Skip to content

[qwen-vl] fix beam search with videos #39726

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Aug 11, 2025

Conversation

zucchini-nlp
Copy link
Member

@zucchini-nlp zucchini-nlp commented Jul 28, 2025

What does this PR do?

As per title, the tests covered only image input so we never noticed the bug. It has been there since model release

Fixes #39723

@zucchini-nlp zucchini-nlp requested a review from Cyrilvallez July 28, 2025 10:22
@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

Copy link
Contributor

[For maintainers] Suggested jobs to run (before merge)

run-slow: glm4v, qwen2_5_vl, qwen2_vl

Copy link
Member

@Cyrilvallez Cyrilvallez left a comment

Choose a reason for hiding this comment

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

Alright, thanks

@zucchini-nlp zucchini-nlp merged commit 3124d1b into huggingface:main Aug 11, 2025
19 checks passed
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.

num_beams > 1 leads to exception for Qwen2.5VL (Qwen family or all VLM models?)
3 participants