kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
5e5300898b
TensorRT-LLMs/cpp/tensorrt_llm
History
Gal Hubara-Agam 5e5300898b
[#8732][feat] Add ReLU2 to TRTLLM Cutlass MoE BF16 kernels (#9191) 
Signed-off-by: Gal Hubara Agam <96368689+galagam@users.noreply.github.com>
2025-11-17 20:30:00 -08:00
..
batch_manager [TRTLLM-8831][feat] Enable early exit with overlap scheduler (#8587) 2025-11-17 18:07:13 +01:00
common [None][feat] Add TRTLLM_NIXL_KVCACHE_BACKEND environment variable for NIXL backend selection (#9075) 2025-11-17 15:39:55 -08:00
cutlass_extensions/include/cutlass_extensions [#8732][feat] Add ReLU2 to TRTLLM Cutlass MoE BF16 kernels (#9191) 2025-11-17 20:30:00 -08:00
deep_ep [TRTLLM-6589][feat] Support CUDA graph for DeepEP (#7514) 2025-10-02 10:13:24 -07:00
deep_gemm [https://nvbugs/5433581][fix] DeepGEMM installation on SBSA (#6588) 2025-08-06 16:44:21 +08:00
executor [None][feat] Add TRTLLM_NIXL_KVCACHE_BACKEND environment variable for NIXL backend selection (#9075) 2025-11-17 15:39:55 -08:00
executor_worker Update TensorRT-LLM (#2792) 2025-02-18 21:27:39 +08:00
flash_mla [TRTLLM-8535][feat] Support DeepSeek V3.2 with FP8 + BF16 KV cache/NVFP4 + BF16 KV cache (#8405) 2025-10-24 13:40:41 -04:00
kernels [#8732][feat] Add ReLU2 to TRTLLM Cutlass MoE BF16 kernels (#9191) 2025-11-17 20:30:00 -08:00
layers [None][feat] Support ignored prompt length for penalties via new sampling config parameter (#8127) 2025-10-27 13:12:31 -04:00
nanobind [TRTLLM-8831][feat] Enable early exit with overlap scheduler (#8587) 2025-11-17 18:07:13 +01:00
plugins [None][fix] Fix the performance issue of FP8 blockwise grouped GEMM when using attention DP (#8501) 2025-10-27 10:18:19 +08:00
pybind [TRTLLM-8831][feat] Enable early exit with overlap scheduler (#8587) 2025-11-17 18:07:13 +01:00
runtime [None][feat] add flag for EPLB to force using GDRCopy (#8650) 2025-10-29 13:33:26 +08:00
testing fix: Improve chunking test and skip empty kernel calls (#5710) 2025-07-04 09:08:15 +02:00
thop [None][feat] Update TRTLLM MoE cubins; reduce mxfp4 weight padding requirement; tighten TMA bound (#9025) 2025-11-17 10:04:29 +08:00
CMakeLists.txt [TRTLLM-8535][feat] Support DeepSeek V3.2 with FP8 + BF16 KV cache/NVFP4 + BF16 KV cache (#8405) 2025-10-24 13:40:41 -04:00