Add fallback for sparsegpt inversion failure

[kylesayrs]

Purpose

• Add fallback for spgt inversion failure, which may occur randomly

[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 @kylesayrs, 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 enhances the robustness of the SparseGPT weight sparsification process by introducing a graceful fallback for numerical instability during Hessian inversion. Instead of crashing when a torch._C._LinAlgError occurs, the system will now log a warning and continue execution by providing a default identity matrix for the inverse Hessian, thereby preventing random failures and improving overall stability.

Highlights

• Error Handling & Robustness: Implemented a fallback mechanism for torch._C._LinAlgError during Hessian inversion in the sparsify_weight function. Previously, this error would halt execution, but now it logs a warning and proceeds by initializing Hinv and H as identity matrices.

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 is currently in preview and 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 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 introduces a fallback mechanism for Hessian matrix inversion failures, enhancing the robustness of the SparseGPT process. My review identifies a critical issue where the logger object is used in the new code without being imported, which would lead to a runtime error. I've provided feedback on this and a minor suggestion for code clarity.