Skip to content

fix(mxfp8_moe): zero empty-expert weight gradients, accept non-contiguous gradients, smoke-test the kernel - #21

Draft
garrett361 wants to merge 4 commits into
mainfrom
feat/mxfp8-moe-sm103
Draft

fix(mxfp8_moe): zero empty-expert weight gradients, accept non-contiguous gradients, smoke-test the kernel#21
garrett361 wants to merge 4 commits into
mainfrom
feat/mxfp8-moe-sm103

docs(mxfp8_moe): state that group sizes must be multiples of the alig…

2018c76
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar