Precompute flash attention padding info #880
Merge pull request #1 from mosaicml/main
04dd3349
Merge pull request #8 from mosaicml/main
87b2fdcd
Merge pull request #12 from mosaicml/main
c9a42e47
Merge branch 'mosaicml:main' into main
ddea9eec
Merge pull request #13 from mosaicml/main
0bcd8eee
Merge pull request #14 from mosaicml/main
f209b581
Merge pull request #15 from mosaicml/main
ec4378df
Merge branch 'mosaicml:main' into main
b4367063
..
bcace036
Merge branch 'mosaicml:main' into main
cf4aa585
Merge branch 'mosaicml:main' into main
7c35ce89
..
0a8ebfbc
..
6f18a332
Merge branch 'mosaicml:main' into main
f42d5859
Merge branch 'mosaicml:main' into main
2f3f53c1
..
77b975f5
Merge branch 'mosaicml:main' into main
e28cfbea
Merge branch 'mosaicml:main' into main
800c6f87
Merge branch 'mosaicml:main' into main
922ef136
Merge branch 'mosaicml:main' into main
d36f5f79
Merge branch 'mosaicml:main' into main
d5245316
..
2b2f3d84
..
e98a01d3
ShashankMosaicML
changed the title Precompute flash attention padding info WIP: Precompute flash attention padding info 2 years ago
..
5a9e1e88
..
61d8ade7
..
e2363059
..
416525ad
..
77597a10
..
09d9bdff
..
0474e059
..
0f950566
..
5063149b
..
0f25b731
..
c3d30f95
..
34e4a99c
..
03113a9c
ShashankMosaicML
changed the title WIP: Precompute flash attention padding info Precompute flash attention padding info 2 years ago
..
3351d23e
Update llmfoundry/models/mpt/modeling_mpt.py
3d8cda89
dummy data
b227bcf2
vchiley
approved these changes
on 2024-01-17
undoing last commit
bd28b43e
..
d844c5fd
..
293dde23
Update llmfoundry/models/mpt/modeling_mpt.py
18bf7ca7
dakinggg
approved these changes
on 2024-01-17
..
11d3d706
..
00bc72b4
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub