Revert "[MoE] MiniMax-M2/M2.1 calibration follow-up (#2335)"

[dsikka]

This reverts commit 2ab0244.

SUMMARY:

• Multiple issues which were masked as the tests were skipped due to requiring transformers v5

[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 rolls back a prior change that aimed to integrate calibration support for MiniMax-M2 models. The original implementation inadvertently masked several issues because its associated tests were bypassed due to specific version requirements. This revert ensures the stability and integrity of the codebase by removing the problematic functionality and its related components.

Highlights

• Revert of MiniMax-M2 Calibration: This pull request fully reverts a previous commit that introduced calibration follow-up for MiniMax-M2/M2.1 models, addressing issues that arose from skipped tests.
• Removal of MiniMax-M2 Calibration Module: The CalibrationMiniMaxM2SparseMoeBlock module, designed for MiniMax-M2 calibration, has been removed from the codebase.
• Removal of Associated Files: The example script for MiniMax-M2 quantization and its corresponding unit tests have been removed as part of this revert.

🧠 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

This pull request reverts the addition of MiniMax-M2/M2.1 calibration support. The changes correctly remove the associated example, modeling code, and tests. The revert is self-contained and appears complete, with no dangling references found in the reviewed files.

[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.