fix: head dim pad in model config

[Prayer3th]

When passing head_dim from model_config to the attention layer, it must align with the padding specified in weight_loader

[gemini-code-assist]

Summary of Changes

Hello @Prayer3th, 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 introduces a fix to ensure that the head_dim parameter in the model configuration is always padded to a multiple of 128. This change is implemented by adding a dedicated utility function to calculate the padded dimension and then applying this value during the model loading process. The primary goal is to enhance compatibility and potentially improve performance, especially when working with hardware accelerators that benefit from such memory alignment.

Highlights

• New Utility Method: A new method, get_padded_head_dim, has been added to the ModelConfig class. This method calculates a head dimension that is padded up to the nearest multiple of 128, which is often crucial for performance optimization in deep learning models.
• Head Dimension Alignment: The load_model function in ModelRunner now utilizes the new get_padded_head_dim method to ensure that the head_dim within the hf_config (Hugging Face configuration) is correctly aligned to a multiple of 128 during model initialization.

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. ↩