Add Attention Quantization Examples

[kylesayrs]

Purpose

• Move FP8 per-head attention quantization example out of experiment folder to reflect current support in vLLM

Changes

• Move FP8 example and readme section out of experimental folder

[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 introduces initial examples for attention quantization by creating a dedicated directory and relocating an existing Llama 3 attention script. The primary goal is to provide a structured location for these examples, though further content, specifically evaluation metrics, is still pending.

Highlights

• New Example Directory: A new directory examples/quantization_attention has been introduced to house examples related to attention quantization.
• Llama 3 Attention Example: The llama3_attention.py script, previously in experimental/attention, has been moved and renamed to examples/quantization_attention/llama3_attention.py.
• README Placeholder: A placeholder README.md file has been added to the new example directory, indicating that evaluation numbers are still needed.

🧠 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.

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.

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

The pull request involves adding attention quantization examples. The changes include adding a README file and renaming a Python file, along with a minor modification to import order in the Python file. There is a medium severity issue regarding the TODO in the README file.

[github-actions]

👋 Hi! Thank you for contributing to llm-compressor. Please add the ready label when the PR is ready for review.

Note: This is required to complete the testing suite, please only add the label once the PR is code complete and local testing has been performed.

[brian-dellabetta]

LGTM, pending broken link

[dsikka]

Can you update the repo readme as well?