Add sync-free masked autoreset and CUDA graph capture of the reset segment - #2604

Add sync-free masked autoreset and CUDA graph capture of the reset segment#2604

Cudrix-dev wants to merge 3 commits into

Motphys:mainMotphys/UniLab:mainfrom

Cudrix-dev:feat/sync-free-graph-captureCudrix-dev/UniLab:feat/sync-free-graph-captureCopy head branch name to clipboard