Fuse cumulative sum into FP8xINT4 Grouped Gemm#3812

Open

jwfromm wants to merge 4 commits intopytorch:mainfrom jwfromm:export-D71081537

Commits on Mar 14, 2025

FBGEMM Add Columnwise Weight Scaling to F8I4 GEMM (pytorch#3766 )

Josh Fromm
authored and
facebook-github-bot
committed
Provide helper functions for int4 quantization (pytorch#3775 )

Josh Fromm
authored and
facebook-github-bot
committed
Add Preshuffled FP8 x INT4 Grouped Gemm Kernel (pytorch#3800 )

Josh Fromm
authored and
facebook-github-bot
committed
Fuse cumulative sum into FP8xINT4 Grouped Gemm (pytorch#3812 )

jwfromm
authored and
facebook-github-bot
committed