Skip to content

Remove oneshot_device #1568

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open

Remove oneshot_device #1568

wants to merge 5 commits into from

Conversation

dsikka
Copy link
Collaborator

@dsikka dsikka commented Jun 18, 2025

Summary

  • Not used and annoying to see everywhere

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.

Copy link
Contributor

@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.

Summary of Changes

Hello @dsikka, 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 a targeted cleanup of the codebase by eliminating the oneshot_device parameter. This parameter was identified as deprecated and non-functional, and its removal simplifies the llmcompressor API, streamlines the oneshot functionality, and improves overall code maintainability by removing obsolete elements and their associated test references.

Highlights

  • Codebase Cleanup: I've removed the oneshot_device argument from the ModelArguments class in src/llmcompressor/args/model_arguments.py and from the oneshot entrypoint function in src/llmcompressor/entrypoints/oneshot.py. This parameter was previously marked as deprecated and unused, simplifying the API and reducing clutter.
  • Test Suite Updates: All references and usages of the oneshot_device parameter have been removed across numerous test files within tests/llmcompressor/transformers/, ensuring the test suite remains consistent with the updated API.
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.

Copy link
Contributor

@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 effectively removes the deprecated and unused oneshot_device argument from the codebase. The changes are clean and applied consistently across definition and call sites. One minor point of attention is an apparently leftover variable definition in tests/llmcompressor/transformers/obcq/test_oneshot_with_modifier.py that likely became unused due to these changes. Addressing this would complete the cleanup.

@dsikka dsikka added the ready When a PR is ready for review label Jun 18, 2025
Copy link
Collaborator

@kylesayrs kylesayrs left a comment

Choose a reason for hiding this comment

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

(env) kyle@janice:~/llm-compressor$ grep -r 'oneshot_device' src/ examples/ tests/ --include="*.py"
tests/llmcompressor/transformers/obcq/test_obcq_sparsity.py:            oneshot_device=self.device,
tests/llmcompressor/transformers/sparsification/test_compress_tensor_utils.py:        oneshot_device=device,
tests/llmcompressor/transformers/sparsification/test_compress_tensor_utils.py:        oneshot_device=device,
tests/llmcompressor/transformers/sparsification/test_compress_tensor_utils.py:        oneshot_device=device,
tests/llmcompressor/transformers/sparsification/test_compress_tensor_utils.py:        oneshot_device=device,

@kylesayrs
Copy link
Collaborator

I agree with this philosophically. Device handling will only become more complicated as of #1558. The user can control which device use to via environment variables, but beyond that we should control all other device dispatching.

@kylesayrs kylesayrs removed the ready When a PR is ready for review label Jun 18, 2025
@kylesayrs kylesayrs marked this pull request as ready for review June 19, 2025 22:46
@kylesayrs
Copy link
Collaborator

kylesayrs commented Jun 20, 2025

Will approve on behalf of @dsikka

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants