Skip to content

Conversation

@yiliu30
Copy link
Owner

@yiliu30 yiliu30 commented Nov 27, 2025

SUMMARY:
"please provide a brief summary"

TEST PLAN:
"please outline how the changes were tested"

@github-actions
Copy link

👋 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.

@yiliu30 yiliu30 changed the title Autoround version test [TEST]Autoround version test Nov 27, 2025
@gemini-code-assist
Copy link

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 focuses on enhancing the integration and stability of the auto-round quantization process. It updates the auto-round library to a specific release version, introduces a configurable batch size for finer control over quantization, and includes a minor type correction for the device argument to ensure seamless operation with the updated library.

Highlights

  • Dependency Update: The auto-round dependency has been updated from a direct git reference to a specific version, 0.9.1, ensuring a stable and released version is used.
  • New batch_size Parameter: A new batch_size parameter with a default value of 8 has been added to the AutoRoundModifier class, allowing for configurable batch processing during quantization.
  • Device Argument Type Fix: The device argument passed to the auto-round quantization function is now explicitly cast to a string, improving compatibility and robustness.
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.

Copy link

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request updates the auto-round dependency to a pinned version and adapts the AutoRoundModifier to the new version's API. The changes include pinning auto-round to version 0.9.1 in setup.py, adding a batch_size parameter to AutoRoundModifier, and ensuring the device parameter is passed as a string. The changes are correct and improve dependency management and fix compatibility issues. I've added a couple of suggestions to improve code documentation and clarity for future maintenance.

# AutoRound modifier arguments
iters: int = 200
enable_torch_compile: bool = True
batch_size: int = 8

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The new batch_size parameter should be documented. Please consider adding it to the class docstring, explaining its purpose, and including it in the sample YAML configuration to guide users on how to configure it. This will improve the usability of the modifier.

inputs=cur_inputs,
q_input=self._q_input,
device=device,
device=str(device),

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

This change to cast device to a string is a necessary fix. To improve code clarity for future maintainers, it would be helpful to add an inline comment explaining why this cast is needed, as the underlying auto-round library's expectation of a string is not immediately obvious.

Suggested change
device=str(device),
device=str(device), # auto-round expects device as a string

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants