Update the docs for --async-scheduling compatibility

[zhandaz]

Overview

Updates the documentation for --async-scheduling flag in Qwen3-VL and GPT-OSS guides to reflect compatibility improvements in new vLLM releases.

• Updated notes about --async-scheduling to indicate that vLLM >= 0.11.1 now provides compatibility with structured output
• Clarified that async scheduling stability has been improved in recent releases
• Encourages users to check latest releases for continued improvements

Context

The --async-scheduling flag was previously incompatible with structured outputs. This limitation was resolved in vLLM 0.11.1 (merged in #26866), along with other improvements: penalty fix 1 #26467 (included in 0.11.1), penalty fix 2 #27910 (included in 0.11.1), spec decode #29223 (merged but not included in 0.11.2).

[gemini-code-assist]

Summary of Changes

Hello @zhandaz, 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 updates the documentation for the --async-scheduling flag across the Qwen3-VL and GPT-OSS guides. The primary goal is to inform users about recent advancements in vLLM, specifically that versions 0.11.1 and later now support structured output with asynchronous scheduling and offer improved stability. This ensures the documentation accurately reflects the current capabilities and recommendations for leveraging this performance-enhancing feature.

Highlights

• Documentation Update for --async-scheduling: The documentation for the --async-scheduling flag in both Qwen3-VL and GPT-OSS guides has been updated to reflect recent compatibility improvements.
• Structured Output Compatibility: vLLM versions 0.11.1 and newer now provide compatibility with structured output when using --async-scheduling, resolving a previous limitation.
• Improved Stability: Recent vLLM releases have significantly improved the stability of asynchronous scheduling.
• User Guidance: The updated documentation encourages users to check the latest vLLM releases for continued improvements in async scheduling.

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 for the --async-scheduling flag in GPT-OSS.md and Qwen3-VL.md to reflect recent compatibility improvements in vLLM. The changes are generally good and informative. I've provided a few suggestions to improve clarity, consistency, and accuracy. The most important feedback is regarding a potentially misleading statement in Qwen/Qwen3-VL.md where a warning about incompatibility with speculative decoding was removed, while it seems it should be preserved based on the PR description. Other comments focus on improving the wording for conciseness and consistency across the documents.