[CI] improve disaggregation CI.

[hnyls2002]

For better running CI locally.

[gemini-code-assist]

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 significantly improves the flexibility and maintainability of the disaggregation Continuous Integration (CI) setup. By centralizing the configuration for disaggregation transfer backends and RDMA devices, it enables developers to easily customize these parameters using environment variables for local testing, while ensuring a consistent and robust setup for automated CI environments. This change streamlines the process of running and debugging disaggregation-related tests.

Highlights

• Centralized Disaggregation Configuration: The pull request centralizes the configuration of disaggregation transfer backend and RDMA devices into a utility file, test_disaggregation_utils.py, moving away from hardcoded values in individual test scripts.
• Environment Variable Support for Local Testing: New environment variables, SGLANG_TEST_PD_DISAGG_BACKEND and SGLANG_TEST_PD_DISAGG_DEVICES, have been introduced to allow for flexible configuration of disaggregation tests when running locally, enhancing the developer experience.
• Simplified Test Arguments: Hardcoded --disaggregation-ib-device and --disaggregation-transfer-backend arguments have been removed from various disaggregation test files, making the test code cleaner and more maintainable.

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 improves the disaggregation CI by centralizing test configurations for transfer backend and RDMA devices into a base class, using environment variables for local runs. This is a good refactoring that enhances configurability. My review includes a suggestion to improve the clarity and robustness of the new configuration logic by simplifying a piece of code and pointing out a naming ambiguity that could cause confusion across different test files.

[ShangmingCai]

What about the decode instances' ib devices like "mlx5_roce2,mlx5_roce3":

def start_decode(cls):
        decode_args = [
            "--trust-remote-code",
            "--disaggregation-mode",
            "decode",
            "--tp",
            "2",
            "--base-gpu-id",
            "2",
            "--disaggregation-ib-device",
            "mlx5_roce2,mlx5_roce3",
        ]

I can make a util to create a map for specific gpu index.