Enwei Zhu 6fe89ea00f [TRTLLM-9819][perf] Reuse alltoall workspace for CuteDSL MoE output (#9840) ... Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>		2025-12-18 10:36:38 -08:00
..
multi_stream	[TRTLLM-7073][feat] Support torch compile for PP for Llama and DeepSeekV3 (#7838)	2025-12-04 13:32:11 +08:00
patterns	[TRTLLM-9660][feat] Convert cuteDSL GEMM to opt-in feature (#9682)	2025-12-06 02:24:51 -08:00
__init__.py	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
backend.py	[TRTLLM-7073][feat] Support torch compile for PP for Llama and DeepSeekV3 (#7838)	2025-12-04 13:32:11 +08:00
piecewise_optimizer.py	[TRTLLM-7073][feat] Support torch compile for PP for Llama and DeepSeekV3 (#7838)	2025-12-04 13:32:11 +08:00
recover_pass.py	[TRTLLM-3105][feat] Add Piecewise CUDA Graph Support (#3804)	2025-05-09 11:04:01 +08:00
remove_copy_pass.py	[TRTLLM-4279] feat: Multistream initial support for torch compile flow (#5847)	2025-07-21 19:10:22 +08:00
utils.py	[TRTLLM-9819][perf] Reuse alltoall workspace for CuteDSL MoE output (#9840)	2025-12-18 10:36:38 -08:00