Skip to content

[Bugfix] fix issue251, qwen3 omni does not support chunked prefill now#256

Merged
hsliuustc0106 merged 1 commit intovllm-project:mainfrom
david6666666:issue251
Dec 9, 2025
Merged

[Bugfix] fix issue251, qwen3 omni does not support chunked prefill now#256
hsliuustc0106 merged 1 commit intovllm-project:mainfrom
david6666666:issue251

Conversation

@david6666666
Copy link
Collaborator

PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS (AT THE BOTTOM) HAVE BEEN CONSIDERED.

Purpose

fix issue #251
refer to:

Test Plan

python examples/online_serving/qwen3_omni/gradio_demo.py
prompt:explain this video
video:
https://github.com/user-attachments/assets/cb9fe21e-cd86-4a68-abd4-2b09eb42a4e9

Test Result

image
Essential Elements of an Effective PR Description Checklist
  • The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
  • The test plan, such as providing test command.
  • The test results, such as pasting the results comparison before and after, or e2e results
  • (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.
  • (Optional) Release notes update. If your change is user facing, please update the release notes draft.

BEFORE SUBMITTING, PLEASE READ https://github.com/vllm-project/vllm-omni/blob/main/CONTRIBUTING.md (anything written below this line will be removed by GitHub Actions)

Signed-off-by: David Chen <[email protected]>
@david6666666 david6666666 changed the title fix issue251 [Bugfix] fix issue251, qwen3 omni does not support chunked prefill now Dec 9, 2025
@david6666666
Copy link
Collaborator Author

@hsliuustc0106 PTAL, thx

Copy link
Collaborator

@hsliuustc0106 hsliuustc0106 left a comment

Choose a reason for hiding this comment

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

lgtm, but we need to tell others the common config change regarding max_num_batched_tokens

@hsliuustc0106 hsliuustc0106 merged commit 75a84c8 into vllm-project:main Dec 9, 2025
4 checks passed
@david6666666 david6666666 deleted the issue251 branch December 11, 2025 03:03
LawJarp-A pushed a commit to LawJarp-A/vllm-omni that referenced this pull request Dec 12, 2025
LawJarp-A pushed a commit to LawJarp-A/vllm-omni that referenced this pull request Dec 12, 2025
faaany pushed a commit to faaany/vllm-omni that referenced this pull request Dec 19, 2025
princepride pushed a commit to princepride/vllm-omni that referenced this pull request Jan 10, 2026
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.

[Bug]: Qwen3-Omni online inference with video input — audio output is garbled

2 participants