transformers
Attention Quantization with FBGemm & TP
#37384
Merged

Attention Quantization with FBGemm & TP #37384

ArthurZucker merged 10 commits into main from fix_fbgemm_tp
MekkCyber
MekkCyber fix
b3e08ec1
github-actions github-actions marked this pull request as draft 258 days ago
github-actions
MekkCyber MekkCyber requested a review from ArthurZucker ArthurZucker 258 days ago
MekkCyber MekkCyber requested a review from SunMarc SunMarc 258 days ago
ArthurZucker ArthurZucker added for patch
HuggingFaceDocBuilderDev
ArthurZucker
ArthurZucker approved these changes on 2025-04-09
MekkCyber MekkCyber marked this pull request as ready for review 258 days ago
ArthurZucker
ArthurZucker commented on 2025-04-09
MekkCyber keep fused
634c9c66
MekkCyber Merge branch 'main' into fix_fbgemm_tp
47799fe7
MekkCyber contiguous
37c53583
MekkCyber rm print
84873cd0
MekkCyber Merge branch 'main' into fix_fbgemm_tp
fd7e309a
MekkCyber Merge branch 'main' into fix_fbgemm_tp
06aec7f8
SunMarc
SunMarc commented on 2025-04-09
MekkCyber update
1c166f35
MekkCyber update
1f1bab81
SunMarc
SunMarc commented on 2025-04-09
MekkCyber rm print
4333431f
ArthurZucker ArthurZucker merged f834ca2c into main 257 days ago
ArthurZucker ArthurZucker deleted the fix_fbgemm_tp branch 257 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone