TensorRT-LLMs/cpp/include/tensorrt_llm/runtime
Robin Kobus 9f9edd783c
refactor: Introduce MpiTag enumeration and update MPI function signatures (#3893)
* refactor: Move executor recv functions into classes

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

* refactor: Enhance MPI logging and error handling

- Updated MPI logging to include destination and tag information for better traceability during send and receive operations.
- Added error checking for MPI_Wait and MPI_Cancel calls to ensure proper handling of multi-device requests.
- Improved code structure for clarity and maintainability.

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

* refactor: Introduce MpiTag enumeration and update MPI function signatures

- Added a new header file `mpiTags.h` to define an enumeration for MPI tags, improving code readability and maintainability.
- Updated function signatures in `mpiUtils.h` and `mpiUtils.cpp` to use the new `MpiTag` type instead of raw integers for tags.
- Refactored various MPI calls across the codebase to utilize the new `MpiTag` enumeration, enhancing type safety and clarity.
- Removed redundant MPI tag constants from several classes, streamlining the code.

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

* fixup! refactor: Introduce MpiTag enumeration and update MPI function signatures

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

* refactor: Rename tags for consistency

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

---------

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
2025-05-04 13:24:29 +02:00
..
utils refactor: Introduce MpiTag enumeration and update MPI function signatures (#3893) 2025-05-04 13:24:29 +02:00
bufferManager.h Update TensorRT-LLM (#2755) 2025-02-11 03:01:00 +00:00
common.h Update TensorRT-LLM (#2502) 2024-11-26 16:51:34 +08:00
cudaEvent.h Update TensorRT-LLM (#787) 2024-01-02 17:54:32 +08:00
cudaStream.h fix: Move all casters to customCasters. (#3945) 2025-05-02 19:08:28 +08:00
decoderState.h refactor: decoder buffers (#3307) 2025-04-12 11:41:24 +02:00
decodingInput.h Feat: Variable-Beam-Width-Search (VBWS) part3 (#3338) 2025-04-08 23:51:27 +08:00
decodingOutput.h Feat: Variable-Beam-Width-Search (VBWS) part3 (#3338) 2025-04-08 23:51:27 +08:00
eagleBuffers.h Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
eagleModule.h Update TensorRT-LLM (#2792) 2025-02-18 21:27:39 +08:00
explicitDraftTokensBuffers.h Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
generationInput.h Feat: Variable-Beam-Width-Search (VBWS) part3 (#3338) 2025-04-08 23:51:27 +08:00
generationOutput.h Feat: Variable-Beam-Width-Search (VBWS) part3 (#3338) 2025-04-08 23:51:27 +08:00
gptDecoder.h Update TensorRT-LLM (#2582) 2024-12-16 21:50:47 -08:00
gptDecoderBatched.h Reapply "refactor: Replace DecoderFinishedEvent with CudaEvent in decoder clas…" (#3183) (#3195) 2025-04-04 15:56:28 +02:00
gptJsonConfig.h Update TensorRT-LLM (#2532) 2024-12-04 21:16:56 +08:00
gptSession.h feat: Integrate GPUDirect Storage (GDS) into Executor API (#3582) 2025-04-18 15:59:21 +08:00
iBuffer.h Update TensorRT-LLM (#2755) 2025-02-11 03:01:00 +00:00
iGptDecoderBatched.h chore: Clean up cpp runtime (#3537) 2025-04-15 16:06:14 +08:00
ipcNvlsMemory.h chore: Stabilize ABI boundary for internal kernel library (#3117) 2025-04-11 15:07:50 +08:00
ipcUtils.h Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
iStatefulGptDecoder.h refactor: Remove speculative decoding parameters from stateful decoders (#3024) 2025-03-26 20:16:26 +08:00
iTensor.h Update TensorRT-LLM (#2532) 2024-12-04 21:16:56 +08:00
lookaheadBuffers.h Feat: Variable-Beam-Width-Search (VBWS) part3 (#3338) 2025-04-08 23:51:27 +08:00
lookaheadModule.h Update TensorRT-LLM (#2582) 2024-12-16 21:50:47 -08:00
loraCache.h Update TensorRT-LLM (#2755) 2025-02-11 03:01:00 +00:00
loraCachePageManagerConfig.h Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
loraModule.h Update TensorRT-LLM (#2755) 2025-02-11 03:01:00 +00:00
medusaModule.h Update TensorRT-LLM (#2436) 2024-11-12 15:27:49 +08:00
memoryCounters.h Update TensorRT-LLM (#2110) 2024-08-13 22:34:33 +08:00
modelConfig.h Feat: Variable-Beam-Width-Search (VBWS) part3 (#3338) 2025-04-08 23:51:27 +08:00
promptTuningParams.h Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
rawEngine.h Update TensorRT-LLM (#2215) 2024-09-10 18:21:22 +08:00
request.h Feat: Variable-Beam-Width-Search (VBWS) part3 (#3338) 2025-04-08 23:51:27 +08:00
runtimeDefaults.h Update TensorRT-LLM (#2436) 2024-11-12 15:27:49 +08:00
samplingConfig.h Feat: Variable-Beam-Width-Search (VBWS) part3 (#3338) 2025-04-08 23:51:27 +08:00
speculativeDecodingMode.h Update TensorRT-LLM (#2436) 2024-11-12 15:27:49 +08:00
speculativeDecodingModule.h Update TensorRT-LLM (#1763) 2024-06-11 16:59:02 +08:00
statefulGptDecoderBatched.h chore: Clean up cpp runtime (#3537) 2025-04-15 16:06:14 +08:00
tllmLogger.h Update TensorRT-LLM (#787) 2024-01-02 17:54:32 +08:00
worldConfig.h bug: Fix hang bug when context server doesn't have enough capacity for KV Cache (#3095) 2025-04-21 15:16:55 +08:00