fix general sparse attn

[Musisoul]

handle #867 change in set_config.py

[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 an issue in the calculation of a critical parameter for sparse attention mechanisms within the transformer_weights module. By introducing a dynamic calculation for attnmap_frame_num based on video dimensions and patch sizes, it ensures that the attention mapping is correctly configured for different video inputs, improving the robustness and accuracy of the model's attention layers.

Highlights

• Dynamic attnmap_frame_num calculation: The attnmap_frame_num parameter, crucial for attention mechanisms, is now dynamically computed based on target_video_length, vae_stride, and patch_size instead of being directly read from the configuration.
• Application to attention types: This new calculation method has been applied to both nbhd_attn (neighborhood attention) and general_sparse_attn types, ensuring consistent and correct behavior across these sparse attention implementations.

🧠 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

• lightx2v/models/networks/wan/weights/transformer_weights.py
  • Modified the __init__ method to dynamically calculate attnmap_frame_num for nbhd_attn and nbhd_attn_flashinfer.
  • Modified the __init__ method to dynamically calculate attnmap_frame_num for general_sparse_attn.

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 fixes an issue with attnmap_frame_num by calculating it instead of relying on configuration. The calculation logic has been added in two places, resulting in code duplication. My review provides suggestions to simplify the added code and recommends a refactoring to eliminate the duplication, which will improve code maintainability.