[Bugfix] Fix Qwen3-VL max_num_video_tokens calculation for video profiling #25648
Conversation
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
Signed-off-by: Isotr0py <[email protected]>
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request addresses a video profiling issue in Qwen3-VL by reusing Qwen2-VL's profiling logic with some modifications. The changes involve reducing _MAX_FRAMES_PER_VIDEO in qwen2_vl.py and adding a hack in qwen3_vl.py to disable resizing during dummy input generation.
While the hack in qwen3_vl.py is clearly documented as a temporary measure, modifying a constant in qwen2_vl.py to fix an issue in qwen3_vl.py introduces an undesirable side effect on Qwen2-VL's own profiling. My review includes a suggestion to isolate this change to qwen3_vl.py to avoid impacting other models.
ywang96
approved these changes
Sep 25, 2025
Zhuul
pushed a commit
to Zhuul/vllm
that referenced
this pull request
Sep 26, 2025
…iling (vllm-project#25648) Signed-off-by: Isotr0py <[email protected]>
12 tasks
yewentao256
pushed a commit
that referenced
this pull request
Oct 3, 2025
…iling (#25648) Signed-off-by: Isotr0py <[email protected]> Signed-off-by: yewentao256 <[email protected]>
xuebwang-amd
pushed a commit
to xuebwang-amd/vllm
that referenced
this pull request
Oct 10, 2025
…iling (vllm-project#25648) Signed-off-by: Isotr0py <[email protected]> Signed-off-by: xuebwang-amd <[email protected]>
choprahetarth
pushed a commit
to Tandemn-Labs/vllm
that referenced
this pull request
Oct 11, 2025
…iling (vllm-project#25648) Signed-off-by: Isotr0py <[email protected]>
lywa1998
pushed a commit
to lywa1998/vllm
that referenced
this pull request
Oct 20, 2025
…iling (vllm-project#25648) Signed-off-by: Isotr0py <[email protected]>
xuebwang-amd
pushed a commit
to xuebwang-amd/vllm
that referenced
this pull request
Oct 24, 2025
…iling (vllm-project#25648) Signed-off-by: Isotr0py <[email protected]> Signed-off-by: xuebwang-amd <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.
Purpose
Test Plan
Test Result
Essential Elements of an Effective PR Description Checklist
supported_models.mdandexamplesfor a new model.