[Auto Sync] Update activation.py, logits_processor.py, rota... (20251107)

[merrymercy]

Sync changes from commit e0a34788.

Files Changed:

• python/sglang/srt/layers/activation.py
• python/sglang/srt/layers/logits_processor.py
• python/sglang/srt/layers/rotary_embedding.py
• python/sglang/srt/layers/sampler.py
• python/sglang/srt/models/qwen2.py
• python/sglang/srt/models/qwen3.py
• python/sglang/srt/server_args.py

Author: Stefan He hebiaobuaa@gmail.com

---

This is an automated PR created by scripts/copy_from_oss.py.

[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 is an automated synchronization of recent changes, primarily focusing on making the rl_on_policy_target configuration more flexible. It refactors conditional checks to be less specific, allowing the system to adapt to various on-policy targets beyond a single hardcoded value. Additionally, it enhances the command-line argument parsing to support a broader range of rl_on_policy_target options dynamically.

Highlights

• Generalization of rl_on_policy_target check: The condition get_global_server_args().rl_on_policy_target == "fsdp" has been generalized to get_global_server_args().rl_on_policy_target is not None across multiple files, making the logic applicable to any configured on-policy target, not just 'fsdp'.
• Extensible rl_on_policy_target choices: The server_args.py file has been updated to introduce a dynamic list RL_ON_POLICY_TARGET_CHOICES and a function add_rl_on_policy_target_choices to allow for extending the available options for the --rl-on-policy-target command-line argument.

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 is an automated sync that generalizes the handling of the rl_on_policy_target server argument. The changes replace specific checks for this argument being equal to 'fsdp' with a more general check for it not being None. This makes the feature applicable to any on-policy reinforcement learning target, not just FSDP. Additionally, server_args.py is updated to make the list of choices for this argument extensible. The changes are consistent across all modified files and improve the code's maintainability and extensibility. The implementation is correct and I have no further suggestions.