Fix InternVL attention when using qk_norm (38B and 78B) #37620
fix internvlvision attention when using qk_norm
d3b2bbc0
yonigozlan
marked this pull request as ready for review 354 days ago
Merge branch 'main' into fix-large-internvl
f1450b4c
Merge remote-tracking branch 'upstream/main' into fix-large-internvl
38111e04
nit
8d49d932
modular
dcf558c0
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub