Add MXFP8 Example

[yiliu30]

SUMMARY:
As the title.
Depends on vllm-project/compressed-tensors#630

TEST PLAN:

========== SAMPLE GENERATION ==============
The attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
Hello my name is James and I am 20 years old. I am an aspiring musician and I am currently studying
==========================================

Checkpoints:

• https://huggingface.co/INC4AI/Qwen3-8B-MXFP8A16-LLMC-TEST-ONLY
• https://huggingface.co/INC4AI/Qwen3-8B-MXFP8-LLMC-TEST-ONLY

cc @hshen14 @thuang6

[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 experimental support for MXFP8 quantization within LLM Compressor, enabling users to quantize both weights and activations using this scheme. It includes a new example script demonstrating how to apply MXFP8 quantization to a Qwen3-8B model and updates the project's README.md to document this new capability and provide a direct link to the example.

Highlights

• MXFP8 Microscale Support: LLM Compressor now experimentally supports MXFP8 quantization for both weights and activations via Post-Training Quantization (PTQ), including a new example script.
• Documentation Update: The README.md has been updated to reflect the new MXFP8 support and link to the corresponding example.

🧠 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. ↩

[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]

Code Review

This pull request introduces experimental MXFP8 quantization support, updating the README.md to reflect this new feature and providing a concrete Python example script. The example script demonstrates how to apply MXFP8 quantization to a Qwen3-8B model using llmcompressor and then perform a sample generation. The changes are well-aligned with the PR's objective.

[brian-dellabetta]

Thank you @yiliu30 !