[fix] Update deprecated sglang ep args in docs and scripts

[guapisolo]

as the title

[gemini-code-assist]

Summary of Changes

Hello @guapisolo, 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 addresses the deprecation of certain sglang command-line arguments by updating them to their current equivalents in both example scripts and user documentation. Concurrently, it streamlines the documentation related to FSDP, reflecting its experimental status and removing detailed usage instructions. The overall impact is to ensure that the provided examples and guides are up-to-date with the latest sglang API and to clarify the current level of support for FSDP.

Highlights

• SGLang Argument Updates: Deprecated SGLang Expert Parallelism (EP) arguments like --sglang-enable-ep-moe have been updated to the new --sglang-ep-size format across various documentation and script files.
• DeepEP MoE Argument Refinement: The --sglang-enable-deepep-moe argument has been replaced with --sglang-moe-a2a-backend deepep to reflect updated DeepEP Mixture of Experts configuration.
• FSDP Documentation Revision: The documentation for FSDP (Fully Sharded Data Parallel) has been significantly revised, including marking it as experimental and removing a dedicated 'How to Use FSDP' section, indicating a potential shift in its support or status.

Changelog

• docs/en/examples/deepseek-r1.md
  • Updated --sglang-enable-ep-moe to --sglang-ep-size 64.
  • Updated --sglang-enable-deepep-moe to --sglang-moe-a2a-backend deepep.
• docs/en/examples/qwen3-30B-A3B.md
  • Updated --sglang-enable-ep-moe to --sglang-ep-size 8.
  • Updated --sglang-enable-ep-moe to --sglang-ep-size 24.
• docs/en/get_started/usage.md
  • Removed 'or FSDP' from the description of training backend loading.
  • Marked fsdp training backend as '(experimental)'.
  • Updated the description of SGLang parameters for multi-node large EP inference, replacing --sglang-enable-ep-moe with --sglang-ep-size and --sglang-enable-deepep-moe with --sglang-moe-a2a-backend deepep.
  • Removed the entire 'How to Use FSDP' section, including its parameter table and quick start guide.
• scripts/run-deepseek-r1.sh
  • Updated --sglang-enable-ep-moe to --sglang-ep-size 64.
  • Updated --sglang-enable-deepep-moe to --sglang-moe-a2a-backend deepep.
• scripts/run-kimi-k2-Instruct.sh
  • Updated commented-out line # --sglang-enable-deepep-moe to # --sglang-moe-a2a-backend deepep.
• scripts/run-kimi-k2-Thinking.sh
  • Updated commented-out line # --sglang-enable-deepep-moe to # --sglang-moe-a2a-backend deepep.
• scripts/run-qwen3-32B.sh
  • Removed commented-out line # --sglang-enable-ep-moe.

Activity

• The pull request was created by guapisolo.
• No additional human activity (comments, reviews, or progress updates) has been recorded since its creation.

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 updates deprecated sglang arguments (--sglang-enable-ep-moe and --sglang-enable-deepep-moe) across documentation files and example scripts. No security vulnerabilities were found. However, a critical typo was identified in one of the updated arguments in an example script. Additionally, the removal of a large section of FSDP documentation seems out of scope for this PR and should be addressed in a separate pull request for clarity.

[gemini-code-assist]

There appears to be a typo in this argument. It starts with four dashes (----) instead of the standard two (--), which will cause the command to fail when executed.

Suggested change

	----sglang-ep-size 64
	--sglang-ep-size 64