[Docs] Add Falcon H1, Hunyuan-Large, Qwen3-Omni support and update Diffusion usage

[pokymono]

Motivation

The documentation for supported models was missing models such as Falcon H1, Hunyuan-Large, and Qwen3-Omni.
Adding a Diffusion to Basic Usage for better guidance.

Modifications

New Model Support:
Generative Models: Added Falcon H1 (0.5B–34B Hybrid Mamba-Transformer) and Hunyuan-Large (389B MoE).
Multimodal Models: Added Step3-VL (10B) and Qwen3-Omni (Omni-modal MoE).

Basic Usage:
Added/Updated Diffusion documentation in the Basic Usage section to provide clear guidance on diffusion language models as requested.

Accuracy Tests

Benchmarking and Profiling

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.
• Follow the SGLang code style guidance.

Review Process

1. Ping Merge Oncalls to start the PR flow. See the PR Merge Process.
2. Get approvals from CODEOWNERS and other reviewers.
3. Trigger CI tests with comments or contact authorized users to do so.
   • /tag-run-ci-label, /rerun-failed-ci, /tag-and-rerun-ci
4. After green CI and required approvals, ask Merge Oncalls to merge.

[gemini-code-assist]

Summary of Changes

Hello @pokymono, 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 enhances the project's documentation by incorporating several newly supported large language models and multimodal models. It also introduces a structured guide for diffusion models, distinguishing between those used for image/video generation and those for text generation, thereby improving clarity and discoverability for users.

Highlights

• New Generative Model Support: Added documentation for new generative models, including Falcon H1 (a hybrid Mamba-Transformer architecture) and Hunyuan-Large (a 389B Mixture of Experts model).
• New Multimodal Model Support: Included new multimodal models, Step3-VL (a 10B VLM) and Qwen3-Omni (an omni-modal MoE model), in the supported models list.
• Enhanced Diffusion Model Documentation: Introduced a dedicated documentation page for Diffusion models, categorizing them into image/video generation and diffusion language models, and updated existing diffusion model documentation to provide clearer cross-references.

🧠 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. ↩

[gemini-code-assist]

Code Review

This pull request updates the documentation to include newly supported models like Falcon H1, Hunyuan-Large, Step3-VL, and Qwen3-Omni. It also adds a new page for diffusion models, improving the overall structure and clarity of the documentation. The changes are well-executed, but I found a minor formatting issue in one of the updated tables.

[pokymono]

@Ratish1 Apologies for the previous PR, please check this one

[Ratish1]

Why do we need this file?, we already have this

sglang/docs/supported_models/diffusion_models.md

Line 1 in 452dce8

# Diffusion Models

basic_usage is model-specific folder only

[pokymono]

Adarsh asked me to add Diffusion in basic usage.

[Ratish1]

Also @pokymono , apply the gemini fix, there is a clear render bug for that file. Fix the lint error aswell

[Ratish1]

There still seems to be a lint error, make sure you are running the pre-commit command

[Ratish1]

LGTM

cc: @adarshxs

[adarshxs]

LGTM. cc @mickqian

[pokymono]

@zhaochenyang20 updated

[adarshxs]

LGTM cc @zhaochenyang20

[zhaochenyang20]

This doc is vibe-coded and introduces unexpected errors in our documentation. We shall spend more time evaluating this PR. @Ratish1

#19104