[None][perf] Overlap TRTLLM-Gen FMHA JIT warmup compilation with engine warmup (opt-in) - #18542

[None][perf] Overlap TRTLLM-Gen FMHA JIT warmup compilation with engine warmup (opt-in)#18542

aaronmeoded-b10 wants to merge 15 commits into

NVIDIA:mainNVIDIA/TensorRT-LLM:mainfrom

aaronmeoded-b10:fmha-async-jit-warmupaaronmeoded-b10/TensorRT-LLM:fmha-async-jit-warmupCopy head branch name to clipboard