Skip to content

Conversation

@jla524
Copy link
Contributor

@jla524 jla524 commented Dec 6, 2024

What does this PR do?

Addresses #34809 (issue)

Who can review?

@ArthurZucker

@jla524 jla524 changed the title Add flex attention for Qwen2VL [WIP] Add flex attention for Qwen2VL Dec 6, 2024
score += causal_mask[b][0][q_idx][kv_idx]
return score

attn_output, attn_weights = flex_attention(
Copy link
Contributor Author

@jla524 jla524 Dec 7, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'm having a hard time getting tests to pass with flex attention.
Can I merge the refactor for now, and add flex attention as a follow up?

@jla524 jla524 closed this Dec 18, 2024
Copy link
Collaborator

@ArthurZucker ArthurZucker left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hey sorry for the late review! We ended up refactoring the API a bit more and I was off for a week! 🤗
Hope we did not deter you from contributing, and thanks for opening the PR! 🤗

@jla524 jla524 deleted the feat/refactor_qwen2vl_attention branch December 21, 2024 21:40
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants