mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
eeb605abd6
* 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> |
||
|---|---|---|
| .. | ||
| cache_transmission | ||
| CMakeLists.txt | ||
| contextPhaseParams.cpp | ||
| debugConfig.cpp | ||
| decodingConfig.cpp | ||
| disaggServerUtil.cpp | ||
| dynamicBatchConfig.cpp | ||
| dynamicBatchTuner.cpp | ||
| dynamicBatchTuner.h | ||
| executor.cpp | ||
| executorConfig.cpp | ||
| executorImpl.cpp | ||
| executorImpl.h | ||
| executorKVCacheEventManager.cpp | ||
| extendedRuntimePerfKnobConfig.cpp | ||
| guidedDecodingConfig.cpp | ||
| guidedDecodingParams.cpp | ||
| intervalSet.h | ||
| jsonSerialization.cpp | ||
| kvCacheConfig.cpp | ||
| kvCacheRetentionConfig.cpp | ||
| logitsPostProcessorConfig.cpp | ||
| loraConfig.cpp | ||
| model.h | ||
| mropeConfig.cpp | ||
| orchestratorConfig.cpp | ||
| orchestratorUtils.h | ||
| outputConfig.cpp | ||
| parallelConfig.cpp | ||
| peftCacheConfig.cpp | ||
| promptTuningConfig.cpp | ||
| request.cpp | ||
| requestImpl.h | ||
| requestUtils.cpp | ||
| requestUtils.h | ||
| requestWithId.cpp | ||
| requestWithId.h | ||
| response.cpp | ||
| responseImpl.h | ||
| samplingConfig.cpp | ||
| schedulerConfig.cpp | ||
| serialization.cpp | ||
| serializeUtils.h | ||
| speculativeDecodingConfig.cpp | ||
| tensor.cpp | ||
| types.cpp | ||