[`Mistral`] Add Flash Attention-2 support for `mistral` #26464
add FA-2 support for mistral
5d9bc483
fixup
0983d88b
add sliding windows
b8c91980
Merge branch 'add-mistral-fa-2' of https://github.com/younesbelkada/t…
d7408497
fixing few nits
bd58ca72
v1 slicing cache - logits do not match
43b02897
add comment
ed2616f2
fix bugs
7cafc2d7
more mem efficient
2b8c7b46
add warning once
4a3387df
add warning once
885b6014
oops
172d99a4
fixup
253b3830
more comments
e4d0fb7a
copy
a245722d
Merge branch 'add-mistral-fa-2' of https://github.com/younesbelkada/t…
30798964
add safety checker
e71c50d3
Merge branch 'add-mistral-fa-2' of https://github.com/younesbelkada/t…
a21d903a
fixup
5d1f5890
younesbelkada
marked this pull request as ready for review 2 years ago
Update src/transformers/models/mistral/modeling_mistral.py
b478e047
copied from
2fe2f490
up
25789d1c
raise when padding side is right
05ec7f47
Merge branch 'add-mistral-fa-2' of https://github.com/younesbelkada/t…
5a79195a
fixup
f9a69bcc
add doc + few minor changes
6a48dd31
Merge branch 'add-mistral-fa-2' of https://github.com/younesbelkada/t…
76763c7c
fixup
c2869469
younesbelkada
changed the title [`Mistral`] Add mistral + FA 2 [`Mistral`] Add Flash Attention-2 support for `mistral` 2 years ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub