TensorRT-LLMs/cpp/tensorrt_llm/plugins/mixtureOfExperts
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
..
CMakeLists.txt Update TensorRT-LLM (#524) 2023-12-01 22:27:51 +08:00
mixtureOfExpertsPlugin.cpp [TRTLLM-7319][perf] Fuse slicing into MoE. (#6728) 2025-08-25 16:52:30 -04:00
mixtureOfExpertsPlugin.h [None][perf] Make finalize fusion part of the tactic selection logic (#6915) 2025-08-21 14:08:03 -07:00