Fix Qwen2.5-VL temporal RoPE scaling applied to still images#45330
Merged
zucchini-nlp merged 2 commits intohuggingface:mainfrom Apr 10, 2026
Merged
Fix Qwen2.5-VL temporal RoPE scaling applied to still images#45330zucchini-nlp merged 2 commits intohuggingface:mainfrom
zucchini-nlp merged 2 commits intohuggingface:mainfrom
Conversation
get_rope_index unconditionally applies tokens_per_second temporal scaling to both images and videos. For still images (modality_type == 1), this shifts the temporal position origin to start_position * tokens_per_second instead of start_position, creating a mismatch with height/width dimensions. Only apply temporal scaling (tokens_per_second * second_per_grid_ts) for video inputs (modality_type == 2). Still images use time_interval=1, keeping the temporal origin aligned with height and width at start_position. Qwen3-VL inherits this fix via super().get_rope_index(). Fixes huggingface#45325
zucchini-nlp
approved these changes
Apr 9, 2026
Member
zucchini-nlp
left a comment
zucchini-nlp
left a comment
There was a problem hiding this comment.
Great catch! Thanks for fixing
Member
|
I'll merge when CI is green, we're waiting internally for the team to skip hub-tests (too flaky) |
Contributor
|
[For maintainers] Suggested jobs to run (before merge) run-slow: qwen2_5_vl |
|
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. |
4 tasks
zucchini-nlp
added
the
for patch
ArthurZucker
pushed a commit
that referenced
this pull request
Apr 13, 2026
get_rope_index unconditionally applies tokens_per_second temporal scaling to both images and videos. For still images (modality_type == 1), this shifts the temporal position origin to start_position * tokens_per_second instead of start_position, creating a mismatch with height/width dimensions. Only apply temporal scaling (tokens_per_second * second_per_grid_ts) for video inputs (modality_type == 2). Still images use time_interval=1, keeping the temporal origin aligned with height and width at start_position. Qwen3-VL inherits this fix via super().get_rope_index(). Fixes #45325 Co-authored-by: Raushan Turganbay <raushan@huggingface.co>
2 tasks
sirzechs66
pushed a commit
to sirzechs66/transformers
that referenced
this pull request
Apr 18, 2026
…face#45330) get_rope_index unconditionally applies tokens_per_second temporal scaling to both images and videos. For still images (modality_type == 1), this shifts the temporal position origin to start_position * tokens_per_second instead of start_position, creating a mismatch with height/width dimensions. Only apply temporal scaling (tokens_per_second * second_per_grid_ts) for video inputs (modality_type == 2). Still images use time_interval=1, keeping the temporal origin aligned with height and width at start_position. Qwen3-VL inherits this fix via super().get_rope_index(). Fixes huggingface#45325 Co-authored-by: Raushan Turganbay <raushan@huggingface.co>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
get_rope_index unconditionally applies tokens_per_second temporal scaling to both images and videos. For still images (modality_type == 1), this shifts the temporal position origin to start_position * tokens_per_second instead of start_position, creating a mismatch with height/width dimensions.
Only apply temporal scaling (tokens_per_second * second_per_grid_ts) for video inputs (modality_type == 2). Still images use time_interval=1, keeping the temporal origin aligned with height and width at start_position.
Qwen3-VL inherits this fix via super().get_rope_index().
What does this PR do?
Fixes #45325
Code Agent Policy
The Transformers repo is currently being overwhelmed by a large number of PRs and issue comments written by
code agents. We are currently bottlenecked by our ability to review and respond to them. As a result,
we ask that new users do not submit pure code agent PRs at this time.
You may use code agents in drafting or to help you diagnose issues. We'd also ask autonomous "OpenClaw"-like agents
not to open any PRs or issues for the moment.
PRs that appear to be fully agent-written will probably be closed without review, and we may block users who do this
repeatedly or maliciously.
This is a rapidly-evolving situation that's causing significant shockwaves in the open-source community. As a result,
this policy is likely to be updated regularly in the near future. For more information, please read
CONTRIBUTING.md.Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
@zucchini-nlp @yonigozlan