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
c5fb692a7d
TensorRT-LLMs/cpp/tensorrt_llm/kernels/trtllmGenKernels
History
ChristinaZ c5fb692a7d
Refactor the rest routing part for the routing kernels in the MoE TRT-LLM backend (#5771) 
Signed-off-by: Christina Zhang <83400082+ChristinaZ@users.noreply.github.com>
2025-07-11 16:37:56 +08:00
..
batchedGemm [feat] Add TRTLLM MoE nvfp4 cubins for mid-high concurrency; attention_dp for TRTLLM MoE (#5723) 2025-07-10 14:06:50 +08:00
blockScaleMoe Refactor the rest routing part for the routing kernels in the MoE TRT-LLM backend (#5771) 2025-07-11 16:37:56 +08:00
fmha [https://jirasw.nvidia.com/browse/TRTLLM-4645] support mutliCtasKvMode for high-throughput MLA kernels (#5426) 2025-06-25 16:31:10 +08:00
gemm [feat] Add TRTLLM MoE nvfp4 cubins for mid-high concurrency; attention_dp for TRTLLM MoE (#5723) 2025-07-10 14:06:50 +08:00
gemmGatedAct [feat] Adds optional module cache for TRT-LLM Gen Gemm interfaces (#5743) 2025-07-07 13:34:55 -07:00
CMakeLists.txt feat: update DeepSeek FP8 TRT-LLM Gen cubins (#4643) 2025-06-03 14:07:54 -07:00