-
Notifications
You must be signed in to change notification settings - Fork 156
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
base: main
Are you sure you want to change the base?
Remove oneshot_device
#1568
Conversation
👋 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. |
There was a problem hiding this 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 theModelArguments
class insrc/llmcompressor/args/model_arguments.py
and from theoneshot
entrypoint function insrc/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 withintests/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
-
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. ↩
There was a problem hiding this 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.
There was a problem hiding this 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,
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. |
Signed-off-by: Kyle Sayers <[email protected]>
Will approve on behalf of @dsikka |
Summary