mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
b15f57763d
11 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Robin Kobus
|
ccff86068e
|
fix: request termination in pipeline parallelism (#3892)
* feat: Implement synchronous request termination in batch manager - Added `terminateRequestSync` method to `TrtEncoderModel` and `TrtGptModelInflightBatching` for handling request termination in the next `forwardSync` call. - Updated existing request termination logic to utilize the new synchronous method, ensuring generated tokens are cleared appropriately. - Enhanced logging for clarity in token management during request processing. Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * fixup! feat: Implement synchronous request termination in batch manager Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * fix: MockedModelCancelRequest Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * fixup! feat: Implement synchronous request termination in batch manager Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * fix: terminate with timeout Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * fixup! feat: Implement synchronous request termination in batch manager Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * docs: Update doc string for allottedTimeMs Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> --------- Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> |
||
|
Daniel Cámpora
|
1299f27c74
|
fix: Fix C++ decoder synchronization in PyTorch (#3106)
* Use updateDecoderBuffers in python decoder. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Fix synchronize in trtllm decoder. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Enable by default. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Use guided_decoder to setup seqslots and free them. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Use always decode_async and update_requests. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Update decoder buffers. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Fix speculative decoding tests. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Send new_tensors_host instead of assuming dict. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Make default False in enable_trtllm_decoder. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Partially fix mtp, partially fix py_executor. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Update request states before sending disagg ctx cache. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Fix disagg test for torch decoder. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Make isend_tensor_list and recv_tensor_list for sending the tensors_host. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Formatting. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Fix rebase. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Add disagg serving case to guided decoder. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Get overlap scheduling to work. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Update cutlass to main. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Update after rebasing. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Formatting. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Update to use decode async and update requests. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Properly pass information to update_requests Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Formatting. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Make disaggregated serving a step closer to working. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Fix rebase. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Fix rebase and format. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Copy new device tokens more pythonic. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Restore MTP add dummy reqs. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Add ordereddict import to py_executor. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Formatting. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Added seq slot manager. Add test. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Use transmission for single tensor except when list of tensors is received. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Add TRTLLMDecoder allocation to estimate max kv cache tokens. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Add stream synchronization Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Formatting. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Make memory calculation of decoder adapt to the chosen decoder. Recognize decoder option passed in executorconfig. Make overlap scheduler test run on TinyLlama. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Format Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Add decoder creation to estimate max kv. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Formatting. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> * Update submodule UCXX inline with main. Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> --------- Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com> |
||
|
Robin Kobus
|
8340657ae4
|
refactor: Introduce DecoderOutputBuffers per batch (#3506)
* refactor: Restructure DecoderBuffers and DecoderStepAsyncSend - Move communication logic from `DecoderBuffers` to `DecoderStepAsyncSend`. - Updated `DecoderStepAsyncSend` constructor to utilize the `DecoderBuffers`, enhancing clarity and reducing parameter complexity. - Refactored related methods to align with the new class structure, improving maintainability and readability of the code. These changes streamline the handling of decoding buffers and improve the overall architecture of the batch manager. Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * refactor: Restructure SlotDecoderBuffers and DecoderSlotAsyncSend - Move communication logic from `SlotDecoderBuffers` to `DecoderSlotAsyncSend`. - Updated `DecoderSlotAsyncSend` constructor to utilize the `SlotDecoderBuffers`, enhancing clarity and reducing parameter complexity. - Refactored related methods to align with the new class structure, improving maintainability and readability of the code. These changes enhance the structure and readability of the batch manager's decoding process. Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * chore: Log DecodingMode Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * refactor: Introduce DecoderOutputBuffers and update related classes - Moved buffers from `DecoderBuffers` to `DecoderOutputBuffers` to better reflect its purpose. - Updated the `DecoderStepAsyncSend` class to utilize `DecoderOutputBuffers`, enhancing clarity in the communication logic. - Refactored the constructor and methods in `DecoderBuffers` to accommodate the new structure, improving maintainability. - Added Python bindings for `DecoderOutputBuffers` to ensure compatibility with existing interfaces. These changes streamline the handling of output buffers in the decoding process, improving the overall architecture of the batch manager. Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * refactor: Update MPI communicator handling - Changed the `commSession` parameter type from `std::shared_ptr<mpi::MpiComm>` to `mpi::MpiComm` in `DecoderStepAsyncSend` and `DecoderSlotAsyncSend` classes for improved clarity and reduced complexity. - Updated related methods and constructors to reflect the new parameter type, enhancing maintainability. - Refactored the `TrtGptModelInflightBatching` class to accommodate these changes, ensuring consistent usage of `MpiComm`. These modifications streamline the communication logic in the decoding process, improving the overall architecture of the batch manager. Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * refactor: Replace shared_ptr with unique_ptr for buffer management - Updated the `TrtGptModelInflightBatching` class to use `std::unique_ptr` instead of `std::shared_ptr` for various buffer types, including `AllReduceBuffers`, `RuntimeBuffers`, `DecoderBuffers`, and `SlotDecoderBuffers`. - This change enhances memory management and ownership semantics, reducing overhead and improving performance. These modifications contribute to a cleaner and more efficient architecture in the batch manager. Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> --------- Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> |
