Adding a sm80 q4 gemm kernel for small tiles #20545
chenfucn
merged
6 commits into
microsoft:main
from
chenfucn:cfu_small_q4gemm
small tile q4 gemm kernel for am80
dd6134a2
add test
8f7f0d5f
add compilation guard to sm80 specific instructions
9bf0f280
skip lint in code relies on cutlass styling
71e8a357
suppress 0 size array warning
733da870
lint
2527bf9d
yufenglee
approved these changes
on 2024-06-05
Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub