[BugFix]Fix recomputed scheduler bug

[nwpu-zxr]

What this PR does / why we need it?

Fix the wrong usage of model_type.

Does this PR introduce any user-facing change?

No.

How was this patch tested?

By CI.

• vLLM version: v0.16.0
• vLLM main: vllm-project/vllm@4034c3d

[github-actions]

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

• A PR should do only one thing, smaller PRs enable faster reviews.
• Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
• Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

[gemini-code-assist]

Summary of Changes

Hello, 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 addresses a bug in the recompute scheduler where the model_type was being accessed incorrectly, potentially leading to misidentification of hybrid models. The fix updates the attribute path to ensure the scheduler correctly identifies specific models (Qwen3_next, Qwen3_5) by referencing hf_text_config.model_type. This change resolves the underlying issue and ensures proper scheduler behavior without introducing any user-facing modifications.

Highlights

• Bug Fix for Recompute Scheduler: Corrected the attribute path used to determine the model type within the RecomputeScheduler, specifically changing model_config.model_type to model_config.hf_text_config.model_type to accurately identify hybrid models like Qwen3_next and Qwen3_5.

🧠 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.

Changelog

• vllm_ascend/core/recompute_scheduler.py
  • Corrected the path for accessing the model type to hf_text_config.model_type when determining if a model is a hybrid type (Qwen3_next or Qwen3_5).

Activity

• No human activity has been recorded on this pull request yet.

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 correctly fixes a bug in RecomputeScheduler by using the right model_type from hf_text_config. This ensures that is_hybrid_model is determined correctly.

I've added one suggestion to improve the maintainability of the hybrid model check. By using a constant list of model substrings, it will be easier and less error-prone to add new hybrid models in the future.

[gemini-code-assist]

For better maintainability and to reduce the risk of future bugs when new hybrid models are introduced, it's better to define the hybrid model substrings in a constant and then check for membership. This makes it easier to update and manage the list of hybrid models.

        hybrid_models = ("qwen3_next", "qwen3_5")
        model_type = self.vllm_config.model_config.hf_text_config.model_type
        self.is_hybrid_model = any(s in model_type for s in hybrid_models)