||
|
katec846
|
eeb605abd6
|
feat: Offloading Multimodal embedding table to CPU in Chunked Prefill Mode (#3380)
* Feat: Offload ptable to cpu if enable_chunk_context Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com> * Feat: offload ptable to cpu for chunk context mode Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com> * Fix and add comment Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com> * Update Readme for multimodal and add a new param mm_embedding_offloading Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com> * fix: Correct prompt table offloading condition in PromptTuningBuffers Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com> * Clean up the code Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com> * Add commits to explain copy from cpu <-> gpu using pinned memory Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com> * Fix namings based on comments Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com> * Fix format based on precommit Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com> * Modify --mm_embedding_offloading flag Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com> --------- Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com> Co-authored-by: Haohang Huang <31998628+symphonylyh@users.noreply.github.com> |
||
|
Netanel Haber
|
3c52ac098f
|
feat: allocate minimal blocks per window size (#3028)
* implement variable window attention by breaking the block manager into window block managers per window size
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* revert isCyclic to be true if the min attention window is reached, not per window size
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* add explanatory comment to mCyclicThreshold
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* load correct gemma config
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* don't shadow inputLength in addSequence - it should remain the function scope input length between window size loop iterations
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* fix KVCacheManagerVariableWindowAttentionWithReuseTest for multiple window block managers
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* if TYPE_CHECKING
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* set temp_attention_window_inputs to None explicitly
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* set temp_attention_window_inputs to None explicitly
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* pass dtype as well
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* test_gemma variable sliding window attention
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* allot a fraction of primary/secondaryBlocks to different window size heaps, depending on the window size's total contribution to the kvcache size (i.e., including all layers)
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* remove || mEnableBlockReuse which erroneously triggers beamsearch code for cyclic variable attention window code
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* turn off request delaying for MaxUtil
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* make comments better
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* windowSizesTotalSum using std::accumulate
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* fix error handling of forwardAsync - forwardAsync catch-all catch cleanup code that runs terminateRequest can also fail and must be caught
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* fix comments
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* remove assert that kills disagg tests, since it isn't necessary
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* fix corrupted expression: 'isNewTask && (peftCacheManager ?' -> '(isNewTask && peftCacheManager) ?' which caused boolean algebra. Main is correct
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* add Gemma3 to SUPPORTED_HF_ARCHITECTURES
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* support Gemma3
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* finally fix test_gemma - always spread at least {} into generate_summary_cmd, never None
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* finally fix test_gemma - always spread at least {} into generate_summary_cmd, never None
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* fix kvfactor field for deepseek
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* fix comment
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* fix gemma-3 entries in testlist to include vswa
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* only quantize gemma2 VSWA
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
remove misleading comment
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
fix test_gemma
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* fix test_gemma
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* fix test_gemma
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* in sendRequestInfo, fromOldAllocatedBlockIds->fromOldAllocatedBlockIds, like in main
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
* fix: disable KV cache reuse if using attention sink (#3021)
* fix: disable KV cache reuse if using attention sink
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* fix: disable KV cache reuse if sink bubble
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
* add comment
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
---------
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
---------
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
Co-authored-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
|
||
|
Robin Kobus
|
1bd84c6d8c
|
feat: Allow individual gatherContext for each additional output (#3374)
* 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> |
||
|
Robin Kobus
|
77724b0fcb
|
Reapply "refactor: Replace DecoderFinishedEvent with CudaEvent in decoder clas…" (#3183) (#3195)
* Reapply "refactor: Replace DecoderFinishedEvent with CudaEvent in decoder clas…" (#3183)
This reverts commit
|
||
|
QI JUN
|
75495730bc
|
Revert "refactor: Replace DecoderFinishedEvent with CudaEvent in decoder clas…" (#3183)
This reverts commit
|
||
|
Robin Kobus
|
3ee4332fb1
|
refactor: Replace DecoderFinishedEvent with CudaEvent in decoder classes (#3078)
- Updated the `forwardAsync` method in `GptDecoderBatched` and `iGptDecoderBatched` to return `CudaEvent` instead of `DecoderFinishedEventPtr`, simplifying event handling. - Removed the `DecoderFinishedEvent` class and its associated usage across various files, streamlining the codebase. - Adjusted related methods and Python bindings to accommodate the new event structure, ensuring compatibility and maintaining functionality. These changes enhance the clarity and efficiency of the decoding process in the batch manager. Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> |
||
|
Aurelien Chartier
|
a33c595c88
|
Fix logits dtype in assert (#3038)
Remove extra methods in trtGptModelInflightBatching.h. The methods were moved out of that class during a previous refactoring, but the definitions have been left behind. Signed-off-by: Aurelien Chartier <achartier@nvidia.com> |
||
|
Kaiyu Xie
|
9b931c0f63
|
Update TensorRT-LLM (#2873) |