[BugFix] Improve GDN layer detection for multimodal models

[SlightwindSec]

Summary

• Enhanced check_gdn_layer() function to properly detect GDN layers in multimodal models
• Added support for checking text_config.layer_types in addition to root-level layer_types
• Fixed potential None reference errors when layer_types attribute is missing

Changes

• Modified vllm_ascend/utils.py:
  • Replaced hasattr() check with safer getattr() approach
  • Added fallback to empty list when layer_types is None
  • Added secondary check for text_config.layer_types to support models like Qwen-Omni

Motivation

Previous implementation only checked layer_types at the root config level, which failed to detect GDN layers in multimodal models where this information is nested under text_config. Additionally, it could raise errors when layer_types was None.

---

Co-authored-by: wanghuanjun2113 wanghuanjun2113@gmail.com
Co-authored-by: SlightwindSec slightwindsec@gmail.com

🤖 Generated with Claude Code

• vLLM version: v0.16.0
• vLLM main: vllm-project/vllm@15d76f7

[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 significantly improves the robustness and compatibility of GDN layer detection within the vllm_ascend framework. By extending the detection logic to account for nested layer_types in multimodal model configurations and implementing safer attribute access, it ensures that GDN layers are correctly identified across a broader range of models, preventing previous detection failures and potential runtime errors.

Highlights

• GDN Layer Detection: The check_gdn_layer() function has been enhanced to accurately detect GDN layers within multimodal models.
• Multimodal Support: Support was added for checking text_config.layer_types, which is crucial for models like Qwen-Omni.
• Error Handling: Potential None reference errors when layer_types is missing have been fixed by providing a fallback to an empty list.

🧠 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/utils.py
  • Replaced hasattr() with getattr() for safer attribute access.
  • Added a fallback to an empty list when layer_types is None.
  • Implemented a secondary check for text_config.layer_types to support multimodal models.

Activity

• The check_gdn_layer function was updated to improve detection logic.
• Testing was performed with the Qwen3-Omni multimodal model.
• Backward compatibility with existing single-modal models was verified.
• All unit tests passed successfully.
• The changes were co-authored by wanghuanjun2113 and SlightwindSec.

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 enhances the check_gdn_layer function in vllm_ascend/utils.py to improve the detection of GDN layers, particularly for multimodal models. The changes introduce support for checking text_config.layer_types in addition to the root-level layer_types and fix a potential None reference error by using getattr with a fallback. The implementation is correct and addresses the stated goals effectively. I have no major concerns with this change.

[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.