Fix: rmsnorm_kernel config ignored when flash attention is not enabled

[sitatec]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @sitatec, 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 where the RMSNorm kernel optimization was inadvertently tied to the activation of the Flash Attention kernel. By moving the RMSNorm kernel integration logic outside the Flash Attention conditional block, this change ensures that the use_rmsnorm_kernel configuration is respected independently, allowing the RMSNorm optimization to be applied even when Flash Attention is not in use.

Highlights

• RMSNorm Kernel Activation: The logic for integrating the RMSNorm kernel has been decoupled from the Flash Attention kernel activation. Previously, the RMSNorm kernel would only be considered if Flash Attention was also enabled, leading to its configuration being ignored in other scenarios.

🧠 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/input_encoders/lightllm/qwen25_text_encoder_kernel.py
  • The if self.use_rmsnorm_kernel: block, responsible for importing and applying the rmsnorm kernel, was moved out of the if self.use_flash_attention_kernel: block. This change ensures that the RMSNorm kernel is initialized based on its own configuration flag, rather than being dependent on Flash Attention.

Activity

• No human activity (comments, reviews, etc.) has been recorded for 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 where the RMSNorm kernel optimization was only applied if Flash Attention was also enabled. By moving the RMSNorm logic out of the conditional block for Flash Attention, the two optimizations are now independent, which aligns with their separate configuration flags. The change is straightforward and correct.