TensorRT-LLMs

mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00

History

dongxuy04 16535991b2 feat: Add MNNVL MoE A2A support (#3504 ) * add MNNVL memory mapping support Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com> * add more MPI environment for trtllm-llmapi-launch Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com> * add MoE communication and prepare kernels Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com> * add MNNVL AlltoAll support for DeepSeekV3 Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com> * add output dump for throughput benchmark Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com> * support dynamic kernel launch grid Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com> * address review comments Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com> * address review comments #2 Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com> --------- Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>		2025-04-25 17:29:08 +08:00
..
batch_manager	fix: 5197419 and removed unused runtime kernels (#3631 )	2025-04-23 18:04:50 +02:00
common	Fix: Revert commit `25f9669` (#3832 )	2025-04-24 14:03:20 +08:00
cutlass_extensions/include/cutlass_extensions	feat: Update cutlass (#2981 )	2025-03-26 22:36:27 +08:00
executor	bug: Fix hang bug when context server doesn't have enough capacity for KV Cache (#3095 )	2025-04-21 15:16:55 +08:00
executor_worker	Update TensorRT-LLM (#2792 )	2025-02-18 21:27:39 +08:00
kernels	feat: Add MNNVL MoE A2A support (#3504 )	2025-04-25 17:29:08 +08:00
layers	fix: Eagle decoding (#3456 )	2025-04-11 22:06:38 +08:00
plugins	refactor: Clean up CMakeLists.txt (#3479 )	2025-04-18 14:39:29 +08:00
pybind	fix: Fix C++ decoder synchronization in PyTorch (#3106 )	2025-04-23 23:55:27 +08:00
runtime	fix: 5197419 and removed unused runtime kernels (#3631 )	2025-04-23 18:04:50 +02:00
thop	feat: Add MNNVL MoE A2A support (#3504 )	2025-04-25 17:29:08 +08:00
CMakeLists.txt	Fix double link to fp8_blockscale_gemm_src (#3707 )	2025-04-23 10:16:07 +08:00