PromptTuningConfig::getInputTokenExtraIds"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig15mEmbeddingTableE", "tensorrt_llm::executor::PromptTuningConfig::mEmbeddingTable"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig19mInputTokenExtraIdsE", "tensorrt_llm::executor::PromptTuningConfig::mInputTokenExtraIds"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor14RandomSeedTypeE", "tensorrt_llm::executor::RandomSeedType"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor7RequestE", "tensorrt_llm::executor::Request"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestERK7Request", "tensorrt_llm::executor::Request::Request"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestERR7Request", "tensorrt_llm::executor::Request::Request"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::badWords"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::clientId"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::contextPhaseParams"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::embeddingBias"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::encoderInputFeatures"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::encoderInputTokenIds"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::encoderOutputLength"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::endId"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::externalDraftTokensConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::inputTokenIds"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::logitsPostProcessorName"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::lookaheadConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::loraConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::maxTokens"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::numReturnSequences"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestERK7Request", "tensorrt_llm::executor::Request::Request::other"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestERR7Request", "tensorrt_llm::executor::Request::Request::other"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::outputConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::pTuningConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::padId"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::positionIds"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::priority"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::returnAllGeneratedTokens"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::samplingConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::stopWords"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::streaming"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32", "tensorrt_llm::executor::Request::Request::type"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request11getBadWordsEv", "tensorrt_llm::executor::Request::getBadWords"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request11getClientIdEv", "tensorrt_llm::executor::Request::getClientId"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request21getContextPhaseParamsEv", "tensorrt_llm::executor::Request::getContextPhaseParams"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request16getEmbeddingBiasEv", "tensorrt_llm::executor::Request::getEmbeddingBias"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request23getEncoderInputFeaturesEv", "tensorrt_llm::executor::Request::getEncoderInputFeatures"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request23getEncoderInputTokenIdsEv", "tensorrt_llm::executor::Request::getEncoderInputTokenIds"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request22getEncoderOutputLengthEv", "tensorrt_llm::executor::Request::getEncoderOutputLength"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request8getEndIdEv", "tensorrt_llm::executor::Request::getEndId"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request28getExternalDraftTokensConfigEv", "tensorrt_llm::executor::Request::getExternalDraftTokensConfig"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request16getInputTokenIdsEv", "tensorrt_llm::executor::Request::getInputTokenIds"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request26getLogitsPostProcessorNameEv", "tensorrt_llm::executor::Request::getLogitsPostProcessorName"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request18getLookaheadConfigEv", "tensorrt_llm::executor::Request::getLookaheadConfig"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request13getLoraConfigEv", "tensorrt_llm::executor::Request::getLoraConfig"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request15getMaxNewTokensEv", "tensorrt_llm::executor::Request::getMaxNewTokens"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request12getMaxTokensEv", "tensorrt_llm::executor::Request::getMaxTokens"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request21getNumReturnSequencesEv", "tensorrt_llm::executor::Request::getNumReturnSequences"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request15getOutputConfigEv", "tensorrt_llm::executor::Request::getOutputConfig"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request8getPadIdEv", "tensorrt_llm::executor::Request::getPadId"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request14getPositionIdsEv", "tensorrt_llm::executor::Request::getPositionIds"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request11getPriorityEv", "tensorrt_llm::executor::Request::getPriority"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request21getPromptTuningConfigEv", "tensorrt_llm::executor::Request::getPromptTuningConfig"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request14getRequestTypeEv", "tensorrt_llm::executor::Request::getRequestType"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request27getReturnAllGeneratedTokensEv", "tensorrt_llm::executor::Request::getReturnAllGeneratedTokens"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request17getSamplingConfigEv", "tensorrt_llm::executor::Request::getSamplingConfig"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request12getStopWordsEv", "tensorrt_llm::executor::Request::getStopWords"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor7Request12getStreamingEv", "tensorrt_llm::executor::Request::getStreaming"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor7Request25kBatchedPostProcessorNameE", "tensorrt_llm::executor::Request::kBatchedPostProcessorName"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor7Request16kDefaultPriorityE", "tensorrt_llm::executor::Request::kDefaultPriority"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor7Request5mImplE", "tensorrt_llm::executor::Request::mImpl"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7RequestaSERK7Request", "tensorrt_llm::executor::Request::operator="], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7RequestaSERR7Request", "tensorrt_llm::executor::Request::operator="], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7RequestaSERK7Request", "tensorrt_llm::executor::Request::operator=::other"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7RequestaSERR7Request", "tensorrt_llm::executor::Request::operator=::other"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request11setBadWordsERKNSt4listI9VecTokensEE", "tensorrt_llm::executor::Request::setBadWords"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request11setBadWordsERKNSt4listI9VecTokensEE", "tensorrt_llm::executor::Request::setBadWords::badWords"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request11setClientIdE6IdType", "tensorrt_llm::executor::Request::setClientId"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request11setClientIdE6IdType", "tensorrt_llm::executor::Request::setClientId::clientId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request21setContextPhaseParamsE18ContextPhaseParams", "tensorrt_llm::executor::Request::setContextPhaseParams"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request21setContextPhaseParamsE18ContextPhaseParams", "tensorrt_llm::executor::Request::setContextPhaseParams::contextPhaseParams"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request16setEmbeddingBiasERK6Tensor", "tensorrt_llm::executor::Request::setEmbeddingBias"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request16setEmbeddingBiasERK6Tensor", "tensorrt_llm::executor::Request::setEmbeddingBias::embeddingBias"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputFeaturesE6Tensor", "tensorrt_llm::executor::Request::setEncoderInputFeatures"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputFeaturesE6Tensor", "tensorrt_llm::executor::Request::setEncoderInputFeatures::encoderInputFeatures"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputTokenIdsERK9VecTokens", "tensorrt_llm::executor::Request::setEncoderInputTokenIds"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputTokenIdsERK9VecTokens", "tensorrt_llm::executor::Request::setEncoderInputTokenIds::encoderInputTokenIds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request22setEncoderOutputLengthE10SizeType32", "tensorrt_llm::executor::Request::setEncoderOutputLength"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request22setEncoderOutputLengthE10SizeType32", "tensorrt_llm::executor::Request::setEncoderOutputLength::encoderOutputLength"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request8setEndIdE10SizeType32", "tensorrt_llm::executor::Request::setEndId"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request8setEndIdE10SizeType32", "tensorrt_llm::executor::Request::setEndId::endId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request28setExternalDraftTokensConfigERK25ExternalDraftTokensConfig", "tensorrt_llm::executor::Request::setExternalDraftTokensConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request28setExternalDraftTokensConfigERK25ExternalDraftTokensConfig", "tensorrt_llm::executor::Request::setExternalDraftTokensConfig::externalDraftTokensConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request26setLogitsPostProcessorNameERKNSt6stringE", "tensorrt_llm::executor::Request::setLogitsPostProcessorName"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request26setLogitsPostProcessorNameERKNSt6stringE", "tensorrt_llm::executor::Request::setLogitsPostProcessorName::logitsPostProcessorName"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request18setLookaheadConfigERK23LookaheadDecodingConfig", "tensorrt_llm::executor::Request::setLookaheadConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request18setLookaheadConfigERK23LookaheadDecodingConfig", "tensorrt_llm::executor::Request::setLookaheadConfig::lookaheadConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request13setLoraConfigERK10LoraConfig", "tensorrt_llm::executor::Request::setLoraConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request13setLoraConfigERK10LoraConfig", "tensorrt_llm::executor::Request::setLoraConfig::loraConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request21setNumReturnSequencesE10SizeType32", "tensorrt_llm::executor::Request::setNumReturnSequences"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request21setNumReturnSequencesE10SizeType32", "tensorrt_llm::executor::Request::setNumReturnSequences::numReturnSequences"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request15setOutputConfigERK12OutputConfig", "tensorrt_llm::executor::Request::setOutputConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request15setOutputConfigERK12OutputConfig", "tensorrt_llm::executor::Request::setOutputConfig::outputConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request8setPadIdE10SizeType32", "tensorrt_llm::executor::Request::setPadId"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request8setPadIdE10SizeType32", "tensorrt_llm::executor::Request::setPadId::padId"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request14setPositionIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::Request::setPositionIds"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request14setPositionIdsERKNSt6vectorI10SizeType32EE", "tensorrt_llm::executor::Request::setPositionIds::positionIds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request11setPriorityE12PriorityType", "tensorrt_llm::executor::Request::setPriority"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request11setPriorityE12PriorityType", "tensorrt_llm::executor::Request::setPriority::priority"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request21setPromptTuningConfigERK18PromptTuningConfig", "tensorrt_llm::executor::Request::setPromptTuningConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request21setPromptTuningConfigERK18PromptTuningConfig", "tensorrt_llm::executor::Request::setPromptTuningConfig::pTuningConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request14setRequestTypeERK11RequestType", "tensorrt_llm::executor::Request::setRequestType"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request14setRequestTypeERK11RequestType", "tensorrt_llm::executor::Request::setRequestType::requestType"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request27setReturnAllGeneratedTokensEb", "tensorrt_llm::executor::Request::setReturnAllGeneratedTokens"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request27setReturnAllGeneratedTokensEb", "tensorrt_llm::executor::Request::setReturnAllGeneratedTokens::returnAllGeneratedTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request17setSamplingConfigERK14SamplingConfig", "tensorrt_llm::executor::Request::setSamplingConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request17setSamplingConfigERK14SamplingConfig", "tensorrt_llm::executor::Request::setSamplingConfig::config"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request12setStopWordsERKNSt4listI9VecTokensEE", "tensorrt_llm::executor::Request::setStopWords"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request12setStopWordsERKNSt4listI9VecTokensEE", "tensorrt_llm::executor::Request::setStopWords::stopWords"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7Request12setStreamingEb", "tensorrt_llm::executor::Request::setStreaming"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor7Request12setStreamingEb", "tensorrt_llm::executor::Request::setStreaming::streaming"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor7RequestD0Ev", "tensorrt_llm::executor::Request::~Request"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor12RequestStageE", "tensorrt_llm::executor::RequestStage"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12RequestStage20kCONTEXT_IN_PROGRESSE", "tensorrt_llm::executor::RequestStage::kCONTEXT_IN_PROGRESS"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12RequestStage20kENCODER_IN_PROGRESSE", "tensorrt_llm::executor::RequestStage::kENCODER_IN_PROGRESS"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12RequestStage20kGENERATION_COMPLETEE", "tensorrt_llm::executor::RequestStage::kGENERATION_COMPLETE"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12RequestStage23kGENERATION_IN_PROGRESSE", "tensorrt_llm::executor::RequestStage::kGENERATION_IN_PROGRESS"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor12RequestStage7kQUEUEDE", "tensorrt_llm::executor::RequestStage::kQUEUED"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor12RequestStatsE", "tensorrt_llm::executor::RequestStats"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats26avgNumDecodedTokensPerIterE", "tensorrt_llm::executor::RequestStats::avgNumDecodedTokensPerIter"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats22contextPrefillPositionE", "tensorrt_llm::executor::RequestStats::contextPrefillPosition"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats2idE", "tensorrt_llm::executor::RequestStats::id"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats18numGeneratedTokensE", "tensorrt_llm::executor::RequestStats::numGeneratedTokens"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats6pausedE", "tensorrt_llm::executor::RequestStats::paused"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats9scheduledE", "tensorrt_llm::executor::RequestStats::scheduled"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor12RequestStats5stageE", "tensorrt_llm::executor::RequestStats::stage"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIterationE", "tensorrt_llm::executor::RequestStatsPerIteration"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIteration4iterE", "tensorrt_llm::executor::RequestStatsPerIteration::iter"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIteration12requestStatsE", "tensorrt_llm::executor::RequestStatsPerIteration::requestStats"], [0, 2, 1, "_CPPv4N12tensorrt_llm8executor11RequestTypeE", "tensorrt_llm::executor::RequestType"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11RequestType35REQUEST_TYPE_CONTEXT_AND_GENERATIONE", "tensorrt_llm::executor::RequestType::REQUEST_TYPE_CONTEXT_AND_GENERATION"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11RequestType25REQUEST_TYPE_CONTEXT_ONLYE", "tensorrt_llm::executor::RequestType::REQUEST_TYPE_CONTEXT_ONLY"], [0, 3, 1, "_CPPv4N12tensorrt_llm8executor11RequestType28REQUEST_TYPE_GENERATION_ONLYE", "tensorrt_llm::executor::RequestType::REQUEST_TYPE_GENERATION_ONLY"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor8ResponseE", "tensorrt_llm::executor::Response"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdType6Result", "tensorrt_llm::executor::Response::Response"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdTypeNSt6stringE", "tensorrt_llm::executor::Response::Response"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERK8Response", "tensorrt_llm::executor::Response::Response"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERR8Response", "tensorrt_llm::executor::Response::Response"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdType6Result", "tensorrt_llm::executor::Response::Response::Result"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdTypeNSt6stringE", "tensorrt_llm::executor::Response::Response::errorMsg"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERK8Response", "tensorrt_llm::executor::Response::Response::other"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERR8Response", "tensorrt_llm::executor::Response::Response::other"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdType6Result", "tensorrt_llm::executor::Response::Response::requestId"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdTypeNSt6stringE", "tensorrt_llm::executor::Response::Response::requestId"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor8Response11getErrorMsgEv", "tensorrt_llm::executor::Response::getErrorMsg"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor8Response12getRequestIdEv", "tensorrt_llm::executor::Response::getRequestId"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor8Response9getResultEv", "tensorrt_llm::executor::Response::getResult"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor8Response8hasErrorEv", "tensorrt_llm::executor::Response::hasError"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor8Response5mImplE", "tensorrt_llm::executor::Response::mImpl"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8ResponseaSERK8Response", "tensorrt_llm::executor::Response::operator="], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8ResponseaSERR8Response", "tensorrt_llm::executor::Response::operator="], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8ResponseaSERK8Response", "tensorrt_llm::executor::Response::operator=::other"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor8ResponseaSERR8Response", "tensorrt_llm::executor::Response::operator=::other"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor8ResponseD0Ev", "tensorrt_llm::executor::Response::~Response"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor6ResultE", "tensorrt_llm::executor::Result"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor6Result13contextLogitsE", "tensorrt_llm::executor::Result::contextLogits"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor6Result18contextPhaseParamsE", "tensorrt_llm::executor::Result::contextPhaseParams"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor6Result11cumLogProbsE", "tensorrt_llm::executor::Result::cumLogProbs"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor6Result12decodingIterE", "tensorrt_llm::executor::Result::decodingIter"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor6Result13encoderOutputE", "tensorrt_llm::executor::Result::encoderOutput"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor6Result13finishReasonsE", "tensorrt_llm::executor::Result::finishReasons"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor6Result16generationLogitsE", "tensorrt_llm::executor::Result::generationLogits"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor6Result7isFinalE", "tensorrt_llm::executor::Result::isFinal"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor6Result15isSequenceFinalE", "tensorrt_llm::executor::Result::isSequenceFinal"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor6Result8logProbsE", "tensorrt_llm::executor::Result::logProbs"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor6Result14outputTokenIdsE", "tensorrt_llm::executor::Result::outputTokenIds"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor6Result13sequenceIndexE", "tensorrt_llm::executor::Result::sequenceIndex"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfigE", "tensorrt_llm::executor::SamplingConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::beamSearchDiversityRate"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::beamWidth"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::earlyStopping"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::frequencyPenalty"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::lengthPenalty"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::minTokens"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::noRepeatNgramSize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::presencePenalty"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::repetitionPenalty"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::seed"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::temperature"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::topK"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::topP"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::topPDecay"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::topPMin"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::SamplingConfig::topPResetIds"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig28checkBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkBeamSearchDiversityRate"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig28checkBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkBeamSearchDiversityRate::beamSearchDiversityRate"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkBeamWidthE10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkBeamWidth"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkBeamWidthE10SizeType32", "tensorrt_llm::executor::SamplingConfig::checkBeamWidth::beamWidth"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkMinTokensERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::checkMinTokens"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkMinTokensERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::checkMinTokens::minTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::checkNoRepeatNgramSize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::checkNoRepeatNgramSize::noRepeatNgramSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkRepetitionPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkRepetitionPenalty"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkRepetitionPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkRepetitionPenalty::penalty"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16checkTemperatureERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTemperature"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16checkTemperatureERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTemperature::temperature"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopKERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopK"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopKERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopK::topK"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopP"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopP::topP"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkTopPDecayERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPDecay"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkTopPDecayERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPDecay::topPDecay"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12checkTopPMinERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPMin"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12checkTopPMinERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPMin::topPMin"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17checkTopPResetIdsERKNSt8optionalI11TokenIdTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPResetIds"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17checkTopPResetIdsERKNSt8optionalI11TokenIdTypeEE", "tensorrt_llm::executor::SamplingConfig::checkTopPResetIds::topPResetIds"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig26getBeamSearchDiversityRateEv", "tensorrt_llm::executor::SamplingConfig::getBeamSearchDiversityRate"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getBeamWidthEv", "tensorrt_llm::executor::SamplingConfig::getBeamWidth"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig16getEarlyStoppingEv", "tensorrt_llm::executor::SamplingConfig::getEarlyStopping"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig19getFrequencyPenaltyEv", "tensorrt_llm::executor::SamplingConfig::getFrequencyPenalty"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig16getLengthPenaltyEv", "tensorrt_llm::executor::SamplingConfig::getLengthPenalty"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getMinLengthEv", "tensorrt_llm::executor::SamplingConfig::getMinLength"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getMinTokensEv", "tensorrt_llm::executor::SamplingConfig::getMinTokens"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig20getNoRepeatNgramSizeEv", "tensorrt_llm::executor::SamplingConfig::getNoRepeatNgramSize"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig18getPresencePenaltyEv", "tensorrt_llm::executor::SamplingConfig::getPresencePenalty"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig13getRandomSeedEv", "tensorrt_llm::executor::SamplingConfig::getRandomSeed"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig20getRepetitionPenaltyEv", "tensorrt_llm::executor::SamplingConfig::getRepetitionPenalty"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getSeedEv", "tensorrt_llm::executor::SamplingConfig::getSeed"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig14getTemperatureEv", "tensorrt_llm::executor::SamplingConfig::getTemperature"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getTopKEv", "tensorrt_llm::executor::SamplingConfig::getTopK"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getTopPEv", "tensorrt_llm::executor::SamplingConfig::getTopP"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getTopPDecayEv", "tensorrt_llm::executor::SamplingConfig::getTopPDecay"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig10getTopPMinEv", "tensorrt_llm::executor::SamplingConfig::getTopPMin"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig15getTopPResetIdsEv", "tensorrt_llm::executor::SamplingConfig::getTopPResetIds"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig24mBeamSearchDiversityRateE", "tensorrt_llm::executor::SamplingConfig::mBeamSearchDiversityRate"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mBeamWidthE", "tensorrt_llm::executor::SamplingConfig::mBeamWidth"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14mEarlyStoppingE", "tensorrt_llm::executor::SamplingConfig::mEarlyStopping"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17mFrequencyPenaltyE", "tensorrt_llm::executor::SamplingConfig::mFrequencyPenalty"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14mLengthPenaltyE", "tensorrt_llm::executor::SamplingConfig::mLengthPenalty"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mMinTokensE", "tensorrt_llm::executor::SamplingConfig::mMinTokens"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18mNoRepeatNgramSizeE", "tensorrt_llm::executor::SamplingConfig::mNoRepeatNgramSize"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16mPresencePenaltyE", "tensorrt_llm::executor::SamplingConfig::mPresencePenalty"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18mRepetitionPenaltyE", "tensorrt_llm::executor::SamplingConfig::mRepetitionPenalty"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mSeedE", "tensorrt_llm::executor::SamplingConfig::mSeed"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12mTemperatureE", "tensorrt_llm::executor::SamplingConfig::mTemperature"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mTopKE", "tensorrt_llm::executor::SamplingConfig::mTopK"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mTopPE", "tensorrt_llm::executor::SamplingConfig::mTopP"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mTopPDecayE", "tensorrt_llm::executor::SamplingConfig::mTopPDecay"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig8mTopPMinE", "tensorrt_llm::executor::SamplingConfig::mTopPMin"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig13mTopPResetIdsE", "tensorrt_llm::executor::SamplingConfig::mTopPResetIds"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfigeqERK14SamplingConfig", "tensorrt_llm::executor::SamplingConfig::operator=="], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor14SamplingConfigeqERK14SamplingConfig", "tensorrt_llm::executor::SamplingConfig::operator==::other"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig26setBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setBeamSearchDiversityRate"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig26setBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setBeamSearchDiversityRate::beamSearchDiversityRate"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setBeamWidthE10SizeType32", "tensorrt_llm::executor::SamplingConfig::setBeamWidth"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setBeamWidthE10SizeType32", "tensorrt_llm::executor::SamplingConfig::setBeamWidth::beamWidth"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setEarlyStoppingERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setEarlyStopping"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setEarlyStoppingERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setEarlyStopping::earlyStopping"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19setFrequencyPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setFrequencyPenalty"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19setFrequencyPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setFrequencyPenalty::frequencyPenalty"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setLengthPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setLengthPenalty"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setLengthPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setLengthPenalty::lengthPenalty"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setMinLengthERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setMinLength"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setMinLengthERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setMinLength::minLength"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setMinTokensERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setMinTokens"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setMinTokensERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setMinTokens::minTokens"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setNoRepeatNgramSize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setNoRepeatNgramSize::noRepeatNgramSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18setPresencePenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setPresencePenalty"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18setPresencePenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setPresencePenalty::presencePenalty"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig13setRandomSeedERKNSt8optionalI14RandomSeedTypeEE", "tensorrt_llm::executor::SamplingConfig::setRandomSeed"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig13setRandomSeedERKNSt8optionalI14RandomSeedTypeEE", "tensorrt_llm::executor::SamplingConfig::setRandomSeed::randomSeed"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setRepetitionPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setRepetitionPenalty"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setRepetitionPenaltyERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setRepetitionPenalty::repetitionPenalty"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setSeedERKNSt8optionalI14RandomSeedTypeEE", "tensorrt_llm::executor::SamplingConfig::setSeed"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setSeedERKNSt8optionalI14RandomSeedTypeEE", "tensorrt_llm::executor::SamplingConfig::setSeed::seed"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14setTemperatureERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTemperature"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14setTemperatureERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTemperature::temperature"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopKERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setTopK"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopKERKNSt8optionalI10SizeType32EE", "tensorrt_llm::executor::SamplingConfig::setTopK::topK"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopP"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopPERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopP::topP"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setTopPDecayERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPDecay"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setTopPDecayERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPDecay::topPDecay"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10setTopPMinERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPMin"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10setTopPMinERKNSt8optionalI9FloatTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPMin::topPMin"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig15setTopPResetIdsERKNSt8optionalI11TokenIdTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPResetIds"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor14SamplingConfig15setTopPResetIdsERKNSt8optionalI11TokenIdTypeEE", "tensorrt_llm::executor::SamplingConfig::setTopPResetIds::topPResetIds"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfigE", "tensorrt_llm::executor::SchedulerConfig"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig15SchedulerConfigE23CapacitySchedulerPolicyNSt8optionalI21ContextChunkingPolicyEE", "tensorrt_llm::executor::SchedulerConfig::SchedulerConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig15SchedulerConfigE23CapacitySchedulerPolicyNSt8optionalI21ContextChunkingPolicyEE", "tensorrt_llm::executor::SchedulerConfig::SchedulerConfig::capacitySchedulerPolicy"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig15SchedulerConfigE23CapacitySchedulerPolicyNSt8optionalI21ContextChunkingPolicyEE", "tensorrt_llm::executor::SchedulerConfig::SchedulerConfig::contextChunkingPolicy"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfig26getCapacitySchedulerPolicyEv", "tensorrt_llm::executor::SchedulerConfig::getCapacitySchedulerPolicy"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfig24getContextChunkingPolicyEv", "tensorrt_llm::executor::SchedulerConfig::getContextChunkingPolicy"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig24mCapacitySchedulerPolicyE", "tensorrt_llm::executor::SchedulerConfig::mCapacitySchedulerPolicy"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig22mContextChunkingPolicyE", "tensorrt_llm::executor::SchedulerConfig::mContextChunkingPolicy"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfigeqERK15SchedulerConfig", "tensorrt_llm::executor::SchedulerConfig::operator=="], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfigeqERK15SchedulerConfig", "tensorrt_llm::executor::SchedulerConfig::operator==::other"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor13SerializationE", "tensorrt_llm::executor::Serialization"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization15deserializeBoolERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeBool"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization15deserializeBoolERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeBool::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeCacheStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeCacheState"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeCacheStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeCacheState::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeCommStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeCommState"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeCommStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeCommState::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeContextPhaseParamsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeContextPhaseParams"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeContextPhaseParamsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeContextPhaseParams::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization28deserializeContextPhaseStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeContextPhaseState"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization28deserializeContextPhaseStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeContextPhaseState::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeDebugConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDebugConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeDebugConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDebugConfig::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDecodingConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDecodingConfig::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeDecodingModeERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDecodingMode"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeDecodingModeERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeDecodingMode::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeExecutorConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExecutorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeExecutorConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExecutorConfig::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization40deserializeExtendedRuntimePerfKnobConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExtendedRuntimePerfKnobConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization40deserializeExtendedRuntimePerfKnobConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExtendedRuntimePerfKnobConfig::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeExternalDraftTokensConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExternalDraftTokensConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeExternalDraftTokensConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeExternalDraftTokensConfig::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeInflightBatchingStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeInflightBatchingStats"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeInflightBatchingStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeInflightBatchingStats::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeIterationStats"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeIterationStats"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeIterationStats::buffer"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeIterationStats::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization24deserializeKvCacheConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeKvCacheConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization24deserializeKvCacheConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeKvCacheConfig::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeKvCacheStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeKvCacheStats"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeKvCacheStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeKvCacheStats::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization34deserializeLookaheadDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeLookaheadDecodingConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization34deserializeLookaheadDecodingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeLookaheadDecodingConfig::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeLoraConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeLoraConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeLoraConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeLoraConfig::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeModelTypeERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeModelType"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeModelTypeERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeModelType::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeOrchestratorConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeOrchestratorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeOrchestratorConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeOrchestratorConfig::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeOutputConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeOutputConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeOutputConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeOutputConfig::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeParallelConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeParallelConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeParallelConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeParallelConfig::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializePeftCacheConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializePeftCacheConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializePeftCacheConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializePeftCacheConfig::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializePromptTuningConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializePromptTuningConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializePromptTuningConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializePromptTuningConfig::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization18deserializeRequestERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequest"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization18deserializeRequestERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeRequest::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization19deserializeResponseERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeResponse"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization19deserializeResponseERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeResponse::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeResponsesERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeResponses"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeResponsesERNSt6vectorIcEE", "tensorrt_llm::executor::Serialization::deserializeResponses::buffer"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeResultERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeResult"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeResultERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeResult::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeSamplingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSamplingConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeSamplingConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSamplingConfig::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializeSchedulerConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSchedulerConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializeSchedulerConfigERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSchedulerConfig::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeSocketStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSocketState"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeSocketStateERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeSocketState::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization30deserializeStaticBatchingStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeStaticBatchingStats"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization30deserializeStaticBatchingStatsERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeStaticBatchingStats::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeStringERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeString"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeStringERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeString::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeTensorERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeTensor"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeTensorERNSt7istreamE", "tensorrt_llm::executor::Serialization::deserializeTensor::is"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK10LoraConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11DebugConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12DecodingModeRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12KvCacheStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12OutputConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK13KvCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14DecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ExecutorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStats", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ParallelConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14SamplingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15PeftCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15SchedulerConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK17ContextPhaseStateRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18ContextPhaseParamsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18OrchestratorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18PromptTuningConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK19StaticBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21InflightBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK23LookaheadDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25ExternalDraftTokensConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK29ExtendedRuntimePerfKnobConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6ResultRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6TensorRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK7RequestRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK8ResponseRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10CacheStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache11SocketStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache9CommStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI8ResponseEE", "tensorrt_llm::executor::Serialization::serialize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK10LoraConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::config"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12OutputConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::config"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14SamplingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::config"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18PromptTuningConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::config"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25ExternalDraftTokensConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::config"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18ContextPhaseParamsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::contextPhaseParams"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK17ContextPhaseStateRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::contextPhaseState"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11DebugConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::debugConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14DecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::decodingConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12DecodingModeRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::decodingMode"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ExecutorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::executorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK29ExtendedRuntimePerfKnobConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::extendedRuntimePerfKnobConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21InflightBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::inflightBatchingStats"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStats", "tensorrt_llm::executor::Serialization::serialize::iterStats"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::iterStats"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK13KvCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::kvCacheConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12KvCacheStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::kvCacheStats"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK23LookaheadDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::lookaheadDecodingConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18OrchestratorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::orchestratorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK10LoraConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11DebugConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12DecodingModeRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12KvCacheStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12OutputConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK13KvCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14DecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ExecutorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ParallelConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14SamplingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15PeftCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15SchedulerConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK17ContextPhaseStateRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18ContextPhaseParamsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18OrchestratorConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18PromptTuningConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK19StaticBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21InflightBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK23LookaheadDecodingConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25ExternalDraftTokensConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK29ExtendedRuntimePerfKnobConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6ResultRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6TensorRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK7RequestRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK8ResponseRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10CacheStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache11SocketStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache9CommStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ParallelConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::parallelConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15PeftCacheConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::peftCacheConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK7RequestRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::request"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK8ResponseRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::response"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI8ResponseEE", "tensorrt_llm::executor::Serialization::serialize::responses"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6ResultRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::result"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15SchedulerConfigRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::schedulerConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10CacheStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::state"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache11SocketStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::state"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache9CommStateERNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::state"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK19StaticBatchingStatsRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::staticBatchingStats"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6TensorRNSt7ostreamE", "tensorrt_llm::executor::Serialization::serialize::tensor"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK10LoraConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11DebugConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12DecodingMode", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12KvCacheStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12OutputConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK13KvCacheConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14DecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ExecutorConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14IterationStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ParallelConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14SamplingConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15PeftCacheConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15SchedulerConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK17ContextPhaseState", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18ContextPhaseParams", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18OrchestratorConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18PromptTuningConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK19StaticBatchingStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK21InflightBatchingStats", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK23LookaheadDecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK25ExternalDraftTokensConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Result", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Tensor", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK7Request", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK8Response", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache10CacheStateE", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache11SocketStateE", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache9CommStateE", "tensorrt_llm::executor::Serialization::serializedSize"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK10LoraConfig", "tensorrt_llm::executor::Serialization::serializedSize::config"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12OutputConfig", "tensorrt_llm::executor::Serialization::serializedSize::config"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14SamplingConfig", "tensorrt_llm::executor::Serialization::serializedSize::config"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18PromptTuningConfig", "tensorrt_llm::executor::Serialization::serializedSize::config"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK25ExternalDraftTokensConfig", "tensorrt_llm::executor::Serialization::serializedSize::config"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18ContextPhaseParams", "tensorrt_llm::executor::Serialization::serializedSize::contextPhaseParams"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK17ContextPhaseState", "tensorrt_llm::executor::Serialization::serializedSize::contextPhaseState"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11DebugConfig", "tensorrt_llm::executor::Serialization::serializedSize::debugConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14DecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize::decodingConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12DecodingMode", "tensorrt_llm::executor::Serialization::serializedSize::decodingMode"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ExecutorConfig", "tensorrt_llm::executor::Serialization::serializedSize::executorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK29ExtendedRuntimePerfKnobConfig", "tensorrt_llm::executor::Serialization::serializedSize::extendedRuntimePerfKnobConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK21InflightBatchingStats", "tensorrt_llm::executor::Serialization::serializedSize::inflightBatchingStats"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14IterationStats", "tensorrt_llm::executor::Serialization::serializedSize::iterStats"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK13KvCacheConfig", "tensorrt_llm::executor::Serialization::serializedSize::kvCacheConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12KvCacheStats", "tensorrt_llm::executor::Serialization::serializedSize::kvCacheStats"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK23LookaheadDecodingConfig", "tensorrt_llm::executor::Serialization::serializedSize::lookaheadDecodingConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18OrchestratorConfig", "tensorrt_llm::executor::Serialization::serializedSize::orchestratorConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ParallelConfig", "tensorrt_llm::executor::Serialization::serializedSize::parallelConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15PeftCacheConfig", "tensorrt_llm::executor::Serialization::serializedSize::peftCacheConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK7Request", "tensorrt_llm::executor::Serialization::serializedSize::request"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK8Response", "tensorrt_llm::executor::Serialization::serializedSize::response"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Result", "tensorrt_llm::executor::Serialization::serializedSize::result"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15SchedulerConfig", "tensorrt_llm::executor::Serialization::serializedSize::schedulerConfig"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache10CacheStateE", "tensorrt_llm::executor::Serialization::serializedSize::state"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache11SocketStateE", "tensorrt_llm::executor::Serialization::serializedSize::state"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache9CommStateE", "tensorrt_llm::executor::Serialization::serializedSize::state"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK19StaticBatchingStats", "tensorrt_llm::executor::Serialization::serializedSize::staticBatchingStats"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Tensor", "tensorrt_llm::executor::Serialization::serializedSize::tensor"], [0, 4, 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, 5, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeENSt16initializer_listI9DimType64EE", "tensorrt_llm::executor::Shape::Shape"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEPK9DimType64N4Base9size_typeE", "tensorrt_llm::executor::Shape::Shape"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEv", "tensorrt_llm::executor::Shape::Shape"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEPK9DimType64N4Base9size_typeE", "tensorrt_llm::executor::Shape::Shape::data"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeENSt16initializer_listI9DimType64EE", "tensorrt_llm::executor::Shape::Shape::dims"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEPK9DimType64N4Base9size_typeE", "tensorrt_llm::executor::Shape::Shape::size"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor10SizeType32E", "tensorrt_llm::executor::SizeType32"], [0, 4, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStatsE", "tensorrt_llm::executor::StaticBatchingStats"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats13emptyGenSlotsE", "tensorrt_llm::executor::StaticBatchingStats::emptyGenSlots"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats18numContextRequestsE", "tensorrt_llm::executor::StaticBatchingStats::numContextRequests"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats12numCtxTokensE", "tensorrt_llm::executor::StaticBatchingStats::numCtxTokens"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats12numGenTokensE", "tensorrt_llm::executor::StaticBatchingStats::numGenTokens"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats20numScheduledRequestsE", "tensorrt_llm::executor::StaticBatchingStats::numScheduledRequests"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor9StreamPtrE", "tensorrt_llm::executor::StreamPtr"], [0, 4, 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, 5, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::Tensor::Tensor"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERK6Tensor", "tensorrt_llm::executor::Tensor::Tensor"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERR6Tensor", "tensorrt_llm::executor::Tensor::Tensor"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorEv", "tensorrt_llm::executor::Tensor::Tensor"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERK6Tensor", "tensorrt_llm::executor::Tensor::Tensor::other"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERR6Tensor", "tensorrt_llm::executor::Tensor::Tensor::other"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::Tensor::Tensor::tensor"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor6copyToENSt10shared_ptrI4ImplEE13CudaStreamPtr", "tensorrt_llm::executor::Tensor::copyTo"], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor6copyToENSt10shared_ptrI4ImplEE13CudaStreamPtr", "tensorrt_llm::executor::Tensor::copyTo::stream"], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor6copyToENSt10shared_ptrI4ImplEE13CudaStreamPtr", "tensorrt_llm::executor::Tensor::copyTo::tensor"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToCpuEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToCpu"], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToCpuEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToCpu::stream"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToGpuEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToGpu"], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToGpuEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToGpu::stream"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor13copyToManagedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToManaged"], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor13copyToManagedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToManaged::stream"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor12copyToPinnedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToPinned"], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor12copyToPinnedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToPinned::stream"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor18copyToPooledPinnedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToPooledPinned"], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor18copyToPooledPinnedEN6Tensor13CudaStreamPtrE", "tensorrt_llm::executor::Tensor::copyToPooledPinned::stream"], [0, 5, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3cpuE6Tensor5Shape", "tensorrt_llm::executor::Tensor::cpu"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3cpuE8DataType5Shape", "tensorrt_llm::executor::Tensor::cpu"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3cpuE6Tensor5Shape", "tensorrt_llm::executor::Tensor::cpu::T"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3cpuE8DataType5Shape", "tensorrt_llm::executor::Tensor::cpu::dataType"], [0, 6, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3cpuE6Tensor5Shape", "tensorrt_llm::executor::Tensor::cpu::shape"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3cpuE8DataType5Shape", "tensorrt_llm::executor::Tensor::cpu::shape"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::Tensor::detail::ofITensor"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::Tensor::detail::ofITensor::tensor"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9toITensorERK6Tensor", "tensorrt_llm::executor::Tensor::detail::toITensor"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9toITensorERK6Tensor", "tensorrt_llm::executor::Tensor::detail::toITensor::tensor"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7getDataEv", "tensorrt_llm::executor::Tensor::getData"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor7getDataEv", "tensorrt_llm::executor::Tensor::getData"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor11getDataTypeEv", "tensorrt_llm::executor::Tensor::getDataType"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor13getMemoryTypeEv", "tensorrt_llm::executor::Tensor::getMemoryType"], [0, 5, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor14getRuntimeTypeE8DataTypev", "tensorrt_llm::executor::Tensor::getRuntimeType"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor14getRuntimeTypeE8DataTypev", "tensorrt_llm::executor::Tensor::getRuntimeType::T"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor8getShapeEv", "tensorrt_llm::executor::Tensor::getShape"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor7getSizeEv", "tensorrt_llm::executor::Tensor::getSize"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor6Tensor14getSizeInBytesEv", "tensorrt_llm::executor::Tensor::getSizeInBytes"], [0, 5, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3gpuE6Tensor13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3gpuE8DataType13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3gpuE6Tensor13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::T"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3gpuE8DataType13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::dataType"], [0, 6, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3gpuE6Tensor13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::shape"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3gpuE8DataType13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::shape"], [0, 6, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3gpuE6Tensor13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::stream"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor3gpuE8DataType13CudaStreamPtr5Shape", "tensorrt_llm::executor::Tensor::gpu::stream"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7mTensorE", "tensorrt_llm::executor::Tensor::mTensor"], [0, 5, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor7managedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::managed"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7managedE8DataType5Shape", "tensorrt_llm::executor::Tensor::managed"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor7managedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::managed::T"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7managedE8DataType5Shape", "tensorrt_llm::executor::Tensor::managed::dataType"], [0, 6, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor7managedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::managed::shape"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7managedE8DataType5Shape", "tensorrt_llm::executor::Tensor::managed::shape"], [0, 5, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorP1T5Shape", "tensorrt_llm::executor::Tensor::of"], [0, 5, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorR1T", "tensorrt_llm::executor::Tensor::of"], [0, 5, 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, 6, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorP1T5Shape", "tensorrt_llm::executor::Tensor::of::data"], [0, 6, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorR1T", "tensorrt_llm::executor::Tensor::of::data"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor2ofE8DataTypePv5Shape", "tensorrt_llm::executor::Tensor::of::data"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor2ofE8DataTypePv5Shape", "tensorrt_llm::executor::Tensor::of::dataType"], [0, 6, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorP1T5Shape", "tensorrt_llm::executor::Tensor::of::shape"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor2ofE8DataTypePv5Shape", "tensorrt_llm::executor::Tensor::of::shape"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor6TensorcvbEv", "tensorrt_llm::executor::Tensor::operator bool"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor6TensorneERK6Tensor", "tensorrt_llm::executor::Tensor::operator!="], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor6TensorneERK6Tensor", "tensorrt_llm::executor::Tensor::operator!=::rhs"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6TensoraSERK6Tensor", "tensorrt_llm::executor::Tensor::operator="], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6TensoraSERR6Tensor", "tensorrt_llm::executor::Tensor::operator="], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6TensoraSERK6Tensor", "tensorrt_llm::executor::Tensor::operator=::other"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6TensoraSERR6Tensor", "tensorrt_llm::executor::Tensor::operator=::other"], [0, 5, 1, "_CPPv4NK12tensorrt_llm8executor6TensoreqERK6Tensor", "tensorrt_llm::executor::Tensor::operator=="], [0, 6, 1, "_CPPv4NK12tensorrt_llm8executor6TensoreqERK6Tensor", "tensorrt_llm::executor::Tensor::operator==::rhs"], [0, 5, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor6pinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pinned"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6pinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pinned"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor6pinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pinned::T"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6pinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pinned::dataType"], [0, 6, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor6pinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pinned::shape"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor6pinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pinned::shape"], [0, 5, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor12pooledPinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pooledPinned"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Tensor12pooledPinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pooledPinned"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor12pooledPinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pooledPinned::T"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor12pooledPinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pooledPinned::dataType"], [0, 6, 1, "_CPPv4I0EN12tensorrt_llm8executor6Tensor12pooledPinnedE6Tensor5Shape", "tensorrt_llm::executor::Tensor::pooledPinned::shape"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor12pooledPinnedE8DataType5Shape", "tensorrt_llm::executor::Tensor::pooledPinned::shape"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7setFromERK6Tensor13CudaStreamPtr", "tensorrt_llm::executor::Tensor::setFrom"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7setFromERK6Tensor13CudaStreamPtr", "tensorrt_llm::executor::Tensor::setFrom::other"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7setFromERK6Tensor13CudaStreamPtr", "tensorrt_llm::executor::Tensor::setFrom::stream"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7setZeroE13CudaStreamPtr", "tensorrt_llm::executor::Tensor::setZero"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6Tensor7setZeroE13CudaStreamPtr", "tensorrt_llm::executor::Tensor::setZero::stream"], [0, 5, 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, 4, 1, "_CPPv4I0_bEN12tensorrt_llm8executor10TypeTraitsE", "tensorrt_llm::executor::TypeTraits"], [0, 8, 1, "_CPPv4I0_bEN12tensorrt_llm8executor10TypeTraitsE", "tensorrt_llm::executor::TypeTraits::T"], [0, 4, 1, "_CPPv4I0EN12tensorrt_llm8executor10TypeTraitsIP1TEE", "tensorrt_llm::executor::TypeTraits&lt;T*&gt;"], [0, 8, 1, "_CPPv4I0EN12tensorrt_llm8executor10TypeTraitsIP1TEE", "tensorrt_llm::executor::TypeTraits&lt;T*&gt;::T"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIP1TE5valueE", "tensorrt_llm::executor::TypeTraits&lt;T*&gt;::value"], [0, 4, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsIbEE", "tensorrt_llm::executor::TypeTraits&lt;bool&gt;"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIbE5valueE", "tensorrt_llm::executor::TypeTraits&lt;bool&gt;::value"], [0, 4, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsIfEE", "tensorrt_llm::executor::TypeTraits&lt;float&gt;"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIfE5valueE", "tensorrt_llm::executor::TypeTraits&lt;float&gt;::value"], [0, 4, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsI4halfEE", "tensorrt_llm::executor::TypeTraits&lt;half&gt;"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsI4halfE5valueE", "tensorrt_llm::executor::TypeTraits&lt;half&gt;::value"], [0, 4, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7int32_tEEE", "tensorrt_llm::executor::TypeTraits&lt;std::int32_t&gt;"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7int32_tEE5valueE", "tensorrt_llm::executor::TypeTraits&lt;std::int32_t&gt;::value"], [0, 4, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7int64_tEEE", "tensorrt_llm::executor::TypeTraits&lt;std::int64_t&gt;"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7int64_tEE5valueE", "tensorrt_llm::executor::TypeTraits&lt;std::int64_t&gt;::value"], [0, 4, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt6int8_tEEE", "tensorrt_llm::executor::TypeTraits&lt;std::int8_t&gt;"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt6int8_tEE5valueE", "tensorrt_llm::executor::TypeTraits&lt;std::int8_t&gt;::value"], [0, 4, 1, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7uint8_tEEE", "tensorrt_llm::executor::TypeTraits&lt;std::uint8_t&gt;"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7uint8_tEE5valueE", "tensorrt_llm::executor::TypeTraits&lt;std::uint8_t&gt;::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, 5, 1, "_CPPv4N12tensorrt_llm8executor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::detail::ofITensor"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE", "tensorrt_llm::executor::detail::ofITensor::tensor"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executor6detail9toITensorERK6Tensor", "tensorrt_llm::executor::detail::toITensor"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executor6detail9toITensorERK6Tensor", "tensorrt_llm::executor::detail::toITensor::tensor"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor30kDefaultIterStatsMaxIterationsE", "tensorrt_llm::executor::kDefaultIterStatsMaxIterations"], [0, 7, 1, "_CPPv4N12tensorrt_llm8executor33kDefaultRequestStatsMaxIterationsE", "tensorrt_llm::executor::kDefaultRequestStatsMaxIterations"], [0, 1, 1, "_CPPv4N12tensorrt_llm8executor8kv_cacheE", "tensorrt_llm::executor::kv_cache"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE21ContextChunkingPolicy", "tensorrt_llm::executor::operator&lt;&lt;"], [0, 5, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE23CapacitySchedulerPolicy", "tensorrt_llm::executor::operator&lt;&lt;"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE21ContextChunkingPolicy", "tensorrt_llm::executor::operator&lt;&lt;::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE23CapacitySchedulerPolicy", "tensorrt_llm::executor::operator&lt;&lt;::os"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE21ContextChunkingPolicy", "tensorrt_llm::executor::operator&lt;&lt;::policy"], [0, 6, 1, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE23CapacitySchedulerPolicy", "tensorrt_llm::executor::operator&lt;&lt;::policy"], [0, 5, 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, 4, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffersE", "tensorrt_llm::runtime::AllReduceBuffers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::hiddenSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::manager"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::maxBatchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::maxBeamWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::maxSequenceLength"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::AllReduceBuffers::AllReduceBuffers::worldConfig"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers9TensorPtrE", "tensorrt_llm::runtime::AllReduceBuffers::TensorPtr"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers18mAllReduceCommPtrsE", "tensorrt_llm::runtime::AllReduceBuffers::mAllReduceCommPtrs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers17mIpcMemoryHandlesE", "tensorrt_llm::runtime::AllReduceBuffers::mIpcMemoryHandles"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataTypeE", "tensorrt_llm::runtime::BufferDataType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb", "tensorrt_llm::runtime::BufferDataType::BufferDataType"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb", "tensorrt_llm::runtime::BufferDataType::BufferDataType::_unsigned"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb", "tensorrt_llm::runtime::BufferDataType::BufferDataType::dataType"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb", "tensorrt_llm::runtime::BufferDataType::BufferDataType::pointer"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType11getDataTypeEv", "tensorrt_llm::runtime::BufferDataType::getDataType"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType7getSizeEv", "tensorrt_llm::runtime::BufferDataType::getSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType9isPointerEv", "tensorrt_llm::runtime::BufferDataType::isPointer"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType10isUnsignedEv", "tensorrt_llm::runtime::BufferDataType::isUnsigned"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType15kTrtPointerTypeE", "tensorrt_llm::runtime::BufferDataType::kTrtPointerType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType9mDataTypeE", "tensorrt_llm::runtime::BufferDataType::mDataType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType8mPointerE", "tensorrt_llm::runtime::BufferDataType::mPointer"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType9mUnsignedE", "tensorrt_llm::runtime::BufferDataType::mUnsigned"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataTypecvN8nvinfer18DataTypeEEv", "tensorrt_llm::runtime::BufferDataType::operator nvinfer1::DataType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManagerE", "tensorrt_llm::runtime::BufferManager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager13BufferManagerE13CudaStreamPtrb", "tensorrt_llm::runtime::BufferManager::BufferManager"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager13BufferManagerE13CudaStreamPtrb", "tensorrt_llm::runtime::BufferManager::BufferManager::stream"], [1, 6, 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, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::dims"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::memoryType"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::memoryType"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::size"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::type"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::allocate::type"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copy"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv", "tensorrt_llm::runtime::BufferManager::copy"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType", "tensorrt_llm::runtime::BufferManager::copy"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy::dst"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::dst"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv", "tensorrt_llm::runtime::BufferManager::copy::dst"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::dst"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy::dst"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::dstType"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy::src"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::src"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv", "tensorrt_llm::runtime::BufferManager::copy::src"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::src"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferR7IBuffer", "tensorrt_llm::runtime::BufferManager::copy::src"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copy::srcType"], [1, 5, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10IBufferPtrRKNSt6vectorI1TEE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom"], [1, 5, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom"], [1, 5, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom"], [1, 5, 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, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::dims"], [1, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::dims"], [1, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10IBufferPtrRKNSt6vectorI1TEE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::memoryType"], [1, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::memoryType"], [1, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::memoryType"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::memoryType"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7ITensor10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::memoryType"], [1, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10IBufferPtrRKNSt6vectorI1TEE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::src"], [1, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::src"], [1, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::src"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7IBuffer10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::src"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7ITensor10MemoryType", "tensorrt_llm::runtime::BufferManager::copyFrom::src"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu::dims"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu::size"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu::type"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::cpu::type"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyBufferE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyBuffer"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyBufferE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyBuffer::memoryType"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyBufferE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyBuffer::type"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyTensorE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyTensor"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyTensorE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyTensor::memoryType"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyTensorE10MemoryTypeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::emptyTensor::type"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager9getStreamEv", "tensorrt_llm::runtime::BufferManager::getStream"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu::dims"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu::size"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu::type"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpu::type"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync::dims"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync::size"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync::type"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::gpuSync::type"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE", "tensorrt_llm::runtime::BufferManager::kBYTE_TYPE"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager5mPoolE", "tensorrt_llm::runtime::BufferManager::mPool"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7mStreamE", "tensorrt_llm::runtime::BufferManager::mStream"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager9mTrimPoolE", "tensorrt_llm::runtime::BufferManager::mTrimPool"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed::dims"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed::size"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed::type"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::managed::type"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager14memoryPoolFreeEv", "tensorrt_llm::runtime::BufferManager::memoryPoolFree"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager18memoryPoolReservedEv", "tensorrt_llm::runtime::BufferManager::memoryPoolReserved"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager16memoryPoolTrimToENSt6size_tE", "tensorrt_llm::runtime::BufferManager::memoryPoolTrimTo"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager16memoryPoolTrimToENSt6size_tE", "tensorrt_llm::runtime::BufferManager::memoryPoolTrimTo::size"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager14memoryPoolUsedEv", "tensorrt_llm::runtime::BufferManager::memoryPoolUsed"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned::dims"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned::size"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned::type"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinned::type"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool::dims"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool::size"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolEN8nvinfer14DimsEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool::type"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolENSt6size_tEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::BufferManager::pinnedPool::type"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager6setMemER7IBuffer7int32_t", "tensorrt_llm::runtime::BufferManager::setMem"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager6setMemER7IBuffer7int32_t", "tensorrt_llm::runtime::BufferManager::setMem::buffer"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager6setMemER7IBuffer7int32_t", "tensorrt_llm::runtime::BufferManager::setMem::value"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager7setZeroER7IBuffer", "tensorrt_llm::runtime::BufferManager::setZero"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager7setZeroER7IBuffer", "tensorrt_llm::runtime::BufferManager::setZero::buffer"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13BufferManagerD0Ev", "tensorrt_llm::runtime::BufferManager::~BufferManager"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime11BufferRangeE", "tensorrt_llm::runtime::BufferRange"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime11BufferRange4BaseE", "tensorrt_llm::runtime::BufferRange::Base"], [1, 5, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI1UEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeERK7IBuffer", "tensorrt_llm::runtime::BufferRange::BufferRange"], [1, 5, 1, "_CPPv4I0_NSt11enable_if_tIXntNSt10is_const_vI1UEEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeER7IBuffer", "tensorrt_llm::runtime::BufferRange::BufferRange"], [1, 5, 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, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI1UEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeERK7IBuffer", "tensorrt_llm::runtime::BufferRange::BufferRange::buffer"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tIXntNSt10is_const_vI1UEEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeER7IBuffer", "tensorrt_llm::runtime::BufferRange::BufferRange::buffer"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11BufferRange11BufferRangeEP1T9size_type", "tensorrt_llm::runtime::BufferRange::BufferRange::data"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11BufferRange11BufferRangeEP1T9size_type", "tensorrt_llm::runtime::BufferRange::BufferRange::size"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime11BufferRangeE", "tensorrt_llm::runtime::BufferRange::T"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEventE", "tensorrt_llm::runtime::CudaEvent"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventE7pointerb", "tensorrt_llm::runtime::CudaEvent::CudaEvent"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventEj", "tensorrt_llm::runtime::CudaEvent::CudaEvent"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventE7pointerb", "tensorrt_llm::runtime::CudaEvent::CudaEvent::event"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventEj", "tensorrt_llm::runtime::CudaEvent::CudaEvent::flags"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventE7pointerb", "tensorrt_llm::runtime::CudaEvent::CudaEvent::ownsEvent"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7DeleterE", "tensorrt_llm::runtime::CudaEvent::Deleter"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEb", "tensorrt_llm::runtime::CudaEvent::Deleter::Deleter"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEv", "tensorrt_llm::runtime::CudaEvent::Deleter::Deleter"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEb", "tensorrt_llm::runtime::CudaEvent::Deleter::Deleter::ownsEvent"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter10mOwnsEventE", "tensorrt_llm::runtime::CudaEvent::Deleter::mOwnsEvent"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent7DeleterclE7pointer", "tensorrt_llm::runtime::CudaEvent::Deleter::operator()"], [1, 6, 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, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent3getEv", "tensorrt_llm::runtime::CudaEvent::get"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent6mEventE", "tensorrt_llm::runtime::CudaEvent::mEvent"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7pointerE", "tensorrt_llm::runtime::CudaEvent::pointer"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent11synchronizeEv", "tensorrt_llm::runtime::CudaEvent::synchronize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStreamE", "tensorrt_llm::runtime::CudaStream"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_t", "tensorrt_llm::runtime::CudaStream::CudaStream"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib", "tensorrt_llm::runtime::CudaStream::CudaStream"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamEji", "tensorrt_llm::runtime::CudaStream::CudaStream"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib", "tensorrt_llm::runtime::CudaStream::CudaStream::device"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamEji", "tensorrt_llm::runtime::CudaStream::CudaStream::flags"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib", "tensorrt_llm::runtime::CudaStream::CudaStream::ownsStream"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamEji", "tensorrt_llm::runtime::CudaStream::CudaStream::priority"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_t", "tensorrt_llm::runtime::CudaStream::CudaStream::stream"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib", "tensorrt_llm::runtime::CudaStream::CudaStream::stream"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7DeleterE", "tensorrt_llm::runtime::CudaStream::Deleter"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEb", "tensorrt_llm::runtime::CudaStream::Deleter::Deleter"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEv", "tensorrt_llm::runtime::CudaStream::Deleter::Deleter"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEb", "tensorrt_llm::runtime::CudaStream::Deleter::Deleter::ownsStream"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter11mOwnsStreamE", "tensorrt_llm::runtime::CudaStream::Deleter::mOwnsStream"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream7DeleterclE12cudaStream_t", "tensorrt_llm::runtime::CudaStream::Deleter::operator()"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream7DeleterclE12cudaStream_t", "tensorrt_llm::runtime::CudaStream::Deleter::operator()::stream"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream9StreamPtrE", "tensorrt_llm::runtime::CudaStream::StreamPtr"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream3getEv", "tensorrt_llm::runtime::CudaStream::get"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream9getDeviceEv", "tensorrt_llm::runtime::CudaStream::getDevice"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7mDeviceE", "tensorrt_llm::runtime::CudaStream::mDevice"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7mStreamE", "tensorrt_llm::runtime::CudaStream::mStream"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordEN9CudaEvent7pointerE", "tensorrt_llm::runtime::CudaStream::record"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordERK9CudaEvent", "tensorrt_llm::runtime::CudaStream::record"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordEN9CudaEvent7pointerE", "tensorrt_llm::runtime::CudaStream::record::event"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordERK9CudaEvent", "tensorrt_llm::runtime::CudaStream::record::event"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream11synchronizeEv", "tensorrt_llm::runtime::CudaStream::synchronize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitEN9CudaEvent7pointerE", "tensorrt_llm::runtime::CudaStream::wait"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitERK9CudaEvent", "tensorrt_llm::runtime::CudaStream::wait"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitEN9CudaEvent7pointerE", "tensorrt_llm::runtime::CudaStream::wait::event"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitERK9CudaEvent", "tensorrt_llm::runtime::CudaStream::wait::event"], [1, 4, 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, 4, 1, "_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE", "tensorrt_llm::runtime::DataTypeTraits&lt;kDataType, kUnsigned, true&gt;"], [1, 8, 1, "_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE", "tensorrt_llm::runtime::DataTypeTraits&lt;kDataType, kUnsigned, true&gt;::kDataType"], [1, 8, 1, "_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE", "tensorrt_llm::runtime::DataTypeTraits&lt;kDataType, kUnsigned, true&gt;::kUnsigned"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4nameE", "tensorrt_llm::runtime::DataTypeTraits&lt;kDataType, kUnsigned, true&gt;::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4sizeE", "tensorrt_llm::runtime::DataTypeTraits&lt;kDataType, kUnsigned, true&gt;::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4typeE", "tensorrt_llm::runtime::DataTypeTraits&lt;kDataType, kUnsigned, true&gt;::type"], [1, 4, 1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedEE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kBOOL, kUnsigned&gt;"], [1, 8, 1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedEE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kBOOL, kUnsigned&gt;::kUnsigned"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4nameE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kBOOL, kUnsigned&gt;::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4sizeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kBOOL, kUnsigned&gt;::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4typeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kBOOL, kUnsigned&gt;::type"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEEE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kFLOAT&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4nameE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kFLOAT&gt;::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4sizeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kFLOAT&gt;::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4typeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kFLOAT&gt;::type"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEEE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kHALF&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4nameE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kHALF&gt;::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4sizeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kHALF&gt;::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4typeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kHALF&gt;::type"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEEE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT32, true&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4nameE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT32, true&gt;::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4sizeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT32, true&gt;::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4typeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT32, true&gt;::type"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EEE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT32&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4nameE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT32&gt;::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4sizeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT32&gt;::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4typeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT32&gt;::type"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEEE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT64, true&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4nameE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT64, true&gt;::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4sizeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT64, true&gt;::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4typeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT64, true&gt;::type"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EEE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT64&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4nameE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT64&gt;::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4sizeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT64&gt;::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4typeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT64&gt;::type"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EEE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT8&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4nameE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT8&gt;::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4sizeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT8&gt;::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4typeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kINT8&gt;::type"], [1, 4, 1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedEE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kUINT8, kUnsigned&gt;"], [1, 8, 1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedEE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kUINT8, kUnsigned&gt;::kUnsigned"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4nameE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kUINT8, kUnsigned&gt;::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4sizeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kUINT8, kUnsigned&gt;::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4typeE", "tensorrt_llm::runtime::DataTypeTraits&lt;nvinfer1::DataType::kUINT8, kUnsigned&gt;::type"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInputE", "tensorrt_llm::runtime::DecodingInput"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13DecodingInputE10SizeType3210SizeType3210SizeType3210SizeType3214TensorConstPtr9TensorPtr14TensorConstPtr", "tensorrt_llm::runtime::DecodingInput::DecodingInput"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13DecodingInputE10SizeType3210SizeType3210SizeType3210SizeType3214TensorConstPtr9TensorPtr14TensorConstPtr", "tensorrt_llm::runtime::DecodingInput::DecodingInput::batchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13DecodingInputE10SizeType3210SizeType3210SizeType3210SizeType3214TensorConstPtr9TensorPtr14TensorConstPtr", "tensorrt_llm::runtime::DecodingInput::DecodingInput::batchSlots"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13DecodingInputE10SizeType3210SizeType3210SizeType3210SizeType3214TensorConstPtr9TensorPtr14TensorConstPtr", "tensorrt_llm::runtime::DecodingInput::DecodingInput::endIds"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13DecodingInputE10SizeType3210SizeType3210SizeType3210SizeType3214TensorConstPtr9TensorPtr14TensorConstPtr", "tensorrt_llm::runtime::DecodingInput::DecodingInput::logits"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13DecodingInputE10SizeType3210SizeType3210SizeType3210SizeType3214TensorConstPtr9TensorPtr14TensorConstPtr", "tensorrt_llm::runtime::DecodingInput::DecodingInput::maxAttentionWindow"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13DecodingInputE10SizeType3210SizeType3210SizeType3210SizeType3214TensorConstPtr9TensorPtr14TensorConstPtr", "tensorrt_llm::runtime::DecodingInput::DecodingInput::maxLength"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13DecodingInputE10SizeType3210SizeType3210SizeType3210SizeType3214TensorConstPtr9TensorPtr14TensorConstPtr", "tensorrt_llm::runtime::DecodingInput::DecodingInput::sinkTokenLength"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15bestPathIndicesE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::bestPathIndices"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15bestPathLengthsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::bestPathLengths"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs16lastDraftIndicesE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::lastDraftIndices"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15lastDraftTokensE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::lastDraftTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs21lastGenerationLengthsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::lastGenerationLengths"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs19lastPositionIdsBaseE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::lastPositionIdsBase"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs5masksE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::masks"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs18maxGenLengthDeviceE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::maxGenLengthDevice"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs16nextDraftIndicesE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::nextDraftIndices"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs14nextDraftProbsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::nextDraftProbs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15nextDraftTokensE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::nextDraftTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs14nextFlatTokensE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::nextFlatTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs21nextGenerationLengthsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::nextGenerationLengths"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs17packedPositionIdsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::packedPositionIds"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs8seqSlotsE", "tensorrt_llm::runtime::DecodingInput::ExplicitDraftTokensInputs::seqSlots"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15LookaheadInputsE", "tensorrt_llm::runtime::DecodingInput::LookaheadInputs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15LookaheadInputs13tokensPerStepE", "tensorrt_llm::runtime::DecodingInput::LookaheadInputs::tokensPerStep"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputsE", "tensorrt_llm::runtime::DecodingInput::MedusaInputs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs22medusaCurTokensPerStepE", "tensorrt_llm::runtime::DecodingInput::MedusaInputs::medusaCurTokensPerStep"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs12medusaLogitsE", "tensorrt_llm::runtime::DecodingInput::MedusaInputs::medusaLogits"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs11medusaPathsE", "tensorrt_llm::runtime::DecodingInput::MedusaInputs::medusaPaths"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs25medusaTargetTokensPerStepE", "tensorrt_llm::runtime::DecodingInput::MedusaInputs::medusaTargetTokensPerStep"], [1, 