[CI/Build] Qwen3 Omni Tests#3802
Open
clodaghwalsh17 wants to merge 4 commits into
Open
Conversation
Signed-off-by: Clodagh Walsh <clodaghwalsh17@gmail.com>
Signed-off-by: Clodagh Walsh <clodaghwalsh17@gmail.com>
Signed-off-by: Clodagh Walsh <clodaghwalsh17@gmail.com>
Signed-off-by: Clodagh Walsh <clodaghwalsh17@gmail.com>
|
Codex usage limits have been reached for code reviews. Please check with the admins of this repo to increase the limits by adding credits. |
Collaborator
|
Missing test results in PR description. Please paste the actual pytest output for:
Also, the PR checklist items are unchecked — please mark what's complete. |
Contributor
There was a problem hiding this comment.
Pull request overview
This PR expands end-to-end test coverage for the Qwen3-Omni model by adding more modality combinations in both offline inference and online serving test suites.
Changes:
- Added offline inference tests for text→text, text→audio, image→text, image→audio, and video→text.
- Added an online serving test for audio→audio using a vendored WAV asset.
- Updated offline prompt selection logic to include text/image/audio prompt variants.
Reviewed changes
Copilot reviewed 2 out of 3 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
tests/e2e/online_serving/test_qwen3_omni_expansion.py |
Adds an audio→audio online E2E test that sends an audio data URL built from a local asset. |
tests/e2e/offline_inference/test_qwen3_omni.py |
Broadens offline E2E coverage across more input/output modality combinations and expands prompt variants. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+45
to
+52
| def get_question(prompt_type="text"): | ||
| prompts = { | ||
| "video": "Describe the video briefly.", | ||
| "image": "Describe the image.", | ||
| "audio": "Describe the audio.", | ||
| "text": "What is the capital of the United Kingdom?", | ||
| } | ||
| return prompts.get(prompt_type, prompts["video"]) | ||
| return prompts.get(prompt_type, prompts["text"]) |
Comment on lines
+556
to
+557
| audio_path = Path(__file__).parent.parent.parent / "assets" / "audio-prompt.wav" | ||
| audio_data_url = f"data:audio/wav;base64,{base64.b64encode(audio_path.read_bytes()).decode('utf-8')}" |
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
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
Improve test coverage for the Qwen3 Omni model
Test Plan
Test Result
Tests pass as expected
Essential Elements of an Effective PR Description Checklist
supported_models.mdandexamplesfor a new model. Please runmkdocs serveto sync the documentation editions to./docs.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)