* Reduce memory usage in fused moe op associated with AutoTuning.
* Replace pre-defined bucket size strategy with a generating function based on the tune_max_num_tokens.
* Add free_memory logic of workspace in min_latency_mode fused moe path.
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
* Fix fused_moe fallback issue. (#3652)
min_latency_mode is only set to False during warmup phase. Thus when it becomes true during inference, all tactics fall back to the default one and thus cause perf regression.
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
---------
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
* add space in test output
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* perf: reduce executor lock scope
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: Move TokenRangeRetentionConfig implementation to cpp file
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* fix: Improve finished steps handling for external draft tokens
- Fixed a bug where the whole finished steps tensor was being zeroes instead of the slices.
- Replaced the creation of a temporary tensor for finished steps with a direct slice from the input tensor, improving efficiency and readability.
- Updated the tensor management logic to streamline the process of setting zero values for finished steps during batch processing.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* chore: Clean up includes
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
---------
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* add pip scripts dir to path
* move nvrtc_wrapper to conan
* support building nvrtc wrapper from source
---------
Signed-off-by: Tyler Burt <195370667+tburt-nv@users.noreply.github.com>
* fix: Fixing issue with first gen token being returned twice with streaming
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
* Fixing not_expectring_strings in test
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
---------
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
Co-authored-by: QI JUN <22017000+QiJune@users.noreply.github.com>
No change of default value (still ON).
These were hidden cmake vars before that patch.
Fix issue #3289
Signed-off-by: William Tambellini <wtambellini@sdl.com>
Co-authored-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
* Add numNodes to ParallelConfig
If not provided, attempt to find the number of nodes by
adding the number of local ranks 0
Update device IDs check accordingly
Signed-off-by: Aurelien Chartier <achartier@nvidia.com>
* Add ParallelConfig pickle test
Signed-off-by: Aurelien Chartier <achartier@nvidia.com>
---------
Signed-off-by: Aurelien Chartier <achartier@nvidia.com>
* refactor: batch slot management in decoder classes
- Changed `forwardBatchSlots` from a single `TensorPtr` to a `std::vector<TensorPtr>` in `decoderBuffers.h` and updated its initialization in `decoderBuffers.cpp`.
- Updated `batchSlots` in `iGptDecoderBatched.h` to a `std::vector<TensorPtr>` for better handling of batch sizes.
- Modified `mBatchSlotsDecoder` in `statefulGptDecoderBatched.h` to use a `std::vector<TensorPtr>` and adjusted its initialization in `statefulGptDecoderBatched.cpp`.
- Ensured proper reshaping of tensors in the setup methods to accommodate the new vector structure.
These changes enhance flexibility in managing tensor buffers across different batch sizes.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: Setup batch slots outside of the decoder
- Refactored batch slot management to utilize `makeBatchSlots`, enhancing clarity and functionality in batch processing.
- Introduced `DecoderState` to `MakeDecodingBatchInputOutput` for improved state handling during decoding.
- Updated the `operator()` method to include `decoderState` as a parameter, facilitating better integration with the decoding process.
- Modified related tests to accommodate changes in batch slot handling and ensure proper functionality.
These updates improve the overall structure and efficiency of the decoding process in the batch manager.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: Enhance decoder input structure with maxDecodingEngineTokens
- Updated the `Input` class in `iGptDecoderBatched.h` to include a new parameter `maxDecodingEngineTokens` for better control over decoding limits.
- Modified the `MakeDecodingBatchInputOutput` algorithm to compute the maximum number of decoding tokens based on active slots.
- Adjusted the `GptDecoderBatched` class to utilize the new `maxDecodingEngineTokens` parameter, improving clarity in token management during decoding.
- Updated Python bindings to reflect changes in the `Input` class constructor.
- Enhanced tests to ensure proper handling of the new parameter.
These changes improve the flexibility and efficiency of the decoding process in the batch manager.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: Streamline decoder input creation and batch slot management
- Introduced a new function `createDecoderInputs` to encapsulate the logic for creating decoder inputs, improving code organization.
- Updated the `operator()` method to utilize the new `createDecoderInputs` function, simplifying the decoding input setup process.
- Removed the `maxOfActiveSlots` template function to streamline the logic for determining the maximum number of active decoding engine tokens.
- Introduced a direct calculation of `maxActiveDecodingEngineTokens` within the `createDecoderInputs` function, enhancing clarity and reducing complexity.
These changes enhance the maintainability and readability of the decoding process in the batch manager.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: Update logits handling in decoder batch
- Modified the `decoder_batch::Input` to accept a vector of vectors for logits, enhancing flexibility in tensor management.
- Adjusted the `createDecoderInputs` function to accommodate the new logits structure, ensuring proper batch processing.
- Updated Python bindings to reflect changes in the `Input` class constructor, maintaining compatibility with existing interfaces.
- Refactored the `GptDecoderBatched` and `StatefulGptDecoderBatched` classes to utilize the updated logits structure, improving clarity in tensor slicing and batch size management.
- Enhanced tests to validate the new input structure and ensure correct functionality across various decoding scenarios.
These changes streamline the decoding process and improve the overall maintainability of the codebase.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: Rename maxDecodingEngineTokens to maxDecoderSteps
- Updated the `Input` class in `iGptDecoderBatched.h` to rename `maxDecodingEngineTokens` to `maxDecoderSteps` for improved clarity.
- Adjusted the `createDecoderInputs` function to reflect the new naming, ensuring consistency in the decoding process.
- Modified the `GptDecoderBatched` class to utilize `maxDecoderSteps` in its logic, enhancing readability and maintainability.
- Updated Python bindings to expose the renamed parameter, maintaining compatibility with existing interfaces.
These changes enhance the clarity of the decoding parameters and improve the overall structure of the codebase.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: remove usage of `active` vector from prepareForward
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: Removed the `active` vector from `decoder_batch::Input`
- Removed the `active` vector from the `Input` class constructor in `iGptDecoderBatched.h`, streamlining the input handling for decoding.
- Updated the `createDecoderInputs` function and related tests to reflect the changes in the `Input` class, ensuring compatibility and maintaining functionality.
- Adjusted Python bindings to accommodate the new constructor signature, enhancing clarity in the interface.
These changes improve the maintainability and readability of the decoding process in the batch manager.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: remove usage of `active` vector from gptDecoderBatchedTest
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: Unify the creation of decoder batch inputs in algorithm and tests
- Added a new static method `createDecoderBatchInputs` to streamline the creation of decoder batch inputs, enhancing clarity and maintainability.
- Updated the implementation to utilize active slots directly, simplifying the logic for managing batch slots and logits.
- Refactored the `operator()` method to leverage the new input creation function, ensuring compatibility with existing decoding processes.
- Enhanced tests to validate the new input handling approach, ensuring correct functionality across various scenarios.
These changes improve the overall structure and readability of the decoding process in the batch manager.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: remove usage of active vector from createDecoderBatchInputs
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: Update maxDecoderSteps calculation
- Replaced integer division with `common::ceilDiv` for calculating `maxDecoderSteps` and `numDecoderSteps`, ensuring correct handling of token counts.
These changes enhance the robustness of the decoding batch input creation process.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
---------
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: remove cumLogProbs and logProbs from DecoderBuffers
- Eliminated cumLogProbs and logProbs from DecoderBuffers, streamlining the buffer management.
- Updated related code in decoderBuffers.cpp and bindings.cpp to reflect these changes, ensuring that only host pointers are used for log probabilities.
These modifications enhance code clarity and maintainability by reducing redundancy in buffer management.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: streamline sequence length handling in GptDecoderBatched and StatefulGptDecoderBatched
- Updated GptDecoderBatched to directly use output.sequenceLengths for lengths assignment, removing unnecessary reshaping.
- Adjusted StatefulGptDecoderBatched to ensure sequence lengths are correctly shaped based on actual batch size and max beam width.
These changes enhance clarity and maintainability in the decoding process.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: integrate DecoderState for sequence length management in decoding process
- Updated DecoderBuffers to remove direct handling of sequence lengths, now utilizing DecoderState for this purpose.
- Adjusted MakeDecodingBatchInputOutput to accept DecoderState, enhancing clarity in the decoding input/output management.
- Refactored GptDecoderBatched and StatefulGptDecoderBatched to streamline sequence length handling, ensuring consistency across the decoding workflow.
refactor: update SlotDecoderBuffers to manage sequence lengths directly
- Introduced sequenceLengths and sequenceLengthsHost to SlotDecoderBuffers for better management of sequence lengths.
- Refactored asyncSend and recv methods to utilize the new sequenceLengths member, enhancing clarity and reducing redundancy.
- Updated TrtGptModelInflightBatching to align with the new structure, ensuring consistent handling of sequence lengths across the decoding process.
These changes improve maintainability and streamline the decoding workflow.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: Delegate to asyncSend method in SlotDecoderBuffers
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
---------
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: Update ExecutorConfig to use AdditionalModelOutput type
- Changed function signatures and member variables across multiple files to replace std::optional<std::vector<std::string>> with std::optional<std::vector<executor::AdditionalModelOutput>> to include gatherContext flag for each additional output.
- Updated related serialization and deserialization methods to accommodate the new type.
- Adjusted tests to reflect the changes in the output handling structure.
This refactor enhances the flexibility and maintainability of the output configuration in the executor and batch manager components.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: Remove equality operator from TrtGptModelOptionalParams
- Deleted the operator== implementation from TrtGptModelOptionalParams to simplify the class.
- Updated the pybind11 bindings to remove the exposure of the equality operator to Python.
This change streamlines the class definition and reduces unnecessary complexity in the bindings.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: Enhance copyAdditionalOutputs to utilize AdditionalModelOutput
- Updated the copyAdditionalOutputs function to accept a vector of AdditionalModelOutput, allowing for the inclusion of the gatherContext flag.
- Adjusted the logic to handle context and non-context outputs separately, improving the output handling mechanism.
- Modified related unit tests to incorporate the new gatherContext parameter, ensuring comprehensive testing of the updated functionality.
This refactor improves the flexibility and clarity of output management in the batch processing workflow.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: Introduce findOutputTensor utility function for output tensor retrieval
- Added a new utility function, findOutputTensor, to encapsulate the logic for finding output tensors and checking their validity.
- Refactored copyAdditionalOutputs to utilize findOutputTensor, reducing code duplication and improving clarity.
- Enhanced error checking for additional context and generation output tensors.
This change streamlines the output tensor retrieval process, enhancing maintainability and readability in the batch processing workflow.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* refactor: Check final indices of additional output tensors and update tests
- Added checks to verify the final indices of additional output tensors for context and generation outputs.
- Updated unit tests to verify the changes.
- Add lastTokenIds input tensor to test engines.
- Logits output depends on gatherContextLogits parameter.
- Removed gatherContextOutputs parameter from the validate method in LlmRequest.
- Context outputs do not depend on computeContextLogits parameter.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* fixup! refactor: Check final indices of additional output tensors and update tests
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* fixup! refactor: Update ExecutorConfig to use AdditionalModelOutput type
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* fixup! refactor: Remove equality operator from TrtGptModelOptionalParams
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* docs: Update executor.md
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* chore: Clean up includes
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
---------
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* One of the tactic is not supported during dispatch.
* final_hidden_states should be unpacked if it is not min_latency_mode.
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
* feat: Add NVFP4 UB pattern optimization pass in torch compile
* Add an additional flag for UB fp4 pattern to avoid inverse the scale
* Add NVFP4 related UB patterns
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
* Update atol, some points fails for B200 umbriel.
Signed-off-by: liji-nv <59594262+liji-nv@users.noreply.github.com>
---------
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
Signed-off-by: liji-nv <59594262+liji-nv@users.noreply.github.com>
* feat: trtllm-gen fp4 GEMM
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
* Clean up
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
* Remove incorrect header
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
* Reviewer comment
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
---------
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
* Instead of allocating UserBuffers at beginning of runtime, UB buffers
are now managed with global allocator. The allocator will dynamically
assign free UB buffer or allocate new buffer for torch tensor. It makes
userbuffers easier to use.
* In common usecase, the Userbuffers will be allocated correctly during
warm up stage. There is no dynamic allocation during inference.
* UB fusion pattern is rewroten using the new UB Allocator. It contains
following passes:
1. Fuse Quant with allreduce, replace with UB impl, and insert a
copy_to_userbuffers. Currently the normal allreduce still does not
support FP8 quant. So this need to be done in UB pass
2. Convert all supported allreduce with UB and insert copy_to_userbuffers.
3. Fuse op before ar with the copy_to_userbuffers. So the op directly
writes to the userbuffer
4. Remove userbuffers finalize if the output is connect to another UB
allreduce.
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
* Several optimizations and fixings on the Autotuner.
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
* Apply the new Python side Autotuner on current linear for nvFP4 data type.
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
* Apply the new Python side Autotuner on MoE op
* Remove routers from cache key to improve inference perf
* Prevent unnecessary code profiling. Use do_preparation keyword to select which part should be executed during before evaluating any tactic.
* Remove try-catch inside moe profiling process.
* Move default tactic -1 to 0 transforms in cpp runner.
* Revise relavant tests.
* Predefined the bucketizing strategy for fused_moe
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
* Add specific_profile support for AutoTuner to bypass the standard cache search process for perf optimization
* Add specific_profile for moe
* Add specific profile for linear
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
* Fixing and revising according to reviewer's suggestions.
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
* Use lru_cache for inference pref optimization.
* Revert gen_custom_cache_key feature
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
* Replace runner with runner id to achieve a serializable cache.
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
* Code clean up and minor fixings.
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
* Move all tunable runners and custom ops into torch_custom_ops.
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
* Treat min_latency_mode as a independent dynamic tensor. Modify get_valid_tactics to suit for it.
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
---------
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
* feat: Add option to run disaggregated serving without ctx servers, to benchmark gen only
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
* Fixing comment in sanity check
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
---------
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
* fp8 kv + bf16 ctx MLA + fp8 gen MLA
Use BF16 for context MLA.
mFP8GenerationMLA and mFP8ContextFMHA shouldn't be enabled together.
Allow mSM==90 for mFP8GenerationMLA==true.
For FMHA, dataTypeKv should be FP8.
For FP8 MLA generation, the output is still in BF16.
Refine debug info for FMHA kernel metadata.
Use inputType, outputType, SM together to hash kernel list.
Add FP8 MLA generation FMHA kernel.
Special WAR of NUM_COMPUTE_GROUPS for MLA generation kernel.
Separate the implementation of fused_multihead_attention_v2.h to CPP and print some debug info if checkIfKernelExist fails.
Refine debug info in fused_multihead_attention_v2.cpp
Correct FP8 MLA metadata.
New kernel provided by Yuxin, which outputs BF16.
smem size is not set correctly, which will lead to illegal mem access.
Yuxin fixed the error in FMHA MLA kernel: previously the BF16 isn't correctly written: some parts are repeatedly written, while some others are untouched.
There are two bmm1 scales that should be set correctly.
New kernel generated by Yuxin.
Modificatiosn to common/attentionOp for FP8 MLA on Hopper using FMHA.
Not necessary. If mFP8GenerationMLA, is_fp8_out is false, so mFP8ContextFMHA is false.
Skip a check in fmhaDispatcher.
Modifications in fmhaRunner:
- Debug dump.
- if (!isFP8GenerationMLA) skips a lot of flag setting.
- TMA descriptor modification for qo (by Yuxin).
Cleanup debug output.
Clean up o tma descriptor modifications.
Signed-off-by: Bo Li <bobboli0202@gmail.com>
* Resolve conflicts.
Signed-off-by: Bo Li <bobboli0202@gmail.com>
* Apply the patch of FP8 FlashMLA and resolve conflicts.
Signed-off-by: Bo Li <bobboli0202@gmail.com>
* Fix compilation error.
Signed-off-by: Bo Li <bobboli0202@gmail.com>
* Fix compile error.
Signed-off-by: Bo Li <bobboli0202@gmail.com>
* pick blackwell support
Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>
* Add copyright notice to fused_multihead_attention_v2.cpp.
Signed-off-by: Bo Li <bobboli0202@gmail.com>
* Add license.
Signed-off-by: Bo Li <bobboli0202@gmail.com>
* Add missing license.
Signed-off-by: Bo Li <bobboli0202@gmail.com>
* Exclude building flashMLA kernels under sm90.
Signed-off-by: Bo Li <bobboli0202@gmail.com>
* Revert "Exclude building flashMLA kernels under sm90."
This reverts commit f0c859d459.
Signed-off-by: Bo Li <bobboli0202@gmail.com>
* Use macro to skip compiling FlashMLA for non sm90 targets.
Signed-off-by: Bo Li <bobboli0202@gmail.com>
---------
Signed-off-by: Bo Li <bobboli0202@gmail.com>
Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>
Co-authored-by: Dylan Chen <ziqingc@nvidia.com>
Co-authored-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>
Co-authored-by: QI JUN <22017000+QiJune@users.noreply.github.com>
* refactor: Expose DecoderState via bindings and integrate in TRTLLMDecoder
- Introduced a new `DecoderState` class in the C++ bindings, encapsulating key functionalities for managing decoding state.
- Adjusted the Python `TRTLLMDecoder` to access properties from `decoder_state`, ensuring consistency and clarity in the decoding process.
These changes streamline the decoder's architecture and enhance maintainability.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* chore: Remove unused new_tokens from DecoderState bindings
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
---------
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* init trtllm attn no cache
Signed-off-by: Qixiang Lin <qixiangl@nvidia.com>
* fix: fix the seq_len issue and attn metadata prepare for qwen reward model test
fix: fix minor bugs after rebase
Signed-off-by: Qixiang Lin <qixiangl@nvidia.com>
* refactor: remove unnecessary debug logs and clean up commented code
refactor: update max_seq_len documentation and remove max_seq_len for decoder model contructor in PyTorchModelEngine
Signed-off-by: Qixiang Lin <qixiangl@nvidia.com>
* refactor: update calculate_ref_result function to accept tensor inputs and mask type, enhance test_attention_no_cache to support FULL and CAUSAL masks
Signed-off-by: Qixiang Lin <qixiangl@nvidia.com>
* refactor: remove unused BERT attention metadata conversion method and add type assertion for no cache attention in PyTorchModelEngine
Signed-off-by: Qixiang Lin <qixiangl@nvidia.com>
* refactor: remove use_kv_cache parameter from attention function and related classes, update documentation for KV cache handling
Signed-off-by: Qixiang Lin <qixiangl@nvidia.com>
* refactor: implement setAttentionMaskType method for better mask type handling and remove unused conversion function
Signed-off-by: Qixiang Lin <qixiangl@nvidia.com>
* refactor: streamline KV cache handling by replacing direct member access with useKVCache method and simplify token per block assignment
remove Debug code.
Signed-off-by: Qixiang Lin <qixiangl@nvidia.com>
* refactor: Resolve comments for Python code
Simplify no cache attention metadata preparation and streamline related attributes in TrtllmAttentionMetadata
Removed the private method for converting to no cache attention metadata and integrated its logic into the prepare method. Updated the test for BERT sequence classification to reflect these changes and ensure proper handling of attention metadata.
Signed-off-by: Qixiang Lin <qixiangl@nvidia.com>
* docs: Add is_dummy_attention field to attention metadata for simulation operations
Signed-off-by: Qixiang Lin <qixiangl@nvidia.com>
* refactor: add KVCacheParams to attention backend interface and import relevant metadata classes
Updated the attention backend interface to include KVCacheParams and imported TrtllmAttentionMetadata and VanillaAttentionMetadata in model_engine.py for enhanced functionality.
Signed-off-by: Qixiang Lin <qixiangl@nvidia.com>
* fix: fix rebase format issue
Signed-off-by: Qixiang Lin <qixiangl@nvidia.com>
* fix: extend attention mask type handling in MHARunnerFixedParams
Added support for additional attention mask types (BIDIRECTIONAL, BIDIRECTIONALGLM, BLOCKSPARSE) in the MHARunnerFixedParams structure to fix the mapping issue between ContextAttentionMaskType and AttentionMaskType
Signed-off-by: Qixiang Lin <qixiangl@nvidia.com>
* fix: enhance attention mask type handling in TllmGenFmhaRunnerParams
Updated the setAttentionMaskType method to include a switch-case structure for better handling of attention mask types, ensuring proper mapping and error handling for invalid types.
Signed-off-by: Qixiang Lin <qixiangl@nvidia.com>
---------
Signed-off-by: Qixiang Lin <qixiangl@nvidia.com>
* Reapply "refactor: Replace DecoderFinishedEvent with CudaEvent in decoder clas…" (#3183)
This reverts commit 75495730bc.
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* fixup! Reapply "refactor: Replace DecoderFinishedEvent with CudaEvent in decoder clas…" (#3183)
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
---------
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
