[`BC 4.37 -> 4.38`] for Llama family, memory and speed #29753
attempt to fix
2fd8c122
Merge branch 'main' of github.com:huggingface/transformers into fix-c…
9c204e09
the actual fix that works with compilation!
2af3c7cd
this?
aece6ca0
Merge branch 'fix-causal-mask-dispatch' of github.com:huggingface/tra…
7c29cb85
temporary update
e45fbf82
nit?
9608a969
dispatcg to memory efficient?
9f07ab70
update both models that have static cache support
c961ee8b
Merge branch 'main' of github.com:huggingface/transformers into fix-c…
9872d2f4
fix copies fix compile
05f7d8b8
make sure fix
d667700d
ArthurZucker
changed the title [`BC 4.37 -> 4.38`] [`BC 4.37 -> 4.38`] for Llama family, memory and speed 2 years ago
fix cohere and gemma
c6cec074
gante
commented
on 2024-03-20
fix beams?
c3d5dac1
nit
050eb20d
slipped through the cracks
bbba5b52
ArthurZucker
marked this pull request as ready for review 2 years ago
nit
d9f3ea38
nits
1e20ce9c
update
f79ea4e5
fix-copies
bc725def
skip failing tests
b46e4479
nits
1abd0986
ArthurZucker
deleted the fix-causal-mask-dispatch branch 2 years ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub