CUTLASS 4.2.2

hwu36 released this 21 Jun 16:44

2b426e9

CUTLASS C++

Make version.h NVRTC JIT compilation compatible.
Allow linking large cutlass library on 64bit platform.
Fix alignment-related miscalculation for pipeline stages of Blackwell blockscaled GEMM.
Fix for blockwise group gemm nosmem epilogues and no sfd with nosmem group gemm epilogues.

Assets 2