[Test] Add ModelRunner V2 with Qwen3-TTS Base E2E Test to CI pipeline#2321
Conversation
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: dc11ed9480
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| soft_fail: | ||
| - exit_status: 1 |
There was a problem hiding this comment.
Keep ModelRunner V2 test blocking
Setting soft_fail for exit_status: 1 makes this new core_model CI step non-blocking: pytest uses exit code 1 for test failures, so regressions in tests/e2e/online_serving/test_qwen3_tts_base.py will only produce a warning and the ready pipeline can still pass. This undermines the purpose of adding the ModelRunner V2 E2E test as CI protection.
Useful? React with 👍 / 👎.
Keep OmniVoice E2E step from main and Qwen3-TTS Base (ModelRunner V2) step from PR vllm-project#2321. Made-with: Cursor Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
…vllm-project#2321) Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
…vllm-project#2321) Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
…vllm-project#2321) Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
…vllm-project#2321) Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
…vllm-project#2321) Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Purpose
This PR aims to add a e2e test for Model Runner V2 with Qwen 3 TTS Base.
Test Plan
\
Test Result
\
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)