kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-29 23:23:48 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
4f84a45899
TensorRT-LLMs/tensorrt_llm/_torch/custom_ops
History
Bo Li bf1b958f1a
[TRTLLM-7319][perf] Fuse slicing into MoE. (#6728) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Signed-off-by: Sergey Klevtsov <sklevtsov@nvidia.com>
Co-authored-by: Sergey Klevtsov <sklevtsov@nvidia.com>
2025-08-25 16:52:30 -04:00
..
__init__.py [None][ci] move unittests to sub-directories (#6635) 2025-08-20 05:42:22 -04:00
cpp_custom_ops.py [TRTLLM-7319][perf] Fuse slicing into MoE. (#6728) 2025-08-25 16:52:30 -04:00
flashinfer_custom_ops.py [None][ci] move unittests to sub-directories (#6635) 2025-08-20 05:42:22 -04:00
torch_custom_ops.py [TRTLLM-7319][perf] Fuse slicing into MoE. (#6728) 2025-08-25 16:52:30 -04:00
trtllm_gen_custom_ops.py [None][perf] Make finalize fusion part of the tactic selection logic (#6915) 2025-08-21 14:08:03 -07:00
userbuffers_custom_ops.py feat: Introduce UB allocator for pytorch flow (#3257) 2025-04-08 18:39:49 +08:00