transformers
[`BC 4.37 -> 4.38`] for Llama family, memory and speed
#29753
Merged

[`BC 4.37 -> 4.38`] for Llama family, memory and speed #29753

ArthurZucker merged 22 commits into main from fix-causal-mask-dispatch
ArthurZucker
ArthurZucker attempt to fix
2fd8c122
ArthurZucker Merge branch 'main' of github.com:huggingface/transformers into fix-c…
9c204e09
ArthurZucker the actual fix that works with compilation!
2af3c7cd
ArthurZucker this?
aece6ca0
ArthurZucker Merge branch 'fix-causal-mask-dispatch' of github.com:huggingface/tra…
7c29cb85
ArthurZucker temporary update
e45fbf82
ArthurZucker nit?
9608a969
ArthurZucker dispatcg to memory efficient?
9f07ab70
ArthurZucker update both models that have static cache support
c961ee8b
ArthurZucker Merge branch 'main' of github.com:huggingface/transformers into fix-c…
9872d2f4
ArthurZucker fix copies fix compile
05f7d8b8
ArthurZucker make sure fix
d667700d
ArthurZucker ArthurZucker changed the title [`BC 4.37 -> 4.38`] [`BC 4.37 -> 4.38`] for Llama family, memory and speed 2 years ago
ArthurZucker fix cohere and gemma
c6cec074
gante
gante commented on 2024-03-20
HuggingFaceDocBuilderDev
ArthurZucker fix beams?
c3d5dac1
ArthurZucker nit
050eb20d
ArthurZucker slipped through the cracks
bbba5b52
ArthurZucker ArthurZucker marked this pull request as ready for review 2 years ago
ArthurZucker nit
d9f3ea38
ArthurZucker nits
1e20ce9c
ArthurZucker
fxmarty
younesbelkada
younesbelkada approved these changes on 2024-03-20
gante
ArthurZucker
ArthurZucker update
f79ea4e5
ArthurZucker fix-copies
bc725def
gante
ArthurZucker skip failing tests
b46e4479
ArthurZucker nits
1abd0986
ArthurZucker ArthurZucker merged ff841900 into main 2 years ago
ArthurZucker ArthurZucker deleted the fix-causal-mask-dispatch branch 2 years ago
poedator
ArthurZucker
gante

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone