Refine naming

[ispobock]

Motivation

unify sink interface name for better compatibility for more attention backends

[gemini-code-assist]

Summary of Changes

Hello @ispobock, 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!

I've made a focused change to refine the naming convention for the 'sink' interface across the attention backend implementations. This involves consistently renaming the sk parameter and related internal variables to sinks or sink_ptr throughout the codebase. The primary goal is to unify the interface name, which improves compatibility and clarity for various attention backends, making the code more readable and maintainable.

Highlights

• Parameter Renaming in Triton Backend: The parameter sk has been renamed to sinks in the forward_extend and forward_decode functions, ensuring consistent naming for the sink interface.
• Triton Kernel Variable Updates: Internal Triton kernel functions and their parameters, such as _fwd_kernel_stage2 and _fwd_kernel, have been updated to use sink_ptr instead of sk_ptr and HAS_SINK instead of HAS_SK.
• Unified Attention Function Signatures: All attention-related functions, including decode_attention_fwd_normal, decode_attention_fwd_grouped, decode_attention_fwd, and extend_attention_fwd, now consistently use sinks as the parameter name for the sink interface.
• Model Integration Update: The gpt_oss.py model's forward_core method has been updated to reflect the new sinks parameter name when calling the attention module.

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 or fill out our survey to provide feedback.

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 provides a clean and consistent refactoring by renaming the sk variable and its derivatives to sinks. This change improves code clarity and readability across multiple files related to the attention mechanism, including Triton kernels. The new naming is more descriptive and has been applied correctly throughout the codebase. The changes are sound, and I have no further recommendations.