[docs] Add autoround doc

[yiliu30]

The follow-up on #1994
The rendered version:
https://github.com/yiliu30/llm-compressor-fork/blob/autoround-doc/README.md
https://github.com/yiliu30/llm-compressor-fork/tree/autoround-doc/examples/autoround
https://github.com/yiliu30/llm-compressor-fork/blob/autoround-doc/docs/getting-started/compress.md

cc @hshen14 @thuang6 @wenhuach21

[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.

[gemini-code-assist]

Summary of Changes

Hello @yiliu30, 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 comprehensive documentation for the AutoRound quantization technique within the llm-compressor project. It aims to guide users through the process of applying AutoRound, from initial setup and calibration to evaluating the accuracy of the quantized models. This enhancement improves the project's usability by providing clear instructions and examples for leveraging this advanced low-bit quantization method.

Highlights

• New AutoRound Documentation: Comprehensive documentation for the AutoRound quantization technique has been added, detailing its installation, usage, and accuracy evaluation.
• Updated Compression Schemes Table: The compress.md guide now includes AutoRound in the table of available compression schemes, highlighting its benefits and methodology.
• Detailed Example Walkthrough: A new README.md file provides a step-by-step guide for applying AutoRound quantization, covering model loading, calibration data preparation, quantization application, and accuracy evaluation with lm_eval.

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 adds documentation for the AutoRound quantization method. It includes an update to the main compression guide and a new detailed README.md for the autoround example. The documentation is well-written and provides a good walkthrough for users. I've identified a couple of minor issues in the new README.md file related to a dependency version and a typo in a scheme name, which could cause confusion or errors for users. Once these are addressed, the documentation will be in great shape.

[hshen14]

@dsikka @kylesayrs @brian-dellabetta please help review. Thanks.

[dsikka]

This LGTM. do you mind adding a small blurb to our repo readme as well, under the What's New section?

[kylesayrs]

Thanks!

[hshen14]

This LGTM. do you mind adding a small blurb to our repo readme as well, under the What's New section?

Will do. Thanks for your suggestion!

[yiliu30]

This LGTM. do you mind adding a small blurb to our repo readme as well, under the What's New section?

Updated! Please take a look when you have a chance, thanks!