Add kimi k2 thinking to ci

[ispobock]

Motivation

Add kimi k2 thinking to ci.

[gemini-code-assist]

Summary of Changes

Hello @ispobock, 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 introduces comprehensive testing for the moonshotai/Kimi-K2-Thinking model, integrating it directly into the continuous integration pipeline. The changes ensure that the model's functionality and performance, particularly on the GSM8K benchmark, are automatically validated with specific configurations, thereby enhancing the overall stability and reliability of the project's model integrations.

Highlights

• New Model Test: A new test file, test_kimi_k2_models.py, has been added to validate the moonshotai/Kimi-K2-Thinking model.
• CI Integration: The newly created test for the Kimi-K2-Thinking model has been integrated into the per-commit-8-gpu continuous integration suite, ensuring automated validation.
• Model Configuration: The test sets up the Kimi-K2-Thinking model with specific server arguments, including 8-way tensor parallelism (--tp 8) and dedicated kimi_k2 parsers for both tool-call and reasoning.
• Performance Assertion: The test includes a few_shot_gsm8k evaluation, asserting that the Kimi-K2-Thinking model achieves an accuracy greater than 0.95 when executed within the CI environment.

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. ↩

[gemini-code-assist]

Code Review

This pull request adds a new test for the Kimi-K2-Thinking model and integrates it into the CI test suite. My review focuses on improving code robustness in the new test file and maintaining code style in the test suite configuration. I've suggested a more robust way to parse the host and port for the test server and recommended reordering the new test entry to adhere to the alphabetical sorting convention in the test suite.

[ispobock]

ci passed: https://github.com/sgl-project/sglang/actions/runs/19204370978/job/54899717469?pr=12907