[Tests] Update Schemes

[dsikka]

SUMMARY:

• Latest CT introduces scale_dtype which if not provided, will use the weight dtype for the scales
• As a result, we no longer hardcode FP8 as the dtype when generating scales for NVFp4 and instead rely on this field. Update the tests to reflect this

Testing

• Addresses 2/14 failures. All other failures are coming from one test case which will be resolved in a follow-up

[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 @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 updates existing tests to accommodate a new scale_dtype parameter introduced in the compressed_tensors library. The change ensures that the scale data type for NVFp4 quantization is explicitly set, rather than relying on implicit behavior or hardcoding. This adjustment is crucial for maintaining correctness in quantization schemes and resolves several related test failures.

Highlights

• Test Scheme Updates: Updated test schemes to explicitly define scale_dtype for NVFp4 quantization, aligning with a recent change in the compressed_tensors library.
• New Import: Introduced the import of FP8_E4M3_DATA to correctly specify the FP8 E4M3 data type for scales in quantization tests.
• Test Fixes: Addressed and resolved 2 out of 14 existing test failures by incorporating the scale_dtype parameter.

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. ↩

[gemini-code-assist]

Code Review

This pull request updates test cases to accommodate a change in the compressed-tensors library, where the scale_dtype for quantization must now be explicitly provided. The changes correctly add the scale_dtype parameter to QuantizationArgs in two test cases within tests/llmcompressor/modifiers/calibration/test_lifecycle.py, ensuring the tests continue to function as expected after the dependency update. The implementation is straightforward and correct. I have no further comments.