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
57944206ba
TensorRT-LLMs/tensorrt_llm/_torch/custom_ops
History
Zongfei Jing 1e5af736ea
Add smart router for moe (#3641) 
Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
2025-04-23 12:21:59 +08:00
..
__init__.py feat: Support cos_sin_cache in all cases. (#3517) 2025-04-16 13:48:44 +08:00
cpp_custom_ops.py Unify two versions of AllReduce custom op (#3032) 2025-04-22 21:58:42 +08:00
flashinfer_custom_ops.py feat: Support cos_sin_cache in all cases. (#3517) 2025-04-16 13:48:44 +08:00
torch_custom_ops.py Add smart router for moe (#3641) 2025-04-23 12:21:59 +08:00
userbuffers_custom_ops.py feat: Introduce UB allocator for pytorch flow (#3257) 2025-04-08 18:39:49 +08:00