Skip to content

Adapt fixture-kit to gsm8k mixin#15599

Merged
hnyls2002 merged 15 commits intomainfrom
lsyin/move-gsm8k-mixin
Dec 22, 2025
Merged

Adapt fixture-kit to gsm8k mixin#15599
hnyls2002 merged 15 commits intomainfrom
lsyin/move-gsm8k-mixin

Conversation

@hnyls2002
Copy link
Copy Markdown
Collaborator

@hnyls2002 hnyls2002 commented Dec 22, 2025

Split the original gsm8k into a fixture-kit mode.

@gemini-code-assist
Copy link
Copy Markdown
Contributor

Summary of Changes

Hello @hnyls2002, 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 focuses on refactoring the testing framework to enhance modularity and maintainability. It introduces a dedicated base class for managing the lifecycle of test servers and reorganizes existing test mixins into a more logical structure. These changes aim to reduce boilerplate code in individual test files and ensure consistent server management across the test suite.

Highlights

  • Refactored Test Infrastructure: A new DefaultServerBase class has been introduced to standardize the setup and teardown of server processes for tests, encapsulating common logic for launching and killing servers.
  • Test Mixin Relocation: The GSM8KMixin class has been moved from python/sglang/test/gsm8k_mixin.py to python/sglang/test/kits/gsm8k_accuracy_kit.py, improving the organization of test-related utilities.
  • Updated Test Class Inheritance: Multiple test classes, including those for Ministral3 and Nvidia Nemotron Nano models, have been updated to inherit from the new DefaultServerBase and the relocated GSM8KMixin, streamlining their test setup.

🧠 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.

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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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 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

  1. 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.

Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

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

Code Review

This pull request refactors the test setup by introducing a DefaultServerBase fixture to manage the server lifecycle for tests. The GSM8KMixin is adapted to this new structure, and several test files are updated to use the new DefaultServerBase fixture alongside GSM8KMixin.

My review has identified a critical issue with the multiple inheritance pattern used, which causes the server setup logic in DefaultServerBase to be overridden by GSM8KMixin. I've also pointed out a potential source of test flakiness in the new server fixture due to the use of a fixed time.sleep(). Please see my detailed comments.

Comment thread test/srt/models/test_ministral3_models.py
Comment thread python/sglang/test/server_fixtures/default_fixture.py
@github-actions github-actions Bot added the Multi-modal multi-modal language model label Dec 22, 2025
@hnyls2002
Copy link
Copy Markdown
Collaborator Author

/tag-and-rerun-ci

@hnyls2002 hnyls2002 merged commit beae3f9 into main Dec 22, 2025
129 of 148 checks passed
@hnyls2002 hnyls2002 deleted the lsyin/move-gsm8k-mixin branch December 22, 2025 06:19
Liwansi added a commit to iforgetmyname/sglang that referenced this pull request Dec 23, 2025
…n_eagle3_dp

* 'main' of https://github.com/sgl-project/sglang: (208 commits)
  MoE: Skip SiLU/GELU activation for masked experts (sgl-project#15539)
  [GLM-ASR] GLM-ASR Support  (sgl-project#15570)
  Improve engine customization interface (sgl-project#15635)
  chore: bump sgl-kernel version to 0.3.20 (sgl-project#15590)
  bugfix[schedule]: Refactor sort method and add related UT (sgl-project#13576)
  Adjust wrong `mtp` meaning introduce by mimo (sgl-project#15632)
  Tiny add back missing router per attempt response metric (sgl-project#15621)
  Fix router gRPC mode launch error caused by async loading (sgl-project#15368)
  [model-gateway] return 503 when all workers are circuit-broken (sgl-project#15611)
  [Diffusion] Support peak memory record in offline generate and serving (sgl-project#15610)
  [VLM] Tiny: Unify VLM environment variables (sgl-project#15572)
  [diffusion] chore: remove default post-denoising dit offload in local mode (sgl-project#15573)
  Tiny enable soft watchdog in CI for stuck without logs (sgl-project#15616)
  Tiny add stuck simulation (sgl-project#15613)
  Support soft watchdog for tokenizer/detokenizer/dp-controller processes (sgl-project#15607)
  Tiny avoid EnvField misuse (sgl-project#15612)
  add decode round robin policy (sgl-project#15164)
  Add glm-4.6-fp8 with/without mtp in nightly ci (sgl-project#15566)
  Adapt fixture-kit to gsm8k mixin (sgl-project#15599)
  [model-gateway] add retry support to OpenAI router chat endpoint (sgl-project#15589)
  ...
jiaming1130 pushed a commit to zhuyijie88/sglang that referenced this pull request Dec 25, 2025
YChange01 pushed a commit to YChange01/sglang that referenced this pull request Jan 13, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Multi-modal multi-modal language model run-ci

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant