kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-05 18:51:38 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
ff3a494f5c
TensorRT-LLMs/cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha
History
sunnyqgg ff0dd6076e
[TRTLLM-10062][feat] Enable MTP for Nemotron Super (#10754) 
Signed-off-by: qgai <qgai@nvidia.com>
2026-01-26 11:23:26 -05:00
..
cubin [None][feat] Add Skip Softmax MLA kernels for Blackwell and Fix an accuracy bug of NVFP4 KV (#10813) 2026-01-26 16:46:33 +08:00
CMakeLists.txt Update TensorRT-LLM (#2755) 2025-02-11 03:01:00 +00:00
fmhaKernels.h [TRTLLM-10062][feat] Enable MTP for Nemotron Super (#10754) 2026-01-26 11:23:26 -05:00
fmhaReduction.cu [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
fmhaReduction.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
fmhaRunner.cpp [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
fmhaRunner.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
fmhaRunnerParams.h [None][feat] update trtllm-gen to support groupsTokensHeadsQ (#10261) 2026-01-15 02:24:25 -05:00
kernelParams.h [None][feat] update trtllm-gen to support groupsTokensHeadsQ (#10261) 2026-01-15 02:24:25 -05:00
kernelUtils.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
prepareCustomMask.cu [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
prepareCustomMask.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00