Skip to content

Fix int32 overflow in qdq_mxfp4 causing GPU memory access fault above INT32_MAX elements - #43

Open
zjin-lcf wants to merge 2 commits into
amd:release/0.12from
zjin-lcf:fix-mxfp4-int32-overflow
Open

zjin-lcf wants to merge 2 commits into
amd:release/0.12from
zjin-lcf:fix-mxfp4-int32-overflow

Use a grid-stride loop in qdq_mxfp4_kernel

467b738
Select commit
Loading
Failed to load commit list.

Workflow runs completed with no jobs