Attention Quantization with FBGemm & TP #37384
fix
b3e08ec1
MekkCyber
marked this pull request as ready for review 258 days ago
keep fused
634c9c66
Merge branch 'main' into fix_fbgemm_tp
47799fe7
contiguous
37c53583
rm print
84873cd0
Merge branch 'main' into fix_fbgemm_tp
fd7e309a
Merge branch 'main' into fix_fbgemm_tp
06aec7f8
update
1c166f35
update
1f1bab81
rm print
4333431f
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub