[TRTLLM-17096][feat] runtime hooks: model opt-in engine fast paths - #20797

[TRTLLM-17096][feat] runtime hooks: model opt-in engine fast paths#20797

xwang233 wants to merge 10 commits into

NVIDIA:mainNVIDIA/TensorRT-LLM:mainfrom

xwang233:modeling-v2-runtime-hooksxwang233/TensorRT-LLM:modeling-v2-runtime-hooksCopy head branch name to clipboard