transformers
fix: Enable flash_attention in Granite4Vision
#46306
Closed
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
1
Changes
View On
GitHub
fix: Enable flash_attention in Granite4Vision
#46306
avihu111
wants to merge 1 commit into
huggingface:main
from
avihu111:gv4_qformer_attn_fix
prevent a crash when loading granite4_vision with flash_attention_2/…
bd6c8b62
avihu111
marked this pull request as ready for review
22 days ago
github-actions
requested a review
from
ArthurZucker
22 days ago
github-actions
requested a review
from
Rocketknight1
22 days ago
zucchini-nlp
commented on 2026-06-01
avihu111
closed this
21 days ago
Login to write a write a comment.
Login via GitHub
Reviewers
zucchini-nlp
ArthurZucker
Rocketknight1
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub