Conversation
Summary of ChangesHello @samuellees, 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! This pull request enhances the testing suite for the prefill kernel by incorporating additional attention head configurations. These new test cases are crucial for validating the kernel's compatibility and performance with advanced model architectures, such as Qwen3N and Qwen3.5, thereby improving the overall robustness and reliability of the system. Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Changelog
Activity
Using Gemini Code AssistThe 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 by creating a comment using either
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 Limitations & Feedback Gemini Code Assist 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. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. 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
|
📝 WalkthroughWalkthroughAdded two larger head-size parameter tuples—(16, 16, 32) and (16, 16, 64)—to parameterization decorators in prefill delta rule tests, expanding test coverage without changing test logic or public interfaces. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Poem
🚥 Pre-merge checks | ✅ 1 | ❌ 2❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches
🧪 Generate unit tests (beta)
No actionable comments were generated in the recent review. 🎉 🧹 Recent nitpick comments
Tip Issue Planner is now in beta. Read the docs and try it out! Share your feedback on Discord. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![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 adds new test cases for Grouped-Value Attention (GVA) configurations, likely for Qwen3N and Qwen3.5 models. The changes correctly expand test coverage. I've included one suggestion to refactor duplicated test parameters for improved maintainability.
| @pytest.mark.parametrize( | ||
| "num_q_heads, num_k_heads, num_v_heads", | ||
| [(1, 1, 1), (4, 1, 1), (3, 3, 3), (6, 2, 2), (1, 1, 2), (2, 2, 4)], | ||
| [ | ||
| (1, 1, 1), | ||
| (4, 1, 1), | ||
| (3, 3, 3), | ||
| (6, 2, 2), | ||
| (1, 1, 2), | ||
| (2, 2, 4), | ||
| (16, 16, 32), | ||
| (16, 16, 64), | ||
| ], | ||
| ) |
There was a problem hiding this comment.
This list of head configurations is identical to the one used for test_prefill_kernel_basic (lines 137-149). To improve maintainability and reduce duplication, consider defining this list as a module-level constant and reusing it in both test functions. For example:
# At module level
_PREFILL_HEAD_CONFIGS = [
(1, 1, 1),
(4, 1, 1),
(3, 3, 3),
(6, 2, 2),
(1, 1, 2),
(2, 2, 4),
(16, 16, 32),
(16, 16, 64),
]
# In test decorators
@pytest.mark.parametrize(
"num_q_heads, num_k_heads, num_v_heads", _PREFILL_HEAD_CONFIGS
)
|
/bot run |
|
@flashinfer-bot run |
|
[FAILED] Pipeline #43685351: 10/20 passed |
|
@samuellees please rebase the PR onto the latest main to kick off CI. |
4 participants
📌 Description
Add test case for Qwen3N, and Qwen3.5 according to vllm-project/vllm#34131
🔍 Related Issues
🚀 Pull Request Checklist
Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete.
✅ Pre-commit Checks
pre-commitby runningpip install pre-commit(or used your preferred method).pre-commit install.pre-commit run --all-filesand fixed any reported issues.🧪 Tests
unittest, etc.).Reviewer Notes
Summary by CodeRabbit