[CI Bugfix] Skip failing Tensorizer+LoRA test #20724
Conversation
Signed-off-by: mgoin <[email protected]>
|
👋 Hi! Thank you for contributing to the vLLM project. 💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels. Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging. To run CI, PR reviewers can either: Add 🚀 |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Summary of Changes
Hello @mgoin, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
I have created this pull request to temporarily disable a specific integration test that is currently causing CI failures. The test, test_tp2_serialize_and_deserialize_lora, is known to be problematic when combining Tensorizer and LoRA, and its underlying issue is being investigated separately. By skipping this test, the CI pipeline can proceed without being blocked, allowing other changes to be integrated.
Highlights
- CI Stability: This pull request addresses a known CI failure by temporarily skipping a specific test case to unblock continuous integration pipelines.
- Test Skipping: The
test_tp2_serialize_and_deserialize_lorafunction, which involves Tensorizer and LoRA functionalities, is now skipped due to an ongoing issue documented in #19619.
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.
| Feature | Command | Description |
|---|---|---|
| Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
| Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
| Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in issue comments and review comments. |
| Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
Footnotes
-
Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
There was a problem hiding this comment.
Code Review
This pull request disables a failing test related to Tensorizer and LoRA, which is a good temporary measure to keep the CI green. I've left one comment regarding a discrepancy in the referenced issue number in the skip reason to improve clarity for future maintenance. Otherwise, the change is correct and follows the PR's intent.
| @pytest.mark.skip(reason=("Skipping this test as tensorizer is not " | ||
| "working with LoRA as of #19619")) |
There was a problem hiding this comment.
Thanks for disabling this failing test. There's a small discrepancy in the issue number referenced. The PR description points to issue #20723, while the skip reason in the code mentions #19619.
To ensure clarity for future developers, it's best to reference the most relevant issue tracking this specific test failure. Assuming #20723 is the correct one, I've suggested an updated and more concise reason.
@pytest.mark.skip(reason="Skipping failing test for tensorizer with LoRA (see #20723).")
| generate_and_test(llm, sql_lora_files) | ||
|
|
||
|
|
||
| @pytest.mark.skip(reason=("Skipping this test as tensorizer is not " |
There was a problem hiding this comment.
Please note that this test looks to be failing due to a now unsupported initialization usage pattern for TensorizerConfig instances, and does not imply that Tensorizer support with LoRA is not working, so this skip reason given here isn't accurate. The same CI run mentioned in the related Issue passed the Tensorizer LoRA test from test_tensorizer_entrypoint.py which serializes a LoRA adapter, deserializes it, serves it and its target model, and performs a completion with the adapter.
There was a problem hiding this comment.
I see, thanks for the context. I'll still land this temporary patch to unblock other PRs in flight, but please do work on a proper fix when you can
Signed-off-by: Jinzhen Lin <[email protected]>
Signed-off-by: Diego-Castan <[email protected]>
4 participants
Purpose
Skip the known failing test #20723 for now while it is investigated
Test Plan
Test Result