7, 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, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12badWordsLensE", "tensorrt_llm::runtime::DecodingInput::badWordsLens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13badWordsListsE", "tensorrt_llm::runtime::DecodingInput::badWordsLists"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12badWordsPtrsE", "tensorrt_llm::runtime::DecodingInput::badWordsPtrs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9batchSizeE", "tensorrt_llm::runtime::DecodingInput::batchSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput10batchSlotsE", "tensorrt_llm::runtime::DecodingInput::batchSlots"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput16cacheIndirectionE", "tensorrt_llm::runtime::DecodingInput::cacheIndirection"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13embeddingBiasE", "tensorrt_llm::runtime::DecodingInput::embeddingBias"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput6endIdsE", "tensorrt_llm::runtime::DecodingInput::endIds"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25explicitDraftTokensInputsE", "tensorrt_llm::runtime::DecodingInput::explicitDraftTokensInputs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13finishReasonsE", "tensorrt_llm::runtime::DecodingInput::finishReasons"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput7lengthsE", "tensorrt_llm::runtime::DecodingInput::lengths"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput6logitsE", "tensorrt_llm::runtime::DecodingInput::logits"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15lookaheadInputsE", "tensorrt_llm::runtime::DecodingInput::lookaheadInputs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput18maxAttentionWindowE", "tensorrt_llm::runtime::DecodingInput::maxAttentionWindow"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput14maxBadWordsLenE", "tensorrt_llm::runtime::DecodingInput::maxBadWordsLen"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9maxLengthE", "tensorrt_llm::runtime::DecodingInput::maxLength"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15maxStopWordsLenE", "tensorrt_llm::runtime::DecodingInput::maxStopWordsLen"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12medusaInputsE", "tensorrt_llm::runtime::DecodingInput::medusaInputs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput17noRepeatNgramSizeE", "tensorrt_llm::runtime::DecodingInput::noRepeatNgramSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput19sequenceLimitLengthE", "tensorrt_llm::runtime::DecodingInput::sequenceLimitLength"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15sinkTokenLengthE", "tensorrt_llm::runtime::DecodingInput::sinkTokenLength"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput4stepE", "tensorrt_llm::runtime::DecodingInput::step"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13stopWordsLensE", "tensorrt_llm::runtime::DecodingInput::stopWordsLens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput14stopWordsListsE", "tensorrt_llm::runtime::DecodingInput::stopWordsLists"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13stopWordsPtrsE", "tensorrt_llm::runtime::DecodingInput::stopWordsPtrs"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutputE", "tensorrt_llm::runtime::DecodingOutput"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypothesesE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses10batchDonesE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::batchDones"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses14cumLogProbsCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::cumLogProbsCBA"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5emptyER13BufferManager", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::empty"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5emptyER13BufferManager", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::empty::manager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses4initER13BufferManager11TokenIdType", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::init"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses4initER13BufferManager11TokenIdType", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::init::endId"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses4initER13BufferManager11TokenIdType", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::init::manager"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses11logProbsCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::logProbsCBA"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses18minNormedScoresCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::minNormedScoresCBA"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses15normedScoresCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::normedScoresCBA"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses11numBeamsCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::numBeamsCBA"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses12outputIdsCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::outputIdsCBA"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7releaseEv", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::release"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::reshape"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::reshape::batchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::reshape::beamWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::reshape::maxSequenceLength"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses18sequenceLengthsCBAE", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::sequenceLengthsCBA"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5sliceE10SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::slice"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5sliceE10SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::slice::batchIndex"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5sliceE10SizeType3210SizeType32", "tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::slice::size"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14DecodingOutputE9TensorPtr9TensorPtr", "tensorrt_llm::runtime::DecodingOutput::DecodingOutput"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14DecodingOutputE9TensorPtr9TensorPtr", "tensorrt_llm::runtime::DecodingOutput::DecodingOutput::gatheredIds"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14DecodingOutputE9TensorPtr9TensorPtr", "tensorrt_llm::runtime::DecodingOutput::DecodingOutput::ids"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputsE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs21acceptedLengthsCumSumE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::acceptedLengthsCumSum"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs17acceptedTokensLenE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::acceptedTokensLen"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs15nextDraftTokensE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::nextDraftTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs18nextDraftTokensLenE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::nextDraftTokensLen"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs12pathsOffsetsE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::pathsOffsets"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs18prevDraftTokensLenE", "tensorrt_llm::runtime::DecodingOutput::SpeculativeDecodingOutputs::prevDraftTokensLen"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE", "tensorrt_llm::runtime::DecodingOutput::TensorPtr"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14beamHypothesesE", "tensorrt_llm::runtime::DecodingOutput::beamHypotheses"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput16cacheIndirectionE", "tensorrt_llm::runtime::DecodingOutput::cacheIndirection"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11cumLogProbsE", "tensorrt_llm::runtime::DecodingOutput::cumLogProbs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26explicitDraftTokensBuffersE", "tensorrt_llm::runtime::DecodingOutput::explicitDraftTokensBuffers"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput13finishReasonsE", "tensorrt_llm::runtime::DecodingOutput::finishReasons"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11finishedSumE", "tensorrt_llm::runtime::DecodingOutput::finishedSum"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11gatheredIdsE", "tensorrt_llm::runtime::DecodingOutput::gatheredIds"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput3idsE", "tensorrt_llm::runtime::DecodingOutput::ids"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput17kNegativeInfinityE", "tensorrt_llm::runtime::DecodingOutput::kNegativeInfinity"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput7lengthsE", "tensorrt_llm::runtime::DecodingOutput::lengths"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput8logProbsE", "tensorrt_llm::runtime::DecodingOutput::logProbs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput16lookaheadOutputsE", "tensorrt_llm::runtime::DecodingOutput::lookaheadOutputs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9newTokensE", "tensorrt_llm::runtime::DecodingOutput::newTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14newTokensStepsE", "tensorrt_llm::runtime::DecodingOutput::newTokensSteps"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput12newTokensVecE", "tensorrt_llm::runtime::DecodingOutput::newTokensVec"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9parentIdsE", "tensorrt_llm::runtime::DecodingOutput::parentIds"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26speculativeDecodingOutputsE", "tensorrt_llm::runtime::DecodingOutput::speculativeDecodingOutputs"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffersE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers9BufferPtrE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::BufferPtr"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineInputs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputs15positionOffsetsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineInputs::positionOffsets"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputs18requestTypesDeviceE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineInputs::requestTypesDevice"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15bestPathIndicesE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::bestPathIndices"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15bestPathLengthsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::bestPathLengths"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs5masksE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::masks"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs11maxGenTokenE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::maxGenToken"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs16nextDraftIndicesE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextDraftIndices"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs14nextDraftProbsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextDraftProbs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15nextDraftTokensE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextDraftTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs14nextFlatTokensE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextFlatTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs21nextGenerationLengthsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextGenerationLengths"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs19nextPositionOffsetsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::nextPositionOffsets"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs17packedPositionIdsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::packedPositionIds"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs13totalGenTokenE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::EngineOutputs::totalGenToken"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers::decodingConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers::manager"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers::maxBatchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers::maxBeamWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers::modelConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers::runtime"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ExplicitDraftTokensBuffers::worldConfig"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7ITensorE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::ITensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6InputsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::create"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::create::maxNumSequences"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::create::modelConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::create::runtime"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::create::worldConfig"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs12draftIndicesE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::draftIndices"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs10draftProbsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::draftProbs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11draftTokensE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::draftTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs17generationLengthsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::generationLengths"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs21generationLengthsHostE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::generationLengthsHost"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs16maxGenLengthHostE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::maxGenLengthHost"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11packedMasksE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::packedMasks"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11positionIdsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::positionIds"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs15positionIdsBaseE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::positionIdsBase"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs16randomDataSampleE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::randomDataSample"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs20randomDataValidationE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::randomDataValidation"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs12temperaturesE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::Inputs::temperatures"], [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, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers23cumSumGenerationLengthsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::cumSumGenerationLengths"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12engineInputsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::engineInputs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13engineOutputsE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::engineOutputs"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::insertInputTensors"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::insertInputTensors::inputBuffers"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::insertInputTensors::outputBuffers"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::insertInputTensors::worldConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::reshape"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::reshape::modelConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::reshape::numCtxSequences"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::reshape::numGenSequences"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers15scanTempStorageE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::scanTempStorage"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers20scanTempStorageBytesE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::scanTempStorageBytes"], [1, 5, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs"], [1, 8, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::T"], [1, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::contextPositionIds"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::contextPositionIds"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::decoderBuffers"], [1, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::draftBuffers"], [1, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::explicitDraftTokensModule"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::modelConfig"], [1, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::numCtxSequences"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::numCtxSequences"], [1, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::numGenSequences"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::numGenSequences"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::requestTypes"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::runtime"], [1, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::seqSlots"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::seqSlots"], [1, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::stream"], [1, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::vocabSizePadded"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::ExplicitDraftTokensBuffers::setFromInputs::worldConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime15GenerationInputE", "tensorrt_llm::runtime::GenerationInput"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime15GenerationInput4BaseE", "tensorrt_llm::runtime::GenerationInput::Base"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime15GenerationInput15GenerationInputEK10SizeType32K10SizeType329TensorPtr9TensorPtrb", "tensorrt_llm::runtime::GenerationInput::GenerationInput"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime15GenerationInput15GenerationInputEK10SizeType32K10SizeType329TensorPtr9TensorPtrb", "tensorrt_llm::runtime::GenerationInput::GenerationInput::endId"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime15GenerationInput15GenerationInputEK10SizeType32K10SizeType329TensorPtr9TensorPtrb", "tensorrt_llm::runtime::GenerationInput::GenerationInput::ids"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime15GenerationInput15GenerationInputEK10SizeType32K10SizeType329TensorPtr9TensorPtrb", "tensorrt_llm::runtime::GenerationInput::GenerationInput::lengths"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime15GenerationInput15GenerationInputEK10SizeType32K10SizeType329TensorPtr9TensorPtrb", "tensorrt_llm::runtime::GenerationInput::GenerationInput::packed"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime15GenerationInput15GenerationInputEK10SizeType32K10SizeType329TensorPtr9TensorPtrb", "tensorrt_llm::runtime::GenerationInput::GenerationInput::padId"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime15GenerationInput9TensorPtrE", "tensorrt_llm::runtime::GenerationInput::TensorPtr"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime16GenerationOutputE", "tensorrt_llm::runtime::GenerationOutput"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime16GenerationOutput4BaseE", "tensorrt_llm::runtime::GenerationOutput::Base"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime16GenerationOutput16GenerationOutputE9TensorPtr9TensorPtr", "tensorrt_llm::runtime::GenerationOutput::GenerationOutput"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime16GenerationOutput16GenerationOutputE9TensorPtr9TensorPtr", "tensorrt_llm::runtime::GenerationOutput::GenerationOutput::ids"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime16GenerationOutput16GenerationOutputE9TensorPtr9TensorPtr", "tensorrt_llm::runtime::GenerationOutput::GenerationOutput::lengths"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime16GenerationOutput9TensorPtrE", "tensorrt_llm::runtime::GenerationOutput::TensorPtr"], [1, 4, 1, "_CPPv4I00EN12tensorrt_llm7runtime22GenericGenerationInputE", "tensorrt_llm::runtime::GenericGenerationInput"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput22GenericGenerationInputEK10SizeType32K10SizeType329TensorPtr9TensorPtrb", "tensorrt_llm::runtime::GenericGenerationInput::GenericGenerationInput"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput22GenericGenerationInputEK10SizeType32K10SizeType329TensorPtr9TensorPtrb", "tensorrt_llm::runtime::GenericGenerationInput::GenericGenerationInput::endId"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput22GenericGenerationInputEK10SizeType32K10SizeType329TensorPtr9TensorPtrb", "tensorrt_llm::runtime::GenericGenerationInput::GenericGenerationInput::ids"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput22GenericGenerationInputEK10SizeType32K10SizeType329TensorPtr9TensorPtrb", "tensorrt_llm::runtime::GenericGenerationInput::GenericGenerationInput::lengths"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput22GenericGenerationInputEK10SizeType32K10SizeType329TensorPtr9TensorPtrb", "tensorrt_llm::runtime::GenericGenerationInput::GenericGenerationInput::packed"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput22GenericGenerationInputEK10SizeType32K10SizeType329TensorPtr9TensorPtrb", "tensorrt_llm::runtime::GenericGenerationInput::GenericGenerationInput::padId"], [1, 8, 1, "_CPPv4I00EN12tensorrt_llm7runtime22GenericGenerationInputE", "tensorrt_llm::runtime::GenericGenerationInput::PromptTuningParams"], [1, 8, 1, "_CPPv4I00EN12tensorrt_llm7runtime22GenericGenerationInputE", "tensorrt_llm::runtime::GenericGenerationInput::TTensor"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput9TensorPtrE", "tensorrt_llm::runtime::GenericGenerationInput::TensorPtr"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput12badWordsListE", "tensorrt_llm::runtime::GenericGenerationInput::badWordsList"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput13embeddingBiasE", "tensorrt_llm::runtime::GenericGenerationInput::embeddingBias"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput5endIdE", "tensorrt_llm::runtime::GenericGenerationInput::endId"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput3idsE", "tensorrt_llm::runtime::GenericGenerationInput::ids"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput7lengthsE", "tensorrt_llm::runtime::GenericGenerationInput::lengths"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput12maxNewTokensE", "tensorrt_llm::runtime::GenericGenerationInput::maxNewTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput6packedE", "tensorrt_llm::runtime::GenericGenerationInput::packed"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput5padIdE", "tensorrt_llm::runtime::GenericGenerationInput::padId"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput18promptTuningParamsE", "tensorrt_llm::runtime::GenericGenerationInput::promptTuningParams"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput13stopWordsListE", "tensorrt_llm::runtime::GenericGenerationInput::stopWordsList"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime23GenericGenerationOutputE", "tensorrt_llm::runtime::GenericGenerationOutput"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput8CallbackE", "tensorrt_llm::runtime::GenericGenerationOutput::Callback"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput23GenericGenerationOutputE9TensorPtr9TensorPtr", "tensorrt_llm::runtime::GenericGenerationOutput::GenericGenerationOutput"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput23GenericGenerationOutputE9TensorPtr9TensorPtr", "tensorrt_llm::runtime::GenericGenerationOutput::GenericGenerationOutput::ids"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput23GenericGenerationOutputE9TensorPtr9TensorPtr", "tensorrt_llm::runtime::GenericGenerationOutput::GenericGenerationOutput::lengths"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime23GenericGenerationOutputE", "tensorrt_llm::runtime::GenericGenerationOutput::TTensor"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput9TensorPtrE", "tensorrt_llm::runtime::GenericGenerationOutput::TensorPtr"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput13contextLogitsE", "tensorrt_llm::runtime::GenericGenerationOutput::contextLogits"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput11cumLogProbsE", "tensorrt_llm::runtime::GenericGenerationOutput::cumLogProbs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput16generationLogitsE", "tensorrt_llm::runtime::GenericGenerationOutput::generationLogits"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput3idsE", "tensorrt_llm::runtime::GenericGenerationOutput::ids"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput7lengthsE", "tensorrt_llm::runtime::GenericGenerationOutput::lengths"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput8logProbsE", "tensorrt_llm::runtime::GenericGenerationOutput::logProbs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput16onTokenGeneratedE", "tensorrt_llm::runtime::GenericGenerationOutput::onTokenGenerated"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime25GenericPromptTuningParamsE", "tensorrt_llm::runtime::GenericPromptTuningParams"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::GenericPromptTuningParams::GenericPromptTuningParams"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::GenericPromptTuningParams::GenericPromptTuningParams::embeddingTable"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::GenericPromptTuningParams::GenericPromptTuningParams::tasks"], [1, 6, 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, 7, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams14embeddingTableE", "tensorrt_llm::runtime::GenericPromptTuningParams::embeddingTable"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams19promptTuningEnabledE", "tensorrt_llm::runtime::GenericPromptTuningParams::promptTuningEnabled"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams5tasksE", "tensorrt_llm::runtime::GenericPromptTuningParams::tasks"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9vocabSizeE", "tensorrt_llm::runtime::GenericPromptTuningParams::vocabSize"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime10GptDecoderE", "tensorrt_llm::runtime::GptDecoder"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13CudaStreamPtrE", "tensorrt_llm::runtime::GptDecoder::CudaStreamPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::maxBatchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::maxBeamWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::maxSequenceLength"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::mode"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::speculativeDecodingModule"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::stream"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::GptDecoder::GptDecoder::vocabSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_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, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardAsync"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardAsync::input"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardAsync::output"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardSync"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardSync::input"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::GptDecoder::forwardSync::output"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10gatherTreeERK14DecodingOutputRK13DecodingInputRK13BufferManagerNSt8optionalINSt17reference_wrapperIK14SamplingConfigEEEE", "tensorrt_llm::runtime::GptDecoder::gatherTree"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10gatherTreeERK14DecodingOutputRK13DecodingInputRK13BufferManagerNSt8optionalINSt17reference_wrapperIK14SamplingConfigEEEE", "tensorrt_llm::runtime::GptDecoder::gatherTree::decodingInput"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10gatherTreeERK14DecodingOutputRK13DecodingInputRK13BufferManagerNSt8optionalINSt17reference_wrapperIK14SamplingConfigEEEE", "tensorrt_llm::runtime::GptDecoder::gatherTree::decodingOutput"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10gatherTreeERK14DecodingOutputRK13DecodingInputRK13BufferManagerNSt8optionalINSt17reference_wrapperIK14SamplingConfigEEEE", "tensorrt_llm::runtime::GptDecoder::gatherTree::manager"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10gatherTreeERK14DecodingOutputRK13DecodingInputRK13BufferManagerNSt8optionalINSt17reference_wrapperIK14SamplingConfigEEEE", "tensorrt_llm::runtime::GptDecoder::gatherTree::samplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder17getSamplingConfigEv", "tensorrt_llm::runtime::GptDecoder::getSamplingConfig"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder23mDecodingLayerWorkspaceE", "tensorrt_llm::runtime::GptDecoder::mDecodingLayerWorkspace"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13mDecodingModeE", "tensorrt_llm::runtime::GptDecoder::mDecodingMode"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder19mDynamicDecodeLayerE", "tensorrt_llm::runtime::GptDecoder::mDynamicDecodeLayer"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder14mLogProbsTiledE", "tensorrt_llm::runtime::GptDecoder::mLogProbsTiled"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder8mManagerE", "tensorrt_llm::runtime::GptDecoder::mManager"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13mMaxBatchSizeE", "tensorrt_llm::runtime::GptDecoder::mMaxBatchSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder15mSamplingConfigE", "tensorrt_llm::runtime::GptDecoder::mSamplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEERKNSt8optionalIKNSt6vectorIN13decoder_batch7RequestEEEEE", "tensorrt_llm::runtime::GptDecoder::setup"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEERKNSt8optionalIKNSt6vectorIN13decoder_batch7RequestEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::batchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEERKNSt8optionalIKNSt6vectorIN13decoder_batch7RequestEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::batchSlots"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEERKNSt8optionalIKNSt6vectorIN13decoder_batch7RequestEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::output"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEERKNSt8optionalIKNSt6vectorIN13decoder_batch7RequestEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::requests"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEERKNSt8optionalIKNSt6vectorIN13decoder_batch7RequestEEEEE", "tensorrt_llm::runtime::GptDecoder::setup::samplingConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatchedE", "tensorrt_llm::runtime::GptDecoderBatched"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13CudaStreamPtrE", "tensorrt_llm::runtime::GptDecoderBatched::CudaStreamPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16DecodingInputPtrE", "tensorrt_llm::runtime::GptDecoderBatched::DecodingInputPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched17DecodingOutputPtrE", "tensorrt_llm::runtime::GptDecoderBatched::DecodingOutputPtr"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11ForwardTypeE", "tensorrt_llm::runtime::GptDecoderBatched::ForwardType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11ForwardType6kASYNCE", "tensorrt_llm::runtime::GptDecoderBatched::ForwardType::kASYNC"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11ForwardType5kSYNCE", "tensorrt_llm::runtime::GptDecoderBatched::ForwardType::kSYNC"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched17GptDecoderBatchedENSt6size_tENSt6size_tE13CudaStreamPtrRK23SpeculativeDecodingModeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::GptDecoderBatched::GptDecoderBatched"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched17GptDecoderBatchedENSt6size_tENSt6size_tE13CudaStreamPtrRK23SpeculativeDecodingModeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::GptDecoderBatched::GptDecoderBatched::dtype"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched17GptDecoderBatchedENSt6size_tENSt6size_tE13CudaStreamPtrRK23SpeculativeDecodingModeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::GptDecoderBatched::GptDecoderBatched::speculativeDecodingMode"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched17GptDecoderBatchedENSt6size_tENSt6size_tE13CudaStreamPtrRK23SpeculativeDecodingModeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::GptDecoderBatched::GptDecoderBatched::stream"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched17GptDecoderBatchedENSt6size_tENSt6size_tE13CudaStreamPtrRK23SpeculativeDecodingModeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::GptDecoderBatched::GptDecoderBatched::vocabSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched17GptDecoderBatchedENSt6size_tENSt6size_tE13CudaStreamPtrRK23SpeculativeDecodingModeN8nvinfer18DataTypeE", "tensorrt_llm::runtime::GptDecoderBatched::GptDecoderBatched::vocabSizePadded"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13GptDecoderPtrE", "tensorrt_llm::runtime::GptDecoderBatched::GptDecoderPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14SharedConstPtrE", "tensorrt_llm::runtime::GptDecoderBatched::SharedConstPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched9TensorPtrE", "tensorrt_llm::runtime::GptDecoderBatched::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched34allocateSpeculativeDecodingBuffersEv", "tensorrt_llm::runtime::GptDecoderBatched::allocateSpeculativeDecodingBuffers"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::finalize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeERK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::finalize"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::finalize::batchSlot"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::finalize::samplingConfig"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeERK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::finalize::samplingConfig"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::finalize::streaming"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardAsync"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12forwardAsyncERN7decoder6OutputERKN7decoder5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardAsync"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardAsync::input"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12forwardAsyncERN7decoder6OutputERKN7decoder5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardAsync::input"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardAsync::output"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12forwardAsyncERN7decoder6OutputERKN7decoder5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardAsync::output"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14forwardDecoderE10SizeType32RN13decoder_batch6OutputERKN13decoder_batch5InputE11ForwardType", "tensorrt_llm::runtime::GptDecoderBatched::forwardDecoder"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14forwardDecoderE10SizeType32RN13decoder_batch6OutputERKN13decoder_batch5InputE11ForwardType", "tensorrt_llm::runtime::GptDecoderBatched::forwardDecoder::forwardType"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14forwardDecoderE10SizeType32RN13decoder_batch6OutputERKN13decoder_batch5InputE11ForwardType", "tensorrt_llm::runtime::GptDecoderBatched::forwardDecoder::input"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14forwardDecoderE10SizeType32RN13decoder_batch6OutputERKN13decoder_batch5InputE11ForwardType", "tensorrt_llm::runtime::GptDecoderBatched::forwardDecoder::output"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14forwardDecoderE10SizeType32RN13decoder_batch6OutputERKN13decoder_batch5InputE11ForwardType", "tensorrt_llm::runtime::GptDecoderBatched::forwardDecoder::step"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15forwardDispatchERN13decoder_batch6OutputERKN13decoder_batch5InputE11ForwardType", "tensorrt_llm::runtime::GptDecoderBatched::forwardDispatch"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15forwardDispatchERN13decoder_batch6OutputERKN13decoder_batch5InputE11ForwardType", "tensorrt_llm::runtime::GptDecoderBatched::forwardDispatch::forwardType"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15forwardDispatchERN13decoder_batch6OutputERKN13decoder_batch5InputE11ForwardType", "tensorrt_llm::runtime::GptDecoderBatched::forwardDispatch::input"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15forwardDispatchERN13decoder_batch6OutputERKN13decoder_batch5InputE11ForwardType", "tensorrt_llm::runtime::GptDecoderBatched::forwardDispatch::output"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11forwardSyncERKN13decoder_batch5TokenE", "tensorrt_llm::runtime::GptDecoderBatched::forwardSync"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11forwardSyncERKN13decoder_batch5TokenERN13decoder_batch6OutputERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardSync"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11forwardSyncEv", "tensorrt_llm::runtime::GptDecoderBatched::forwardSync"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11forwardSyncERKN13decoder_batch5TokenERN13decoder_batch6OutputERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardSync::input"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11forwardSyncERKN13decoder_batch5TokenERN13decoder_batch6OutputERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardSync::output"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11forwardSyncERKN13decoder_batch5TokenE", "tensorrt_llm::runtime::GptDecoderBatched::forwardSync::token"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11forwardSyncERKN13decoder_batch5TokenERN13decoder_batch6OutputERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::forwardSync::token"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched24getAcceptedLengthsCumSumEv", "tensorrt_llm::runtime::GptDecoderBatched::getAcceptedLengthsCumSum"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched22getAcceptedPackedPathsEv", "tensorrt_llm::runtime::GptDecoderBatched::getAcceptedPackedPaths"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched15getAllNewTokensEv", "tensorrt_llm::runtime::GptDecoderBatched::getAllNewTokens"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched14getCumLogProbsE10SizeType32", "tensorrt_llm::runtime::GptDecoderBatched::getCumLogProbs"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched14getCumLogProbsEv", "tensorrt_llm::runtime::GptDecoderBatched::getCumLogProbs"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched14getCumLogProbsE10SizeType32", "tensorrt_llm::runtime::GptDecoderBatched::getCumLogProbs::batchIdx"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched15getDecodingModeEv", "tensorrt_llm::runtime::GptDecoderBatched::getDecodingMode"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched16getFinishReasonsEv", "tensorrt_llm::runtime::GptDecoderBatched::getFinishReasons"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched11getFinishedEv", "tensorrt_llm::runtime::GptDecoderBatched::getFinished"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched14getGatheredIdsE10SizeType32", "tensorrt_llm::runtime::GptDecoderBatched::getGatheredIds"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched14getGatheredIdsEv", "tensorrt_llm::runtime::GptDecoderBatched::getGatheredIds"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched14getGatheredIdsE10SizeType32", "tensorrt_llm::runtime::GptDecoderBatched::getGatheredIds::batchIdx"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched6getIdsE10SizeType32", "tensorrt_llm::runtime::GptDecoderBatched::getIds"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched6getIdsEv", "tensorrt_llm::runtime::GptDecoderBatched::getIds"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched6getIdsE10SizeType32", "tensorrt_llm::runtime::GptDecoderBatched::getIds::batchIdx"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched11getLogProbsE10SizeType32", "tensorrt_llm::runtime::GptDecoderBatched::getLogProbs"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched11getLogProbsEv", "tensorrt_llm::runtime::GptDecoderBatched::getLogProbs"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched11getLogProbsE10SizeType32", "tensorrt_llm::runtime::GptDecoderBatched::getLogProbs::batchIdx"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched13getNbFinishedEv", "tensorrt_llm::runtime::GptDecoderBatched::getNbFinished"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched10getNbStepsEv", "tensorrt_llm::runtime::GptDecoderBatched::getNbSteps"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched12getNewTokensE10SizeType32", "tensorrt_llm::runtime::GptDecoderBatched::getNewTokens"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched12getNewTokensE10SizeType32", "tensorrt_llm::runtime::GptDecoderBatched::getNewTokens::iter"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched18getNextDraftTokensEv", "tensorrt_llm::runtime::GptDecoderBatched::getNextDraftTokens"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched25getNextDraftTokensLengthsEv", "tensorrt_llm::runtime::GptDecoderBatched::getNextDraftTokensLengths"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched12getParentIdsEv", "tensorrt_llm::runtime::GptDecoderBatched::getParentIds"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched25getPrevDraftTokensLengthsEv", "tensorrt_llm::runtime::GptDecoderBatched::getPrevDraftTokensLengths"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15mAcceptByLogitsE", "tensorrt_llm::runtime::GptDecoderBatched::mAcceptByLogits"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16mActualBatchSizeE", "tensorrt_llm::runtime::GptDecoderBatched::mActualBatchSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched23mBatchSlotsAcceptLogitsE", "tensorrt_llm::runtime::GptDecoderBatched::mBatchSlotsAcceptLogits"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched23mBatchSlotsAcceptTokensE", "tensorrt_llm::runtime::GptDecoderBatched::mBatchSlotsAcceptTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched18mBatchSlotsDecoderE", "tensorrt_llm::runtime::GptDecoderBatched::mBatchSlotsDecoder"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16mBatchSlotsSetupE", "tensorrt_llm::runtime::GptDecoderBatched::mBatchSlotsSetup"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11mBeamWidthsE", "tensorrt_llm::runtime::GptDecoderBatched::mBeamWidths"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mBufferManagerE", "tensorrt_llm::runtime::GptDecoderBatched::mBufferManager"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15mCumLogProbsTmpE", "tensorrt_llm::runtime::GptDecoderBatched::mCumLogProbsTmp"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13mCurandStatesE", "tensorrt_llm::runtime::GptDecoderBatched::mCurandStates"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched8mDecoderE", "tensorrt_llm::runtime::GptDecoderBatched::mDecoder"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mDecoderStreamE", "tensorrt_llm::runtime::GptDecoderBatched::mDecoderStream"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13mDecodingModeE", "tensorrt_llm::runtime::GptDecoderBatched::mDecodingMode"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12mDraftLogitsE", "tensorrt_llm::runtime::GptDecoderBatched::mDraftLogits"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11mDraftProbsE", "tensorrt_llm::runtime::GptDecoderBatched::mDraftProbs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mDraftTokenIdsE", "tensorrt_llm::runtime::GptDecoderBatched::mDraftTokenIds"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched9mFinishedE", "tensorrt_llm::runtime::GptDecoderBatched::mFinished"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mFinishedStepsE", "tensorrt_llm::runtime::GptDecoderBatched::mFinishedSteps"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12mFinishedSumE", "tensorrt_llm::runtime::GptDecoderBatched::mFinishedSum"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13mForwardEventE", "tensorrt_llm::runtime::GptDecoderBatched::mForwardEvent"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13mForwardTokenE", "tensorrt_llm::runtime::GptDecoderBatched::mForwardToken"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched19mJointDecodingInputE", "tensorrt_llm::runtime::GptDecoderBatched::mJointDecodingInput"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched20mJointDecodingOutputE", "tensorrt_llm::runtime::GptDecoderBatched::mJointDecodingOutput"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched19mMaxAttentionWindowE", "tensorrt_llm::runtime::GptDecoderBatched::mMaxAttentionWindow"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched25mMaxDecodingDecoderTokensE", "tensorrt_llm::runtime::GptDecoderBatched::mMaxDecodingDecoderTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched24mMaxDecodingEngineTokensE", "tensorrt_llm::runtime::GptDecoderBatched::mMaxDecodingEngineTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13mMaxNewTokensE", "tensorrt_llm::runtime::GptDecoderBatched::mMaxNewTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched18mMaxSequenceLengthE", "tensorrt_llm::runtime::GptDecoderBatched::mMaxSequenceLength"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched8mNbStepsE", "tensorrt_llm::runtime::GptDecoderBatched::mNbSteps"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched24mNumDecodingEngineTokensE", "tensorrt_llm::runtime::GptDecoderBatched::mNumDecodingEngineTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15mNumDraftTokensE", "tensorrt_llm::runtime::GptDecoderBatched::mNumDraftTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched7mNumSMsE", "tensorrt_llm::runtime::GptDecoderBatched::mNumSMs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched21mOutputBeamHypothesesE", "tensorrt_llm::runtime::GptDecoderBatched::mOutputBeamHypotheses"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mRuntimeStreamE", "tensorrt_llm::runtime::GptDecoderBatched::mRuntimeStream"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16mSinkTokenLengthE", "tensorrt_llm::runtime::GptDecoderBatched::mSinkTokenLength"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched24mSpeculativeDecodingModeE", "tensorrt_llm::runtime::GptDecoderBatched::mSpeculativeDecodingMode"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched17mTargetLogitsPtrsE", "tensorrt_llm::runtime::GptDecoderBatched::mTargetLogitsPtrs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12mTargetProbsE", "tensorrt_llm::runtime::GptDecoderBatched::mTargetProbs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched10mVocabSizeE", "tensorrt_llm::runtime::GptDecoderBatched::mVocabSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16mVocabSizePaddedE", "tensorrt_llm::runtime::GptDecoderBatched::mVocabSizePadded"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::newBatch"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::newBatch::inputs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::newBatch::outputs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::newBatch::samplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched10newRequestE10SizeType32RKN13decoder_batch7RequestERK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::newRequest"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched10newRequestE10SizeType32RKN13decoder_batch7RequestERK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::newRequest::batchSlot"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched10newRequestE10SizeType32RKN13decoder_batch7RequestERK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::newRequest::request"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched10newRequestE10SizeType32RKN13decoder_batch7RequestERK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::newRequest::samplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched29newRequestDraftTokensExternalE10SizeType32RKN13decoder_batch7RequestERK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::newRequestDraftTokensExternal"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched29newRequestDraftTokensExternalE10SizeType32RKN13decoder_batch7RequestERK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::newRequestDraftTokensExternal::batchIdx"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched29newRequestDraftTokensExternalE10SizeType32RKN13decoder_batch7RequestERK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::newRequestDraftTokensExternal::request"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched29newRequestDraftTokensExternalE10SizeType32RKN13decoder_batch7RequestERK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::newRequestDraftTokensExternal::samplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched29newRequestExplicitDraftTokensE10SizeType32RKN13decoder_batch7RequestE", "tensorrt_llm::runtime::GptDecoderBatched::newRequestExplicitDraftTokens"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched29newRequestExplicitDraftTokensE10SizeType32RKN13decoder_batch7RequestE", "tensorrt_llm::runtime::GptDecoderBatched::newRequestExplicitDraftTokens::batchIdx"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched29newRequestExplicitDraftTokensE10SizeType32RKN13decoder_batch7RequestE", "tensorrt_llm::runtime::GptDecoderBatched::newRequestExplicitDraftTokens::request"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched19newRequestLookaheadE10SizeType32RKN13decoder_batch7RequestE", "tensorrt_llm::runtime::GptDecoderBatched::newRequestLookahead"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched19newRequestLookaheadE10SizeType32RKN13decoder_batch7RequestE", "tensorrt_llm::runtime::GptDecoderBatched::newRequestLookahead::batchIdx"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched19newRequestLookaheadE10SizeType32RKN13decoder_batch7RequestE", "tensorrt_llm::runtime::GptDecoderBatched::newRequestLookahead::request"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16newRequestMedusaE10SizeType32RKN13decoder_batch7RequestE", "tensorrt_llm::runtime::GptDecoderBatched::newRequestMedusa"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16newRequestMedusaE10SizeType32RKN13decoder_batch7RequestE", "tensorrt_llm::runtime::GptDecoderBatched::newRequestMedusa::batchIdx"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16newRequestMedusaE10SizeType32RKN13decoder_batch7RequestE", "tensorrt_llm::runtime::GptDecoderBatched::newRequestMedusa::request"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched29newRequestSpeculativeDecodingE10SizeType32RKN13decoder_batch7RequestERK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::newRequestSpeculativeDecoding"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched29newRequestSpeculativeDecodingE10SizeType32RKN13decoder_batch7RequestERK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::newRequestSpeculativeDecoding::batchIdx"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched29newRequestSpeculativeDecodingE10SizeType32RKN13decoder_batch7RequestERK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::newRequestSpeculativeDecoding::request"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched29newRequestSpeculativeDecodingE10SizeType32RKN13decoder_batch7RequestERK14SamplingConfig", "tensorrt_llm::runtime::GptDecoderBatched::newRequestSpeculativeDecoding::samplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11newRequestsERKNSt6vectorI10SizeType32EERKNSt6vectorIN13decoder_batch7RequestEEERKNSt6vectorI14SamplingConfigEE", "tensorrt_llm::runtime::GptDecoderBatched::newRequests"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11newRequestsERKNSt6vectorI10SizeType32EERKNSt6vectorIN13decoder_batch7RequestEEERKNSt6vectorI14SamplingConfigEE", "tensorrt_llm::runtime::GptDecoderBatched::newRequests::requests"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11newRequestsERKNSt6vectorI10SizeType32EERKNSt6vectorIN13decoder_batch7RequestEEERKNSt6vectorI14SamplingConfigEE", "tensorrt_llm::runtime::GptDecoderBatched::newRequests::samplingConfigs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11newRequestsERKNSt6vectorI10SizeType32EERKNSt6vectorIN13decoder_batch7RequestEEERKNSt6vectorI14SamplingConfigEE", "tensorrt_llm::runtime::GptDecoderBatched::newRequests::seqSlots"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched18postProcessRequestE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::postProcessRequest"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched18postProcessRequestE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::postProcessRequest::batchIdx"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched18postProcessRequestE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::postProcessRequest::samplingConfig"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched18postProcessRequestE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::GptDecoderBatched::postProcessRequest::streaming"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched28setExplicitDraftTokensInputsERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::setExplicitDraftTokensInputs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched28setExplicitDraftTokensInputsERKN13decoder_batch5InputE", "tensorrt_llm::runtime::GptDecoderBatched::setExplicitDraftTokensInputs::input"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::dtype"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::maxAttentionWindow"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::maxBatchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::maxBeamWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::maxSequenceLength"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::maxTokensPerStep"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::mode"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::modelConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::GptDecoderBatched::setup::sinkTokenLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched24setupExplicitDraftTokensEN26ExplicitDraftTokensBuffers6InputsE", "tensorrt_llm::runtime::GptDecoderBatched::setupExplicitDraftTokens"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched24setupExplicitDraftTokensEN26ExplicitDraftTokensBuffers6InputsE", "tensorrt_llm::runtime::GptDecoderBatched::setupExplicitDraftTokens::explicitDraftTokensBuffers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14setupLookaheadE24LookaheadDecodingBuffers", "tensorrt_llm::runtime::GptDecoderBatched::setupLookahead"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14setupLookaheadERK11ModelConfig", "tensorrt_llm::runtime::GptDecoderBatched::setupLookahead"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14setupLookaheadE24LookaheadDecodingBuffers", "tensorrt_llm::runtime::GptDecoderBatched::setupLookahead::lookaheadDecodingBuffers"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14setupLookaheadERK11ModelConfig", "tensorrt_llm::runtime::GptDecoderBatched::setupLookahead::modelConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched24setupSpeculativeDecodingERK11ModelConfig", "tensorrt_llm::runtime::GptDecoderBatched::setupSpeculativeDecoding"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched24setupSpeculativeDecodingERK11ModelConfig", "tensorrt_llm::runtime::GptDecoderBatched::setupSpeculativeDecoding::modelConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14updateFinishedERKN13decoder_batch5TokenE", "tensorrt_llm::runtime::GptDecoderBatched::updateFinished"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14updateFinishedERKN13decoder_batch5TokenE", "tensorrt_llm::runtime::GptDecoderBatched::updateFinished::token"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfigE", "tensorrt_llm::runtime::GptJsonConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3211ModelConfig", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3211ModelConfig", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::gpusPerNode"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3211ModelConfig", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::modelConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3211ModelConfig", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::name"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3211ModelConfig", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::pipelineParallelism"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3211ModelConfig", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::precision"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3211ModelConfig", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::tensorParallelism"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3211ModelConfig", "tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig::version"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfig", "tensorrt_llm::runtime::GptJsonConfig::engineFilename"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfigRKNSt6stringE", "tensorrt_llm::runtime::GptJsonConfig::engineFilename"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfigRKNSt6stringE", "tensorrt_llm::runtime::GptJsonConfig::engineFilename::model"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfig", "tensorrt_llm::runtime::GptJsonConfig::engineFilename::worldConfig"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfigRKNSt6stringE", "tensorrt_llm::runtime::GptJsonConfig::engineFilename::worldConfig"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14getGpusPerNodeEv", "tensorrt_llm::runtime::GptJsonConfig::getGpusPerNode"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14getModelConfigEv", "tensorrt_llm::runtime::GptJsonConfig::getModelConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig21getModelConfigMutableEv", "tensorrt_llm::runtime::GptJsonConfig::getModelConfigMutable"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig7getNameEv", "tensorrt_llm::runtime::GptJsonConfig::getName"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig22getPipelineParallelismEv", "tensorrt_llm::runtime::GptJsonConfig::getPipelineParallelism"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getPrecisionEv", "tensorrt_llm::runtime::GptJsonConfig::getPrecision"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig20getTensorParallelismEv", "tensorrt_llm::runtime::GptJsonConfig::getTensorParallelism"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig10getVersionEv", "tensorrt_llm::runtime::GptJsonConfig::getVersion"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getWorldSizeEv", "tensorrt_llm::runtime::GptJsonConfig::getWorldSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig12mGpusPerNodeE", "tensorrt_llm::runtime::GptJsonConfig::mGpusPerNode"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig12mModelConfigE", "tensorrt_llm::runtime::GptJsonConfig::mModelConfig"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5mNameE", "tensorrt_llm::runtime::GptJsonConfig::mName"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig20mPipelineParallelismE", "tensorrt_llm::runtime::GptJsonConfig::mPipelineParallelism"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig10mPrecisionE", "tensorrt_llm::runtime::GptJsonConfig::mPrecision"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig18mTensorParallelismE", "tensorrt_llm::runtime::GptJsonConfig::mTensorParallelism"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig8mVersionE", "tensorrt_llm::runtime::GptJsonConfig::mVersion"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt10filesystem4pathE", "tensorrt_llm::runtime::GptJsonConfig::parse"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt6stringE", "tensorrt_llm::runtime::GptJsonConfig::parse"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERNSt7istreamE", "tensorrt_llm::runtime::GptJsonConfig::parse"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt6stringE", "tensorrt_llm::runtime::GptJsonConfig::parse::json"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERNSt7istreamE", "tensorrt_llm::runtime::GptJsonConfig::parse::json"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt10filesystem4pathE", "tensorrt_llm::runtime::GptJsonConfig::parse::path"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptSessionE", "tensorrt_llm::runtime::GptSession"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6ConfigE", "tensorrt_llm::runtime::GptSession::Config"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config6ConfigE10SizeType3210SizeType3210SizeType32f", "tensorrt_llm::runtime::GptSession::Config::Config"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config6ConfigE10SizeType3210SizeType3210SizeType32f", "tensorrt_llm::runtime::GptSession::Config::Config::gpuWeightsPercent"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config6ConfigE10SizeType3210SizeType3210SizeType32f", "tensorrt_llm::runtime::GptSession::Config::Config::maxBatchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config6ConfigE10SizeType3210SizeType3210SizeType32f", "tensorrt_llm::runtime::GptSession::Config::Config::maxBeamWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config6ConfigE10SizeType3210SizeType3210SizeType32f", "tensorrt_llm::runtime::GptSession::Config::Config::maxSequenceLength"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config17ctxMicroBatchSizeE", "tensorrt_llm::runtime::GptSession::Config::ctxMicroBatchSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config13cudaGraphModeE", "tensorrt_llm::runtime::GptSession::Config::cudaGraphMode"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config17decoderPerRequestE", "tensorrt_llm::runtime::GptSession::Config::decoderPerRequest"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config12decodingModeE", "tensorrt_llm::runtime::GptSession::Config::decodingMode"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config10enginePathE", "tensorrt_llm::runtime::GptSession::Config::enginePath"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config17genMicroBatchSizeE", "tensorrt_llm::runtime::GptSession::Config::genMicroBatchSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config17gpuWeightsPercentE", "tensorrt_llm::runtime::GptSession::Config::gpuWeightsPercent"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config13kvCacheConfigE", "tensorrt_llm::runtime::GptSession::Config::kvCacheConfig"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config12maxBatchSizeE", "tensorrt_llm::runtime::GptSession::Config::maxBatchSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config12maxBeamWidthE", "tensorrt_llm::runtime::GptSession::Config::maxBeamWidth"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config17maxSequenceLengthE", "tensorrt_llm::runtime::GptSession::Config::maxSequenceLength"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config17normalizeLogProbsE", "tensorrt_llm::runtime::GptSession::Config::normalizeLogProbs"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutorE", "tensorrt_llm::runtime::GptSession::CudaGraphExecutor"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor17CudaGraphExecutorEv", "tensorrt_llm::runtime::GptSession::CudaGraphExecutor::CudaGraphExecutor"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor5clearEv", "tensorrt_llm::runtime::GptSession::CudaGraphExecutor::clear"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6createERK11cudaGraph_t", "tensorrt_llm::runtime::GptSession::CudaGraphExecutor::create"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6createERK11cudaGraph_t", "tensorrt_llm::runtime::GptSession::CudaGraphExecutor::create::graph"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor11hasInstanceEv", "tensorrt_llm::runtime::GptSession::CudaGraphExecutor::hasInstance"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6launchERK10CudaStream", "tensorrt_llm::runtime::GptSession::CudaGraphExecutor::launch"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6launchERK10CudaStream", "tensorrt_llm::runtime::GptSession::CudaGraphExecutor::launch::stream"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor9mInstanceE", "tensorrt_llm::runtime::GptSession::CudaGraphExecutor::mInstance"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor16prepareNextGraphERK11TllmRuntime10SizeType32", "tensorrt_llm::runtime::GptSession::CudaGraphExecutor::prepareNextGraph"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor16prepareNextGraphERK11TllmRuntime10SizeType32", "tensorrt_llm::runtime::GptSession::CudaGraphExecutor::prepareNextGraph::nextContextId"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor16prepareNextGraphERK11TllmRuntime10SizeType32", "tensorrt_llm::runtime::GptSession::CudaGraphExecutor::prepareNextGraph::runtime"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6updateERK11cudaGraph_t", "tensorrt_llm::runtime::GptSession::CudaGraphExecutor::update"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6updateERK11cudaGraph_t", "tensorrt_llm::runtime::GptSession::CudaGraphExecutor::update::graph"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor14uploadToStreamERK10CudaStream", "tensorrt_llm::runtime::GptSession::CudaGraphExecutor::uploadToStream"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor14uploadToStreamERK10CudaStream", "tensorrt_llm::runtime::GptSession::CudaGraphExecutor::uploadToStream::stream"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutorD0Ev", "tensorrt_llm::runtime::GptSession::CudaGraphExecutor::~CudaGraphExecutor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession18GenerationProfilerE", "tensorrt_llm::runtime::GptSession::GenerationProfiler"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession18GenerationProfiler18GenerationProfilerEv", "tensorrt_llm::runtime::GptSession::GenerationProfiler::GenerationProfiler"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession18GenerationProfiler3endE", "tensorrt_llm::runtime::GptSession::GenerationProfiler::end"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession18GenerationProfiler5flagsE", "tensorrt_llm::runtime::GptSession::GenerationProfiler::flags"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession18GenerationProfiler16getElapsedTimeMsEv", "tensorrt_llm::runtime::GptSession::GenerationProfiler::getElapsedTimeMs"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession18GenerationProfiler6getEndEv", "tensorrt_llm::runtime::GptSession::GenerationProfiler::getEnd"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession18GenerationProfiler8getStartEv", "tensorrt_llm::runtime::GptSession::GenerationProfiler::getStart"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession18GenerationProfiler5startE", "tensorrt_llm::runtime::GptSession::GenerationProfiler::start"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigPKvNSt6size_tE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRK9RawEngine9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRKNSt6stringE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRKNSt6vectorI7uint8_tEE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigPKvNSt6size_tE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::engineBuffer"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRKNSt6vectorI7uint8_tEE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::engineBuffer"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRKNSt6stringE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::engineFile"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigPKvNSt6size_tE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::engineSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigPKvNSt6size_tE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::logger"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRK9RawEngine9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::logger"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRKNSt6stringE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::logger"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRKNSt6vectorI7uint8_tEE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::logger"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigPKvNSt6size_tE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::modelConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRK9RawEngine9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::modelConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRKNSt6stringE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::modelConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRKNSt6vectorI7uint8_tEE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::modelConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRK9RawEngine9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::rawEngine"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigPKvNSt6size_tE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::sessionConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRK9RawEngine9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::sessionConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRKNSt6stringE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::sessionConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRKNSt6vectorI7uint8_tEE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::sessionConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigPKvNSt6size_tE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::worldConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRK9RawEngine9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::worldConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRKNSt6stringE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::worldConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRKNSt6vectorI7uint8_tEE9LoggerPtr", "tensorrt_llm::runtime::GptSession::GptSession::worldConfig"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession13KvCacheConfigE", "tensorrt_llm::runtime::GptSession::KvCacheConfig"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession14KvCacheManagerE", "tensorrt_llm::runtime::GptSession::KvCacheManager"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession9LoggerPtrE", "tensorrt_llm::runtime::GptSession::LoggerPtr"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfigE", "tensorrt_llm::runtime::GptSession::MicroBatchConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig16MicroBatchConfigE10SizeType3210SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::GptSession::MicroBatchConfig::MicroBatchConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig16MicroBatchConfigEv", "tensorrt_llm::runtime::GptSession::MicroBatchConfig::MicroBatchConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig16MicroBatchConfigE10SizeType3210SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::GptSession::MicroBatchConfig::MicroBatchConfig::ctxMicroBatchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig16MicroBatchConfigE10SizeType3210SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::GptSession::MicroBatchConfig::MicroBatchConfig::genMicroBatchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig16MicroBatchConfigE10SizeType3210SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::GptSession::MicroBatchConfig::MicroBatchConfig::maxBatchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig16MicroBatchConfigE10SizeType3210SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::GptSession::MicroBatchConfig::MicroBatchConfig::pipelineParallelism"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig12ctxBatchSizeE", "tensorrt_llm::runtime::GptSession::MicroBatchConfig::ctxBatchSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig12genBatchSizeE", "tensorrt_llm::runtime::GptSession::MicroBatchConfig::genBatchSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig13getGenGraphIdE10SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::MicroBatchConfig::getGenGraphId"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig13getGenGraphIdE10SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::MicroBatchConfig::getGenGraphId::flipFlopId"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig13getGenGraphIdE10SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::MicroBatchConfig::getGenGraphId::generationBatchId"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig13numCtxBatchesE", "tensorrt_llm::runtime::GptSession::MicroBatchConfig::numCtxBatches"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig12numCtxPerGenEv", "tensorrt_llm::runtime::GptSession::MicroBatchConfig::numCtxPerGen"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig13numGenBatchesE", "tensorrt_llm::runtime::GptSession::MicroBatchConfig::numGenBatches"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession9TensorPtrE", "tensorrt_llm::runtime::GptSession::TensorPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession22TokenGeneratedCallbackE", "tensorrt_llm::runtime::GptSession::TokenGeneratedCallback"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession13createBuffersE10SizeType32", "tensorrt_llm::runtime::GptSession::createBuffers"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession13createBuffersE10SizeType32", "tensorrt_llm::runtime::GptSession::createBuffers::numMicroBatches"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession14createContextsEv", "tensorrt_llm::runtime::GptSession::createContexts"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession30createCustomAllReduceWorkspaceE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::createCustomAllReduceWorkspace"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession30createCustomAllReduceWorkspaceE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::createCustomAllReduceWorkspace::batchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession30createCustomAllReduceWorkspaceE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::createCustomAllReduceWorkspace::beamWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession30createCustomAllReduceWorkspaceE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::createCustomAllReduceWorkspace::maxSequenceLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession14createDecodersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeEb10SizeType32RKN8executor12DecodingModeE", "tensorrt_llm::runtime::GptSession::createDecoders"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession14createDecodersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeEb10SizeType32RKN8executor12DecodingModeE", "tensorrt_llm::runtime::GptSession::createDecoders::batchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession14createDecodersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeEb10SizeType32RKN8executor12DecodingModeE", "tensorrt_llm::runtime::GptSession::createDecoders::beamWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession14createDecodersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeEb10SizeType32RKN8executor12DecodingModeE", "tensorrt_llm::runtime::GptSession::createDecoders::decoderPerRequest"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession14createDecodersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeEb10SizeType32RKN8executor12DecodingModeE", "tensorrt_llm::runtime::GptSession::createDecoders::decodingMode"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession14createDecodersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeEb10SizeType32RKN8executor12DecodingModeE", "tensorrt_llm::runtime::GptSession::createDecoders::logitsType"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession14createDecodersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeEb10SizeType32RKN8executor12DecodingModeE", "tensorrt_llm::runtime::GptSession::createDecoders::maxAttentionWindow"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession14createDecodersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeEb10SizeType32RKN8executor12DecodingModeE", "tensorrt_llm::runtime::GptSession::createDecoders::maxSequenceLength"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession14createDecodersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeEb10SizeType32RKN8executor12DecodingModeE", "tensorrt_llm::runtime::GptSession::createDecoders::numMicroBatches"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession14createDecodersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeEb10SizeType32RKN8executor12DecodingModeE", "tensorrt_llm::runtime::GptSession::createDecoders::sinkTokenLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession20createKvCacheManagerE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK13KvCacheConfig", "tensorrt_llm::runtime::GptSession::createKvCacheManager"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession20createKvCacheManagerE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK13KvCacheConfig", "tensorrt_llm::runtime::GptSession::createKvCacheManager::batchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession20createKvCacheManagerE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK13KvCacheConfig", "tensorrt_llm::runtime::GptSession::createKvCacheManager::beamWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession20createKvCacheManagerE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK13KvCacheConfig", "tensorrt_llm::runtime::GptSession::createKvCacheManager::config"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession20createKvCacheManagerE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK13KvCacheConfig", "tensorrt_llm::runtime::GptSession::createKvCacheManager::maxAttentionWindow"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession20createKvCacheManagerE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK13KvCacheConfig", "tensorrt_llm::runtime::GptSession::createKvCacheManager::maxSequenceLength"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession20createKvCacheManagerE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK13KvCacheConfig", "tensorrt_llm::runtime::GptSession::createKvCacheManager::sinkTokenLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession30createOnTokenGeneratedCallbackER16GenerationOutput", "tensorrt_llm::runtime::GptSession::createOnTokenGeneratedCallback"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession30createOnTokenGeneratedCallbackER16GenerationOutput", "tensorrt_llm::runtime::GptSession::createOnTokenGeneratedCallback::outputs"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession16decoderStepAsyncE10SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::decoderStepAsync"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession16decoderStepAsyncE10SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::decoderStepAsync::decoderStep"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession16decoderStepAsyncE10SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::decoderStepAsync::microBatchId"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession18executeContextStepERKNSt6vectorI15GenerationInputEERKNSt6vectorI10SizeType32EEPK14KvCacheManager", "tensorrt_llm::runtime::GptSession::executeContextStep"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession18executeContextStepERKNSt6vectorI15GenerationInputEERKNSt6vectorI10SizeType32EEPK14KvCacheManager", "tensorrt_llm::runtime::GptSession::executeContextStep::generationBatchesInputs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession18executeContextStepERKNSt6vectorI15GenerationInputEERKNSt6vectorI10SizeType32EEPK14KvCacheManager", "tensorrt_llm::runtime::GptSession::executeContextStep::generationBatchesOffsets"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession18executeContextStepERKNSt6vectorI15GenerationInputEERKNSt6vectorI10SizeType32EEPK14KvCacheManager", "tensorrt_llm::runtime::GptSession::executeContextStep::kvCacheManager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession21executeGenerationStepE10SizeType32RKNSt6vectorI15GenerationInputEERNSt6vectorI16GenerationOutputEERKNSt6vectorI10SizeType32EEP14KvCacheManagerRNSt6vectorIbEE", "tensorrt_llm::runtime::GptSession::executeGenerationStep"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession21executeGenerationStepE10SizeType32RKNSt6vectorI15GenerationInputEERNSt6vectorI16GenerationOutputEERKNSt6vectorI10SizeType32EEP14KvCacheManagerRNSt6vectorIbEE", "tensorrt_llm::runtime::GptSession::executeGenerationStep::kvCacheManager"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession21executeGenerationStepE10SizeType32RKNSt6vectorI15GenerationInputEERNSt6vectorI16GenerationOutputEERKNSt6vectorI10SizeType32EEP14KvCacheManagerRNSt6vectorIbEE", "tensorrt_llm::runtime::GptSession::executeGenerationStep::microBatchOffsets"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession21executeGenerationStepE10SizeType32RKNSt6vectorI15GenerationInputEERNSt6vectorI16GenerationOutputEERKNSt6vectorI10SizeType32EEP14KvCacheManagerRNSt6vectorIbEE", "tensorrt_llm::runtime::GptSession::executeGenerationStep::microBatchesFinished"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession21executeGenerationStepE10SizeType32RKNSt6vectorI15GenerationInputEERNSt6vectorI16GenerationOutputEERKNSt6vectorI10SizeType32EEP14KvCacheManagerRNSt6vectorIbEE", "tensorrt_llm::runtime::GptSession::executeGenerationStep::microBatchesInputs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession21executeGenerationStepE10SizeType32RKNSt6vectorI15GenerationInputEERNSt6vectorI16GenerationOutputEERKNSt6vectorI10SizeType32EEP14KvCacheManagerRNSt6vectorIbEE", "tensorrt_llm::runtime::GptSession::executeGenerationStep::microBatchesOutputs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession21executeGenerationStepE10SizeType32RKNSt6vectorI15GenerationInputEERNSt6vectorI16GenerationOutputEERKNSt6vectorI10SizeType32EEP14KvCacheManagerRNSt6vectorIbEE", "tensorrt_llm::runtime::GptSession::executeGenerationStep::step"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession8finalizeE10SizeType32RK14SamplingConfig", "tensorrt_llm::runtime::GptSession::finalize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession8finalizeE10SizeType32RK14SamplingConfig", "tensorrt_llm::runtime::GptSession::finalize::microBatchId"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession8finalizeE10SizeType32RK14SamplingConfig", "tensorrt_llm::runtime::GptSession::finalize::samplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession8generateER16GenerationOutputRK15GenerationInputRK14SamplingConfigKNSt10shared_ptrI18GenerationProfilerEE", "tensorrt_llm::runtime::GptSession::generate"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession8generateER16GenerationOutputRK15GenerationInputRK14SamplingConfigKNSt10shared_ptrI18GenerationProfilerEE", "tensorrt_llm::runtime::GptSession::generate::generationProfiler"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession8generateER16GenerationOutputRK15GenerationInputRK14SamplingConfigKNSt10shared_ptrI18GenerationProfilerEE", "tensorrt_llm::runtime::GptSession::generate::inputs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession8generateER16GenerationOutputRK15GenerationInputRK14SamplingConfigKNSt10shared_ptrI18GenerationProfilerEE", "tensorrt_llm::runtime::GptSession::generate::outputs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession8generateER16GenerationOutputRK15GenerationInputRK14SamplingConfigKNSt10shared_ptrI18GenerationProfilerEE", "tensorrt_llm::runtime::GptSession::generate::samplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession15generateBatchedERNSt6vectorI16GenerationOutputEERKNSt6vectorI15GenerationInputEERK14SamplingConfigRK22TokenGeneratedCallbackKNSt10shared_ptrI18GenerationProfilerEE", "tensorrt_llm::runtime::GptSession::generateBatched"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession15generateBatchedERNSt6vectorI16GenerationOutputEERKNSt6vectorI15GenerationInputEERK14SamplingConfigRK22TokenGeneratedCallbackKNSt10shared_ptrI18GenerationProfilerEE", "tensorrt_llm::runtime::GptSession::generateBatched::generationProfiler"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession15generateBatchedERNSt6vectorI16GenerationOutputEERKNSt6vectorI15GenerationInputEERK14SamplingConfigRK22TokenGeneratedCallbackKNSt10shared_ptrI18GenerationProfilerEE", "tensorrt_llm::runtime::GptSession::generateBatched::microBatchesInputs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession15generateBatchedERNSt6vectorI16GenerationOutputEERKNSt6vectorI15GenerationInputEERK14SamplingConfigRK22TokenGeneratedCallbackKNSt10shared_ptrI18GenerationProfilerEE", "tensorrt_llm::runtime::GptSession::generateBatched::microBatchesOutputs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession15generateBatchedERNSt6vectorI16GenerationOutputEERKNSt6vectorI15GenerationInputEERK14SamplingConfigRK22TokenGeneratedCallbackKNSt10shared_ptrI18GenerationProfilerEE", "tensorrt_llm::runtime::GptSession::generateBatched::onTokenGenerated"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession15generateBatchedERNSt6vectorI16GenerationOutputEERKNSt6vectorI15GenerationInputEERK14SamplingConfigRK22TokenGeneratedCallbackKNSt10shared_ptrI18GenerationProfilerEE", "tensorrt_llm::runtime::GptSession::generateBatched::samplingConfig"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession16getBufferManagerEv", "tensorrt_llm::runtime::GptSession::getBufferManager"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession9getDeviceEv", "tensorrt_llm::runtime::GptSession::getDevice"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession18getEngineInspectorEv", "tensorrt_llm::runtime::GptSession::getEngineInspector"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession19getLayerProfileInfoEv", "tensorrt_llm::runtime::GptSession::getLayerProfileInfo"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession9getLoggerEv", "tensorrt_llm::runtime::GptSession::getLogger"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession16getLogitDataTypeEv", "tensorrt_llm::runtime::GptSession::getLogitDataType"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession14getModelConfigEv", "tensorrt_llm::runtime::GptSession::getModelConfig"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession20getNormalizeLogProbsEv", "tensorrt_llm::runtime::GptSession::getNormalizeLogProbs"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession19getRuntimeStreamPtrEv", "tensorrt_llm::runtime::GptSession::getRuntimeStreamPtr"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession14getWorldConfigEv", "tensorrt_llm::runtime::GptSession::getWorldConfig"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession11initDecoderER7ITensorRK15GenerationInputRK16GenerationOutputRK14SamplingConfig10SizeType32", "tensorrt_llm::runtime::GptSession::initDecoder"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession11initDecoderER7ITensorRK15GenerationInputRK16GenerationOutputRK14SamplingConfig10SizeType32", "tensorrt_llm::runtime::GptSession::initDecoder::inputs"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession11initDecoderER7ITensorRK15GenerationInputRK16GenerationOutputRK14SamplingConfig10SizeType32", "tensorrt_llm::runtime::GptSession::initDecoder::microBatchId"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession11initDecoderER7ITensorRK15GenerationInputRK16GenerationOutputRK14SamplingConfig10SizeType32", "tensorrt_llm::runtime::GptSession::initDecoder::outputIds"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession11initDecoderER7ITensorRK15GenerationInputRK16GenerationOutputRK14SamplingConfig10SizeType32", "tensorrt_llm::runtime::GptSession::initDecoder::outputs"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession11initDecoderER7ITensorRK15GenerationInputRK16GenerationOutputRK14SamplingConfig10SizeType32", "tensorrt_llm::runtime::GptSession::initDecoder::samplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession19kvCacheAddSequencesE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::kvCacheAddSequences"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession19kvCacheAddSequencesE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::kvCacheAddSequences::beamWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession19kvCacheAddSequencesE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::kvCacheAddSequences::firstBatchIdx"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession19kvCacheAddSequencesE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::kvCacheAddSequences::microBatchId"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17mAllReduceBuffersE", "tensorrt_llm::runtime::GptSession::mAllReduceBuffers"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession8mBuffersE", "tensorrt_llm::runtime::GptSession::mBuffers"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession10mCommEventE", "tensorrt_llm::runtime::GptSession::mCommEvent"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession11mCommStreamE", "tensorrt_llm::runtime::GptSession::mCommStream"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession19mCudaGraphInstancesE", "tensorrt_llm::runtime::GptSession::mCudaGraphInstances"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession14mCudaGraphModeE", "tensorrt_llm::runtime::GptSession::mCudaGraphMode"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession26mDecoderMaxAttentionWindowE", "tensorrt_llm::runtime::GptSession::mDecoderMaxAttentionWindow"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession29mDecoderMaxAttentionWindowVecE", "tensorrt_llm::runtime::GptSession::mDecoderMaxAttentionWindowVec"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession25mDecoderMaxSequenceLengthE", "tensorrt_llm::runtime::GptSession::mDecoderMaxSequenceLength"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession23mDecoderSinkTokenLengthE", "tensorrt_llm::runtime::GptSession::mDecoderSinkTokenLength"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession9mDecodersE", "tensorrt_llm::runtime::GptSession::mDecoders"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession7mDeviceE", "tensorrt_llm::runtime::GptSession::mDevice"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession15mKvCacheManagerE", "tensorrt_llm::runtime::GptSession::mKvCacheManager"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession7mLoggerE", "tensorrt_llm::runtime::GptSession::mLogger"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession17mMicroBatchConfigE", "tensorrt_llm::runtime::GptSession::mMicroBatchConfig"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession12mModelConfigE", "tensorrt_llm::runtime::GptSession::mModelConfig"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession18mNormalizeLogProbsE", "tensorrt_llm::runtime::GptSession::mNormalizeLogProbs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession13mPipelineCommE", "tensorrt_llm::runtime::GptSession::mPipelineComm"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession15mReceivedEventsE", "tensorrt_llm::runtime::GptSession::mReceivedEvents"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession8mRuntimeE", "tensorrt_llm::runtime::GptSession::mRuntime"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession12mWorldConfigE", "tensorrt_llm::runtime::GptSession::mWorldConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession16setLayerProfilerEv", "tensorrt_llm::runtime::GptSession::setLayerProfiler"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession5setupERK6Config", "tensorrt_llm::runtime::GptSession::setup"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession5setupERK6Config", "tensorrt_llm::runtime::GptSession::setup::sessionConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession14shouldStopSyncE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::shouldStopSync"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession14shouldStopSyncE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::shouldStopSync::batchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession14shouldStopSyncE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::shouldStopSync::beamWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession14shouldStopSyncE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::GptSession::shouldStopSync::microBatchId"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10GptSession23shouldUseKVCacheManagerEv", "tensorrt_llm::runtime::GptSession::shouldUseKVCacheManager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10GptSession13useCudaGraphsEv", "tensorrt_llm::runtime::GptSession::useCudaGraphs"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7IBufferE", "tensorrt_llm::runtime::IBuffer"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer8DataTypeE", "tensorrt_llm::runtime::IBuffer::DataType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferERK7IBuffer", "tensorrt_llm::runtime::IBuffer::IBuffer"], [1, 5, 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, 5, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE", "tensorrt_llm::runtime::IBuffer::data"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4dataEv", "tensorrt_llm::runtime::IBuffer::data"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE", "tensorrt_llm::runtime::IBuffer::data"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataEv", "tensorrt_llm::runtime::IBuffer::data"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE", "tensorrt_llm::runtime::IBuffer::data::index"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE", "tensorrt_llm::runtime::IBuffer::data::index"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer11getCapacityEv", "tensorrt_llm::runtime::IBuffer::getCapacity"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer11getDataTypeEv", "tensorrt_llm::runtime::IBuffer::getDataType"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer15getDataTypeNameEv", "tensorrt_llm::runtime::IBuffer::getDataTypeName"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer13getMemoryTypeEv", "tensorrt_llm::runtime::IBuffer::getMemoryType"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer17getMemoryTypeNameEv", "tensorrt_llm::runtime::IBuffer::getMemoryTypeName"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer7getSizeEv", "tensorrt_llm::runtime::IBuffer::getSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer14getSizeInBytesEv", "tensorrt_llm::runtime::IBuffer::getSizeInBytes"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer10memoryTypeEPKv", "tensorrt_llm::runtime::IBuffer::memoryType"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer10memoryTypeEPKv", "tensorrt_llm::runtime::IBuffer::memoryType::data"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7IBufferaSERK7IBuffer", "tensorrt_llm::runtime::IBuffer::operator="], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer7releaseEv", "tensorrt_llm::runtime::IBuffer::release"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer6resizeENSt6size_tE", "tensorrt_llm::runtime::IBuffer::resize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer6resizeENSt6size_tE", "tensorrt_llm::runtime::IBuffer::resize::newSize"], [1, 5, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice"], [1, 5, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice"], [1, 5, 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, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::buffer"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::buffer"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::offset"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::offset"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::offset"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::offset"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::size"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::size"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::tensor"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::slice::tensor"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer7toBytesENSt6size_tE", "tensorrt_llm::runtime::IBuffer::toBytes"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer7toBytesENSt6size_tE", "tensorrt_llm::runtime::IBuffer::toBytes::size"], [1, 5, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtr", "tensorrt_llm::runtime::IBuffer::view"], [1, 5, 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, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view::size"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view::size"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view::tensor"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtr", "tensorrt_llm::runtime::IBuffer::view::tensor"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::IBuffer::view::tensor"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrRNSt6vectorI1TEE", "tensorrt_llm::runtime::IBuffer::wrap"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap"], [1, 5, 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, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::capacity"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::capacity"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::data"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::data"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::data"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::data"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::size"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::size"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::size"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::size"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::type"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::IBuffer::wrap::type"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrRNSt6vectorI1TEE", "tensorrt_llm::runtime::IBuffer::wrap::v"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7IBufferD0Ev", "tensorrt_llm::runtime::IBuffer::~IBuffer"], [1, 4, 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, 5, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder22acceptDraftTokensByIdsERK7ITensorRK7ITensorRK7ITensorRK7ITensorR7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByIds"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder22acceptDraftTokensByIdsERK7ITensorRK7ITensorRK7ITensorRK7ITensorR7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByIds::batchSlots"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder22acceptDraftTokensByIdsERK7ITensorRK7ITensorRK7ITensorRK7ITensorR7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByIds::contextLengths"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder22acceptDraftTokensByIdsERK7ITensorRK7ITensorRK7ITensorRK7ITensorR7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByIds::draftTokenIds"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder22acceptDraftTokensByIdsERK7ITensorRK7ITensorRK7ITensorRK7ITensorR7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByIds::finishedFinal"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder22acceptDraftTokensByIdsERK7ITensorRK7ITensorRK7ITensorRK7ITensorR7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByIds::finishedSum"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder22acceptDraftTokensByIdsERK7ITensorRK7ITensorRK7ITensorRK7ITensorR7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByIds::finishedVec"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder22acceptDraftTokensByIdsERK7ITensorRK7ITensorRK7ITensorRK7ITensorR7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByIds::numDraftTokens"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder22acceptDraftTokensByIdsERK7ITensorRK7ITensorRK7ITensorRK7ITensorR7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByIds::sequenceLengths"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder22acceptDraftTokensByIdsERK7ITensorRK7ITensorRK7ITensorRK7ITensorR7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByIds::stream"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder22acceptDraftTokensByIdsERK7ITensorRK7ITensorRK7ITensorRK7ITensorR7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByIds::targetTokenIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensorRK7ITensor10SizeType3210SizeType32bfP13curandState_tRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByLogits"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensorRK7ITensor10SizeType3210SizeType32bfP13curandState_tRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByLogits::batchSlots"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensorRK7ITensor10SizeType3210SizeType32bfP13curandState_tRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByLogits::curandState"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensorRK7ITensor10SizeType3210SizeType32bfP13curandState_tRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByLogits::draftLogits"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensorRK7ITensor10SizeType3210SizeType32bfP13curandState_tRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByLogits::draftProbs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensorRK7ITensor10SizeType3210SizeType32bfP13curandState_tRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByLogits::finished"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensorRK7ITensor10SizeType3210SizeType32bfP13curandState_tRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByLogits::numDraftTokens"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensorRK7ITensor10SizeType3210SizeType32bfP13curandState_tRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByLogits::randomAcceptThreshold"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensorRK7ITensor10SizeType3210SizeType32bfP13curandState_tRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByLogits::stream"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensorRK7ITensor10SizeType3210SizeType32bfP13curandState_tRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByLogits::targetLogits"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensorRK7ITensor10SizeType3210SizeType32bfP13curandState_tRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByLogits::targetProbs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensorRK7ITensor10SizeType3210SizeType32bfP13curandState_tRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByLogits::useRandomAcceptThreshold"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensorRK7ITensor10SizeType3210SizeType32bfP13curandState_tRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByLogits::vocabSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensorRK7ITensor10SizeType3210SizeType32bfP13curandState_tRKN13BufferManager13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByLogits::vocabSizePadded"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrENSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrENSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::dtype"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrENSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::maxBatchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrENSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::maxBeamWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrENSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::maxSequenceLength"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrENSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::mode"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrENSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::speculativeDecodingModule"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrENSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::stream"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrENSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::vocabSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrENSt10shared_ptrIK25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::IGptDecoder::create::vocabSizePadded"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardAsync"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardAsync::input"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardAsync::output"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardSync"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardSync::input"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput", "tensorrt_llm::runtime::IGptDecoder::forwardSync::output"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder10gatherTreeERK14DecodingOutputRK13DecodingInputRK13BufferManagerNSt8optionalINSt17reference_wrapperIK14SamplingConfigEEEE", "tensorrt_llm::runtime::IGptDecoder::gatherTree"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder10gatherTreeERK14DecodingOutputRK13DecodingInputRK13BufferManagerNSt8optionalINSt17reference_wrapperIK14SamplingConfigEEEE", "tensorrt_llm::runtime::IGptDecoder::gatherTree::decodingInput"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder10gatherTreeERK14DecodingOutputRK13DecodingInputRK13BufferManagerNSt8optionalINSt17reference_wrapperIK14SamplingConfigEEEE", "tensorrt_llm::runtime::IGptDecoder::gatherTree::decodingOutput"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder10gatherTreeERK14DecodingOutputRK13DecodingInputRK13BufferManagerNSt8optionalINSt17reference_wrapperIK14SamplingConfigEEEE", "tensorrt_llm::runtime::IGptDecoder::gatherTree::manager"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder10gatherTreeERK14DecodingOutputRK13DecodingInputRK13BufferManagerNSt8optionalINSt17reference_wrapperIK14SamplingConfigEEEE", "tensorrt_llm::runtime::IGptDecoder::gatherTree::samplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder17getSamplingConfigEv", "tensorrt_llm::runtime::IGptDecoder::getSamplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEERKNSt8optionalIKNSt6vectorIN13decoder_batch7RequestEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEERKNSt8optionalIKNSt6vectorIN13decoder_batch7RequestEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::batchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEERKNSt8optionalIKNSt6vectorIN13decoder_batch7RequestEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::batchSlots"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEERKNSt8optionalIKNSt6vectorIN13decoder_batch7RequestEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::output"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEERKNSt8optionalIKNSt6vectorIN13decoder_batch7RequestEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::requests"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEERKNSt8optionalIKNSt6vectorIN13decoder_batch7RequestEEEEE", "tensorrt_llm::runtime::IGptDecoder::setup::samplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoderD0Ev", "tensorrt_llm::runtime::IGptDecoder::~IGptDecoder"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatchedE", "tensorrt_llm::runtime::IGptDecoderBatched"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched13CudaStreamPtrE", "tensorrt_llm::runtime::IGptDecoderBatched::CudaStreamPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched18IGptDecoderBatchedEv", "tensorrt_llm::runtime::IGptDecoderBatched::IGptDecoderBatched"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched9TensorPtrE", "tensorrt_llm::runtime::IGptDecoderBatched::TensorPtr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched8TokenPtrE", "tensorrt_llm::runtime::IGptDecoderBatched::TokenPtr"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched8finalizeE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::IGptDecoderBatched::finalize"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched8finalizeE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::IGptDecoderBatched::finalize::batchIdx"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched8finalizeE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::IGptDecoderBatched::finalize::samplingConfig"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched8finalizeE10SizeType32RK14SamplingConfigb", "tensorrt_llm::runtime::IGptDecoderBatched::finalize::streaming"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched7forwardERN13decoder_batch6OutputERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forward"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched7forwardERN13decoder_batch6OutputERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forward::input"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched7forwardERN13decoder_batch6OutputERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forward::output"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forwardAsync"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forwardAsync::input"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forwardAsync::output"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched11forwardSyncERKN13decoder_batch5TokenE", "tensorrt_llm::runtime::IGptDecoderBatched::forwardSync"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched11forwardSyncERKN13decoder_batch5TokenERN13decoder_batch6OutputERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forwardSync"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched11forwardSyncERKN13decoder_batch5TokenERN13decoder_batch6OutputERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forwardSync::input"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched11forwardSyncERKN13decoder_batch5TokenERN13decoder_batch6OutputERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forwardSync::output"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched11forwardSyncERKN13decoder_batch5TokenE", "tensorrt_llm::runtime::IGptDecoderBatched::forwardSync::token"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched11forwardSyncERKN13decoder_batch5TokenERN13decoder_batch6OutputERKN13decoder_batch5InputE", "tensorrt_llm::runtime::IGptDecoderBatched::forwardSync::token"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched24getAcceptedLengthsCumSumEv", "tensorrt_llm::runtime::IGptDecoderBatched::getAcceptedLengthsCumSum"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched22getAcceptedPackedPathsEv", "tensorrt_llm::runtime::IGptDecoderBatched::getAcceptedPackedPaths"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched14getCumLogProbsE10SizeType32", "tensorrt_llm::runtime::IGptDecoderBatched::getCumLogProbs"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched14getCumLogProbsEv", "tensorrt_llm::runtime::IGptDecoderBatched::getCumLogProbs"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched14getCumLogProbsE10SizeType32", "tensorrt_llm::runtime::IGptDecoderBatched::getCumLogProbs::batchIdx"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched15getDecodingModeEv", "tensorrt_llm::runtime::IGptDecoderBatched::getDecodingMode"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched16getFinishReasonsEv", "tensorrt_llm::runtime::IGptDecoderBatched::getFinishReasons"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched11getFinishedEv", "tensorrt_llm::runtime::IGptDecoderBatched::getFinished"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched14getGatheredIdsE10SizeType32", "tensorrt_llm::runtime::IGptDecoderBatched::getGatheredIds"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched14getGatheredIdsE10SizeType32", "tensorrt_llm::runtime::IGptDecoderBatched::getGatheredIds::batchIdx"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched6getIdsE10SizeType32", "tensorrt_llm::runtime::IGptDecoderBatched::getIds"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched6getIdsE10SizeType32", "tensorrt_llm::runtime::IGptDecoderBatched::getIds::batchIdx"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched11getLogProbsE10SizeType32", "tensorrt_llm::runtime::IGptDecoderBatched::getLogProbs"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched11getLogProbsEv", "tensorrt_llm::runtime::IGptDecoderBatched::getLogProbs"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched11getLogProbsE10SizeType32", "tensorrt_llm::runtime::IGptDecoderBatched::getLogProbs::batchIdx"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched10getNbStepsEv", "tensorrt_llm::runtime::IGptDecoderBatched::getNbSteps"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched18getNextDraftTokensEv", "tensorrt_llm::runtime::IGptDecoderBatched::getNextDraftTokens"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched25getNextDraftTokensLengthsEv", "tensorrt_llm::runtime::IGptDecoderBatched::getNextDraftTokensLengths"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched12getParentIdsEv", "tensorrt_llm::runtime::IGptDecoderBatched::getParentIds"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched25getPrevDraftTokensLengthsEv", "tensorrt_llm::runtime::IGptDecoderBatched::getPrevDraftTokensLengths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched11newRequestsERKNSt6vectorI10SizeType32EERKNSt6vectorIN13decoder_batch7RequestEEERKNSt6vectorI14SamplingConfigEE", "tensorrt_llm::runtime::IGptDecoderBatched::newRequests"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched11newRequestsERKNSt6vectorI10SizeType32EERKNSt6vectorIN13decoder_batch7RequestEEERKNSt6vectorI14SamplingConfigEE", "tensorrt_llm::runtime::IGptDecoderBatched::newRequests::requests"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched11newRequestsERKNSt6vectorI10SizeType32EERKNSt6vectorIN13decoder_batch7RequestEEERKNSt6vectorI14SamplingConfigEE", "tensorrt_llm::runtime::IGptDecoderBatched::newRequests::samplingConfigs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched11newRequestsERKNSt6vectorI10SizeType32EERKNSt6vectorIN13decoder_batch7RequestEEERKNSt6vectorI14SamplingConfigEE", "tensorrt_llm::runtime::IGptDecoderBatched::newRequests::seqSlots"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched24setupExplicitDraftTokensEN26ExplicitDraftTokensBuffers6InputsE", "tensorrt_llm::runtime::IGptDecoderBatched::setupExplicitDraftTokens"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched24setupExplicitDraftTokensEN26ExplicitDraftTokensBuffers6InputsE", "tensorrt_llm::runtime::IGptDecoderBatched::setupExplicitDraftTokens::explicitDraftTokensBuffers"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched14setupLookaheadE24LookaheadDecodingBuffers", "tensorrt_llm::runtime::IGptDecoderBatched::setupLookahead"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched14setupLookaheadE24LookaheadDecodingBuffers", "tensorrt_llm::runtime::IGptDecoderBatched::setupLookahead::lookaheadDecodingBuffers"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoderE", "tensorrt_llm::runtime::IStatefulGptDecoder"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder13CudaStreamPtrE", "tensorrt_llm::runtime::IStatefulGptDecoder::CudaStreamPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder19IStatefulGptDecoderEv", "tensorrt_llm::runtime::IStatefulGptDecoder::IStatefulGptDecoder"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder9TensorPtrE", "tensorrt_llm::runtime::IStatefulGptDecoder::TensorPtr"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder8finalizeERK14SamplingConfig", "tensorrt_llm::runtime::IStatefulGptDecoder::finalize"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder8finalizeERK14SamplingConfig", "tensorrt_llm::runtime::IStatefulGptDecoder::finalize::samplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder7forwardERN7decoder6OutputERKN7decoder5InputE", "tensorrt_llm::runtime::IStatefulGptDecoder::forward"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder7forwardERN7decoder6OutputERKN7decoder5InputE", "tensorrt_llm::runtime::IStatefulGptDecoder::forward::input"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder7forwardERN7decoder6OutputERKN7decoder5InputE", "tensorrt_llm::runtime::IStatefulGptDecoder::forward::output"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder12forwardAsyncERN7decoder6OutputERKN7decoder5InputE", "tensorrt_llm::runtime::IStatefulGptDecoder::forwardAsync"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder12forwardAsyncERN7decoder6OutputERKN7decoder5InputE", "tensorrt_llm::runtime::IStatefulGptDecoder::forwardAsync::input"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder12forwardAsyncERN7decoder6OutputERKN7decoder5InputE", "tensorrt_llm::runtime::IStatefulGptDecoder::forwardAsync::output"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder11forwardSyncEv", "tensorrt_llm::runtime::IStatefulGptDecoder::forwardSync"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder15getAllNewTokensEv", "tensorrt_llm::runtime::IStatefulGptDecoder::getAllNewTokens"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder14getCumLogProbsEv", "tensorrt_llm::runtime::IStatefulGptDecoder::getCumLogProbs"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder14getGatheredIdsEv", "tensorrt_llm::runtime::IStatefulGptDecoder::getGatheredIds"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder6getIdsEv", "tensorrt_llm::runtime::IStatefulGptDecoder::getIds"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder11getLogProbsEv", "tensorrt_llm::runtime::IStatefulGptDecoder::getLogProbs"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder13getNbFinishedEv", "tensorrt_llm::runtime::IStatefulGptDecoder::getNbFinished"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder12getNewTokensE10SizeType32", "tensorrt_llm::runtime::IStatefulGptDecoder::getNewTokens"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder12getNewTokensE10SizeType32", "tensorrt_llm::runtime::IStatefulGptDecoder::getNewTokens::iter"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig", "tensorrt_llm::runtime::IStatefulGptDecoder::newBatch"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig", "tensorrt_llm::runtime::IStatefulGptDecoder::newBatch::inputs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig", "tensorrt_llm::runtime::IStatefulGptDecoder::newBatch::outputs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig", "tensorrt_llm::runtime::IStatefulGptDecoder::newBatch::samplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::IStatefulGptDecoder::setup"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::IStatefulGptDecoder::setup::dtype"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::IStatefulGptDecoder::setup::maxAttentionWindow"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::IStatefulGptDecoder::setup::maxBatchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::IStatefulGptDecoder::setup::maxBeamWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::IStatefulGptDecoder::setup::maxSequenceLength"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::IStatefulGptDecoder::setup::maxTokensPerStep"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::IStatefulGptDecoder::setup::mode"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::IStatefulGptDecoder::setup::modelConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig", "tensorrt_llm::runtime::IStatefulGptDecoder::setup::sinkTokenLength"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoderD0Ev", "tensorrt_llm::runtime::IStatefulGptDecoder::~IStatefulGptDecoder"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7ITensorE", "tensorrt_llm::runtime::ITensor"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9DimType64E", "tensorrt_llm::runtime::ITensor::DimType64"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorERK7ITensor", "tensorrt_llm::runtime::ITensor::ITensor"], [1, 5, 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, 5, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at"], [1, 5, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atEN7ITensor14UniqueConstPtrERR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at"], [1, 5, 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, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at::offsetDims"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atEN7ITensor14UniqueConstPtrERR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at::offsetDims"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at::offsetDims"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at::offsetDims"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at::tensor"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atEN7ITensor14UniqueConstPtrERR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at::tensor"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::at::tensor"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::at::tensor"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8castSizeE6size_t", "tensorrt_llm::runtime::ITensor::castSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8castSizeE6size_t", "tensorrt_llm::runtime::ITensor::castSize::newSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8flattenNE9SharedPtrNSt7int64_tE", "tensorrt_llm::runtime::ITensor::flattenN"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8flattenNE9SharedPtrNSt7int64_tE", "tensorrt_llm::runtime::ITensor::flattenN::sliceN"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8flattenNE9SharedPtrNSt7int64_tE", "tensorrt_llm::runtime::ITensor::flattenN::tensor"], [1, 5, 1, "_CPPv4I_10SizeType32ENK12tensorrt_llm7runtime7ITensor12getDimensionE9DimType64v", "tensorrt_llm::runtime::ITensor::getDimension"], [1, 8, 1, "_CPPv4I_10SizeType32ENK12tensorrt_llm7runtime7ITensor12getDimensionE9DimType64v", "tensorrt_llm::runtime::ITensor::getDimension::n"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime7ITensor8getShapeEv", "tensorrt_llm::runtime::ITensor::getShape"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9makeShapeERKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::makeShape"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9makeShapeERKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::makeShape::dims"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensoraSERK7ITensor", "tensorrt_llm::runtime::ITensor::operator="], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7reshapeERK5Shape", "tensorrt_llm::runtime::ITensor::reshape"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7reshapeERK5Shape", "tensorrt_llm::runtime::ITensor::reshape::dims"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor6resizeENSt6size_tE", "tensorrt_llm::runtime::ITensor::resize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor6resizeENSt6size_tE", "tensorrt_llm::runtime::ITensor::resize::newSize"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals"], [1, 5, 1, "_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapeRK5Shape", "tensorrt_llm::runtime::ITensor::shapeEquals"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERK5Shape", "tensorrt_llm::runtime::ITensor::shapeEquals"], [1, 5, 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, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::count"], [1, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::count"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::dims"], [1, 6, 1, "_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::dims"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T10SizeType32", "tensorrt_llm::runtime::ITensor::shapeEquals::lhs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapeRK5Shape", "tensorrt_llm::runtime::ITensor::shapeEquals::lhs"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERK5Shape", "tensorrt_llm::runtime::ITensor::shapeEquals::other"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERKNSt16initializer_listI10SizeType32EE", "tensorrt_llm::runtime::ITensor::shapeEquals::other"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapeRK5Shape", "tensorrt_llm::runtime::ITensor::shapeEquals::rhs"], [1, 5, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 5, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 5, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice"], [1, 5, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 5, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice"], [1, 5, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape9DimType64", "tensorrt_llm::runtime::ITensor::slice"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice"], [1, 5, 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, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offset"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offset"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offset"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offset"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape9DimType64", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE9DimType64", "tensorrt_llm::runtime::ITensor::slice::offsetDims"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape9DimType64", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE9DimType64", "tensorrt_llm::runtime::ITensor::slice::size"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape9DimType64", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE9DimType64", "tensorrt_llm::runtime::ITensor::slice::tensor"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeE10SizeType32", "tensorrt_llm::runtime::ITensor::squeeze"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::squeeze"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeE10SizeType32", "tensorrt_llm::runtime::ITensor::squeeze::dim"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::squeeze::dim"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::squeeze::shape"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7stridesERK5Shape", "tensorrt_llm::runtime::ITensor::strides"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor7stridesERK5Shape", "tensorrt_llm::runtime::ITensor::strides::dims"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8toStringERK5Shape", "tensorrt_llm::runtime::ITensor::toString"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor8toStringERK5Shape", "tensorrt_llm::runtime::ITensor::toString::dims"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeE10SizeType32", "tensorrt_llm::runtime::ITensor::unsqueeze"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::unsqueeze"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeE10SizeType32", "tensorrt_llm::runtime::ITensor::unsqueeze::dim"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::unsqueeze::dim"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeERK5Shape10SizeType32", "tensorrt_llm::runtime::ITensor::unsqueeze::shape"], [1, 5, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::view"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewE9SharedPtr", "tensorrt_llm::runtime::ITensor::view"], [1, 5, 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, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewEN7IBuffer9SharedPtrERK5Shape", "tensorrt_llm::runtime::ITensor::view::buffer"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::view::dims"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewEN7IBuffer9SharedPtrERK5Shape", "tensorrt_llm::runtime::ITensor::view::dims"], [1, 6, 1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape", "tensorrt_llm::runtime::ITensor::view::tensor"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewE9SharedPtr", "tensorrt_llm::runtime::ITensor::view::tensor"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor6volumeERK5Shape", "tensorrt_llm::runtime::ITensor::volume"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor6volumeERK5Shape", "tensorrt_llm::runtime::ITensor::volume::dims"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor17volumeNonNegativeERK5Shape", "tensorrt_llm::runtime::ITensor::volumeNonNegative"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor17volumeNonNegativeERK5Shape", "tensorrt_llm::runtime::ITensor::volumeNonNegative::shape"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape", "tensorrt_llm::runtime::ITensor::wrap"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape", "tensorrt_llm::runtime::ITensor::wrap"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape", "tensorrt_llm::runtime::ITensor::wrap"], [1, 5, 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, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::capacity"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::capacity"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape", "tensorrt_llm::runtime::ITensor::wrap::data"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::data"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape", "tensorrt_llm::runtime::ITensor::wrap::data"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::data"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape", "tensorrt_llm::runtime::ITensor::wrap::shape"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::shape"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape", "tensorrt_llm::runtime::ITensor::wrap::shape"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape", "tensorrt_llm::runtime::ITensor::wrap::shape"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::shape"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape", "tensorrt_llm::runtime::ITensor::wrap::type"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE", "tensorrt_llm::runtime::ITensor::wrap::type"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape", "tensorrt_llm::runtime::ITensor::wrap::v"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7ITensorD0Ev", "tensorrt_llm::runtime::ITensor::~ITensor"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryE", "tensorrt_llm::runtime::IpcMemory"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9BufferPtrE", "tensorrt_llm::runtime::IpcMemory::BufferPtr"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory10FLAGS_SIZEE", "tensorrt_llm::runtime::IpcMemory::FLAGS_SIZE"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb", "tensorrt_llm::runtime::IpcMemory::IpcMemory"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryERK9IpcMemory", "tensorrt_llm::runtime::IpcMemory::IpcMemory"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryERR9IpcMemory", "tensorrt_llm::runtime::IpcMemory::IpcMemory"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb", "tensorrt_llm::runtime::IpcMemory::IpcMemory::bufferSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb", "tensorrt_llm::runtime::IpcMemory::IpcMemory::manager"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb", "tensorrt_llm::runtime::IpcMemory::IpcMemory::openIpc"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb", "tensorrt_llm::runtime::IpcMemory::IpcMemory::worldConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::IpcMemory::allocateIpcMemory"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::IpcMemory::allocateIpcMemory::bufferSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::IpcMemory::allocateIpcMemory::manager"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfig", "tensorrt_llm::runtime::IpcMemory::allocateIpcMemory::worldConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory16destroyIpcMemoryEv", "tensorrt_llm::runtime::IpcMemory::destroyIpcMemory"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9IpcMemory11getCommPtrsEv", "tensorrt_llm::runtime::IpcMemory::getCommPtrs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory7mBufferE", "tensorrt_llm::runtime::IpcMemory::mBuffer"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9mCommPtrsE", "tensorrt_llm::runtime::IpcMemory::mCommPtrs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory8mOpenIpcE", "tensorrt_llm::runtime::IpcMemory::mOpenIpc"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory7mTpRankE", "tensorrt_llm::runtime::IpcMemory::mTpRank"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryaSERK9IpcMemory", "tensorrt_llm::runtime::IpcMemory::operator="], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryaSERR9IpcMemory", "tensorrt_llm::runtime::IpcMemory::operator="], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryD0Ev", "tensorrt_llm::runtime::IpcMemory::~IpcMemory"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffersE", "tensorrt_llm::runtime::LookaheadDecodingBuffers"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers7ITensorE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::ITensor"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers24LookaheadDecodingBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::LookaheadDecodingBuffers"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers24LookaheadDecodingBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::LookaheadDecodingBuffers::bufferManager"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers24LookaheadDecodingBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::LookaheadDecodingBuffers::maxNumSequences"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers24LookaheadDecodingBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::LookaheadDecodingBuffers::maxTokensPerStep"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers10SizeType32E", "tensorrt_llm::runtime::LookaheadDecodingBuffers::SizeType32"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers9TensorPtrE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::TensorPtr"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers17generationLengthsE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::generationLengths"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers11packedMasksE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::packedMasks"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers11positionIdsE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::positionIds"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers15positionOffsetsE", "tensorrt_llm::runtime::LookaheadDecodingBuffers::positionOffsets"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModuleE", "tensorrt_llm::runtime::LookaheadModule"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadModule::LookaheadModule"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleEv", "tensorrt_llm::runtime::LookaheadModule::LookaheadModule"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadModule::LookaheadModule::maxDecodingDraftTokens"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadModule::LookaheadModule::maxDraftPathLen"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime15LookaheadModule18getExecutionConfigEv", "tensorrt_llm::runtime::LookaheadModule::getExecutionConfig"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule16mExecutionConfigE", "tensorrt_llm::runtime::LookaheadModule::mExecutionConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule18setExecutionConfigERKN8executor23LookaheadDecodingConfigE", "tensorrt_llm::runtime::LookaheadModule::setExecutionConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule18setExecutionConfigERKN8executor23LookaheadDecodingConfigE", "tensorrt_llm::runtime::LookaheadModule::setExecutionConfig::config"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffersE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers7ITensorE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::ITensor"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::decodingConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::manager"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::maxBatchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::maxBeamWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::modelConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::runtime"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::LookaheadRuntimeBuffers::worldConfig"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers10SizeType32E", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::SizeType32"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers9TensorMapE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::TensorMap"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers9TensorPtrE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::TensorPtr"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers18batchSlotsHostCopyE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::batchSlotsHostCopy"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23generationLengthsDeviceE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::generationLengthsDevice"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers21generationLengthsHostE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::generationLengthsHost"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers25generationLengthsHostCopyE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::generationLengthsHostCopy"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::insertInputTensors"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::insertInputTensors::inputBuffers"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::insertInputTensors::outputBuffers"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::insertInputTensors::worldConfig"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers14packedMaskHostE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::packedMaskHost"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers18packedMaskHostCopyE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::packedMaskHostCopy"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers17packedMasksDeviceE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::packedMasksDevice"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers17positionIdsDeviceE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionIdsDevice"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers15positionIdsHostE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionIdsHost"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers19positionIdsHostCopyE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionIdsHostCopy"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers21positionOffsetsDeviceE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionOffsetsDevice"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers19positionOffsetsHostE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionOffsetsHost"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23positionOffsetsHostCopyE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::positionOffsetsHostCopy"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::reshape"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::reshape::numCtxSequences"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::reshape::numGenSequences"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers7reshapeE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::reshape::tokensPerStep"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRK24LookaheadDecodingBuffersRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRK24LookaheadDecodingBuffersRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::decoderLookaheadBuffers"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRK24LookaheadDecodingBuffersRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::modelConfig"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRK24LookaheadDecodingBuffersRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::numCtxSequences"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRK24LookaheadDecodingBuffersRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::numGenSequences"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRK24LookaheadDecodingBuffersRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::requestTypes"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRK24LookaheadDecodingBuffersRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::runtime"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRK24LookaheadDecodingBuffersRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::seqSlots"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRK24LookaheadDecodingBuffersRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE", "tensorrt_llm::runtime::LookaheadRuntimeBuffers::setFromInputs::worldConfig"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCacheE", "tensorrt_llm::runtime::LoraCache"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCache::LoraCache"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCache::LoraCache::bufferManager"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCache::LoraCache::modelConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCache::LoraCache::pageManagerConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCache::LoraCache::worldConfig"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache10TaskIdTypeE", "tensorrt_llm::runtime::LoraCache::TaskIdType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig11adapterSizeE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::adapterSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig6inSizeE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::inSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7layerIdE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::layerId"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8moduleIdE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::moduleId"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8numSlotsE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::numSlots"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfigeqERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::operator=="], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfigeqERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::operator==::o"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7outSizeE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::outSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig6pageIdE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::pageId"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7slotIdxE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::slotIdx"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8toStringEv", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::toString"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig16weightsInPointerE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::weightsInPointer"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig17weightsOutPointerE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfig::weightsOutPointer"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache28TaskLayerModuleConfigListPtrE", "tensorrt_llm::runtime::LoraCache::TaskLayerModuleConfigListPtr"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueE", "tensorrt_llm::runtime::LoraCache::TaskValue"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERR9TaskValue", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueEv", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::configs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::done"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::inProgress"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::it"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::loadInProgress"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::loaded"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERR9TaskValue", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::o"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb", "tensorrt_llm::runtime::LoraCache::TaskValue::TaskValue::pageIds"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue7configsE", "tensorrt_llm::runtime::LoraCache::TaskValue::configs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue4doneE", "tensorrt_llm::runtime::LoraCache::TaskValue::done"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue10inProgressE", "tensorrt_llm::runtime::LoraCache::TaskValue::inProgress"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue2itE", "tensorrt_llm::runtime::LoraCache::TaskValue::it"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue14loadInProgressE", "tensorrt_llm::runtime::LoraCache::TaskValue::loadInProgress"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue6loadedE", "tensorrt_llm::runtime::LoraCache::TaskValue::loaded"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueaSERR9TaskValue", "tensorrt_llm::runtime::LoraCache::TaskValue::operator="], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueaSERR9TaskValue", "tensorrt_llm::runtime::LoraCache::TaskValue::operator=::o"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue7pageIdsE", "tensorrt_llm::runtime::LoraCache::TaskValue::pageIds"], [1, 5, 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, 2, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatusE", "tensorrt_llm::runtime::LoraCache::ValueStatus"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus20kVALUE_STATUS_LOADEDE", "tensorrt_llm::runtime::LoraCache::ValueStatus::kVALUE_STATUS_LOADED"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus21kVALUE_STATUS_MISSINGE", "tensorrt_llm::runtime::LoraCache::ValueStatus::kVALUE_STATUS_MISSING"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus24kVALUE_STATUS_PROCESSINGE", "tensorrt_llm::runtime::LoraCache::ValueStatus::kVALUE_STATUS_PROCESSING"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache4bumpE10TaskIdType", "tensorrt_llm::runtime::LoraCache::bump"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache4bumpE10TaskIdType", "tensorrt_llm::runtime::LoraCache::bump::taskId"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache18bumpTaskInProgressE10TaskIdType", "tensorrt_llm::runtime::LoraCache::bumpTaskInProgress"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache18bumpTaskInProgressE10TaskIdType", "tensorrt_llm::runtime::LoraCache::bumpTaskInProgress::taskId"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache19claimPagesWithEvictE10SizeType32", "tensorrt_llm::runtime::LoraCache::claimPagesWithEvict"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache19claimPagesWithEvictE10SizeType32", "tensorrt_llm::runtime::LoraCache::claimPagesWithEvict::numPages"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache8copyTaskE10TaskIdTypeR9LoraCacheb", "tensorrt_llm::runtime::LoraCache::copyTask"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache8copyTaskE10TaskIdTypeR9LoraCacheb", "tensorrt_llm::runtime::LoraCache::copyTask::deviceCache"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache8copyTaskE10TaskIdTypeR9LoraCacheb", "tensorrt_llm::runtime::LoraCache::copyTask::markDone"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache8copyTaskE10TaskIdTypeR9LoraCacheb", "tensorrt_llm::runtime::LoraCache::copyTask::taskId"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache", "tensorrt_llm::runtime::LoraCache::copyTaskMapPages"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache", "tensorrt_llm::runtime::LoraCache::copyTaskMapPages::sourceTaskValue"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache", "tensorrt_llm::runtime::LoraCache::copyTaskMapPages::targetCache"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache", "tensorrt_llm::runtime::LoraCache::copyTaskMapPages::targetPageIds"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache", "tensorrt_llm::runtime::LoraCache::copyTaskMapPages::targetTaskValue"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::config"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::manager"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::modelConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::moduleIdToModel"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::pageIds"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::pages"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::weights"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCache::copyToPages::worldConfig"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE10TaskIdType", "tensorrt_llm::runtime::LoraCache::determineNumPages"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE9TensorPtr", "tensorrt_llm::runtime::LoraCache::determineNumPages"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE9TensorPtr", "tensorrt_llm::runtime::LoraCache::determineNumPages::config"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE10TaskIdType", "tensorrt_llm::runtime::LoraCache::determineNumPages::taskId"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache4fitsE9TensorPtr", "tensorrt_llm::runtime::LoraCache::fits"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache4fitsE9TensorPtr", "tensorrt_llm::runtime::LoraCache::fits::config"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3getE10TaskIdType", "tensorrt_llm::runtime::LoraCache::get"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3getE10TaskIdType", "tensorrt_llm::runtime::LoraCache::get::taskId"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache11getNumPagesEv", "tensorrt_llm::runtime::LoraCache::getNumPages"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache10getPagePtrE6size_t", "tensorrt_llm::runtime::LoraCache::getPagePtr"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache10getPagePtrE6size_t", "tensorrt_llm::runtime::LoraCache::getPagePtr::pageId"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache9getStatusE10TaskIdType", "tensorrt_llm::runtime::LoraCache::getStatus"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache9getStatusE10TaskIdType", "tensorrt_llm::runtime::LoraCache::getStatus::taskId"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache3hasE10TaskIdType", "tensorrt_llm::runtime::LoraCache::has"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache3hasE10TaskIdType", "tensorrt_llm::runtime::LoraCache::has::taskId"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache6isDoneE10TaskIdType", "tensorrt_llm::runtime::LoraCache::isDone"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache6isDoneE10TaskIdType", "tensorrt_llm::runtime::LoraCache::isDone::taskId"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache8isLoadedE10TaskIdType", "tensorrt_llm::runtime::LoraCache::isLoaded"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache8isLoadedE10TaskIdType", "tensorrt_llm::runtime::LoraCache::isLoaded::taskId"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus20kVALUE_STATUS_LOADEDE", "tensorrt_llm::runtime::LoraCache::kVALUE_STATUS_LOADED"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus21kVALUE_STATUS_MISSINGE", "tensorrt_llm::runtime::LoraCache::kVALUE_STATUS_MISSING"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus24kVALUE_STATUS_PROCESSINGE", "tensorrt_llm::runtime::LoraCache::kVALUE_STATUS_PROCESSING"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsE10TaskIdType9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsER9TaskValue9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsER9TaskValue9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::cacheValue"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsE10TaskIdType9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::config"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsER9TaskValue9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::config"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsE10TaskIdType9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::taskId"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsE10TaskIdType9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::weights"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsER9TaskValue9TensorPtr9TensorPtr", "tensorrt_llm::runtime::LoraCache::loadWeights::weights"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache14mBufferManagerE", "tensorrt_llm::runtime::LoraCache::mBufferManager"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9mCacheMapE", "tensorrt_llm::runtime::LoraCache::mCacheMap"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11mCacheMutexE", "tensorrt_llm::runtime::LoraCache::mCacheMutex"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17mCachePageManagerE", "tensorrt_llm::runtime::LoraCache::mCachePageManager"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21mDeviceBufferManagersE", "tensorrt_llm::runtime::LoraCache::mDeviceBufferManagers"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache10mDoneTasksE", "tensorrt_llm::runtime::LoraCache::mDoneTasks"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16mInProgressTasksE", "tensorrt_llm::runtime::LoraCache::mInProgressTasks"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12mModelConfigE", "tensorrt_llm::runtime::LoraCache::mModelConfig"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17mModuleIdToModuleE", "tensorrt_llm::runtime::LoraCache::mModuleIdToModule"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache18mPageManagerConfigE", "tensorrt_llm::runtime::LoraCache::mPageManagerConfig"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11mPagesMutexE", "tensorrt_llm::runtime::LoraCache::mPagesMutex"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12mWorldConfigE", "tensorrt_llm::runtime::LoraCache::mWorldConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11markAllDoneEv", "tensorrt_llm::runtime::LoraCache::markAllDone"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12markTaskDoneE10TaskIdType", "tensorrt_llm::runtime::LoraCache::markTaskDone"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12markTaskDoneE10TaskIdType", "tensorrt_llm::runtime::LoraCache::markTaskDone::taskId"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb", "tensorrt_llm::runtime::LoraCache::put"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb", "tensorrt_llm::runtime::LoraCache::put::config"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb", "tensorrt_llm::runtime::LoraCache::put::load"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb", "tensorrt_llm::runtime::LoraCache::put::taskId"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb", "tensorrt_llm::runtime::LoraCache::put::weights"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpu"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpu::input"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpu::output"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpu::tpRank"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpu::tpSize"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner::T"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner::input"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner::output"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner::tpRank"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCache::splitTransposeCpuInner::tpSize"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullExceptionE", "tensorrt_llm::runtime::LoraCacheFullException"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullException22LoraCacheFullExceptionERKNSt6stringE", "tensorrt_llm::runtime::LoraCacheFullException::LoraCacheFullException"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullException22LoraCacheFullExceptionERKNSt6stringE", "tensorrt_llm::runtime::LoraCacheFullException::LoraCacheFullException::msg"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullExceptionD0Ev", "tensorrt_llm::runtime::LoraCacheFullException::~LoraCacheFullException"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManagerE", "tensorrt_llm::runtime::LoraCachePageManager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager20LoraCachePageManagerERK26LoraCachePageManagerConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCachePageManager::LoraCachePageManager"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager20LoraCachePageManagerERK26LoraCachePageManagerConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCachePageManager::LoraCachePageManager::bufferManager"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager20LoraCachePageManagerERK26LoraCachePageManagerConfigRK13BufferManager", "tensorrt_llm::runtime::LoraCachePageManager::LoraCachePageManager::config"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager9TensorPtrE", "tensorrt_llm::runtime::LoraCachePageManager::TensorPtr"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager8blockPtrE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManager::blockPtr"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager8blockPtrE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManager::blockPtr::blockIdx"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10claimPagesE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManager::claimPages"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10claimPagesE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManager::claimPages::numPages"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10initializeERK13BufferManager", "tensorrt_llm::runtime::LoraCachePageManager::initialize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10initializeERK13BufferManager", "tensorrt_llm::runtime::LoraCachePageManager::initialize::bufferManager"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager7mConfigE", "tensorrt_llm::runtime::LoraCachePageManager::mConfig"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager12mFreePageIdsE", "tensorrt_llm::runtime::LoraCachePageManager::mFreePageIds"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager11mIsPageFreeE", "tensorrt_llm::runtime::LoraCachePageManager::mIsPageFree"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager11mPageBlocksE", "tensorrt_llm::runtime::LoraCachePageManager::mPageBlocks"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager14mutablePagePtrENSt6size_tE", "tensorrt_llm::runtime::LoraCachePageManager::mutablePagePtr"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager14mutablePagePtrENSt6size_tE", "tensorrt_llm::runtime::LoraCachePageManager::mutablePagePtr::pageIdx"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager17numAvailablePagesEv", "tensorrt_llm::runtime::LoraCachePageManager::numAvailablePages"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager7pagePtrENSt6size_tE", "tensorrt_llm::runtime::LoraCachePageManager::pagePtr"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager7pagePtrENSt6size_tE", "tensorrt_llm::runtime::LoraCachePageManager::pagePtr::pageIdx"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager12releasePagesERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCachePageManager::releasePages"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager12releasePagesERKNSt6vectorINSt6size_tEEE", "tensorrt_llm::runtime::LoraCachePageManager::releasePages::pages"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfigE", "tensorrt_llm::runtime::LoraCachePageManagerConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::dType"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::maxPagesPerBlock"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::memType"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::numCopyStreams"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::pageWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::slotsPerPage"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::LoraCachePageManagerConfig::totalNumPages"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig11getDataTypeEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getDataType"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig13getInitToZeroEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getInitToZero"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig19getMaxPagesPerBlockEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getMaxPagesPerBlock"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig13getMemoryTypeEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getMemoryType"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig17getNumCopyStreamsEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getNumCopyStreams"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig12getPageWidthEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getPageWidth"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig15getSlotsPerPageEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getSlotsPerPage"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig16getTotalNumPagesEv", "tensorrt_llm::runtime::LoraCachePageManagerConfig::getTotalNumPages"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig9mDataTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mDataType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11mInitToZeroE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mInitToZero"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig17mMaxPagesPerBlockE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mMaxPagesPerBlock"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11mMemoryTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mMemoryType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15mNumCopyStreamsE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mNumCopyStreams"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig10mPageWidthE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mPageWidth"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13mSlotsPerPageE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mSlotsPerPage"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig14mTotalNumPagesE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::mTotalNumPages"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11setDataTypeERKN8nvinfer18DataTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setDataType"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11setDataTypeERKN8nvinfer18DataTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setDataType::dtype"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setInitToZeroEb", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setInitToZero"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setInitToZeroEb", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setInitToZero::initToZero"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig19setMaxPagesPerBlockERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setMaxPagesPerBlock"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig19setMaxPagesPerBlockERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setMaxPagesPerBlock::maxPagesPerBlock"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setMemoryTypeERKN7runtime10MemoryTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setMemoryType"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setMemoryTypeERKN7runtime10MemoryTypeE", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setMemoryType::memoryType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig17setNumCopyStreamsE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setNumCopyStreams"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig17setNumCopyStreamsE10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setNumCopyStreams::numCopyStreams"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig12setPageWidthERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setPageWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig12setPageWidthERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setPageWidth::pageWidth"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setSlotsPerPageERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setSlotsPerPage"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setSlotsPerPageERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setSlotsPerPage::slotsPerPage"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setTotalNumPageERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setTotalNumPage"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setTotalNumPageERK10SizeType32", "tensorrt_llm::runtime::LoraCachePageManagerConfig::setTotalNumPage::totalNumPages"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedExceptionE", "tensorrt_llm::runtime::LoraExpectedException"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedException21LoraExpectedExceptionERKNSt6stringE", "tensorrt_llm::runtime::LoraExpectedException::LoraExpectedException"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedException21LoraExpectedExceptionERKNSt6stringE", "tensorrt_llm::runtime::LoraExpectedException::LoraExpectedException::msg"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedExceptionD0Ev", "tensorrt_llm::runtime::LoraExpectedException::~LoraExpectedException"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModuleE", "tensorrt_llm::runtime::LoraModule"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10LoraModule", "tensorrt_llm::runtime::LoraModule::LoraModule"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleEv", "tensorrt_llm::runtime::LoraModule::LoraModule"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::inDim"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::inDimFirst"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::inTpSplitDim"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10LoraModule", "tensorrt_llm::runtime::LoraModule::LoraModule::o"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::outDim"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::outDimFirst"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::outTpSplitDim"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::LoraModule::t"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleTypeE", "tensorrt_llm::runtime::LoraModule::ModuleType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kATTN_DENSEE", "tensorrt_llm::runtime::LoraModule::ModuleType::kATTN_DENSE"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_KE", "tensorrt_llm::runtime::LoraModule::ModuleType::kATTN_K"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_QE", "tensorrt_llm::runtime::LoraModule::ModuleType::kATTN_Q"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kATTN_QKVE", "tensorrt_llm::runtime::LoraModule::ModuleType::kATTN_QKV"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_VE", "tensorrt_llm::runtime::LoraModule::ModuleType::kATTN_V"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType17kCROSS_ATTN_DENSEE", "tensorrt_llm::runtime::LoraModule::ModuleType::kCROSS_ATTN_DENSE"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_KE", "tensorrt_llm::runtime::LoraModule::ModuleType::kCROSS_ATTN_K"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_QE", "tensorrt_llm::runtime::LoraModule::ModuleType::kCROSS_ATTN_Q"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType15kCROSS_ATTN_QKVE", "tensorrt_llm::runtime::LoraModule::ModuleType::kCROSS_ATTN_QKV"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_VE", "tensorrt_llm::runtime::LoraModule::ModuleType::kCROSS_ATTN_V"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType8kINVALIDE", "tensorrt_llm::runtime::LoraModule::ModuleType::kINVALID"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMLP_4H_TO_HE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMLP_4H_TO_H"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kMLP_GATEE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMLP_GATE"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMLP_H_TO_4HE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMLP_H_TO_4H"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kMLP_ROUTERE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMLP_ROUTER"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMOE_4H_TO_HE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMOE_4H_TO_H"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kMOE_GATEE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMOE_GATE"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMOE_H_TO_4HE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMOE_H_TO_4H"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kMOE_ROUTERE", "tensorrt_llm::runtime::LoraModule::ModuleType::kMOE_ROUTER"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule9TensorPtrE", "tensorrt_llm::runtime::LoraModule::TensorPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::attentionHeadSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::hiddenSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::loraModuleNames"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::mlpHiddenSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::numAttentionHeads"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::numExperts"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::numKvAttentionHeads"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::createLoraModules::tpSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18flattenedInOutSizeE10SizeType32", "tensorrt_llm::runtime::LoraModule::flattenedInOutSize"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18flattenedInOutSizeE10SizeType32", "tensorrt_llm::runtime::LoraModule::flattenedInOutSize::adapterSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule5inDimEv", "tensorrt_llm::runtime::LoraModule::inDim"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule10inDimFirstEv", "tensorrt_llm::runtime::LoraModule::inDimFirst"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule6inSizeE10SizeType32", "tensorrt_llm::runtime::LoraModule::inSize"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule6inSizeE10SizeType32", "tensorrt_llm::runtime::LoraModule::inSize::adapterSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12inTpSplitDimEv", "tensorrt_llm::runtime::LoraModule::inTpSplitDim"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18localInAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInAdapterSize"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18localInAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInAdapterSize::adapterSize"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18localInAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInAdapterSize::tpSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule10localInDimE10SizeType32", "tensorrt_llm::runtime::LoraModule::localInDim"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule10localInDimE10SizeType32", "tensorrt_llm::runtime::LoraModule::localInDim::tpSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localInOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInOutSize"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localInOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInOutSize::adapterSize"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localInOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInOutSize::tpSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localInSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInSize"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localInSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInSize::adapterSize"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localInSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localInSize::tpSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule19localOutAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutAdapterSize"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule19localOutAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutAdapterSize::adapterSize"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule19localOutAdapterSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutAdapterSize::tpSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localOutDimE10SizeType32", "tensorrt_llm::runtime::LoraModule::localOutDim"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localOutDimE10SizeType32", "tensorrt_llm::runtime::LoraModule::localOutDim::tpSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12localOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutSize"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12localOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutSize::adapterSize"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12localOutSizeE10SizeType3210SizeType32", "tensorrt_llm::runtime::LoraModule::localOutSize::tpSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule6mInDimE", "tensorrt_llm::runtime::LoraModule::mInDim"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule11mInDimFirstE", "tensorrt_llm::runtime::LoraModule::mInDimFirst"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule13mInTpSplitDimE", "tensorrt_llm::runtime::LoraModule::mInTpSplitDim"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule7mOutDimE", "tensorrt_llm::runtime::LoraModule::mOutDim"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12mOutDimFirstE", "tensorrt_llm::runtime::LoraModule::mOutDimFirst"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule14mOutTpSplitDimE", "tensorrt_llm::runtime::LoraModule::mOutTpSplitDim"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule5mTypeE", "tensorrt_llm::runtime::LoraModule::mType"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule4nameEv", "tensorrt_llm::runtime::LoraModule::name"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModuleaSERK10LoraModule", "tensorrt_llm::runtime::LoraModule::operator="], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModuleaSERK10LoraModule", "tensorrt_llm::runtime::LoraModule::operator=::o"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule6outDimEv", "tensorrt_llm::runtime::LoraModule::outDim"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11outDimFirstEv", "tensorrt_llm::runtime::LoraModule::outDimFirst"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule7outSizeE10SizeType32", "tensorrt_llm::runtime::LoraModule::outSize"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule7outSizeE10SizeType32", "tensorrt_llm::runtime::LoraModule::outSize::adapterSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule13outTpSplitDimEv", "tensorrt_llm::runtime::LoraModule::outTpSplitDim"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10ModuleType", "tensorrt_llm::runtime::LoraModule::toModuleName"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10SizeType32", "tensorrt_llm::runtime::LoraModule::toModuleName"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10SizeType32", "tensorrt_llm::runtime::LoraModule::toModuleName::id"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10ModuleType", "tensorrt_llm::runtime::LoraModule::toModuleName::t"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleTypeERKNSt11string_viewE", "tensorrt_llm::runtime::LoraModule::toModuleType"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleTypeERKNSt11string_viewE", "tensorrt_llm::runtime::LoraModule::toModuleType::name"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule5valueEv", "tensorrt_llm::runtime::LoraModule::value"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14LoraTaskIdTypeE", "tensorrt_llm::runtime::LoraTaskIdType"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModuleE", "tensorrt_llm::runtime::MedusaModule"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule13MedusaChoicesE", "tensorrt_llm::runtime::MedusaModule::MedusaChoices"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::MedusaModule::MedusaModule"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleEv", "tensorrt_llm::runtime::MedusaModule::MedusaModule"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::MedusaModule::MedusaModule::maxAcceptedTokens"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleE10SizeType3210SizeType32", "tensorrt_llm::runtime::MedusaModule::MedusaModule::maxDraftTokens"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule14MedusaTreeNodeE", "tensorrt_llm::runtime::MedusaModule::MedusaTreeNode"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule14MedusaTreeNode18childLinearIndicesE", "tensorrt_llm::runtime::MedusaModule::MedusaTreeNode::childLinearIndices"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule14MedusaTreeNode5depthE", "tensorrt_llm::runtime::MedusaModule::MedusaTreeNode::depth"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule14MedusaTreeNode9linearIdxE", "tensorrt_llm::runtime::MedusaModule::MedusaTreeNode::linearIdx"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule14MedusaTreeNode6nodeIdE", "tensorrt_llm::runtime::MedusaModule::MedusaTreeNode::nodeId"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule14MedusaTreeNode15parentLinearIdxE", "tensorrt_llm::runtime::MedusaModule::MedusaTreeNode::parentLinearIdx"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule22PREFIX_CHUNK_SIZE_BITSE", "tensorrt_llm::runtime::MedusaModule::PREFIX_CHUNK_SIZE_BITS"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule16PREFIX_MAX_VALUEE", "tensorrt_llm::runtime::MedusaModule::PREFIX_MAX_VALUE"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule6PrefixE", "tensorrt_llm::runtime::MedusaModule::Prefix"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule9TensorPtrE", "tensorrt_llm::runtime::MedusaModule::TensorPtr"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule19computePathsAndMaskERKNSt6vectorI14MedusaTreeNodeEER9TensorPtrR9TensorPtr", "tensorrt_llm::runtime::MedusaModule::computePathsAndMask"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule19computePathsAndMaskERKNSt6vectorI14MedusaTreeNodeEER9TensorPtrR9TensorPtr", "tensorrt_llm::runtime::MedusaModule::computePathsAndMask::packedMask"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule19computePathsAndMaskERKNSt6vectorI14MedusaTreeNodeEER9TensorPtrR9TensorPtr", "tensorrt_llm::runtime::MedusaModule::computePathsAndMask::paths"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule19computePathsAndMaskERKNSt6vectorI14MedusaTreeNodeEER9TensorPtrR9TensorPtr", "tensorrt_llm::runtime::MedusaModule::computePathsAndMask::tree"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule13computePrefixERKNSt6vectorI10SizeType32EE10SizeType32", "tensorrt_llm::runtime::MedusaModule::computePrefix"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule13computePrefixERKNSt6vectorI10SizeType32EE10SizeType32", "tensorrt_llm::runtime::MedusaModule::computePrefix::len"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule13computePrefixERKNSt6vectorI10SizeType32EE10SizeType32", "tensorrt_llm::runtime::MedusaModule::computePrefix::vec"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule14copyPackedMaskER9TensorPtr10SizeType3210SizeType32", "tensorrt_llm::runtime::MedusaModule::copyPackedMask"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule14copyPackedMaskER9TensorPtr10SizeType3210SizeType32", "tensorrt_llm::runtime::MedusaModule::copyPackedMask::dstIdx"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule14copyPackedMaskER9TensorPtr10SizeType3210SizeType32", "tensorrt_llm::runtime::MedusaModule::copyPackedMask::mask"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule14copyPackedMaskER9TensorPtr10SizeType3210SizeType32", "tensorrt_llm::runtime::MedusaModule::copyPackedMask::srcIdx"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule11dumpChoicesERK13MedusaChoicesRKNSt6vectorI10SizeType32EE", "tensorrt_llm::runtime::MedusaModule::dumpChoices"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule11dumpChoicesERK13MedusaChoicesRKNSt6vectorI10SizeType32EE", "tensorrt_llm::runtime::MedusaModule::dumpChoices::choices"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule11dumpChoicesERK13MedusaChoicesRKNSt6vectorI10SizeType32EE", "tensorrt_llm::runtime::MedusaModule::dumpChoices::indices"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule16getMedusaChoicesEv", "tensorrt_llm::runtime::MedusaModule::getMedusaChoices"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule28initMedusaTensorsFromChoicesERK13MedusaChoicesRNSt6vectorI10SizeType32EER9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR10SizeType32", "tensorrt_llm::runtime::MedusaModule::initMedusaTensorsFromChoices"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule28initMedusaTensorsFromChoicesERK13MedusaChoicesRNSt6vectorI10SizeType32EER9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR10SizeType32", "tensorrt_llm::runtime::MedusaModule::initMedusaTensorsFromChoices::choices"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule28initMedusaTensorsFromChoicesERK13MedusaChoicesRNSt6vectorI10SizeType32EER9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR10SizeType32", "tensorrt_llm::runtime::MedusaModule::initMedusaTensorsFromChoices::generationInputLengths"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule28initMedusaTensorsFromChoicesERK13MedusaChoicesRNSt6vectorI10SizeType32EER9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR10SizeType32", "tensorrt_llm::runtime::MedusaModule::initMedusaTensorsFromChoices::packedMask"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule28initMedusaTensorsFromChoicesERK13MedusaChoicesRNSt6vectorI10SizeType32EER9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR10SizeType32", "tensorrt_llm::runtime::MedusaModule::initMedusaTensorsFromChoices::paths"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule28initMedusaTensorsFromChoicesERK13MedusaChoicesRNSt6vectorI10SizeType32EER9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR10SizeType32", "tensorrt_llm::runtime::MedusaModule::initMedusaTensorsFromChoices::positionOffsets"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule28initMedusaTensorsFromChoicesERK13MedusaChoicesRNSt6vectorI10SizeType32EER9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR10SizeType32", "tensorrt_llm::runtime::MedusaModule::initMedusaTensorsFromChoices::topKs"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule28initMedusaTensorsFromChoicesERK13MedusaChoicesRNSt6vectorI10SizeType32EER9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR10SizeType32", "tensorrt_llm::runtime::MedusaModule::initMedusaTensorsFromChoices::totalPaths"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule28initMedusaTensorsFromChoicesERK13MedusaChoicesRNSt6vectorI10SizeType32EER9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR10SizeType32", "tensorrt_llm::runtime::MedusaModule::initMedusaTensorsFromChoices::treeIds"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule21mDefaultMedusaChoicesE", "tensorrt_llm::runtime::MedusaModule::mDefaultMedusaChoices"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule16setOnePackedMaskER9TensorPtr10SizeType3210SizeType32", "tensorrt_llm::runtime::MedusaModule::setOnePackedMask"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule16setOnePackedMaskER9TensorPtr10SizeType3210SizeType32", "tensorrt_llm::runtime::MedusaModule::setOnePackedMask::col"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule16setOnePackedMaskER9TensorPtr10SizeType3210SizeType32", "tensorrt_llm::runtime::MedusaModule::setOnePackedMask::mask"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule16setOnePackedMaskER9TensorPtr10SizeType3210SizeType32", "tensorrt_llm::runtime::MedusaModule::setOnePackedMask::row"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCountersE", "tensorrt_llm::runtime::MemoryCounters"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE", "tensorrt_llm::runtime::MemoryCounters::DiffType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters14MemoryCountersEv", "tensorrt_llm::runtime::MemoryCounters::MemoryCounters"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10SizeType32E", "tensorrt_llm::runtime::MemoryCounters::SizeType32"], [1, 5, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters8allocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8allocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate"], [1, 8, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters8allocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate::T"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8allocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate::memoryType"], [1, 6, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters8allocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate::size"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8allocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::allocate::size"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE10SizeType32i", "tensorrt_llm::runtime::MemoryCounters::bytesToString"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8DiffTypei", "tensorrt_llm::runtime::MemoryCounters::bytesToString"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE10SizeType32i", "tensorrt_llm::runtime::MemoryCounters::bytesToString::bytes"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8DiffTypei", "tensorrt_llm::runtime::MemoryCounters::bytesToString::bytes"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE10SizeType32i", "tensorrt_llm::runtime::MemoryCounters::bytesToString::precision"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8DiffTypei", "tensorrt_llm::runtime::MemoryCounters::bytesToString::precision"], [1, 5, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters10deallocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10deallocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate"], [1, 8, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters10deallocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate::T"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10deallocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate::memoryType"], [1, 6, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters10deallocateEv10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate::size"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10deallocateE10MemoryType10SizeType32", "tensorrt_llm::runtime::MemoryCounters::deallocate::size"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getCpuEv", "tensorrt_llm::runtime::MemoryCounters::getCpu"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getCpuDiffEv", "tensorrt_llm::runtime::MemoryCounters::getCpuDiff"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getGpuEv", "tensorrt_llm::runtime::MemoryCounters::getGpu"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getGpuDiffEv", "tensorrt_llm::runtime::MemoryCounters::getGpuDiff"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11getInstanceEv", "tensorrt_llm::runtime::MemoryCounters::getInstance"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters9getPinnedEv", "tensorrt_llm::runtime::MemoryCounters::getPinned"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters13getPinnedDiffEv", "tensorrt_llm::runtime::MemoryCounters::getPinnedDiff"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters13getPinnedPoolEv", "tensorrt_llm::runtime::MemoryCounters::getPinnedPool"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters17getPinnedPoolDiffEv", "tensorrt_llm::runtime::MemoryCounters::getPinnedPoolDiff"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getUVMEv", "tensorrt_llm::runtime::MemoryCounters::getUVM"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getUVMDiffEv", "tensorrt_llm::runtime::MemoryCounters::getUVMDiff"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mCpuE", "tensorrt_llm::runtime::MemoryCounters::mCpu"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mCpuDiffE", "tensorrt_llm::runtime::MemoryCounters::mCpuDiff"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mGpuE", "tensorrt_llm::runtime::MemoryCounters::mGpu"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mGpuDiffE", "tensorrt_llm::runtime::MemoryCounters::mGpuDiff"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters7mPinnedE", "tensorrt_llm::runtime::MemoryCounters::mPinned"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11mPinnedDiffE", "tensorrt_llm::runtime::MemoryCounters::mPinnedDiff"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11mPinnedPoolE", "tensorrt_llm::runtime::MemoryCounters::mPinnedPool"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters15mPinnedPoolDiffE", "tensorrt_llm::runtime::MemoryCounters::mPinnedPoolDiff"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mUVME", "tensorrt_llm::runtime::MemoryCounters::mUVM"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mUVMDiffE", "tensorrt_llm::runtime::MemoryCounters::mUVMDiff"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters8toStringEv", "tensorrt_llm::runtime::MemoryCounters::toString"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryTypeE", "tensorrt_llm::runtime::MemoryType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kCPUE", "tensorrt_llm::runtime::MemoryType::kCPU"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kGPUE", "tensorrt_llm::runtime::MemoryType::kGPU"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryType7kPINNEDE", "tensorrt_llm::runtime::MemoryType::kPINNED"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryType11kPINNEDPOOLE", "tensorrt_llm::runtime::MemoryType::kPINNEDPOOL"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kUVME", "tensorrt_llm::runtime::MemoryType::kUVM"], [1, 4, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime16MemoryTypeStringE", "tensorrt_llm::runtime::MemoryTypeString"], [1, 8, 1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime16MemoryTypeStringE", "tensorrt_llm::runtime::MemoryTypeString::T"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEEE", "tensorrt_llm::runtime::MemoryTypeString&lt;MemoryType::kCPU&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEE5valueE", "tensorrt_llm::runtime::MemoryTypeString&lt;MemoryType::kCPU&gt;::value"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEEE", "tensorrt_llm::runtime::MemoryTypeString&lt;MemoryType::kGPU&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEE5valueE", "tensorrt_llm::runtime::MemoryTypeString&lt;MemoryType::kGPU&gt;::value"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEEE", "tensorrt_llm::runtime::MemoryTypeString&lt;MemoryType::kPINNED&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEE5valueE", "tensorrt_llm::runtime::MemoryTypeString&lt;MemoryType::kPINNED&gt;::value"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType11kPINNEDPOOLEEE", "tensorrt_llm::runtime::MemoryTypeString&lt;MemoryType::kPINNEDPOOL&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType11kPINNEDPOOLEE5valueE", "tensorrt_llm::runtime::MemoryTypeString&lt;MemoryType::kPINNEDPOOL&gt;::value"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kUVMEEE", "tensorrt_llm::runtime::MemoryTypeString&lt;MemoryType::kUVM&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kUVMEE5valueE", "tensorrt_llm::runtime::MemoryTypeString&lt;MemoryType::kUVM&gt;::value"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfigE", "tensorrt_llm::runtime::ModelConfig"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheTypeE", "tensorrt_llm::runtime::ModelConfig::KVCacheType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType11kCONTINUOUSE", "tensorrt_llm::runtime::ModelConfig::KVCacheType::kCONTINUOUS"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType9kDISABLEDE", "tensorrt_llm::runtime::ModelConfig::KVCacheType::kDISABLED"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType6kPAGEDE", "tensorrt_llm::runtime::ModelConfig::KVCacheType::kPAGED"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21KVCacheTypeFromStringENSt6stringE", "tensorrt_llm::runtime::ModelConfig::KVCacheTypeFromString"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21KVCacheTypeFromStringENSt6stringE", "tensorrt_llm::runtime::ModelConfig::KVCacheTypeFromString::value"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerTypeE", "tensorrt_llm::runtime::ModelConfig::LayerType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType10kATTENTIONE", "tensorrt_llm::runtime::ModelConfig::LayerType::kATTENTION"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType10kRECURRENTE", "tensorrt_llm::runtime::ModelConfig::LayerType::kRECURRENT"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsTypeE", "tensorrt_llm::runtime::ModelConfig::ManageWeightsType"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsType9kDisabledE", "tensorrt_llm::runtime::ModelConfig::ManageWeightsType::kDisabled"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsType8kEnabledE", "tensorrt_llm::runtime::ModelConfig::ManageWeightsType::kEnabled"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::dtype"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::hiddenSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::nbAttentionLayers"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::nbHeads"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::nbRnnLayers"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::ModelConfig::vocabSize"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariantE", "tensorrt_llm::runtime::ModelConfig::ModelVariant"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant8kChatGlmE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kChatGlm"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant7kEncDecE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kEncDec"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant4kGlmE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kGlm"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant4kGptE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kGpt"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant6kMambaE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kMamba"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant15kRecurrentGemmaE", "tensorrt_llm::runtime::ModelConfig::ModelVariant::kRecurrentGemma"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfigE", "tensorrt_llm::runtime::ModelConfig::RnnConfig"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig10convKernelE", "tensorrt_llm::runtime::ModelConfig::RnnConfig::convKernel"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig14rnnConvDimSizeE", "tensorrt_llm::runtime::ModelConfig::RnnConfig::rnnConvDimSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig11rnnHeadSizeE", "tensorrt_llm::runtime::ModelConfig::RnnConfig::rnnHeadSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig13rnnHiddenSizeE", "tensorrt_llm::runtime::ModelConfig::RnnConfig::rnnHiddenSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig9stateSizeE", "tensorrt_llm::runtime::ModelConfig::RnnConfig::stateSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20computeContextLogitsEb", "tensorrt_llm::runtime::ModelConfig::computeContextLogits"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20computeContextLogitsEv", "tensorrt_llm::runtime::ModelConfig::computeContextLogits"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20computeContextLogitsEb", "tensorrt_llm::runtime::ModelConfig::computeContextLogits::computeContextLogits"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23computeGenerationLogitsEb", "tensorrt_llm::runtime::ModelConfig::computeGenerationLogits"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig23computeGenerationLogitsEv", "tensorrt_llm::runtime::ModelConfig::computeGenerationLogits"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23computeGenerationLogitsEb", "tensorrt_llm::runtime::ModelConfig::computeGenerationLogits::computeGenerationLogits"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getContextFMHAEv", "tensorrt_llm::runtime::ModelConfig::getContextFMHA"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig11getDataTypeEv", "tensorrt_llm::runtime::ModelConfig::getDataType"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getEncoderHiddenSizeEv", "tensorrt_llm::runtime::ModelConfig::getEncoderHiddenSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getHiddenSizeEv", "tensorrt_llm::runtime::ModelConfig::getHiddenSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getKVCacheTypeEv", "tensorrt_llm::runtime::ModelConfig::getKVCacheType"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getKvDataTypeEv", "tensorrt_llm::runtime::ModelConfig::getKvDataType"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getLayerTypesEv", "tensorrt_llm::runtime::ModelConfig::getLayerTypes"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getLogitsDtypeEv", "tensorrt_llm::runtime::ModelConfig::getLogitsDtype"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getLoraModulesEv", "tensorrt_llm::runtime::ModelConfig::getLoraModules"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getManageWeightsTypeEv", "tensorrt_llm::runtime::ModelConfig::getManageWeightsType"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxBatchSizeEv", "tensorrt_llm::runtime::ModelConfig::getMaxBatchSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxBeamWidthEv", "tensorrt_llm::runtime::ModelConfig::getMaxBeamWidth"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig25getMaxDecodingDraftTokensEv", "tensorrt_llm::runtime::ModelConfig::getMaxDecodingDraftTokens"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getMaxDecodingTokensEv", "tensorrt_llm::runtime::ModelConfig::getMaxDecodingTokens"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16getMaxEncoderLenEv", "tensorrt_llm::runtime::ModelConfig::getMaxEncoderLen"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getMaxInputLenEv", "tensorrt_llm::runtime::ModelConfig::getMaxInputLen"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getMaxLoraRankEv", "tensorrt_llm::runtime::ModelConfig::getMaxLoraRank"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxNumTokensEv", "tensorrt_llm::runtime::ModelConfig::getMaxNumTokens"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig30getMaxPromptEmbeddingTableSizeEv", "tensorrt_llm::runtime::ModelConfig::getMaxPromptEmbeddingTableSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17getMaxSequenceLenEv", "tensorrt_llm::runtime::ModelConfig::getMaxSequenceLen"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16getMlpHiddenSizeEv", "tensorrt_llm::runtime::ModelConfig::getMlpHiddenSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getModelNameEv", "tensorrt_llm::runtime::ModelConfig::getModelName"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getModelVariantEv", "tensorrt_llm::runtime::ModelConfig::getModelVariant"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getNbAttentionLayersE10SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbAttentionLayers"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getNbAttentionLayersE10SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbAttentionLayers::pipelineParallelism"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig10getNbHeadsEv", "tensorrt_llm::runtime::ModelConfig::getNbHeads"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getNbKvHeadsEv", "tensorrt_llm::runtime::ModelConfig::getNbKvHeads"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getNbRnnLayersE10SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbRnnLayers"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getNbRnnLayersE10SizeType32", "tensorrt_llm::runtime::ModelConfig::getNbRnnLayers::pipelineParallelism"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig25getOptProfilesSplitPointsEv", "tensorrt_llm::runtime::ModelConfig::getOptProfilesSplitPoints"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig19getPagedContextFMHAEv", "tensorrt_llm::runtime::ModelConfig::getPagedContextFMHA"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getQuantModeEv", "tensorrt_llm::runtime::ModelConfig::getQuantMode"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getRnnConfigEv", "tensorrt_llm::runtime::ModelConfig::getRnnConfig"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getSizePerHeadEv", "tensorrt_llm::runtime::ModelConfig::getSizePerHead"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig26getSpeculativeDecodingModeEv", "tensorrt_llm::runtime::ModelConfig::getSpeculativeDecodingMode"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig28getSpeculativeDecodingModuleEv", "tensorrt_llm::runtime::ModelConfig::getSpeculativeDecodingModule"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig31getSpeculativeDecodingModulePtrEv", "tensorrt_llm::runtime::ModelConfig::getSpeculativeDecodingModulePtr"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig31getSpeculativeDecodingModulePtrEv", "tensorrt_llm::runtime::ModelConfig::getSpeculativeDecodingModulePtr"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17getTokensPerBlockEv", "tensorrt_llm::runtime::ModelConfig::getTokensPerBlock"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getVocabSizeEv", "tensorrt_llm::runtime::ModelConfig::getVocabSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getVocabSizePaddedE10SizeType32", "tensorrt_llm::runtime::ModelConfig::getVocabSizePadded"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getVocabSizePaddedE10SizeType32", "tensorrt_llm::runtime::ModelConfig::getVocabSizePadded::worldSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12hasRnnConfigEv", "tensorrt_llm::runtime::ModelConfig::hasRnnConfig"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig28hasSpeculativeDecodingModuleEv", "tensorrt_llm::runtime::ModelConfig::hasSpeculativeDecodingModule"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig19isContinuousKVCacheEv", "tensorrt_llm::runtime::ModelConfig::isContinuousKVCache"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16isKVCacheEnabledEv", "tensorrt_llm::runtime::ModelConfig::isKVCacheEnabled"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14isPagedKVCacheEv", "tensorrt_llm::runtime::ModelConfig::isPagedKVCache"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig10isRnnBasedEv", "tensorrt_llm::runtime::ModelConfig::isRnnBased"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18isTransformerBasedEv", "tensorrt_llm::runtime::ModelConfig::isTransformerBased"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26kOPT_PROFILES_SPLIT_POINTSE", "tensorrt_llm::runtime::ModelConfig::kOPT_PROFILES_SPLIT_POINTS"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mComputeContextLogitsE", "tensorrt_llm::runtime::ModelConfig::mComputeContextLogits"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24mComputeGenerationLogitsE", "tensorrt_llm::runtime::ModelConfig::mComputeGenerationLogits"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mContextFMHAE", "tensorrt_llm::runtime::ModelConfig::mContextFMHA"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9mDataTypeE", "tensorrt_llm::runtime::ModelConfig::mDataType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mEncoderHiddenSizeE", "tensorrt_llm::runtime::ModelConfig::mEncoderHiddenSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mHiddenSizeE", "tensorrt_llm::runtime::ModelConfig::mHiddenSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mInputPackedE", "tensorrt_llm::runtime::ModelConfig::mInputPacked"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mKVCacheTypeE", "tensorrt_llm::runtime::ModelConfig::mKVCacheType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mLayerTypesE", "tensorrt_llm::runtime::ModelConfig::mLayerTypes"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mLogitsDtypeE", "tensorrt_llm::runtime::ModelConfig::mLogitsDtype"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mLoraModulesE", "tensorrt_llm::runtime::ModelConfig::mLoraModules"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mManageWeightsTypeE", "tensorrt_llm::runtime::ModelConfig::mManageWeightsType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxBatchSizeE", "tensorrt_llm::runtime::ModelConfig::mMaxBatchSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxBeamWidthE", "tensorrt_llm::runtime::ModelConfig::mMaxBeamWidth"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mMaxEncoderLenE", "tensorrt_llm::runtime::ModelConfig::mMaxEncoderLen"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mMaxInputLenE", "tensorrt_llm::runtime::ModelConfig::mMaxInputLen"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mMaxLoraRankE", "tensorrt_llm::runtime::ModelConfig::mMaxLoraRank"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxNumTokensE", "tensorrt_llm::runtime::ModelConfig::mMaxNumTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28mMaxPromptEmbeddingTableSizeE", "tensorrt_llm::runtime::ModelConfig::mMaxPromptEmbeddingTableSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15mMaxSequenceLenE", "tensorrt_llm::runtime::ModelConfig::mMaxSequenceLen"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mMlpHiddenSizeE", "tensorrt_llm::runtime::ModelConfig::mMlpHiddenSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mModelNameE", "tensorrt_llm::runtime::ModelConfig::mModelName"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mModelVariantE", "tensorrt_llm::runtime::ModelConfig::mModelVariant"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mNbAttentionLayersE", "tensorrt_llm::runtime::ModelConfig::mNbAttentionLayers"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig8mNbHeadsE", "tensorrt_llm::runtime::ModelConfig::mNbHeads"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mNbKvHeadsE", "tensorrt_llm::runtime::ModelConfig::mNbKvHeads"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mNbRnnLayersE", "tensorrt_llm::runtime::ModelConfig::mNbRnnLayers"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17mPagedContextFMHAE", "tensorrt_llm::runtime::ModelConfig::mPagedContextFMHA"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mPagedStateE", "tensorrt_llm::runtime::ModelConfig::mPagedState"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mQuantModeE", "tensorrt_llm::runtime::ModelConfig::mQuantMode"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mRnnConfigE", "tensorrt_llm::runtime::ModelConfig::mRnnConfig"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mSizePerHeadE", "tensorrt_llm::runtime::ModelConfig::mSizePerHead"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24mSpeculativeDecodingModeE", "tensorrt_llm::runtime::ModelConfig::mSpeculativeDecodingMode"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26mSpeculativeDecodingModuleE", "tensorrt_llm::runtime::ModelConfig::mSpeculativeDecodingModule"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15mTokensPerBlockE", "tensorrt_llm::runtime::ModelConfig::mTokensPerBlock"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mUseCrossAttentionE", "tensorrt_llm::runtime::ModelConfig::mUseCrossAttention"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22mUseGptAttentionPluginE", "tensorrt_llm::runtime::ModelConfig::mUseGptAttentionPlugin"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mUseLoraPluginE", "tensorrt_llm::runtime::ModelConfig::mUseLoraPlugin"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mUseMambaConv1dPluginE", "tensorrt_llm::runtime::ModelConfig::mUseMambaConv1dPlugin"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mUsePositionEmbeddingE", "tensorrt_llm::runtime::ModelConfig::mUsePositionEmbedding"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mUseShapeInferenceE", "tensorrt_llm::runtime::ModelConfig::mUseShapeInference"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22mUseTokenTypeEmbeddingE", "tensorrt_llm::runtime::ModelConfig::mUseTokenTypeEmbedding"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig7mUseXQAE", "tensorrt_llm::runtime::ModelConfig::mUseXQA"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mVocabSizeE", "tensorrt_llm::runtime::ModelConfig::mVocabSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setContextFMHAEb", "tensorrt_llm::runtime::ModelConfig::setContextFMHA"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setContextFMHAEb", "tensorrt_llm::runtime::ModelConfig::setContextFMHA::contextFMHA"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setEncoderHiddenSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setEncoderHiddenSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setEncoderHiddenSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setEncoderHiddenSize::encoderHiddenSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setKVCacheTypeE11KVCacheType", "tensorrt_llm::runtime::ModelConfig::setKVCacheType"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setKVCacheTypeE11KVCacheType", "tensorrt_llm::runtime::ModelConfig::setKVCacheType::kvCacheType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13setLayerTypesERKNSt6vectorI9LayerTypeEE", "tensorrt_llm::runtime::ModelConfig::setLayerTypes"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13setLayerTypesERKNSt6vectorI9LayerTypeEE", "tensorrt_llm::runtime::ModelConfig::setLayerTypes::layerTypes"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLogitsDtypeEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::setLogitsDtype"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLogitsDtypeEN8nvinfer18DataTypeE", "tensorrt_llm::runtime::ModelConfig::setLogitsDtype::inputDtype"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLoraModulesERKNSt6vectorI10LoraModuleEE", "tensorrt_llm::runtime::ModelConfig::setLoraModules"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLoraModulesERKNSt6vectorI10LoraModuleEE", "tensorrt_llm::runtime::ModelConfig::setLoraModules::loraModules"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setManageWeightsTypeEK17ManageWeightsType", "tensorrt_llm::runtime::ModelConfig::setManageWeightsType"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setManageWeightsTypeEK17ManageWeightsType", "tensorrt_llm::runtime::ModelConfig::setManageWeightsType::manageWeightType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBatchSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxBatchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBatchSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxBatchSize::maxBatchSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBeamWidthE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxBeamWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBeamWidthE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxBeamWidth::maxBeamWidth"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMaxEncoderLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxEncoderLen"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMaxEncoderLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxEncoderLen::maxEncoderLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxInputLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxInputLen"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxInputLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxInputLen::maxInputLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxLoraRankE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxLoraRank"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxLoraRankE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxLoraRank::maxLoraRank"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxNumTokensENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setMaxNumTokens"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxNumTokensENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::ModelConfig::setMaxNumTokens::maxNumTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig30setMaxPromptEmbeddingTableSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxPromptEmbeddingTableSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig30setMaxPromptEmbeddingTableSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxPromptEmbeddingTableSize::maxPromptEmbeddingTableSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setMaxSequenceLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxSequenceLen"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setMaxSequenceLenE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMaxSequenceLen::maxSequenceLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMlpHiddenSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMlpHiddenSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMlpHiddenSizeE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setMlpHiddenSize::mlpHiddenSize"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setModelNameERKNSt6stringE", "tensorrt_llm::runtime::ModelConfig::setModelName"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setModelNameERKNSt6stringE", "tensorrt_llm::runtime::ModelConfig::setModelName::modelName"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setModelVariantE12ModelVariant", "tensorrt_llm::runtime::ModelConfig::setModelVariant"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setModelVariantE12ModelVariant", "tensorrt_llm::runtime::ModelConfig::setModelVariant::modelVariant"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setNbKvHeadsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setNbKvHeads"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setNbKvHeadsE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setNbKvHeads::nbKvHeads"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig19setPagedContextFMHAEb", "tensorrt_llm::runtime::ModelConfig::setPagedContextFMHA"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig19setPagedContextFMHAEb", "tensorrt_llm::runtime::ModelConfig::setPagedContextFMHA::pagedContextFMHA"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setQuantModeEN6common9QuantModeE", "tensorrt_llm::runtime::ModelConfig::setQuantMode"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setQuantModeEN6common9QuantModeE", "tensorrt_llm::runtime::ModelConfig::setQuantMode::QuantMode"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setRnnConfigERK9RnnConfig", "tensorrt_llm::runtime::ModelConfig::setRnnConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setRnnConfigERK9RnnConfig", "tensorrt_llm::runtime::ModelConfig::setRnnConfig::rnnConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setSizePerHeadE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setSizePerHead"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setSizePerHeadE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setSizePerHead::sizePerHead"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26setSpeculativeDecodingModeE23SpeculativeDecodingMode", "tensorrt_llm::runtime::ModelConfig::setSpeculativeDecodingMode"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26setSpeculativeDecodingModeE23SpeculativeDecodingMode", "tensorrt_llm::runtime::ModelConfig::setSpeculativeDecodingMode::mode"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28setSpeculativeDecodingModuleERKNSt10shared_ptrI25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::ModelConfig::setSpeculativeDecodingModule"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28setSpeculativeDecodingModuleERKNSt10shared_ptrI25SpeculativeDecodingModuleEE", "tensorrt_llm::runtime::ModelConfig::setSpeculativeDecodingModule::speculativeDecodingModule"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setTokensPerBlockE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setTokensPerBlock"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setTokensPerBlockE10SizeType32", "tensorrt_llm::runtime::ModelConfig::setTokensPerBlock::TokensPerBlock"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseCrossAttentionEb", "tensorrt_llm::runtime::ModelConfig::setUseCrossAttention"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseCrossAttentionEb", "tensorrt_llm::runtime::ModelConfig::setUseCrossAttention::useCrossAttention"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23setUsePositionEmbeddingEb", "tensorrt_llm::runtime::ModelConfig::setUsePositionEmbedding"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23setUsePositionEmbeddingEb", "tensorrt_llm::runtime::ModelConfig::setUsePositionEmbedding::usePositionEmbedding"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseShapeInferenceEb", "tensorrt_llm::runtime::ModelConfig::setUseShapeInference"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseShapeInferenceEb", "tensorrt_llm::runtime::ModelConfig::setUseShapeInference::useShapeInference"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24setUseTokenTypeEmbeddingEb", "tensorrt_llm::runtime::ModelConfig::setUseTokenTypeEmbedding"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24setUseTokenTypeEmbeddingEb", "tensorrt_llm::runtime::ModelConfig::setUseTokenTypeEmbedding::useTokenTypeEmbedding"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig24supportsInflightBatchingEv", "tensorrt_llm::runtime::ModelConfig::supportsInflightBatching"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17useCrossAttentionEv", "tensorrt_llm::runtime::ModelConfig::useCrossAttention"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21useGptAttentionPluginEb", "tensorrt_llm::runtime::ModelConfig::useGptAttentionPlugin"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21useGptAttentionPluginEv", "tensorrt_llm::runtime::ModelConfig::useGptAttentionPlugin"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21useGptAttentionPluginEb", "tensorrt_llm::runtime::ModelConfig::useGptAttentionPlugin::useGptAttentionPlugin"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13useLoraPluginEb", "tensorrt_llm::runtime::ModelConfig::useLoraPlugin"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13useLoraPluginEv", "tensorrt_llm::runtime::ModelConfig::useLoraPlugin"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13useLoraPluginEb", "tensorrt_llm::runtime::ModelConfig::useLoraPlugin::useLoraPlugin"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20useMambaConv1dPluginEb", "tensorrt_llm::runtime::ModelConfig::useMambaConv1dPlugin"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20useMambaConv1dPluginEv", "tensorrt_llm::runtime::ModelConfig::useMambaConv1dPlugin"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20useMambaConv1dPluginEb", "tensorrt_llm::runtime::ModelConfig::useMambaConv1dPlugin::useMambaConv1dPlugin"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14usePackedInputEb", "tensorrt_llm::runtime::ModelConfig::usePackedInput"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14usePackedInputEv", "tensorrt_llm::runtime::ModelConfig::usePackedInput"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14usePackedInputEb", "tensorrt_llm::runtime::ModelConfig::usePackedInput::inputPacked"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13usePagedStateEb", "tensorrt_llm::runtime::ModelConfig::usePagedState"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13usePagedStateEv", "tensorrt_llm::runtime::ModelConfig::usePagedState"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13usePagedStateEb", "tensorrt_llm::runtime::ModelConfig::usePagedState::pagedState"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20usePositionEmbeddingEv", "tensorrt_llm::runtime::ModelConfig::usePositionEmbedding"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15usePromptTuningEv", "tensorrt_llm::runtime::ModelConfig::usePromptTuning"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17useShapeInferenceEv", "tensorrt_llm::runtime::ModelConfig::useShapeInference"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21useTokenTypeEmbeddingEv", "tensorrt_llm::runtime::ModelConfig::useTokenTypeEmbedding"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig6useXQAEb", "tensorrt_llm::runtime::ModelConfig::useXQA"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig6useXQAEv", "tensorrt_llm::runtime::ModelConfig::useXQA"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig6useXQAEb", "tensorrt_llm::runtime::ModelConfig::useXQA::useXQA"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4nameE", "tensorrt_llm::runtime::PhonyNameDueToError::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4nameE", "tensorrt_llm::runtime::PhonyNameDueToError::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4nameE", "tensorrt_llm::runtime::PhonyNameDueToError::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4nameE", "tensorrt_llm::runtime::PhonyNameDueToError::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4nameE", "tensorrt_llm::runtime::PhonyNameDueToError::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4nameE", "tensorrt_llm::runtime::PhonyNameDueToError::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4nameE", "tensorrt_llm::runtime::PhonyNameDueToError::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4nameE", "tensorrt_llm::runtime::PhonyNameDueToError::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4nameE", "tensorrt_llm::runtime::PhonyNameDueToError::name"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4sizeE", "tensorrt_llm::runtime::PhonyNameDueToError::size"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4sizeE", "tensorrt_llm::runtime::PhonyNameDueToError::size"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4sizeE", "tensorrt_llm::runtime::PhonyNameDueToError::size"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4sizeE", "tensorrt_llm::runtime::PhonyNameDueToError::size"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4sizeE", "tensorrt_llm::runtime::PhonyNameDueToError::size"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4sizeE", "tensorrt_llm::runtime::PhonyNameDueToError::size"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4sizeE", "tensorrt_llm::runtime::PhonyNameDueToError::size"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4sizeE", "tensorrt_llm::runtime::PhonyNameDueToError::size"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4sizeE", "tensorrt_llm::runtime::PhonyNameDueToError::size"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE", "tensorrt_llm::runtime::PhonyNameDueToError::type"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE", "tensorrt_llm::runtime::PhonyNameDueToError::type"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE", "tensorrt_llm::runtime::PhonyNameDueToError::type"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE", "tensorrt_llm::runtime::PhonyNameDueToError::type"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE", "tensorrt_llm::runtime::PhonyNameDueToError::type"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE", "tensorrt_llm::runtime::PhonyNameDueToError::type"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE", "tensorrt_llm::runtime::PhonyNameDueToError::type"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE", "tensorrt_llm::runtime::PhonyNameDueToError::type"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE", "tensorrt_llm::runtime::PhonyNameDueToError::type"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError5valueE", "tensorrt_llm::runtime::PhonyNameDueToError::value"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError5valueE", "tensorrt_llm::runtime::PhonyNameDueToError::value"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError5valueE", "tensorrt_llm::runtime::PhonyNameDueToError::value"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError5valueE", "tensorrt_llm::runtime::PhonyNameDueToError::value"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError5valueE", "tensorrt_llm::runtime::PhonyNameDueToError::value"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError5valueE", "tensorrt_llm::runtime::PhonyNameDueToError::value"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError5valueE", "tensorrt_llm::runtime::PhonyNameDueToError::value"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError5valueE", "tensorrt_llm::runtime::PhonyNameDueToError::value"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError5valueE", "tensorrt_llm::runtime::PhonyNameDueToError::value"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError5valueE", "tensorrt_llm::runtime::PhonyNameDueToError::value"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError5valueE", "tensorrt_llm::runtime::PhonyNameDueToError::value"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError5valueE", "tensorrt_llm::runtime::PhonyNameDueToError::value"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError5valueE", "tensorrt_llm::runtime::PhonyNameDueToError::value"], [1, 1, 1, "_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE", "tensorrt_llm::runtime::PointerElementType"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE", "tensorrt_llm::runtime::PointerElementType::T"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParamsE", "tensorrt_llm::runtime::PromptTuningParams"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::PromptTuningParams::PromptTuningParams"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::PromptTuningParams::PromptTuningParams::embeddingTable"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr", "tensorrt_llm::runtime::PromptTuningParams::PromptTuningParams::tasks"], [1, 6, 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, 5, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtrK10SizeType32K10SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtrK10SizeType32K10SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::batchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtrK10SizeType32K10SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::manager"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtrK10SizeType32K10SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::numContextRequests"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtrK10SizeType32K10SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::packedInput"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtrK10SizeType32K10SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::reqBeamWidths"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtrK10SizeType32K10SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::reqPromptLengths"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtrK10SizeType32K10SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb", "tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor::tasksHost"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngineE", "tensorrt_llm::runtime::RawEngine"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngineUt1_1E", "tensorrt_llm::runtime::RawEngine::[anonymous]"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type15AddressWithSizeE", "tensorrt_llm::runtime::RawEngine::AddressWithSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type8FilePathE", "tensorrt_llm::runtime::RawEngine::FilePath"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type10HostMemoryE", "tensorrt_llm::runtime::RawEngine::HostMemory"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineENSt10filesystem4pathE", "tensorrt_llm::runtime::RawEngine::RawEngine"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKN8nvinfer111IHostMemoryE", "tensorrt_llm::runtime::RawEngine::RawEngine"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKvNSt6size_tE", "tensorrt_llm::runtime::RawEngine::RawEngine"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKvNSt6size_tE", "tensorrt_llm::runtime::RawEngine::RawEngine::engineAddr"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKN8nvinfer111IHostMemoryE", "tensorrt_llm::runtime::RawEngine::RawEngine::engineBuffer"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineENSt10filesystem4pathE", "tensorrt_llm::runtime::RawEngine::RawEngine::enginePath"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKvNSt6size_tE", "tensorrt_llm::runtime::RawEngine::RawEngine::engineSize"], [1, 2, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4TypeE", "tensorrt_llm::runtime::RawEngine::Type"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type15AddressWithSizeE", "tensorrt_llm::runtime::RawEngine::Type::AddressWithSize"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type8FilePathE", "tensorrt_llm::runtime::RawEngine::Type::FilePath"], [1, 3, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type10HostMemoryE", "tensorrt_llm::runtime::RawEngine::Type::HostMemory"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine10getAddressEv", "tensorrt_llm::runtime::RawEngine::getAddress"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine13getHostMemoryEv", "tensorrt_llm::runtime::RawEngine::getHostMemory"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine23getManagedWeightsMapOptEv", "tensorrt_llm::runtime::RawEngine::getManagedWeightsMapOpt"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getPathEv", "tensorrt_llm::runtime::RawEngine::getPath"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine10getPathOptEv", "tensorrt_llm::runtime::RawEngine::getPathOpt"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getSizeEv", "tensorrt_llm::runtime::RawEngine::getSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getTypeEv", "tensorrt_llm::runtime::RawEngine::getType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEngineAddrE", "tensorrt_llm::runtime::RawEngine::mEngineAddr"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine13mEngineBufferE", "tensorrt_llm::runtime::RawEngine::mEngineBuffer"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEnginePathE", "tensorrt_llm::runtime::RawEngine::mEnginePath"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEngineSizeE", "tensorrt_llm::runtime::RawEngine::mEngineSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine18mManagedWeightsMapE", "tensorrt_llm::runtime::RawEngine::mManagedWeightsMap"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine5mTypeE", "tensorrt_llm::runtime::RawEngine::mType"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine20setManagedWeightsMapENSt3mapINSt6stringEN12tensorrt_llm8executor6TensorEEE", "tensorrt_llm::runtime::RawEngine::setManagedWeightsMap"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine20setManagedWeightsMapENSt3mapINSt6stringEN12tensorrt_llm8executor6TensorEEE", "tensorrt_llm::runtime::RawEngine::setManagedWeightsMap::managedWeightsMap"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine7setPathENSt10filesystem4pathE", "tensorrt_llm::runtime::RawEngine::setPath"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9RawEngine7setPathENSt10filesystem4pathE", "tensorrt_llm::runtime::RawEngine::setPath::enginePath"], [1, 4, 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, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigE10SizeType32", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKN8executor14SamplingConfigERKNSt8optionalIN8executor25ExternalDraftTokensConfigEEE", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKNSt6vectorI14SamplingConfigEE", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigE10SizeType32", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig::beamWidth"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKNSt6vectorI14SamplingConfigEE", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig::configs"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKN8executor14SamplingConfigERKNSt8optionalIN8executor25ExternalDraftTokensConfigEEE", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig::externalDraftTokensConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKN8executor14SamplingConfigERKNSt8optionalIN8executor25ExternalDraftTokensConfigEEE", "tensorrt_llm::runtime::SamplingConfig::SamplingConfig::samplingConfig"], [1, 1, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig3VecE", "tensorrt_llm::runtime::SamplingConfig::Vec"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig3VecE", "tensorrt_llm::runtime::SamplingConfig::Vec::T"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig23beamSearchDiversityRateE", "tensorrt_llm::runtime::SamplingConfig::beamSearchDiversityRate"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9beamWidthE", "tensorrt_llm::runtime::SamplingConfig::beamWidth"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig11cumLogProbsE", "tensorrt_llm::runtime::SamplingConfig::cumLogProbs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig24draftAcceptanceThresholdE", "tensorrt_llm::runtime::SamplingConfig::draftAcceptanceThreshold"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig13earlyStoppingE", "tensorrt_llm::runtime::SamplingConfig::earlyStopping"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig16frequencyPenaltyE", "tensorrt_llm::runtime::SamplingConfig::frequencyPenalty"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T", "tensorrt_llm::runtime::SamplingConfig::fuseValues"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T", "tensorrt_llm::runtime::SamplingConfig::fuseValues::T"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T", "tensorrt_llm::runtime::SamplingConfig::fuseValues::accessor"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T", "tensorrt_llm::runtime::SamplingConfig::fuseValues::configs"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T", "tensorrt_llm::runtime::SamplingConfig::fuseValues::defaultValue"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig13lengthPenaltyE", "tensorrt_llm::runtime::SamplingConfig::lengthPenalty"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9minLengthE", "tensorrt_llm::runtime::SamplingConfig::minLength"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17noRepeatNgramSizeE", "tensorrt_llm::runtime::SamplingConfig::noRepeatNgramSize"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17normalizeLogProbsE", "tensorrt_llm::runtime::SamplingConfig::normalizeLogProbs"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime14SamplingConfigeqERK14SamplingConfig", "tensorrt_llm::runtime::SamplingConfig::operator=="], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime14SamplingConfigeqERK14SamplingConfig", "tensorrt_llm::runtime::SamplingConfig::operator==::other"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14outputLogProbsE", "tensorrt_llm::runtime::SamplingConfig::outputLogProbs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig15presencePenaltyE", "tensorrt_llm::runtime::SamplingConfig::presencePenalty"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig10randomSeedE", "tensorrt_llm::runtime::SamplingConfig::randomSeed"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17repetitionPenaltyE", "tensorrt_llm::runtime::SamplingConfig::repetitionPenalty"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig11temperatureE", "tensorrt_llm::runtime::SamplingConfig::temperature"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topKE", "tensorrt_llm::runtime::SamplingConfig::topK"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig15topKMedusaHeadsE", "tensorrt_llm::runtime::SamplingConfig::topKMedusaHeads"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topPE", "tensorrt_llm::runtime::SamplingConfig::topP"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9topPDecayE", "tensorrt_llm::runtime::SamplingConfig::topPDecay"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig7topPMinE", "tensorrt_llm::runtime::SamplingConfig::topPMin"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig12topPResetIdsE", "tensorrt_llm::runtime::SamplingConfig::topPResetIds"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig8validateEv", "tensorrt_llm::runtime::SamplingConfig::validate"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec::T"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec::max"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec::min"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec::name"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE", "tensorrt_llm::runtime::SamplingConfig::validateVec::vec"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime10SizeType32E", "tensorrt_llm::runtime::SizeType32"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingModeE", "tensorrt_llm::runtime::SpeculativeDecodingMode"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode19DraftTokensExternalEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::DraftTokensExternal"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode19ExplicitDraftTokensEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::ExplicitDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode17LookaheadDecodingEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::LookaheadDecoding"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode6MedusaEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::Medusa"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode4NoneEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::None"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode23SpeculativeDecodingModeE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::SpeculativeDecodingMode"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode23SpeculativeDecodingModeE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::SpeculativeDecodingMode::state"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode14UnderlyingTypeE", "tensorrt_llm::runtime::SpeculativeDecodingMode::UnderlyingType"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9allBitSetE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::allBitSet"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9allBitSetE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::allBitSet::bits"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9anyBitSetE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::anyBitSet"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9anyBitSetE14UnderlyingType", "tensorrt_llm::runtime::SpeculativeDecodingMode::anyBitSet::bits"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode14hasDraftLogitsEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::hasDraftLogits"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21isDraftTokensExternalEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::isDraftTokensExternal"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21isExplicitDraftTokensEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::isExplicitDraftTokens"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19isLookaheadDecodingEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::isLookaheadDecoding"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode8isMedusaEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::isMedusa"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode6isNoneEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::isNone"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode20kDraftTokensExternalE", "tensorrt_llm::runtime::SpeculativeDecodingMode::kDraftTokensExternal"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode20kExplicitDraftTokensE", "tensorrt_llm::runtime::SpeculativeDecodingMode::kExplicitDraftTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode18kLookaheadDecodingE", "tensorrt_llm::runtime::SpeculativeDecodingMode::kLookaheadDecoding"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode7kMedusaE", "tensorrt_llm::runtime::SpeculativeDecodingMode::kMedusa"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode5kNoneE", "tensorrt_llm::runtime::SpeculativeDecodingMode::kNone"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode6mStateE", "tensorrt_llm::runtime::SpeculativeDecodingMode::mState"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode20needsDecoderPrologueEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::needsDecoderPrologue"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode18needsKVCacheRewindEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::needsKVCacheRewind"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingModeeqERK23SpeculativeDecodingMode", "tensorrt_llm::runtime::SpeculativeDecodingMode::operator=="], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingModeeqERK23SpeculativeDecodingMode", "tensorrt_llm::runtime::SpeculativeDecodingMode::operator==::other"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19predictsDraftTokensEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::predictsDraftTokens"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21requiresAttentionMaskEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::requiresAttentionMask"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode18updatesPositionIdsEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::updatesPositionIds"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19variableDraftLengthEv", "tensorrt_llm::runtime::SpeculativeDecodingMode::variableDraftLength"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleE", "tensorrt_llm::runtime::SpeculativeDecodingModule"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleERK25SpeculativeDecodingModule", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule::maxDecodingDraftTokens"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule::maxDraftPathLen"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleE10SizeType3210SizeType3210SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule::maxNumPaths"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleERK25SpeculativeDecodingModule", "tensorrt_llm::runtime::SpeculativeDecodingModule::SpeculativeDecodingModule::o"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule21computeNumPackedMasksEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::computeNumPackedMasks"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule25getMaxDecodingDraftTokensEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getMaxDecodingDraftTokens"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule20getMaxDecodingTokensEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getMaxDecodingTokens"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule18getMaxDraftPathLenEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getMaxDraftPathLen"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule14getMaxNumPathsEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getMaxNumPaths"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule13getMaxPathLenEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getMaxPathLen"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule17getNumPackedMasksEv", "tensorrt_llm::runtime::SpeculativeDecodingModule::getNumPackedMasks"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule23mMaxDecodingDraftTokensE", "tensorrt_llm::runtime::SpeculativeDecodingModule::mMaxDecodingDraftTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule16mMaxDraftPathLenE", "tensorrt_llm::runtime::SpeculativeDecodingModule::mMaxDraftPathLen"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule18mMaxNumPackedMasksE", "tensorrt_llm::runtime::SpeculativeDecodingModule::mMaxNumPackedMasks"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule12mMaxNumPathsE", "tensorrt_llm::runtime::SpeculativeDecodingModule::mMaxNumPaths"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleaSERK25SpeculativeDecodingModule", "tensorrt_llm::runtime::SpeculativeDecodingModule::operator="], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleaSERK25SpeculativeDecodingModule", "tensorrt_llm::runtime::SpeculativeDecodingModule::operator=::o"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule18setMaxDraftPathLenE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxDraftPathLen"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule18setMaxDraftPathLenE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxDraftPathLen::maxDraftPathLen"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule17setMaxDraftTokensE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxDraftTokens"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule17setMaxDraftTokensE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxDraftTokens::maxDraftTokens"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule14setMaxNumPathsE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxNumPaths"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule14setMaxNumPathsE10SizeType32", "tensorrt_llm::runtime::SpeculativeDecodingModule::setMaxNumPaths::maxNumPaths"], [1, 5, 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, 4, 1, "_CPPv4I0_bEN12tensorrt_llm7runtime11TRTDataTypeE", "tensorrt_llm::runtime::TRTDataType"], [1, 8, 1, "_CPPv4I0_bEN12tensorrt_llm7runtime11TRTDataTypeE", "tensorrt_llm::runtime::TRTDataType::T"], [1, 4, 1, "_CPPv4I0EN12tensorrt_llm7runtime11TRTDataTypeIP1TEE", "tensorrt_llm::runtime::TRTDataType&lt;T*&gt;"], [1, 8, 1, "_CPPv4I0EN12tensorrt_llm7runtime11TRTDataTypeIP1TEE", "tensorrt_llm::runtime::TRTDataType&lt;T*&gt;::T"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE15kUnderlyingTypeE", "tensorrt_llm::runtime::TRTDataType&lt;T*&gt;::kUnderlyingType"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE5valueE", "tensorrt_llm::runtime::TRTDataType&lt;T*&gt;::value"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIbEE", "tensorrt_llm::runtime::TRTDataType&lt;bool&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIbE5valueE", "tensorrt_llm::runtime::TRTDataType&lt;bool&gt;::value"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIfEE", "tensorrt_llm::runtime::TRTDataType&lt;float&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIfE5valueE", "tensorrt_llm::runtime::TRTDataType&lt;float&gt;::value"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeI4halfEE", "tensorrt_llm::runtime::TRTDataType&lt;half&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeI4halfE5valueE", "tensorrt_llm::runtime::TRTDataType&lt;half&gt;::value"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIN7kernels13FinishedStateEEE", "tensorrt_llm::runtime::TRTDataType&lt;kernels::FinishedState&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIN7kernels13FinishedStateEE5valueE", "tensorrt_llm::runtime::TRTDataType&lt;kernels::FinishedState&gt;::value"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIN7kernels12KVCacheIndexEEE", "tensorrt_llm::runtime::TRTDataType&lt;kernels::KVCacheIndex&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIN7kernels12KVCacheIndexEE5valueE", "tensorrt_llm::runtime::TRTDataType&lt;kernels::KVCacheIndex&gt;::value"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEEE", "tensorrt_llm::runtime::TRTDataType&lt;std::int32_t&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEE5valueE", "tensorrt_llm::runtime::TRTDataType&lt;std::int32_t&gt;::value"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEEE", "tensorrt_llm::runtime::TRTDataType&lt;std::int64_t&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEE5valueE", "tensorrt_llm::runtime::TRTDataType&lt;std::int64_t&gt;::value"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEEE", "tensorrt_llm::runtime::TRTDataType&lt;std::int8_t&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEE5valueE", "tensorrt_llm::runtime::TRTDataType&lt;std::int8_t&gt;::value"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEEE", "tensorrt_llm::runtime::TRTDataType&lt;std::uint32_t&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEE5valueE", "tensorrt_llm::runtime::TRTDataType&lt;std::uint32_t&gt;::value"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEEE", "tensorrt_llm::runtime::TRTDataType&lt;std::uint64_t&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEE5valueE", "tensorrt_llm::runtime::TRTDataType&lt;std::uint64_t&gt;::value"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEEE", "tensorrt_llm::runtime::TRTDataType&lt;std::uint8_t&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEE5valueE", "tensorrt_llm::runtime::TRTDataType&lt;std::uint8_t&gt;::value"], [1, 4, 1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIPvEE", "tensorrt_llm::runtime::TRTDataType&lt;void*&gt;"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIPvE5valueE", "tensorrt_llm::runtime::TRTDataType&lt;void*&gt;::value"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLoggerE", "tensorrt_llm::runtime::TllmLogger"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger8getLevelEv", "tensorrt_llm::runtime::TllmLogger::getLevel"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger3logE8SeverityPKN8nvinfer19AsciiCharE", "tensorrt_llm::runtime::TllmLogger::log"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger3logE8SeverityPKN8nvinfer19AsciiCharE", "tensorrt_llm::runtime::TllmLogger::log::msg"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger3logE8SeverityPKN8nvinfer19AsciiCharE", "tensorrt_llm::runtime::TllmLogger::log::severity"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger8setLevelE8Severity", "tensorrt_llm::runtime::TllmLogger::setLevel"], [1, 6, 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, 4, 1, "_CPPv4N12tensorrt_llm7runtime11UniqueTokenE", "tensorrt_llm::runtime::UniqueToken"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11UniqueTokeneqERK11UniqueToken", "tensorrt_llm::runtime::UniqueToken::operator=="], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime11UniqueTokeneqERK11UniqueToken", "tensorrt_llm::runtime::UniqueToken::operator==::other"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11UniqueToken12tokenExtraIdE", "tensorrt_llm::runtime::UniqueToken::tokenExtraId"], [1, 7, 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, 4, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfigE", "tensorrt_llm::runtime::WorldConfig"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::runtime::WorldConfig::WorldConfig"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::runtime::WorldConfig::WorldConfig::deviceIds"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::runtime::WorldConfig::WorldConfig::gpusPerNode"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::runtime::WorldConfig::WorldConfig::pipelineParallelism"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::runtime::WorldConfig::WorldConfig::rank"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::runtime::WorldConfig::WorldConfig::tensorParallelism"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig9getDeviceEv", "tensorrt_llm::runtime::WorldConfig::getDevice"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getDeviceOfE10SizeType32", "tensorrt_llm::runtime::WorldConfig::getDeviceOf"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getDeviceOfE10SizeType32", "tensorrt_llm::runtime::WorldConfig::getDeviceOf::rank"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig15getGpusPerGroupEv", "tensorrt_llm::runtime::WorldConfig::getGpusPerGroup"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig14getGpusPerNodeEv", "tensorrt_llm::runtime::WorldConfig::getGpusPerNode"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getLastRankEv", "tensorrt_llm::runtime::WorldConfig::getLastRank"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig12getLocalRankEv", "tensorrt_llm::runtime::WorldConfig::getLocalRank"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getNodeRankEv", "tensorrt_llm::runtime::WorldConfig::getNodeRank"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig13getNodeRankOfE10SizeType32", "tensorrt_llm::runtime::WorldConfig::getNodeRankOf"], [1, 6, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig13getNodeRankOfE10SizeType32", "tensorrt_llm::runtime::WorldConfig::getNodeRankOf::rank"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig24getPipelineParallelGroupEv", "tensorrt_llm::runtime::WorldConfig::getPipelineParallelGroup"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig23getPipelineParallelRankEv", "tensorrt_llm::runtime::WorldConfig::getPipelineParallelRank"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getPipelineParallelismEv", "tensorrt_llm::runtime::WorldConfig::getPipelineParallelism"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getRankEv", "tensorrt_llm::runtime::WorldConfig::getRank"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getSizeEv", "tensorrt_llm::runtime::WorldConfig::getSize"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getTensorParallelGroupEv", "tensorrt_llm::runtime::WorldConfig::getTensorParallelGroup"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig21getTensorParallelRankEv", "tensorrt_llm::runtime::WorldConfig::getTensorParallelRank"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig20getTensorParallelismEv", "tensorrt_llm::runtime::WorldConfig::getTensorParallelism"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig27isFirstPipelineParallelRankEv", "tensorrt_llm::runtime::WorldConfig::isFirstPipelineParallelRank"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig25isFirstTensorParallelRankEv", "tensorrt_llm::runtime::WorldConfig::isFirstTensorParallelRank"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig26isLastPipelineParallelRankEv", "tensorrt_llm::runtime::WorldConfig::isLastPipelineParallelRank"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig18isPipelineParallelEv", "tensorrt_llm::runtime::WorldConfig::isPipelineParallel"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig16isTensorParallelEv", "tensorrt_llm::runtime::WorldConfig::isTensorParallel"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig19kDefaultGpusPerNodeE", "tensorrt_llm::runtime::WorldConfig::kDefaultGpusPerNode"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig10mDeviceIdsE", "tensorrt_llm::runtime::WorldConfig::mDeviceIds"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig12mGpusPerNodeE", "tensorrt_llm::runtime::WorldConfig::mGpusPerNode"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig20mPipelineParallelismE", "tensorrt_llm::runtime::WorldConfig::mPipelineParallelism"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig5mRankE", "tensorrt_llm::runtime::WorldConfig::mRank"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig18mTensorParallelismE", "tensorrt_llm::runtime::WorldConfig::mTensorParallelism"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::runtime::WorldConfig::mpi"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::runtime::WorldConfig::mpi::deviceIds"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::runtime::WorldConfig::mpi::gpusPerNode"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::runtime::WorldConfig::mpi::pipelineParallelism"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEE", "tensorrt_llm::runtime::WorldConfig::mpi::tensorParallelism"], [1, 5, 1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig14validMpiConfigEv", "tensorrt_llm::runtime::WorldConfig::validMpiConfig"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEP1TR7IBuffer", "tensorrt_llm::runtime::bufferCast"], [1, 5, 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, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEP1TR7IBuffer", "tensorrt_llm::runtime::bufferCast::buffer"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEPK1TRK7IBuffer", "tensorrt_llm::runtime::bufferCast::buffer"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7IBuffer9SharedPtrE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7ITensor9SharedPtrE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7IBuffer9SharedPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7ITensor9SharedPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7IBuffer14SharedConstPtrE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7ITensor14SharedConstPtrE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 5, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7IBuffer14SharedConstPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull"], [1, 5, 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, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7IBuffer9SharedPtrE", "tensorrt_llm::runtime::bufferCastOrNull::bufferPtr"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7IBuffer14SharedConstPtrE", "tensorrt_llm::runtime::bufferCastOrNull::bufferPtr"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7IBuffer9SharedPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::optionalBufferPtr"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7IBuffer14SharedConstPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::optionalBufferPtr"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7ITensor9SharedPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::optionalTensorPtr"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7ITensor14SharedConstPtrEEE", "tensorrt_llm::runtime::bufferCastOrNull::optionalTensorPtr"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7ITensor9SharedPtrE", "tensorrt_llm::runtime::bufferCastOrNull::tensorPtr"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7ITensor14SharedConstPtrE", "tensorrt_llm::runtime::bufferCastOrNull::tensorPtr"], [1, 5, 1, "_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE", "tensorrt_llm::runtime::constPointerCast"], [1, 5, 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, 6, 1, "_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE", "tensorrt_llm::runtime::constPointerCast::ptr"], [1, 6, 1, "_CPPv4I0EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERKNSt10shared_ptrI1TEE", "tensorrt_llm::runtime::constPointerCast::ptr"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7decoderE", "tensorrt_llm::runtime::decoder"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder5InputE", "tensorrt_llm::runtime::decoder::Input"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder5Input5InputE9TensorPtr", "tensorrt_llm::runtime::decoder::Input::Input"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime7decoder5Input5InputE9TensorPtr", "tensorrt_llm::runtime::decoder::Input::Input::logits"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7decoder5Input9TensorPtrE", "tensorrt_llm::runtime::decoder::Input::TensorPtr"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime7decoder5Input16cacheIndirectionE", "tensorrt_llm::runtime::decoder::Input::cacheIndirection"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime7decoder5Input6logitsE", "tensorrt_llm::runtime::decoder::Input::logits"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime7decoder6OutputE", "tensorrt_llm::runtime::decoder::Output"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime7decoder6Output6OutputEv", "tensorrt_llm::runtime::decoder::Output::Output"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime7decoder6Output9TensorPtrE", "tensorrt_llm::runtime::decoder::Output::TensorPtr"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime7decoder6Output16cacheIndirectionE", "tensorrt_llm::runtime::decoder::Output::cacheIndirection"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime7decoder6Output15sequenceLengthsE", "tensorrt_llm::runtime::decoder::Output::sequenceLengths"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batchE", "tensorrt_llm::runtime::decoder_batch"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batchE", "tensorrt_llm::runtime::decoder_batch"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5InputE", "tensorrt_llm::runtime::decoder_batch::Input"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI9TensorPtrEE", "tensorrt_llm::runtime::decoder_batch::Input::Input"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI9TensorPtrEERKNSt6vectorIbEE", "tensorrt_llm::runtime::decoder_batch::Input::Input"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI9TensorPtrEERKNSt6vectorIbEE", "tensorrt_llm::runtime::decoder_batch::Input::Input::active"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI9TensorPtrEE", "tensorrt_llm::runtime::decoder_batch::Input::Input::logits"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI9TensorPtrEERKNSt6vectorIbEE", "tensorrt_llm::runtime::decoder_batch::Input::Input::logits"], [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, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input6activeE", "tensorrt_llm::runtime::decoder_batch::Input::active"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input16cacheIndirectionE", "tensorrt_llm::runtime::decoder_batch::Input::cacheIndirection"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input25explicitDraftTokensInputsE", "tensorrt_llm::runtime::decoder_batch::Input::explicitDraftTokensInputs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input29explicitDraftTokensLastInputsE", "tensorrt_llm::runtime::decoder_batch::Input::explicitDraftTokensLastInputs"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input6logitsE", "tensorrt_llm::runtime::decoder_batch::Input::logits"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input20predictedDraftLogitsE", "tensorrt_llm::runtime::decoder_batch::Input::predictedDraftLogits"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input8seqSlotsE", "tensorrt_llm::runtime::decoder_batch::Input::seqSlots"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch6OutputE", "tensorrt_llm::runtime::decoder_batch::Output"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7RequestE", "tensorrt_llm::runtime::decoder_batch::Request"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9BufferPtrE", "tensorrt_llm::runtime::decoder_batch::Request::BufferPtr"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14TensorConstPtr10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::decoder_batch::Request::Request"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14TensorConstPtr10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::decoder_batch::Request::Request::endId"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14TensorConstPtr10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::decoder_batch::Request::Request::ids"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14TensorConstPtr10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE", "tensorrt_llm::runtime::decoder_batch::Request::Request::inputLen"], [1, 6, 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, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request12badWordsListE", "tensorrt_llm::runtime::decoder_batch::Request::badWordsList"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11draftLogitsE", "tensorrt_llm::runtime::decoder_batch::Request::draftLogits"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11draftTokensE", "tensorrt_llm::runtime::decoder_batch::Request::draftTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request5dtypeE", "tensorrt_llm::runtime::decoder_batch::Request::dtype"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13embeddingBiasE", "tensorrt_llm::runtime::decoder_batch::Request::embeddingBias"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request5endIdE", "tensorrt_llm::runtime::decoder_batch::Request::endId"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request28generatedTokensPerEngineStepE", "tensorrt_llm::runtime::decoder_batch::Request::generatedTokensPerEngineStep"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request3idsE", "tensorrt_llm::runtime::decoder_batch::Request::ids"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request8inputLenE", "tensorrt_llm::runtime::decoder_batch::Request::inputLen"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request22lookaheadRuntimeConfigE", "tensorrt_llm::runtime::decoder_batch::Request::lookaheadRuntimeConfig"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request12maxNewTokensE", "tensorrt_llm::runtime::decoder_batch::Request::maxNewTokens"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11medusaPathsE", "tensorrt_llm::runtime::decoder_batch::Request::medusaPaths"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13medusaTreeIdsE", "tensorrt_llm::runtime::decoder_batch::Request::medusaTreeIds"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13stopWordsListE", "tensorrt_llm::runtime::decoder_batch::Request::stopWordsList"], [1, 4, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5TokenE", "tensorrt_llm::runtime::decoder_batch::Token"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Token5TokenERR9CudaEventRKNSt6vectorIbEE", "tensorrt_llm::runtime::decoder_batch::Token::Token"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Token5TokenERR9CudaEventRKNSt6vectorIbEE", "tensorrt_llm::runtime::decoder_batch::Token::Token::active"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Token5TokenERR9CudaEventRKNSt6vectorIbEE", "tensorrt_llm::runtime::decoder_batch::Token::Token::event"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Token6activeE", "tensorrt_llm::runtime::decoder_batch::Token::active"], [1, 7, 1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Token5eventE", "tensorrt_llm::runtime::decoder_batch::Token::event"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime20getDefaultBatchSlotsEN7runtime10SizeType32ERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::getDefaultBatchSlots"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime20getDefaultBatchSlotsEN7runtime10SizeType32ERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::getDefaultBatchSlots::batchSize"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime20getDefaultBatchSlotsEN7runtime10SizeType32ERKN7runtime13BufferManagerE", "tensorrt_llm::runtime::getDefaultBatchSlots::bufferManager"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK10LoraModule", "tensorrt_llm::runtime::operator&lt;&lt;"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK26LoraCachePageManagerConfig", "tensorrt_llm::runtime::operator&lt;&lt;"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7IBuffer", "tensorrt_llm::runtime::operator&lt;&lt;"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7ITensor", "tensorrt_llm::runtime::operator&lt;&lt;"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN7ITensor5ShapeE", "tensorrt_llm::runtime::operator&lt;&lt;"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::operator&lt;&lt;"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7IBuffer", "tensorrt_llm::runtime::operator&lt;&lt;::buffer"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK26LoraCachePageManagerConfig", "tensorrt_llm::runtime::operator&lt;&lt;::c"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN7ITensor5ShapeE", "tensorrt_llm::runtime::operator&lt;&lt;::dims"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK10LoraModule", "tensorrt_llm::runtime::operator&lt;&lt;::module"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK26LoraCachePageManagerConfig", "tensorrt_llm::runtime::operator&lt;&lt;::os"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::operator&lt;&lt;::os"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK10LoraModule", "tensorrt_llm::runtime::operator&lt;&lt;::output"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7IBuffer", "tensorrt_llm::runtime::operator&lt;&lt;::output"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7ITensor", "tensorrt_llm::runtime::operator&lt;&lt;::output"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN7ITensor5ShapeE", "tensorrt_llm::runtime::operator&lt;&lt;::output"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7ITensor", "tensorrt_llm::runtime::operator&lt;&lt;::tensor"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::operator&lt;&lt;::v"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9to_stringERK26LoraCachePageManagerConfig", "tensorrt_llm::runtime::to_string"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime9to_stringERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::to_string"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9to_stringERK26LoraCachePageManagerConfig", "tensorrt_llm::runtime::to_string::c"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime9to_stringERKN9LoraCache21TaskLayerModuleConfigE", "tensorrt_llm::runtime::to_string::v"], [1, 1, 1, "_CPPv4N12tensorrt_llm7runtime5utilsE", "tensorrt_llm::runtime::utils"], [1, 5, 1, "_CPPv4N12tensorrt_llm7runtime5utils10loadEngineERKNSt6stringE", "tensorrt_llm::runtime::utils::loadEngine"], [1, 6, 1, "_CPPv4N12tensorrt_llm7runtime5utils10loadEngineERKNSt6stringE", "tensorrt_llm::runtime::utils::loadEngine::enginePath"], [49, 9, 0, "-", "tensorrt_llm"]], "tensorrt_llm": [[44, 9, 0, "-", "functional"], [46, 9, 0, "-", "models"], [47, 9, 0, "-", "plugin"], [48, 9, 0, "-", "quantization"], [49, 9, 0, "-", "runtime"]], "tensorrt_llm.functional": [[44, 10, 1, "", "AllReduceConfig"], [44, 10, 1, "", "AllReduceFusionOp"], [44, 10, 1, "", "AllReduceFusionParams"], [44, 10, 1, "", "AllReduceStrategy"], [44, 10, 1, "", "AttentionMaskType"], [44, 10, 1, "", "Conditional"], [44, 10, 1, "", "DimRange"], [44, 10, 1, "", "LayerNormPositionType"], [44, 10, 1, "", "LayerNormType"], [44, 10, 1, "", "MLPType"], [44, 10, 1, "", "PositionEmbeddingType"], [44, 10, 1, "", "RopeEmbeddingUtils"], [44, 10, 1, "", "RotaryScalingType"], [44, 10, 1, "", "Tensor"], [44, 14, 1, "", "abs"], [44, 14, 1, "", "activation"], [44, 14, 1, "", "add"], [44, 14, 1, "", "allgather"], [44, 14, 1, "", "allreduce"], [44, 14, 1, "", "arange"], [44, 14, 1, "", "argmax"], [44, 14, 1, "", "assertion"], [44, 14, 1, "", "avg_pool2d"], [44, 14, 1, "", "bert_attention"], [44, 14, 1, "", "broadcast_helper"], [44, 14, 1, "", "cast"], [44, 14, 1, "", "categorical_sample"], [44, 14, 1, "", "chunk"], [44, 14, 1, "", "clip"], [44, 14, 1, "", "concat"], [44, 14, 1, "", "constant"], [44, 14, 1, "", "constant_to_tensor_"], [44, 14, 1, "", "constants_to_tensors_"], [44, 14, 1, "", "conv1d"], [44, 14, 1, "", "conv2d"], [44, 14, 1, "", "conv_transpose2d"], [44, 14, 1, "", "cos"], [44, 14, 1, "", "create_allreduce_plugin"], [44, 14, 1, "", "cumsum"], [44, 14, 1, "", "div"], [44, 14, 1, "", "einsum"], [44, 14, 1, "", "elementwise_binary"], [44, 14, 1, "", "embedding"], [44, 14, 1, "", "eq"], [44, 14, 1, "", "exp"], [44, 14, 1, "", "expand"], [44, 14, 1, "", "expand_dims"], [44, 14, 1, "", "expand_dims_like"], [44, 14, 1, "", "expand_mask"], [44, 14, 1, "", "flatten"], [44, 14, 1, "", "flip"], [44, 14, 1, "", "floordiv"], [44, 14, 1, "", "gather"], [44, 14, 1, "", "gather_last_token_logits"], [44, 14, 1, "", "gather_nd"], [44, 14, 1, "", "gegelu"], [44, 14, 1, "", "geglu"], [44, 14, 1, "", "gelu"], [44, 14, 1, "", "gemm_swiglu"], [44, 14, 1, "", "generate_alibi_biases"], [44, 14, 1, "", "generate_alibi_slopes"], [44, 14, 1, "", "gpt_attention"], [44, 14, 1, "", "group_norm"], [44, 14, 1, "", "gt"], [44, 14, 1, "", "identity"], [44, 14, 1, "", "index_select"], [44, 14, 1, "", "int_clip"], [44, 14, 1, "", "interpolate"], [44, 14, 1, "", "is_gated_activation"], [44, 14, 1, "", "layer_norm"], [44, 14, 1, "", "log"], [44, 14, 1, "", "log_softmax"], [44, 14, 1, "", "lora_plugin"], [44, 14, 1, "", "low_latency_gemm"], [44, 14, 1, "", "lt"], [44, 14, 1, "", "mamba_conv1d"], [44, 14, 1, "", "masked_scatter"], [44, 14, 1, "", "masked_select"], [44, 14, 1, "", "matmul"], [44, 14, 1, "", "max"], [44, 14, 1, "", "maximum"], [44, 14, 1, "", "mean"], [44, 14, 1, "", "min"], [44, 14, 1, "", "minimum"], [44, 14, 1, "", "modulo"], [44, 14, 1, "", "mul"], [44, 14, 1, "", "non_gated_version"], [44, 14, 1, "", "nonzero"], [44, 14, 1, "", "not_op"], [44, 14, 1, "", "op_and"], [44, 14, 1, "", "op_or"], [44, 14, 1, "", "outer"], [44, 14, 1, "", "permute"], [44, 14, 1, "", "pow"], [44, 14, 1, "", "prod"], [44, 14, 1, "", "quick_gelu"], [44, 14, 1, "", "rand"], [44, 14, 1, "", "recv"], [44, 14, 1, "", "reduce"], [44, 14, 1, "", "relu"], [44, 14, 1, "", "repeat_interleave"], [44, 14, 1, "", "rg_lru"], [44, 14, 1, "", "rms_norm"], [44, 14, 1, "", "round"], [44, 14, 1, "", "scatter"], [44, 14, 1, "", "scatter_nd"], [44, 14, 1, "", "select"], [44, 14, 1, "", "selective_scan"], [44, 14, 1, "", "send"], [44, 14, 1, "", "shape"], [44, 14, 1, "", "sigmoid"], [44, 14, 1, "", "silu"], [44, 14, 1, "", "sin"], [44, 14, 1, "", "slice"], [44, 14, 1, "", "softmax"], [44, 14, 1, "", "softplus"], [44, 14, 1, "", "split"], [44, 14, 1, "", "sqrt"], [44, 14, 1, "", "squared_relu"], [44, 14, 1, "", "squeeze"], [44, 14, 1, "", "stack"], [44, 14, 1, "", "sub"], [44, 14, 1, "", "sum"], [44, 14, 1, "", "swiglu"], [44, 14, 1, "", "tanh"], [44, 14, 1, "", "topk"], [44, 14, 1, "", "transpose"], [44, 14, 1, "", "unary"], [44, 14, 1, "", "unbind"], [44, 14, 1, "", "unsqueeze"], [44, 14, 1, "", "view"], [44, 14, 1, "", "where"]], "tensorrt_llm.functional.AllReduceConfig": [[44, 11, 1, "", "PUSH_MODE"], [44, 11, 1, "", "USE_MEMCPY"]], "tensorrt_llm.functional.AllReduceFusionOp": [[44, 11, 1, "", "NONE"], [44, 11, 1, "", "RESIDUAL_RMS_NORM"]], "tensorrt_llm.functional.AllReduceFusionParams": [[44, 12, 1, "", "has_affine"], [44, 12, 1, "", "has_bias"]], "tensorrt_llm.functional.AllReduceStrategy": [[44, 11, 1, "", "AUTO"], [44, 11, 1, "", "NCCL"], [44, 11, 1, "", "ONESHOT"], [44, 11, 1, "", "TWOSHOT"]], "tensorrt_llm.functional.AttentionMaskType": [[44, 11, 1, "", "bidirectional"], [44, 11, 1, "", "bidirectionalglm"], [44, 11, 1, "", "blocksparse"], [44, 11, 1, "", "causal"], [44, 11, 1, "", "custom_mask"], [44, 11, 1, "", "padding"], [44, 11, 1, "", "sliding_window_causal"]], "tensorrt_llm.functional.Conditional": [[44, 12, 1, "", "add_input"], [44, 12, 1, "", "add_output"]], "tensorrt_llm.functional.LayerNormPositionType": [[44, 11, 1, "", "post_layernorm"], [44, 11, 1, "", "pre_layernorm"]], "tensorrt_llm.functional.LayerNormType": [[44, 11, 1, "", "GroupNorm"], [44, 11, 1, "", "LayerNorm"], [44, 11, 1, "", "RmsNorm"]], "tensorrt_llm.functional.MLPType": [[44, 11, 1, "", "FusedGatedMLP"], [44, 11, 1, "", "GatedMLP"], [44, 11, 1, "", "MLP"]], "tensorrt_llm.functional.PositionEmbeddingType": [[44, 11, 1, "", "alibi"], [44, 11, 1, "", "alibi_with_scale"], [44, 11, 1, "", "chatglm"], [44, 12, 1, "", "choices"], [44, 12, 1, "", "from_string"], [44, 12, 1, "", "is_alibi"], [44, 12, 1, "", "is_rope"], [44, 11, 1, "", "learned_absolute"], [44, 11, 1, "", "long_rope"], [44, 11, 1, "", "relative"], [44, 11, 1, "", "rope_gpt_neox"], [44, 11, 1, "", "rope_gptj"]], "tensorrt_llm.functional.RopeEmbeddingUtils": [[44, 12, 1, "", "apply_llama3_scaling"], [44, 12, 1, "", "apply_rotary_pos_emb"], [44, 12, 1, "", "apply_rotary_pos_emb_chatglm"], [44, 12, 1, "", "apply_rotary_pos_emb_cogvlm"], [44, 12, 1, "", "create_sinusoidal_positions"], [44, 12, 1, "", "create_sinusoidal_positions_for_attention_plugin"], [44, 12, 1, "", "create_sinusoidal_positions_for_cogvlm_attention_plugin"], [44, 12, 1, "", "create_sinusoidal_positions_long_rope"], [44, 12, 1, "", "rotate_every_two"], [44, 12, 1, "", "rotate_half"]], "tensorrt_llm.functional.RotaryScalingType": [[44, 11, 1, "", "dynamic"], [44, 12, 1, "", "from_string"], [44, 11, 1, "", "linear"], [44, 11, 1, "", "llama3"], [44, 11, 1, "", "longrope"], [44, 11, 1, "", "none"]], "tensorrt_llm.functional.Tensor": [[44, 12, 1, "", "abs"], [44, 12, 1, "", "cast"], [44, 13, 1, "", "dtype"], [44, 12, 1, "", "flatten"], [44, 12, 1, "", "get_parent"], [44, 12, 1, "", "get_users"], [44, 12, 1, "", "is_dynamic"], [44, 12, 1, "", "is_trt_wrapper"], [44, 13, 1, "", "location"], [44, 12, 1, "", "log"], [44, 12, 1, "", "mark_output"], [44, 12, 1, "", "max"], [44, 12, 1, "", "mean"], [44, 13, 1, "", "name"], [44, 12, 1, "", "ndim"], [44, 13, 1, "", "network"], [44, 12, 1, "", "permute"], [44, 12, 1, "", "rank"], [44, 12, 1, "", "replace_all_uses_with"], [44, 13, 1, "", "shape"], [44, 12, 1, "", "size"], [44, 12, 1, "", "split"], [44, 12, 1, "", "sqrt"], [44, 12, 1, "", "transpose"], [44, 12, 1, "", "unbind"], [44, 12, 1, "", "view"]], "tensorrt_llm.hlapi": [[39, 10, 1, "", "BuildCacheConfig"], [39, 10, 1, "", "BuildConfig"], [39, 10, 1, "", "CapacitySchedulerPolicy"], [39, 10, 1, "", "KvCacheConfig"], [39, 10, 1, "", "LLM"], [39, 10, 1, "", "QuantAlgo"], [39, 10, 1, "", "QuantConfig"], [39, 10, 1, "", "RequestOutput"], [39, 10, 1, "", "SamplingParams"], [39, 10, 1, "", "SchedulerConfig"]], "tensorrt_llm.hlapi.BuildCacheConfig": [[39, 12, 1, "", "__init__"], [39, 13, 1, "id0", "cache_root"], [39, 13, 1, "id1", "max_cache_storage_gb"], [39, 13, 1, "id2", "max_records"]], "tensorrt_llm.hlapi.BuildConfig": [[39, 12, 1, "", "__init__"], [39, 11, 1, "", "auto_parallel_config"], [39, 11, 1, "", "builder_opt"], [39, 11, 1, "", "dry_run"], [39, 11, 1, "", "enable_debug_output"], [39, 11, 1, "", "force_num_profiles"], [39, 12, 1, "", "from_dict"], [39, 12, 1, "", "from_json_file"], [39, 11, 1, "", "gather_context_logits"], [39, 11, 1, "", "gather_generation_logits"], [39, 11, 1, "", "input_timing_cache"], [39, 11, 1, "", "kv_cache_type"], [39, 11, 1, "", "lora_config"], [39, 11, 1, "", "max_batch_size"], [39, 11, 1, "", "max_beam_width"], [39, 11, 1, "", "max_draft_len"], [39, 11, 1, "", "max_encoder_input_len"], [39, 11, 1, "", "max_input_len"], [39, 11, 1, "", "max_num_tokens"], [39, 11, 1, "", "max_prompt_embedding_table_size"], [39, 11, 1, "", "max_seq_len"], [39, 11, 1, "", "opt_batch_size"], [39, 11, 1, "", "opt_num_tokens"], [39, 11, 1, "", "output_timing_cache"], [39, 11, 1, "", "plugin_config"], [39, 11, 1, "", "profiling_verbosity"], [39, 11, 1, "", "speculative_decoding_mode"], [39, 11, 1, "", "strongly_typed"], [39, 12, 1, "", "to_dict"], [39, 12, 1, "", "update"], [39, 12, 1, "", "update_from_dict"], [39, 12, 1, "", "update_kv_cache_type"], [39, 11, 1, "", "use_fused_mlp"], [39, 11, 1, "", "use_refit"], [39, 11, 1, "", "use_strip_plan"], [39, 11, 1, "", "visualize_network"], [39, 11, 1, "", "weight_sparsity"], [39, 11, 1, "", "weight_streaming"]], "tensorrt_llm.hlapi.CapacitySchedulerPolicy": [[39, 11, 1, "", "GUARANTEED_NO_EVICT"], [39, 11, 1, "", "MAX_UTILIZATION"], [39, 11, 1, "", "STATIC_BATCH"], [39, 12, 1, "", "__init__"], [39, 13, 1, "", "name"], [39, 13, 1, "", "value"]], "tensorrt_llm.hlapi.KvCacheConfig": [[39, 12, 1, "", "__init__"], [39, 13, 1, "", "enable_block_reuse"], [39, 13, 1, "", "free_gpu_memory_fraction"], [39, 13, 1, "", "host_cache_size"], [39, 13, 1, "", "max_attention_window"], [39, 13, 1, "", "max_tokens"], [39, 13, 1, "", "onboard_blocks"], [39, 13, 1, "", "sink_token_length"]], "tensorrt_llm.hlapi.LLM": [[39, 12, 1, "", "__init__"], [39, 12, 1, "", "generate"], [39, 12, 1, "", "generate_async"], [39, 12, 1, "", "save"], [39, 13, 1, "", "tokenizer"], [39, 13, 1, "", "workspace"]], "tensorrt_llm.hlapi.QuantAlgo": [[39, 11, 1, "", "FP8"], [39, 11, 1, "", "FP8_PER_CHANNEL_PER_TOKEN"], [39, 11, 1, "", "INT8"], [39, 11, 1, "", "W4A16"], [39, 11, 1, "", "W4A16_AWQ"], [39, 11, 1, "", "W4A16_GPTQ"], [39, 11, 1, "", "W4A8_AWQ"], [39, 11, 1, "", "W8A16"], [39, 11, 1, "", "W8A8_SQ_PER_CHANNEL"], [39, 11, 1, "", "W8A8_SQ_PER_CHANNEL_PER_TENSOR_PLUGIN"], [39, 11, 1, "", "W8A8_SQ_PER_CHANNEL_PER_TOKEN_PLUGIN"], [39, 11, 1, "", "W8A8_SQ_PER_TENSOR_PER_TOKEN_PLUGIN"], [39, 11, 1, "", "W8A8_SQ_PER_TENSOR_PLUGIN"]], "tensorrt_llm.hlapi.QuantConfig": [[39, 12, 1, "", "__init__"], [39, 11, 1, "", "clamp_val"], [39, 11, 1, "", "exclude_modules"], [39, 12, 1, "", "from_dict"], [39, 12, 1, "", "get_modelopt_kv_cache_dtype"], [39, 12, 1, "", "get_modelopt_qformat"], [39, 11, 1, "", "group_size"], [39, 11, 1, "", "has_zero_point"], [39, 11, 1, "", "kv_cache_quant_algo"], [39, 11, 1, "", "pre_quant_scale"], [39, 11, 1, "", "quant_algo"], [39, 13, 1, "", "quant_mode"], [39, 13, 1, "", "requires_calibration"], [39, 13, 1, "", "requires_modelopt_quantization"], [39, 11, 1, "", "smoothquant_val"], [39, 12, 1, "", "to_dict"], [39, 13, 1, "", "use_plugin_sq"]], "tensorrt_llm.hlapi.RequestOutput": [[39, 12, 1, "", "__init__"], [39, 12, 1, "", "handle_response"]], "tensorrt_llm.hlapi.SamplingParams": [[39, 12, 1, "", "__init__"], [39, 11, 1, "", "add_special_tokens"], [39, 11, 1, "", "bad"], [39, 11, 1, "", "bad_token_ids"], [39, 11, 1, "", "beam_search_diversity_rate"], [39, 11, 1, "", "beam_width"], [39, 11, 1, "", "early_stopping"], [39, 11, 1, "", "embedding_bias"], [39, 11, 1, "", "end_id"], [39, 11, 1, "", "exclude_input_from_output"], [39, 11, 1, "", "external_draft_tokens_config"], [39, 11, 1, "", "frequency_penalty"], [39, 11, 1, "", "include_stop_str_in_output"], [39, 11, 1, "", "length_penalty"], [39, 11, 1, "", "logits_post_processor_name"], [39, 11, 1, "", "max_new_tokens"], [39, 11, 1, "", "max_tokens"], [39, 11, 1, "", "min_length"], [39, 11, 1, "", "min_tokens"], [39, 11, 1, "", "no_repeat_ngram_size"], [39, 11, 1, "", "pad_id"], [39, 11, 1, "", "presence_penalty"], [39, 11, 1, "", "prompt_tuning_config"], [39, 11, 1, "", "random_seed"], [39, 11, 1, "", "repetition_penalty"], [39, 11, 1, "", "return_context_logits"], [39, 11, 1, "", "return_encoder_output"], [39, 11, 1, "", "return_generation_logits"], [39, 11, 1, "", "return_log_probs"], [39, 11, 1, "", "seed"], [39, 12, 1, "", "setup"], [39, 11, 1, "", "stop"], [39, 11, 1, "", "stop_token_ids"], [39, 11, 1, "", "temperature"], [39, 11, 1, "", "top_k"], [39, 11, 1, "", "top_p"], [39, 11, 1, "", "top_p_decay"], [39, 11, 1, "", "top_p_min"], [39, 11, 1, "", "top_p_reset_ids"]], "tensorrt_llm.hlapi.SchedulerConfig": [[39, 12, 1, "", "__init__"], [39, 13, 1, "", "capacity_scheduler_policy"], [39, 13, 1, "", "context_chunking_policy"]], "tensorrt_llm.layers": [[45, 9, 0, "-", "activation"], [45, 9, 0, "-", "attention"], [45, 9, 0, "-", "cast"], [45, 9, 0, "-", "conv"], [45, 9, 0, "-", "embedding"], [45, 9, 0, "-", "linear"], [45, 9, 0, "-", "mlp"], [45, 9, 0, "-", "normalization"], [45, 9, 0, "-", "pooling"]], "tensorrt_llm.layers.activation": [[45, 10, 1, "", "Mish"]], "tensorrt_llm.layers.activation.Mish": [[45, 12, 1, "", "forward"]], "tensorrt_llm.layers.attention": [[45, 10, 1, "", "Attention"], [45, 10, 1, "", "AttentionParams"], [45, 10, 1, "", "BertAttention"], [45, 10, 1, "", "BlockSparseAttnParams"], [45, 10, 1, "", "CogVLMAttention"], [45, 10, 1, "", "KeyValueCacheParams"], [45, 10, 1, "", "SpecDecodingParams"], [45, 14, 1, "", "compute_relative_bias"], [45, 14, 1, "", "make_causal_mask"]], "tensorrt_llm.layers.attention.Attention": [[45, 12, 1, "", "create_attention_const_params"], [45, 12, 1, "", "fill_attention_params"], [45, 12, 1, "", "forward"], [45, 12, 1, "", "postprocess"], [45, 12, 1, "", "set_rel_attn_table"]], "tensorrt_llm.layers.attention.AttentionParams": [[45, 12, 1, "", "fill_attention_const_params_for_long_rope"], [45, 12, 1, "", "fill_attention_const_params_for_rope"], [45, 12, 1, "", "is_valid"], [45, 12, 1, "", "is_valid_cross_attn"]], "tensorrt_llm.layers.attention.BertAttention": [[45, 12, 1, "", "forward"]], "tensorrt_llm.layers.attention.CogVLMAttention": [[45, 12, 1, "", "forward"]], "tensorrt_llm.layers.attention.KeyValueCacheParams": [[45, 12, 1, "", "fill_none_tensor_list"], [45, 12, 1, "", "get_first_past_key_value"], [45, 12, 1, "", "is_valid"]], "tensorrt_llm.layers.cast": [[45, 10, 1, "", "Cast"]], "tensorrt_llm.layers.cast.Cast": [[45, 12, 1, "", "forward"]], "tensorrt_llm.layers.conv": [[45, 10, 1, "", "Conv1d"], [45, 10, 1, "", "Conv2d"], [45, 10, 1, "", "ConvTranspose2d"]], "tensorrt_llm.layers.conv.Conv1d": [[45, 12, 1, "", "forward"]], "tensorrt_llm.layers.conv.Conv2d": [[45, 12, 1, "", "forward"]], "tensorrt_llm.layers.conv.ConvTranspose2d": [[45, 12, 1, "", "forward"]], "tensorrt_llm.layers.embedding": [[45, 10, 1, "", "Embedding"], [45, 10, 1, "", "PromptTuningEmbedding"]], "tensorrt_llm.layers.embedding.Embedding": [[45, 12, 1, "", "forward"], [45, 12, 1, "", "postprocess"], [45, 12, 1, "", "weight_loader"]], "tensorrt_llm.layers.embedding.PromptTuningEmbedding": [[45, 12, 1, "", "forward"]], "tensorrt_llm.layers.linear": [[45, 11, 1, "", "ColumnLinear"], [45, 10, 1, "", "Linear"], [45, 10, 1, "", "LinearBase"], [45, 10, 1, "", "RowLinear"]], "tensorrt_llm.layers.linear.Linear": [[45, 12, 1, "", "collect_and_bias"], [45, 12, 1, "", "postprocess"], [45, 12, 1, "", "tp_split_dim"]], "tensorrt_llm.layers.linear.LinearBase": [[45, 12, 1, "", "collect_and_bias"], [45, 12, 1, "", "forward"], [45, 12, 1, "", "get_weight"], [45, 12, 1, "", "multiply_and_lora"], [45, 12, 1, "", "multiply_collect"], [45, 12, 1, "", "tp_split_dim"], [45, 12, 1, "", "weight_is_kn"], [45, 12, 1, "", "weight_loader"]], "tensorrt_llm.layers.linear.RowLinear": [[45, 12, 1, "", "collect_and_bias"], [45, 12, 1, "", "tp_split_dim"]], "tensorrt_llm.layers.mlp": [[45, 10, 1, "", "FusedGatedMLP"], [45, 10, 1, "", "GatedMLP"], [45, 10, 1, "", "MLP"], [45, 14, 1, "", "fc_gate_lora"]], "tensorrt_llm.layers.mlp.FusedGatedMLP": [[45, 12, 1, "", "fc_gate"], [45, 12, 1, "", "fc_gate_plugin"], [45, 12, 1, "", "forward"]], "tensorrt_llm.layers.mlp.GatedMLP": [[45, 12, 1, "", "forward"]], "tensorrt_llm.layers.mlp.MLP": [[45, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization": [[45, 10, 1, "", "GroupNorm"], [45, 10, 1, "", "LayerNorm"], [45, 10, 1, "", "RmsNorm"]], "tensorrt_llm.layers.normalization.GroupNorm": [[45, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization.LayerNorm": [[45, 12, 1, "", "forward"]], "tensorrt_llm.layers.normalization.RmsNorm": [[45, 12, 1, "", "forward"]], "tensorrt_llm.layers.pooling": [[45, 10, 1, "", "AvgPool2d"]], "tensorrt_llm.layers.pooling.AvgPool2d": [[45, 12, 1, "", "forward"]], "tensorrt_llm.models": [[46, 10, 1, "", "BaichuanForCausalLM"], [46, 10, 1, "", "BertForQuestionAnswering"], [46, 10, 1, "", "BertForSequenceClassification"], [46, 10, 1, "", "BertModel"], [46, 10, 1, "", "BloomForCausalLM"], [46, 10, 1, "", "BloomModel"], [46, 10, 1, "", "ChatGLMConfig"], [46, 10, 1, "", "ChatGLMForCausalLM"], [46, 10, 1, "", "ChatGLMModel"], [46, 10, 1, "", "CogVLMConfig"], [46, 10, 1, "", "CogVLMForCausalLM"], [46, 10, 1, "", "DbrxConfig"], [46, 10, 1, "", "DbrxForCausalLM"], [46, 10, 1, "", "DecoderModel"], [46, 10, 1, "", "DeepseekForCausalLM"], [46, 10, 1, "", "DiT"], [46, 10, 1, "", "EncoderModel"], [46, 10, 1, "", "FalconConfig"], [46, 10, 1, "", "FalconForCausalLM"], [46, 10, 1, "", "FalconModel"], [46, 10, 1, "", "GPTConfig"], [46, 10, 1, "", "GPTForCausalLM"], [46, 10, 1, "", "GPTJConfig"], [46, 10, 1, "", "GPTJForCausalLM"], [46, 10, 1, "", "GPTJModel"], [46, 10, 1, "", "GPTModel"], [46, 10, 1, "", "GPTNeoXForCausalLM"], [46, 10, 1, "", "GPTNeoXModel"], [46, 10, 1, "", "GemmaConfig"], [46, 10, 1, "", "GemmaForCausalLM"], [46, 10, 1, "", "LLaMAConfig"], [46, 10, 1, "", "LLaMAForCausalLM"], [46, 10, 1, "", "LLaMAModel"], [46, 10, 1, "", "MPTForCausalLM"], [46, 10, 1, "", "MPTModel"], [46, 10, 1, "", "MambaForCausalLM"], [46, 10, 1, "", "MedusaConfig"], [46, 10, 1, "", "MedusaForCausalLm"], [46, 10, 1, "", "OPTForCausalLM"], [46, 10, 1, "", "OPTModel"], [46, 10, 1, "", "Phi3ForCausalLM"], [46, 10, 1, "", "Phi3Model"], [46, 10, 1, "", "PhiForCausalLM"], [46, 10, 1, "", "PhiModel"], [46, 10, 1, "", "PretrainedConfig"], [46, 10, 1, "", "PretrainedModel"], [46, 10, 1, "", "ReDrafterForCausalLM"], [46, 10, 1, "", "RecurrentGemmaForCausalLM"], [46, 10, 1, "", "SpeculativeDecodingMode"], [46, 10, 1, "", "WhisperEncoder"]], "tensorrt_llm.models.BaichuanForCausalLM": [[46, 11, 1, "", "config_class"], [46, 12, 1, "", "from_hugging_face"], [46, 12, 1, "", "quantize"]], "tensorrt_llm.models.BertForQuestionAnswering": [[46, 12, 1, "", "forward"]], "tensorrt_llm.models.BertForSequenceClassification": [[46, 12, 1, "", "forward"]], "tensorrt_llm.models.BertModel": [[46, 12, 1, "", "forward"]], "tensorrt_llm.models.BloomModel": [[46, 12, 1, "", "forward"]], "tensorrt_llm.models.ChatGLMConfig": [[46, 12, 1, "", "from_hugging_face"], [46, 12, 1, "", "to_dict"]], "tensorrt_llm.models.ChatGLMForCausalLM": [[46, 11, 1, "", "config_class"], [46, 12, 1, "", "from_hugging_face"], [46, 12, 1, "", "prepare_inputs"], [46, 12, 1, "", "quantize"]], "tensorrt_llm.models.ChatGLMModel": [[46, 12, 1, "", "forward"]], "tensorrt_llm.models.CogVLMConfig": [[46, 12, 1, "", "to_dict"]], "tensorrt_llm.models.CogVLMForCausalLM": [[46, 11, 1, "", "config_class"], [46, 12, 1, "", "default_plugin_config"], [46, 12, 1, "", "from_hugging_face"], [46, 12, 1, "", "quantize"]], "tensorrt_llm.models.DbrxConfig": [[46, 12, 1, "", "to_dict"]], "tensorrt_llm.models.DbrxForCausalLM": [[46, 11, 1, "", "config_class"]], "tensorrt_llm.models.DecoderModel": [[46, 12, 1, "", "check_config"], [46, 12, 1, "", "forward"], [46, 12, 1, "", "precompute_relative_attention_bias"], [46, 12, 1, "", "prepare_inputs"], [46, 12, 1, "", "use_lora"]], "tensorrt_llm.models.DeepseekForCausalLM": [[46, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.DiT": [[46, 12, 1, "", "check_config"], [46, 12, 1, "", "forward"], [46, 12, 1, "", "forward_with_cfg"], [46, 12, 1, "", "forward_without_cfg"], [46, 12, 1, "", "prepare_inputs"], [46, 12, 1, "", "unpatchify"]], "tensorrt_llm.models.EncoderModel": [[46, 12, 1, "", "check_config"], [46, 12, 1, "", "forward"], [46, 12, 1, "", "precompute_relative_attention_bias"], [46, 12, 1, "", "prepare_inputs"], [46, 12, 1, "", "use_lora"], [46, 12, 1, "", "use_prompt_tuning"]], "tensorrt_llm.models.FalconConfig": [[46, 12, 1, "", "from_hugging_face"], [46, 12, 1, "", "to_dict"]], "tensorrt_llm.models.FalconForCausalLM": [[46, 12, 1, "", "check_config"], [46, 11, 1, "", "config_class"], [46, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.FalconModel": [[46, 12, 1, "", "forward"]], "tensorrt_llm.models.GPTConfig": [[46, 12, 1, "", "from_hugging_face"], [46, 12, 1, "", "from_nemo"], [46, 12, 1, "", "to_dict"]], "tensorrt_llm.models.GPTForCausalLM": [[46, 11, 1, "", "config_class"], [46, 12, 1, "", "from_hugging_face"], [46, 12, 1, "", "from_nemo"], [46, 12, 1, "", "quantize"], [46, 12, 1, "", "use_lora"]], "tensorrt_llm.models.GPTJConfig": [[46, 12, 1, "", "from_hugging_face"], [46, 12, 1, "", "to_dict"]], "tensorrt_llm.models.GPTJForCausalLM": [[46, 11, 1, "", "config_class"], [46, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.GPTJModel": [[46, 12, 1, "", "forward"]], "tensorrt_llm.models.GPTModel": [[46, 12, 1, "", "forward"]], "tensorrt_llm.models.GPTNeoXModel": [[46, 12, 1, "", "forward"]], "tensorrt_llm.models.GemmaConfig": [[46, 11, 1, "", "GEMMA2_ADDED_FIELDS"], [46, 11, 1, "", "GEMMA_ADDED_FIELDS"], [46, 11, 1, "", "VERBATIM"], [46, 12, 1, "", "from_hugging_face"], [46, 12, 1, "", "gemma2_config"], [46, 13, 1, "", "is_gemma_2"], [46, 12, 1, "", "to_dict"]], "tensorrt_llm.models.GemmaForCausalLM": [[46, 11, 1, "", "NATIVE_QUANT_FLOW"], [46, 12, 1, "", "assert_valid_quant_algo"], [46, 11, 1, "", "config_class"], [46, 12, 1, "", "from_hugging_face"], [46, 12, 1, "", "quantize"]], "tensorrt_llm.models.LLaMAConfig": [[46, 12, 1, "", "from_hugging_face"], [46, 12, 1, "", "from_meta_ckpt"], [46, 12, 1, "", "to_dict"]], "tensorrt_llm.models.LLaMAForCausalLM": [[46, 11, 1, "", "config_class"], [46, 12, 1, "", "default_plugin_config"], [46, 12, 1, "", "from_hugging_face"], [46, 12, 1, "", "from_meta_ckpt"], [46, 12, 1, "", "quantize"], [46, 12, 1, "", "use_lora"]], "tensorrt_llm.models.LLaMAModel": [[46, 12, 1, "", "forward"]], "tensorrt_llm.models.MPTForCausalLM": [[46, 12, 1, "", "check_config"]], "tensorrt_llm.models.MPTModel": [[46, 12, 1, "", "forward"]], "tensorrt_llm.models.MambaForCausalLM": [[46, 12, 1, "", "forward"], [46, 12, 1, "", "prepare_inputs"]], "tensorrt_llm.models.MedusaConfig": [[46, 12, 1, "", "to_dict"]], "tensorrt_llm.models.MedusaForCausalLm": [[46, 11, 1, "", "config_class"], [46, 12, 1, "", "forward"], [46, 12, 1, "", "prepare_inputs"]], "tensorrt_llm.models.OPTForCausalLM": [[46, 12, 1, "", "check_config"]], "tensorrt_llm.models.OPTModel": [[46, 12, 1, "", "forward"]], "tensorrt_llm.models.Phi3ForCausalLM": [[46, 11, 1, "", "config_class"], [46, 12, 1, "", "from_hugging_face"], [46, 12, 1, "", "use_lora"]], "tensorrt_llm.models.Phi3Model": [[46, 12, 1, "", "forward"]], "tensorrt_llm.models.PhiForCausalLM": [[46, 12, 1, "", "check_config"], [46, 11, 1, "", "config_class"], [46, 12, 1, "", "from_hugging_face"]], "tensorrt_llm.models.PhiModel": [[46, 12, 1, "", "forward"]], "tensorrt_llm.models.PretrainedConfig": [[46, 12, 1, "", "for_each_rank"], [46, 12, 1, "", "from_checkpoint"], [46, 12, 1, "", "from_dict"], [46, 12, 1, "", "from_json_file"], [46, 12, 1, "", "get_config_group"], [46, 12, 1, "", "has_config_group"], [46, 13, 1, "", "kv_dtype"], [46, 13, 1, "", "quant_mode"], [46, 12, 1, "", "set_if_not_exist"], [46, 12, 1, "", "set_rank"], [46, 12, 1, "", "to_dict"], [46, 12, 1, "", "to_json_file"]], "tensorrt_llm.models.PretrainedModel": [[46, 12, 1, "", "check_config"], [46, 12, 1, "", "from_checkpoint"], [46, 12, 1, "", "from_config"], [46, 12, 1, "", "load"], [46, 12, 1, "", "prepare_inputs"], [46, 12, 1, "", "quantize"], [46, 12, 1, "", "release"], [46, 12, 1, "", "save_checkpoint"]], "tensorrt_llm.models.ReDrafterForCausalLM": [[46, 12, 1, "", "forward"], [46, 12, 1, "", "prepare_inputs"]], "tensorrt_llm.models.RecurrentGemmaForCausalLM": [[46, 12, 1, "", "forward"], [46, 12, 1, "", "prepare_inputs"], [46, 12, 1, "", "prepare_recurrent_inputs"]], "tensorrt_llm.models.SpeculativeDecodingMode": [[46, 11, 1, "", "DRAFT_TOKENS_EXTERNAL"], [46, 11, 1, "", "EXPLICIT_DRAFT_TOKENS"], [46, 11, 1, "", "LOOKAHEAD_DECODING"], [46, 11, 1, "", "MEDUSA"], [46, 11, 1, "", "NONE"], [46, 12, 1, "", "from_arguments"]], "tensorrt_llm.models.WhisperEncoder": [[46, 12, 1, "", "forward"], [46, 12, 1, "", "precompute_relative_attention_bias"], [46, 12, 1, "", "prepare_inputs"]], "tensorrt_llm.plugin": [[47, 10, 1, "", "PluginConfig"]], "tensorrt_llm.plugin.PluginConfig": [[47, 12, 1, "", "to_legacy_setting"]], "tensorrt_llm.quantization": [[48, 10, 1, "", "QuantAlgo"], [48, 10, 1, "", "QuantMode"], [48, 14, 1, "", "quantize_and_export"]], "tensorrt_llm.runtime": [[49, 10, 1, "", "ChatGLMGenerationSession"], [49, 10, 1, "", "EncDecModelRunner"], [49, 10, 1, "", "GenerationSequence"], [49, 10, 1, "", "GenerationSession"], [49, 10, 1, "", "KVCacheManager"], [49, 10, 1, "", "LogitsProcessor"], [49, 10, 1, "", "LogitsProcessorList"], [49, 10, 1, "", "ModelConfig"], [49, 10, 1, "", "ModelRunner"], [49, 10, 1, "", "ModelRunnerCpp"], [49, 10, 1, "", "MultimodalModelRunner"], [49, 10, 1, "", "QWenForCausalLMGenerationSession"], [49, 10, 1, "", "SamplingConfig"], [49, 10, 1, "", "Session"], [49, 10, 1, "", "StoppingCriteria"], [49, 10, 1, "", "StoppingCriteriaList"], [49, 10, 1, "", "TensorInfo"], [49, 14, 1, "", "decode_words_list"]], "tensorrt_llm.runtime.EncDecModelRunner": [[49, 12, 1, "", "encoder_run"], [49, 12, 1, "", "from_engine"], [49, 12, 1, "", "generate"], [49, 12, 1, "", "process_input"]], "tensorrt_llm.runtime.GenerationSequence": [[49, 12, 1, "", "get_batch_idx"], [49, 12, 1, "", "get_seq_idx"]], "tensorrt_llm.runtime.GenerationSession": [[49, 11, 1, "", "batch_size"], [49, 11, 1, "", "buffer_allocated"], [49, 13, 1, "", "context_mem_size"], [49, 13, 1, "", "conv_kernel"], [49, 13, 1, "", "cross_attention"], [49, 11, 1, "", "cuda_graph_mode"], [49, 12, 1, "", "cuda_stream_guard"], [49, 11, 1, "", "debug_mode"], [49, 11, 1, "", "debug_tensors_to_save"], [49, 12, 1, "", "decode"], [49, 12, 1, "", "decode_batch"], [49, 12, 1, "", "decode_regular"], [49, 12, 1, "", "decode_stream"], [49, 11, 1, "", "device"], [49, 13, 1, "", "dtype"], [49, 12, 1, "", "dump_debug_buffers"], [49, 12, 1, "", "early_stop_criteria"], [49, 13, 1, "", "engine_inspector"], [49, 12, 1, "", "filter_medusa_logits"], [49, 12, 1, "", "finalize_decoder"], [49, 12, 1, "", "find_best_medusa_path"], [49, 13, 1, "", "first_layer"], [49, 13, 1, "", "gather_context_logits"], [49, 13, 1, "", "gather_generation_logits"], [49, 12, 1, "", "get_next_medusa_tokens"], [49, 12, 1, "", "get_num_heads_kv"], [49, 12, 1, "", "handle_per_step"], [49, 13, 1, "", "has_position_embedding"], [49, 13, 1, "", "has_token_type_embedding"], [49, 13, 1, "", "head_size"], [49, 13, 1, "", "hidden_size"], [49, 13, 1, "", "is_medusa_mode"], [49, 13, 1, "", "is_redrafter_mode"], [49, 13, 1, "", "kv_cache_type"], [49, 13, 1, "", "last_layer"], [49, 12, 1, "", "locate_accepted_draft_tokens"], [49, 11, 1, "", "mapping"], [49, 13, 1, "", "max_draft_tokens"], [49, 13, 1, "", "max_prompt_embedding_table_size"], [49, 12, 1, "", "medusa_decode_and_verify"], [49, 11, 1, "", "medusa_paths"], [49, 11, 1, "", "medusa_position_offsets"], [49, 11, 1, "", "medusa_temperature"], [49, 11, 1, "", "medusa_topks"], [49, 11, 1, "", "medusa_tree_ids"], [49, 12, 1, "", "next_medusa_input_ids"], [49, 11, 1, "", "num_draft_tokens"], [49, 13, 1, "", "num_heads"], [49, 13, 1, "", "num_layers"], [49, 13, 1, "", "num_medusa_heads"], [49, 13, 1, "", "paged_kv_cache"], [49, 13, 1, "", "paged_state"], [49, 12, 1, "", "pp_communicate_final_output_ids"], [49, 12, 1, "", "pp_communicate_new_tokens"], [49, 12, 1, "", "process_logits_including_draft"], [49, 13, 1, "", "profiler"], [49, 13, 1, "", "quant_mode"], [49, 13, 1, "", "remove_input_padding"], [49, 12, 1, "", "reorder_kv_cache_for_beam_search"], [49, 13, 1, "", "rnn_conv_dim_size"], [49, 13, 1, "", "rnn_head_size"], [49, 13, 1, "", "rnn_hidden_size"], [49, 11, 1, "", "runtime"], [49, 12, 1, "", "setup"], [49, 13, 1, "", "state_dtype"], [49, 13, 1, "", "state_size"], [49, 13, 1, "", "tokens_per_block"], [49, 12, 1, "", "update_output_ids_by_offset"], [49, 13, 1, "", "use_gpt_attention_plugin"], [49, 13, 1, "", "use_kv_cache"], [49, 13, 1, "", "use_lora_plugin"], [49, 13, 1, "", "use_mamba_conv1d_plugin"], [49, 13, 1, "", "vocab_size"]], "tensorrt_llm.runtime.KVCacheManager": [[49, 12, 1, "", "add_sequence"], [49, 12, 1, "", "get_block_offsets"], [49, 12, 1, "", "step"]], "tensorrt_llm.runtime.ModelConfig": [[49, 11, 1, "", "conv_kernel"], [49, 11, 1, "", "cross_attention"], [49, 11, 1, "", "dtype"], [49, 11, 1, "", "gather_context_logits"], [49, 11, 1, "", "gather_generation_logits"], [49, 11, 1, "", "gpt_attention_plugin"], [49, 11, 1, "", "gpu_weights_percent"], [49, 11, 1, "", "has_position_embedding"], [49, 11, 1, "", "has_token_type_embedding"], [49, 11, 1, "", "head_size"], [49, 11, 1, "", "hidden_size"], [49, 11, 1, "", "kv_cache_type"], [49, 11, 1, "", "layer_types"], [49, 11, 1, "", "lora_plugin"], [49, 11, 1, "", "lora_target_modules"], [49, 11, 1, "", "mamba_conv1d_plugin"], [49, 11, 1, "", "max_batch_size"], [49, 11, 1, "", "max_beam_width"], [49, 11, 1, "", "max_medusa_tokens"], [49, 11, 1, "", "max_prompt_embedding_table_size"], [49, 11, 1, "", "model_name"], [49, 11, 1, "", "num_heads"], [49, 11, 1, "", "num_kv_heads"], [49, 11, 1, "", "num_kv_heads_per_layer"], [49, 11, 1, "", "num_layers"], [49, 11, 1, "", "num_medusa_heads"], [49, 11, 1, "", "paged_state"], [49, 11, 1, "", "quant_mode"], [49, 11, 1, "", "redrafter_draft_len_per_beam"], [49, 11, 1, "", "redrafter_num_beams"], [49, 11, 1, "", "remove_input_padding"], [49, 11, 1, "", "rnn_conv_dim_size"], [49, 11, 1, "", "rnn_head_size"], [49, 11, 1, "", "rnn_hidden_size"], [49, 11, 1, "", "skip_cross_qkv"], [49, 11, 1, "", "state_dtype"], [49, 11, 1, "", "state_size"], [49, 11, 1, "", "tokens_per_block"], [49, 11, 1, "", "trtllm_modules_to_hf_modules"], [49, 11, 1, "", "vocab_size"]], "tensorrt_llm.runtime.ModelRunner": [[49, 13, 1, "", "dtype"], [49, 12, 1, "", "from_dir"], [49, 12, 1, "", "from_engine"], [49, 13, 1, "", "gather_context_logits"], [49, 13, 1, "", "gather_generation_logits"], [49, 12, 1, "", "generate"], [49, 13, 1, "", "hidden_size"], [49, 13, 1, "", "mapping"], [49, 13, 1, "", "max_prompt_embedding_table_size"], [49, 13, 1, "", "max_sequence_length"], [49, 13, 1, "", "num_heads"], [49, 13, 1, "", "num_layers"], [49, 13, 1, "", "remove_input_padding"], [49, 12, 1, "", "serialize_engine"], [49, 13, 1, "", "use_lora_plugin"], [49, 13, 1, "", "vocab_size"], [49, 13, 1, "", "vocab_size_padded"]], "tensorrt_llm.runtime.ModelRunnerCpp": [[49, 13, 1, "", "dtype"], [49, 12, 1, "", "from_dir"], [49, 13, 1, "", "gather_context_logits"], [49, 13, 1, "", "gather_generation_logits"], [49, 12, 1, "", "generate"], [49, 13, 1, "", "hidden_size"], [49, 13, 1, "", "max_prompt_embedding_table_size"], [49, 13, 1, "", "max_sequence_length"], [49, 13, 1, "", "num_heads"], [49, 13, 1, "", "num_layers"], [49, 13, 1, "", "remove_input_padding"], [49, 13, 1, "", "vocab_size"], [49, 13, 1, "", "vocab_size_padded"]], "tensorrt_llm.runtime.MultimodalModelRunner": [[49, 12, 1, "", "generate"], [49, 12, 1, "", "get_visual_features"], [49, 12, 1, "", "init_image_encoder"], [49, 12, 1, "", "init_llm"], [49, 12, 1, "", "init_tokenizer"], [49, 12, 1, "", "load_test_image"], [49, 12, 1, "", "prepare_position_ids_for_cogvlm"], [49, 12, 1, "", "preprocess"], [49, 12, 1, "", "ptuning_setup"], [49, 12, 1, "", "ptuning_setup_fuyu"], [49, 12, 1, "", "ptuning_setup_llava_next"], [49, 12, 1, "", "ptuning_setup_phi3"], [49, 12, 1, "", "run"], [49, 12, 1, "", "setup_fake_prompts"], [49, 12, 1, "", "setup_fake_prompts_vila"], [49, 12, 1, "", "setup_inputs"], [49, 12, 1, "", "split_prompt_by_images"], [49, 12, 1, "", "tokenizer_image_token"], [49, 12, 1, "", "video_preprocess"]], "tensorrt_llm.runtime.QWenForCausalLMGenerationSession": [[49, 12, 1, "", "generate"]], "tensorrt_llm.runtime.SamplingConfig": [[49, 11, 1, "", "bad_words_list"], [49, 11, 1, "", "beam_search_diversity_rate"], [49, 11, 1, "", "early_stopping"], [49, 11, 1, "", "end_id"], [49, 11, 1, "", "frequency_penalty"], [49, 11, 1, "", "length_penalty"], [49, 11, 1, "", "max_attention_window_size"], [49, 11, 1, "", "max_new_tokens"], [49, 11, 1, "", "min_length"], [49, 11, 1, "", "no_repeat_ngram_size"], [49, 11, 1, "", "num_beams"], [49, 11, 1, "", "output_cum_log_probs"], [49, 11, 1, "", "output_log_probs"], [49, 11, 1, "", "output_sequence_lengths"], [49, 11, 1, "", "pad_id"], [49, 11, 1, "", "presence_penalty"], [49, 11, 1, "", "random_seed"], [49, 11, 1, "", "repetition_penalty"], [49, 11, 1, "", "return_dict"], [49, 11, 1, "", "sink_token_length"], [49, 11, 1, "", "stop_words_list"], [49, 11, 1, "", "temperature"], [49, 11, 1, "", "top_k"], [49, 11, 1, "", "top_p"], [49, 11, 1, "", "top_p_decay"], [49, 11, 1, "", "top_p_min"], [49, 11, 1, "", "top_p_reset_ids"], [49, 12, 1, "", "update"], [49, 11, 1, "", "use_beam_hyps"]], "tensorrt_llm.runtime.Session": [[49, 13, 1, "", "context"], [49, 13, 1, "", "context_mem_size"], [49, 13, 1, "", "engine"], [49, 12, 1, "", "from_engine"], [49, 12, 1, "", "from_serialized_engine"], [49, 12, 1, "", "infer_shapes"], [49, 12, 1, "", "run"], [49, 13, 1, "", "runtime"], [49, 12, 1, "", "set_shapes"]], "tensorrt_llm.runtime.TensorInfo": [[49, 11, 1, "", "dtype"], [49, 11, 1, "", "name"], [49, 11, 1, "", "shape"]]}, "objtypes": {"0": "c:macro", "1": "cpp:type", "2": "cpp:enum", "3": "cpp:enumerator", "4": "cpp:class", "5": "cpp:function", "6": "cpp:functionParam", "7": "cpp:member", "8": "cpp:templateParam", "9": "py:module", "10": "py:class", "11": "py:attribute", "12": "py:method", "13": "py:property", "14": "py:function"}, "objnames": {"0": ["c", "macro", "C macro"], "1": ["cpp", "type", "C++ type"], "2": ["cpp", "enum", "C++ enum"], "3": ["cpp", "enumerator", "C++ enumerator"], "4": ["cpp", "class", "C++ class"], "5": ["cpp", "function", "C++ function"], "6": ["cpp", "functionParam", "C++ function parameter"], "7": ["cpp", "member", "C++ member"], "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"]}, "titleterms": {"executor": [0, 22], "h": [0, 1], "serial": 0, "tensor": [0, 3, 4, 6, 8, 51], "type": [0, 42], "runtim": [1, 5, 8, 12, 24, 25, 30, 42, 49, 51], "buffermanag": 1, "common": [1, 30, 40], "cudaev": 1, "cudastream": 1, "decodinginput": 1, "decodingoutput": 1, "explicitdrafttokensbuff": 1, "generationinput": 1, "generationoutput": 1, "gptdecod": 1, "gptdecoderbatch": 1, "gptjsonconfig": 1, "gptsession": 1, "ibuff": 1, "igptdecoderbatch": 1, "istatefulgptdecod": 1, "itensor": 1, "ipcutil": 1, "lookaheadmodul": 1, "loracach": [1, 8], "loracachepagemanagerconfig": 1, "loramodul": 1, "medusamodul": 1, "memorycount": 1, "modelconfig": 1, "prompttuningparam": 1, "rawengin": 1, "request": [1, 2, 7, 22], "samplingconfig": 1, "speculativedecodingmod": 1, "speculativedecodingmodul": 1, "tllmlogger": 1, "worldconfig": 1, "lookaheadbuff": 1, "The": [2, 5, 22, 52], "batch": [2, 4, 5, 40, 42], "manag": [2, 6], "tensorrt": [2, 3, 11, 12, 13, 14, 15, 17, 18, 20, 23, 24, 25, 31, 40, 42, 50, 51, 55, 56], "llm": [2, 3, 11, 13, 14, 15, 17, 18, 20, 23, 24, 25, 31, 33, 34, 35, 36, 37, 38, 40, 42, 50, 51, 53, 55, 56], "api": [2, 6, 9, 15, 22, 39, 50, 55], "get": [2, 23], "send": [2, 22], "callback": 2, "interrupt": 2, "statist": 2, "logit": [2, 21, 22], "post": [2, 22], "processor": [2, 22], "option": [2, 22, 24, 41, 42], "other": 2, "mandatori": 2, "gptmanag": [2, 8], "paramet": [2, 5], "respons": [2, 7, 22], "content": 2, "design": 2, "multi": [2, 4, 12, 40, 41, 42, 53], "gpu": [2, 9, 12, 16, 40, 41, 42, 51], "execut": [2, 41, 54, 56], "In": [2, 4, 5, 40, 42], "flight": [2, 4, 5, 40, 42], "triton": [2, 50, 56], "infer": [2, 7, 20, 40, 41, 50, 51, 56], "server": [2, 50, 56], "expert": 3, "parallel": [3, 8, 21, 33, 42], "mixtur": 3, "moe": 3, "v": [3, 18], "how": [3, 29, 42], "enabl": [3, 29], "head": [4, 42], "queri": 4, "group": 4, "attent": [4, 11, 40, 42, 45], "import": 4, "note": [4, 55], "pad": [4, 42], "pack": 4, "context": [4, 42], "gener": [4, 30, 34, 35, 36, 37], "phase": 4, "fp8": [4, 11, 17, 40, 42, 52], "fmha": 4, "xqa": [4, 19], "optim": [4, 42], "chunk": [4, 42], "kv": [4, 11, 29, 42, 51], "cach": [4, 11, 29, 42, 51], "contigu": 4, "page": [4, 40, 42], "int8": [4, 52], "slide": 4, "window": [4, 25, 27, 40, 42], "cyclic": 4, "roll": 4, "buffer": [4, 51], "streamingllm": 4, "beam": [4, 22], "search": 4, "input": [4, 42], "qkv": 4, "rotari": 4, "posit": 4, "embed": [4, 42, 45], "rope": 4, "alibi": 4, "scale": [4, 11], "factor": [4, 11], "": [4, 17, 20, 23], "cross": 4, "rel": 4, "bia": 4, "rab": 4, "c": [5, 22, 24, 25, 51], "gpt": [5, 8, 42], "overview": [5, 11, 13, 15, 40, 43, 56], "model": [5, 10, 12, 13, 14, 31, 41, 42, 46, 50, 53, 54, 55, 56], "configur": [5, 8, 30], "world": 5, "sampl": [5, 30, 56], "session": 5, "intern": 5, "compon": 5, "support": [5, 12, 13, 24, 31, 40, 52, 53], "know": 5, "issu": [5, 43, 51, 55], "futur": [5, 30], "chang": [5, 9, 55], "graph": 6, "rewrit": 6, "modul": [6, 8], "when": 6, "us": [6, 8, 51, 56], "relat": [6, 50], "method": [6, 20], "flayerinfo": 6, "retriev": 6, "high": 6, "level": 6, "inform": [6, 50], "function": [6, 13, 44], "pattern": [6, 12], "record_signatur": 6, "decor": 6, "requir": 6, "classic": 6, "workflow": [6, 13, 15], "run": [8, 9, 25, 43, 50], "2b": 8, "lora": [8, 21], "cpp": 8, "format": 8, "detail": [8, 52], "exampl": [8, 11, 13, 22, 31, 32, 41], "id": 8, "map": 8, "With": [9, 40], "weight": [9, 10, 11, 12, 13, 14, 51, 52], "stream": [9, 36], "reduc": [9, 42], "memori": [9, 18, 29, 42, 51], "consumpt": 9, "ad": 10, "step": [10, 24, 50], "1": [10, 24, 51, 55], "write": 10, "part": 10, "2": [10, 19, 24, 51, 53], "implement": 10, "convers": [10, 15], "3": [10, 51], "regist": 10, "new": [10, 19], "4": [10, 17], "verifi": 10, "refer": [10, 23, 39], "checkpoint": [11, 56], "prepar": [11, 31, 43], "config": [11, 21], "rank": [11, 41], "mlp": [11, 42, 45], "layernorm": 11, "quantiz": [11, 15, 20, 30, 38, 48, 52], "awq": [11, 16, 52], "build": [11, 15, 21, 24, 25, 30, 42, 43, 54, 56], "engin": [11, 12, 31, 43, 50, 56], "make": 11, "evalu": 11, "definit": 12, "compil": [12, 50], "bind": [12, 22, 24], "match": 12, "fusion": [12, 42], "plugin": [12, 21, 42, 47], "node": [12, 40], "loader": 13, "translat": 13, "load": 13, "postprocess": 13, "nativ": [13, 40], "custom": [13, 30], "kei": [13, 28, 55], "name": [13, 21], "layout": 13, "fulli": 13, "troubl": 13, "shoot": 13, "architectur": [14, 23], "cli": 15, "tool": 15, "falcon": 16, "180b": 16, "singl": [16, 41], "h200": [16, 18, 19], "int4": [16, 52], "6": 16, "7x": 16, "faster": 16, "llama": [16, 19, 43], "70b": [16, 19], "over": 16, "a100": [16, 17], "up": [16, 19, 20, 42], "close": [16, 19], "h100": [17, 18], "ha": 17, "6x": 17, "perform": [17, 20, 23, 29, 41, 42, 56], "achiev": [17, 18], "10": [17, 55], "000": [17, 18], "tok": 17, "100m": 17, "first": 17, "token": [17, 18, 30, 42], "mlperf": 17, "what": [17, 20, 40], "i": [17, 51], "nearli": 18, "12": [18, 55], "sec": 18, "llama2": 18, "13b": 18, "latest": [18, 40], "hbm": 18, "kernel": 19, "provid": 19, "4x": 19, "more": 19, "throughput": [19, 43], "within": 19, "same": 19, "latenc": 19, "budget": 19, "increas": 19, "speed": 20, "sota": 20, "techniqu": 20, "trt": 20, "benchmark": [20, 43], "accuraci": 20, "best": [20, 42], "practic": [20, 42], "choos": 20, "right": 20, "come": 20, "next": [20, 50], "trtllm": 21, "argument": 21, "specul": [21, 56], "decod": [21, 51, 56], "auto": [21, 33], "class": 22, "result": [22, 43], "differ": 22, "width": 22, "python": [22, 24, 51], "welcom": 23, "document": 23, "start": [23, 50], "instal": [23, 26, 27, 54], "advanc": 23, "indic": 23, "tabl": 23, "from": [24, 25, 31, 56], "sourc": [24, 25], "code": [24, 25], "linux": [24, 26], "prerequisit": [24, 25, 50], "docker": [24, 25], "imag": [24, 25], "One": 24, "By": 24, "creat": 24, "contain": [24, 25], "link": [24, 25, 54], "header": 24, "file": [24, 25], "desktop": 25, "acquir": 25, "an": [25, 56], "extract": 25, "bare": 25, "metal": 25, "featur": [28, 41, 55], "reus": 29, "p": 29, "tune": [29, 42], "expect": 29, "situat": 29, "can": [29, 40], "prevent": 29, "offload": 29, "host": 29, "disabl": 30, "asyncio": 30, "base": 30, "style": 30, "introduct": 31, "hug": 31, "face": 31, "hub": 31, "local": 31, "script": 32, "async": [35, 36], "distribut": 37, "about": 40, "you": 40, "do": 40, "analysi": 41, "descript": 41, "usag": [41, 51], "time": [41, 51], "command": [41, 43], "line": 41, "environ": 41, "variabl": [41, 43], "coordin": 41, "nvidia": 41, "nsight": 41, "system": 41, "launch": 41, "profil": [41, 42], "ifb": 41, "iter": 41, "To": 42, "measur": [42, 43], "max_batch_s": 42, "max_seq_len": 42, "max_num_token": 42, "multipl": 42, "fuse": [42, 43], "remov": 42, "sequenc": 42, "norm": 42, "share": 42, "look": 42, "horizont": 42, "gate": [42, 43], "gemm": 42, "swiglu": 42, "small": 42, "size": [42, 51], "bert": 42, "max": 42, "free": 42, "fraction": 42, "schedul": 42, "polici": 42, "overlap": 42, "maximum": 42, "known": [43, 51, 55], "matmul": 43, "silu": 43, "reproduc": 43, "dataset": 43, "layer": 45, "activ": [45, 51], "cast": 45, "conv": 45, "linear": 45, "normal": 45, "pool": [45, 51], "quick": 50, "guid": 50, "deploi": 50, "understand": 51, "o": 51, "except": 51, "Not": 51, "recommend": 51, "faq": 51, "numer": 52, "precis": 52, "fp32": 52, "fp16": 52, "bf16": 52, "dequant": 52, "q": 52, "dq": 52, "smoothquant": 52, "w8a8": 52, "onli": 52, "w4a16": 52, "w8a16": 52, "gptq": 52, "hopper": 52, "matrix": [52, 53], "technic": 52, "quantmod": 52, "flag": 52, "modal": 53, "hardwar": 53, "softwar": 53, "troubleshoot": 54, "error": 54, "cudnn": 54, "debug": 54, "unit": 54, "test": 54, "e2": 54, "tip": 54, "releas": 55, "0": 55, "13": 55, "enhanc": 55, "updat": 55, "fix": 55, "infrastructur": 55, "11": 55, "announc": 55, "9": 55, "limit": [55, 56], "8": 55, "7": 55, "improv": 56, "draft": 56, "approach": 56, "medusa": 56, "tree": 56, "redraft": 56, "lookahead": 56, "convert": 56}, "envversion": {"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.viewcode": 1, "sphinx.ext.todo": 2, "sphinx": 60}, "alltitles": {"Executor": [[0, "executor"]], "executor.h": [[0, "executor-h"]], "serialization.h": [[0, "serialization-h"]], "tensor.h": [[0, "tensor-h"]], "types.h": [[0, "types-h"]], "Runtime": [[1, "runtime"], [12, "runtime"], [49, "module-tensorrt_llm"]], "bufferManager.h": [[1, "buffermanager-h"]], "common.h": [[1, "common-h"]], "cudaEvent.h": [[1, "cudaevent-h"]], "cudaStream.h": [[1, "cudastream-h"]], "decodingInput.h": [[1, "decodinginput-h"]], "decodingOutput.h": [[1, "decodingoutput-h"]], "explicitDraftTokensBuffers.h": [[1, "explicitdrafttokensbuffers-h"]], "generationInput.h": [[1, "generationinput-h"]], "generationOutput.h": [[1, "generationoutput-h"]], "gptDecoder.h": [[1, "gptdecoder-h"]], "gptDecoderBatched.h": [[1, "gptdecoderbatched-h"]], "gptJsonConfig.h": [[1, "gptjsonconfig-h"]], "gptSession.h": [[1, "gptsession-h"]], "iBuffer.h": [[1, "ibuffer-h"]], "iGptDecoderBatched.h": [[1, "igptdecoderbatched-h"]], "iStatefulGptDecoder.h": [[1, "istatefulgptdecoder-h"]], "iTensor.h": [[1, "itensor-h"]], "ipcUtils.h": [[1, "ipcutils-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"]], "samplingConfig.h": [[1, "samplingconfig-h"]], "speculativeDecodingMode.h": [[1, "speculativedecodingmode-h"]], "speculativeDecodingModule.h": [[1, "speculativedecodingmodule-h"]], "tllmLogger.h": [[1, "tllmlogger-h"]], "worldConfig.h": [[1, "worldconfig-h"]], "lookaheadBuffers.h": [[1, "lookaheadbuffers-h"]], "The Batch Manager in TensorRT-LLM": [[2, "the-batch-manager-in-tensorrt-llm"]], "The Batch Manager API": [[2, "the-batch-manager-api"]], "Get and Send Callbacks": [[2, "get-and-send-callbacks"]], "Request Interruption": [[2, "request-interruption"]], "Statistics": [[2, "statistics"]], "Logits Post-Processor (optional)": [[2, "logits-post-processor-optional"], [22, "logits-post-processor-optional"]], "Other mandatory GptManager parameters": [[2, "other-mandatory-gptmanager-parameters"]], "Optional GptManager parameters": [[2, "optional-gptmanager-parameters"]], "Responses content": [[2, "responses-content"]], "GptManager Design": [[2, "gptmanager-design"]], "Multi-GPU execution": [[2, "multi-gpu-execution"]], "In-flight Batching with the Triton Inference Server": [[2, "in-flight-batching-with-the-triton-inference-server"]], "Expert Parallelism in TensorRT-LLM": [[3, "expert-parallelism-in-tensorrt-llm"]], "Mixture of Experts (MoE)": [[3, "mixture-of-experts-moe"]], "Tensor Parallel vs Expert Parallel": [[3, "tensor-parallel-vs-expert-parallel"]], "How to Enable": [[3, "how-to-enable"]], "Multi-Head, Multi-Query, and Group-Query Attention": [[4, "multi-head-multi-query-and-group-query-attention"]], "Important Note": [[4, "important-note"]], "Padded and Packed Tensors": [[4, "padded-and-packed-tensors"]], "Context and Generation Phases": [[4, "context-and-generation-phases"]], "Context Phase": [[4, "context-phase"]], "FP8 Context FMHA": [[4, "fp8-context-fmha"]], "Generation Phase": [[4, "generation-phase"]], "XQA Optimization": [[4, "xqa-optimization"]], "In-flight Batching": [[4, "in-flight-batching"]], "Chunked Context": [[4, "chunked-context"], [42, "chunked-context"]], "KV Cache": [[4, "kv-cache"]], "Contiguous KV Cache": [[4, "contiguous-kv-cache"]], "Paged KV Cache": [[4, "paged-kv-cache"], [42, "paged-kv-cache"]], "INT8/FP8 KV Caches": [[4, "int8-fp8-kv-caches"]], "Sliding Window Attention, Cyclic (Rolling Buffer) KV Cache": [[4, "sliding-window-attention-cyclic-rolling-buffer-kv-cache"]], "StreamingLLM": [[4, "streamingllm"]], "Beam-Search": [[4, "beam-search"]], "Input QKV tensor": [[4, "input-qkv-tensor"]], "Rotary Positional Embedding (RoPE)": [[4, "rotary-positional-embedding-rope"]], "ALiBi": [[4, "alibi"]], "Scaling factor(s)": [[4, "scaling-factor-s"]], "Cross Attention": [[4, "cross-attention"]], "Relative Attention Bias (RAB)": [[4, "relative-attention-bias-rab"]], "C++ GPT Runtime": [[5, "c-gpt-runtime"]], "Overview": [[5, "overview"], [11, "overview"], [13, "overview"], [15, "overview"], [40, "overview"], [43, "overview"], [56, "overview"]], "Model Configuration": [[5, "model-configuration"]], "World Configuration": [[5, "world-configuration"]], "Sampling Parameters": [[5, "sampling-parameters"]], "The Session": [[5, "the-session"]], "Internal Components": [[5, "internal-components"]], "In-flight Batching Support": [[5, "in-flight-batching-support"]], "Know Issues and Future Changes": [[5, "know-issues-and-future-changes"]], "Graph Rewriting Module": [[6, "graph-rewriting-module"]], "When to Use Graph Rewriting?": [[6, "when-to-use-graph-rewriting"]], "Graph Rewriting APIs": [[6, "graph-rewriting-apis"]], "Tensor-Related Methods": [[6, "tensor-related-methods"]], "FLayerInfo for Retrieving High-Level Information for a Functional": [[6, "flayerinfo-for-retrieving-high-level-information-for-a-functional"]], "Pattern and Pattern Manager": [[6, "pattern-and-pattern-manager"]], "@record_signature to Decorate Functionals Requiring FLayerInfo": [[6, "record-signature-to-decorate-functionals-requiring-flayerinfo"]], "Classical Workflow": [[6, "classical-workflow"]], "Inference Request": [[7, "inference-request"]], "Responses": [[7, "responses"]], "Run gpt-2b + LoRA using GptManager / cpp runtime": [[8, "run-gpt-2b-lora-using-gptmanager-cpp-runtime"]], "LoRA tensor format details": [[8, "lora-tensor-format-details"]], "Example LoRA tensors": [[8, "example-lora-tensors"]], "LoRA Module id mapping": [[8, "lora-module-id-mapping"]], "LoraCache configuration": [[8, "loracache-configuration"]], "LoRA with tensor parallel": [[8, "lora-with-tensor-parallel"]], "Running With Weight Streaming to Reduce GPU Memory Consumption": [[9, "running-with-weight-streaming-to-reduce-gpu-memory-consumption"]], "API Changes": [[9, "api-changes"], [55, "api-changes"], [55, "id3"], [55, "id9"], [55, "id15"], [55, "id21"]], "Adding a Model": [[10, "adding-a-model"]], "Step 1. Write Modeling Part": [[10, "step-1-write-modeling-part"]], "Step 2. Implement Weight Conversion": [[10, "step-2-implement-weight-conversion"]], "Step 3. Register New Model": [[10, "step-3-register-new-model"]], "Step 4. Verify New Model": [[10, "step-4-verify-new-model"]], "Reference": [[10, "reference"], [23, null]], "TensorRT-LLM Checkpoint": [[11, "tensorrt-llm-checkpoint"]], "Prepare the TensorRT-LLM Checkpoint": [[11, "prepare-the-tensorrt-llm-checkpoint"]], "Config": [[11, "config"]], "Rank Weights": [[11, "rank-weights"]], "Attention Weights": [[11, "attention-weights"]], "MLP Weights": [[11, "mlp-weights"]], "LayerNorm Weights": [[11, "layernorm-weights"]], "KV Cache Quantization Scaling Factors": [[11, "kv-cache-quantization-scaling-factors"]], "FP8 Quantization Scaling Factors": [[11, "fp8-quantization-scaling-factors"]], "AWQ Quantization Scaling Factors": [[11, "awq-quantization-scaling-factors"]], "Example": [[11, "example"]], "Build Checkpoint into TensorRT Engine": [[11, "build-checkpoint-into-tensorrt-engine"]], "Make Evaluation": [[11, "make-evaluation"]], "Model Definition": [[12, "model-definition"]], "Compilation": [[12, "compilation"]], "TensorRT Compiler": [[12, "tensorrt-compiler"]], "Model Engine": [[12, "model-engine"]], "Weight Bindings": [[12, "weight-bindings"]], "Pattern-Matching and Fusion": [[12, "pattern-matching-and-fusion"]], "Plugins": [[12, "plugins"]], "Multi-GPU and Multi-Node Support": [[12, "multi-gpu-and-multi-node-support"]], "TensorRT-LLM Model Weights Loader": [[13, "tensorrt-llm-model-weights-loader"]], "Workflow": [[13, "workflow"]], "Translator": [[13, "translator"]], "Loading function": [[13, "loading-function"]], "Postprocessing functions": [[13, "postprocessing-functions"]], "Examples": [[13, "examples"], [32, "examples"], [41, "examples"]], "Natively supported models": [[13, "natively-supported-models"]], "Models with customized key names": [[13, "models-with-customized-key-names"]], "Models with customized weight layout": [[13, "models-with-customized-weight-layout"]], "Fully customized": [[13, "fully-customized"]], "Trouble shooting": [[13, "trouble-shooting"]], "TensorRT-LLM Architecture": [[14, "tensorrt-llm-architecture"]], "Model Weights": [[14, "model-weights"]], "TensorRT-LLM Build Workflow": [[15, "tensorrt-llm-build-workflow"]], "Conversion APIs": [[15, "conversion-apis"]], "Quantization APIs": [[15, "quantization-apis"]], "Build APIs": [[15, "build-apis"]], "CLI Tools": [[15, "cli-tools"]], "Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100": [[16, "falcon-180b-on-a-single-h200-gpu-with-int4-awq-and-6-7x-faster-llama-70b-over-a100"]], "Falcon-180B on a single H200 with INT4 AWQ": [[16, "falcon-180b-on-a-single-h200-with-int4-awq"]], "Llama-70B on H200 up to 6.7x A100": [[16, "llama-70b-on-h200-up-to-6-7x-a100"]], "Closing": [[16, "closing"], [19, "closing"]], "H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token": [[17, "h100-has-4-6x-a100-performance-in-tensorrt-llm-achieving-10-000-tok-s-at-100ms-to-first-token"]], "MLPerf on H100 with FP8": [[17, "mlperf-on-h100-with-fp8"]], "What is H100 FP8?": [[17, "what-is-h100-fp8"]], "H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM": [[18, "h200-achieves-nearly-12-000-tokens-sec-on-llama2-13b-with-tensorrt-llm"]], "H200 vs H100": [[18, "h200-vs-h100"]], "Latest HBM Memory": [[18, "latest-hbm-memory"]], "New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget": [[19, "new-xqa-kernel-provides-2-4x-more-llama-70b-throughput-within-the-same-latency-budget"]], "Llama-70B on H200 up to 2.4x increased throughput with XQA within same latency budget": [[19, "llama-70b-on-h200-up-to-2-4x-increased-throughput-with-xqa-within-same-latency-budget"]], "Speed up inference with SOTA quantization techniques in TRT-LLM": [[20, "speed-up-inference-with-sota-quantization-techniques-in-trt-llm"]], "Quantization in TensorRT-LLM": [[20, "quantization-in-tensorrt-llm"]], "Benchmark": [[20, "benchmark"]], "Performance": [[20, "performance"], [23, null]], "Accuracy": [[20, "accuracy"]], "Best practices to choose the right quantization methods": [[20, "best-practices-to-choose-the-right-quantization-methods"]], "What\u2019s coming next": [[20, "whats-coming-next"]], "trtllm-build": [[21, "trtllm-build"]], "Named Arguments": [[21, "tensorrt_llm.commands.build-parse_arguments-named-arguments"]], "Logits arguments": [[21, "tensorrt_llm.commands.build-parse_arguments-logits-arguments"]], "LoRA arguments": [[21, "tensorrt_llm.commands.build-parse_arguments-lora-arguments"]], "Speculative decoding arguments": [[21, "tensorrt_llm.commands.build-parse_arguments-speculative-decoding-arguments"]], "Auto parallel arguments": [[21, "tensorrt_llm.commands.build-parse_arguments-auto-parallel-arguments"]], "Plugin config arguments": [[21, "tensorrt_llm.commands.build-parse_arguments-plugin-config-arguments"]], "Executor API": [[22, "executor-api"]], "The Executor Class": [[22, "the-executor-class"]], "The Request Class": [[22, "the-request-class"]], "The Response Class": [[22, "the-response-class"]], "The Result Class": [[22, "the-result-class"]], "Sending Requests with Different Beam Widths": [[22, "sending-requests-with-different-beam-widths"]], "C++ Executor API Example": [[22, "c-executor-api-example"]], "Python Bindings for the Executor API": [[22, "python-bindings-for-the-executor-api"]], "Welcome to TensorRT-LLM\u2019s Documentation!": [[23, "welcome-to-tensorrt-llm-s-documentation"]], "Getting Started": [[23, null]], "Installation": [[23, null]], "Architecture": [[23, null]], "Advanced": [[23, null]], "Indices and tables": [[23, "indices-and-tables"]], "Building from Source Code on Linux": [[24, "building-from-source-code-on-linux"]], "Prerequisites": [[24, "prerequisites"], [25, "prerequisites"], [50, "prerequisites"]], "Building a TensorRT-LLM Docker Image": [[24, "building-a-tensorrt-llm-docker-image"], [25, "building-a-tensorrt-llm-docker-image"]], "Option 1: Build TensorRT-LLM in One Step": [[24, "option-1-build-tensorrt-llm-in-one-step"]], "Option 2: Build TensorRT-LLM Step-By-Step": [[24, "option-2-build-tensorrt-llm-step-by-step"]], "Create the Container": [[24, "create-the-container"]], "Build TensorRT-LLM": [[24, "build-tensorrt-llm"]], "Building the Python Bindings for the C++ Runtime": [[24, "building-the-python-bindings-for-the-c-runtime"]], "Linking with the TensorRT-LLM C++ Runtime": [[24, "linking-with-the-tensorrt-llm-c-runtime"], [25, "linking-with-the-tensorrt-llm-c-runtime"]], "Supported C++ Header Files": [[24, "supported-c-header-files"]], "Building from Source Code on Windows": [[25, "building-from-source-code-on-windows"]], "Docker Desktop": [[25, "docker-desktop"]], "Acquire an Image": [[25, "acquire-an-image"]], "Run the Container": [[25, "run-the-container"]], "Build and Extract Files": [[25, "build-and-extract-files"]], "Building TensorRT-LLM on Bare Metal": [[25, "building-tensorrt-llm-on-bare-metal"]], "Installing on Linux": [[26, "installing-on-linux"]], "Installing on Windows": [[27, "installing-on-windows"]], "Key Features": [[28, "key-features"]], "KV cache reuse": [[29, "kv-cache-reuse"]], "How to enable kv cache reuse": [[29, "how-to-enable-kv-cache-reuse"]], "Enable kv cache reuse for p-tuning": [[29, "enable-kv-cache-reuse-for-p-tuning"]], "Performance expectations": [[29, "performance-expectations"]], "Situations that can prevent kv cache reuse": [[29, "situations-that-can-prevent-kv-cache-reuse"]], "Offloading to host memory": [[29, "offloading-to-host-memory"]], "Common Customizations": [[30, "common-customizations"]], "Quantization": [[30, "quantization"], [48, "module-tensorrt_llm"]], "Sampling": [[30, "sampling"]], "Build Configuration": [[30, "build-configuration"]], "Runtime Customization": [[30, "runtime-customization"]], "Tokenizer Customization": [[30, "tokenizer-customization"]], "Disable Tokenizer": [[30, "disable-tokenizer"]], "Generation": [[30, "generation"]], "Asyncio-Based Generation": [[30, "asyncio-based-generation"]], "Future-Style Generation": [[30, "future-style-generation"]], "LLM Examples Introduction": [[31, "llm-examples-introduction"]], "Supported Models": [[31, "supported-models"]], "Model Preparation": [[31, "model-preparation"]], "Hugging Face Hub": [[31, "hugging-face-hub"]], "Local Hugging Face Models": [[31, "local-hugging-face-models"]], "From TensorRT-LLM Engine": [[31, "from-tensorrt-llm-engine"]], "Scripts": [[32, null]], "LLM Auto Parallel": [[33, "llm-auto-parallel"]], "LLM Generate": [[34, "llm-generate"]], "LLM Generate Async": [[35, "llm-generate-async"]], "LLM Generate Async Streaming": [[36, "llm-generate-async-streaming"]], "LLM Generate Distributed": [[37, "llm-generate-distributed"]], "LLM Quantization": [[38, "llm-quantization"]], "API Reference": [[39, "api-reference"]], "About TensorRT-LLM": [[40, "about-tensorrt-llm"]], "Common LLM Support": [[40, "common-llm-support"]], "In-Flight Batching and Paged Attention": [[40, "in-flight-batching-and-paged-attention"]], "Multi-GPU Multi-Node Inference": [[40, "multi-gpu-multi-node-inference"]], "FP8 Support": [[40, "fp8-support"]], "Latest GPU Support": [[40, "latest-gpu-support"]], "Native Windows Support": [[40, "native-windows-support"]], "What Can You Do With TensorRT-LLM?": [[40, "what-can-you-do-with-tensorrt-llm"]], "Performance Analysis": [[41, "performance-analysis"]], "Feature Descriptions": [[41, "feature-descriptions"]], "Usage": [[41, "usage"]], "Inference Time Command Line Options": [[41, "inference-time-command-line-options"]], "Inference Time Environment Variables": [[41, "inference-time-environment-variables"]], "Coordinating with NVIDIA Nsight Systems Launch": [[41, "coordinating-with-nvidia-nsight-systems-launch"]], "Profiling a single IFB iteration executing on a single rank of a multi-GPU model": [[41, "profiling-a-single-ifb-iteration-executing-on-a-single-rank-of-a-multi-gpu-model"]], "Best Practices for Tuning the Performance of TensorRT-LLM": [[42, "best-practices-for-tuning-the-performance-of-tensorrt-llm"]], "How To Measure Performance?": [[42, "how-to-measure-performance"]], "Build Options to Optimize the Performance of TensorRT-LLM Models": [[42, "build-options-to-optimize-the-performance-of-tensorrt-llm-models"]], "max_batch_size, max_seq_len and max_num_tokens": [[42, "max-batch-size-max-seq-len-and-max-num-tokens"]], "max_batch_size": [[42, "max-batch-size"]], "max_seq_len": [[42, "max-seq-len"]], "max_num_tokens": [[42, "max-num-tokens"]], "Multiple profiles": [[42, "multiple-profiles"]], "GPT Attention Plugin and Context Fused Multi-Head Attention": [[42, "gpt-attention-plugin-and-context-fused-multi-head-attention"]], "FP8 Context Fused Multi-Head Attention": [[42, "fp8-context-fused-multi-head-attention"]], "Remove Input Padding": [[42, "remove-input-padding"]], "In-flight Sequence Batching": [[42, "in-flight-sequence-batching"]], "Reduce Norm Fusion": [[42, "reduce-norm-fusion"]], "Embedding Parallelism, Embedding Sharing, and Look-Up Plugin": [[42, "embedding-parallelism-embedding-sharing-and-look-up-plugin"]], "Horizontal Fusion in Gated-MLP": [[42, "horizontal-fusion-in-gated-mlp"]], "GEMM + SwiGLU Fusion in Gated-MLP": [[42, "gemm-swiglu-fusion-in-gated-mlp"]], "GEMM Plugin": [[42, "gemm-plugin"]], "FP8 GEMM Plugin for Small Batch Size Performance Optimization": [[42, "fp8-gemm-plugin-for-small-batch-size-performance-optimization"]], "BERT Attention Plugin and Context Fused Multi-Head Attention": [[42, "bert-attention-plugin-and-context-fused-multi-head-attention"]], "Runtime Options to Optimize the Performance of TensorRT-LLM Models": [[42, "runtime-options-to-optimize-the-performance-of-tensorrt-llm-models"]], "GPT Model Type": [[42, "gpt-model-type"]], "Max Tokens in Paged KV Cache and KV Cache Free GPU Memory Fraction": [[42, "max-tokens-in-paged-kv-cache-and-kv-cache-free-gpu-memory-fraction"]], "Batch Scheduler Policy": [[42, "batch-scheduler-policy"]], "TensorRT Overlap": [[42, "tensorrt-overlap"]], "Maximum Attention Window Size": [[42, "maximum-attention-window-size"]], "Known Issues": [[43, "known-issues"], [51, "known-issues"], [55, "known-issues"], [55, "id7"], [55, "id13"], [55, "id29"]], "Fused Matmul + Gated-SiLU (LLaMA)": [[43, "fused-matmul-gated-silu-llama"]], "Throughput Measurements": [[43, "throughput-measurements"]], "Reproducing Benchmarked Results": [[43, "reproducing-benchmarked-results"]], "Commands": [[43, "commands"]], "Variables": [[43, "variables"]], "Preparing a Dataset": [[43, "preparing-a-dataset"]], "Engine Building": [[43, "engine-building"]], "Running the Benchmark": [[43, "running-the-benchmark"]], "Functionals": [[44, "module-tensorrt_llm"]], "Layers": [[45, "module-tensorrt_llm"]], "Activation": [[45, "module-tensorrt_llm.layers.activation"]], "Attention": [[45, "module-tensorrt_llm.layers.attention"]], "Cast": [[45, "module-tensorrt_llm.layers.cast"]], "Conv": [[45, "module-tensorrt_llm.layers.conv"]], "Embedding": [[45, "module-tensorrt_llm.layers.embedding"]], "Linear": [[45, "module-tensorrt_llm.layers.linear"]], "MLP": [[45, "module-tensorrt_llm.layers.mlp"]], "Normalization": [[45, "module-tensorrt_llm.layers.normalization"]], "Pooling": [[45, "module-tensorrt_llm.layers.pooling"]], "Models": [[46, "module-tensorrt_llm"], [53, "models"]], "Plugin": [[47, "module-tensorrt_llm"]], "Quick Start Guide": [[50, "quick-start-guide"]], "Compile the Model into a TensorRT Engine": [[50, "compile-the-model-into-a-tensorrt-engine"]], "Run the Model": [[50, "run-the-model"]], "Deploy with Triton Inference Server": [[50, "deploy-with-triton-inference-server"]], "LLM API": [[50, "llm-api"]], "Next Steps": [[50, "next-steps"]], "Related Information": [[50, "related-information"]], "Memory Usage of TensorRT-LLM": [[51, "memory-usage-of-tensorrt-llm"]], "Understand inference time GPU memory usage": [[51, "understand-inference-time-gpu-memory-usage"]], "1. Weights size": [[51, "weights-size"]], "2. Activation size": [[51, "activation-size"]], "3. I/O tensors": [[51, "i-o-tensors"]], "3.1 Runtime and decoder buffers except KV cache tensor": [[51, "runtime-and-decoder-buffers-except-kv-cache-tensor"]], "C++ runtime": [[51, "c-runtime"], [51, "id1"]], "3.2 KV cache tensor": [[51, "kv-cache-tensor"]], "Python runtime (Not recommended to be used)": [[51, "python-runtime-not-recommended-to-be-used"]], "Memory pool": [[51, "memory-pool"]], "FAQ": [[51, "faq"]], "Numerical Precision": [[52, "numerical-precision"]], "FP32, FP16 and BF16": [[52, "fp32-fp16-and-bf16"]], "Quantization and Dequantization (Q/DQ)": [[52, "quantization-and-dequantization-q-dq"]], "INT8 SmoothQuant (W8A8)": [[52, "int8-smoothquant-w8a8"]], "INT4 and INT8 Weight-Only (W4A16 and W8A16)": [[52, "int4-and-int8-weight-only-w4a16-and-w8a16"]], "GPTQ and AWQ (W4A16)": [[52, "gptq-and-awq-w4a16"]], "FP8 (Hopper)": [[52, "fp8-hopper"]], "Support matrix": [[52, "support-matrix"]], "Technical Detail: The QuantMode Flags": [[52, "technical-detail-the-quantmode-flags"]], "Support Matrix": [[53, "support-matrix"]], "LLM Models": [[53, "llm-models"]], "Multi-Modal Models 2": [[53, "multi-modal-models"]], "Hardware": [[53, "hardware"]], "Software": [[53, "software"]], "Troubleshooting": [[54, "troubleshooting"]], "Build Errors": [[54, "build-errors"]], "cuDNN Linking Errors": [[54, "cudnn-linking-errors"]], "Debug on Unit Tests": [[54, "debug-on-unit-tests"]], "Debug on E2E Models": [[54, "debug-on-e2e-models"]], "Debug Execution Errors": [[54, "debug-execution-errors"]], "Installation Errors": [[54, "installation-errors"]], "Tips": [[54, "tips"]], "Release Notes": [[55, "release-notes"]], "TensorRT-LLM Release 0.13.0": [[55, "tensorrt-llm-release-0-13-0"]], "Key Features and Enhancements": [[55, "key-features-and-enhancements"], [55, "id2"], [55, "id8"], [55, "id14"], [55, "id20"], [55, "id24"], [55, "id26"]], "Model Updates": [[55, "model-updates"], [55, "id4"], [55, "id10"], [55, "id16"], [55, "id22"], [55, "id25"], [55, "id27"]], "Fixed Issues": [[55, "fixed-issues"], [55, "id5"], [55, "id11"], [55, "id17"], [55, "id23"], [55, "id28"]], "Infrastructure Changes": [[55, "infrastructure-changes"], [55, "id6"], [55, "id12"]], "TensorRT-LLM Release 0.12.0": [[55, "tensorrt-llm-release-0-12-0"]], "TensorRT-LLM Release 0.11.0": [[55, "tensorrt-llm-release-0-11-0"]], "TensorRT-LLM Release 0.10.0": [[55, "tensorrt-llm-release-0-10-0"]], "Announcements": [[55, "announcements"], [55, "id19"]], "Infrastructure changes": [[55, "id18"]], "TensorRT-LLM Release 0.9.0": [[55, "tensorrt-llm-release-0-9-0"]], "Limitations": [[55, "limitations"], [56, "limitations"]], "TensorRT-LLM Release 0.8.0": [[55, "tensorrt-llm-release-0-8-0"]], "TensorRT-LLM Release 0.7.1": [[55, "tensorrt-llm-release-0-7-1"]], "Speculative Sampling": [[56, "speculative-sampling"]], "Performance Improvements": [[56, "performance-improvements"]], "Draft Model Approach": [[56, "draft-model-approach"]], "Using Draft model approach with Triton Inference Server": [[56, "using-draft-model-approach-with-triton-inference-server"]], "Medusa": [[56, "medusa"]], "Medusa Tree": [[56, "medusa-tree"]], "Using Medusa with TensorRT-LLM": [[56, "using-medusa-with-tensorrt-llm"]], "ReDrafter": [[56, "redrafter"]], "Lookahead decoding": [[56, "lookahead-decoding"]], "Build and execute an engine from a model": [[56, "build-and-execute-an-engine-from-a-model"]], "Convert a model to checkpoint": [[56, "convert-a-model-to-checkpoint"]], "Build checkpoints for an engine": [[56, "build-checkpoints-for-an-engine"]], "Execute an engine": [[56, "execute-an-engine"]]}, "indexentries": {"tensorrt_llm (c++ type)": [[0, "_CPPv412tensorrt_llm"], [1, "_CPPv412tensorrt_llm"]], "tensorrt_llm::executor (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executorE"]], "tensorrt_llm::executor::batchingtype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor12BatchingTypeE"]], "tensorrt_llm::executor::batchingtype::kinflight (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12BatchingType9kINFLIGHTE"]], "tensorrt_llm::executor::batchingtype::kstatic (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12BatchingType7kSTATICE"]], "tensorrt_llm::executor::beamtokens (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor10BeamTokensE"]], "tensorrt_llm::executor::bufferview (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor10BufferViewE"]], "tensorrt_llm::executor::capacityschedulerpolicy (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicyE"]], "tensorrt_llm::executor::capacityschedulerpolicy::kguaranteed_no_evict (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicy20kGUARANTEED_NO_EVICTE"]], "tensorrt_llm::executor::capacityschedulerpolicy::kmax_utilization (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor23CapacitySchedulerPolicy16kMAX_UTILIZATIONE"]], "tensorrt_llm::executor::communicationmode (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor17CommunicationModeE"]], "tensorrt_llm::executor::communicationmode::kleader (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor17CommunicationMode7kLEADERE"]], "tensorrt_llm::executor::communicationmode::korchestrator (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor17CommunicationMode13kORCHESTRATORE"]], "tensorrt_llm::executor::communicationtype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor17CommunicationTypeE"]], "tensorrt_llm::executor::communicationtype::kmpi (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor17CommunicationType4kMPIE"]], "tensorrt_llm::executor::contextchunkingpolicy (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicyE"]], "tensorrt_llm::executor::contextchunkingpolicy::kequal_progress (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicy15kEQUAL_PROGRESSE"]], "tensorrt_llm::executor::contextchunkingpolicy::kfirst_come_first_served (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor21ContextChunkingPolicy24kFIRST_COME_FIRST_SERVEDE"]], "tensorrt_llm::executor::contextphaseparams (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsE"]], "tensorrt_llm::executor::contextphaseparams::contextphaseparams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokens"], [0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsE9VecTokensPv"], [0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsERK18ContextPhaseParams"], [0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams18ContextPhaseParamsERR18ContextPhaseParams"]], "tensorrt_llm::executor::contextphaseparams::stateptr (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams8StatePtrE"]], "tensorrt_llm::executor::contextphaseparams::deleter (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams7deleterEPKv"]], "tensorrt_llm::executor::contextphaseparams::getfirstgentokens (c++ function)": [[0, "_CPPv4NKR12tensorrt_llm8executor18ContextPhaseParams17getFirstGenTokensEv"]], "tensorrt_llm::executor::contextphaseparams::getstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams8getStateEv"], [0, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParams8getStateEv"]], "tensorrt_llm::executor::contextphaseparams::mfirstgentokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams15mFirstGenTokensE"]], "tensorrt_llm::executor::contextphaseparams::mstate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams6mStateE"]], "tensorrt_llm::executor::contextphaseparams::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsaSERK18ContextPhaseParams"], [0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParamsaSERR18ContextPhaseParams"]], "tensorrt_llm::executor::contextphaseparams::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18ContextPhaseParamseqERK18ContextPhaseParams"]], "tensorrt_llm::executor::contextphaseparams::popfirstgentokens (c++ function)": [[0, "_CPPv4NO12tensorrt_llm8executor18ContextPhaseParams17popFirstGenTokensEv"]], "tensorrt_llm::executor::contextphaseparams::releasestate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18ContextPhaseParams12releaseStateEv"]], "tensorrt_llm::executor::datatype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor8DataTypeE"]], "tensorrt_llm::executor::datatype::kbf16 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType5kBF16E"]], "tensorrt_llm::executor::datatype::kbool (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType5kBOOLE"]], "tensorrt_llm::executor::datatype::kfp16 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType5kFP16E"]], "tensorrt_llm::executor::datatype::kfp32 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType5kFP32E"]], "tensorrt_llm::executor::datatype::kfp8 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType4kFP8E"]], "tensorrt_llm::executor::datatype::kint32 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType6kINT32E"]], "tensorrt_llm::executor::datatype::kint64 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType6kINT64E"]], "tensorrt_llm::executor::datatype::kint8 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType5kINT8E"]], "tensorrt_llm::executor::datatype::kuint8 (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType6kUINT8E"]], "tensorrt_llm::executor::datatype::kunknown (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor8DataType8kUNKNOWNE"]], "tensorrt_llm::executor::debugconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfigE"]], "tensorrt_llm::executor::debugconfig::debugconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig11DebugConfigEbb9StringVec"]], "tensorrt_llm::executor::debugconfig::stringvec (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig9StringVecE"]], "tensorrt_llm::executor::debugconfig::getdebugtensornames (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11DebugConfig19getDebugTensorNamesEv"]], "tensorrt_llm::executor::debugconfig::getdumpinputtensors (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11DebugConfig19getDumpInputTensorsEv"]], "tensorrt_llm::executor::debugconfig::getdumpoutputtensors (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11DebugConfig20getDumpOutputTensorsEv"]], "tensorrt_llm::executor::debugconfig::mdebugtensornames (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig17mDebugTensorNamesE"]], "tensorrt_llm::executor::debugconfig::mdumpinputtensors (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig17mDumpInputTensorsE"]], "tensorrt_llm::executor::debugconfig::mdumpouputtensors (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig17mDumpOuputTensorsE"]], "tensorrt_llm::executor::debugconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor11DebugConfigeqERK11DebugConfig"]], "tensorrt_llm::executor::debugconfig::setdebugtensornames (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig19setDebugTensorNamesERK9StringVec"]], "tensorrt_llm::executor::debugconfig::setdumpinputtensors (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig19setDumpInputTensorsEb"]], "tensorrt_llm::executor::debugconfig::setdumpouputtensors (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor11DebugConfig19setDumpOuputTensorsEb"]], "tensorrt_llm::executor::decodingconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfigE"]], "tensorrt_llm::executor::decodingconfig::decodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14DecodingConfigENSt8optionalI12DecodingModeEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalI13MedusaChoicesEE"]], "tensorrt_llm::executor::decodingconfig::getdecodingmode (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig15getDecodingModeEv"]], "tensorrt_llm::executor::decodingconfig::getlookaheaddecodingconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig26getLookaheadDecodingConfigEv"]], "tensorrt_llm::executor::decodingconfig::getmedusachoices (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14DecodingConfig16getMedusaChoicesEv"]], "tensorrt_llm::executor::decodingconfig::mdecodingmode (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig13mDecodingModeE"]], "tensorrt_llm::executor::decodingconfig::mlookaheaddecodingconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig24mLookaheadDecodingConfigE"]], "tensorrt_llm::executor::decodingconfig::mmedusachoices (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig14mMedusaChoicesE"]], "tensorrt_llm::executor::decodingconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14DecodingConfigeqERK14DecodingConfig"]], "tensorrt_llm::executor::decodingconfig::setdecodingmode (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig15setDecodingModeERK12DecodingMode"]], "tensorrt_llm::executor::decodingconfig::setlookaheaddecoding (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig20setLookaheadDecodingERK23LookaheadDecodingConfig"]], "tensorrt_llm::executor::decodingconfig::setmedusachoices (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14DecodingConfig16setMedusaChoicesERK13MedusaChoices"]], "tensorrt_llm::executor::decodingmode (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingModeE"]], "tensorrt_llm::executor::decodingmode::auto (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode4AutoEv"]], "tensorrt_llm::executor::decodingmode::beamsearch (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode10BeamSearchEv"]], "tensorrt_llm::executor::decodingmode::decodingmode (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode12DecodingModeE14UnderlyingType"]], "tensorrt_llm::executor::decodingmode::explicitdrafttokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode19ExplicitDraftTokensEv"]], "tensorrt_llm::executor::decodingmode::lookahead (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode9LookaheadEv"]], "tensorrt_llm::executor::decodingmode::medusa (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode6MedusaEv"]], "tensorrt_llm::executor::decodingmode::topk (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode4TopKEv"]], "tensorrt_llm::executor::decodingmode::topktopp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode8TopKTopPEv"]], "tensorrt_llm::executor::decodingmode::topp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode4TopPEv"]], "tensorrt_llm::executor::decodingmode::underlyingtype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode14UnderlyingTypeE"]], "tensorrt_llm::executor::decodingmode::allbitset (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9allBitSetE14UnderlyingType"]], "tensorrt_llm::executor::decodingmode::anybitset (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode9anyBitSetE14UnderlyingType"]], "tensorrt_llm::executor::decodingmode::getstate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode8getStateEv"]], "tensorrt_llm::executor::decodingmode::isauto (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isAutoEv"]], "tensorrt_llm::executor::decodingmode::isbeamsearch (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isBeamSearchEv"]], "tensorrt_llm::executor::decodingmode::isexplicitdrafttokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode21isExplicitDraftTokensEv"]], "tensorrt_llm::executor::decodingmode::islookahead (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode11isLookaheadEv"]], "tensorrt_llm::executor::decodingmode::ismedusa (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode8isMedusaEv"]], "tensorrt_llm::executor::decodingmode::istopk (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isTopKEv"]], "tensorrt_llm::executor::decodingmode::istopkandtopp (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode13isTopKandTopPEv"]], "tensorrt_llm::executor::decodingmode::istopkortopp (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isTopKorTopPEv"]], "tensorrt_llm::executor::decodingmode::istopp (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode6isTopPEv"]], "tensorrt_llm::executor::decodingmode::isusebantokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseBanTokensEv"]], "tensorrt_llm::executor::decodingmode::isusebanwords (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode13isUseBanWordsEv"]], "tensorrt_llm::executor::decodingmode::isuseexpliciteosstop (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode20isUseExplicitEosStopEv"]], "tensorrt_llm::executor::decodingmode::isusefrequencypenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode21isUseFrequencyPenaltyEv"]], "tensorrt_llm::executor::decodingmode::isusemaxlengthstop (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode18isUseMaxLengthStopEv"]], "tensorrt_llm::executor::decodingmode::isuseminlength (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseMinLengthEv"]], "tensorrt_llm::executor::decodingmode::isusenorepeatngramsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseNoRepeatNgramSizeEv"]], "tensorrt_llm::executor::decodingmode::isuseoccurrencepenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseOccurrencePenaltyEv"]], "tensorrt_llm::executor::decodingmode::isusepenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode12isUsePenaltyEv"]], "tensorrt_llm::executor::decodingmode::isusepresencepenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode20isUsePresencePenaltyEv"]], "tensorrt_llm::executor::decodingmode::isuserepetitionpenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode22isUseRepetitionPenaltyEv"]], "tensorrt_llm::executor::decodingmode::isusestopcriteria (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode17isUseStopCriteriaEv"]], "tensorrt_llm::executor::decodingmode::isusestopwords (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode14isUseStopWordsEv"]], "tensorrt_llm::executor::decodingmode::isusetemperature (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingMode16isUseTemperatureEv"]], "tensorrt_llm::executor::decodingmode::kauto (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kAutoE"]], "tensorrt_llm::executor::decodingmode::kbeamsearch (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode11kBeamSearchE"]], "tensorrt_llm::executor::decodingmode::kexplicitdrafttokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode20kExplicitDraftTokensE"]], "tensorrt_llm::executor::decodingmode::klookahead (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode10kLookaheadE"]], "tensorrt_llm::executor::decodingmode::kmedusa (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode7kMedusaE"]], "tensorrt_llm::executor::decodingmode::knumflags (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode9kNumFlagsE"]], "tensorrt_llm::executor::decodingmode::kstandardstopcriteria (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode21kStandardStopCriteriaE"]], "tensorrt_llm::executor::decodingmode::ktopk (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kTopKE"]], "tensorrt_llm::executor::decodingmode::ktopktopp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode9kTopKTopPE"]], "tensorrt_llm::executor::decodingmode::ktopp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode5kTopPE"]], "tensorrt_llm::executor::decodingmode::kusebantokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseBanTokensE"]], "tensorrt_llm::executor::decodingmode::kusebanwords (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode12kUseBanWordsE"]], "tensorrt_llm::executor::decodingmode::kuseexpliciteosstop (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode19kUseExplicitEosStopE"]], "tensorrt_llm::executor::decodingmode::kusefrequencypenalties (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode22kUseFrequencyPenaltiesE"]], "tensorrt_llm::executor::decodingmode::kusemaxlengthstop (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode17kUseMaxLengthStopE"]], "tensorrt_llm::executor::decodingmode::kuseminlength (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseMinLengthE"]], "tensorrt_llm::executor::decodingmode::kusenorepeatngramsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode21kUseNoRepeatNgramSizeE"]], "tensorrt_llm::executor::decodingmode::kuseoccurrencepenalties (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode23kUseOccurrencePenaltiesE"]], "tensorrt_llm::executor::decodingmode::kusepenalties (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUsePenaltiesE"]], "tensorrt_llm::executor::decodingmode::kusepresencepenalties (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode21kUsePresencePenaltiesE"]], "tensorrt_llm::executor::decodingmode::kuserepetitionpenalties (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode23kUseRepetitionPenaltiesE"]], "tensorrt_llm::executor::decodingmode::kusestopwords (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode13kUseStopWordsE"]], "tensorrt_llm::executor::decodingmode::kusetemperature (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode15kUseTemperatureE"]], "tensorrt_llm::executor::decodingmode::mstate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode6mStateE"]], "tensorrt_llm::executor::decodingmode::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor12DecodingModeeqERK12DecodingMode"]], "tensorrt_llm::executor::decodingmode::setbitto (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode8setBitToE14UnderlyingTypeb"]], "tensorrt_llm::executor::decodingmode::usebantokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useBanTokensEb"]], "tensorrt_llm::executor::decodingmode::usebanwords (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode11useBanWordsEb"]], "tensorrt_llm::executor::decodingmode::useexpliciteosstop (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode18useExplicitEosStopEb"]], "tensorrt_llm::executor::decodingmode::usefrequencypenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode19useFrequencyPenaltyEb"]], "tensorrt_llm::executor::decodingmode::usemaxlengthstop (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode16useMaxLengthStopEb"]], "tensorrt_llm::executor::decodingmode::useminlength (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useMinLengthEb"]], "tensorrt_llm::executor::decodingmode::usenorepeatngramsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useNoRepeatNgramSizeEb"]], "tensorrt_llm::executor::decodingmode::useoccurrencepenalties (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode22useOccurrencePenaltiesEb"]], "tensorrt_llm::executor::decodingmode::usepresencepenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode18usePresencePenaltyEb"]], "tensorrt_llm::executor::decodingmode::userepetitionpenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode20useRepetitionPenaltyEb"]], "tensorrt_llm::executor::decodingmode::usestopwords (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode12useStopWordsEb"]], "tensorrt_llm::executor::decodingmode::usetemperature (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12DecodingMode14useTemperatureEb"]], "tensorrt_llm::executor::executor (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8ExecutorE"]], "tensorrt_llm::executor::executor::executor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEENSt10shared_ptrI5ModelEERK14ExecutorConfig"], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorENSt10shared_ptrI5ModelEERK14ExecutorConfig"], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfigRKNSt8optionalINSt3mapINSt6stringE6TensorEEEE"], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERK10BufferViewRKNSt6stringERK10BufferViewRKNSt6stringE9ModelTypeRK14ExecutorConfig"], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig"], [0, "_CPPv4N12tensorrt_llm8executor8Executor8ExecutorERKNSt10filesystem4pathERKNSt10filesystem4pathE9ModelTypeRK14ExecutorConfig"]], "tensorrt_llm::executor::executor::awaitresponses (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERK6IdTypeRKNSt8optionalINSt6chrono12millisecondsEEE"], [0, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt6vectorI6IdTypeEERKNSt8optionalINSt6chrono12millisecondsEEE"], [0, "_CPPv4N12tensorrt_llm8executor8Executor14awaitResponsesERKNSt8optionalINSt6chrono12millisecondsEEE"]], "tensorrt_llm::executor::executor::canenqueuerequests (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Executor18canEnqueueRequestsEv"]], "tensorrt_llm::executor::executor::cancelrequest (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor13cancelRequestE6IdType"]], "tensorrt_llm::executor::executor::enqueuerequest (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor14enqueueRequestERK7Request"]], "tensorrt_llm::executor::executor::enqueuerequests (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor15enqueueRequestsERKNSt6vectorI7RequestEE"]], "tensorrt_llm::executor::executor::getlatestiterationstats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor23getLatestIterationStatsEv"]], "tensorrt_llm::executor::executor::getlatestrequeststats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor21getLatestRequestStatsEv"]], "tensorrt_llm::executor::executor::getnumresponsesready (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Executor20getNumResponsesReadyERKNSt8optionalI6IdTypeEE"]], "tensorrt_llm::executor::executor::mimpl (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor5mImplE"]], "tensorrt_llm::executor::executor::shutdown (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Executor8shutdownEv"]], "tensorrt_llm::executor::executor::~executor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8ExecutorD0Ev"]], "tensorrt_llm::executor::executorconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfigE"]], "tensorrt_llm::executor::executorconfig::executorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14ExecutorConfigE10SizeType32RK15SchedulerConfigRK13KvCacheConfigbb10SizeType3210SizeType3212BatchingTypeNSt8optionalI10SizeType32EENSt8optionalI10SizeType32EENSt8optionalI14ParallelConfigEERKNSt8optionalI15PeftCacheConfigEENSt8optionalI25LogitsPostProcessorConfigEENSt8optionalI14DecodingConfigEEfNSt8optionalI10SizeType32EERK29ExtendedRuntimePerfKnobConfigNSt8optionalI11DebugConfigEE10SizeType328uint64_t"]], "tensorrt_llm::executor::executorconfig::getbatchingtype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getBatchingTypeEv"]], "tensorrt_llm::executor::executorconfig::getdebugconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig14getDebugConfigEv"]], "tensorrt_llm::executor::executorconfig::getdecodingconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig17getDecodingConfigEv"]], "tensorrt_llm::executor::executorconfig::getenablechunkedcontext (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig23getEnableChunkedContextEv"]], "tensorrt_llm::executor::executorconfig::getextendedruntimeperfknobconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig32getExtendedRuntimePerfKnobConfigEv"]], "tensorrt_llm::executor::executorconfig::getgpuweightspercent (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig20getGpuWeightsPercentEv"]], "tensorrt_llm::executor::executorconfig::getiterstatsmaxiterations (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getIterStatsMaxIterationsEv"]], "tensorrt_llm::executor::executorconfig::getkvcacheconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig16getKvCacheConfigEv"]], "tensorrt_llm::executor::executorconfig::getlogitspostprocessorconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig28getLogitsPostProcessorConfigEv"]], "tensorrt_llm::executor::executorconfig::getmaxbatchsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxBatchSizeEv"]], "tensorrt_llm::executor::executorconfig::getmaxbeamwidth (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxBeamWidthEv"]], "tensorrt_llm::executor::executorconfig::getmaxnumtokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxNumTokensEv"]], "tensorrt_llm::executor::executorconfig::getmaxqueuesize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig15getMaxQueueSizeEv"]], "tensorrt_llm::executor::executorconfig::getmaxseqidlemicroseconds (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig25getMaxSeqIdleMicrosecondsEv"]], "tensorrt_llm::executor::executorconfig::getnormalizelogprobs (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig20getNormalizeLogProbsEv"]], "tensorrt_llm::executor::executorconfig::getparallelconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig17getParallelConfigEv"]], "tensorrt_llm::executor::executorconfig::getpeftcacheconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig18getPeftCacheConfigEv"]], "tensorrt_llm::executor::executorconfig::getrecvpollperiodms (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig19getRecvPollPeriodMsEv"]], "tensorrt_llm::executor::executorconfig::getrequeststatsmaxiterations (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig28getRequestStatsMaxIterationsEv"]], "tensorrt_llm::executor::executorconfig::getschedulerconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ExecutorConfig18getSchedulerConfigEv"]], "tensorrt_llm::executor::executorconfig::mbatchingtype (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mBatchingTypeE"]], "tensorrt_llm::executor::executorconfig::mdebugconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig12mDebugConfigE"]], "tensorrt_llm::executor::executorconfig::mdecodingconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15mDecodingConfigE"]], "tensorrt_llm::executor::executorconfig::menablechunkedcontext (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig21mEnableChunkedContextE"]], "tensorrt_llm::executor::executorconfig::mextendedruntimeperfknobconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig30mExtendedRuntimePerfKnobConfigE"]], "tensorrt_llm::executor::executorconfig::mgpuweightspercent (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18mGpuWeightsPercentE"]], "tensorrt_llm::executor::executorconfig::miterstatsmaxiterations (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mIterStatsMaxIterationsE"]], "tensorrt_llm::executor::executorconfig::mkvcacheconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14mKvCacheConfigE"]], "tensorrt_llm::executor::executorconfig::mlogitspostprocessorconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig26mLogitsPostProcessorConfigE"]], "tensorrt_llm::executor::executorconfig::mmaxbatchsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxBatchSizeE"]], "tensorrt_llm::executor::executorconfig::mmaxbeamwidth (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxBeamWidthE"]], "tensorrt_llm::executor::executorconfig::mmaxnumtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxNumTokensE"]], "tensorrt_llm::executor::executorconfig::mmaxqueuesize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig13mMaxQueueSizeE"]], "tensorrt_llm::executor::executorconfig::mmaxseqidlemicroseconds (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23mMaxSeqIdleMicrosecondsE"]], "tensorrt_llm::executor::executorconfig::mnormalizelogprobs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18mNormalizeLogProbsE"]], "tensorrt_llm::executor::executorconfig::mparallelconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15mParallelConfigE"]], "tensorrt_llm::executor::executorconfig::mpeftcacheconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16mPeftCacheConfigE"]], "tensorrt_llm::executor::executorconfig::mrecvpollperiodms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17mRecvPollPeriodMsE"]], "tensorrt_llm::executor::executorconfig::mrequeststatsmaxiterations (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig26mRequestStatsMaxIterationsE"]], "tensorrt_llm::executor::executorconfig::mschedulerconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16mSchedulerConfigE"]], "tensorrt_llm::executor::executorconfig::setbatchingtype (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setBatchingTypeE12BatchingType"]], "tensorrt_llm::executor::executorconfig::setdebugconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig14setDebugConfigERK11DebugConfig"]], "tensorrt_llm::executor::executorconfig::setdecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setDecodingConfigERK14DecodingConfig"]], "tensorrt_llm::executor::executorconfig::setenablechunkedcontext (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig23setEnableChunkedContextEb"]], "tensorrt_llm::executor::executorconfig::setextendedruntimeperfknobconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig32setExtendedRuntimePerfKnobConfigERK29ExtendedRuntimePerfKnobConfig"]], "tensorrt_llm::executor::executorconfig::setgpuweightspercent (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setGpuWeightsPercentERKf"]], "tensorrt_llm::executor::executorconfig::setiterstatsmaxiterations (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setIterStatsMaxIterationsE10SizeType32"]], "tensorrt_llm::executor::executorconfig::setkvcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig16setKvCacheConfigERK13KvCacheConfig"]], "tensorrt_llm::executor::executorconfig::setlogitspostprocessorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setLogitsPostProcessorConfigERK25LogitsPostProcessorConfig"]], "tensorrt_llm::executor::executorconfig::setmaxbatchsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBatchSizeE10SizeType32"]], "tensorrt_llm::executor::executorconfig::setmaxbeamwidth (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxBeamWidthE10SizeType32"]], "tensorrt_llm::executor::executorconfig::setmaxnumtokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxNumTokensE10SizeType32"]], "tensorrt_llm::executor::executorconfig::setmaxqueuesize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig15setMaxQueueSizeERKNSt8optionalI10SizeType32EE"]], "tensorrt_llm::executor::executorconfig::setmaxseqidlemicroseconds (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig25setMaxSeqIdleMicrosecondsE8uint64_t"]], "tensorrt_llm::executor::executorconfig::setnormalizelogprobs (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig20setNormalizeLogProbsEb"]], "tensorrt_llm::executor::executorconfig::setparallelconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig17setParallelConfigERK14ParallelConfig"]], "tensorrt_llm::executor::executorconfig::setpeftcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setPeftCacheConfigERK15PeftCacheConfig"]], "tensorrt_llm::executor::executorconfig::setrecvpollperiodms (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig19setRecvPollPeriodMsERK10SizeType32"]], "tensorrt_llm::executor::executorconfig::setrequeststatsmaxiterations (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig28setRequestStatsMaxIterationsE10SizeType32"]], "tensorrt_llm::executor::executorconfig::setschedulerconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ExecutorConfig18setSchedulerConfigERK15SchedulerConfig"]], "tensorrt_llm::executor::extendedruntimeperfknobconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfigE"]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::extendedruntimeperfknobconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig29ExtendedRuntimePerfKnobConfigEbb"]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::getenablecontextfmhafp32acc (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig27getEnableContextFMHAFP32AccEv"]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::getmultiblockmode (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig17getMultiBlockModeEv"]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::menablecontextfmhafp32acc (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig25mEnableContextFMHAFP32AccE"]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::mmultiblockmode (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig15mMultiBlockModeE"]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfigeqERK29ExtendedRuntimePerfKnobConfig"]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::setenablecontextfmhafp32acc (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig27setEnableContextFMHAFP32AccEb"]], "tensorrt_llm::executor::extendedruntimeperfknobconfig::setmultiblockmode (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor29ExtendedRuntimePerfKnobConfig17setMultiBlockModeEb"]], "tensorrt_llm::executor::externaldrafttokensconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfigE"]], "tensorrt_llm::executor::externaldrafttokensconfig::externaldrafttokensconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig25ExternalDraftTokensConfigE9VecTokensNSt8optionalI6TensorEERKNSt8optionalI9FloatTypeEE"]], "tensorrt_llm::executor::externaldrafttokensconfig::getacceptancethreshold (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig22getAcceptanceThresholdEv"]], "tensorrt_llm::executor::externaldrafttokensconfig::getlogits (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig9getLogitsEv"]], "tensorrt_llm::executor::externaldrafttokensconfig::gettokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25ExternalDraftTokensConfig9getTokensEv"]], "tensorrt_llm::executor::externaldrafttokensconfig::macceptancethreshold (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig20mAcceptanceThresholdE"]], "tensorrt_llm::executor::externaldrafttokensconfig::mlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig7mLogitsE"]], "tensorrt_llm::executor::externaldrafttokensconfig::mtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25ExternalDraftTokensConfig7mTokensE"]], "tensorrt_llm::executor::finishreason (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReasonE"]], "tensorrt_llm::executor::finishreason::kend_id (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReason7kEND_IDE"]], "tensorrt_llm::executor::finishreason::klength (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReason7kLENGTHE"]], "tensorrt_llm::executor::finishreason::knot_finished (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReason13kNOT_FINISHEDE"]], "tensorrt_llm::executor::finishreason::kstop_words (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12FinishReason11kSTOP_WORDSE"]], "tensorrt_llm::executor::floattype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor9FloatTypeE"]], "tensorrt_llm::executor::idtype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor6IdTypeE"]], "tensorrt_llm::executor::inflightbatchingstats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStatsE"]], "tensorrt_llm::executor::inflightbatchingstats::avgnumdecodedtokensperiter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats26avgNumDecodedTokensPerIterE"]], "tensorrt_llm::executor::inflightbatchingstats::microbatchid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats12microBatchIdE"]], "tensorrt_llm::executor::inflightbatchingstats::numcontextrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats18numContextRequestsE"]], "tensorrt_llm::executor::inflightbatchingstats::numctxtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats12numCtxTokensE"]], "tensorrt_llm::executor::inflightbatchingstats::numgenrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats14numGenRequestsE"]], "tensorrt_llm::executor::inflightbatchingstats::numpausedrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats17numPausedRequestsE"]], "tensorrt_llm::executor::inflightbatchingstats::numscheduledrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor21InflightBatchingStats20numScheduledRequestsE"]], "tensorrt_llm::executor::iterationstats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStatsE"]], "tensorrt_llm::executor::iterationstats::cpumemusage (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats11cpuMemUsageE"]], "tensorrt_llm::executor::iterationstats::crosskvcachestats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats17crossKvCacheStatsE"]], "tensorrt_llm::executor::iterationstats::gpumemusage (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats11gpuMemUsageE"]], "tensorrt_llm::executor::iterationstats::inflightbatchingstats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats21inflightBatchingStatsE"]], "tensorrt_llm::executor::iterationstats::iter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats4iterE"]], "tensorrt_llm::executor::iterationstats::iterlatencyms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats13iterLatencyMSE"]], "tensorrt_llm::executor::iterationstats::kvcachestats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats12kvCacheStatsE"]], "tensorrt_llm::executor::iterationstats::maxnumactiverequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats20maxNumActiveRequestsE"]], "tensorrt_llm::executor::iterationstats::newactiverequestsqueuelatencyms (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats31newActiveRequestsQueueLatencyMSE"]], "tensorrt_llm::executor::iterationstats::numactiverequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats17numActiveRequestsE"]], "tensorrt_llm::executor::iterationstats::numcompletedrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats20numCompletedRequestsE"]], "tensorrt_llm::executor::iterationstats::numqueuedrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats17numQueuedRequestsE"]], "tensorrt_llm::executor::iterationstats::pinnedmemusage (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats14pinnedMemUsageE"]], "tensorrt_llm::executor::iterationstats::staticbatchingstats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats19staticBatchingStatsE"]], "tensorrt_llm::executor::iterationstats::timestamp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14IterationStats9timestampE"]], "tensorrt_llm::executor::iterationtype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor13IterationTypeE"]], "tensorrt_llm::executor::jsonserialization (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor17JsonSerializationE"]], "tensorrt_llm::executor::jsonserialization::tojsonstr (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK12RequestStats"], [0, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK14IterationStats"], [0, "_CPPv4N12tensorrt_llm8executor17JsonSerialization9toJsonStrERK24RequestStatsPerIteration"]], "tensorrt_llm::executor::kvcacheconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfigE"]], "tensorrt_llm::executor::kvcacheconfig::kvcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig13KvCacheConfigEbRKNSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI6size_tEEb"]], "tensorrt_llm::executor::kvcacheconfig::getenableblockreuse (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig19getEnableBlockReuseEv"]], "tensorrt_llm::executor::kvcacheconfig::getfreegpumemoryfraction (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig24getFreeGpuMemoryFractionEv"]], "tensorrt_llm::executor::kvcacheconfig::gethostcachesize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig16getHostCacheSizeEv"]], "tensorrt_llm::executor::kvcacheconfig::getmaxattentionwindowvec (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig24getMaxAttentionWindowVecEv"]], "tensorrt_llm::executor::kvcacheconfig::getmaxtokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig12getMaxTokensEv"]], "tensorrt_llm::executor::kvcacheconfig::getonboardblocks (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig16getOnboardBlocksEv"]], "tensorrt_llm::executor::kvcacheconfig::getsinktokenlength (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor13KvCacheConfig18getSinkTokenLengthEv"]], "tensorrt_llm::executor::kvcacheconfig::menableblockreuse (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig17mEnableBlockReuseE"]], "tensorrt_llm::executor::kvcacheconfig::mfreegpumemoryfraction (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig22mFreeGpuMemoryFractionE"]], "tensorrt_llm::executor::kvcacheconfig::mhostcachesize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig14mHostCacheSizeE"]], "tensorrt_llm::executor::kvcacheconfig::mmaxattentionwindowvec (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig22mMaxAttentionWindowVecE"]], "tensorrt_llm::executor::kvcacheconfig::mmaxtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig10mMaxTokensE"]], "tensorrt_llm::executor::kvcacheconfig::monboardblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig14mOnboardBlocksE"]], "tensorrt_llm::executor::kvcacheconfig::msinktokenlength (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16mSinkTokenLengthE"]], "tensorrt_llm::executor::kvcacheconfig::setenableblockreuse (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig19setEnableBlockReuseEb"]], "tensorrt_llm::executor::kvcacheconfig::setfreegpumemoryfraction (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setFreeGpuMemoryFractionE9FloatType"]], "tensorrt_llm::executor::kvcacheconfig::sethostcachesize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setHostCacheSizeE6size_t"]], "tensorrt_llm::executor::kvcacheconfig::setmaxattentionwindowvec (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig24setMaxAttentionWindowVecENSt6vectorI10SizeType32EE"]], "tensorrt_llm::executor::kvcacheconfig::setmaxtokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig12setMaxTokensE10SizeType32"]], "tensorrt_llm::executor::kvcacheconfig::setonboardblocks (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig16setOnboardBlocksEb"]], "tensorrt_llm::executor::kvcacheconfig::setsinktokenlength (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13KvCacheConfig18setSinkTokenLengthE10SizeType32"]], "tensorrt_llm::executor::kvcachestats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStatsE"]], "tensorrt_llm::executor::kvcachestats::allocnewblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats14allocNewBlocksE"]], "tensorrt_llm::executor::kvcachestats::alloctotalblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats16allocTotalBlocksE"]], "tensorrt_llm::executor::kvcachestats::freenumblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats13freeNumBlocksE"]], "tensorrt_llm::executor::kvcachestats::maxnumblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12maxNumBlocksE"]], "tensorrt_llm::executor::kvcachestats::reusedblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats12reusedBlocksE"]], "tensorrt_llm::executor::kvcachestats::tokensperblock (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats14tokensPerBlockE"]], "tensorrt_llm::executor::kvcachestats::usednumblocks (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12KvCacheStats13usedNumBlocksE"]], "tensorrt_llm::executor::logitspostprocessor (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor19LogitsPostProcessorE"]], "tensorrt_llm::executor::logitspostprocessorbatched (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor26LogitsPostProcessorBatchedE"]], "tensorrt_llm::executor::logitspostprocessorconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfigE"]], "tensorrt_llm::executor::logitspostprocessorconfig::logitspostprocessorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig25LogitsPostProcessorConfigENSt8optionalI22LogitsPostProcessorMapEENSt8optionalI26LogitsPostProcessorBatchedEEb"]], "tensorrt_llm::executor::logitspostprocessorconfig::getprocessorbatched (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig19getProcessorBatchedEv"]], "tensorrt_llm::executor::logitspostprocessorconfig::getprocessormap (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig15getProcessorMapEv"]], "tensorrt_llm::executor::logitspostprocessorconfig::getreplicate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor25LogitsPostProcessorConfig12getReplicateEv"]], "tensorrt_llm::executor::logitspostprocessorconfig::mprocessorbatched (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig17mProcessorBatchedE"]], "tensorrt_llm::executor::logitspostprocessorconfig::mprocessormap (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig13mProcessorMapE"]], "tensorrt_llm::executor::logitspostprocessorconfig::mreplicate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig10mReplicateE"]], "tensorrt_llm::executor::logitspostprocessorconfig::setprocessorbatched (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig19setProcessorBatchedERK26LogitsPostProcessorBatched"]], "tensorrt_llm::executor::logitspostprocessorconfig::setprocessormap (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig15setProcessorMapERK22LogitsPostProcessorMap"]], "tensorrt_llm::executor::logitspostprocessorconfig::setreplicate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor25LogitsPostProcessorConfig12setReplicateEb"]], "tensorrt_llm::executor::logitspostprocessormap (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor22LogitsPostProcessorMapE"]], "tensorrt_llm::executor::lookaheaddecodingconfig (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfigE"]], "tensorrt_llm::executor::lookaheaddecodingconfig::lookaheaddecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigE10SizeType3210SizeType3210SizeType32"], [0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig23LookaheadDecodingConfigEv"]], "tensorrt_llm::executor::lookaheaddecodingconfig::calculatespeculativeresource (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig28calculateSpeculativeResourceEv"]], "tensorrt_llm::executor::lookaheaddecodingconfig::get (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig3getEv"]], "tensorrt_llm::executor::lookaheaddecodingconfig::getngramsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig12getNgramSizeEv"]], "tensorrt_llm::executor::lookaheaddecodingconfig::getverificationsetsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig22getVerificationSetSizeEv"]], "tensorrt_llm::executor::lookaheaddecodingconfig::getwindowsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig13getWindowSizeEv"]], "tensorrt_llm::executor::lookaheaddecodingconfig::isle (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfig4isLEERK23LookaheadDecodingConfig"]], "tensorrt_llm::executor::lookaheaddecodingconfig::islegal (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig7isLegalE10SizeType3210SizeType3210SizeType32"]], "tensorrt_llm::executor::lookaheaddecodingconfig::mngramsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig10mNgramSizeE"]], "tensorrt_llm::executor::lookaheaddecodingconfig::mverificationsetsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig20mVerificationSetSizeE"]], "tensorrt_llm::executor::lookaheaddecodingconfig::mwindowsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor23LookaheadDecodingConfig11mWindowSizeE"]], "tensorrt_llm::executor::lookaheaddecodingconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor23LookaheadDecodingConfigeqERK23LookaheadDecodingConfig"]], "tensorrt_llm::executor::loraconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor10LoraConfigE"]], "tensorrt_llm::executor::loraconfig::loraconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor10LoraConfig10LoraConfigE6IdTypeNSt8optionalI6TensorEENSt8optionalI6TensorEE"]], "tensorrt_llm::executor::loraconfig::getconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor10LoraConfig9getConfigEv"]], "tensorrt_llm::executor::loraconfig::gettaskid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor10LoraConfig9getTaskIdEv"]], "tensorrt_llm::executor::loraconfig::getweights (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor10LoraConfig10getWeightsEv"]], "tensorrt_llm::executor::loraconfig::mconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10LoraConfig7mConfigE"]], "tensorrt_llm::executor::loraconfig::mtaskid (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10LoraConfig7mTaskIdE"]], "tensorrt_llm::executor::loraconfig::mweights (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10LoraConfig8mWeightsE"]], "tensorrt_llm::executor::medusachoices (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor13MedusaChoicesE"]], "tensorrt_llm::executor::memorytype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryTypeE"]], "tensorrt_llm::executor::memorytype::kcpu (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType4kCPUE"]], "tensorrt_llm::executor::memorytype::kcpu_pinned (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType11kCPU_PINNEDE"]], "tensorrt_llm::executor::memorytype::kcpu_pinnedpool (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType15kCPU_PINNEDPOOLE"]], "tensorrt_llm::executor::memorytype::kgpu (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType4kGPUE"]], "tensorrt_llm::executor::memorytype::kunknown (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType8kUNKNOWNE"]], "tensorrt_llm::executor::memorytype::kuvm (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor10MemoryType4kUVME"]], "tensorrt_llm::executor::modeltype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor9ModelTypeE"]], "tensorrt_llm::executor::modeltype::kdecoder_only (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor9ModelType13kDECODER_ONLYE"]], "tensorrt_llm::executor::modeltype::kencoder_decoder (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor9ModelType16kENCODER_DECODERE"]], "tensorrt_llm::executor::modeltype::kencoder_only (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor9ModelType13kENCODER_ONLYE"]], "tensorrt_llm::executor::orchestratorconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfigE"]], "tensorrt_llm::executor::orchestratorconfig::orchestratorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig18OrchestratorConfigEbNSt6stringENSt10shared_ptrIN3mpi7MpiCommEEEb"]], "tensorrt_llm::executor::orchestratorconfig::getisorchestrator (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getIsOrchestratorEv"]], "tensorrt_llm::executor::orchestratorconfig::getorchleadercomm (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getOrchLeaderCommEv"]], "tensorrt_llm::executor::orchestratorconfig::getspawnprocesses (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig17getSpawnProcessesEv"]], "tensorrt_llm::executor::orchestratorconfig::getworkerexecutablepath (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18OrchestratorConfig23getWorkerExecutablePathEv"]], "tensorrt_llm::executor::orchestratorconfig::misorchestrator (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mIsOrchestratorE"]], "tensorrt_llm::executor::orchestratorconfig::morchleadercomm (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mOrchLeaderCommE"]], "tensorrt_llm::executor::orchestratorconfig::mspawnprocesses (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig15mSpawnProcessesE"]], "tensorrt_llm::executor::orchestratorconfig::mworkerexecutablepath (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig21mWorkerExecutablePathE"]], "tensorrt_llm::executor::orchestratorconfig::setisorchestrator (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setIsOrchestratorEb"]], "tensorrt_llm::executor::orchestratorconfig::setorchleadercomm (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setOrchLeaderCommERKNSt10shared_ptrIN3mpi7MpiCommEEE"]], "tensorrt_llm::executor::orchestratorconfig::setspawnprocesses (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig17setSpawnProcessesEb"]], "tensorrt_llm::executor::orchestratorconfig::setworkerexecutablepath (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18OrchestratorConfig23setWorkerExecutablePathERKNSt6stringE"]], "tensorrt_llm::executor::outputconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfigE"]], "tensorrt_llm::executor::outputconfig::outputconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig12OutputConfigEbbbbb"]], "tensorrt_llm::executor::outputconfig::excludeinputfromoutput (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig22excludeInputFromOutputE"]], "tensorrt_llm::executor::outputconfig::returncontextlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig19returnContextLogitsE"]], "tensorrt_llm::executor::outputconfig::returnencoderoutput (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig19returnEncoderOutputE"]], "tensorrt_llm::executor::outputconfig::returngenerationlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig22returnGenerationLogitsE"]], "tensorrt_llm::executor::outputconfig::returnlogprobs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12OutputConfig14returnLogProbsE"]], "tensorrt_llm::executor::parallelconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfigE"]], "tensorrt_llm::executor::parallelconfig::parallelconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig14ParallelConfigE17CommunicationType17CommunicationModeNSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt6vectorI10SizeType32EEEERKNSt8optionalI18OrchestratorConfigEE"]], "tensorrt_llm::executor::parallelconfig::getcommunicationmode (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig20getCommunicationModeEv"]], "tensorrt_llm::executor::parallelconfig::getcommunicationtype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig20getCommunicationTypeEv"]], "tensorrt_llm::executor::parallelconfig::getdeviceids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig12getDeviceIdsEv"]], "tensorrt_llm::executor::parallelconfig::getorchestratorconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig21getOrchestratorConfigEv"]], "tensorrt_llm::executor::parallelconfig::getparticipantids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14ParallelConfig17getParticipantIdsEv"]], "tensorrt_llm::executor::parallelconfig::mcommmode (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig9mCommModeE"]], "tensorrt_llm::executor::parallelconfig::mcommtype (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig9mCommTypeE"]], "tensorrt_llm::executor::parallelconfig::mdeviceids (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig10mDeviceIdsE"]], "tensorrt_llm::executor::parallelconfig::morchestratorconfig (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig19mOrchestratorConfigE"]], "tensorrt_llm::executor::parallelconfig::mparticipantids (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig15mParticipantIdsE"]], "tensorrt_llm::executor::parallelconfig::setcommunicationmode (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationModeE17CommunicationMode"]], "tensorrt_llm::executor::parallelconfig::setcommunicationtype (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig20setCommunicationTypeE17CommunicationType"]], "tensorrt_llm::executor::parallelconfig::setdeviceids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig12setDeviceIdsERKNSt6vectorI10SizeType32EE"]], "tensorrt_llm::executor::parallelconfig::setorchestratorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig21setOrchestratorConfigERK18OrchestratorConfig"]], "tensorrt_llm::executor::parallelconfig::setparticipantids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14ParallelConfig17setParticipantIdsERKNSt6vectorI10SizeType32EE"]], "tensorrt_llm::executor::peftcacheconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfigE"]], "tensorrt_llm::executor::peftcacheconfig::peftcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15PeftCacheConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalIfEERKNSt8optionalI6size_tEE"]], "tensorrt_llm::executor::peftcacheconfig::getdevicecachepercent (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getDeviceCachePercentEv"]], "tensorrt_llm::executor::peftcacheconfig::gethostcachesize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig16getHostCacheSizeEv"]], "tensorrt_llm::executor::peftcacheconfig::getmaxadaptersize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig17getMaxAdapterSizeEv"]], "tensorrt_llm::executor::peftcacheconfig::getmaxpagesperblockdevice (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig25getMaxPagesPerBlockDeviceEv"]], "tensorrt_llm::executor::peftcacheconfig::getmaxpagesperblockhost (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig23getMaxPagesPerBlockHostEv"]], "tensorrt_llm::executor::peftcacheconfig::getnumcopystreams (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig17getNumCopyStreamsEv"]], "tensorrt_llm::executor::peftcacheconfig::getnumdevicemodulelayer (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig23getNumDeviceModuleLayerEv"]], "tensorrt_llm::executor::peftcacheconfig::getnumensureworkers (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig19getNumEnsureWorkersEv"]], "tensorrt_llm::executor::peftcacheconfig::getnumhostmodulelayer (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getNumHostModuleLayerEv"]], "tensorrt_llm::executor::peftcacheconfig::getnumputworkers (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig16getNumPutWorkersEv"]], "tensorrt_llm::executor::peftcacheconfig::getoptimaladaptersize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfig21getOptimalAdapterSizeEv"]], "tensorrt_llm::executor::peftcacheconfig::mdevicecachepercent (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mDeviceCachePercentE"]], "tensorrt_llm::executor::peftcacheconfig::mhostcachesize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig14mHostCacheSizeE"]], "tensorrt_llm::executor::peftcacheconfig::mmaxadaptersize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15mMaxAdapterSizeE"]], "tensorrt_llm::executor::peftcacheconfig::mmaxpagesperblockdevice (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig23mMaxPagesPerBlockDeviceE"]], "tensorrt_llm::executor::peftcacheconfig::mmaxpagesperblockhost (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig21mMaxPagesPerBlockHostE"]], "tensorrt_llm::executor::peftcacheconfig::mnumcopystreams (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig15mNumCopyStreamsE"]], "tensorrt_llm::executor::peftcacheconfig::mnumdevicemodulelayer (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig21mNumDeviceModuleLayerE"]], "tensorrt_llm::executor::peftcacheconfig::mnumensureworkers (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig17mNumEnsureWorkersE"]], "tensorrt_llm::executor::peftcacheconfig::mnumhostmodulelayer (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mNumHostModuleLayerE"]], "tensorrt_llm::executor::peftcacheconfig::mnumputworkers (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig14mNumPutWorkersE"]], "tensorrt_llm::executor::peftcacheconfig::moptimaladaptersize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15PeftCacheConfig19mOptimalAdapterSizeE"]], "tensorrt_llm::executor::peftcacheconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15PeftCacheConfigeqERK15PeftCacheConfig"]], "tensorrt_llm::executor::phonynameduetoerror::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19PhonyNameDueToError5valueE"]], "tensorrt_llm::executor::prioritytype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor12PriorityTypeE"]], "tensorrt_llm::executor::prompttuningconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfigE"]], "tensorrt_llm::executor::prompttuningconfig::prompttuningconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig18PromptTuningConfigE6TensorNSt8optionalI16VecTokenExtraIdsEE"]], "tensorrt_llm::executor::prompttuningconfig::getembeddingtable (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18PromptTuningConfig17getEmbeddingTableEv"]], "tensorrt_llm::executor::prompttuningconfig::getinputtokenextraids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor18PromptTuningConfig21getInputTokenExtraIdsEv"]], "tensorrt_llm::executor::prompttuningconfig::membeddingtable (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig15mEmbeddingTableE"]], "tensorrt_llm::executor::prompttuningconfig::minputtokenextraids (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor18PromptTuningConfig19mInputTokenExtraIdsE"]], "tensorrt_llm::executor::randomseedtype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor14RandomSeedTypeE"]], "tensorrt_llm::executor::request (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor7RequestE"]], "tensorrt_llm::executor::request::request (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request7RequestE9VecTokens10SizeType32bRK14SamplingConfigRK12OutputConfigRKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EENSt8optionalINSt6vectorI10SizeType32EEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalINSt4listI9VecTokensEEEENSt8optionalI6TensorEENSt8optionalI25ExternalDraftTokensConfigEENSt8optionalI18PromptTuningConfigEENSt8optionalI10LoraConfigEENSt8optionalI23LookaheadDecodingConfigEENSt8optionalINSt6stringEEENSt8optionalI9VecTokensEENSt8optionalI6IdTypeEEb12PriorityType11RequestTypeNSt8optionalI18ContextPhaseParamsEENSt8optionalI6TensorEENSt8optionalI10SizeType32EE10SizeType32"], [0, "_CPPv4N12tensorrt_llm8executor7Request7RequestERK7Request"], [0, "_CPPv4N12tensorrt_llm8executor7Request7RequestERR7Request"]], "tensorrt_llm::executor::request::getbadwords (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request11getBadWordsEv"]], "tensorrt_llm::executor::request::getclientid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request11getClientIdEv"]], "tensorrt_llm::executor::request::getcontextphaseparams (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request21getContextPhaseParamsEv"]], "tensorrt_llm::executor::request::getembeddingbias (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request16getEmbeddingBiasEv"]], "tensorrt_llm::executor::request::getencoderinputfeatures (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request23getEncoderInputFeaturesEv"]], "tensorrt_llm::executor::request::getencoderinputtokenids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request23getEncoderInputTokenIdsEv"]], "tensorrt_llm::executor::request::getencoderoutputlength (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request22getEncoderOutputLengthEv"]], "tensorrt_llm::executor::request::getendid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request8getEndIdEv"]], "tensorrt_llm::executor::request::getexternaldrafttokensconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request28getExternalDraftTokensConfigEv"]], "tensorrt_llm::executor::request::getinputtokenids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request16getInputTokenIdsEv"]], "tensorrt_llm::executor::request::getlogitspostprocessorname (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request26getLogitsPostProcessorNameEv"]], "tensorrt_llm::executor::request::getlookaheadconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request18getLookaheadConfigEv"]], "tensorrt_llm::executor::request::getloraconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request13getLoraConfigEv"]], "tensorrt_llm::executor::request::getmaxnewtokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request15getMaxNewTokensEv"]], "tensorrt_llm::executor::request::getmaxtokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request12getMaxTokensEv"]], "tensorrt_llm::executor::request::getnumreturnsequences (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request21getNumReturnSequencesEv"]], "tensorrt_llm::executor::request::getoutputconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request15getOutputConfigEv"]], "tensorrt_llm::executor::request::getpadid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request8getPadIdEv"]], "tensorrt_llm::executor::request::getpositionids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request14getPositionIdsEv"]], "tensorrt_llm::executor::request::getpriority (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request11getPriorityEv"]], "tensorrt_llm::executor::request::getprompttuningconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request21getPromptTuningConfigEv"]], "tensorrt_llm::executor::request::getrequesttype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request14getRequestTypeEv"]], "tensorrt_llm::executor::request::getreturnallgeneratedtokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request27getReturnAllGeneratedTokensEv"]], "tensorrt_llm::executor::request::getsamplingconfig (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request17getSamplingConfigEv"]], "tensorrt_llm::executor::request::getstopwords (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request12getStopWordsEv"]], "tensorrt_llm::executor::request::getstreaming (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor7Request12getStreamingEv"]], "tensorrt_llm::executor::request::kbatchedpostprocessorname (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor7Request25kBatchedPostProcessorNameE"]], "tensorrt_llm::executor::request::kdefaultpriority (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor7Request16kDefaultPriorityE"]], "tensorrt_llm::executor::request::mimpl (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor7Request5mImplE"]], "tensorrt_llm::executor::request::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7RequestaSERK7Request"], [0, "_CPPv4N12tensorrt_llm8executor7RequestaSERR7Request"]], "tensorrt_llm::executor::request::setbadwords (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request11setBadWordsERKNSt4listI9VecTokensEE"]], "tensorrt_llm::executor::request::setclientid (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request11setClientIdE6IdType"]], "tensorrt_llm::executor::request::setcontextphaseparams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request21setContextPhaseParamsE18ContextPhaseParams"]], "tensorrt_llm::executor::request::setembeddingbias (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request16setEmbeddingBiasERK6Tensor"]], "tensorrt_llm::executor::request::setencoderinputfeatures (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputFeaturesE6Tensor"]], "tensorrt_llm::executor::request::setencoderinputtokenids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request23setEncoderInputTokenIdsERK9VecTokens"]], "tensorrt_llm::executor::request::setencoderoutputlength (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request22setEncoderOutputLengthE10SizeType32"]], "tensorrt_llm::executor::request::setendid (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request8setEndIdE10SizeType32"]], "tensorrt_llm::executor::request::setexternaldrafttokensconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request28setExternalDraftTokensConfigERK25ExternalDraftTokensConfig"]], "tensorrt_llm::executor::request::setlogitspostprocessorname (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request26setLogitsPostProcessorNameERKNSt6stringE"]], "tensorrt_llm::executor::request::setlookaheadconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request18setLookaheadConfigERK23LookaheadDecodingConfig"]], "tensorrt_llm::executor::request::setloraconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request13setLoraConfigERK10LoraConfig"]], "tensorrt_llm::executor::request::setnumreturnsequences (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request21setNumReturnSequencesE10SizeType32"]], "tensorrt_llm::executor::request::setoutputconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request15setOutputConfigERK12OutputConfig"]], "tensorrt_llm::executor::request::setpadid (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request8setPadIdE10SizeType32"]], "tensorrt_llm::executor::request::setpositionids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request14setPositionIdsERKNSt6vectorI10SizeType32EE"]], "tensorrt_llm::executor::request::setpriority (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request11setPriorityE12PriorityType"]], "tensorrt_llm::executor::request::setprompttuningconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request21setPromptTuningConfigERK18PromptTuningConfig"]], "tensorrt_llm::executor::request::setrequesttype (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request14setRequestTypeERK11RequestType"]], "tensorrt_llm::executor::request::setreturnallgeneratedtokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request27setReturnAllGeneratedTokensEb"]], "tensorrt_llm::executor::request::setsamplingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request17setSamplingConfigERK14SamplingConfig"]], "tensorrt_llm::executor::request::setstopwords (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request12setStopWordsERKNSt4listI9VecTokensEE"]], "tensorrt_llm::executor::request::setstreaming (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7Request12setStreamingEb"]], "tensorrt_llm::executor::request::~request (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7RequestD0Ev"]], "tensorrt_llm::executor::requeststage (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStageE"]], "tensorrt_llm::executor::requeststage::kcontext_in_progress (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStage20kCONTEXT_IN_PROGRESSE"]], "tensorrt_llm::executor::requeststage::kencoder_in_progress (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStage20kENCODER_IN_PROGRESSE"]], "tensorrt_llm::executor::requeststage::kgeneration_complete (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStage20kGENERATION_COMPLETEE"]], "tensorrt_llm::executor::requeststage::kgeneration_in_progress (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStage23kGENERATION_IN_PROGRESSE"]], "tensorrt_llm::executor::requeststage::kqueued (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStage7kQUEUEDE"]], "tensorrt_llm::executor::requeststats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStatsE"]], "tensorrt_llm::executor::requeststats::avgnumdecodedtokensperiter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats26avgNumDecodedTokensPerIterE"]], "tensorrt_llm::executor::requeststats::contextprefillposition (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats22contextPrefillPositionE"]], "tensorrt_llm::executor::requeststats::id (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats2idE"]], "tensorrt_llm::executor::requeststats::numgeneratedtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats18numGeneratedTokensE"]], "tensorrt_llm::executor::requeststats::paused (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats6pausedE"]], "tensorrt_llm::executor::requeststats::scheduled (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats9scheduledE"]], "tensorrt_llm::executor::requeststats::stage (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor12RequestStats5stageE"]], "tensorrt_llm::executor::requeststatsperiteration (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIterationE"]], "tensorrt_llm::executor::requeststatsperiteration::iter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIteration4iterE"]], "tensorrt_llm::executor::requeststatsperiteration::requeststats (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor24RequestStatsPerIteration12requestStatsE"]], "tensorrt_llm::executor::requesttype (c++ enum)": [[0, "_CPPv4N12tensorrt_llm8executor11RequestTypeE"]], "tensorrt_llm::executor::requesttype::request_type_context_and_generation (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor11RequestType35REQUEST_TYPE_CONTEXT_AND_GENERATIONE"]], "tensorrt_llm::executor::requesttype::request_type_context_only (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor11RequestType25REQUEST_TYPE_CONTEXT_ONLYE"]], "tensorrt_llm::executor::requesttype::request_type_generation_only (c++ enumerator)": [[0, "_CPPv4N12tensorrt_llm8executor11RequestType28REQUEST_TYPE_GENERATION_ONLYE"]], "tensorrt_llm::executor::response (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor8ResponseE"]], "tensorrt_llm::executor::response::response (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdType6Result"], [0, "_CPPv4N12tensorrt_llm8executor8Response8ResponseE6IdTypeNSt6stringE"], [0, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERK8Response"], [0, "_CPPv4N12tensorrt_llm8executor8Response8ResponseERR8Response"]], "tensorrt_llm::executor::response::geterrormsg (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Response11getErrorMsgEv"]], "tensorrt_llm::executor::response::getrequestid (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Response12getRequestIdEv"]], "tensorrt_llm::executor::response::getresult (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Response9getResultEv"]], "tensorrt_llm::executor::response::haserror (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor8Response8hasErrorEv"]], "tensorrt_llm::executor::response::mimpl (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor8Response5mImplE"]], "tensorrt_llm::executor::response::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8ResponseaSERK8Response"], [0, "_CPPv4N12tensorrt_llm8executor8ResponseaSERR8Response"]], "tensorrt_llm::executor::response::~response (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor8ResponseD0Ev"]], "tensorrt_llm::executor::result (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor6ResultE"]], "tensorrt_llm::executor::result::contextlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result13contextLogitsE"]], "tensorrt_llm::executor::result::contextphaseparams (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result18contextPhaseParamsE"]], "tensorrt_llm::executor::result::cumlogprobs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result11cumLogProbsE"]], "tensorrt_llm::executor::result::decodingiter (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result12decodingIterE"]], "tensorrt_llm::executor::result::encoderoutput (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result13encoderOutputE"]], "tensorrt_llm::executor::result::finishreasons (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result13finishReasonsE"]], "tensorrt_llm::executor::result::generationlogits (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result16generationLogitsE"]], "tensorrt_llm::executor::result::isfinal (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result7isFinalE"]], "tensorrt_llm::executor::result::issequencefinal (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result15isSequenceFinalE"]], "tensorrt_llm::executor::result::logprobs (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result8logProbsE"]], "tensorrt_llm::executor::result::outputtokenids (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result14outputTokenIdsE"]], "tensorrt_llm::executor::result::sequenceindex (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Result13sequenceIndexE"]], "tensorrt_llm::executor::samplingconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfigE"]], "tensorrt_llm::executor::samplingconfig::samplingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14SamplingConfigE10SizeType32RKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI11TokenIdTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI14RandomSeedTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI9FloatTypeEERKNSt8optionalI10SizeType32EERKNSt8optionalI10SizeType32EE"]], "tensorrt_llm::executor::samplingconfig::checkbeamsearchdiversityrate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig28checkBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE"]], "tensorrt_llm::executor::samplingconfig::checkbeamwidth (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkBeamWidthE10SizeType32"]], "tensorrt_llm::executor::samplingconfig::checkmintokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkMinTokensERKNSt8optionalI10SizeType32EE"]], "tensorrt_llm::executor::samplingconfig::checknorepeatngramsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE"]], "tensorrt_llm::executor::samplingconfig::checkrepetitionpenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig22checkRepetitionPenaltyERKNSt8optionalI9FloatTypeEE"]], "tensorrt_llm::executor::samplingconfig::checktemperature (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16checkTemperatureERKNSt8optionalI9FloatTypeEE"]], "tensorrt_llm::executor::samplingconfig::checktopk (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopKERKNSt8optionalI9FloatTypeEE"]], "tensorrt_llm::executor::samplingconfig::checktopp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig9checkTopPERKNSt8optionalI9FloatTypeEE"]], "tensorrt_llm::executor::samplingconfig::checktoppdecay (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14checkTopPDecayERKNSt8optionalI9FloatTypeEE"]], "tensorrt_llm::executor::samplingconfig::checktoppmin (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12checkTopPMinERKNSt8optionalI9FloatTypeEE"]], "tensorrt_llm::executor::samplingconfig::checktoppresetids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17checkTopPResetIdsERKNSt8optionalI11TokenIdTypeEE"]], "tensorrt_llm::executor::samplingconfig::getbeamsearchdiversityrate (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig26getBeamSearchDiversityRateEv"]], "tensorrt_llm::executor::samplingconfig::getbeamwidth (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getBeamWidthEv"]], "tensorrt_llm::executor::samplingconfig::getearlystopping (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig16getEarlyStoppingEv"]], "tensorrt_llm::executor::samplingconfig::getfrequencypenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig19getFrequencyPenaltyEv"]], "tensorrt_llm::executor::samplingconfig::getlengthpenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig16getLengthPenaltyEv"]], "tensorrt_llm::executor::samplingconfig::getminlength (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getMinLengthEv"]], "tensorrt_llm::executor::samplingconfig::getmintokens (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getMinTokensEv"]], "tensorrt_llm::executor::samplingconfig::getnorepeatngramsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig20getNoRepeatNgramSizeEv"]], "tensorrt_llm::executor::samplingconfig::getpresencepenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig18getPresencePenaltyEv"]], "tensorrt_llm::executor::samplingconfig::getrandomseed (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig13getRandomSeedEv"]], "tensorrt_llm::executor::samplingconfig::getrepetitionpenalty (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig20getRepetitionPenaltyEv"]], "tensorrt_llm::executor::samplingconfig::getseed (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getSeedEv"]], "tensorrt_llm::executor::samplingconfig::gettemperature (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig14getTemperatureEv"]], "tensorrt_llm::executor::samplingconfig::gettopk (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getTopKEv"]], "tensorrt_llm::executor::samplingconfig::gettopp (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig7getTopPEv"]], "tensorrt_llm::executor::samplingconfig::gettoppdecay (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig12getTopPDecayEv"]], "tensorrt_llm::executor::samplingconfig::gettoppmin (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig10getTopPMinEv"]], "tensorrt_llm::executor::samplingconfig::gettoppresetids (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfig15getTopPResetIdsEv"]], "tensorrt_llm::executor::samplingconfig::mbeamsearchdiversityrate (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig24mBeamSearchDiversityRateE"]], "tensorrt_llm::executor::samplingconfig::mbeamwidth (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mBeamWidthE"]], "tensorrt_llm::executor::samplingconfig::mearlystopping (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14mEarlyStoppingE"]], "tensorrt_llm::executor::samplingconfig::mfrequencypenalty (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig17mFrequencyPenaltyE"]], "tensorrt_llm::executor::samplingconfig::mlengthpenalty (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14mLengthPenaltyE"]], "tensorrt_llm::executor::samplingconfig::mmintokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mMinTokensE"]], "tensorrt_llm::executor::samplingconfig::mnorepeatngramsize (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18mNoRepeatNgramSizeE"]], "tensorrt_llm::executor::samplingconfig::mpresencepenalty (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16mPresencePenaltyE"]], "tensorrt_llm::executor::samplingconfig::mrepetitionpenalty (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18mRepetitionPenaltyE"]], "tensorrt_llm::executor::samplingconfig::mseed (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mSeedE"]], "tensorrt_llm::executor::samplingconfig::mtemperature (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12mTemperatureE"]], "tensorrt_llm::executor::samplingconfig::mtopk (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mTopKE"]], "tensorrt_llm::executor::samplingconfig::mtopp (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig5mTopPE"]], "tensorrt_llm::executor::samplingconfig::mtoppdecay (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10mTopPDecayE"]], "tensorrt_llm::executor::samplingconfig::mtoppmin (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig8mTopPMinE"]], "tensorrt_llm::executor::samplingconfig::mtoppresetids (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig13mTopPResetIdsE"]], "tensorrt_llm::executor::samplingconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor14SamplingConfigeqERK14SamplingConfig"]], "tensorrt_llm::executor::samplingconfig::setbeamsearchdiversityrate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig26setBeamSearchDiversityRateERKNSt8optionalI9FloatTypeEE"]], "tensorrt_llm::executor::samplingconfig::setbeamwidth (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setBeamWidthE10SizeType32"]], "tensorrt_llm::executor::samplingconfig::setearlystopping (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setEarlyStoppingERKNSt8optionalI10SizeType32EE"]], "tensorrt_llm::executor::samplingconfig::setfrequencypenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig19setFrequencyPenaltyERKNSt8optionalI9FloatTypeEE"]], "tensorrt_llm::executor::samplingconfig::setlengthpenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig16setLengthPenaltyERKNSt8optionalI9FloatTypeEE"]], "tensorrt_llm::executor::samplingconfig::setminlength (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setMinLengthERKNSt8optionalI10SizeType32EE"]], "tensorrt_llm::executor::samplingconfig::setmintokens (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setMinTokensERKNSt8optionalI10SizeType32EE"]], "tensorrt_llm::executor::samplingconfig::setnorepeatngramsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setNoRepeatNgramSizeERKNSt8optionalI10SizeType32EE"]], "tensorrt_llm::executor::samplingconfig::setpresencepenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig18setPresencePenaltyERKNSt8optionalI9FloatTypeEE"]], "tensorrt_llm::executor::samplingconfig::setrandomseed (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig13setRandomSeedERKNSt8optionalI14RandomSeedTypeEE"]], "tensorrt_llm::executor::samplingconfig::setrepetitionpenalty (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig20setRepetitionPenaltyERKNSt8optionalI9FloatTypeEE"]], "tensorrt_llm::executor::samplingconfig::setseed (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setSeedERKNSt8optionalI14RandomSeedTypeEE"]], "tensorrt_llm::executor::samplingconfig::settemperature (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig14setTemperatureERKNSt8optionalI9FloatTypeEE"]], "tensorrt_llm::executor::samplingconfig::settopk (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopKERKNSt8optionalI10SizeType32EE"]], "tensorrt_llm::executor::samplingconfig::settopp (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig7setTopPERKNSt8optionalI9FloatTypeEE"]], "tensorrt_llm::executor::samplingconfig::settoppdecay (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig12setTopPDecayERKNSt8optionalI9FloatTypeEE"]], "tensorrt_llm::executor::samplingconfig::settoppmin (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig10setTopPMinERKNSt8optionalI9FloatTypeEE"]], "tensorrt_llm::executor::samplingconfig::settoppresetids (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor14SamplingConfig15setTopPResetIdsERKNSt8optionalI11TokenIdTypeEE"]], "tensorrt_llm::executor::schedulerconfig (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor15SchedulerConfigE"]], "tensorrt_llm::executor::schedulerconfig::schedulerconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig15SchedulerConfigE23CapacitySchedulerPolicyNSt8optionalI21ContextChunkingPolicyEE"]], "tensorrt_llm::executor::schedulerconfig::getcapacityschedulerpolicy (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfig26getCapacitySchedulerPolicyEv"]], "tensorrt_llm::executor::schedulerconfig::getcontextchunkingpolicy (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfig24getContextChunkingPolicyEv"]], "tensorrt_llm::executor::schedulerconfig::mcapacityschedulerpolicy (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig24mCapacitySchedulerPolicyE"]], "tensorrt_llm::executor::schedulerconfig::mcontextchunkingpolicy (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor15SchedulerConfig22mContextChunkingPolicyE"]], "tensorrt_llm::executor::schedulerconfig::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor15SchedulerConfigeqERK15SchedulerConfig"]], "tensorrt_llm::executor::serialization (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor13SerializationE"]], "tensorrt_llm::executor::serialization::deserializebool (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization15deserializeBoolERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializecachestate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeCacheStateERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializecommstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeCommStateERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializecontextphaseparams (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeContextPhaseParamsERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializecontextphasestate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization28deserializeContextPhaseStateERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializedebugconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeDebugConfigERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializedecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeDecodingConfigERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializedecodingmode (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeDecodingModeERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializeexecutorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeExecutorConfigERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializeextendedruntimeperfknobconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization40deserializeExtendedRuntimePerfKnobConfigERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializeexternaldrafttokensconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization36deserializeExternalDraftTokensConfigERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializeinflightbatchingstats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization32deserializeInflightBatchingStatsERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializeiterationstats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt6vectorIcEE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeIterationStatsERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializekvcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization24deserializeKvCacheConfigERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializekvcachestats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeKvCacheStatsERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializelookaheaddecodingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization34deserializeLookaheadDecodingConfigERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializeloraconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization21deserializeLoraConfigERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializemodeltype (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeModelTypeERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializeorchestratorconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializeOrchestratorConfigERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializeoutputconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization23deserializeOutputConfigERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializeparallelconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeParallelConfigERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializepeftcacheconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializePeftCacheConfigERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializeprompttuningconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization29deserializePromptTuningConfigERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializerequest (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization18deserializeRequestERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializeresponse (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization19deserializeResponseERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializeresponses (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization20deserializeResponsesERNSt6vectorIcEE"]], "tensorrt_llm::executor::serialization::deserializeresult (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeResultERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializesamplingconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization25deserializeSamplingConfigERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializeschedulerconfig (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization26deserializeSchedulerConfigERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializesocketstate (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization22deserializeSocketStateERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializestaticbatchingstats (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization30deserializeStaticBatchingStatsERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializestring (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeStringERNSt7istreamE"]], "tensorrt_llm::executor::serialization::deserializetensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization17deserializeTensorERNSt7istreamE"]], "tensorrt_llm::executor::serialization::serialize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK10LoraConfigRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK11DebugConfigRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12DecodingModeRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12KvCacheStatsRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK12OutputConfigRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK13KvCacheConfigRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14DecodingConfigRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ExecutorConfigRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStats"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14IterationStatsRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14ParallelConfigRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK14SamplingConfigRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15PeftCacheConfigRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK15SchedulerConfigRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK17ContextPhaseStateRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18ContextPhaseParamsRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18OrchestratorConfigRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK18PromptTuningConfigRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK19StaticBatchingStatsRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK21InflightBatchingStatsRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK23LookaheadDecodingConfigRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK25ExternalDraftTokensConfigRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK29ExtendedRuntimePerfKnobConfigRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6ResultRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK6TensorRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK7RequestRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERK8ResponseRNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache10CacheStateERNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache11SocketStateERNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKN8kv_cache9CommStateERNSt7ostreamE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization9serializeERKNSt6vectorI8ResponseEE"]], "tensorrt_llm::executor::serialization::serializedsize (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK10LoraConfig"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK11DebugConfig"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12DecodingMode"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12KvCacheStats"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK12OutputConfig"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK13KvCacheConfig"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14DecodingConfig"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ExecutorConfig"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14IterationStats"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14ParallelConfig"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK14SamplingConfig"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15PeftCacheConfig"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK15SchedulerConfig"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK17ContextPhaseState"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18ContextPhaseParams"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18OrchestratorConfig"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK18PromptTuningConfig"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK19StaticBatchingStats"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK21InflightBatchingStats"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK23LookaheadDecodingConfig"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK25ExternalDraftTokensConfig"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK29ExtendedRuntimePerfKnobConfig"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Result"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK6Tensor"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK7Request"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERK8Response"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache10CacheStateE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache11SocketStateE"], [0, "_CPPv4N12tensorrt_llm8executor13Serialization14serializedSizeERKN8kv_cache9CommStateE"]], "tensorrt_llm::executor::shape (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor5ShapeE"]], "tensorrt_llm::executor::shape::base (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor5Shape4BaseE"]], "tensorrt_llm::executor::shape::dimtype64 (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor5Shape9DimType64E"]], "tensorrt_llm::executor::shape::shape (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeENSt16initializer_listI9DimType64EE"], [0, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEPK9DimType64N4Base9size_typeE"], [0, "_CPPv4N12tensorrt_llm8executor5Shape5ShapeEv"]], "tensorrt_llm::executor::sizetype32 (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor10SizeType32E"]], "tensorrt_llm::executor::staticbatchingstats (c++ struct)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStatsE"]], "tensorrt_llm::executor::staticbatchingstats::emptygenslots (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats13emptyGenSlotsE"]], "tensorrt_llm::executor::staticbatchingstats::numcontextrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats18numContextRequestsE"]], "tensorrt_llm::executor::staticbatchingstats::numctxtokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats12numCtxTokensE"]], "tensorrt_llm::executor::staticbatchingstats::numgentokens (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats12numGenTokensE"]], "tensorrt_llm::executor::staticbatchingstats::numscheduledrequests (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor19StaticBatchingStats20numScheduledRequestsE"]], "tensorrt_llm::executor::streamptr (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor9StreamPtrE"]], "tensorrt_llm::executor::tensor (c++ class)": [[0, "_CPPv4N12tensorrt_llm8executor6TensorE"]], "tensorrt_llm::executor::tensor::cudastreamptr (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor13CudaStreamPtrE"]], "tensorrt_llm::executor::tensor::impl (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor4ImplE"]], "tensorrt_llm::executor::tensor::tensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorENSt10shared_ptrIN7runtime7ITensorEEE"], [0, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERK6Tensor"], [0, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorERR6Tensor"], [0, "_CPPv4N12tensorrt_llm8executor6Tensor6TensorEv"]], "tensorrt_llm::executor::tensor::copyto (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor6copyToENSt10shared_ptrI4ImplEE13CudaStreamPtr"]], "tensorrt_llm::executor::tensor::copytocpu (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToCpuEN6Tensor13CudaStreamPtrE"]], "tensorrt_llm::executor::tensor::copytogpu (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor9copyToGpuEN6Tensor13CudaStreamPtrE"]], "tensorrt_llm::executor::tensor::copytomanaged (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor13copyToManagedEN6Tensor13CudaStreamPtrE"]], "tensorrt_llm::executor::tensor::copytopinned (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor12copyToPinnedEN6Tensor13CudaStreamPtrE"]], "tensorrt_llm::executor::tensor::copytopooledpinned (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor18copyToPooledPinnedEN6Tensor13CudaStreamPtrE"]], "tensorrt_llm::executor::tensor::cpu (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3cpuE6Tensor5Shape"], [0, "_CPPv4N12tensorrt_llm8executor6Tensor3cpuE8DataType5Shape"]], "tensorrt_llm::executor::tensor::detail::ofitensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE"]], "tensorrt_llm::executor::tensor::detail::toitensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor6detail9toITensorERK6Tensor"]], "tensorrt_llm::executor::tensor::getdata (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor7getDataEv"], [0, "_CPPv4NK12tensorrt_llm8executor6Tensor7getDataEv"]], "tensorrt_llm::executor::tensor::getdatatype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor11getDataTypeEv"]], "tensorrt_llm::executor::tensor::getmemorytype (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor13getMemoryTypeEv"]], "tensorrt_llm::executor::tensor::getruntimetype (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor14getRuntimeTypeE8DataTypev"]], "tensorrt_llm::executor::tensor::getshape (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor8getShapeEv"]], "tensorrt_llm::executor::tensor::getsize (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor7getSizeEv"]], "tensorrt_llm::executor::tensor::getsizeinbytes (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6Tensor14getSizeInBytesEv"]], "tensorrt_llm::executor::tensor::gpu (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor3gpuE6Tensor13CudaStreamPtr5Shape"], [0, "_CPPv4N12tensorrt_llm8executor6Tensor3gpuE8DataType13CudaStreamPtr5Shape"]], "tensorrt_llm::executor::tensor::mtensor (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor7mTensorE"]], "tensorrt_llm::executor::tensor::managed (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor7managedE6Tensor5Shape"], [0, "_CPPv4N12tensorrt_llm8executor6Tensor7managedE8DataType5Shape"]], "tensorrt_llm::executor::tensor::of (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorP1T5Shape"], [0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor2ofE6TensorR1T"], [0, "_CPPv4N12tensorrt_llm8executor6Tensor2ofE8DataTypePv5Shape"]], "tensorrt_llm::executor::tensor::operator bool (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6TensorcvbEv"]], "tensorrt_llm::executor::tensor::operator!= (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6TensorneERK6Tensor"]], "tensorrt_llm::executor::tensor::operator= (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6TensoraSERK6Tensor"], [0, "_CPPv4N12tensorrt_llm8executor6TensoraSERR6Tensor"]], "tensorrt_llm::executor::tensor::operator== (c++ function)": [[0, "_CPPv4NK12tensorrt_llm8executor6TensoreqERK6Tensor"]], "tensorrt_llm::executor::tensor::pinned (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor6pinnedE6Tensor5Shape"], [0, "_CPPv4N12tensorrt_llm8executor6Tensor6pinnedE8DataType5Shape"]], "tensorrt_llm::executor::tensor::pooledpinned (c++ function)": [[0, "_CPPv4I0EN12tensorrt_llm8executor6Tensor12pooledPinnedE6Tensor5Shape"], [0, "_CPPv4N12tensorrt_llm8executor6Tensor12pooledPinnedE8DataType5Shape"]], "tensorrt_llm::executor::tensor::setfrom (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor7setFromERK6Tensor13CudaStreamPtr"]], "tensorrt_llm::executor::tensor::setzero (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6Tensor7setZeroE13CudaStreamPtr"]], "tensorrt_llm::executor::tensor::~tensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6TensorD0Ev"]], "tensorrt_llm::executor::tensorptr (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor9TensorPtrE"]], "tensorrt_llm::executor::tokenidtype (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor11TokenIdTypeE"]], "tensorrt_llm::executor::typetraits (c++ struct)": [[0, "_CPPv4I0_bEN12tensorrt_llm8executor10TypeTraitsE"]], "tensorrt_llm::executor::typetraits<t*> (c++ struct)": [[0, "_CPPv4I0EN12tensorrt_llm8executor10TypeTraitsIP1TEE"]], "tensorrt_llm::executor::typetraits<t*>::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIP1TE5valueE"]], "tensorrt_llm::executor::typetraits<bool> (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsIbEE"]], "tensorrt_llm::executor::typetraits<bool>::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIbE5valueE"]], "tensorrt_llm::executor::typetraits<float> (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsIfEE"]], "tensorrt_llm::executor::typetraits<float>::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsIfE5valueE"]], "tensorrt_llm::executor::typetraits<half> (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsI4halfEE"]], "tensorrt_llm::executor::typetraits<half>::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsI4halfE5valueE"]], "tensorrt_llm::executor::typetraits<std::int32_t> (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7int32_tEEE"]], "tensorrt_llm::executor::typetraits<std::int32_t>::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7int32_tEE5valueE"]], "tensorrt_llm::executor::typetraits<std::int64_t> (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7int64_tEEE"]], "tensorrt_llm::executor::typetraits<std::int64_t>::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7int64_tEE5valueE"]], "tensorrt_llm::executor::typetraits<std::int8_t> (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt6int8_tEEE"]], "tensorrt_llm::executor::typetraits<std::int8_t>::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt6int8_tEE5valueE"]], "tensorrt_llm::executor::typetraits<std::uint8_t> (c++ struct)": [[0, "_CPPv4IEN12tensorrt_llm8executor10TypeTraitsINSt7uint8_tEEE"]], "tensorrt_llm::executor::typetraits<std::uint8_t>::value (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor10TypeTraitsINSt7uint8_tEE5valueE"]], "tensorrt_llm::executor::veclogprobs (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor11VecLogProbsE"]], "tensorrt_llm::executor::vectokenextraids (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor16VecTokenExtraIdsE"]], "tensorrt_llm::executor::vectokens (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor9VecTokensE"]], "tensorrt_llm::executor::detail (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor6detailE"]], "tensorrt_llm::executor::detail::dimtype64 (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor6detail9DimType64E"]], "tensorrt_llm::executor::detail::ofitensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6detail9ofITensorENSt10shared_ptrIN7runtime7ITensorEEE"]], "tensorrt_llm::executor::detail::toitensor (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor6detail9toITensorERK6Tensor"]], "tensorrt_llm::executor::kdefaultiterstatsmaxiterations (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor30kDefaultIterStatsMaxIterationsE"]], "tensorrt_llm::executor::kdefaultrequeststatsmaxiterations (c++ member)": [[0, "_CPPv4N12tensorrt_llm8executor33kDefaultRequestStatsMaxIterationsE"]], "tensorrt_llm::executor::kv_cache (c++ type)": [[0, "_CPPv4N12tensorrt_llm8executor8kv_cacheE"]], "tensorrt_llm::executor::operator<< (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE21ContextChunkingPolicy"], [0, "_CPPv4N12tensorrt_llm8executorlsERNSt7ostreamE23CapacitySchedulerPolicy"]], "tensorrt_llm::executor::version (c++ function)": [[0, "_CPPv4N12tensorrt_llm8executor7versionEv"]], "tensorrt_llm::mpi (c++ type)": [[0, "_CPPv4N12tensorrt_llm3mpiE"]], "tensorrt_llm::runtime (c++ type)": [[0, "_CPPv4N12tensorrt_llm7runtimeE"], [1, "_CPPv4N12tensorrt_llm7runtimeE"]], "fmt_dim (c macro)": [[1, "c.FMT_DIM"]], "set_from_optional (c macro)": [[1, "c.SET_FROM_OPTIONAL"]], "nvinfer1 (c++ type)": [[1, "_CPPv48nvinfer1"]], "tensorrt_llm::batch_manager (c++ type)": [[1, "_CPPv4N12tensorrt_llm13batch_managerE"]], "tensorrt_llm::batch_manager::kv_cache_manager (c++ type)": [[1, "_CPPv4N12tensorrt_llm13batch_manager16kv_cache_managerE"]], "tensorrt_llm::layers (c++ type)": [[1, "_CPPv4N12tensorrt_llm6layersE"]], "tensorrt_llm::runtime::allreducebuffers (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffersE"]], "tensorrt_llm::runtime::allreducebuffers::allreducebuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers16AllReduceBuffersE10SizeType3210SizeType3210SizeType3210SizeType32RK13BufferManagerRK11WorldConfig"]], "tensorrt_llm::runtime::allreducebuffers::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers9TensorPtrE"]], "tensorrt_llm::runtime::allreducebuffers::mallreducecommptrs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers18mAllReduceCommPtrsE"]], "tensorrt_llm::runtime::allreducebuffers::mipcmemoryhandles (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16AllReduceBuffers17mIpcMemoryHandlesE"]], "tensorrt_llm::runtime::bufferdatatype (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataTypeE"]], "tensorrt_llm::runtime::bufferdatatype::bufferdatatype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb"]], "tensorrt_llm::runtime::bufferdatatype::getdatatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType11getDataTypeEv"]], "tensorrt_llm::runtime::bufferdatatype::getsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType7getSizeEv"]], "tensorrt_llm::runtime::bufferdatatype::ispointer (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType9isPointerEv"]], "tensorrt_llm::runtime::bufferdatatype::isunsigned (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataType10isUnsignedEv"]], "tensorrt_llm::runtime::bufferdatatype::ktrtpointertype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType15kTrtPointerTypeE"]], "tensorrt_llm::runtime::bufferdatatype::mdatatype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType9mDataTypeE"]], "tensorrt_llm::runtime::bufferdatatype::mpointer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType8mPointerE"]], "tensorrt_llm::runtime::bufferdatatype::munsigned (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14BufferDataType9mUnsignedE"]], "tensorrt_llm::runtime::bufferdatatype::operator nvinfer1::datatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14BufferDataTypecvN8nvinfer18DataTypeEEv"]], "tensorrt_llm::runtime::buffermanager (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManagerE"]], "tensorrt_llm::runtime::buffermanager::buffermanager (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager13BufferManagerE13CudaStreamPtrb"]], "tensorrt_llm::runtime::buffermanager::cudamempoolptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager14CudaMemPoolPtrE"]], "tensorrt_llm::runtime::buffermanager::cudastreamptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager13CudaStreamPtrE"]], "tensorrt_llm::runtime::buffermanager::ibufferptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10IBufferPtrE"]], "tensorrt_llm::runtime::buffermanager::itensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10ITensorPtrE"]], "tensorrt_llm::runtime::buffermanager::allocate (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE"], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE"]], "tensorrt_llm::runtime::buffermanager::copy (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer"], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType"], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv"], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType"], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferR7IBuffer"]], "tensorrt_llm::runtime::buffermanager::copyfrom (c++ function)": [[1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10IBufferPtrRKNSt6vectorI1TEE10MemoryType"], [1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType"], [1, "_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType"], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7IBuffer10MemoryType"], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7ITensor10MemoryType"]], "tensorrt_llm::runtime::buffermanager::cpu (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuEN8nvinfer14DimsEN8nvinfer18DataTypeE"], [1, "_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuENSt6size_tEN8nvinfer18DataTypeE"]], "tensorrt_llm::runtime::buffermanager::emptybuffer (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyBufferE10MemoryTypeN8nvinfer18DataTypeE"]], "tensorrt_llm::runtime::buffermanager::emptytensor (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyTensorE10MemoryTypeN8nvinfer18DataTypeE"]], "tensorrt_llm::runtime::buffermanager::getstream (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager9getStreamEv"]], "tensorrt_llm::runtime::buffermanager::gpu (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuEN8nvinfer14DimsEN8nvinfer18DataTypeE"], [1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuENSt6size_tEN8nvinfer18DataTypeE"]], "tensorrt_llm::runtime::buffermanager::gpusync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncEN8nvinfer14DimsEN8nvinfer18DataTypeE"], [1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7gpuSyncENSt6size_tEN8nvinfer18DataTypeE"]], "tensorrt_llm::runtime::buffermanager::kbyte_type (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE"]], "tensorrt_llm::runtime::buffermanager::mpool (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager5mPoolE"]], "tensorrt_llm::runtime::buffermanager::mstream (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7mStreamE"]], "tensorrt_llm::runtime::buffermanager::mtrimpool (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager9mTrimPoolE"]], "tensorrt_llm::runtime::buffermanager::managed (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedEN8nvinfer14DimsEN8nvinfer18DataTypeE"], [1, "_CPPv4N12tensorrt_llm7runtime13BufferManager7managedENSt6size_tEN8nvinfer18DataTypeE"]], "tensorrt_llm::runtime::buffermanager::memorypoolfree (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager14memoryPoolFreeEv"]], "tensorrt_llm::runtime::buffermanager::memorypoolreserved (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager18memoryPoolReservedEv"]], "tensorrt_llm::runtime::buffermanager::memorypooltrimto (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager16memoryPoolTrimToENSt6size_tE"]], "tensorrt_llm::runtime::buffermanager::memorypoolused (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager14memoryPoolUsedEv"]], "tensorrt_llm::runtime::buffermanager::pinned (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedEN8nvinfer14DimsEN8nvinfer18DataTypeE"], [1, "_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedENSt6size_tEN8nvinfer18DataTypeE"]], "tensorrt_llm::runtime::buffermanager::pinnedpool (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolEN8nvinfer14DimsEN8nvinfer18DataTypeE"], [1, "_CPPv4N12tensorrt_llm7runtime13BufferManager10pinnedPoolENSt6size_tEN8nvinfer18DataTypeE"]], "tensorrt_llm::runtime::buffermanager::setmem (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager6setMemER7IBuffer7int32_t"]], "tensorrt_llm::runtime::buffermanager::setzero (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13BufferManager7setZeroER7IBuffer"]], "tensorrt_llm::runtime::buffermanager::~buffermanager (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13BufferManagerD0Ev"]], "tensorrt_llm::runtime::bufferrange (c++ class)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime11BufferRangeE"]], "tensorrt_llm::runtime::bufferrange::base (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime11BufferRange4BaseE"]], "tensorrt_llm::runtime::bufferrange::bufferrange (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI1UEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeERK7IBuffer"], [1, "_CPPv4I0_NSt11enable_if_tIXntNSt10is_const_vI1UEEEbEEEN12tensorrt_llm7runtime11BufferRange11BufferRangeER7IBuffer"], [1, "_CPPv4N12tensorrt_llm7runtime11BufferRange11BufferRangeEP1T9size_type"]], "tensorrt_llm::runtime::cudaevent (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEventE"]], "tensorrt_llm::runtime::cudaevent::cudaevent (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventE7pointerb"], [1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventEj"]], "tensorrt_llm::runtime::cudaevent::deleter (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7DeleterE"]], "tensorrt_llm::runtime::cudaevent::deleter::deleter (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEb"], [1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEv"]], "tensorrt_llm::runtime::cudaevent::deleter::mownsevent (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter10mOwnsEventE"]], "tensorrt_llm::runtime::cudaevent::deleter::operator() (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent7DeleterclE7pointer"]], "tensorrt_llm::runtime::cudaevent::eventptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent8EventPtrE"]], "tensorrt_llm::runtime::cudaevent::element_type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent12element_typeE"]], "tensorrt_llm::runtime::cudaevent::get (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent3getEv"]], "tensorrt_llm::runtime::cudaevent::mevent (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent6mEventE"]], "tensorrt_llm::runtime::cudaevent::pointer (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9CudaEvent7pointerE"]], "tensorrt_llm::runtime::cudaevent::synchronize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9CudaEvent11synchronizeEv"]], "tensorrt_llm::runtime::cudastream (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStreamE"]], "tensorrt_llm::runtime::cudastream::cudastream (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_t"], [1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib"], [1, "_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamEji"]], "tensorrt_llm::runtime::cudastream::deleter (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7DeleterE"]], "tensorrt_llm::runtime::cudastream::deleter::deleter (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEb"], [1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEv"]], "tensorrt_llm::runtime::cudastream::deleter::mownsstream (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter11mOwnsStreamE"]], "tensorrt_llm::runtime::cudastream::deleter::operator() (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream7DeleterclE12cudaStream_t"]], "tensorrt_llm::runtime::cudastream::streamptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream9StreamPtrE"]], "tensorrt_llm::runtime::cudastream::get (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream3getEv"]], "tensorrt_llm::runtime::cudastream::getdevice (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream9getDeviceEv"]], "tensorrt_llm::runtime::cudastream::mdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7mDeviceE"]], "tensorrt_llm::runtime::cudastream::mstream (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10CudaStream7mStreamE"]], "tensorrt_llm::runtime::cudastream::record (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordEN9CudaEvent7pointerE"], [1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordERK9CudaEvent"]], "tensorrt_llm::runtime::cudastream::synchronize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream11synchronizeEv"]], "tensorrt_llm::runtime::cudastream::wait (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitEN9CudaEvent7pointerE"], [1, "_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitERK9CudaEvent"]], "tensorrt_llm::runtime::datatypetraits (c++ struct)": [[1, "_CPPv4I_N8nvinfer18DataTypeE_b_bEN12tensorrt_llm7runtime14DataTypeTraitsE"]], "tensorrt_llm::runtime::datatypetraits<kdatatype, kunsigned, true> (c++ struct)": [[1, "_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE"]], "tensorrt_llm::runtime::datatypetraits<kdatatype, kunsigned, true>::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4nameE"]], "tensorrt_llm::runtime::datatypetraits<kdatatype, kunsigned, true>::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4sizeE"]], "tensorrt_llm::runtime::datatypetraits<kdatatype, kunsigned, true>::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4typeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kbool, kunsigned> (c++ struct)": [[1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedEE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kbool, kunsigned>::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4nameE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kbool, kunsigned>::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4sizeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kbool, kunsigned>::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4typeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kfloat> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEEE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kfloat>::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4nameE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kfloat>::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4sizeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kfloat>::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4typeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::khalf> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEEE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::khalf>::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4nameE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::khalf>::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4sizeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::khalf>::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4typeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint32, true> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEEE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint32, true>::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4nameE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint32, true>::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4sizeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint32, true>::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4typeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint32> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EEE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint32>::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4nameE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint32>::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4sizeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint32>::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4typeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint64, true> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEEE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint64, true>::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4nameE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint64, true>::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4sizeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint64, true>::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4typeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint64> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EEE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint64>::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4nameE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint64>::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4sizeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint64>::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4typeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint8> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EEE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint8>::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4nameE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint8>::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4sizeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kint8>::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4typeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kuint8, kunsigned> (c++ struct)": [[1, "_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedEE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kuint8, kunsigned>::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4nameE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kuint8, kunsigned>::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4sizeE"]], "tensorrt_llm::runtime::datatypetraits<nvinfer1::datatype::kuint8, kunsigned>::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4typeE"]], "tensorrt_llm::runtime::decodinginput (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInputE"]], "tensorrt_llm::runtime::decodinginput::decodinginput (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13DecodingInputE10SizeType3210SizeType3210SizeType3210SizeType3214TensorConstPtr9TensorPtr14TensorConstPtr"]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputsE"]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::bestpathindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15bestPathIndicesE"]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::bestpathlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15bestPathLengthsE"]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::lastdraftindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs16lastDraftIndicesE"]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::lastdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15lastDraftTokensE"]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::lastgenerationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs21lastGenerationLengthsE"]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::lastpositionidsbase (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs19lastPositionIdsBaseE"]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::masks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs5masksE"]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::maxgenlengthdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs18maxGenLengthDeviceE"]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::nextdraftindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs16nextDraftIndicesE"]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::nextdraftprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs14nextDraftProbsE"]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::nextdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs15nextDraftTokensE"]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::nextflattokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs14nextFlatTokensE"]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::nextgenerationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs21nextGenerationLengthsE"]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::packedpositionids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs17packedPositionIdsE"]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs::seqslots (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25ExplicitDraftTokensInputs8seqSlotsE"]], "tensorrt_llm::runtime::decodinginput::lookaheadinputs (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15LookaheadInputsE"]], "tensorrt_llm::runtime::decodinginput::lookaheadinputs::tokensperstep (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15LookaheadInputs13tokensPerStepE"]], "tensorrt_llm::runtime::decodinginput::medusainputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputsE"]], "tensorrt_llm::runtime::decodinginput::medusainputs::medusacurtokensperstep (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs22medusaCurTokensPerStepE"]], "tensorrt_llm::runtime::decodinginput::medusainputs::medusalogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs12medusaLogitsE"]], "tensorrt_llm::runtime::decodinginput::medusainputs::medusapaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs11medusaPathsE"]], "tensorrt_llm::runtime::decodinginput::medusainputs::medusatargettokensperstep (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs25medusaTargetTokensPerStepE"]], "tensorrt_llm::runtime::decodinginput::medusainputs::medusatreeids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12MedusaInputs13medusaTreeIdsE"]], "tensorrt_llm::runtime::decodinginput::tensorconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput14TensorConstPtrE"]], "tensorrt_llm::runtime::decodinginput::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE"]], "tensorrt_llm::runtime::decodinginput::badwordslens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12badWordsLensE"]], "tensorrt_llm::runtime::decodinginput::badwordslists (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13badWordsListsE"]], "tensorrt_llm::runtime::decodinginput::badwordsptrs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12badWordsPtrsE"]], "tensorrt_llm::runtime::decodinginput::batchsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9batchSizeE"]], "tensorrt_llm::runtime::decodinginput::batchslots (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput10batchSlotsE"]], "tensorrt_llm::runtime::decodinginput::cacheindirection (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput16cacheIndirectionE"]], "tensorrt_llm::runtime::decodinginput::embeddingbias (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13embeddingBiasE"]], "tensorrt_llm::runtime::decodinginput::endids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput6endIdsE"]], "tensorrt_llm::runtime::decodinginput::explicitdrafttokensinputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput25explicitDraftTokensInputsE"]], "tensorrt_llm::runtime::decodinginput::finishreasons (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13finishReasonsE"]], "tensorrt_llm::runtime::decodinginput::lengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput7lengthsE"]], "tensorrt_llm::runtime::decodinginput::logits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput6logitsE"]], "tensorrt_llm::runtime::decodinginput::lookaheadinputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15lookaheadInputsE"]], "tensorrt_llm::runtime::decodinginput::maxattentionwindow (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput18maxAttentionWindowE"]], "tensorrt_llm::runtime::decodinginput::maxbadwordslen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput14maxBadWordsLenE"]], "tensorrt_llm::runtime::decodinginput::maxlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput9maxLengthE"]], "tensorrt_llm::runtime::decodinginput::maxstopwordslen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15maxStopWordsLenE"]], "tensorrt_llm::runtime::decodinginput::medusainputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput12medusaInputsE"]], "tensorrt_llm::runtime::decodinginput::norepeatngramsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput17noRepeatNgramSizeE"]], "tensorrt_llm::runtime::decodinginput::sequencelimitlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput19sequenceLimitLengthE"]], "tensorrt_llm::runtime::decodinginput::sinktokenlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput15sinkTokenLengthE"]], "tensorrt_llm::runtime::decodinginput::step (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput4stepE"]], "tensorrt_llm::runtime::decodinginput::stopwordslens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13stopWordsLensE"]], "tensorrt_llm::runtime::decodinginput::stopwordslists (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput14stopWordsListsE"]], "tensorrt_llm::runtime::decodinginput::stopwordsptrs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13DecodingInput13stopWordsPtrsE"]], "tensorrt_llm::runtime::decodingoutput (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutputE"]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypothesesE"]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::batchdones (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses10batchDonesE"]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::cumlogprobscba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses14cumLogProbsCBAE"]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::empty (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5emptyER13BufferManager"]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::init (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses4initER13BufferManager11TokenIdType"]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::logprobscba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses11logProbsCBAE"]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::minnormedscorescba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses18minNormedScoresCBAE"]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::normedscorescba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses15normedScoresCBAE"]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::numbeamscba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses11numBeamsCBAE"]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::outputidscba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses12outputIdsCBAE"]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::release (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7releaseEv"]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::reshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE10SizeType3210SizeType3210SizeType32"]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::sequencelengthscba (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses18sequenceLengthsCBAE"]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses::slice (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5sliceE10SizeType3210SizeType32"]], "tensorrt_llm::runtime::decodingoutput::decodingoutput (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14DecodingOutputE9TensorPtr9TensorPtr"]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputsE"]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::acceptedlengthscumsum (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs21acceptedLengthsCumSumE"]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::acceptedtokenslen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs17acceptedTokensLenE"]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::nextdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs15nextDraftTokensE"]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::nextdrafttokenslen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs18nextDraftTokensLenE"]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::pathsoffsets (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs12pathsOffsetsE"]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs::prevdrafttokenslen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26SpeculativeDecodingOutputs18prevDraftTokensLenE"]], "tensorrt_llm::runtime::decodingoutput::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE"]], "tensorrt_llm::runtime::decodingoutput::beamhypotheses (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14beamHypothesesE"]], "tensorrt_llm::runtime::decodingoutput::cacheindirection (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput16cacheIndirectionE"]], "tensorrt_llm::runtime::decodingoutput::cumlogprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11cumLogProbsE"]], "tensorrt_llm::runtime::decodingoutput::explicitdrafttokensbuffers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26explicitDraftTokensBuffersE"]], "tensorrt_llm::runtime::decodingoutput::finishreasons (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput13finishReasonsE"]], "tensorrt_llm::runtime::decodingoutput::finishedsum (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11finishedSumE"]], "tensorrt_llm::runtime::decodingoutput::gatheredids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput11gatheredIdsE"]], "tensorrt_llm::runtime::decodingoutput::ids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput3idsE"]], "tensorrt_llm::runtime::decodingoutput::knegativeinfinity (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput17kNegativeInfinityE"]], "tensorrt_llm::runtime::decodingoutput::lengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput7lengthsE"]], "tensorrt_llm::runtime::decodingoutput::logprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput8logProbsE"]], "tensorrt_llm::runtime::decodingoutput::lookaheadoutputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput16lookaheadOutputsE"]], "tensorrt_llm::runtime::decodingoutput::newtokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9newTokensE"]], "tensorrt_llm::runtime::decodingoutput::newtokenssteps (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput14newTokensStepsE"]], "tensorrt_llm::runtime::decodingoutput::newtokensvec (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput12newTokensVecE"]], "tensorrt_llm::runtime::decodingoutput::parentids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput9parentIdsE"]], "tensorrt_llm::runtime::decodingoutput::speculativedecodingoutputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14DecodingOutput26speculativeDecodingOutputsE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffersE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::bufferptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers9BufferPtrE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineinputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputsE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineinputs::positionoffsets (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputs15positionOffsetsE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineinputs::requesttypesdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12EngineInputs18requestTypesDeviceE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputsE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::bestpathindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15bestPathIndicesE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::bestpathlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15bestPathLengthsE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::masks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs5masksE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::maxgentoken (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs11maxGenTokenE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextdraftindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs16nextDraftIndicesE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextdraftprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs14nextDraftProbsE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs15nextDraftTokensE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextflattokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs14nextFlatTokensE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextgenerationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs21nextGenerationLengthsE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::nextpositionoffsets (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs19nextPositionOffsetsE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::packedpositionids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs17packedPositionIdsE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs::totalgentoken (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13EngineOutputs13totalGenTokenE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::explicitdrafttokensbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers26ExplicitDraftTokensBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::itensor (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7ITensorE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6InputsE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::create (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs6createE10SizeType32RKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::draftindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs12draftIndicesE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::draftprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs10draftProbsE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::drafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11draftTokensE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::generationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs17generationLengthsE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::generationlengthshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs21generationLengthsHostE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::maxgenlengthhost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs16maxGenLengthHostE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::packedmasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11packedMasksE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::positionids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs11positionIdsE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::positionidsbase (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs15positionIdsBaseE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::randomdatasample (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs16randomDataSampleE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::randomdatavalidation (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs20randomDataValidationE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::inputs::temperatures (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers6Inputs12temperaturesE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers10SizeType32E"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::tensormap (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers9TensorMapE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers9TensorPtrE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::cumsumgenerationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers23cumSumGenerationLengthsE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineinputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers12engineInputsE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::engineoutputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13engineOutputsE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::insertinputtensors (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::reshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers7reshapeE10SizeType3210SizeType32RKN7runtime11ModelConfigE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::scantempstorage (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers15scanTempStorageE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::scantempstoragebytes (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26ExplicitDraftTokensBuffers20scanTempStorageBytesE"]], "tensorrt_llm::runtime::explicitdrafttokensbuffers::setfrominputs (c++ function)": [[1, "_CPPv4I0ENK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsEv10SizeType3210SizeType3210SizeType32RK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime25ExplicitDraftTokensModuleERKN7runtime10CudaStreamE"], [1, "_CPPv4NK12tensorrt_llm7runtime26ExplicitDraftTokensBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRKN26ExplicitDraftTokensBuffers6InputsERK7ITensorRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE"]], "tensorrt_llm::runtime::generationinput (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime15GenerationInputE"]], "tensorrt_llm::runtime::generationinput::base (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime15GenerationInput4BaseE"]], "tensorrt_llm::runtime::generationinput::generationinput (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime15GenerationInput15GenerationInputEK10SizeType32K10SizeType329TensorPtr9TensorPtrb"]], "tensorrt_llm::runtime::generationinput::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime15GenerationInput9TensorPtrE"]], "tensorrt_llm::runtime::generationoutput (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime16GenerationOutputE"]], "tensorrt_llm::runtime::generationoutput::base (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime16GenerationOutput4BaseE"]], "tensorrt_llm::runtime::generationoutput::generationoutput (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime16GenerationOutput16GenerationOutputE9TensorPtr9TensorPtr"]], "tensorrt_llm::runtime::generationoutput::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime16GenerationOutput9TensorPtrE"]], "tensorrt_llm::runtime::genericgenerationinput (c++ class)": [[1, "_CPPv4I00EN12tensorrt_llm7runtime22GenericGenerationInputE"]], "tensorrt_llm::runtime::genericgenerationinput::genericgenerationinput (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput22GenericGenerationInputEK10SizeType32K10SizeType329TensorPtr9TensorPtrb"]], "tensorrt_llm::runtime::genericgenerationinput::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput9TensorPtrE"]], "tensorrt_llm::runtime::genericgenerationinput::badwordslist (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput12badWordsListE"]], "tensorrt_llm::runtime::genericgenerationinput::embeddingbias (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput13embeddingBiasE"]], "tensorrt_llm::runtime::genericgenerationinput::endid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput5endIdE"]], "tensorrt_llm::runtime::genericgenerationinput::ids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput3idsE"]], "tensorrt_llm::runtime::genericgenerationinput::lengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput7lengthsE"]], "tensorrt_llm::runtime::genericgenerationinput::maxnewtokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput12maxNewTokensE"]], "tensorrt_llm::runtime::genericgenerationinput::packed (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput6packedE"]], "tensorrt_llm::runtime::genericgenerationinput::padid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput5padIdE"]], "tensorrt_llm::runtime::genericgenerationinput::prompttuningparams (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput18promptTuningParamsE"]], "tensorrt_llm::runtime::genericgenerationinput::stopwordslist (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput13stopWordsListE"]], "tensorrt_llm::runtime::genericgenerationoutput (c++ class)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime23GenericGenerationOutputE"]], "tensorrt_llm::runtime::genericgenerationoutput::callback (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput8CallbackE"]], "tensorrt_llm::runtime::genericgenerationoutput::genericgenerationoutput (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput23GenericGenerationOutputE9TensorPtr9TensorPtr"]], "tensorrt_llm::runtime::genericgenerationoutput::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput9TensorPtrE"]], "tensorrt_llm::runtime::genericgenerationoutput::contextlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput13contextLogitsE"]], "tensorrt_llm::runtime::genericgenerationoutput::cumlogprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput11cumLogProbsE"]], "tensorrt_llm::runtime::genericgenerationoutput::generationlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput16generationLogitsE"]], "tensorrt_llm::runtime::genericgenerationoutput::ids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput3idsE"]], "tensorrt_llm::runtime::genericgenerationoutput::lengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput7lengthsE"]], "tensorrt_llm::runtime::genericgenerationoutput::logprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput8logProbsE"]], "tensorrt_llm::runtime::genericgenerationoutput::ontokengenerated (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput16onTokenGeneratedE"]], "tensorrt_llm::runtime::genericprompttuningparams (c++ class)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime25GenericPromptTuningParamsE"]], "tensorrt_llm::runtime::genericprompttuningparams::genericprompttuningparams (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr"]], "tensorrt_llm::runtime::genericprompttuningparams::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams10SizeType32E"]], "tensorrt_llm::runtime::genericprompttuningparams::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE"]], "tensorrt_llm::runtime::genericprompttuningparams::embeddingtable (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams14embeddingTableE"]], "tensorrt_llm::runtime::genericprompttuningparams::prompttuningenabled (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams19promptTuningEnabledE"]], "tensorrt_llm::runtime::genericprompttuningparams::tasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams5tasksE"]], "tensorrt_llm::runtime::genericprompttuningparams::vocabsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9vocabSizeE"]], "tensorrt_llm::runtime::gptdecoder (c++ class)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime10GptDecoderE"]], "tensorrt_llm::runtime::gptdecoder::cudastreamptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13CudaStreamPtrE"]], "tensorrt_llm::runtime::gptdecoder::gptdecoder (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderERKN8executor12DecodingModeE6size_t6size_t6size_t6size_t6size_tRK13CudaStreamPtrNSt10shared_ptrIK25SpeculativeDecodingModuleEE"]], "tensorrt_llm::runtime::gptdecoder::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder9TensorPtrE"]], "tensorrt_llm::runtime::gptdecoder::forwardasync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput"]], "tensorrt_llm::runtime::gptdecoder::forwardsync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput"]], "tensorrt_llm::runtime::gptdecoder::gathertree (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder10gatherTreeERK14DecodingOutputRK13DecodingInputRK13BufferManagerNSt8optionalINSt17reference_wrapperIK14SamplingConfigEEEE"]], "tensorrt_llm::runtime::gptdecoder::getsamplingconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder17getSamplingConfigEv"]], "tensorrt_llm::runtime::gptdecoder::mdecodinglayerworkspace (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder23mDecodingLayerWorkspaceE"]], "tensorrt_llm::runtime::gptdecoder::mdecodingmode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13mDecodingModeE"]], "tensorrt_llm::runtime::gptdecoder::mdynamicdecodelayer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder19mDynamicDecodeLayerE"]], "tensorrt_llm::runtime::gptdecoder::mlogprobstiled (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder14mLogProbsTiledE"]], "tensorrt_llm::runtime::gptdecoder::mmanager (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder8mManagerE"]], "tensorrt_llm::runtime::gptdecoder::mmaxbatchsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder13mMaxBatchSizeE"]], "tensorrt_llm::runtime::gptdecoder::msamplingconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder15mSamplingConfigE"]], "tensorrt_llm::runtime::gptdecoder::setup (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEERKNSt8optionalIKNSt6vectorIN13decoder_batch7RequestEEEEE"]], "tensorrt_llm::runtime::gptdecoderbatched (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatchedE"]], "tensorrt_llm::runtime::gptdecoderbatched::cudastreamptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13CudaStreamPtrE"]], "tensorrt_llm::runtime::gptdecoderbatched::decodinginputptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16DecodingInputPtrE"]], "tensorrt_llm::runtime::gptdecoderbatched::decodingoutputptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched17DecodingOutputPtrE"]], "tensorrt_llm::runtime::gptdecoderbatched::forwardtype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11ForwardTypeE"]], "tensorrt_llm::runtime::gptdecoderbatched::forwardtype::kasync (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11ForwardType6kASYNCE"]], "tensorrt_llm::runtime::gptdecoderbatched::forwardtype::ksync (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11ForwardType5kSYNCE"]], "tensorrt_llm::runtime::gptdecoderbatched::gptdecoderbatched (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched17GptDecoderBatchedENSt6size_tENSt6size_tE13CudaStreamPtrRK23SpeculativeDecodingModeN8nvinfer18DataTypeE"]], "tensorrt_llm::runtime::gptdecoderbatched::gptdecoderptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13GptDecoderPtrE"]], "tensorrt_llm::runtime::gptdecoderbatched::sharedconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14SharedConstPtrE"]], "tensorrt_llm::runtime::gptdecoderbatched::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched9TensorPtrE"]], "tensorrt_llm::runtime::gptdecoderbatched::allocatespeculativedecodingbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched34allocateSpeculativeDecodingBuffersEv"]], "tensorrt_llm::runtime::gptdecoderbatched::finalize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeE10SizeType32RK14SamplingConfigb"], [1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched8finalizeERK14SamplingConfig"]], "tensorrt_llm::runtime::gptdecoderbatched::forwardasync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE"], [1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12forwardAsyncERN7decoder6OutputERKN7decoder5InputE"]], "tensorrt_llm::runtime::gptdecoderbatched::forwarddecoder (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14forwardDecoderE10SizeType32RN13decoder_batch6OutputERKN13decoder_batch5InputE11ForwardType"]], "tensorrt_llm::runtime::gptdecoderbatched::forwarddispatch (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15forwardDispatchERN13decoder_batch6OutputERKN13decoder_batch5InputE11ForwardType"]], "tensorrt_llm::runtime::gptdecoderbatched::forwardsync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11forwardSyncERKN13decoder_batch5TokenE"], [1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11forwardSyncERKN13decoder_batch5TokenERN13decoder_batch6OutputERKN13decoder_batch5InputE"], [1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11forwardSyncEv"]], "tensorrt_llm::runtime::gptdecoderbatched::getacceptedlengthscumsum (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched24getAcceptedLengthsCumSumEv"]], "tensorrt_llm::runtime::gptdecoderbatched::getacceptedpackedpaths (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched22getAcceptedPackedPathsEv"]], "tensorrt_llm::runtime::gptdecoderbatched::getallnewtokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched15getAllNewTokensEv"]], "tensorrt_llm::runtime::gptdecoderbatched::getcumlogprobs (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched14getCumLogProbsE10SizeType32"], [1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched14getCumLogProbsEv"]], "tensorrt_llm::runtime::gptdecoderbatched::getdecodingmode (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched15getDecodingModeEv"]], "tensorrt_llm::runtime::gptdecoderbatched::getfinishreasons (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched16getFinishReasonsEv"]], "tensorrt_llm::runtime::gptdecoderbatched::getfinished (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched11getFinishedEv"]], "tensorrt_llm::runtime::gptdecoderbatched::getgatheredids (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched14getGatheredIdsE10SizeType32"], [1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched14getGatheredIdsEv"]], "tensorrt_llm::runtime::gptdecoderbatched::getids (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched6getIdsE10SizeType32"], [1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched6getIdsEv"]], "tensorrt_llm::runtime::gptdecoderbatched::getlogprobs (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched11getLogProbsE10SizeType32"], [1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched11getLogProbsEv"]], "tensorrt_llm::runtime::gptdecoderbatched::getnbfinished (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched13getNbFinishedEv"]], "tensorrt_llm::runtime::gptdecoderbatched::getnbsteps (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched10getNbStepsEv"]], "tensorrt_llm::runtime::gptdecoderbatched::getnewtokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched12getNewTokensE10SizeType32"]], "tensorrt_llm::runtime::gptdecoderbatched::getnextdrafttokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched18getNextDraftTokensEv"]], "tensorrt_llm::runtime::gptdecoderbatched::getnextdrafttokenslengths (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched25getNextDraftTokensLengthsEv"]], "tensorrt_llm::runtime::gptdecoderbatched::getparentids (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched12getParentIdsEv"]], "tensorrt_llm::runtime::gptdecoderbatched::getprevdrafttokenslengths (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched25getPrevDraftTokensLengthsEv"]], "tensorrt_llm::runtime::gptdecoderbatched::macceptbylogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15mAcceptByLogitsE"]], "tensorrt_llm::runtime::gptdecoderbatched::mactualbatchsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16mActualBatchSizeE"]], "tensorrt_llm::runtime::gptdecoderbatched::mbatchslotsacceptlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched23mBatchSlotsAcceptLogitsE"]], "tensorrt_llm::runtime::gptdecoderbatched::mbatchslotsaccepttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched23mBatchSlotsAcceptTokensE"]], "tensorrt_llm::runtime::gptdecoderbatched::mbatchslotsdecoder (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched18mBatchSlotsDecoderE"]], "tensorrt_llm::runtime::gptdecoderbatched::mbatchslotssetup (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16mBatchSlotsSetupE"]], "tensorrt_llm::runtime::gptdecoderbatched::mbeamwidths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11mBeamWidthsE"]], "tensorrt_llm::runtime::gptdecoderbatched::mbuffermanager (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mBufferManagerE"]], "tensorrt_llm::runtime::gptdecoderbatched::mcumlogprobstmp (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15mCumLogProbsTmpE"]], "tensorrt_llm::runtime::gptdecoderbatched::mcurandstates (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13mCurandStatesE"]], "tensorrt_llm::runtime::gptdecoderbatched::mdecoder (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched8mDecoderE"]], "tensorrt_llm::runtime::gptdecoderbatched::mdecoderstream (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mDecoderStreamE"]], "tensorrt_llm::runtime::gptdecoderbatched::mdecodingmode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13mDecodingModeE"]], "tensorrt_llm::runtime::gptdecoderbatched::mdraftlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12mDraftLogitsE"]], "tensorrt_llm::runtime::gptdecoderbatched::mdraftprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11mDraftProbsE"]], "tensorrt_llm::runtime::gptdecoderbatched::mdrafttokenids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mDraftTokenIdsE"]], "tensorrt_llm::runtime::gptdecoderbatched::mfinished (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched9mFinishedE"]], "tensorrt_llm::runtime::gptdecoderbatched::mfinishedsteps (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mFinishedStepsE"]], "tensorrt_llm::runtime::gptdecoderbatched::mfinishedsum (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12mFinishedSumE"]], "tensorrt_llm::runtime::gptdecoderbatched::mforwardevent (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13mForwardEventE"]], "tensorrt_llm::runtime::gptdecoderbatched::mforwardtoken (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13mForwardTokenE"]], "tensorrt_llm::runtime::gptdecoderbatched::mjointdecodinginput (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched19mJointDecodingInputE"]], "tensorrt_llm::runtime::gptdecoderbatched::mjointdecodingoutput (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched20mJointDecodingOutputE"]], "tensorrt_llm::runtime::gptdecoderbatched::mmaxattentionwindow (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched19mMaxAttentionWindowE"]], "tensorrt_llm::runtime::gptdecoderbatched::mmaxdecodingdecodertokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched25mMaxDecodingDecoderTokensE"]], "tensorrt_llm::runtime::gptdecoderbatched::mmaxdecodingenginetokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched24mMaxDecodingEngineTokensE"]], "tensorrt_llm::runtime::gptdecoderbatched::mmaxnewtokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched13mMaxNewTokensE"]], "tensorrt_llm::runtime::gptdecoderbatched::mmaxsequencelength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched18mMaxSequenceLengthE"]], "tensorrt_llm::runtime::gptdecoderbatched::mnbsteps (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched8mNbStepsE"]], "tensorrt_llm::runtime::gptdecoderbatched::mnumdecodingenginetokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched24mNumDecodingEngineTokensE"]], "tensorrt_llm::runtime::gptdecoderbatched::mnumdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched15mNumDraftTokensE"]], "tensorrt_llm::runtime::gptdecoderbatched::mnumsms (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched7mNumSMsE"]], "tensorrt_llm::runtime::gptdecoderbatched::moutputbeamhypotheses (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched21mOutputBeamHypothesesE"]], "tensorrt_llm::runtime::gptdecoderbatched::mruntimestream (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14mRuntimeStreamE"]], "tensorrt_llm::runtime::gptdecoderbatched::msinktokenlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16mSinkTokenLengthE"]], "tensorrt_llm::runtime::gptdecoderbatched::mspeculativedecodingmode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched24mSpeculativeDecodingModeE"]], "tensorrt_llm::runtime::gptdecoderbatched::mtargetlogitsptrs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched17mTargetLogitsPtrsE"]], "tensorrt_llm::runtime::gptdecoderbatched::mtargetprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched12mTargetProbsE"]], "tensorrt_llm::runtime::gptdecoderbatched::mvocabsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched10mVocabSizeE"]], "tensorrt_llm::runtime::gptdecoderbatched::mvocabsizepadded (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16mVocabSizePaddedE"]], "tensorrt_llm::runtime::gptdecoderbatched::newbatch (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig"]], "tensorrt_llm::runtime::gptdecoderbatched::newrequest (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched10newRequestE10SizeType32RKN13decoder_batch7RequestERK14SamplingConfig"]], "tensorrt_llm::runtime::gptdecoderbatched::newrequestdrafttokensexternal (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched29newRequestDraftTokensExternalE10SizeType32RKN13decoder_batch7RequestERK14SamplingConfig"]], "tensorrt_llm::runtime::gptdecoderbatched::newrequestexplicitdrafttokens (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched29newRequestExplicitDraftTokensE10SizeType32RKN13decoder_batch7RequestE"]], "tensorrt_llm::runtime::gptdecoderbatched::newrequestlookahead (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched19newRequestLookaheadE10SizeType32RKN13decoder_batch7RequestE"]], "tensorrt_llm::runtime::gptdecoderbatched::newrequestmedusa (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched16newRequestMedusaE10SizeType32RKN13decoder_batch7RequestE"]], "tensorrt_llm::runtime::gptdecoderbatched::newrequestspeculativedecoding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched29newRequestSpeculativeDecodingE10SizeType32RKN13decoder_batch7RequestERK14SamplingConfig"]], "tensorrt_llm::runtime::gptdecoderbatched::newrequests (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched11newRequestsERKNSt6vectorI10SizeType32EERKNSt6vectorIN13decoder_batch7RequestEEERKNSt6vectorI14SamplingConfigEE"]], "tensorrt_llm::runtime::gptdecoderbatched::postprocessrequest (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime17GptDecoderBatched18postProcessRequestE10SizeType32RK14SamplingConfigb"]], "tensorrt_llm::runtime::gptdecoderbatched::setexplicitdrafttokensinputs (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched28setExplicitDraftTokensInputsERKN13decoder_batch5InputE"]], "tensorrt_llm::runtime::gptdecoderbatched::setup (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig"]], "tensorrt_llm::runtime::gptdecoderbatched::setupexplicitdrafttokens (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched24setupExplicitDraftTokensEN26ExplicitDraftTokensBuffers6InputsE"]], "tensorrt_llm::runtime::gptdecoderbatched::setuplookahead (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14setupLookaheadE24LookaheadDecodingBuffers"], [1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14setupLookaheadERK11ModelConfig"]], "tensorrt_llm::runtime::gptdecoderbatched::setupspeculativedecoding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched24setupSpeculativeDecodingERK11ModelConfig"]], "tensorrt_llm::runtime::gptdecoderbatched::updatefinished (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime17GptDecoderBatched14updateFinishedERKN13decoder_batch5TokenE"]], "tensorrt_llm::runtime::gptjsonconfig (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfigE"]], "tensorrt_llm::runtime::gptjsonconfig::gptjsonconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE10SizeType3210SizeType3210SizeType3211ModelConfig"]], "tensorrt_llm::runtime::gptjsonconfig::enginefilename (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfig"], [1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfigRKNSt6stringE"]], "tensorrt_llm::runtime::gptjsonconfig::getgpuspernode (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14getGpusPerNodeEv"]], "tensorrt_llm::runtime::gptjsonconfig::getmodelconfig (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14getModelConfigEv"]], "tensorrt_llm::runtime::gptjsonconfig::getmodelconfigmutable (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig21getModelConfigMutableEv"]], "tensorrt_llm::runtime::gptjsonconfig::getname (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig7getNameEv"]], "tensorrt_llm::runtime::gptjsonconfig::getpipelineparallelism (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig22getPipelineParallelismEv"]], "tensorrt_llm::runtime::gptjsonconfig::getprecision (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getPrecisionEv"]], "tensorrt_llm::runtime::gptjsonconfig::gettensorparallelism (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig20getTensorParallelismEv"]], "tensorrt_llm::runtime::gptjsonconfig::getversion (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig10getVersionEv"]], "tensorrt_llm::runtime::gptjsonconfig::getworldsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getWorldSizeEv"]], "tensorrt_llm::runtime::gptjsonconfig::mgpuspernode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig12mGpusPerNodeE"]], "tensorrt_llm::runtime::gptjsonconfig::mmodelconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig12mModelConfigE"]], "tensorrt_llm::runtime::gptjsonconfig::mname (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5mNameE"]], "tensorrt_llm::runtime::gptjsonconfig::mpipelineparallelism (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig20mPipelineParallelismE"]], "tensorrt_llm::runtime::gptjsonconfig::mprecision (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig10mPrecisionE"]], "tensorrt_llm::runtime::gptjsonconfig::mtensorparallelism (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig18mTensorParallelismE"]], "tensorrt_llm::runtime::gptjsonconfig::mversion (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig8mVersionE"]], "tensorrt_llm::runtime::gptjsonconfig::parse (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt10filesystem4pathE"], [1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt6stringE"], [1, "_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERNSt7istreamE"]], "tensorrt_llm::runtime::gptsession (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSessionE"]], "tensorrt_llm::runtime::gptsession::config (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession6ConfigE"]], "tensorrt_llm::runtime::gptsession::config::config (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config6ConfigE10SizeType3210SizeType3210SizeType32f"]], "tensorrt_llm::runtime::gptsession::config::ctxmicrobatchsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config17ctxMicroBatchSizeE"]], "tensorrt_llm::runtime::gptsession::config::cudagraphmode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config13cudaGraphModeE"]], "tensorrt_llm::runtime::gptsession::config::decoderperrequest (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config17decoderPerRequestE"]], "tensorrt_llm::runtime::gptsession::config::decodingmode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config12decodingModeE"]], "tensorrt_llm::runtime::gptsession::config::enginepath (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config10enginePathE"]], "tensorrt_llm::runtime::gptsession::config::genmicrobatchsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config17genMicroBatchSizeE"]], "tensorrt_llm::runtime::gptsession::config::gpuweightspercent (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config17gpuWeightsPercentE"]], "tensorrt_llm::runtime::gptsession::config::kvcacheconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config13kvCacheConfigE"]], "tensorrt_llm::runtime::gptsession::config::maxbatchsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config12maxBatchSizeE"]], "tensorrt_llm::runtime::gptsession::config::maxbeamwidth (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config12maxBeamWidthE"]], "tensorrt_llm::runtime::gptsession::config::maxsequencelength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config17maxSequenceLengthE"]], "tensorrt_llm::runtime::gptsession::config::normalizelogprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession6Config17normalizeLogProbsE"]], "tensorrt_llm::runtime::gptsession::cudagraphexecutor (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutorE"]], "tensorrt_llm::runtime::gptsession::cudagraphexecutor::cudagraphexecutor (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor17CudaGraphExecutorEv"]], "tensorrt_llm::runtime::gptsession::cudagraphexecutor::clear (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor5clearEv"]], "tensorrt_llm::runtime::gptsession::cudagraphexecutor::create (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6createERK11cudaGraph_t"]], "tensorrt_llm::runtime::gptsession::cudagraphexecutor::hasinstance (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor11hasInstanceEv"]], "tensorrt_llm::runtime::gptsession::cudagraphexecutor::launch (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6launchERK10CudaStream"]], "tensorrt_llm::runtime::gptsession::cudagraphexecutor::minstance (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor9mInstanceE"]], "tensorrt_llm::runtime::gptsession::cudagraphexecutor::preparenextgraph (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor16prepareNextGraphERK11TllmRuntime10SizeType32"]], "tensorrt_llm::runtime::gptsession::cudagraphexecutor::update (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6updateERK11cudaGraph_t"]], "tensorrt_llm::runtime::gptsession::cudagraphexecutor::uploadtostream (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor14uploadToStreamERK10CudaStream"]], "tensorrt_llm::runtime::gptsession::cudagraphexecutor::~cudagraphexecutor (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutorD0Ev"]], "tensorrt_llm::runtime::gptsession::generationprofiler (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession18GenerationProfilerE"]], "tensorrt_llm::runtime::gptsession::generationprofiler::generationprofiler (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession18GenerationProfiler18GenerationProfilerEv"]], "tensorrt_llm::runtime::gptsession::generationprofiler::end (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession18GenerationProfiler3endE"]], "tensorrt_llm::runtime::gptsession::generationprofiler::flags (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession18GenerationProfiler5flagsE"]], "tensorrt_llm::runtime::gptsession::generationprofiler::getelapsedtimems (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession18GenerationProfiler16getElapsedTimeMsEv"]], "tensorrt_llm::runtime::gptsession::generationprofiler::getend (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10GptSession18GenerationProfiler6getEndEv"]], "tensorrt_llm::runtime::gptsession::generationprofiler::getstart (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10GptSession18GenerationProfiler8getStartEv"]], "tensorrt_llm::runtime::gptsession::generationprofiler::start (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession18GenerationProfiler5startE"]], "tensorrt_llm::runtime::gptsession::gptsession (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigPKvNSt6size_tE9LoggerPtr"], [1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRK9RawEngine9LoggerPtr"], [1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRKNSt6stringE9LoggerPtr"], [1, "_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK11ModelConfigRK11WorldConfigRKNSt6vectorI7uint8_tEE9LoggerPtr"]], "tensorrt_llm::runtime::gptsession::kvcacheconfig (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession13KvCacheConfigE"]], "tensorrt_llm::runtime::gptsession::kvcachemanager (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession14KvCacheManagerE"]], "tensorrt_llm::runtime::gptsession::loggerptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession9LoggerPtrE"]], "tensorrt_llm::runtime::gptsession::microbatchconfig (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfigE"]], "tensorrt_llm::runtime::gptsession::microbatchconfig::microbatchconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig16MicroBatchConfigE10SizeType3210SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE"], [1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig16MicroBatchConfigEv"]], "tensorrt_llm::runtime::gptsession::microbatchconfig::ctxbatchsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig12ctxBatchSizeE"]], "tensorrt_llm::runtime::gptsession::microbatchconfig::genbatchsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig12genBatchSizeE"]], "tensorrt_llm::runtime::gptsession::microbatchconfig::getgengraphid (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig13getGenGraphIdE10SizeType3210SizeType32"]], "tensorrt_llm::runtime::gptsession::microbatchconfig::numctxbatches (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig13numCtxBatchesE"]], "tensorrt_llm::runtime::gptsession::microbatchconfig::numctxpergen (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig12numCtxPerGenEv"]], "tensorrt_llm::runtime::gptsession::microbatchconfig::numgenbatches (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig13numGenBatchesE"]], "tensorrt_llm::runtime::gptsession::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession9TensorPtrE"]], "tensorrt_llm::runtime::gptsession::tokengeneratedcallback (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession22TokenGeneratedCallbackE"]], "tensorrt_llm::runtime::gptsession::createbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession13createBuffersE10SizeType32"]], "tensorrt_llm::runtime::gptsession::createcontexts (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession14createContextsEv"]], "tensorrt_llm::runtime::gptsession::createcustomallreduceworkspace (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession30createCustomAllReduceWorkspaceE10SizeType3210SizeType3210SizeType32"]], "tensorrt_llm::runtime::gptsession::createdecoders (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession14createDecodersE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeEb10SizeType32RKN8executor12DecodingModeE"]], "tensorrt_llm::runtime::gptsession::createkvcachemanager (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession20createKvCacheManagerE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32RK13KvCacheConfig"]], "tensorrt_llm::runtime::gptsession::createontokengeneratedcallback (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession30createOnTokenGeneratedCallbackER16GenerationOutput"]], "tensorrt_llm::runtime::gptsession::decoderstepasync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession16decoderStepAsyncE10SizeType3210SizeType32"]], "tensorrt_llm::runtime::gptsession::executecontextstep (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession18executeContextStepERKNSt6vectorI15GenerationInputEERKNSt6vectorI10SizeType32EEPK14KvCacheManager"]], "tensorrt_llm::runtime::gptsession::executegenerationstep (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession21executeGenerationStepE10SizeType32RKNSt6vectorI15GenerationInputEERNSt6vectorI16GenerationOutputEERKNSt6vectorI10SizeType32EEP14KvCacheManagerRNSt6vectorIbEE"]], "tensorrt_llm::runtime::gptsession::finalize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession8finalizeE10SizeType32RK14SamplingConfig"]], "tensorrt_llm::runtime::gptsession::generate (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession8generateER16GenerationOutputRK15GenerationInputRK14SamplingConfigKNSt10shared_ptrI18GenerationProfilerEE"]], "tensorrt_llm::runtime::gptsession::generatebatched (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession15generateBatchedERNSt6vectorI16GenerationOutputEERKNSt6vectorI15GenerationInputEERK14SamplingConfigRK22TokenGeneratedCallbackKNSt10shared_ptrI18GenerationProfilerEE"]], "tensorrt_llm::runtime::gptsession::getbuffermanager (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10GptSession16getBufferManagerEv"]], "tensorrt_llm::runtime::gptsession::getdevice (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10GptSession9getDeviceEv"]], "tensorrt_llm::runtime::gptsession::getengineinspector (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10GptSession18getEngineInspectorEv"]], "tensorrt_llm::runtime::gptsession::getlayerprofileinfo (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10GptSession19getLayerProfileInfoEv"]], "tensorrt_llm::runtime::gptsession::getlogger (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10GptSession9getLoggerEv"]], "tensorrt_llm::runtime::gptsession::getlogitdatatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10GptSession16getLogitDataTypeEv"]], "tensorrt_llm::runtime::gptsession::getmodelconfig (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10GptSession14getModelConfigEv"]], "tensorrt_llm::runtime::gptsession::getnormalizelogprobs (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10GptSession20getNormalizeLogProbsEv"]], "tensorrt_llm::runtime::gptsession::getruntimestreamptr (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10GptSession19getRuntimeStreamPtrEv"]], "tensorrt_llm::runtime::gptsession::getworldconfig (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10GptSession14getWorldConfigEv"]], "tensorrt_llm::runtime::gptsession::initdecoder (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10GptSession11initDecoderER7ITensorRK15GenerationInputRK16GenerationOutputRK14SamplingConfig10SizeType32"]], "tensorrt_llm::runtime::gptsession::kvcacheaddsequences (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession19kvCacheAddSequencesE10SizeType3210SizeType3210SizeType32"]], "tensorrt_llm::runtime::gptsession::mallreducebuffers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession17mAllReduceBuffersE"]], "tensorrt_llm::runtime::gptsession::mbuffers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession8mBuffersE"]], "tensorrt_llm::runtime::gptsession::mcommevent (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession10mCommEventE"]], "tensorrt_llm::runtime::gptsession::mcommstream (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession11mCommStreamE"]], "tensorrt_llm::runtime::gptsession::mcudagraphinstances (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession19mCudaGraphInstancesE"]], "tensorrt_llm::runtime::gptsession::mcudagraphmode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession14mCudaGraphModeE"]], "tensorrt_llm::runtime::gptsession::mdecodermaxattentionwindow (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession26mDecoderMaxAttentionWindowE"]], "tensorrt_llm::runtime::gptsession::mdecodermaxattentionwindowvec (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession29mDecoderMaxAttentionWindowVecE"]], "tensorrt_llm::runtime::gptsession::mdecodermaxsequencelength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession25mDecoderMaxSequenceLengthE"]], "tensorrt_llm::runtime::gptsession::mdecodersinktokenlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession23mDecoderSinkTokenLengthE"]], "tensorrt_llm::runtime::gptsession::mdecoders (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession9mDecodersE"]], "tensorrt_llm::runtime::gptsession::mdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession7mDeviceE"]], "tensorrt_llm::runtime::gptsession::mkvcachemanager (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession15mKvCacheManagerE"]], "tensorrt_llm::runtime::gptsession::mlogger (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession7mLoggerE"]], "tensorrt_llm::runtime::gptsession::mmicrobatchconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession17mMicroBatchConfigE"]], "tensorrt_llm::runtime::gptsession::mmodelconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession12mModelConfigE"]], "tensorrt_llm::runtime::gptsession::mnormalizelogprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession18mNormalizeLogProbsE"]], "tensorrt_llm::runtime::gptsession::mpipelinecomm (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession13mPipelineCommE"]], "tensorrt_llm::runtime::gptsession::mreceivedevents (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession15mReceivedEventsE"]], "tensorrt_llm::runtime::gptsession::mruntime (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession8mRuntimeE"]], "tensorrt_llm::runtime::gptsession::mworldconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession12mWorldConfigE"]], "tensorrt_llm::runtime::gptsession::setlayerprofiler (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession16setLayerProfilerEv"]], "tensorrt_llm::runtime::gptsession::setup (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession5setupERK6Config"]], "tensorrt_llm::runtime::gptsession::shouldstopsync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession14shouldStopSyncE10SizeType3210SizeType3210SizeType32"]], "tensorrt_llm::runtime::gptsession::shouldusekvcachemanager (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10GptSession23shouldUseKVCacheManagerEv"]], "tensorrt_llm::runtime::gptsession::usecudagraphs (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10GptSession13useCudaGraphsEv"]], "tensorrt_llm::runtime::ibuffer (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBufferE"]], "tensorrt_llm::runtime::ibuffer::datatype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer8DataTypeE"]], "tensorrt_llm::runtime::ibuffer::ibuffer (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferERK7IBuffer"], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferEv"]], "tensorrt_llm::runtime::ibuffer::sharedconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer14SharedConstPtrE"]], "tensorrt_llm::runtime::ibuffer::sharedptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer9SharedPtrE"]], "tensorrt_llm::runtime::ibuffer::uniqueconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer14UniqueConstPtrE"]], "tensorrt_llm::runtime::ibuffer::uniqueptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE"]], "tensorrt_llm::runtime::ibuffer::data (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE"], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4dataEv"], [1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE"], [1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataEv"]], "tensorrt_llm::runtime::ibuffer::getcapacity (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer11getCapacityEv"]], "tensorrt_llm::runtime::ibuffer::getdatatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer11getDataTypeEv"]], "tensorrt_llm::runtime::ibuffer::getdatatypename (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer15getDataTypeNameEv"]], "tensorrt_llm::runtime::ibuffer::getmemorytype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer13getMemoryTypeEv"]], "tensorrt_llm::runtime::ibuffer::getmemorytypename (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer17getMemoryTypeNameEv"]], "tensorrt_llm::runtime::ibuffer::getsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer7getSizeEv"]], "tensorrt_llm::runtime::ibuffer::getsizeinbytes (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer14getSizeInBytesEv"]], "tensorrt_llm::runtime::ibuffer::memorytype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer10memoryTypeEPKv"]], "tensorrt_llm::runtime::ibuffer::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBufferaSERK7IBuffer"]], "tensorrt_llm::runtime::ibuffer::release (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer7releaseEv"]], "tensorrt_llm::runtime::ibuffer::resize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBuffer6resizeENSt6size_tE"]], "tensorrt_llm::runtime::ibuffer::slice (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE"], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE"], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tE"], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE"]], "tensorrt_llm::runtime::ibuffer::tobytes (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7IBuffer7toBytesENSt6size_tE"]], "tensorrt_llm::runtime::ibuffer::view (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE"], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtr"], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtrNSt6size_tE"]], "tensorrt_llm::runtime::ibuffer::wrap (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE"], [1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE"], [1, "_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrRNSt6vectorI1TEE"], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE"], [1, "_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE"]], "tensorrt_llm::runtime::ibuffer::~ibuffer (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7IBufferD0Ev"]], "tensorrt_llm::runtime::igptdecoder (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoderE"]], "tensorrt_llm::runtime::igptdecoder::tensorconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder14TensorConstPtrE"]], "tensorrt_llm::runtime::igptdecoder::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder9TensorPtrE"]], "tensorrt_llm::runtime::igptdecoder::acceptdrafttokensbyids (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder22acceptDraftTokensByIdsERK7ITensorRK7ITensorRK7ITensorRK7ITensorR7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorRKN13BufferManager13CudaStreamPtrE"]], "tensorrt_llm::runtime::igptdecoder::acceptdrafttokensbylogits (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensorRK7ITensor10SizeType3210SizeType32bfP13curandState_tRKN13BufferManager13CudaStreamPtrE"]], "tensorrt_llm::runtime::igptdecoder::create (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createERKN8executor12DecodingModeEN8nvinfer18DataTypeE6size_t6size_t6size_t6size_t6size_tRKN13BufferManager13CudaStreamPtrENSt10shared_ptrIK25SpeculativeDecodingModuleEE"]], "tensorrt_llm::runtime::igptdecoder::forwardasync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput"]], "tensorrt_llm::runtime::igptdecoder::forwardsync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder11forwardSyncER14DecodingOutputRK13DecodingInput"]], "tensorrt_llm::runtime::igptdecoder::gathertree (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder10gatherTreeERK14DecodingOutputRK13DecodingInputRK13BufferManagerNSt8optionalINSt17reference_wrapperIK14SamplingConfigEEEE"]], "tensorrt_llm::runtime::igptdecoder::getsamplingconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder17getSamplingConfigEv"]], "tensorrt_llm::runtime::igptdecoder::setup (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_tRK14TensorConstPtrRKNSt8optionalI14DecodingOutputEERKNSt8optionalIKNSt6vectorIN13decoder_batch7RequestEEEEE"]], "tensorrt_llm::runtime::igptdecoder::~igptdecoder (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11IGptDecoderD0Ev"]], "tensorrt_llm::runtime::igptdecoderbatched (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatchedE"]], "tensorrt_llm::runtime::igptdecoderbatched::cudastreamptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched13CudaStreamPtrE"]], "tensorrt_llm::runtime::igptdecoderbatched::igptdecoderbatched (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched18IGptDecoderBatchedEv"]], "tensorrt_llm::runtime::igptdecoderbatched::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched9TensorPtrE"]], "tensorrt_llm::runtime::igptdecoderbatched::tokenptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched8TokenPtrE"]], "tensorrt_llm::runtime::igptdecoderbatched::finalize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched8finalizeE10SizeType32RK14SamplingConfigb"]], "tensorrt_llm::runtime::igptdecoderbatched::forward (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched7forwardERN13decoder_batch6OutputERKN13decoder_batch5InputE"]], "tensorrt_llm::runtime::igptdecoderbatched::forwardasync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE"]], "tensorrt_llm::runtime::igptdecoderbatched::forwardsync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched11forwardSyncERKN13decoder_batch5TokenE"], [1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched11forwardSyncERKN13decoder_batch5TokenERN13decoder_batch6OutputERKN13decoder_batch5InputE"]], "tensorrt_llm::runtime::igptdecoderbatched::getacceptedlengthscumsum (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched24getAcceptedLengthsCumSumEv"]], "tensorrt_llm::runtime::igptdecoderbatched::getacceptedpackedpaths (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched22getAcceptedPackedPathsEv"]], "tensorrt_llm::runtime::igptdecoderbatched::getcumlogprobs (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched14getCumLogProbsE10SizeType32"], [1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched14getCumLogProbsEv"]], "tensorrt_llm::runtime::igptdecoderbatched::getdecodingmode (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched15getDecodingModeEv"]], "tensorrt_llm::runtime::igptdecoderbatched::getfinishreasons (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched16getFinishReasonsEv"]], "tensorrt_llm::runtime::igptdecoderbatched::getfinished (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched11getFinishedEv"]], "tensorrt_llm::runtime::igptdecoderbatched::getgatheredids (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched14getGatheredIdsE10SizeType32"]], "tensorrt_llm::runtime::igptdecoderbatched::getids (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched6getIdsE10SizeType32"]], "tensorrt_llm::runtime::igptdecoderbatched::getlogprobs (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched11getLogProbsE10SizeType32"], [1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched11getLogProbsEv"]], "tensorrt_llm::runtime::igptdecoderbatched::getnbsteps (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched10getNbStepsEv"]], "tensorrt_llm::runtime::igptdecoderbatched::getnextdrafttokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched18getNextDraftTokensEv"]], "tensorrt_llm::runtime::igptdecoderbatched::getnextdrafttokenslengths (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched25getNextDraftTokensLengthsEv"]], "tensorrt_llm::runtime::igptdecoderbatched::getparentids (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched12getParentIdsEv"]], "tensorrt_llm::runtime::igptdecoderbatched::getprevdrafttokenslengths (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime18IGptDecoderBatched25getPrevDraftTokensLengthsEv"]], "tensorrt_llm::runtime::igptdecoderbatched::newrequests (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched11newRequestsERKNSt6vectorI10SizeType32EERKNSt6vectorIN13decoder_batch7RequestEEERKNSt6vectorI14SamplingConfigEE"]], "tensorrt_llm::runtime::igptdecoderbatched::setupexplicitdrafttokens (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched24setupExplicitDraftTokensEN26ExplicitDraftTokensBuffers6InputsE"]], "tensorrt_llm::runtime::igptdecoderbatched::setuplookahead (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18IGptDecoderBatched14setupLookaheadE24LookaheadDecodingBuffers"]], "tensorrt_llm::runtime::istatefulgptdecoder (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoderE"]], "tensorrt_llm::runtime::istatefulgptdecoder::cudastreamptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder13CudaStreamPtrE"]], "tensorrt_llm::runtime::istatefulgptdecoder::istatefulgptdecoder (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder19IStatefulGptDecoderEv"]], "tensorrt_llm::runtime::istatefulgptdecoder::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder9TensorPtrE"]], "tensorrt_llm::runtime::istatefulgptdecoder::finalize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder8finalizeERK14SamplingConfig"]], "tensorrt_llm::runtime::istatefulgptdecoder::forward (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder7forwardERN7decoder6OutputERKN7decoder5InputE"]], "tensorrt_llm::runtime::istatefulgptdecoder::forwardasync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder12forwardAsyncERN7decoder6OutputERKN7decoder5InputE"]], "tensorrt_llm::runtime::istatefulgptdecoder::forwardsync (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder11forwardSyncEv"]], "tensorrt_llm::runtime::istatefulgptdecoder::getallnewtokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder15getAllNewTokensEv"]], "tensorrt_llm::runtime::istatefulgptdecoder::getcumlogprobs (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder14getCumLogProbsEv"]], "tensorrt_llm::runtime::istatefulgptdecoder::getgatheredids (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder14getGatheredIdsEv"]], "tensorrt_llm::runtime::istatefulgptdecoder::getids (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder6getIdsEv"]], "tensorrt_llm::runtime::istatefulgptdecoder::getlogprobs (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder11getLogProbsEv"]], "tensorrt_llm::runtime::istatefulgptdecoder::getnbfinished (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder13getNbFinishedEv"]], "tensorrt_llm::runtime::istatefulgptdecoder::getnewtokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder12getNewTokensE10SizeType32"]], "tensorrt_llm::runtime::istatefulgptdecoder::newbatch (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig"]], "tensorrt_llm::runtime::istatefulgptdecoder::setup (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder5setupERKN8executor12DecodingModeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeERK11ModelConfig"]], "tensorrt_llm::runtime::istatefulgptdecoder::~istatefulgptdecoder (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoderD0Ev"]], "tensorrt_llm::runtime::itensor (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensorE"]], "tensorrt_llm::runtime::itensor::dimtype64 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9DimType64E"]], "tensorrt_llm::runtime::itensor::itensor (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorERK7ITensor"], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorEv"]], "tensorrt_llm::runtime::itensor::shape (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE"]], "tensorrt_llm::runtime::itensor::sharedconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor14SharedConstPtrE"]], "tensorrt_llm::runtime::itensor::sharedptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE"]], "tensorrt_llm::runtime::itensor::tensormap (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9TensorMapE"]], "tensorrt_llm::runtime::itensor::uniqueconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor14UniqueConstPtrE"]], "tensorrt_llm::runtime::itensor::uniqueptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE"]], "tensorrt_llm::runtime::itensor::at (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atE14UniqueConstPtrRR9TConstPtrRK5Shape"], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor2atEN7ITensor14UniqueConstPtrERR9TConstPtrRKNSt16initializer_listI9DimType64EE"], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRK5Shape"], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor2atE9SharedPtrRKNSt16initializer_listI9DimType64EE"]], "tensorrt_llm::runtime::itensor::castsize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor8castSizeE6size_t"]], "tensorrt_llm::runtime::itensor::flattenn (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor8flattenNE9SharedPtrNSt7int64_tE"]], "tensorrt_llm::runtime::itensor::getdimension (c++ function)": [[1, "_CPPv4I_10SizeType32ENK12tensorrt_llm7runtime7ITensor12getDimensionE9DimType64v"]], "tensorrt_llm::runtime::itensor::getshape (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime7ITensor8getShapeEv"]], "tensorrt_llm::runtime::itensor::makeshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9makeShapeERKNSt16initializer_listI9DimType64EE"]], "tensorrt_llm::runtime::itensor::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensoraSERK7ITensor"]], "tensorrt_llm::runtime::itensor::reshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor7reshapeERK5Shape"]], "tensorrt_llm::runtime::itensor::resize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor6resizeENSt6size_tE"]], "tensorrt_llm::runtime::itensor::shapeequals (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T10SizeType32"], [1, "_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T10SizeType32"], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapeRK5Shape"], [1, "_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERK5Shape"], [1, "_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERKNSt16initializer_listI10SizeType32EE"]], "tensorrt_llm::runtime::itensor::slice (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE"], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE"], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5Shape"], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRK5ShapeNSt6size_tE"], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EE"], [1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrRKNSt16initializer_listI9DimType64EENSt6size_tE"], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tE"], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE"], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape"], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRK5Shape9DimType64"], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE"], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrRKNSt16initializer_listI9DimType64EE9DimType64"]], "tensorrt_llm::runtime::itensor::squeeze (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeE10SizeType32"], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeERK5Shape10SizeType32"]], "tensorrt_llm::runtime::itensor::strides (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor7stridesERK5Shape"]], "tensorrt_llm::runtime::itensor::tostring (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor8toStringERK5Shape"]], "tensorrt_llm::runtime::itensor::unsqueeze (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeE10SizeType32"], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeERK5Shape10SizeType32"]], "tensorrt_llm::runtime::itensor::view (c++ function)": [[1, "_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape"], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewE9SharedPtr"], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor4viewEN7IBuffer9SharedPtrERK5Shape"]], "tensorrt_llm::runtime::itensor::volume (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor6volumeERK5Shape"]], "tensorrt_llm::runtime::itensor::volumenonnegative (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensor17volumeNonNegativeERK5Shape"]], "tensorrt_llm::runtime::itensor::wrap (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape"], [1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE"], [1, "_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape"], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape"], [1, "_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE"]], "tensorrt_llm::runtime::itensor::~itensor (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7ITensorD0Ev"]], "tensorrt_llm::runtime::ipcmemory (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryE"]], "tensorrt_llm::runtime::ipcmemory::bufferptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9BufferPtrE"]], "tensorrt_llm::runtime::ipcmemory::flags_size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory10FLAGS_SIZEE"]], "tensorrt_llm::runtime::ipcmemory::ipcmemory (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfigb"], [1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryERK9IpcMemory"], [1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryERR9IpcMemory"]], "tensorrt_llm::runtime::ipcmemory::allocateipcmemory (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryENSt6size_tERK13BufferManagerRK11WorldConfig"]], "tensorrt_llm::runtime::ipcmemory::destroyipcmemory (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory16destroyIpcMemoryEv"]], "tensorrt_llm::runtime::ipcmemory::getcommptrs (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9IpcMemory11getCommPtrsEv"]], "tensorrt_llm::runtime::ipcmemory::mbuffer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory7mBufferE"]], "tensorrt_llm::runtime::ipcmemory::mcommptrs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory9mCommPtrsE"]], "tensorrt_llm::runtime::ipcmemory::mopenipc (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory8mOpenIpcE"]], "tensorrt_llm::runtime::ipcmemory::mtprank (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemory7mTpRankE"]], "tensorrt_llm::runtime::ipcmemory::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryaSERK9IpcMemory"], [1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryaSERR9IpcMemory"]], "tensorrt_llm::runtime::ipcmemory::~ipcmemory (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9IpcMemoryD0Ev"]], "tensorrt_llm::runtime::lookaheaddecodingbuffers (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffersE"]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::itensor (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers7ITensorE"]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::lookaheaddecodingbuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers24LookaheadDecodingBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerE"]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers10SizeType32E"]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers9TensorPtrE"]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::generationlengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers17generationLengthsE"]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::packedmasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers11packedMasksE"]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::positionids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers11positionIdsE"]], "tensorrt_llm::runtime::lookaheaddecodingbuffers::positionoffsets (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime24LookaheadDecodingBuffers15positionOffsetsE"]], "tensorrt_llm::runtime::lookaheadmodule (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModuleE"]], "tensorrt_llm::runtime::lookaheadmodule::lookaheadmodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleE10SizeType3210SizeType32"], [1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule15LookaheadModuleEv"]], "tensorrt_llm::runtime::lookaheadmodule::getexecutionconfig (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime15LookaheadModule18getExecutionConfigEv"]], "tensorrt_llm::runtime::lookaheadmodule::mexecutionconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule16mExecutionConfigE"]], "tensorrt_llm::runtime::lookaheadmodule::setexecutionconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime15LookaheadModule18setExecutionConfigERKN8executor23LookaheadDecodingConfigE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffersE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::itensor (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers7ITensorE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::lookaheadruntimebuffers (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23LookaheadRuntimeBuffersE10SizeType3210SizeType32RKN7runtime13BufferManagerERKN7runtime11ModelConfigERKN7runtime11WorldConfigERKN8executor14DecodingConfigERKN7runtime11TllmRuntimeE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers10SizeType32E"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::tensormap (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers9TensorMapE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers9TensorPtrE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::batchslotshostcopy (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers18batchSlotsHostCopyE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::generationlengthsdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23generationLengthsDeviceE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::generationlengthshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers21generationLengthsHostE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::generationlengthshostcopy (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers25generationLengthsHostCopyE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::insertinputtensors (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers18insertInputTensorsER9TensorMapR9TensorMapRKN7runtime11WorldConfigE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::packedmaskhost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers14packedMaskHostE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::packedmaskhostcopy (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers18packedMaskHostCopyE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::packedmasksdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers17packedMasksDeviceE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionidsdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers17positionIdsDeviceE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionidshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers15positionIdsHostE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionidshostcopy (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers19positionIdsHostCopyE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionoffsetsdevice (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers21positionOffsetsDeviceE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionoffsetshost (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers19positionOffsetsHostE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::positionoffsetshostcopy (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers23positionOffsetsHostCopyE"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::reshape (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23LookaheadRuntimeBuffers7reshapeE10SizeType3210SizeType3210SizeType32"]], "tensorrt_llm::runtime::lookaheadruntimebuffers::setfrominputs (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23LookaheadRuntimeBuffers13setFromInputsE10SizeType3210SizeType32RKN7runtime7ITensorERK7ITensorRK24LookaheadDecodingBuffersRKN7runtime11TllmRuntimeERKN7runtime11ModelConfigERKN7runtime11WorldConfigE"]], "tensorrt_llm::runtime::loracache (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCacheE"]], "tensorrt_llm::runtime::loracache::loracache (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9LoraCacheERK26LoraCachePageManagerConfigRK11ModelConfigRK11WorldConfigRK13BufferManager"]], "tensorrt_llm::runtime::loracache::taskidtype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache10TaskIdTypeE"]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfigE"]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::adaptersize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig11adapterSizeE"]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::insize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig6inSizeE"]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::layerid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7layerIdE"]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::moduleid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8moduleIdE"]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::numslots (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8numSlotsE"]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::operator== (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfigeqERKN9LoraCache21TaskLayerModuleConfigE"]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::outsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7outSizeE"]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::pageid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig6pageIdE"]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::slotidx (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig7slotIdxE"]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::tostring (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig8toStringEv"]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::weightsinpointer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig16weightsInPointerE"]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfig::weightsoutpointer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21TaskLayerModuleConfig17weightsOutPointerE"]], "tensorrt_llm::runtime::loracache::tasklayermoduleconfiglistptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache28TaskLayerModuleConfigListPtrE"]], "tensorrt_llm::runtime::loracache::taskvalue (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueE"]], "tensorrt_llm::runtime::loracache::taskvalue::taskvalue (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERKNSt6vectorINSt6size_tEEERK28TaskLayerModuleConfigListPtrNSt4listI10TaskIdTypeE8iteratorEbbbb"], [1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueERR9TaskValue"], [1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue9TaskValueEv"]], "tensorrt_llm::runtime::loracache::taskvalue::configs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue7configsE"]], "tensorrt_llm::runtime::loracache::taskvalue::done (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue4doneE"]], "tensorrt_llm::runtime::loracache::taskvalue::inprogress (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue10inProgressE"]], "tensorrt_llm::runtime::loracache::taskvalue::it (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue2itE"]], "tensorrt_llm::runtime::loracache::taskvalue::loadinprogress (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue14loadInProgressE"]], "tensorrt_llm::runtime::loracache::taskvalue::loaded (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue6loadedE"]], "tensorrt_llm::runtime::loracache::taskvalue::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueaSERR9TaskValue"]], "tensorrt_llm::runtime::loracache::taskvalue::pageids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValue7pageIdsE"]], "tensorrt_llm::runtime::loracache::taskvalue::~taskvalue (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TaskValueD0Ev"]], "tensorrt_llm::runtime::loracache::taskvalueptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12TaskValuePtrE"]], "tensorrt_llm::runtime::loracache::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9TensorPtrE"]], "tensorrt_llm::runtime::loracache::valuestatus (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatusE"]], "tensorrt_llm::runtime::loracache::valuestatus::kvalue_status_loaded (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus20kVALUE_STATUS_LOADEDE"]], "tensorrt_llm::runtime::loracache::valuestatus::kvalue_status_missing (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus21kVALUE_STATUS_MISSINGE"]], "tensorrt_llm::runtime::loracache::valuestatus::kvalue_status_processing (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11ValueStatus24kVALUE_STATUS_PROCESSINGE"]], "tensorrt_llm::runtime::loracache::bump (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache4bumpE10TaskIdType"]], "tensorrt_llm::runtime::loracache::bumptaskinprogress (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache18bumpTaskInProgressE10TaskIdType"]], "tensorrt_llm::runtime::loracache::claimpageswithevict (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache19claimPagesWithEvictE10SizeType32"]], "tensorrt_llm::runtime::loracache::copytask (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache8copyTaskE10TaskIdTypeR9LoraCacheb"]], "tensorrt_llm::runtime::loracache::copytaskmappages (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16copyTaskMapPagesER9TaskValueRK9TaskValueRKNSt6vectorI6size_tEERK9LoraCache"]], "tensorrt_llm::runtime::loracache::copytopages (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11copyToPagesE9TensorPtr9TensorPtrRK11ModelConfigRK11WorldConfigNSt13unordered_mapI10SizeType3210LoraModuleEERK13BufferManagerRKNSt6vectorI9TensorPtrEERKNSt6vectorINSt6size_tEEE"]], "tensorrt_llm::runtime::loracache::determinenumpages (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE10TaskIdType"], [1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache17determineNumPagesE9TensorPtr"]], "tensorrt_llm::runtime::loracache::fits (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache4fitsE9TensorPtr"]], "tensorrt_llm::runtime::loracache::get (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3getE10TaskIdType"]], "tensorrt_llm::runtime::loracache::getnumpages (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache11getNumPagesEv"]], "tensorrt_llm::runtime::loracache::getpageptr (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache10getPagePtrE6size_t"]], "tensorrt_llm::runtime::loracache::getstatus (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache9getStatusE10TaskIdType"]], "tensorrt_llm::runtime::loracache::has (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache3hasE10TaskIdType"]], "tensorrt_llm::runtime::loracache::isdone (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache6isDoneE10TaskIdType"]], "tensorrt_llm::runtime::loracache::isloaded (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9LoraCache8isLoadedE10TaskIdType"]], "tensorrt_llm::runtime::loracache::loadweights (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsE10TaskIdType9TensorPtr9TensorPtr"], [1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11loadWeightsER9TaskValue9TensorPtr9TensorPtr"]], "tensorrt_llm::runtime::loracache::mbuffermanager (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache14mBufferManagerE"]], "tensorrt_llm::runtime::loracache::mcachemap (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache9mCacheMapE"]], "tensorrt_llm::runtime::loracache::mcachemutex (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11mCacheMutexE"]], "tensorrt_llm::runtime::loracache::mcachepagemanager (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17mCachePageManagerE"]], "tensorrt_llm::runtime::loracache::mdevicebuffermanagers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache21mDeviceBufferManagersE"]], "tensorrt_llm::runtime::loracache::mdonetasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache10mDoneTasksE"]], "tensorrt_llm::runtime::loracache::minprogresstasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache16mInProgressTasksE"]], "tensorrt_llm::runtime::loracache::mmodelconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12mModelConfigE"]], "tensorrt_llm::runtime::loracache::mmoduleidtomodule (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17mModuleIdToModuleE"]], "tensorrt_llm::runtime::loracache::mpagemanagerconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache18mPageManagerConfigE"]], "tensorrt_llm::runtime::loracache::mpagesmutex (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11mPagesMutexE"]], "tensorrt_llm::runtime::loracache::mworldconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12mWorldConfigE"]], "tensorrt_llm::runtime::loracache::markalldone (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache11markAllDoneEv"]], "tensorrt_llm::runtime::loracache::marktaskdone (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache12markTaskDoneE10TaskIdType"]], "tensorrt_llm::runtime::loracache::put (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache3putE10TaskIdType9TensorPtr9TensorPtrb"]], "tensorrt_llm::runtime::loracache::splittransposecpu (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9LoraCache17splitTransposeCpuER7ITensorRK7ITensor10SizeType3210SizeType32"]], "tensorrt_llm::runtime::loracache::splittransposecpuinner (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime9LoraCache22splitTransposeCpuInnerEvR7ITensorRK7ITensor10SizeType3210SizeType32"]], "tensorrt_llm::runtime::loracachefullexception (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullExceptionE"]], "tensorrt_llm::runtime::loracachefullexception::loracachefullexception (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullException22LoraCacheFullExceptionERKNSt6stringE"]], "tensorrt_llm::runtime::loracachefullexception::~loracachefullexception (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime22LoraCacheFullExceptionD0Ev"]], "tensorrt_llm::runtime::loracachepagemanager (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManagerE"]], "tensorrt_llm::runtime::loracachepagemanager::loracachepagemanager (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager20LoraCachePageManagerERK26LoraCachePageManagerConfigRK13BufferManager"]], "tensorrt_llm::runtime::loracachepagemanager::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager9TensorPtrE"]], "tensorrt_llm::runtime::loracachepagemanager::blockptr (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager8blockPtrE10SizeType32"]], "tensorrt_llm::runtime::loracachepagemanager::claimpages (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10claimPagesE10SizeType32"]], "tensorrt_llm::runtime::loracachepagemanager::initialize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager10initializeERK13BufferManager"]], "tensorrt_llm::runtime::loracachepagemanager::mconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager7mConfigE"]], "tensorrt_llm::runtime::loracachepagemanager::mfreepageids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager12mFreePageIdsE"]], "tensorrt_llm::runtime::loracachepagemanager::mispagefree (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager11mIsPageFreeE"]], "tensorrt_llm::runtime::loracachepagemanager::mpageblocks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager11mPageBlocksE"]], "tensorrt_llm::runtime::loracachepagemanager::mutablepageptr (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager14mutablePagePtrENSt6size_tE"]], "tensorrt_llm::runtime::loracachepagemanager::numavailablepages (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager17numAvailablePagesEv"]], "tensorrt_llm::runtime::loracachepagemanager::pageptr (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime20LoraCachePageManager7pagePtrENSt6size_tE"]], "tensorrt_llm::runtime::loracachepagemanager::releasepages (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20LoraCachePageManager12releasePagesERKNSt6vectorINSt6size_tEEE"]], "tensorrt_llm::runtime::loracachepagemanagerconfig (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfigE"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::loracachepagemanagerconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig26LoraCachePageManagerConfigEN7runtime10MemoryTypeEN8nvinfer18DataTypeE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getdatatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig11getDataTypeEv"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getinittozero (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig13getInitToZeroEv"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getmaxpagesperblock (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig19getMaxPagesPerBlockEv"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getmemorytype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig13getMemoryTypeEv"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getnumcopystreams (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig17getNumCopyStreamsEv"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getpagewidth (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig12getPageWidthEv"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::getslotsperpage (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig15getSlotsPerPageEv"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::gettotalnumpages (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime26LoraCachePageManagerConfig16getTotalNumPagesEv"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mdatatype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig9mDataTypeE"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::minittozero (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11mInitToZeroE"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mmaxpagesperblock (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig17mMaxPagesPerBlockE"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mmemorytype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11mMemoryTypeE"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mnumcopystreams (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15mNumCopyStreamsE"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mpagewidth (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig10mPageWidthE"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mslotsperpage (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13mSlotsPerPageE"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::mtotalnumpages (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig14mTotalNumPagesE"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setdatatype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig11setDataTypeERKN8nvinfer18DataTypeE"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setinittozero (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setInitToZeroEb"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setmaxpagesperblock (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig19setMaxPagesPerBlockERK10SizeType32"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setmemorytype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig13setMemoryTypeERKN7runtime10MemoryTypeE"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setnumcopystreams (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig17setNumCopyStreamsE10SizeType32"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setpagewidth (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig12setPageWidthERK10SizeType32"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::setslotsperpage (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setSlotsPerPageERK10SizeType32"]], "tensorrt_llm::runtime::loracachepagemanagerconfig::settotalnumpage (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime26LoraCachePageManagerConfig15setTotalNumPageERK10SizeType32"]], "tensorrt_llm::runtime::loraexpectedexception (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedExceptionE"]], "tensorrt_llm::runtime::loraexpectedexception::loraexpectedexception (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedException21LoraExpectedExceptionERKNSt6stringE"]], "tensorrt_llm::runtime::loraexpectedexception::~loraexpectedexception (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime21LoraExpectedExceptionD0Ev"]], "tensorrt_llm::runtime::loramodule (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModuleE"]], "tensorrt_llm::runtime::loramodule::loramodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10LoraModule"], [1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleERK10ModuleType10SizeType3210SizeType32bb10SizeType3210SizeType32"], [1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10LoraModuleEv"]], "tensorrt_llm::runtime::loramodule::moduletype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleTypeE"]], "tensorrt_llm::runtime::loramodule::moduletype::kattn_dense (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kATTN_DENSEE"]], "tensorrt_llm::runtime::loramodule::moduletype::kattn_k (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_KE"]], "tensorrt_llm::runtime::loramodule::moduletype::kattn_q (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_QE"]], "tensorrt_llm::runtime::loramodule::moduletype::kattn_qkv (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kATTN_QKVE"]], "tensorrt_llm::runtime::loramodule::moduletype::kattn_v (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType7kATTN_VE"]], "tensorrt_llm::runtime::loramodule::moduletype::kcross_attn_dense (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType17kCROSS_ATTN_DENSEE"]], "tensorrt_llm::runtime::loramodule::moduletype::kcross_attn_k (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_KE"]], "tensorrt_llm::runtime::loramodule::moduletype::kcross_attn_q (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_QE"]], "tensorrt_llm::runtime::loramodule::moduletype::kcross_attn_qkv (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType15kCROSS_ATTN_QKVE"]], "tensorrt_llm::runtime::loramodule::moduletype::kcross_attn_v (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType13kCROSS_ATTN_VE"]], "tensorrt_llm::runtime::loramodule::moduletype::kinvalid (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType8kINVALIDE"]], "tensorrt_llm::runtime::loramodule::moduletype::kmlp_4h_to_h (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMLP_4H_TO_HE"]], "tensorrt_llm::runtime::loramodule::moduletype::kmlp_gate (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kMLP_GATEE"]], "tensorrt_llm::runtime::loramodule::moduletype::kmlp_h_to_4h (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMLP_H_TO_4HE"]], "tensorrt_llm::runtime::loramodule::moduletype::kmlp_router (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kMLP_ROUTERE"]], "tensorrt_llm::runtime::loramodule::moduletype::kmoe_4h_to_h (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMOE_4H_TO_HE"]], "tensorrt_llm::runtime::loramodule::moduletype::kmoe_gate (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType9kMOE_GATEE"]], "tensorrt_llm::runtime::loramodule::moduletype::kmoe_h_to_4h (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType12kMOE_H_TO_4HE"]], "tensorrt_llm::runtime::loramodule::moduletype::kmoe_router (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule10ModuleType11kMOE_ROUTERE"]], "tensorrt_llm::runtime::loramodule::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule9TensorPtrE"]], "tensorrt_llm::runtime::loramodule::createloramodules (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule17createLoraModulesERKNSt6vectorINSt6stringEEE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType3210SizeType32"]], "tensorrt_llm::runtime::loramodule::flattenedinoutsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18flattenedInOutSizeE10SizeType32"]], "tensorrt_llm::runtime::loramodule::indim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule5inDimEv"]], "tensorrt_llm::runtime::loramodule::indimfirst (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule10inDimFirstEv"]], "tensorrt_llm::runtime::loramodule::insize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule6inSizeE10SizeType32"]], "tensorrt_llm::runtime::loramodule::intpsplitdim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12inTpSplitDimEv"]], "tensorrt_llm::runtime::loramodule::localinadaptersize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule18localInAdapterSizeE10SizeType3210SizeType32"]], "tensorrt_llm::runtime::loramodule::localindim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule10localInDimE10SizeType32"]], "tensorrt_llm::runtime::loramodule::localinoutsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule14localInOutSizeE10SizeType3210SizeType32"]], "tensorrt_llm::runtime::loramodule::localinsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localInSizeE10SizeType3210SizeType32"]], "tensorrt_llm::runtime::loramodule::localoutadaptersize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule19localOutAdapterSizeE10SizeType3210SizeType32"]], "tensorrt_llm::runtime::loramodule::localoutdim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11localOutDimE10SizeType32"]], "tensorrt_llm::runtime::loramodule::localoutsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule12localOutSizeE10SizeType3210SizeType32"]], "tensorrt_llm::runtime::loramodule::mindim (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule6mInDimE"]], "tensorrt_llm::runtime::loramodule::mindimfirst (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule11mInDimFirstE"]], "tensorrt_llm::runtime::loramodule::mintpsplitdim (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule13mInTpSplitDimE"]], "tensorrt_llm::runtime::loramodule::moutdim (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule7mOutDimE"]], "tensorrt_llm::runtime::loramodule::moutdimfirst (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12mOutDimFirstE"]], "tensorrt_llm::runtime::loramodule::mouttpsplitdim (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule14mOutTpSplitDimE"]], "tensorrt_llm::runtime::loramodule::mtype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule5mTypeE"]], "tensorrt_llm::runtime::loramodule::name (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule4nameEv"]], "tensorrt_llm::runtime::loramodule::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModuleaSERK10LoraModule"]], "tensorrt_llm::runtime::loramodule::outdim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule6outDimEv"]], "tensorrt_llm::runtime::loramodule::outdimfirst (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule11outDimFirstEv"]], "tensorrt_llm::runtime::loramodule::outsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule7outSizeE10SizeType32"]], "tensorrt_llm::runtime::loramodule::outtpsplitdim (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule13outTpSplitDimEv"]], "tensorrt_llm::runtime::loramodule::tomodulename (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10ModuleType"], [1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleNameE10SizeType32"]], "tensorrt_llm::runtime::loramodule::tomoduletype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10LoraModule12toModuleTypeERKNSt11string_viewE"]], "tensorrt_llm::runtime::loramodule::value (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime10LoraModule5valueEv"]], "tensorrt_llm::runtime::lorataskidtype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14LoraTaskIdTypeE"]], "tensorrt_llm::runtime::medusamodule (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModuleE"]], "tensorrt_llm::runtime::medusamodule::medusachoices (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule13MedusaChoicesE"]], "tensorrt_llm::runtime::medusamodule::medusamodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleE10SizeType3210SizeType32"], [1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule12MedusaModuleEv"]], "tensorrt_llm::runtime::medusamodule::medusatreenode (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule14MedusaTreeNodeE"]], "tensorrt_llm::runtime::medusamodule::medusatreenode::childlinearindices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule14MedusaTreeNode18childLinearIndicesE"]], "tensorrt_llm::runtime::medusamodule::medusatreenode::depth (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule14MedusaTreeNode5depthE"]], "tensorrt_llm::runtime::medusamodule::medusatreenode::linearidx (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule14MedusaTreeNode9linearIdxE"]], "tensorrt_llm::runtime::medusamodule::medusatreenode::nodeid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule14MedusaTreeNode6nodeIdE"]], "tensorrt_llm::runtime::medusamodule::medusatreenode::parentlinearidx (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule14MedusaTreeNode15parentLinearIdxE"]], "tensorrt_llm::runtime::medusamodule::prefix_chunk_size_bits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule22PREFIX_CHUNK_SIZE_BITSE"]], "tensorrt_llm::runtime::medusamodule::prefix_max_value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule16PREFIX_MAX_VALUEE"]], "tensorrt_llm::runtime::medusamodule::prefix (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule6PrefixE"]], "tensorrt_llm::runtime::medusamodule::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule9TensorPtrE"]], "tensorrt_llm::runtime::medusamodule::computepathsandmask (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule19computePathsAndMaskERKNSt6vectorI14MedusaTreeNodeEER9TensorPtrR9TensorPtr"]], "tensorrt_llm::runtime::medusamodule::computeprefix (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule13computePrefixERKNSt6vectorI10SizeType32EE10SizeType32"]], "tensorrt_llm::runtime::medusamodule::copypackedmask (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule14copyPackedMaskER9TensorPtr10SizeType3210SizeType32"]], "tensorrt_llm::runtime::medusamodule::dumpchoices (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule11dumpChoicesERK13MedusaChoicesRKNSt6vectorI10SizeType32EE"]], "tensorrt_llm::runtime::medusamodule::getmedusachoices (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule16getMedusaChoicesEv"]], "tensorrt_llm::runtime::medusamodule::initmedusatensorsfromchoices (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule28initMedusaTensorsFromChoicesERK13MedusaChoicesRNSt6vectorI10SizeType32EER9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR9TensorPtrR10SizeType32"]], "tensorrt_llm::runtime::medusamodule::mdefaultmedusachoices (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime12MedusaModule21mDefaultMedusaChoicesE"]], "tensorrt_llm::runtime::medusamodule::setonepackedmask (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime12MedusaModule16setOnePackedMaskER9TensorPtr10SizeType3210SizeType32"]], "tensorrt_llm::runtime::memorycounters (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCountersE"]], "tensorrt_llm::runtime::memorycounters::difftype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE"]], "tensorrt_llm::runtime::memorycounters::memorycounters (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters14MemoryCountersEv"]], "tensorrt_llm::runtime::memorycounters::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10SizeType32E"]], "tensorrt_llm::runtime::memorycounters::allocate (c++ function)": [[1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters8allocateEv10SizeType32"], [1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8allocateE10MemoryType10SizeType32"]], "tensorrt_llm::runtime::memorycounters::bytestostring (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE10SizeType32i"], [1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8DiffTypei"]], "tensorrt_llm::runtime::memorycounters::deallocate (c++ function)": [[1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters10deallocateEv10SizeType32"], [1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters10deallocateE10MemoryType10SizeType32"]], "tensorrt_llm::runtime::memorycounters::getcpu (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getCpuEv"]], "tensorrt_llm::runtime::memorycounters::getcpudiff (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getCpuDiffEv"]], "tensorrt_llm::runtime::memorycounters::getgpu (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getGpuEv"]], "tensorrt_llm::runtime::memorycounters::getgpudiff (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getGpuDiffEv"]], "tensorrt_llm::runtime::memorycounters::getinstance (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11getInstanceEv"]], "tensorrt_llm::runtime::memorycounters::getpinned (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters9getPinnedEv"]], "tensorrt_llm::runtime::memorycounters::getpinneddiff (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters13getPinnedDiffEv"]], "tensorrt_llm::runtime::memorycounters::getpinnedpool (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters13getPinnedPoolEv"]], "tensorrt_llm::runtime::memorycounters::getpinnedpooldiff (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters17getPinnedPoolDiffEv"]], "tensorrt_llm::runtime::memorycounters::getuvm (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getUVMEv"]], "tensorrt_llm::runtime::memorycounters::getuvmdiff (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getUVMDiffEv"]], "tensorrt_llm::runtime::memorycounters::mcpu (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mCpuE"]], "tensorrt_llm::runtime::memorycounters::mcpudiff (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mCpuDiffE"]], "tensorrt_llm::runtime::memorycounters::mgpu (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mGpuE"]], "tensorrt_llm::runtime::memorycounters::mgpudiff (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mGpuDiffE"]], "tensorrt_llm::runtime::memorycounters::mpinned (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters7mPinnedE"]], "tensorrt_llm::runtime::memorycounters::mpinneddiff (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11mPinnedDiffE"]], "tensorrt_llm::runtime::memorycounters::mpinnedpool (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters11mPinnedPoolE"]], "tensorrt_llm::runtime::memorycounters::mpinnedpooldiff (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters15mPinnedPoolDiffE"]], "tensorrt_llm::runtime::memorycounters::muvm (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mUVME"]], "tensorrt_llm::runtime::memorycounters::muvmdiff (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mUVMDiffE"]], "tensorrt_llm::runtime::memorycounters::tostring (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14MemoryCounters8toStringEv"]], "tensorrt_llm::runtime::memorytype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryTypeE"]], "tensorrt_llm::runtime::memorytype::kcpu (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kCPUE"]], "tensorrt_llm::runtime::memorytype::kgpu (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kGPUE"]], "tensorrt_llm::runtime::memorytype::kpinned (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryType7kPINNEDE"]], "tensorrt_llm::runtime::memorytype::kpinnedpool (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryType11kPINNEDPOOLE"]], "tensorrt_llm::runtime::memorytype::kuvm (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime10MemoryType4kUVME"]], "tensorrt_llm::runtime::memorytypestring (c++ struct)": [[1, "_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime16MemoryTypeStringE"]], "tensorrt_llm::runtime::memorytypestring<memorytype::kcpu> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEEE"]], "tensorrt_llm::runtime::memorytypestring<memorytype::kcpu>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEE5valueE"]], "tensorrt_llm::runtime::memorytypestring<memorytype::kgpu> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEEE"]], "tensorrt_llm::runtime::memorytypestring<memorytype::kgpu>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEE5valueE"]], "tensorrt_llm::runtime::memorytypestring<memorytype::kpinned> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEEE"]], "tensorrt_llm::runtime::memorytypestring<memorytype::kpinned>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEE5valueE"]], "tensorrt_llm::runtime::memorytypestring<memorytype::kpinnedpool> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType11kPINNEDPOOLEEE"]], "tensorrt_llm::runtime::memorytypestring<memorytype::kpinnedpool>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType11kPINNEDPOOLEE5valueE"]], "tensorrt_llm::runtime::memorytypestring<memorytype::kuvm> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kUVMEEE"]], "tensorrt_llm::runtime::memorytypestring<memorytype::kuvm>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kUVMEE5valueE"]], "tensorrt_llm::runtime::modelconfig (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfigE"]], "tensorrt_llm::runtime::modelconfig::kvcachetype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheTypeE"]], "tensorrt_llm::runtime::modelconfig::kvcachetype::kcontinuous (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType11kCONTINUOUSE"]], "tensorrt_llm::runtime::modelconfig::kvcachetype::kdisabled (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType9kDISABLEDE"]], "tensorrt_llm::runtime::modelconfig::kvcachetype::kpaged (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11KVCacheType6kPAGEDE"]], "tensorrt_llm::runtime::modelconfig::kvcachetypefromstring (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21KVCacheTypeFromStringENSt6stringE"]], "tensorrt_llm::runtime::modelconfig::layertype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerTypeE"]], "tensorrt_llm::runtime::modelconfig::layertype::kattention (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType10kATTENTIONE"]], "tensorrt_llm::runtime::modelconfig::layertype::krecurrent (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9LayerType10kRECURRENTE"]], "tensorrt_llm::runtime::modelconfig::manageweightstype (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsTypeE"]], "tensorrt_llm::runtime::modelconfig::manageweightstype::kdisabled (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsType9kDisabledE"]], "tensorrt_llm::runtime::modelconfig::manageweightstype::kenabled (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17ManageWeightsType8kEnabledE"]], "tensorrt_llm::runtime::modelconfig::modelconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11ModelConfigE10SizeType3210SizeType3210SizeType3210SizeType3210SizeType32N8nvinfer18DataTypeE"]], "tensorrt_llm::runtime::modelconfig::modelvariant (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariantE"]], "tensorrt_llm::runtime::modelconfig::modelvariant::kchatglm (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant8kChatGlmE"]], "tensorrt_llm::runtime::modelconfig::modelvariant::kencdec (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant7kEncDecE"]], "tensorrt_llm::runtime::modelconfig::modelvariant::kglm (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant4kGlmE"]], "tensorrt_llm::runtime::modelconfig::modelvariant::kgpt (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant4kGptE"]], "tensorrt_llm::runtime::modelconfig::modelvariant::kmamba (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant6kMambaE"]], "tensorrt_llm::runtime::modelconfig::modelvariant::krecurrentgemma (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12ModelVariant15kRecurrentGemmaE"]], "tensorrt_llm::runtime::modelconfig::rnnconfig (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfigE"]], "tensorrt_llm::runtime::modelconfig::rnnconfig::convkernel (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig10convKernelE"]], "tensorrt_llm::runtime::modelconfig::rnnconfig::rnnconvdimsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig14rnnConvDimSizeE"]], "tensorrt_llm::runtime::modelconfig::rnnconfig::rnnheadsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig11rnnHeadSizeE"]], "tensorrt_llm::runtime::modelconfig::rnnconfig::rnnhiddensize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig13rnnHiddenSizeE"]], "tensorrt_llm::runtime::modelconfig::rnnconfig::statesize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9RnnConfig9stateSizeE"]], "tensorrt_llm::runtime::modelconfig::computecontextlogits (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20computeContextLogitsEb"], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20computeContextLogitsEv"]], "tensorrt_llm::runtime::modelconfig::computegenerationlogits (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23computeGenerationLogitsEb"], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig23computeGenerationLogitsEv"]], "tensorrt_llm::runtime::modelconfig::getcontextfmha (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getContextFMHAEv"]], "tensorrt_llm::runtime::modelconfig::getdatatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig11getDataTypeEv"]], "tensorrt_llm::runtime::modelconfig::getencoderhiddensize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getEncoderHiddenSizeEv"]], "tensorrt_llm::runtime::modelconfig::gethiddensize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getHiddenSizeEv"]], "tensorrt_llm::runtime::modelconfig::getkvcachetype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getKVCacheTypeEv"]], "tensorrt_llm::runtime::modelconfig::getkvdatatype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getKvDataTypeEv"]], "tensorrt_llm::runtime::modelconfig::getlayertypes (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13getLayerTypesEv"]], "tensorrt_llm::runtime::modelconfig::getlogitsdtype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getLogitsDtypeEv"]], "tensorrt_llm::runtime::modelconfig::getloramodules (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getLoraModulesEv"]], "tensorrt_llm::runtime::modelconfig::getmanageweightstype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getManageWeightsTypeEv"]], "tensorrt_llm::runtime::modelconfig::getmaxbatchsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxBatchSizeEv"]], "tensorrt_llm::runtime::modelconfig::getmaxbeamwidth (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxBeamWidthEv"]], "tensorrt_llm::runtime::modelconfig::getmaxdecodingdrafttokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig25getMaxDecodingDraftTokensEv"]], "tensorrt_llm::runtime::modelconfig::getmaxdecodingtokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getMaxDecodingTokensEv"]], "tensorrt_llm::runtime::modelconfig::getmaxencoderlen (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16getMaxEncoderLenEv"]], "tensorrt_llm::runtime::modelconfig::getmaxinputlen (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getMaxInputLenEv"]], "tensorrt_llm::runtime::modelconfig::getmaxlorarank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getMaxLoraRankEv"]], "tensorrt_llm::runtime::modelconfig::getmaxnumtokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getMaxNumTokensEv"]], "tensorrt_llm::runtime::modelconfig::getmaxpromptembeddingtablesize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig30getMaxPromptEmbeddingTableSizeEv"]], "tensorrt_llm::runtime::modelconfig::getmaxsequencelen (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17getMaxSequenceLenEv"]], "tensorrt_llm::runtime::modelconfig::getmlphiddensize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16getMlpHiddenSizeEv"]], "tensorrt_llm::runtime::modelconfig::getmodelname (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getModelNameEv"]], "tensorrt_llm::runtime::modelconfig::getmodelvariant (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15getModelVariantEv"]], "tensorrt_llm::runtime::modelconfig::getnbattentionlayers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20getNbAttentionLayersE10SizeType32"]], "tensorrt_llm::runtime::modelconfig::getnbheads (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig10getNbHeadsEv"]], "tensorrt_llm::runtime::modelconfig::getnbkvheads (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getNbKvHeadsEv"]], "tensorrt_llm::runtime::modelconfig::getnbrnnlayers (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getNbRnnLayersE10SizeType32"]], "tensorrt_llm::runtime::modelconfig::getoptprofilessplitpoints (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig25getOptProfilesSplitPointsEv"]], "tensorrt_llm::runtime::modelconfig::getpagedcontextfmha (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig19getPagedContextFMHAEv"]], "tensorrt_llm::runtime::modelconfig::getquantmode (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getQuantModeEv"]], "tensorrt_llm::runtime::modelconfig::getrnnconfig (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getRnnConfigEv"]], "tensorrt_llm::runtime::modelconfig::getsizeperhead (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14getSizePerHeadEv"]], "tensorrt_llm::runtime::modelconfig::getspeculativedecodingmode (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig26getSpeculativeDecodingModeEv"]], "tensorrt_llm::runtime::modelconfig::getspeculativedecodingmodule (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig28getSpeculativeDecodingModuleEv"]], "tensorrt_llm::runtime::modelconfig::getspeculativedecodingmoduleptr (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig31getSpeculativeDecodingModulePtrEv"], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig31getSpeculativeDecodingModulePtrEv"]], "tensorrt_llm::runtime::modelconfig::gettokensperblock (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17getTokensPerBlockEv"]], "tensorrt_llm::runtime::modelconfig::getvocabsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12getVocabSizeEv"]], "tensorrt_llm::runtime::modelconfig::getvocabsizepadded (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18getVocabSizePaddedE10SizeType32"]], "tensorrt_llm::runtime::modelconfig::hasrnnconfig (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig12hasRnnConfigEv"]], "tensorrt_llm::runtime::modelconfig::hasspeculativedecodingmodule (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig28hasSpeculativeDecodingModuleEv"]], "tensorrt_llm::runtime::modelconfig::iscontinuouskvcache (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig19isContinuousKVCacheEv"]], "tensorrt_llm::runtime::modelconfig::iskvcacheenabled (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig16isKVCacheEnabledEv"]], "tensorrt_llm::runtime::modelconfig::ispagedkvcache (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14isPagedKVCacheEv"]], "tensorrt_llm::runtime::modelconfig::isrnnbased (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig10isRnnBasedEv"]], "tensorrt_llm::runtime::modelconfig::istransformerbased (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig18isTransformerBasedEv"]], "tensorrt_llm::runtime::modelconfig::kopt_profiles_split_points (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26kOPT_PROFILES_SPLIT_POINTSE"]], "tensorrt_llm::runtime::modelconfig::mcomputecontextlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mComputeContextLogitsE"]], "tensorrt_llm::runtime::modelconfig::mcomputegenerationlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24mComputeGenerationLogitsE"]], "tensorrt_llm::runtime::modelconfig::mcontextfmha (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mContextFMHAE"]], "tensorrt_llm::runtime::modelconfig::mdatatype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig9mDataTypeE"]], "tensorrt_llm::runtime::modelconfig::mencoderhiddensize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mEncoderHiddenSizeE"]], "tensorrt_llm::runtime::modelconfig::mhiddensize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mHiddenSizeE"]], "tensorrt_llm::runtime::modelconfig::minputpacked (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mInputPackedE"]], "tensorrt_llm::runtime::modelconfig::mkvcachetype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mKVCacheTypeE"]], "tensorrt_llm::runtime::modelconfig::mlayertypes (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mLayerTypesE"]], "tensorrt_llm::runtime::modelconfig::mlogitsdtype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mLogitsDtypeE"]], "tensorrt_llm::runtime::modelconfig::mloramodules (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mLoraModulesE"]], "tensorrt_llm::runtime::modelconfig::mmanageweightstype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mManageWeightsTypeE"]], "tensorrt_llm::runtime::modelconfig::mmaxbatchsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxBatchSizeE"]], "tensorrt_llm::runtime::modelconfig::mmaxbeamwidth (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxBeamWidthE"]], "tensorrt_llm::runtime::modelconfig::mmaxencoderlen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mMaxEncoderLenE"]], "tensorrt_llm::runtime::modelconfig::mmaxinputlen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mMaxInputLenE"]], "tensorrt_llm::runtime::modelconfig::mmaxlorarank (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mMaxLoraRankE"]], "tensorrt_llm::runtime::modelconfig::mmaxnumtokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mMaxNumTokensE"]], "tensorrt_llm::runtime::modelconfig::mmaxpromptembeddingtablesize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28mMaxPromptEmbeddingTableSizeE"]], "tensorrt_llm::runtime::modelconfig::mmaxsequencelen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15mMaxSequenceLenE"]], "tensorrt_llm::runtime::modelconfig::mmlphiddensize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mMlpHiddenSizeE"]], "tensorrt_llm::runtime::modelconfig::mmodelname (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mModelNameE"]], "tensorrt_llm::runtime::modelconfig::mmodelvariant (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13mModelVariantE"]], "tensorrt_llm::runtime::modelconfig::mnbattentionlayers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mNbAttentionLayersE"]], "tensorrt_llm::runtime::modelconfig::mnbheads (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig8mNbHeadsE"]], "tensorrt_llm::runtime::modelconfig::mnbkvheads (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mNbKvHeadsE"]], "tensorrt_llm::runtime::modelconfig::mnbrnnlayers (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mNbRnnLayersE"]], "tensorrt_llm::runtime::modelconfig::mpagedcontextfmha (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17mPagedContextFMHAE"]], "tensorrt_llm::runtime::modelconfig::mpagedstate (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig11mPagedStateE"]], "tensorrt_llm::runtime::modelconfig::mquantmode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mQuantModeE"]], "tensorrt_llm::runtime::modelconfig::mrnnconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mRnnConfigE"]], "tensorrt_llm::runtime::modelconfig::msizeperhead (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12mSizePerHeadE"]], "tensorrt_llm::runtime::modelconfig::mspeculativedecodingmode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24mSpeculativeDecodingModeE"]], "tensorrt_llm::runtime::modelconfig::mspeculativedecodingmodule (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26mSpeculativeDecodingModuleE"]], "tensorrt_llm::runtime::modelconfig::mtokensperblock (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15mTokensPerBlockE"]], "tensorrt_llm::runtime::modelconfig::musecrossattention (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mUseCrossAttentionE"]], "tensorrt_llm::runtime::modelconfig::musegptattentionplugin (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22mUseGptAttentionPluginE"]], "tensorrt_llm::runtime::modelconfig::museloraplugin (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14mUseLoraPluginE"]], "tensorrt_llm::runtime::modelconfig::musemambaconv1dplugin (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mUseMambaConv1dPluginE"]], "tensorrt_llm::runtime::modelconfig::musepositionembedding (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21mUsePositionEmbeddingE"]], "tensorrt_llm::runtime::modelconfig::museshapeinference (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig18mUseShapeInferenceE"]], "tensorrt_llm::runtime::modelconfig::musetokentypeembedding (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig22mUseTokenTypeEmbeddingE"]], "tensorrt_llm::runtime::modelconfig::musexqa (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig7mUseXQAE"]], "tensorrt_llm::runtime::modelconfig::mvocabsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig10mVocabSizeE"]], "tensorrt_llm::runtime::modelconfig::setcontextfmha (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setContextFMHAEb"]], "tensorrt_llm::runtime::modelconfig::setencoderhiddensize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setEncoderHiddenSizeE10SizeType32"]], "tensorrt_llm::runtime::modelconfig::setkvcachetype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setKVCacheTypeE11KVCacheType"]], "tensorrt_llm::runtime::modelconfig::setlayertypes (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13setLayerTypesERKNSt6vectorI9LayerTypeEE"]], "tensorrt_llm::runtime::modelconfig::setlogitsdtype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLogitsDtypeEN8nvinfer18DataTypeE"]], "tensorrt_llm::runtime::modelconfig::setloramodules (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setLoraModulesERKNSt6vectorI10LoraModuleEE"]], "tensorrt_llm::runtime::modelconfig::setmanageweightstype (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setManageWeightsTypeEK17ManageWeightsType"]], "tensorrt_llm::runtime::modelconfig::setmaxbatchsize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBatchSizeE10SizeType32"]], "tensorrt_llm::runtime::modelconfig::setmaxbeamwidth (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxBeamWidthE10SizeType32"]], "tensorrt_llm::runtime::modelconfig::setmaxencoderlen (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMaxEncoderLenE10SizeType32"]], "tensorrt_llm::runtime::modelconfig::setmaxinputlen (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxInputLenE10SizeType32"]], "tensorrt_llm::runtime::modelconfig::setmaxlorarank (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setMaxLoraRankE10SizeType32"]], "tensorrt_llm::runtime::modelconfig::setmaxnumtokens (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setMaxNumTokensENSt8optionalI10SizeType32EE"]], "tensorrt_llm::runtime::modelconfig::setmaxpromptembeddingtablesize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig30setMaxPromptEmbeddingTableSizeE10SizeType32"]], "tensorrt_llm::runtime::modelconfig::setmaxsequencelen (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setMaxSequenceLenE10SizeType32"]], "tensorrt_llm::runtime::modelconfig::setmlphiddensize (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig16setMlpHiddenSizeE10SizeType32"]], "tensorrt_llm::runtime::modelconfig::setmodelname (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setModelNameERKNSt6stringE"]], "tensorrt_llm::runtime::modelconfig::setmodelvariant (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig15setModelVariantE12ModelVariant"]], "tensorrt_llm::runtime::modelconfig::setnbkvheads (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setNbKvHeadsE10SizeType32"]], "tensorrt_llm::runtime::modelconfig::setpagedcontextfmha (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig19setPagedContextFMHAEb"]], "tensorrt_llm::runtime::modelconfig::setquantmode (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setQuantModeEN6common9QuantModeE"]], "tensorrt_llm::runtime::modelconfig::setrnnconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig12setRnnConfigERK9RnnConfig"]], "tensorrt_llm::runtime::modelconfig::setsizeperhead (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14setSizePerHeadE10SizeType32"]], "tensorrt_llm::runtime::modelconfig::setspeculativedecodingmode (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig26setSpeculativeDecodingModeE23SpeculativeDecodingMode"]], "tensorrt_llm::runtime::modelconfig::setspeculativedecodingmodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig28setSpeculativeDecodingModuleERKNSt10shared_ptrI25SpeculativeDecodingModuleEE"]], "tensorrt_llm::runtime::modelconfig::settokensperblock (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig17setTokensPerBlockE10SizeType32"]], "tensorrt_llm::runtime::modelconfig::setusecrossattention (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseCrossAttentionEb"]], "tensorrt_llm::runtime::modelconfig::setusepositionembedding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig23setUsePositionEmbeddingEb"]], "tensorrt_llm::runtime::modelconfig::setuseshapeinference (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20setUseShapeInferenceEb"]], "tensorrt_llm::runtime::modelconfig::setusetokentypeembedding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig24setUseTokenTypeEmbeddingEb"]], "tensorrt_llm::runtime::modelconfig::supportsinflightbatching (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig24supportsInflightBatchingEv"]], "tensorrt_llm::runtime::modelconfig::usecrossattention (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17useCrossAttentionEv"]], "tensorrt_llm::runtime::modelconfig::usegptattentionplugin (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig21useGptAttentionPluginEb"], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21useGptAttentionPluginEv"]], "tensorrt_llm::runtime::modelconfig::useloraplugin (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13useLoraPluginEb"], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13useLoraPluginEv"]], "tensorrt_llm::runtime::modelconfig::usemambaconv1dplugin (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig20useMambaConv1dPluginEb"], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20useMambaConv1dPluginEv"]], "tensorrt_llm::runtime::modelconfig::usepackedinput (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig14usePackedInputEb"], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig14usePackedInputEv"]], "tensorrt_llm::runtime::modelconfig::usepagedstate (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig13usePagedStateEb"], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig13usePagedStateEv"]], "tensorrt_llm::runtime::modelconfig::usepositionembedding (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig20usePositionEmbeddingEv"]], "tensorrt_llm::runtime::modelconfig::useprompttuning (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig15usePromptTuningEv"]], "tensorrt_llm::runtime::modelconfig::useshapeinference (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig17useShapeInferenceEv"]], "tensorrt_llm::runtime::modelconfig::usetokentypeembedding (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig21useTokenTypeEmbeddingEv"]], "tensorrt_llm::runtime::modelconfig::usexqa (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11ModelConfig6useXQAEb"], [1, "_CPPv4NK12tensorrt_llm7runtime11ModelConfig6useXQAEv"]], "tensorrt_llm::runtime::phonynameduetoerror::name (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4nameE"]], "tensorrt_llm::runtime::phonynameduetoerror::size (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4sizeE"]], "tensorrt_llm::runtime::phonynameduetoerror::type (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE"]], "tensorrt_llm::runtime::phonynameduetoerror::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError5valueE"]], "tensorrt_llm::runtime::pointerelementtype (c++ type)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE"]], "tensorrt_llm::runtime::prompttuningparams (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParamsE"]], "tensorrt_llm::runtime::prompttuningparams::prompttuningparams (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr"]], "tensorrt_llm::runtime::prompttuningparams::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams10SizeType32E"]], "tensorrt_llm::runtime::prompttuningparams::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams9TensorPtrE"]], "tensorrt_llm::runtime::prompttuningparams::filltaskstensor (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtrK10SizeType32K10SizeType32RKNSt6vectorI10SizeType32EERKNSt6vectorI10SizeType32EERK13BufferManagerb"]], "tensorrt_llm::runtime::rawengine (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngineE"]], "tensorrt_llm::runtime::rawengine::rawengine (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineENSt10filesystem4pathE"], [1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKN8nvinfer111IHostMemoryE"], [1, "_CPPv4N12tensorrt_llm7runtime9RawEngine9RawEngineEPKvNSt6size_tE"]], "tensorrt_llm::runtime::rawengine::type (c++ enum)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4TypeE"]], "tensorrt_llm::runtime::rawengine::type::addresswithsize (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type15AddressWithSizeE"]], "tensorrt_llm::runtime::rawengine::type::filepath (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type8FilePathE"]], "tensorrt_llm::runtime::rawengine::type::hostmemory (c++ enumerator)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine4Type10HostMemoryE"]], "tensorrt_llm::runtime::rawengine::[anonymous] (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngineUt1_1E"]], "tensorrt_llm::runtime::rawengine::getaddress (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine10getAddressEv"]], "tensorrt_llm::runtime::rawengine::gethostmemory (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine13getHostMemoryEv"]], "tensorrt_llm::runtime::rawengine::getmanagedweightsmapopt (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine23getManagedWeightsMapOptEv"]], "tensorrt_llm::runtime::rawengine::getpath (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getPathEv"]], "tensorrt_llm::runtime::rawengine::getpathopt (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine10getPathOptEv"]], "tensorrt_llm::runtime::rawengine::getsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getSizeEv"]], "tensorrt_llm::runtime::rawengine::gettype (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime9RawEngine7getTypeEv"]], "tensorrt_llm::runtime::rawengine::mengineaddr (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEngineAddrE"]], "tensorrt_llm::runtime::rawengine::menginebuffer (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine13mEngineBufferE"]], "tensorrt_llm::runtime::rawengine::menginepath (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEnginePathE"]], "tensorrt_llm::runtime::rawengine::menginesize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine11mEngineSizeE"]], "tensorrt_llm::runtime::rawengine::mmanagedweightsmap (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine18mManagedWeightsMapE"]], "tensorrt_llm::runtime::rawengine::mtype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine5mTypeE"]], "tensorrt_llm::runtime::rawengine::setmanagedweightsmap (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine20setManagedWeightsMapENSt3mapINSt6stringEN12tensorrt_llm8executor6TensorEEE"]], "tensorrt_llm::runtime::rawengine::setpath (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9RawEngine7setPathENSt10filesystem4pathE"]], "tensorrt_llm::runtime::samplingconfig (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfigE"]], "tensorrt_llm::runtime::samplingconfig::floattype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE"]], "tensorrt_llm::runtime::samplingconfig::optvec (c++ type)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE"]], "tensorrt_llm::runtime::samplingconfig::samplingconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigE10SizeType32"], [1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKN8executor14SamplingConfigERKNSt8optionalIN8executor25ExternalDraftTokensConfigEEE"], [1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigERKNSt6vectorI14SamplingConfigEE"]], "tensorrt_llm::runtime::samplingconfig::vec (c++ type)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig3VecE"]], "tensorrt_llm::runtime::samplingconfig::beamsearchdiversityrate (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig23beamSearchDiversityRateE"]], "tensorrt_llm::runtime::samplingconfig::beamwidth (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9beamWidthE"]], "tensorrt_llm::runtime::samplingconfig::cumlogprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig11cumLogProbsE"]], "tensorrt_llm::runtime::samplingconfig::draftacceptancethreshold (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig24draftAcceptanceThresholdE"]], "tensorrt_llm::runtime::samplingconfig::earlystopping (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig13earlyStoppingE"]], "tensorrt_llm::runtime::samplingconfig::frequencypenalty (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig16frequencyPenaltyE"]], "tensorrt_llm::runtime::samplingconfig::fusevalues (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig10fuseValuesE6OptVecI1TERKNSt6vectorI14SamplingConfigEENSt8functionIF6OptVecI1TE6size_tEEE1T"]], "tensorrt_llm::runtime::samplingconfig::lengthpenalty (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig13lengthPenaltyE"]], "tensorrt_llm::runtime::samplingconfig::minlength (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9minLengthE"]], "tensorrt_llm::runtime::samplingconfig::norepeatngramsize (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17noRepeatNgramSizeE"]], "tensorrt_llm::runtime::samplingconfig::normalizelogprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17normalizeLogProbsE"]], "tensorrt_llm::runtime::samplingconfig::operator== (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime14SamplingConfigeqERK14SamplingConfig"]], "tensorrt_llm::runtime::samplingconfig::outputlogprobs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig14outputLogProbsE"]], "tensorrt_llm::runtime::samplingconfig::presencepenalty (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig15presencePenaltyE"]], "tensorrt_llm::runtime::samplingconfig::randomseed (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig10randomSeedE"]], "tensorrt_llm::runtime::samplingconfig::repetitionpenalty (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig17repetitionPenaltyE"]], "tensorrt_llm::runtime::samplingconfig::temperature (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig11temperatureE"]], "tensorrt_llm::runtime::samplingconfig::topk (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topKE"]], "tensorrt_llm::runtime::samplingconfig::topkmedusaheads (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig15topKMedusaHeadsE"]], "tensorrt_llm::runtime::samplingconfig::topp (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topPE"]], "tensorrt_llm::runtime::samplingconfig::toppdecay (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig9topPDecayE"]], "tensorrt_llm::runtime::samplingconfig::toppmin (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig7topPMinE"]], "tensorrt_llm::runtime::samplingconfig::toppresetids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig12topPResetIdsE"]], "tensorrt_llm::runtime::samplingconfig::validate (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime14SamplingConfig8validateEv"]], "tensorrt_llm::runtime::samplingconfig::validatevec (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig11validateVecEbNSt6stringERK6OptVecI1TE1TNSt8optionalI1TEE"]], "tensorrt_llm::runtime::sizetype32 (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime10SizeType32E"]], "tensorrt_llm::runtime::speculativedecodingmode (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingModeE"]], "tensorrt_llm::runtime::speculativedecodingmode::drafttokensexternal (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode19DraftTokensExternalEv"]], "tensorrt_llm::runtime::speculativedecodingmode::explicitdrafttokens (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode19ExplicitDraftTokensEv"]], "tensorrt_llm::runtime::speculativedecodingmode::lookaheaddecoding (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode17LookaheadDecodingEv"]], "tensorrt_llm::runtime::speculativedecodingmode::medusa (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode6MedusaEv"]], "tensorrt_llm::runtime::speculativedecodingmode::none (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode4NoneEv"]], "tensorrt_llm::runtime::speculativedecodingmode::speculativedecodingmode (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode23SpeculativeDecodingModeE14UnderlyingType"]], "tensorrt_llm::runtime::speculativedecodingmode::underlyingtype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode14UnderlyingTypeE"]], "tensorrt_llm::runtime::speculativedecodingmode::allbitset (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9allBitSetE14UnderlyingType"]], "tensorrt_llm::runtime::speculativedecodingmode::anybitset (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode9anyBitSetE14UnderlyingType"]], "tensorrt_llm::runtime::speculativedecodingmode::hasdraftlogits (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode14hasDraftLogitsEv"]], "tensorrt_llm::runtime::speculativedecodingmode::isdrafttokensexternal (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21isDraftTokensExternalEv"]], "tensorrt_llm::runtime::speculativedecodingmode::isexplicitdrafttokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21isExplicitDraftTokensEv"]], "tensorrt_llm::runtime::speculativedecodingmode::islookaheaddecoding (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19isLookaheadDecodingEv"]], "tensorrt_llm::runtime::speculativedecodingmode::ismedusa (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode8isMedusaEv"]], "tensorrt_llm::runtime::speculativedecodingmode::isnone (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode6isNoneEv"]], "tensorrt_llm::runtime::speculativedecodingmode::kdrafttokensexternal (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode20kDraftTokensExternalE"]], "tensorrt_llm::runtime::speculativedecodingmode::kexplicitdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode20kExplicitDraftTokensE"]], "tensorrt_llm::runtime::speculativedecodingmode::klookaheaddecoding (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode18kLookaheadDecodingE"]], "tensorrt_llm::runtime::speculativedecodingmode::kmedusa (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode7kMedusaE"]], "tensorrt_llm::runtime::speculativedecodingmode::knone (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode5kNoneE"]], "tensorrt_llm::runtime::speculativedecodingmode::mstate (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime23SpeculativeDecodingMode6mStateE"]], "tensorrt_llm::runtime::speculativedecodingmode::needsdecoderprologue (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode20needsDecoderPrologueEv"]], "tensorrt_llm::runtime::speculativedecodingmode::needskvcacherewind (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode18needsKVCacheRewindEv"]], "tensorrt_llm::runtime::speculativedecodingmode::operator== (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingModeeqERK23SpeculativeDecodingMode"]], "tensorrt_llm::runtime::speculativedecodingmode::predictsdrafttokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19predictsDraftTokensEv"]], "tensorrt_llm::runtime::speculativedecodingmode::requiresattentionmask (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode21requiresAttentionMaskEv"]], "tensorrt_llm::runtime::speculativedecodingmode::updatespositionids (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode18updatesPositionIdsEv"]], "tensorrt_llm::runtime::speculativedecodingmode::variabledraftlength (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime23SpeculativeDecodingMode19variableDraftLengthEv"]], "tensorrt_llm::runtime::speculativedecodingmodule (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleE"]], "tensorrt_llm::runtime::speculativedecodingmodule::speculativedecodingmodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleE10SizeType3210SizeType3210SizeType32"], [1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleERK25SpeculativeDecodingModule"], [1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule25SpeculativeDecodingModuleEv"]], "tensorrt_llm::runtime::speculativedecodingmodule::computenumpackedmasks (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule21computeNumPackedMasksEv"]], "tensorrt_llm::runtime::speculativedecodingmodule::getmaxdecodingdrafttokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule25getMaxDecodingDraftTokensEv"]], "tensorrt_llm::runtime::speculativedecodingmodule::getmaxdecodingtokens (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule20getMaxDecodingTokensEv"]], "tensorrt_llm::runtime::speculativedecodingmodule::getmaxdraftpathlen (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule18getMaxDraftPathLenEv"]], "tensorrt_llm::runtime::speculativedecodingmodule::getmaxnumpaths (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule14getMaxNumPathsEv"]], "tensorrt_llm::runtime::speculativedecodingmodule::getmaxpathlen (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule13getMaxPathLenEv"]], "tensorrt_llm::runtime::speculativedecodingmodule::getnumpackedmasks (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime25SpeculativeDecodingModule17getNumPackedMasksEv"]], "tensorrt_llm::runtime::speculativedecodingmodule::mmaxdecodingdrafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule23mMaxDecodingDraftTokensE"]], "tensorrt_llm::runtime::speculativedecodingmodule::mmaxdraftpathlen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule16mMaxDraftPathLenE"]], "tensorrt_llm::runtime::speculativedecodingmodule::mmaxnumpackedmasks (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule18mMaxNumPackedMasksE"]], "tensorrt_llm::runtime::speculativedecodingmodule::mmaxnumpaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule12mMaxNumPathsE"]], "tensorrt_llm::runtime::speculativedecodingmodule::operator= (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleaSERK25SpeculativeDecodingModule"]], "tensorrt_llm::runtime::speculativedecodingmodule::setmaxdraftpathlen (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule18setMaxDraftPathLenE10SizeType32"]], "tensorrt_llm::runtime::speculativedecodingmodule::setmaxdrafttokens (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule17setMaxDraftTokensE10SizeType32"]], "tensorrt_llm::runtime::speculativedecodingmodule::setmaxnumpaths (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModule14setMaxNumPathsE10SizeType32"]], "tensorrt_llm::runtime::speculativedecodingmodule::~speculativedecodingmodule (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime25SpeculativeDecodingModuleD0Ev"]], "tensorrt_llm::runtime::stringptrmap (c++ type)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime12StringPtrMapE"]], "tensorrt_llm::runtime::trtdatatype (c++ struct)": [[1, "_CPPv4I0_bEN12tensorrt_llm7runtime11TRTDataTypeE"]], "tensorrt_llm::runtime::trtdatatype<t*> (c++ struct)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime11TRTDataTypeIP1TEE"]], "tensorrt_llm::runtime::trtdatatype<t*>::kunderlyingtype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE15kUnderlyingTypeE"]], "tensorrt_llm::runtime::trtdatatype<t*>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE5valueE"]], "tensorrt_llm::runtime::trtdatatype<bool> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIbEE"]], "tensorrt_llm::runtime::trtdatatype<bool>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIbE5valueE"]], "tensorrt_llm::runtime::trtdatatype<float> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIfEE"]], "tensorrt_llm::runtime::trtdatatype<float>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIfE5valueE"]], "tensorrt_llm::runtime::trtdatatype<half> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeI4halfEE"]], "tensorrt_llm::runtime::trtdatatype<half>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeI4halfE5valueE"]], "tensorrt_llm::runtime::trtdatatype<kernels::finishedstate> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIN7kernels13FinishedStateEEE"]], "tensorrt_llm::runtime::trtdatatype<kernels::finishedstate>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIN7kernels13FinishedStateEE5valueE"]], "tensorrt_llm::runtime::trtdatatype<kernels::kvcacheindex> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIN7kernels12KVCacheIndexEEE"]], "tensorrt_llm::runtime::trtdatatype<kernels::kvcacheindex>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIN7kernels12KVCacheIndexEE5valueE"]], "tensorrt_llm::runtime::trtdatatype<std::int32_t> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEEE"]], "tensorrt_llm::runtime::trtdatatype<std::int32_t>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEE5valueE"]], "tensorrt_llm::runtime::trtdatatype<std::int64_t> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEEE"]], "tensorrt_llm::runtime::trtdatatype<std::int64_t>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEE5valueE"]], "tensorrt_llm::runtime::trtdatatype<std::int8_t> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEEE"]], "tensorrt_llm::runtime::trtdatatype<std::int8_t>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEE5valueE"]], "tensorrt_llm::runtime::trtdatatype<std::uint32_t> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEEE"]], "tensorrt_llm::runtime::trtdatatype<std::uint32_t>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEE5valueE"]], "tensorrt_llm::runtime::trtdatatype<std::uint64_t> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEEE"]], "tensorrt_llm::runtime::trtdatatype<std::uint64_t>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEE5valueE"]], "tensorrt_llm::runtime::trtdatatype<std::uint8_t> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEEE"]], "tensorrt_llm::runtime::trtdatatype<std::uint8_t>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEE5valueE"]], "tensorrt_llm::runtime::trtdatatype<void*> (c++ struct)": [[1, "_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIPvEE"]], "tensorrt_llm::runtime::trtdatatype<void*>::value (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIPvE5valueE"]], "tensorrt_llm::runtime::tllmlogger (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime10TllmLoggerE"]], "tensorrt_llm::runtime::tllmlogger::getlevel (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger8getLevelEv"]], "tensorrt_llm::runtime::tllmlogger::log (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger3logE8SeverityPKN8nvinfer19AsciiCharE"]], "tensorrt_llm::runtime::tllmlogger::setlevel (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime10TllmLogger8setLevelE8Severity"]], "tensorrt_llm::runtime::tokenextraidtype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime16TokenExtraIdTypeE"]], "tensorrt_llm::runtime::tokenidtype (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime11TokenIdTypeE"]], "tensorrt_llm::runtime::uniquetoken (c++ struct)": [[1, "_CPPv4N12tensorrt_llm7runtime11UniqueTokenE"]], "tensorrt_llm::runtime::uniquetoken::operator== (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11UniqueTokeneqERK11UniqueToken"]], "tensorrt_llm::runtime::uniquetoken::tokenextraid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11UniqueToken12tokenExtraIdE"]], "tensorrt_llm::runtime::uniquetoken::tokenid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11UniqueToken7tokenIdE"]], "tensorrt_llm::runtime::vectokenextraids (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime16VecTokenExtraIdsE"]], "tensorrt_llm::runtime::vecuniquetokens (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime15VecUniqueTokensE"]], "tensorrt_llm::runtime::worldconfig (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfigE"]], "tensorrt_llm::runtime::worldconfig::worldconfig (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE10SizeType3210SizeType3210SizeType3210SizeType32RKNSt8optionalINSt6vectorI10SizeType32EEEE"]], "tensorrt_llm::runtime::worldconfig::getdevice (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig9getDeviceEv"]], "tensorrt_llm::runtime::worldconfig::getdeviceof (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getDeviceOfE10SizeType32"]], "tensorrt_llm::runtime::worldconfig::getgpuspergroup (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig15getGpusPerGroupEv"]], "tensorrt_llm::runtime::worldconfig::getgpuspernode (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig14getGpusPerNodeEv"]], "tensorrt_llm::runtime::worldconfig::getlastrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getLastRankEv"]], "tensorrt_llm::runtime::worldconfig::getlocalrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig12getLocalRankEv"]], "tensorrt_llm::runtime::worldconfig::getnoderank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getNodeRankEv"]], "tensorrt_llm::runtime::worldconfig::getnoderankof (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig13getNodeRankOfE10SizeType32"]], "tensorrt_llm::runtime::worldconfig::getpipelineparallelgroup (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig24getPipelineParallelGroupEv"]], "tensorrt_llm::runtime::worldconfig::getpipelineparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig23getPipelineParallelRankEv"]], "tensorrt_llm::runtime::worldconfig::getpipelineparallelism (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getPipelineParallelismEv"]], "tensorrt_llm::runtime::worldconfig::getrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getRankEv"]], "tensorrt_llm::runtime::worldconfig::getsize (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getSizeEv"]], "tensorrt_llm::runtime::worldconfig::gettensorparallelgroup (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getTensorParallelGroupEv"]], "tensorrt_llm::runtime::worldconfig::gettensorparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig21getTensorParallelRankEv"]], "tensorrt_llm::runtime::worldconfig::gettensorparallelism (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig20getTensorParallelismEv"]], "tensorrt_llm::runtime::worldconfig::isfirstpipelineparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig27isFirstPipelineParallelRankEv"]], "tensorrt_llm::runtime::worldconfig::isfirsttensorparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig25isFirstTensorParallelRankEv"]], "tensorrt_llm::runtime::worldconfig::islastpipelineparallelrank (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig26isLastPipelineParallelRankEv"]], "tensorrt_llm::runtime::worldconfig::ispipelineparallel (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig18isPipelineParallelEv"]], "tensorrt_llm::runtime::worldconfig::istensorparallel (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig16isTensorParallelEv"]], "tensorrt_llm::runtime::worldconfig::kdefaultgpuspernode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig19kDefaultGpusPerNodeE"]], "tensorrt_llm::runtime::worldconfig::mdeviceids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig10mDeviceIdsE"]], "tensorrt_llm::runtime::worldconfig::mgpuspernode (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig12mGpusPerNodeE"]], "tensorrt_llm::runtime::worldconfig::mpipelineparallelism (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig20mPipelineParallelismE"]], "tensorrt_llm::runtime::worldconfig::mrank (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig5mRankE"]], "tensorrt_llm::runtime::worldconfig::mtensorparallelism (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig18mTensorParallelismE"]], "tensorrt_llm::runtime::worldconfig::mpi (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EERKNSt8optionalINSt6vectorI10SizeType32EEEE"]], "tensorrt_llm::runtime::worldconfig::validmpiconfig (c++ function)": [[1, "_CPPv4NK12tensorrt_llm7runtime11WorldConfig14validMpiConfigEv"]], "tensorrt_llm::runtime::buffercast (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEP1TR7IBuffer"], [1, "_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEPK1TRK7IBuffer"]], "tensorrt_llm::runtime::buffercastornull (c++ function)": [[1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7IBuffer9SharedPtrE"], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKN7ITensor9SharedPtrE"], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7IBuffer9SharedPtrEEE"], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEP1TRKNSt8optionalIN7ITensor9SharedPtrEEE"], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7IBuffer14SharedConstPtrE"], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKN7ITensor14SharedConstPtrE"], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7IBuffer14SharedConstPtrEEE"], [1, "_CPPv4I0EN12tensorrt_llm7runtime16bufferCastOrNullEPK1TRKNSt8optionalIN7ITensor14SharedConstPtrEEE"]], "tensorrt_llm::runtime::constpointercast (c++ function)": [[1, "_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE"], [1, "_CPPv4I0EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERKNSt10shared_ptrI1TEE"]], "tensorrt_llm::runtime::decoder (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoderE"]], "tensorrt_llm::runtime::decoder::input (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder5InputE"]], "tensorrt_llm::runtime::decoder::input::input (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder5Input5InputE9TensorPtr"]], "tensorrt_llm::runtime::decoder::input::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder5Input9TensorPtrE"]], "tensorrt_llm::runtime::decoder::input::cacheindirection (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder5Input16cacheIndirectionE"]], "tensorrt_llm::runtime::decoder::input::logits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder5Input6logitsE"]], "tensorrt_llm::runtime::decoder::output (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder6OutputE"]], "tensorrt_llm::runtime::decoder::output::output (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder6Output6OutputEv"]], "tensorrt_llm::runtime::decoder::output::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder6Output9TensorPtrE"]], "tensorrt_llm::runtime::decoder::output::cacheindirection (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder6Output16cacheIndirectionE"]], "tensorrt_llm::runtime::decoder::output::sequencelengths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime7decoder6Output15sequenceLengthsE"]], "tensorrt_llm::runtime::decoder_batch (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batchE"]], "tensorrt_llm::runtime::decoder_batch::input (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5InputE"]], "tensorrt_llm::runtime::decoder_batch::input::input (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI9TensorPtrEE"], [1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI9TensorPtrEERKNSt6vectorIbEE"]], "tensorrt_llm::runtime::decoder_batch::input::tensorconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input14TensorConstPtrE"]], "tensorrt_llm::runtime::decoder_batch::input::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input9TensorPtrE"]], "tensorrt_llm::runtime::decoder_batch::input::active (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input6activeE"]], "tensorrt_llm::runtime::decoder_batch::input::cacheindirection (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input16cacheIndirectionE"]], "tensorrt_llm::runtime::decoder_batch::input::explicitdrafttokensinputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input25explicitDraftTokensInputsE"]], "tensorrt_llm::runtime::decoder_batch::input::explicitdrafttokenslastinputs (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input29explicitDraftTokensLastInputsE"]], "tensorrt_llm::runtime::decoder_batch::input::logits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input6logitsE"]], "tensorrt_llm::runtime::decoder_batch::input::predicteddraftlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input20predictedDraftLogitsE"]], "tensorrt_llm::runtime::decoder_batch::input::seqslots (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input8seqSlotsE"]], "tensorrt_llm::runtime::decoder_batch::output (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch6OutputE"]], "tensorrt_llm::runtime::decoder_batch::request (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7RequestE"]], "tensorrt_llm::runtime::decoder_batch::request::bufferptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9BufferPtrE"]], "tensorrt_llm::runtime::decoder_batch::request::request (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14TensorConstPtr10SizeType32NSt8optionalI10SizeType32EENSt8optionalI10SizeType32EE"]], "tensorrt_llm::runtime::decoder_batch::request::tensorconstptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request14TensorConstPtrE"]], "tensorrt_llm::runtime::decoder_batch::request::tensorptr (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9TensorPtrE"]], "tensorrt_llm::runtime::decoder_batch::request::badwordslist (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request12badWordsListE"]], "tensorrt_llm::runtime::decoder_batch::request::draftlogits (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11draftLogitsE"]], "tensorrt_llm::runtime::decoder_batch::request::drafttokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11draftTokensE"]], "tensorrt_llm::runtime::decoder_batch::request::dtype (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request5dtypeE"]], "tensorrt_llm::runtime::decoder_batch::request::embeddingbias (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13embeddingBiasE"]], "tensorrt_llm::runtime::decoder_batch::request::endid (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request5endIdE"]], "tensorrt_llm::runtime::decoder_batch::request::generatedtokensperenginestep (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request28generatedTokensPerEngineStepE"]], "tensorrt_llm::runtime::decoder_batch::request::ids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request3idsE"]], "tensorrt_llm::runtime::decoder_batch::request::inputlen (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request8inputLenE"]], "tensorrt_llm::runtime::decoder_batch::request::lookaheadruntimeconfig (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request22lookaheadRuntimeConfigE"]], "tensorrt_llm::runtime::decoder_batch::request::maxnewtokens (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request12maxNewTokensE"]], "tensorrt_llm::runtime::decoder_batch::request::medusapaths (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11medusaPathsE"]], "tensorrt_llm::runtime::decoder_batch::request::medusatreeids (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13medusaTreeIdsE"]], "tensorrt_llm::runtime::decoder_batch::request::stopwordslist (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13stopWordsListE"]], "tensorrt_llm::runtime::decoder_batch::token (c++ class)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5TokenE"]], "tensorrt_llm::runtime::decoder_batch::token::token (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Token5TokenERR9CudaEventRKNSt6vectorIbEE"]], "tensorrt_llm::runtime::decoder_batch::token::active (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Token6activeE"]], "tensorrt_llm::runtime::decoder_batch::token::event (c++ member)": [[1, "_CPPv4N12tensorrt_llm7runtime13decoder_batch5Token5eventE"]], "tensorrt_llm::runtime::getdefaultbatchslots (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime20getDefaultBatchSlotsEN7runtime10SizeType32ERKN7runtime13BufferManagerE"]], "tensorrt_llm::runtime::operator<< (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK10LoraModule"], [1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK26LoraCachePageManagerConfig"], [1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7IBuffer"], [1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7ITensor"], [1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN7ITensor5ShapeE"], [1, "_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN9LoraCache21TaskLayerModuleConfigE"]], "tensorrt_llm::runtime::to_string (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime9to_stringERK26LoraCachePageManagerConfig"], [1, "_CPPv4N12tensorrt_llm7runtime9to_stringERKN9LoraCache21TaskLayerModuleConfigE"]], "tensorrt_llm::runtime::utils (c++ type)": [[1, "_CPPv4N12tensorrt_llm7runtime5utilsE"]], "tensorrt_llm::runtime::utils::loadengine (c++ function)": [[1, "_CPPv4N12tensorrt_llm7runtime5utils10loadEngineERKNSt6stringE"]], "buildcacheconfig (class in tensorrt_llm.hlapi)": [[39, "tensorrt_llm.hlapi.BuildCacheConfig"]], "buildconfig (class in tensorrt_llm.hlapi)": [[39, "tensorrt_llm.hlapi.BuildConfig"]], "capacityschedulerpolicy (class in tensorrt_llm.hlapi)": [[39, "tensorrt_llm.hlapi.CapacitySchedulerPolicy"]], "fp8 (tensorrt_llm.hlapi.quantalgo attribute)": [[39, "tensorrt_llm.hlapi.QuantAlgo.FP8"]], "fp8_per_channel_per_token (tensorrt_llm.hlapi.quantalgo attribute)": [[39, "tensorrt_llm.hlapi.QuantAlgo.FP8_PER_CHANNEL_PER_TOKEN"]], "guaranteed_no_evict (tensorrt_llm.hlapi.capacityschedulerpolicy attribute)": [[39, "tensorrt_llm.hlapi.CapacitySchedulerPolicy.GUARANTEED_NO_EVICT"]], "int8 (tensorrt_llm.hlapi.quantalgo attribute)": [[39, "tensorrt_llm.hlapi.QuantAlgo.INT8"]], "kvcacheconfig (class in tensorrt_llm.hlapi)": [[39, "tensorrt_llm.hlapi.KvCacheConfig"]], "llm (class in tensorrt_llm.hlapi)": [[39, "tensorrt_llm.hlapi.LLM"]], "max_utilization (tensorrt_llm.hlapi.capacityschedulerpolicy attribute)": [[39, "tensorrt_llm.hlapi.CapacitySchedulerPolicy.MAX_UTILIZATION"]], "quantalgo (class in tensorrt_llm.hlapi)": [[39, "tensorrt_llm.hlapi.QuantAlgo"]], "quantconfig (class in tensorrt_llm.hlapi)": [[39, "tensorrt_llm.hlapi.QuantConfig"]], "requestoutput (class in tensorrt_llm.hlapi)": [[39, "tensorrt_llm.hlapi.RequestOutput"]], "static_batch (tensorrt_llm.hlapi.capacityschedulerpolicy attribute)": [[39, "tensorrt_llm.hlapi.CapacitySchedulerPolicy.STATIC_BATCH"]], "samplingparams (class in tensorrt_llm.hlapi)": [[39, "tensorrt_llm.hlapi.SamplingParams"]], "schedulerconfig (class in tensorrt_llm.hlapi)": [[39, "tensorrt_llm.hlapi.SchedulerConfig"]], "w4a16 (tensorrt_llm.hlapi.quantalgo attribute)": [[39, "tensorrt_llm.hlapi.QuantAlgo.W4A16"]], "w4a16_awq (tensorrt_llm.hlapi.quantalgo attribute)": [[39, "tensorrt_llm.hlapi.QuantAlgo.W4A16_AWQ"]], "w4a16_gptq (tensorrt_llm.hlapi.quantalgo attribute)": [[39, "tensorrt_llm.hlapi.QuantAlgo.W4A16_GPTQ"]], "w4a8_awq (tensorrt_llm.hlapi.quantalgo attribute)": [[39, "tensorrt_llm.hlapi.QuantAlgo.W4A8_AWQ"]], "w8a16 (tensorrt_llm.hlapi.quantalgo attribute)": [[39, "tensorrt_llm.hlapi.QuantAlgo.W8A16"]], "w8a8_sq_per_channel (tensorrt_llm.hlapi.quantalgo attribute)": [[39, "tensorrt_llm.hlapi.QuantAlgo.W8A8_SQ_PER_CHANNEL"]], "w8a8_sq_per_channel_per_tensor_plugin (tensorrt_llm.hlapi.quantalgo attribute)": [[39, "tensorrt_llm.hlapi.QuantAlgo.W8A8_SQ_PER_CHANNEL_PER_TENSOR_PLUGIN"]], "w8a8_sq_per_channel_per_token_plugin (tensorrt_llm.hlapi.quantalgo attribute)": [[39, "tensorrt_llm.hlapi.QuantAlgo.W8A8_SQ_PER_CHANNEL_PER_TOKEN_PLUGIN"]], "w8a8_sq_per_tensor_per_token_plugin (tensorrt_llm.hlapi.quantalgo attribute)": [[39, "tensorrt_llm.hlapi.QuantAlgo.W8A8_SQ_PER_TENSOR_PER_TOKEN_PLUGIN"]], "w8a8_sq_per_tensor_plugin (tensorrt_llm.hlapi.quantalgo attribute)": [[39, "tensorrt_llm.hlapi.QuantAlgo.W8A8_SQ_PER_TENSOR_PLUGIN"]], "__init__() (tensorrt_llm.hlapi.buildcacheconfig method)": [[39, "tensorrt_llm.hlapi.BuildCacheConfig.__init__"]], "__init__() (tensorrt_llm.hlapi.buildconfig method)": [[39, "tensorrt_llm.hlapi.BuildConfig.__init__"]], "__init__() (tensorrt_llm.hlapi.capacityschedulerpolicy method)": [[39, "tensorrt_llm.hlapi.CapacitySchedulerPolicy.__init__"]], "__init__() (tensorrt_llm.hlapi.kvcacheconfig method)": [[39, "tensorrt_llm.hlapi.KvCacheConfig.__init__"]], "__init__() (tensorrt_llm.hlapi.llm method)": [[39, "tensorrt_llm.hlapi.LLM.__init__"]], "__init__() (tensorrt_llm.hlapi.quantconfig method)": [[39, "tensorrt_llm.hlapi.QuantConfig.__init__"]], "__init__() (tensorrt_llm.hlapi.requestoutput method)": [[39, "tensorrt_llm.hlapi.RequestOutput.__init__"]], "__init__() (tensorrt_llm.hlapi.samplingparams method)": [[39, "tensorrt_llm.hlapi.SamplingParams.__init__"]], "__init__() (tensorrt_llm.hlapi.schedulerconfig method)": [[39, "tensorrt_llm.hlapi.SchedulerConfig.__init__"]], "add_special_tokens (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.add_special_tokens"]], "auto_parallel_config (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.auto_parallel_config"]], "bad (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.bad"]], "bad_token_ids (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.bad_token_ids"]], "beam_search_diversity_rate (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.beam_search_diversity_rate"]], "beam_width (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.beam_width"]], "builder_opt (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.builder_opt"]], "cache_root (tensorrt_llm.hlapi.buildcacheconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildCacheConfig.cache_root"]], "cache_root (tensorrt_llm.hlapi.buildcacheconfig property)": [[39, "id0"]], "capacity_scheduler_policy (tensorrt_llm.hlapi.schedulerconfig property)": [[39, "tensorrt_llm.hlapi.SchedulerConfig.capacity_scheduler_policy"]], "clamp_val (tensorrt_llm.hlapi.quantconfig attribute)": [[39, "tensorrt_llm.hlapi.QuantConfig.clamp_val"]], "context_chunking_policy (tensorrt_llm.hlapi.schedulerconfig property)": [[39, "tensorrt_llm.hlapi.SchedulerConfig.context_chunking_policy"]], "dry_run (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.dry_run"]], "early_stopping (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.early_stopping"]], "embedding_bias (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.embedding_bias"]], "enable_block_reuse (tensorrt_llm.hlapi.kvcacheconfig property)": [[39, "tensorrt_llm.hlapi.KvCacheConfig.enable_block_reuse"]], "enable_debug_output (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.enable_debug_output"]], "end_id (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.end_id"]], "exclude_input_from_output (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.exclude_input_from_output"]], "exclude_modules (tensorrt_llm.hlapi.quantconfig attribute)": [[39, "tensorrt_llm.hlapi.QuantConfig.exclude_modules"]], "external_draft_tokens_config (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.external_draft_tokens_config"]], "force_num_profiles (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.force_num_profiles"]], "free_gpu_memory_fraction (tensorrt_llm.hlapi.kvcacheconfig property)": [[39, "tensorrt_llm.hlapi.KvCacheConfig.free_gpu_memory_fraction"]], "frequency_penalty (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.frequency_penalty"]], "from_dict() (tensorrt_llm.hlapi.buildconfig class method)": [[39, "tensorrt_llm.hlapi.BuildConfig.from_dict"]], "from_dict() (tensorrt_llm.hlapi.quantconfig class method)": [[39, "tensorrt_llm.hlapi.QuantConfig.from_dict"]], "from_json_file() (tensorrt_llm.hlapi.buildconfig class method)": [[39, "tensorrt_llm.hlapi.BuildConfig.from_json_file"]], "gather_context_logits (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.gather_context_logits"]], "gather_generation_logits (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.gather_generation_logits"]], "generate() (tensorrt_llm.hlapi.llm method)": [[39, "tensorrt_llm.hlapi.LLM.generate"]], "generate_async() (tensorrt_llm.hlapi.llm method)": [[39, "tensorrt_llm.hlapi.LLM.generate_async"]], "get_modelopt_kv_cache_dtype() (tensorrt_llm.hlapi.quantconfig method)": [[39, "tensorrt_llm.hlapi.QuantConfig.get_modelopt_kv_cache_dtype"]], "get_modelopt_qformat() (tensorrt_llm.hlapi.quantconfig method)": [[39, "tensorrt_llm.hlapi.QuantConfig.get_modelopt_qformat"]], "group_size (tensorrt_llm.hlapi.quantconfig attribute)": [[39, "tensorrt_llm.hlapi.QuantConfig.group_size"]], "handle_response() (tensorrt_llm.hlapi.requestoutput method)": [[39, "tensorrt_llm.hlapi.RequestOutput.handle_response"]], "has_zero_point (tensorrt_llm.hlapi.quantconfig attribute)": [[39, "tensorrt_llm.hlapi.QuantConfig.has_zero_point"]], "host_cache_size (tensorrt_llm.hlapi.kvcacheconfig property)": [[39, "tensorrt_llm.hlapi.KvCacheConfig.host_cache_size"]], "include_stop_str_in_output (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.include_stop_str_in_output"]], "input_timing_cache (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.input_timing_cache"]], "kv_cache_quant_algo (tensorrt_llm.hlapi.quantconfig attribute)": [[39, "tensorrt_llm.hlapi.QuantConfig.kv_cache_quant_algo"]], "kv_cache_type (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.kv_cache_type"]], "length_penalty (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.length_penalty"]], "logits_post_processor_name (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.logits_post_processor_name"]], "lora_config (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.lora_config"]], "max_attention_window (tensorrt_llm.hlapi.kvcacheconfig property)": [[39, "tensorrt_llm.hlapi.KvCacheConfig.max_attention_window"]], "max_batch_size (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.max_batch_size"]], "max_beam_width (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.max_beam_width"]], "max_cache_storage_gb (tensorrt_llm.hlapi.buildcacheconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildCacheConfig.max_cache_storage_gb"]], "max_cache_storage_gb (tensorrt_llm.hlapi.buildcacheconfig property)": [[39, "id1"]], "max_draft_len (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.max_draft_len"]], "max_encoder_input_len (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.max_encoder_input_len"]], "max_input_len (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.max_input_len"]], "max_new_tokens (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.max_new_tokens"]], "max_num_tokens (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.max_num_tokens"]], "max_prompt_embedding_table_size (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.max_prompt_embedding_table_size"]], "max_records (tensorrt_llm.hlapi.buildcacheconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildCacheConfig.max_records"]], "max_records (tensorrt_llm.hlapi.buildcacheconfig property)": [[39, "id2"]], "max_seq_len (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.max_seq_len"]], "max_tokens (tensorrt_llm.hlapi.kvcacheconfig property)": [[39, "tensorrt_llm.hlapi.KvCacheConfig.max_tokens"]], "max_tokens (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.max_tokens"]], "min_length (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.min_length"]], "min_tokens (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.min_tokens"]], "name (tensorrt_llm.hlapi.capacityschedulerpolicy property)": [[39, "tensorrt_llm.hlapi.CapacitySchedulerPolicy.name"]], "no_repeat_ngram_size (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.no_repeat_ngram_size"]], "onboard_blocks (tensorrt_llm.hlapi.kvcacheconfig property)": [[39, "tensorrt_llm.hlapi.KvCacheConfig.onboard_blocks"]], "opt_batch_size (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.opt_batch_size"]], "opt_num_tokens (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.opt_num_tokens"]], "output_timing_cache (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.output_timing_cache"]], "pad_id (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.pad_id"]], "plugin_config (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.plugin_config"]], "pre_quant_scale (tensorrt_llm.hlapi.quantconfig attribute)": [[39, "tensorrt_llm.hlapi.QuantConfig.pre_quant_scale"]], "presence_penalty (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.presence_penalty"]], "profiling_verbosity (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.profiling_verbosity"]], "prompt_tuning_config (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.prompt_tuning_config"]], "quant_algo (tensorrt_llm.hlapi.quantconfig attribute)": [[39, "tensorrt_llm.hlapi.QuantConfig.quant_algo"]], "quant_mode (tensorrt_llm.hlapi.quantconfig property)": [[39, "tensorrt_llm.hlapi.QuantConfig.quant_mode"]], "random_seed (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.random_seed"]], "repetition_penalty (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.repetition_penalty"]], "requires_calibration (tensorrt_llm.hlapi.quantconfig property)": [[39, "tensorrt_llm.hlapi.QuantConfig.requires_calibration"]], "requires_modelopt_quantization (tensorrt_llm.hlapi.quantconfig property)": [[39, "tensorrt_llm.hlapi.QuantConfig.requires_modelopt_quantization"]], "return_context_logits (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.return_context_logits"]], "return_encoder_output (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.return_encoder_output"]], "return_generation_logits (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.return_generation_logits"]], "return_log_probs (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.return_log_probs"]], "save() (tensorrt_llm.hlapi.llm method)": [[39, "tensorrt_llm.hlapi.LLM.save"]], "seed (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.seed"]], "setup() (tensorrt_llm.hlapi.samplingparams method)": [[39, "tensorrt_llm.hlapi.SamplingParams.setup"]], "sink_token_length (tensorrt_llm.hlapi.kvcacheconfig property)": [[39, "tensorrt_llm.hlapi.KvCacheConfig.sink_token_length"]], "smoothquant_val (tensorrt_llm.hlapi.quantconfig attribute)": [[39, "tensorrt_llm.hlapi.QuantConfig.smoothquant_val"]], "speculative_decoding_mode (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.speculative_decoding_mode"]], "stop (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.stop"]], "stop_token_ids (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.stop_token_ids"]], "strongly_typed (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.strongly_typed"]], "temperature (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.temperature"]], "to_dict() (tensorrt_llm.hlapi.buildconfig method)": [[39, "tensorrt_llm.hlapi.BuildConfig.to_dict"]], "to_dict() (tensorrt_llm.hlapi.quantconfig method)": [[39, "tensorrt_llm.hlapi.QuantConfig.to_dict"]], "tokenizer (tensorrt_llm.hlapi.llm property)": [[39, "tensorrt_llm.hlapi.LLM.tokenizer"]], "top_k (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.top_k"]], "top_p (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.top_p"]], "top_p_decay (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.top_p_decay"]], "top_p_min (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.top_p_min"]], "top_p_reset_ids (tensorrt_llm.hlapi.samplingparams attribute)": [[39, "tensorrt_llm.hlapi.SamplingParams.top_p_reset_ids"]], "update() (tensorrt_llm.hlapi.buildconfig method)": [[39, "tensorrt_llm.hlapi.BuildConfig.update"]], "update_from_dict() (tensorrt_llm.hlapi.buildconfig method)": [[39, "tensorrt_llm.hlapi.BuildConfig.update_from_dict"]], "update_kv_cache_type() (tensorrt_llm.hlapi.buildconfig method)": [[39, "tensorrt_llm.hlapi.BuildConfig.update_kv_cache_type"]], "use_fused_mlp (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.use_fused_mlp"]], "use_plugin_sq (tensorrt_llm.hlapi.quantconfig property)": [[39, "tensorrt_llm.hlapi.QuantConfig.use_plugin_sq"]], "use_refit (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.use_refit"]], "use_strip_plan (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.use_strip_plan"]], "value (tensorrt_llm.hlapi.capacityschedulerpolicy property)": [[39, "tensorrt_llm.hlapi.CapacitySchedulerPolicy.value"]], "visualize_network (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.visualize_network"]], "weight_sparsity (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.weight_sparsity"]], "weight_streaming (tensorrt_llm.hlapi.buildconfig attribute)": [[39, "tensorrt_llm.hlapi.BuildConfig.weight_streaming"]], "workspace (tensorrt_llm.hlapi.llm property)": [[39, "tensorrt_llm.hlapi.LLM.workspace"]], "auto (tensorrt_llm.functional.allreducestrategy attribute)": [[44, "tensorrt_llm.functional.AllReduceStrategy.AUTO"]], "allreduceconfig (class in tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.AllReduceConfig"]], "allreducefusionop (class in tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.AllReduceFusionOp"]], "allreducefusionparams (class in tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.AllReduceFusionParams"]], "allreducestrategy (class in tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.AllReduceStrategy"]], "attentionmasktype (class in tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.AttentionMaskType"]], "conditional (class in tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.Conditional"]], "dimrange (class in tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.DimRange"]], "fusedgatedmlp (tensorrt_llm.functional.mlptype attribute)": [[44, "tensorrt_llm.functional.MLPType.FusedGatedMLP"]], "gatedmlp (tensorrt_llm.functional.mlptype attribute)": [[44, "tensorrt_llm.functional.MLPType.GatedMLP"]], "groupnorm (tensorrt_llm.functional.layernormtype attribute)": [[44, "tensorrt_llm.functional.LayerNormType.GroupNorm"]], "layernorm (tensorrt_llm.functional.layernormtype attribute)": [[44, "tensorrt_llm.functional.LayerNormType.LayerNorm"]], "layernormpositiontype (class in tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.LayerNormPositionType"]], "layernormtype (class in tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.LayerNormType"]], "mlp (tensorrt_llm.functional.mlptype attribute)": [[44, "tensorrt_llm.functional.MLPType.MLP"]], "mlptype (class in tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.MLPType"]], "nccl (tensorrt_llm.functional.allreducestrategy attribute)": [[44, "tensorrt_llm.functional.AllReduceStrategy.NCCL"]], "none (tensorrt_llm.functional.allreducefusionop attribute)": [[44, "tensorrt_llm.functional.AllReduceFusionOp.NONE"]], "oneshot (tensorrt_llm.functional.allreducestrategy attribute)": [[44, "tensorrt_llm.functional.AllReduceStrategy.ONESHOT"]], "push_mode (tensorrt_llm.functional.allreduceconfig attribute)": [[44, "tensorrt_llm.functional.AllReduceConfig.PUSH_MODE"]], "positionembeddingtype (class in tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.PositionEmbeddingType"]], "residual_rms_norm (tensorrt_llm.functional.allreducefusionop attribute)": [[44, "tensorrt_llm.functional.AllReduceFusionOp.RESIDUAL_RMS_NORM"]], "rmsnorm (tensorrt_llm.functional.layernormtype attribute)": [[44, "tensorrt_llm.functional.LayerNormType.RmsNorm"]], "ropeembeddingutils (class in tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.RopeEmbeddingUtils"]], "rotaryscalingtype (class in tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.RotaryScalingType"]], "twoshot (tensorrt_llm.functional.allreducestrategy attribute)": [[44, "tensorrt_llm.functional.AllReduceStrategy.TWOSHOT"]], "tensor (class in tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.Tensor"]], "use_memcpy (tensorrt_llm.functional.allreduceconfig attribute)": [[44, "tensorrt_llm.functional.AllReduceConfig.USE_MEMCPY"]], "abs() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.abs"]], "abs() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.abs"]], "activation() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.activation"]], "add() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.add"]], "add_input() (tensorrt_llm.functional.conditional method)": [[44, "tensorrt_llm.functional.Conditional.add_input"]], "add_output() (tensorrt_llm.functional.conditional method)": [[44, "tensorrt_llm.functional.Conditional.add_output"]], "alibi (tensorrt_llm.functional.positionembeddingtype attribute)": [[44, "tensorrt_llm.functional.PositionEmbeddingType.alibi"]], "alibi_with_scale (tensorrt_llm.functional.positionembeddingtype attribute)": [[44, "tensorrt_llm.functional.PositionEmbeddingType.alibi_with_scale"]], "allgather() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.allgather"]], "allreduce() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.allreduce"]], "apply_llama3_scaling() (tensorrt_llm.functional.ropeembeddingutils static method)": [[44, "tensorrt_llm.functional.RopeEmbeddingUtils.apply_llama3_scaling"]], "apply_rotary_pos_emb() (tensorrt_llm.functional.ropeembeddingutils static method)": [[44, "tensorrt_llm.functional.RopeEmbeddingUtils.apply_rotary_pos_emb"]], "apply_rotary_pos_emb_chatglm() (tensorrt_llm.functional.ropeembeddingutils static method)": [[44, "tensorrt_llm.functional.RopeEmbeddingUtils.apply_rotary_pos_emb_chatglm"]], "apply_rotary_pos_emb_cogvlm() (tensorrt_llm.functional.ropeembeddingutils static method)": [[44, "tensorrt_llm.functional.RopeEmbeddingUtils.apply_rotary_pos_emb_cogvlm"]], "arange() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.arange"]], "argmax() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.argmax"]], "assertion() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.assertion"]], "avg_pool2d() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.avg_pool2d"]], "bert_attention() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.bert_attention"]], "bidirectional (tensorrt_llm.functional.attentionmasktype attribute)": [[44, "tensorrt_llm.functional.AttentionMaskType.bidirectional"]], "bidirectionalglm (tensorrt_llm.functional.attentionmasktype attribute)": [[44, "tensorrt_llm.functional.AttentionMaskType.bidirectionalglm"]], "blocksparse (tensorrt_llm.functional.attentionmasktype attribute)": [[44, "tensorrt_llm.functional.AttentionMaskType.blocksparse"]], "broadcast_helper() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.broadcast_helper"]], "cast() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.cast"]], "cast() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.cast"]], "categorical_sample() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.categorical_sample"]], "causal (tensorrt_llm.functional.attentionmasktype attribute)": [[44, "tensorrt_llm.functional.AttentionMaskType.causal"]], "chatglm (tensorrt_llm.functional.positionembeddingtype attribute)": [[44, "tensorrt_llm.functional.PositionEmbeddingType.chatglm"]], "choices() (tensorrt_llm.functional.positionembeddingtype static method)": [[44, "tensorrt_llm.functional.PositionEmbeddingType.choices"]], "chunk() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.chunk"]], "clip() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.clip"]], "concat() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.concat"]], "constant() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.constant"]], "constant_to_tensor_() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.constant_to_tensor_"]], "constants_to_tensors_() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.constants_to_tensors_"]], "conv1d() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.conv1d"]], "conv2d() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.conv2d"]], "conv_transpose2d() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.conv_transpose2d"]], "cos() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.cos"]], "create_allreduce_plugin() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.create_allreduce_plugin"]], "create_sinusoidal_positions() (tensorrt_llm.functional.ropeembeddingutils static method)": [[44, "tensorrt_llm.functional.RopeEmbeddingUtils.create_sinusoidal_positions"]], "create_sinusoidal_positions_for_attention_plugin() (tensorrt_llm.functional.ropeembeddingutils static method)": [[44, "tensorrt_llm.functional.RopeEmbeddingUtils.create_sinusoidal_positions_for_attention_plugin"]], "create_sinusoidal_positions_for_cogvlm_attention_plugin() (tensorrt_llm.functional.ropeembeddingutils static method)": [[44, "tensorrt_llm.functional.RopeEmbeddingUtils.create_sinusoidal_positions_for_cogvlm_attention_plugin"]], "create_sinusoidal_positions_long_rope() (tensorrt_llm.functional.ropeembeddingutils method)": [[44, "tensorrt_llm.functional.RopeEmbeddingUtils.create_sinusoidal_positions_long_rope"]], "cumsum() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.cumsum"]], "custom_mask (tensorrt_llm.functional.attentionmasktype attribute)": [[44, "tensorrt_llm.functional.AttentionMaskType.custom_mask"]], "div() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.div"]], "dtype (tensorrt_llm.functional.tensor property)": [[44, "tensorrt_llm.functional.Tensor.dtype"]], "dynamic (tensorrt_llm.functional.rotaryscalingtype attribute)": [[44, "tensorrt_llm.functional.RotaryScalingType.dynamic"]], "einsum() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.einsum"]], "elementwise_binary() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.elementwise_binary"]], "embedding() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.embedding"]], "eq() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.eq"]], "exp() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.exp"]], "expand() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.expand"]], "expand_dims() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.expand_dims"]], "expand_dims_like() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.expand_dims_like"]], "expand_mask() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.expand_mask"]], "flatten() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.flatten"]], "flatten() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.flatten"]], "flip() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.flip"]], "floordiv() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.floordiv"]], "from_string() (tensorrt_llm.functional.positionembeddingtype static method)": [[44, "tensorrt_llm.functional.PositionEmbeddingType.from_string"]], "from_string() (tensorrt_llm.functional.rotaryscalingtype static method)": [[44, "tensorrt_llm.functional.RotaryScalingType.from_string"]], "gather() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.gather"]], "gather_last_token_logits() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.gather_last_token_logits"]], "gather_nd() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.gather_nd"]], "gegelu() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.gegelu"]], "geglu() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.geglu"]], "gelu() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.gelu"]], "gemm_swiglu() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.gemm_swiglu"]], "generate_alibi_biases() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.generate_alibi_biases"]], "generate_alibi_slopes() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.generate_alibi_slopes"]], "get_parent() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.get_parent"]], "get_users() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.get_users"]], "gpt_attention() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.gpt_attention"]], "group_norm() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.group_norm"]], "gt() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.gt"]], "has_affine() (tensorrt_llm.functional.allreducefusionparams method)": [[44, "tensorrt_llm.functional.AllReduceFusionParams.has_affine"]], "has_bias() (tensorrt_llm.functional.allreducefusionparams method)": [[44, "tensorrt_llm.functional.AllReduceFusionParams.has_bias"]], "identity() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.identity"]], "index_select() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.index_select"]], "int_clip() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.int_clip"]], "interpolate() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.interpolate"]], "is_alibi() (tensorrt_llm.functional.positionembeddingtype method)": [[44, "tensorrt_llm.functional.PositionEmbeddingType.is_alibi"]], "is_dynamic() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.is_dynamic"]], "is_gated_activation() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.is_gated_activation"]], "is_rope() (tensorrt_llm.functional.positionembeddingtype method)": [[44, "tensorrt_llm.functional.PositionEmbeddingType.is_rope"]], "is_trt_wrapper() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.is_trt_wrapper"]], "layer_norm() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.layer_norm"]], "learned_absolute (tensorrt_llm.functional.positionembeddingtype attribute)": [[44, "tensorrt_llm.functional.PositionEmbeddingType.learned_absolute"]], "linear (tensorrt_llm.functional.rotaryscalingtype attribute)": [[44, "tensorrt_llm.functional.RotaryScalingType.linear"]], "llama3 (tensorrt_llm.functional.rotaryscalingtype attribute)": [[44, "tensorrt_llm.functional.RotaryScalingType.llama3"]], "location (tensorrt_llm.functional.tensor property)": [[44, "tensorrt_llm.functional.Tensor.location"]], "log() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.log"]], "log() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.log"]], "log_softmax() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.log_softmax"]], "long_rope (tensorrt_llm.functional.positionembeddingtype attribute)": [[44, "tensorrt_llm.functional.PositionEmbeddingType.long_rope"]], "longrope (tensorrt_llm.functional.rotaryscalingtype attribute)": [[44, "tensorrt_llm.functional.RotaryScalingType.longrope"]], "lora_plugin() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.lora_plugin"]], "low_latency_gemm() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.low_latency_gemm"]], "lt() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.lt"]], "mamba_conv1d() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.mamba_conv1d"]], "mark_output() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.mark_output"]], "masked_scatter() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.masked_scatter"]], "masked_select() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.masked_select"]], "matmul() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.matmul"]], "max() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.max"]], "max() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.max"]], "maximum() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.maximum"]], "mean() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.mean"]], "mean() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.mean"]], "min() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.min"]], "minimum() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.minimum"]], "module": [[44, "module-tensorrt_llm"], [44, "module-tensorrt_llm.functional"], [45, "module-tensorrt_llm"], [45, "module-tensorrt_llm.layers.activation"], [45, "module-tensorrt_llm.layers.attention"], [45, "module-tensorrt_llm.layers.cast"], [45, "module-tensorrt_llm.layers.conv"], [45, "module-tensorrt_llm.layers.embedding"], [45, "module-tensorrt_llm.layers.linear"], [45, "module-tensorrt_llm.layers.mlp"], [45, "module-tensorrt_llm.layers.normalization"], [45, "module-tensorrt_llm.layers.pooling"], [46, "module-tensorrt_llm"], [46, "module-tensorrt_llm.models"], [47, "module-tensorrt_llm"], [47, "module-tensorrt_llm.plugin"], [48, "module-tensorrt_llm"], [48, "module-tensorrt_llm.quantization"], [49, "module-tensorrt_llm"], [49, "module-tensorrt_llm.runtime"]], "modulo() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.modulo"]], "mul() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.mul"]], "name (tensorrt_llm.functional.tensor property)": [[44, "tensorrt_llm.functional.Tensor.name"]], "ndim() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.ndim"]], "network (tensorrt_llm.functional.tensor property)": [[44, "tensorrt_llm.functional.Tensor.network"]], "non_gated_version() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.non_gated_version"]], "none (tensorrt_llm.functional.rotaryscalingtype attribute)": [[44, "tensorrt_llm.functional.RotaryScalingType.none"]], "nonzero() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.nonzero"]], "not_op() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.not_op"]], "op_and() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.op_and"]], "op_or() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.op_or"]], "outer() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.outer"]], "padding (tensorrt_llm.functional.attentionmasktype attribute)": [[44, "tensorrt_llm.functional.AttentionMaskType.padding"]], "permute() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.permute"]], "permute() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.permute"]], "post_layernorm (tensorrt_llm.functional.layernormpositiontype attribute)": [[44, "tensorrt_llm.functional.LayerNormPositionType.post_layernorm"]], "pow() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.pow"]], "pre_layernorm (tensorrt_llm.functional.layernormpositiontype attribute)": [[44, "tensorrt_llm.functional.LayerNormPositionType.pre_layernorm"]], "prod() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.prod"]], "quick_gelu() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.quick_gelu"]], "rand() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.rand"]], "rank() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.rank"]], "recv() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.recv"]], "reduce() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.reduce"]], "relative (tensorrt_llm.functional.positionembeddingtype attribute)": [[44, "tensorrt_llm.functional.PositionEmbeddingType.relative"]], "relu() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.relu"]], "repeat_interleave() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.repeat_interleave"]], "replace_all_uses_with() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.replace_all_uses_with"]], "rg_lru() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.rg_lru"]], "rms_norm() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.rms_norm"]], "rope_gpt_neox (tensorrt_llm.functional.positionembeddingtype attribute)": [[44, "tensorrt_llm.functional.PositionEmbeddingType.rope_gpt_neox"]], "rope_gptj (tensorrt_llm.functional.positionembeddingtype attribute)": [[44, "tensorrt_llm.functional.PositionEmbeddingType.rope_gptj"]], "rotate_every_two() (tensorrt_llm.functional.ropeembeddingutils static method)": [[44, "tensorrt_llm.functional.RopeEmbeddingUtils.rotate_every_two"]], "rotate_half() (tensorrt_llm.functional.ropeembeddingutils static method)": [[44, "tensorrt_llm.functional.RopeEmbeddingUtils.rotate_half"]], "round() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.round"]], "scatter() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.scatter"]], "scatter_nd() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.scatter_nd"]], "select() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.select"]], "selective_scan() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.selective_scan"]], "send() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.send"]], "shape (tensorrt_llm.functional.tensor property)": [[44, "tensorrt_llm.functional.Tensor.shape"]], "shape() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.shape"]], "sigmoid() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.sigmoid"]], "silu() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.silu"]], "sin() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.sin"]], "size() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.size"]], "slice() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.slice"]], "sliding_window_causal (tensorrt_llm.functional.attentionmasktype attribute)": [[44, "tensorrt_llm.functional.AttentionMaskType.sliding_window_causal"]], "softmax() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.softmax"]], "softplus() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.softplus"]], "split() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.split"]], "split() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.split"]], "sqrt() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.sqrt"]], "sqrt() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.sqrt"]], "squared_relu() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.squared_relu"]], "squeeze() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.squeeze"]], "stack() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.stack"]], "sub() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.sub"]], "sum() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.sum"]], "swiglu() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.swiglu"]], "tanh() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.tanh"]], "tensorrt_llm": [[44, "module-tensorrt_llm"], [45, "module-tensorrt_llm"], [46, "module-tensorrt_llm"], [47, "module-tensorrt_llm"], [48, "module-tensorrt_llm"], [49, "module-tensorrt_llm"]], "tensorrt_llm.functional": [[44, "module-tensorrt_llm.functional"]], "topk() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.topk"]], "transpose() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.transpose"]], "transpose() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.transpose"]], "unary() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.unary"]], "unbind() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.unbind"]], "unbind() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.unbind"]], "unsqueeze() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.unsqueeze"]], "view() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.view"]], "view() (tensorrt_llm.functional.tensor method)": [[44, "tensorrt_llm.functional.Tensor.view"]], "where() (in module tensorrt_llm.functional)": [[44, "tensorrt_llm.functional.where"]], "attention (class in tensorrt_llm.layers.attention)": [[45, "tensorrt_llm.layers.attention.Attention"]], "attentionparams (class in tensorrt_llm.layers.attention)": [[45, "tensorrt_llm.layers.attention.AttentionParams"]], "avgpool2d (class in tensorrt_llm.layers.pooling)": [[45, "tensorrt_llm.layers.pooling.AvgPool2d"]], "bertattention (class in tensorrt_llm.layers.attention)": [[45, "tensorrt_llm.layers.attention.BertAttention"]], "blocksparseattnparams (class in tensorrt_llm.layers.attention)": [[45, "tensorrt_llm.layers.attention.BlockSparseAttnParams"]], "cast (class in tensorrt_llm.layers.cast)": [[45, "tensorrt_llm.layers.cast.Cast"]], "cogvlmattention (class in tensorrt_llm.layers.attention)": [[45, "tensorrt_llm.layers.attention.CogVLMAttention"]], "columnlinear (in module tensorrt_llm.layers.linear)": [[45, "tensorrt_llm.layers.linear.ColumnLinear"]], "conv1d (class in tensorrt_llm.layers.conv)": [[45, "tensorrt_llm.layers.conv.Conv1d"]], "conv2d (class in tensorrt_llm.layers.conv)": [[45, "tensorrt_llm.layers.conv.Conv2d"]], "convtranspose2d (class in tensorrt_llm.layers.conv)": [[45, "tensorrt_llm.layers.conv.ConvTranspose2d"]], "embedding (class in tensorrt_llm.layers.embedding)": [[45, "tensorrt_llm.layers.embedding.Embedding"]], "fusedgatedmlp (class in tensorrt_llm.layers.mlp)": [[45, "tensorrt_llm.layers.mlp.FusedGatedMLP"]], "gatedmlp (class in tensorrt_llm.layers.mlp)": [[45, "tensorrt_llm.layers.mlp.GatedMLP"]], "groupnorm (class in tensorrt_llm.layers.normalization)": [[45, "tensorrt_llm.layers.normalization.GroupNorm"]], "keyvaluecacheparams (class in tensorrt_llm.layers.attention)": [[45, "tensorrt_llm.layers.attention.KeyValueCacheParams"]], "layernorm (class in tensorrt_llm.layers.normalization)": [[45, "tensorrt_llm.layers.normalization.LayerNorm"]], "linear (class in tensorrt_llm.layers.linear)": [[45, "tensorrt_llm.layers.linear.Linear"]], "linearbase (class in tensorrt_llm.layers.linear)": [[45, "tensorrt_llm.layers.linear.LinearBase"]], "mlp (class in tensorrt_llm.layers.mlp)": [[45, "tensorrt_llm.layers.mlp.MLP"]], "mish (class in tensorrt_llm.layers.activation)": [[45, "tensorrt_llm.layers.activation.Mish"]], "prompttuningembedding (class in tensorrt_llm.layers.embedding)": [[45, "tensorrt_llm.layers.embedding.PromptTuningEmbedding"]], "rmsnorm (class in tensorrt_llm.layers.normalization)": [[45, "tensorrt_llm.layers.normalization.RmsNorm"]], "rowlinear (class in tensorrt_llm.layers.linear)": [[45, "tensorrt_llm.layers.linear.RowLinear"]], "specdecodingparams (class in tensorrt_llm.layers.attention)": [[45, "tensorrt_llm.layers.attention.SpecDecodingParams"]], "collect_and_bias() (tensorrt_llm.layers.linear.linear method)": [[45, "tensorrt_llm.layers.linear.Linear.collect_and_bias"]], "collect_and_bias() (tensorrt_llm.layers.linear.linearbase method)": [[45, "tensorrt_llm.layers.linear.LinearBase.collect_and_bias"]], "collect_and_bias() (tensorrt_llm.layers.linear.rowlinear method)": [[45, "tensorrt_llm.layers.linear.RowLinear.collect_and_bias"]], "compute_relative_bias() (in module tensorrt_llm.layers.attention)": [[45, "tensorrt_llm.layers.attention.compute_relative_bias"]], "create_attention_const_params() (tensorrt_llm.layers.attention.attention static method)": [[45, "tensorrt_llm.layers.attention.Attention.create_attention_const_params"]], "fc_gate() (tensorrt_llm.layers.mlp.fusedgatedmlp method)": [[45, "tensorrt_llm.layers.mlp.FusedGatedMLP.fc_gate"]], "fc_gate_lora() (in module tensorrt_llm.layers.mlp)": [[45, "tensorrt_llm.layers.mlp.fc_gate_lora"]], "fc_gate_plugin() (tensorrt_llm.layers.mlp.fusedgatedmlp method)": [[45, "tensorrt_llm.layers.mlp.FusedGatedMLP.fc_gate_plugin"]], "fill_attention_const_params_for_long_rope() (tensorrt_llm.layers.attention.attentionparams method)": [[45, "tensorrt_llm.layers.attention.AttentionParams.fill_attention_const_params_for_long_rope"]], "fill_attention_const_params_for_rope() (tensorrt_llm.layers.attention.attentionparams method)": [[45, "tensorrt_llm.layers.attention.AttentionParams.fill_attention_const_params_for_rope"]], "fill_attention_params() (tensorrt_llm.layers.attention.attention static method)": [[45, "tensorrt_llm.layers.attention.Attention.fill_attention_params"]], "fill_none_tensor_list() (tensorrt_llm.layers.attention.keyvaluecacheparams method)": [[45, "tensorrt_llm.layers.attention.KeyValueCacheParams.fill_none_tensor_list"]], "forward() (tensorrt_llm.layers.activation.mish method)": [[45, "tensorrt_llm.layers.activation.Mish.forward"]], "forward() (tensorrt_llm.layers.attention.attention method)": [[45, "tensorrt_llm.layers.attention.Attention.forward"]], "forward() (tensorrt_llm.layers.attention.bertattention method)": [[45, "tensorrt_llm.layers.attention.BertAttention.forward"]], "forward() (tensorrt_llm.layers.attention.cogvlmattention method)": [[45, "tensorrt_llm.layers.attention.CogVLMAttention.forward"]], "forward() (tensorrt_llm.layers.cast.cast method)": [[45, "tensorrt_llm.layers.cast.Cast.forward"]], "forward() (tensorrt_llm.layers.conv.conv1d method)": [[45, "tensorrt_llm.layers.conv.Conv1d.forward"]], "forward() (tensorrt_llm.layers.conv.conv2d method)": [[45, "tensorrt_llm.layers.conv.Conv2d.forward"]], "forward() (tensorrt_llm.layers.conv.convtranspose2d method)": [[45, "tensorrt_llm.layers.conv.ConvTranspose2d.forward"]], "forward() (tensorrt_llm.layers.embedding.embedding method)": [[45, "tensorrt_llm.layers.embedding.Embedding.forward"]], "forward() (tensorrt_llm.layers.embedding.prompttuningembedding method)": [[45, "tensorrt_llm.layers.embedding.PromptTuningEmbedding.forward"]], "forward() (tensorrt_llm.layers.linear.linearbase method)": [[45, "tensorrt_llm.layers.linear.LinearBase.forward"]], "forward() (tensorrt_llm.layers.mlp.fusedgatedmlp method)": [[45, "tensorrt_llm.layers.mlp.FusedGatedMLP.forward"]], "forward() (tensorrt_llm.layers.mlp.gatedmlp method)": [[45, "tensorrt_llm.layers.mlp.GatedMLP.forward"]], "forward() (tensorrt_llm.layers.mlp.mlp method)": [[45, "tensorrt_llm.layers.mlp.MLP.forward"]], "forward() (tensorrt_llm.layers.normalization.groupnorm method)": [[45, "tensorrt_llm.layers.normalization.GroupNorm.forward"]], "forward() (tensorrt_llm.layers.normalization.layernorm method)": [[45, "tensorrt_llm.layers.normalization.LayerNorm.forward"]], "forward() (tensorrt_llm.layers.normalization.rmsnorm method)": [[45, "tensorrt_llm.layers.normalization.RmsNorm.forward"]], "forward() (tensorrt_llm.layers.pooling.avgpool2d method)": [[45, "tensorrt_llm.layers.pooling.AvgPool2d.forward"]], "get_first_past_key_value() (tensorrt_llm.layers.attention.keyvaluecacheparams method)": [[45, "tensorrt_llm.layers.attention.KeyValueCacheParams.get_first_past_key_value"]], "get_weight() (tensorrt_llm.layers.linear.linearbase method)": [[45, "tensorrt_llm.layers.linear.LinearBase.get_weight"]], "is_valid() (tensorrt_llm.layers.attention.attentionparams method)": [[45, "tensorrt_llm.layers.attention.AttentionParams.is_valid"]], "is_valid() (tensorrt_llm.layers.attention.keyvaluecacheparams method)": [[45, "tensorrt_llm.layers.attention.KeyValueCacheParams.is_valid"]], "is_valid_cross_attn() (tensorrt_llm.layers.attention.attentionparams method)": [[45, "tensorrt_llm.layers.attention.AttentionParams.is_valid_cross_attn"]], "make_causal_mask() (in module tensorrt_llm.layers.attention)": [[45, "tensorrt_llm.layers.attention.make_causal_mask"]], "multiply_and_lora() (tensorrt_llm.layers.linear.linearbase method)": [[45, "tensorrt_llm.layers.linear.LinearBase.multiply_and_lora"]], "multiply_collect() (tensorrt_llm.layers.linear.linearbase method)": [[45, "tensorrt_llm.layers.linear.LinearBase.multiply_collect"]], "postprocess() (tensorrt_llm.layers.attention.attention method)": [[45, "tensorrt_llm.layers.attention.Attention.postprocess"]], "postprocess() (tensorrt_llm.layers.embedding.embedding method)": [[45, "tensorrt_llm.layers.embedding.Embedding.postprocess"]], "postprocess() (tensorrt_llm.layers.linear.linear method)": [[45, "tensorrt_llm.layers.linear.Linear.postprocess"]], "set_rel_attn_table() (tensorrt_llm.layers.attention.attention method)": [[45, "tensorrt_llm.layers.attention.Attention.set_rel_attn_table"]], "tensorrt_llm.layers.activation": [[45, "module-tensorrt_llm.layers.activation"]], "tensorrt_llm.layers.attention": [[45, "module-tensorrt_llm.layers.attention"]], "tensorrt_llm.layers.cast": [[45, "module-tensorrt_llm.layers.cast"]], "tensorrt_llm.layers.conv": [[45, "module-tensorrt_llm.layers.conv"]], "tensorrt_llm.layers.embedding": [[45, "module-tensorrt_llm.layers.embedding"]], "tensorrt_llm.layers.linear": [[45, "module-tensorrt_llm.layers.linear"]], "tensorrt_llm.layers.mlp": [[45, "module-tensorrt_llm.layers.mlp"]], "tensorrt_llm.layers.normalization": [[45, "module-tensorrt_llm.layers.normalization"]], "tensorrt_llm.layers.pooling": [[45, "module-tensorrt_llm.layers.pooling"]], "tp_split_dim() (tensorrt_llm.layers.linear.linear class method)": [[45, "tensorrt_llm.layers.linear.Linear.tp_split_dim"]], "tp_split_dim() (tensorrt_llm.layers.linear.linearbase class method)": [[45, "tensorrt_llm.layers.linear.LinearBase.tp_split_dim"]], "tp_split_dim() (tensorrt_llm.layers.linear.rowlinear class method)": [[45, "tensorrt_llm.layers.linear.RowLinear.tp_split_dim"]], "weight_is_kn() (tensorrt_llm.layers.linear.linearbase method)": [[45, "tensorrt_llm.layers.linear.LinearBase.weight_is_kn"]], "weight_loader() (tensorrt_llm.layers.embedding.embedding method)": [[45, "tensorrt_llm.layers.embedding.Embedding.weight_loader"]], "weight_loader() (tensorrt_llm.layers.linear.linearbase method)": [[45, "tensorrt_llm.layers.linear.LinearBase.weight_loader"]], "baichuanforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.BaichuanForCausalLM"]], "bertforquestionanswering (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.BertForQuestionAnswering"]], "bertforsequenceclassification (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.BertForSequenceClassification"]], "bertmodel (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.BertModel"]], "bloomforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.BloomForCausalLM"]], "bloommodel (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.BloomModel"]], "chatglmconfig (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.ChatGLMConfig"]], "chatglmforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.ChatGLMForCausalLM"]], "chatglmmodel (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.ChatGLMModel"]], "cogvlmconfig (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.CogVLMConfig"]], "cogvlmforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.CogVLMForCausalLM"]], "draft_tokens_external (tensorrt_llm.models.speculativedecodingmode attribute)": [[46, "tensorrt_llm.models.SpeculativeDecodingMode.DRAFT_TOKENS_EXTERNAL"]], "dbrxconfig (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.DbrxConfig"]], "dbrxforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.DbrxForCausalLM"]], "decodermodel (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.DecoderModel"]], "deepseekforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.DeepseekForCausalLM"]], "dit (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.DiT"]], "explicit_draft_tokens (tensorrt_llm.models.speculativedecodingmode attribute)": [[46, "tensorrt_llm.models.SpeculativeDecodingMode.EXPLICIT_DRAFT_TOKENS"]], "encodermodel (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.EncoderModel"]], "falconconfig (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.FalconConfig"]], "falconforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.FalconForCausalLM"]], "falconmodel (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.FalconModel"]], "gemma2_added_fields (tensorrt_llm.models.gemmaconfig attribute)": [[46, "tensorrt_llm.models.GemmaConfig.GEMMA2_ADDED_FIELDS"]], "gemma_added_fields (tensorrt_llm.models.gemmaconfig attribute)": [[46, "tensorrt_llm.models.GemmaConfig.GEMMA_ADDED_FIELDS"]], "gptconfig (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.GPTConfig"]], "gptforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.GPTForCausalLM"]], "gptjconfig (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.GPTJConfig"]], "gptjforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.GPTJForCausalLM"]], "gptjmodel (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.GPTJModel"]], "gptmodel (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.GPTModel"]], "gptneoxforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.GPTNeoXForCausalLM"]], "gptneoxmodel (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.GPTNeoXModel"]], "gemmaconfig (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.GemmaConfig"]], "gemmaforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.GemmaForCausalLM"]], "llamaconfig (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.LLaMAConfig"]], "llamaforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.LLaMAForCausalLM"]], "llamamodel (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.LLaMAModel"]], "lookahead_decoding (tensorrt_llm.models.speculativedecodingmode attribute)": [[46, "tensorrt_llm.models.SpeculativeDecodingMode.LOOKAHEAD_DECODING"]], "medusa (tensorrt_llm.models.speculativedecodingmode attribute)": [[46, "tensorrt_llm.models.SpeculativeDecodingMode.MEDUSA"]], "mptforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.MPTForCausalLM"]], "mptmodel (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.MPTModel"]], "mambaforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.MambaForCausalLM"]], "medusaconfig (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.MedusaConfig"]], "medusaforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.MedusaForCausalLm"]], "native_quant_flow (tensorrt_llm.models.gemmaforcausallm attribute)": [[46, "tensorrt_llm.models.GemmaForCausalLM.NATIVE_QUANT_FLOW"]], "none (tensorrt_llm.models.speculativedecodingmode attribute)": [[46, "tensorrt_llm.models.SpeculativeDecodingMode.NONE"]], "optforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.OPTForCausalLM"]], "optmodel (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.OPTModel"]], "phi3forcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.Phi3ForCausalLM"]], "phi3model (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.Phi3Model"]], "phiforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.PhiForCausalLM"]], "phimodel (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.PhiModel"]], "pretrainedconfig (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.PretrainedConfig"]], "pretrainedmodel (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.PretrainedModel"]], "redrafterforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.ReDrafterForCausalLM"]], "recurrentgemmaforcausallm (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.RecurrentGemmaForCausalLM"]], "speculativedecodingmode (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.SpeculativeDecodingMode"]], "verbatim (tensorrt_llm.models.gemmaconfig attribute)": [[46, "tensorrt_llm.models.GemmaConfig.VERBATIM"]], "whisperencoder (class in tensorrt_llm.models)": [[46, "tensorrt_llm.models.WhisperEncoder"]], "assert_valid_quant_algo() (tensorrt_llm.models.gemmaforcausallm class method)": [[46, "tensorrt_llm.models.GemmaForCausalLM.assert_valid_quant_algo"]], "check_config() (tensorrt_llm.models.decodermodel method)": [[46, "tensorrt_llm.models.DecoderModel.check_config"]], "check_config() (tensorrt_llm.models.dit method)": [[46, "tensorrt_llm.models.DiT.check_config"]], "check_config() (tensorrt_llm.models.encodermodel method)": [[46, "tensorrt_llm.models.EncoderModel.check_config"]], "check_config() (tensorrt_llm.models.falconforcausallm method)": [[46, "tensorrt_llm.models.FalconForCausalLM.check_config"]], "check_config() (tensorrt_llm.models.mptforcausallm method)": [[46, "tensorrt_llm.models.MPTForCausalLM.check_config"]], "check_config() (tensorrt_llm.models.optforcausallm method)": [[46, "tensorrt_llm.models.OPTForCausalLM.check_config"]], "check_config() (tensorrt_llm.models.phiforcausallm method)": [[46, "tensorrt_llm.models.PhiForCausalLM.check_config"]], "check_config() (tensorrt_llm.models.pretrainedmodel method)": [[46, "tensorrt_llm.models.PretrainedModel.check_config"]], "config_class (tensorrt_llm.models.baichuanforcausallm attribute)": [[46, "tensorrt_llm.models.BaichuanForCausalLM.config_class"]], "config_class (tensorrt_llm.models.chatglmforcausallm attribute)": [[46, "tensorrt_llm.models.ChatGLMForCausalLM.config_class"]], "config_class (tensorrt_llm.models.cogvlmforcausallm attribute)": [[46, "tensorrt_llm.models.CogVLMForCausalLM.config_class"]], "config_class (tensorrt_llm.models.dbrxforcausallm attribute)": [[46, "tensorrt_llm.models.DbrxForCausalLM.config_class"]], "config_class (tensorrt_llm.models.falconforcausallm attribute)": [[46, "tensorrt_llm.models.FalconForCausalLM.config_class"]], "config_class (tensorrt_llm.models.gptforcausallm attribute)": [[46, "tensorrt_llm.models.GPTForCausalLM.config_class"]], "config_class (tensorrt_llm.models.gptjforcausallm attribute)": [[46, "tensorrt_llm.models.GPTJForCausalLM.config_class"]], "config_class (tensorrt_llm.models.gemmaforcausallm attribute)": [[46, "tensorrt_llm.models.GemmaForCausalLM.config_class"]], "config_class (tensorrt_llm.models.llamaforcausallm attribute)": [[46, "tensorrt_llm.models.LLaMAForCausalLM.config_class"]], "config_class (tensorrt_llm.models.medusaforcausallm attribute)": [[46, "tensorrt_llm.models.MedusaForCausalLm.config_class"]], "config_class (tensorrt_llm.models.phi3forcausallm attribute)": [[46, "tensorrt_llm.models.Phi3ForCausalLM.config_class"]], "config_class (tensorrt_llm.models.phiforcausallm attribute)": [[46, "tensorrt_llm.models.PhiForCausalLM.config_class"]], "default_plugin_config() (tensorrt_llm.models.cogvlmforcausallm method)": [[46, "tensorrt_llm.models.CogVLMForCausalLM.default_plugin_config"]], "default_plugin_config() (tensorrt_llm.models.llamaforcausallm method)": [[46, "tensorrt_llm.models.LLaMAForCausalLM.default_plugin_config"]], "for_each_rank() (tensorrt_llm.models.pretrainedconfig method)": [[46, "tensorrt_llm.models.PretrainedConfig.for_each_rank"]], "forward() (tensorrt_llm.models.bertforquestionanswering method)": [[46, "tensorrt_llm.models.BertForQuestionAnswering.forward"]], "forward() (tensorrt_llm.models.bertforsequenceclassification method)": [[46, "tensorrt_llm.models.BertForSequenceClassification.forward"]], "forward() (tensorrt_llm.models.bertmodel method)": [[46, "tensorrt_llm.models.BertModel.forward"]], "forward() (tensorrt_llm.models.bloommodel method)": [[46, "tensorrt_llm.models.BloomModel.forward"]], "forward() (tensorrt_llm.models.chatglmmodel method)": [[46, "tensorrt_llm.models.ChatGLMModel.forward"]], "forward() (tensorrt_llm.models.decodermodel method)": [[46, "tensorrt_llm.models.DecoderModel.forward"]], "forward() (tensorrt_llm.models.dit method)": [[46, "tensorrt_llm.models.DiT.forward"]], "forward() (tensorrt_llm.models.encodermodel method)": [[46, "tensorrt_llm.models.EncoderModel.forward"]], "forward() (tensorrt_llm.models.falconmodel method)": [[46, "tensorrt_llm.models.FalconModel.forward"]], "forward() (tensorrt_llm.models.gptjmodel method)": [[46, "tensorrt_llm.models.GPTJModel.forward"]], "forward() (tensorrt_llm.models.gptmodel method)": [[46, "tensorrt_llm.models.GPTModel.forward"]], "forward() (tensorrt_llm.models.gptneoxmodel method)": [[46, "tensorrt_llm.models.GPTNeoXModel.forward"]], "forward() (tensorrt_llm.models.llamamodel method)": [[46, "tensorrt_llm.models.LLaMAModel.forward"]], "forward() (tensorrt_llm.models.mptmodel method)": [[46, "tensorrt_llm.models.MPTModel.forward"]], "forward() (tensorrt_llm.models.mambaforcausallm method)": [[46, "tensorrt_llm.models.MambaForCausalLM.forward"]], "forward() (tensorrt_llm.models.medusaforcausallm method)": [[46, "tensorrt_llm.models.MedusaForCausalLm.forward"]], "forward() (tensorrt_llm.models.optmodel method)": [[46, "tensorrt_llm.models.OPTModel.forward"]], "forward() (tensorrt_llm.models.phi3model method)": [[46, "tensorrt_llm.models.Phi3Model.forward"]], "forward() (tensorrt_llm.models.phimodel method)": [[46, "tensorrt_llm.models.PhiModel.forward"]], "forward() (tensorrt_llm.models.redrafterforcausallm method)": [[46, "tensorrt_llm.models.ReDrafterForCausalLM.forward"]], "forward() (tensorrt_llm.models.recurrentgemmaforcausallm method)": [[46, "tensorrt_llm.models.RecurrentGemmaForCausalLM.forward"]], "forward() (tensorrt_llm.models.whisperencoder method)": [[46, "tensorrt_llm.models.WhisperEncoder.forward"]], "forward_with_cfg() (tensorrt_llm.models.dit method)": [[46, "tensorrt_llm.models.DiT.forward_with_cfg"]], "forward_without_cfg() (tensorrt_llm.models.dit method)": [[46, "tensorrt_llm.models.DiT.forward_without_cfg"]], "from_arguments() (tensorrt_llm.models.speculativedecodingmode static method)": [[46, "tensorrt_llm.models.SpeculativeDecodingMode.from_arguments"]], "from_checkpoint() (tensorrt_llm.models.pretrainedconfig class method)": [[46, "tensorrt_llm.models.PretrainedConfig.from_checkpoint"]], "from_checkpoint() (tensorrt_llm.models.pretrainedmodel class method)": [[46, "tensorrt_llm.models.PretrainedModel.from_checkpoint"]], "from_config() (tensorrt_llm.models.pretrainedmodel class method)": [[46, "tensorrt_llm.models.PretrainedModel.from_config"]], "from_dict() (tensorrt_llm.models.pretrainedconfig class method)": [[46, "tensorrt_llm.models.PretrainedConfig.from_dict"]], "from_hugging_face() (tensorrt_llm.models.baichuanforcausallm class method)": [[46, "tensorrt_llm.models.BaichuanForCausalLM.from_hugging_face"]], "from_hugging_face() (tensorrt_llm.models.chatglmconfig class method)": [[46, "tensorrt_llm.models.ChatGLMConfig.from_hugging_face"]], "from_hugging_face() (tensorrt_llm.models.chatglmforcausallm class method)": [[46, "tensorrt_llm.models.ChatGLMForCausalLM.from_hugging_face"]], "from_hugging_face() (tensorrt_llm.models.cogvlmforcausallm class method)": [[46, "tensorrt_llm.models.CogVLMForCausalLM.from_hugging_face"]], "from_hugging_face() (tensorrt_llm.models.deepseekforcausallm class method)": [[46, "tensorrt_llm.models.DeepseekForCausalLM.from_hugging_face"]], "from_hugging_face() (tensorrt_llm.models.falconconfig class method)": [[46, "tensorrt_llm.models.FalconConfig.from_hugging_face"]], "from_hugging_face() (tensorrt_llm.models.falconforcausallm class method)": [[46, "tensorrt_llm.models.FalconForCausalLM.from_hugging_face"]], "from_hugging_face() (tensorrt_llm.models.gptconfig class method)": [[46, "tensorrt_llm.models.GPTConfig.from_hugging_face"]], "from_hugging_face() (tensorrt_llm.models.gptforcausallm class method)": [[46, "tensorrt_llm.models.GPTForCausalLM.from_hugging_face"]], "from_hugging_face() (tensorrt_llm.models.gptjconfig class method)": [[46, "tensorrt_llm.models.GPTJConfig.from_hugging_face"]], "from_hugging_face() (tensorrt_llm.models.gptjforcausallm class method)": [[46, "tensorrt_llm.models.GPTJForCausalLM.from_hugging_face"]], "from_hugging_face() (tensorrt_llm.models.gemmaconfig class method)": [[46, "tensorrt_llm.models.GemmaConfig.from_hugging_face"]], "from_hugging_face() (tensorrt_llm.models.gemmaforcausallm class method)": [[46, "tensorrt_llm.models.GemmaForCausalLM.from_hugging_face"]], "from_hugging_face() (tensorrt_llm.models.llamaconfig class method)": [[46, "tensorrt_llm.models.LLaMAConfig.from_hugging_face"]], "from_hugging_face() (tensorrt_llm.models.llamaforcausallm class method)": [[46, "tensorrt_llm.models.LLaMAForCausalLM.from_hugging_face"]], "from_hugging_face() (tensorrt_llm.models.phi3forcausallm class method)": [[46, "tensorrt_llm.models.Phi3ForCausalLM.from_hugging_face"]], "from_hugging_face() (tensorrt_llm.models.phiforcausallm class method)": [[46, "tensorrt_llm.models.PhiForCausalLM.from_hugging_face"]], "from_json_file() (tensorrt_llm.models.pretrainedconfig class method)": [[46, "tensorrt_llm.models.PretrainedConfig.from_json_file"]], "from_meta_ckpt() (tensorrt_llm.models.llamaconfig class method)": [[46, "tensorrt_llm.models.LLaMAConfig.from_meta_ckpt"]], "from_meta_ckpt() (tensorrt_llm.models.llamaforcausallm class method)": [[46, "tensorrt_llm.models.LLaMAForCausalLM.from_meta_ckpt"]], "from_nemo() (tensorrt_llm.models.gptconfig class method)": [[46, "tensorrt_llm.models.GPTConfig.from_nemo"]], "from_nemo() (tensorrt_llm.models.gptforcausallm class method)": [[46, "tensorrt_llm.models.GPTForCausalLM.from_nemo"]], "gemma2_config() (tensorrt_llm.models.gemmaconfig method)": [[46, "tensorrt_llm.models.GemmaConfig.gemma2_config"]], "get_config_group() (tensorrt_llm.models.pretrainedconfig method)": [[46, "tensorrt_llm.models.PretrainedConfig.get_config_group"]], "has_config_group() (tensorrt_llm.models.pretrainedconfig method)": [[46, "tensorrt_llm.models.PretrainedConfig.has_config_group"]], "is_gemma_2 (tensorrt_llm.models.gemmaconfig property)": [[46, "tensorrt_llm.models.GemmaConfig.is_gemma_2"]], "kv_dtype (tensorrt_llm.models.pretrainedconfig property)": [[46, "tensorrt_llm.models.PretrainedConfig.kv_dtype"]], "load() (tensorrt_llm.models.pretrainedmodel method)": [[46, "tensorrt_llm.models.PretrainedModel.load"]], "precompute_relative_attention_bias() (tensorrt_llm.models.decodermodel method)": [[46, "tensorrt_llm.models.DecoderModel.precompute_relative_attention_bias"]], "precompute_relative_attention_bias() (tensorrt_llm.models.encodermodel method)": [[46, "tensorrt_llm.models.EncoderModel.precompute_relative_attention_bias"]], "precompute_relative_attention_bias() (tensorrt_llm.models.whisperencoder method)": [[46, "tensorrt_llm.models.WhisperEncoder.precompute_relative_attention_bias"]], "prepare_inputs() (tensorrt_llm.models.chatglmforcausallm method)": [[46, "tensorrt_llm.models.ChatGLMForCausalLM.prepare_inputs"]], "prepare_inputs() (tensorrt_llm.models.decodermodel method)": [[46, "tensorrt_llm.models.DecoderModel.prepare_inputs"]], "prepare_inputs() (tensorrt_llm.models.dit method)": [[46, "tensorrt_llm.models.DiT.prepare_inputs"]], "prepare_inputs() (tensorrt_llm.models.encodermodel method)": [[46, "tensorrt_llm.models.EncoderModel.prepare_inputs"]], "prepare_inputs() (tensorrt_llm.models.mambaforcausallm method)": [[46, "tensorrt_llm.models.MambaForCausalLM.prepare_inputs"]], "prepare_inputs() (tensorrt_llm.models.medusaforcausallm method)": [[46, "tensorrt_llm.models.MedusaForCausalLm.prepare_inputs"]], "prepare_inputs() (tensorrt_llm.models.pretrainedmodel method)": [[46, "tensorrt_llm.models.PretrainedModel.prepare_inputs"]], "prepare_inputs() (tensorrt_llm.models.redrafterforcausallm method)": [[46, "tensorrt_llm.models.ReDrafterForCausalLM.prepare_inputs"]], "prepare_inputs() (tensorrt_llm.models.recurrentgemmaforcausallm method)": [[46, "tensorrt_llm.models.RecurrentGemmaForCausalLM.prepare_inputs"]], "prepare_inputs() (tensorrt_llm.models.whisperencoder method)": [[46, "tensorrt_llm.models.WhisperEncoder.prepare_inputs"]], "prepare_recurrent_inputs() (tensorrt_llm.models.recurrentgemmaforcausallm method)": [[46, "tensorrt_llm.models.RecurrentGemmaForCausalLM.prepare_recurrent_inputs"]], "quant_mode (tensorrt_llm.models.pretrainedconfig property)": [[46, "tensorrt_llm.models.PretrainedConfig.quant_mode"]], "quantize() (tensorrt_llm.models.baichuanforcausallm class method)": [[46, "tensorrt_llm.models.BaichuanForCausalLM.quantize"]], "quantize() (tensorrt_llm.models.chatglmforcausallm class method)": [[46, "tensorrt_llm.models.ChatGLMForCausalLM.quantize"]], "quantize() (tensorrt_llm.models.cogvlmforcausallm class method)": [[46, "tensorrt_llm.models.CogVLMForCausalLM.quantize"]], "quantize() (tensorrt_llm.models.gptforcausallm class method)": [[46, "tensorrt_llm.models.GPTForCausalLM.quantize"]], "quantize() (tensorrt_llm.models.gemmaforcausallm class method)": [[46, "tensorrt_llm.models.GemmaForCausalLM.quantize"]], "quantize() (tensorrt_llm.models.llamaforcausallm class method)": [[46, "tensorrt_llm.models.LLaMAForCausalLM.quantize"]], "quantize() (tensorrt_llm.models.pretrainedmodel class method)": [[46, "tensorrt_llm.models.PretrainedModel.quantize"]], "release() (tensorrt_llm.models.pretrainedmodel method)": [[46, "tensorrt_llm.models.PretrainedModel.release"]], "save_checkpoint() (tensorrt_llm.models.pretrainedmodel method)": [[46, "tensorrt_llm.models.PretrainedModel.save_checkpoint"]], "set_if_not_exist() (tensorrt_llm.models.pretrainedconfig method)": [[46, "tensorrt_llm.models.PretrainedConfig.set_if_not_exist"]], "set_rank() (tensorrt_llm.models.pretrainedconfig method)": [[46, "tensorrt_llm.models.PretrainedConfig.set_rank"]], "tensorrt_llm.models": [[46, "module-tensorrt_llm.models"]], "to_dict() (tensorrt_llm.models.chatglmconfig method)": [[46, "tensorrt_llm.models.ChatGLMConfig.to_dict"]], "to_dict() (tensorrt_llm.models.cogvlmconfig method)": [[46, "tensorrt_llm.models.CogVLMConfig.to_dict"]], "to_dict() (tensorrt_llm.models.dbrxconfig method)": [[46, "tensorrt_llm.models.DbrxConfig.to_dict"]], "to_dict() (tensorrt_llm.models.falconconfig method)": [[46, "tensorrt_llm.models.FalconConfig.to_dict"]], "to_dict() (tensorrt_llm.models.gptconfig method)": [[46, "tensorrt_llm.models.GPTConfig.to_dict"]], "to_dict() (tensorrt_llm.models.gptjconfig method)": [[46, "tensorrt_llm.models.GPTJConfig.to_dict"]], "to_dict() (tensorrt_llm.models.gemmaconfig method)": [[46, "tensorrt_llm.models.GemmaConfig.to_dict"]], "to_dict() (tensorrt_llm.models.llamaconfig method)": [[46, "tensorrt_llm.models.LLaMAConfig.to_dict"]], "to_dict() (tensorrt_llm.models.medusaconfig method)": [[46, "tensorrt_llm.models.MedusaConfig.to_dict"]], "to_dict() (tensorrt_llm.models.pretrainedconfig method)": [[46, "tensorrt_llm.models.PretrainedConfig.to_dict"]], "to_json_file() (tensorrt_llm.models.pretrainedconfig method)": [[46, "tensorrt_llm.models.PretrainedConfig.to_json_file"]], "unpatchify() (tensorrt_llm.models.dit method)": [[46, "tensorrt_llm.models.DiT.unpatchify"]], "use_lora() (tensorrt_llm.models.decodermodel method)": [[46, "tensorrt_llm.models.DecoderModel.use_lora"]], "use_lora() (tensorrt_llm.models.encodermodel method)": [[46, "tensorrt_llm.models.EncoderModel.use_lora"]], "use_lora() (tensorrt_llm.models.gptforcausallm method)": [[46, "tensorrt_llm.models.GPTForCausalLM.use_lora"]], "use_lora() (tensorrt_llm.models.llamaforcausallm method)": [[46, "tensorrt_llm.models.LLaMAForCausalLM.use_lora"]], "use_lora() (tensorrt_llm.models.phi3forcausallm method)": [[46, "tensorrt_llm.models.Phi3ForCausalLM.use_lora"]], "use_prompt_tuning() (tensorrt_llm.models.encodermodel method)": [[46, "tensorrt_llm.models.EncoderModel.use_prompt_tuning"]], "pluginconfig (class in tensorrt_llm.plugin)": [[47, "tensorrt_llm.plugin.PluginConfig"]], "tensorrt_llm.plugin": [[47, "module-tensorrt_llm.plugin"]], "to_legacy_setting() (tensorrt_llm.plugin.pluginconfig method)": [[47, "tensorrt_llm.plugin.PluginConfig.to_legacy_setting"]], "quantalgo (class in tensorrt_llm.quantization)": [[48, "tensorrt_llm.quantization.QuantAlgo"]], "quantmode (class in tensorrt_llm.quantization)": [[48, "tensorrt_llm.quantization.QuantMode"]], "quantize_and_export() (in module tensorrt_llm.quantization)": [[48, "tensorrt_llm.quantization.quantize_and_export"]], "tensorrt_llm.quantization": [[48, "module-tensorrt_llm.quantization"]], "chatglmgenerationsession (class in tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.ChatGLMGenerationSession"]], "encdecmodelrunner (class in tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.EncDecModelRunner"]], "generationsequence (class in tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.GenerationSequence"]], "generationsession (class in tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.GenerationSession"]], "kvcachemanager (class in tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.KVCacheManager"]], "logitsprocessor (class in tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.LogitsProcessor"]], "logitsprocessorlist (class in tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.LogitsProcessorList"]], "modelconfig (class in tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.ModelConfig"]], "modelrunner (class in tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.ModelRunner"]], "modelrunnercpp (class in tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.ModelRunnerCpp"]], "multimodalmodelrunner (class in tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner"]], "qwenforcausallmgenerationsession (class in tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.QWenForCausalLMGenerationSession"]], "samplingconfig (class in tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.SamplingConfig"]], "session (class in tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.Session"]], "stoppingcriteria (class in tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.StoppingCriteria"]], "stoppingcriterialist (class in tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.StoppingCriteriaList"]], "tensorinfo (class in tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.TensorInfo"]], "add_sequence() (tensorrt_llm.runtime.kvcachemanager method)": [[49, "tensorrt_llm.runtime.KVCacheManager.add_sequence"]], "bad_words_list (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.bad_words_list"]], "batch_size (tensorrt_llm.runtime.generationsession attribute)": [[49, "tensorrt_llm.runtime.GenerationSession.batch_size"]], "beam_search_diversity_rate (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.beam_search_diversity_rate"]], "buffer_allocated (tensorrt_llm.runtime.generationsession attribute)": [[49, "tensorrt_llm.runtime.GenerationSession.buffer_allocated"]], "context (tensorrt_llm.runtime.session property)": [[49, "tensorrt_llm.runtime.Session.context"]], "context_mem_size (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.context_mem_size"]], "context_mem_size (tensorrt_llm.runtime.session property)": [[49, "tensorrt_llm.runtime.Session.context_mem_size"]], "conv_kernel (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.conv_kernel"]], "conv_kernel (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.conv_kernel"]], "cross_attention (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.cross_attention"]], "cross_attention (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.cross_attention"]], "cuda_graph_mode (tensorrt_llm.runtime.generationsession attribute)": [[49, "tensorrt_llm.runtime.GenerationSession.cuda_graph_mode"]], "cuda_stream_guard() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.cuda_stream_guard"]], "debug_mode (tensorrt_llm.runtime.generationsession attribute)": [[49, "tensorrt_llm.runtime.GenerationSession.debug_mode"]], "debug_tensors_to_save (tensorrt_llm.runtime.generationsession attribute)": [[49, "tensorrt_llm.runtime.GenerationSession.debug_tensors_to_save"]], "decode() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.decode"]], "decode_batch() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.decode_batch"]], "decode_regular() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.decode_regular"]], "decode_stream() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.decode_stream"]], "decode_words_list() (in module tensorrt_llm.runtime)": [[49, "tensorrt_llm.runtime.decode_words_list"]], "device (tensorrt_llm.runtime.generationsession attribute)": [[49, "tensorrt_llm.runtime.GenerationSession.device"]], "dtype (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.dtype"]], "dtype (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.dtype"]], "dtype (tensorrt_llm.runtime.modelrunner property)": [[49, "tensorrt_llm.runtime.ModelRunner.dtype"]], "dtype (tensorrt_llm.runtime.modelrunnercpp property)": [[49, "tensorrt_llm.runtime.ModelRunnerCpp.dtype"]], "dtype (tensorrt_llm.runtime.tensorinfo attribute)": [[49, "tensorrt_llm.runtime.TensorInfo.dtype"]], "dump_debug_buffers() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.dump_debug_buffers"]], "early_stop_criteria() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.early_stop_criteria"]], "early_stopping (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.early_stopping"]], "encoder_run() (tensorrt_llm.runtime.encdecmodelrunner method)": [[49, "tensorrt_llm.runtime.EncDecModelRunner.encoder_run"]], "end_id (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.end_id"]], "engine (tensorrt_llm.runtime.session property)": [[49, "tensorrt_llm.runtime.Session.engine"]], "engine_inspector (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.engine_inspector"]], "filter_medusa_logits() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.filter_medusa_logits"]], "finalize_decoder() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.finalize_decoder"]], "find_best_medusa_path() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.find_best_medusa_path"]], "first_layer (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.first_layer"]], "frequency_penalty (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.frequency_penalty"]], "from_dir() (tensorrt_llm.runtime.modelrunner class method)": [[49, "tensorrt_llm.runtime.ModelRunner.from_dir"]], "from_dir() (tensorrt_llm.runtime.modelrunnercpp class method)": [[49, "tensorrt_llm.runtime.ModelRunnerCpp.from_dir"]], "from_engine() (tensorrt_llm.runtime.encdecmodelrunner class method)": [[49, "tensorrt_llm.runtime.EncDecModelRunner.from_engine"]], "from_engine() (tensorrt_llm.runtime.modelrunner class method)": [[49, "tensorrt_llm.runtime.ModelRunner.from_engine"]], "from_engine() (tensorrt_llm.runtime.session static method)": [[49, "tensorrt_llm.runtime.Session.from_engine"]], "from_serialized_engine() (tensorrt_llm.runtime.session static method)": [[49, "tensorrt_llm.runtime.Session.from_serialized_engine"]], "gather_context_logits (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.gather_context_logits"]], "gather_context_logits (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.gather_context_logits"]], "gather_context_logits (tensorrt_llm.runtime.modelrunner property)": [[49, "tensorrt_llm.runtime.ModelRunner.gather_context_logits"]], "gather_context_logits (tensorrt_llm.runtime.modelrunnercpp property)": [[49, "tensorrt_llm.runtime.ModelRunnerCpp.gather_context_logits"]], "gather_generation_logits (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.gather_generation_logits"]], "gather_generation_logits (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.gather_generation_logits"]], "gather_generation_logits (tensorrt_llm.runtime.modelrunner property)": [[49, "tensorrt_llm.runtime.ModelRunner.gather_generation_logits"]], "gather_generation_logits (tensorrt_llm.runtime.modelrunnercpp property)": [[49, "tensorrt_llm.runtime.ModelRunnerCpp.gather_generation_logits"]], "generate() (tensorrt_llm.runtime.encdecmodelrunner method)": [[49, "tensorrt_llm.runtime.EncDecModelRunner.generate"]], "generate() (tensorrt_llm.runtime.modelrunner method)": [[49, "tensorrt_llm.runtime.ModelRunner.generate"]], "generate() (tensorrt_llm.runtime.modelrunnercpp method)": [[49, "tensorrt_llm.runtime.ModelRunnerCpp.generate"]], "generate() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.generate"]], "generate() (tensorrt_llm.runtime.qwenforcausallmgenerationsession method)": [[49, "tensorrt_llm.runtime.QWenForCausalLMGenerationSession.generate"]], "get_batch_idx() (tensorrt_llm.runtime.generationsequence method)": [[49, "tensorrt_llm.runtime.GenerationSequence.get_batch_idx"]], "get_block_offsets() (tensorrt_llm.runtime.kvcachemanager method)": [[49, "tensorrt_llm.runtime.KVCacheManager.get_block_offsets"]], "get_next_medusa_tokens() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.get_next_medusa_tokens"]], "get_num_heads_kv() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.get_num_heads_kv"]], "get_seq_idx() (tensorrt_llm.runtime.generationsequence method)": [[49, "tensorrt_llm.runtime.GenerationSequence.get_seq_idx"]], "get_visual_features() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.get_visual_features"]], "gpt_attention_plugin (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.gpt_attention_plugin"]], "gpu_weights_percent (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.gpu_weights_percent"]], "handle_per_step() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.handle_per_step"]], "has_position_embedding (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.has_position_embedding"]], "has_position_embedding (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.has_position_embedding"]], "has_token_type_embedding (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.has_token_type_embedding"]], "has_token_type_embedding (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.has_token_type_embedding"]], "head_size (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.head_size"]], "head_size (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.head_size"]], "hidden_size (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.hidden_size"]], "hidden_size (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.hidden_size"]], "hidden_size (tensorrt_llm.runtime.modelrunner property)": [[49, "tensorrt_llm.runtime.ModelRunner.hidden_size"]], "hidden_size (tensorrt_llm.runtime.modelrunnercpp property)": [[49, "tensorrt_llm.runtime.ModelRunnerCpp.hidden_size"]], "infer_shapes() (tensorrt_llm.runtime.session method)": [[49, "tensorrt_llm.runtime.Session.infer_shapes"]], "init_image_encoder() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.init_image_encoder"]], "init_llm() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.init_llm"]], "init_tokenizer() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.init_tokenizer"]], "is_medusa_mode (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.is_medusa_mode"]], "is_redrafter_mode (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.is_redrafter_mode"]], "kv_cache_type (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.kv_cache_type"]], "kv_cache_type (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.kv_cache_type"]], "last_layer (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.last_layer"]], "layer_types (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.layer_types"]], "length_penalty (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.length_penalty"]], "load_test_image() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.load_test_image"]], "locate_accepted_draft_tokens() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.locate_accepted_draft_tokens"]], "lora_plugin (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.lora_plugin"]], "lora_target_modules (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.lora_target_modules"]], "mamba_conv1d_plugin (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.mamba_conv1d_plugin"]], "mapping (tensorrt_llm.runtime.generationsession attribute)": [[49, "tensorrt_llm.runtime.GenerationSession.mapping"]], "mapping (tensorrt_llm.runtime.modelrunner property)": [[49, "tensorrt_llm.runtime.ModelRunner.mapping"]], "max_attention_window_size (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.max_attention_window_size"]], "max_batch_size (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.max_batch_size"]], "max_beam_width (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.max_beam_width"]], "max_draft_tokens (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.max_draft_tokens"]], "max_medusa_tokens (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.max_medusa_tokens"]], "max_new_tokens (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.max_new_tokens"]], "max_prompt_embedding_table_size (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.max_prompt_embedding_table_size"]], "max_prompt_embedding_table_size (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.max_prompt_embedding_table_size"]], "max_prompt_embedding_table_size (tensorrt_llm.runtime.modelrunner property)": [[49, "tensorrt_llm.runtime.ModelRunner.max_prompt_embedding_table_size"]], "max_prompt_embedding_table_size (tensorrt_llm.runtime.modelrunnercpp property)": [[49, "tensorrt_llm.runtime.ModelRunnerCpp.max_prompt_embedding_table_size"]], "max_sequence_length (tensorrt_llm.runtime.modelrunner property)": [[49, "tensorrt_llm.runtime.ModelRunner.max_sequence_length"]], "max_sequence_length (tensorrt_llm.runtime.modelrunnercpp property)": [[49, "tensorrt_llm.runtime.ModelRunnerCpp.max_sequence_length"]], "medusa_decode_and_verify() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.medusa_decode_and_verify"]], "medusa_paths (tensorrt_llm.runtime.generationsession attribute)": [[49, "tensorrt_llm.runtime.GenerationSession.medusa_paths"]], "medusa_position_offsets (tensorrt_llm.runtime.generationsession attribute)": [[49, "tensorrt_llm.runtime.GenerationSession.medusa_position_offsets"]], "medusa_temperature (tensorrt_llm.runtime.generationsession attribute)": [[49, "tensorrt_llm.runtime.GenerationSession.medusa_temperature"]], "medusa_topks (tensorrt_llm.runtime.generationsession attribute)": [[49, "tensorrt_llm.runtime.GenerationSession.medusa_topks"]], "medusa_tree_ids (tensorrt_llm.runtime.generationsession attribute)": [[49, "tensorrt_llm.runtime.GenerationSession.medusa_tree_ids"]], "min_length (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.min_length"]], "model_name (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.model_name"]], "name (tensorrt_llm.runtime.tensorinfo attribute)": [[49, "tensorrt_llm.runtime.TensorInfo.name"]], "next_medusa_input_ids() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.next_medusa_input_ids"]], "no_repeat_ngram_size (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.no_repeat_ngram_size"]], "num_beams (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.num_beams"]], "num_draft_tokens (tensorrt_llm.runtime.generationsession attribute)": [[49, "tensorrt_llm.runtime.GenerationSession.num_draft_tokens"]], "num_heads (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.num_heads"]], "num_heads (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.num_heads"]], "num_heads (tensorrt_llm.runtime.modelrunner property)": [[49, "tensorrt_llm.runtime.ModelRunner.num_heads"]], "num_heads (tensorrt_llm.runtime.modelrunnercpp property)": [[49, "tensorrt_llm.runtime.ModelRunnerCpp.num_heads"]], "num_kv_heads (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.num_kv_heads"]], "num_kv_heads_per_layer (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.num_kv_heads_per_layer"]], "num_layers (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.num_layers"]], "num_layers (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.num_layers"]], "num_layers (tensorrt_llm.runtime.modelrunner property)": [[49, "tensorrt_llm.runtime.ModelRunner.num_layers"]], "num_layers (tensorrt_llm.runtime.modelrunnercpp property)": [[49, "tensorrt_llm.runtime.ModelRunnerCpp.num_layers"]], "num_medusa_heads (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.num_medusa_heads"]], "num_medusa_heads (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.num_medusa_heads"]], "output_cum_log_probs (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.output_cum_log_probs"]], "output_log_probs (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.output_log_probs"]], "output_sequence_lengths (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.output_sequence_lengths"]], "pad_id (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.pad_id"]], "paged_kv_cache (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.paged_kv_cache"]], "paged_state (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.paged_state"]], "paged_state (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.paged_state"]], "pp_communicate_final_output_ids() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.pp_communicate_final_output_ids"]], "pp_communicate_new_tokens() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.pp_communicate_new_tokens"]], "prepare_position_ids_for_cogvlm() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.prepare_position_ids_for_cogvlm"]], "preprocess() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.preprocess"]], "presence_penalty (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.presence_penalty"]], "process_input() (tensorrt_llm.runtime.encdecmodelrunner method)": [[49, "tensorrt_llm.runtime.EncDecModelRunner.process_input"]], "process_logits_including_draft() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.process_logits_including_draft"]], "profiler (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.profiler"]], "ptuning_setup() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.ptuning_setup"]], "ptuning_setup_fuyu() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.ptuning_setup_fuyu"]], "ptuning_setup_llava_next() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.ptuning_setup_llava_next"]], "ptuning_setup_phi3() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.ptuning_setup_phi3"]], "quant_mode (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.quant_mode"]], "quant_mode (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.quant_mode"]], "random_seed (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.random_seed"]], "redrafter_draft_len_per_beam (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.redrafter_draft_len_per_beam"]], "redrafter_num_beams (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.redrafter_num_beams"]], "remove_input_padding (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.remove_input_padding"]], "remove_input_padding (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.remove_input_padding"]], "remove_input_padding (tensorrt_llm.runtime.modelrunner property)": [[49, "tensorrt_llm.runtime.ModelRunner.remove_input_padding"]], "remove_input_padding (tensorrt_llm.runtime.modelrunnercpp property)": [[49, "tensorrt_llm.runtime.ModelRunnerCpp.remove_input_padding"]], "reorder_kv_cache_for_beam_search() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.reorder_kv_cache_for_beam_search"]], "repetition_penalty (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.repetition_penalty"]], "return_dict (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.return_dict"]], "rnn_conv_dim_size (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.rnn_conv_dim_size"]], "rnn_conv_dim_size (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.rnn_conv_dim_size"]], "rnn_head_size (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.rnn_head_size"]], "rnn_head_size (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.rnn_head_size"]], "rnn_hidden_size (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.rnn_hidden_size"]], "rnn_hidden_size (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.rnn_hidden_size"]], "run() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.run"]], "run() (tensorrt_llm.runtime.session method)": [[49, "tensorrt_llm.runtime.Session.run"]], "runtime (tensorrt_llm.runtime.generationsession attribute)": [[49, "tensorrt_llm.runtime.GenerationSession.runtime"]], "runtime (tensorrt_llm.runtime.session property)": [[49, "tensorrt_llm.runtime.Session.runtime"]], "serialize_engine() (tensorrt_llm.runtime.modelrunner method)": [[49, "tensorrt_llm.runtime.ModelRunner.serialize_engine"]], "set_shapes() (tensorrt_llm.runtime.session method)": [[49, "tensorrt_llm.runtime.Session.set_shapes"]], "setup() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.setup"]], "setup_fake_prompts() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.setup_fake_prompts"]], "setup_fake_prompts_vila() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.setup_fake_prompts_vila"]], "setup_inputs() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.setup_inputs"]], "shape (tensorrt_llm.runtime.tensorinfo attribute)": [[49, "tensorrt_llm.runtime.TensorInfo.shape"]], "sink_token_length (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.sink_token_length"]], "skip_cross_qkv (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.skip_cross_qkv"]], "split_prompt_by_images() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.split_prompt_by_images"]], "state_dtype (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.state_dtype"]], "state_dtype (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.state_dtype"]], "state_size (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.state_size"]], "state_size (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.state_size"]], "step() (tensorrt_llm.runtime.kvcachemanager method)": [[49, "tensorrt_llm.runtime.KVCacheManager.step"]], "stop_words_list (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.stop_words_list"]], "temperature (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.temperature"]], "tensorrt_llm.runtime": [[49, "module-tensorrt_llm.runtime"]], "tokenizer_image_token() (tensorrt_llm.runtime.multimodalmodelrunner static method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.tokenizer_image_token"]], "tokens_per_block (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.tokens_per_block"]], "tokens_per_block (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.tokens_per_block"]], "top_k (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.top_k"]], "top_p (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.top_p"]], "top_p_decay (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.top_p_decay"]], "top_p_min (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.top_p_min"]], "top_p_reset_ids (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.top_p_reset_ids"]], "trtllm_modules_to_hf_modules (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.trtllm_modules_to_hf_modules"]], "update() (tensorrt_llm.runtime.samplingconfig method)": [[49, "tensorrt_llm.runtime.SamplingConfig.update"]], "update_output_ids_by_offset() (tensorrt_llm.runtime.generationsession method)": [[49, "tensorrt_llm.runtime.GenerationSession.update_output_ids_by_offset"]], "use_beam_hyps (tensorrt_llm.runtime.samplingconfig attribute)": [[49, "tensorrt_llm.runtime.SamplingConfig.use_beam_hyps"]], "use_gpt_attention_plugin (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.use_gpt_attention_plugin"]], "use_kv_cache (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.use_kv_cache"]], "use_lora_plugin (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.use_lora_plugin"]], "use_lora_plugin (tensorrt_llm.runtime.modelrunner property)": [[49, "tensorrt_llm.runtime.ModelRunner.use_lora_plugin"]], "use_mamba_conv1d_plugin (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.use_mamba_conv1d_plugin"]], "video_preprocess() (tensorrt_llm.runtime.multimodalmodelrunner method)": [[49, "tensorrt_llm.runtime.MultimodalModelRunner.video_preprocess"]], "vocab_size (tensorrt_llm.runtime.generationsession property)": [[49, "tensorrt_llm.runtime.GenerationSession.vocab_size"]], "vocab_size (tensorrt_llm.runtime.modelconfig attribute)": [[49, "tensorrt_llm.runtime.ModelConfig.vocab_size"]], "vocab_size (tensorrt_llm.runtime.modelrunner property)": [[49, "tensorrt_llm.runtime.ModelRunner.vocab_size"]], "vocab_size (tensorrt_llm.runtime.modelrunnercpp property)": [[49, "tensorrt_llm.runtime.ModelRunnerCpp.vocab_size"]], "vocab_size_padded (tensorrt_llm.runtime.modelrunner property)": [[49, "tensorrt_llm.runtime.ModelRunner.vocab_size_padded"]], "vocab_size_padded (tensorrt_llm.runtime.modelrunnercpp property)": [[49, "tensorrt_llm.runtime.ModelRunnerCpp.vocab_size_padded"]]}})