mlapo fit different hidden state dim

[Todobe]

Modify the MLAPO op to be compatible with hidden state dimensions of different sizes.

Test Result：

DeepSeek（hidden state dim：7168）

LongCat（hidden state dim：6144）

[gemini-code-assist]

Summary of Changes

Hello @Todobe, 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 adaptability of the MLAPO operation by enabling it to work with neural network models that have varying hidden state dimensions. This change allows the operation to be more broadly applicable without requiring code modifications for different model architectures, making it more robust and reusable.

Highlights

• Dynamic Hidden State Dimension: The MLAPO operation has been modified to dynamically accept and utilize different hidden state dimensions, moving away from a hardcoded constant.
• Code Refactoring: The hardcoded HIDDEN_STRATE constant has been removed from various files and replaced with a hiddenStateDim parameter or member variable, enhancing flexibility.
• Memory Allocation Adjustment: Buffer allocation calculations within the kernel operations (mla_preprocess_mix_bf16.hpp and mla_preprocess_mix_fp16.hpp) now correctly use the dynamic hidden state dimension.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 successfully refactors the MLAPO op to support variable hidden state dimensions, removing the previously hardcoded value. The changes are well-implemented across the host and kernel code, passing the dynamic dimension down from the op's input tensor. My review includes a couple of suggestions to improve the readability and maintainability of buffer offset calculations within the kernel files, which currently use repetitive expressions.