Clean up server args & Add CI scripts

[merrymercy]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @merrymercy, 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 primarily focuses on enhancing the maintainability and clarity of server configurations by extensively refactoring and cleaning up server arguments. It also updates the project's documentation to reflect broader platform support and introduces new automation scripts for managing CI infrastructure.

Highlights

• Server Argument Refactoring: Numerous server arguments within the ServerArgs dataclass and add_cli_args function in python/sglang/srt/server_args.py have been reorganized and reordered for improved clarity and logical grouping.
• Deprecated Argument Removal: Several deprecated MoE-related command-line arguments have been removed from the add_cli_args function, streamlining the available options.
• Documentation Updates: The installation guide (docs/get_started/install.md) has been updated to include new platform references such as TPU and NVIDIA DGX Spark.
• CI Runner Scripts: A new suite of shell scripts has been introduced in scripts/ci_config_runner/ to automate the configuration and management of GitHub Actions self-hosted runners, including Docker and NVIDIA container toolkit setup.
• Code Enhancements: Comments were added to launch_server.py for better server type identification, and lru_cache was applied to the is_npu function in utils/common.py for potential performance benefits.

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 provides a good cleanup of the server arguments, improving the organization and maintainability of the configuration code. The addition of CI runner scripts is also a valuable contribution. My feedback focuses on improving the robustness and security of these new scripts, with a critical suggestion to avoid hardcoding secret placeholders.

[gemini-code-assist]

Hardcoding the runner version and its checksum can make future updates more difficult. Consider defining these as variables at the top of the script for easier maintenance.