Add E2E test config for AWQ symmetric quantization

[WenheLI]

Adding a PR to try to add e2e test for resolving this ticket:
#1852
Still new to this codebase, so not sure if this aligns with what we want to do.
Let me know if I miss anything

[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 @WenheLI, 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 introduces a new end-to-end test configuration designed to validate the implementation of AWQ symmetric quantization. By adding a dedicated YAML file, it sets up a regression test for the TinyLlama model using a specific W4A16 quantization scheme and a defined dataset for calibration, directly contributing to the resolution of a reported issue.

Highlights

• New E2E Test Configuration: A new end-to-end test configuration file (w4a16_grouped_quant_sym_awq.yaml) has been added to enable testing for AWQ symmetric quantization.
• Quantization Scheme and Model: The configuration specifies the W4A16_weight_sym_awq scheme for the TinyLlama/TinyLlama-1.1B-Chat-v1.0 model, including details for dataset and calibration.
• Issue Resolution: This pull request directly addresses issue [Help Wanted] Add AWQ E2E tests #1852, aiming to provide a robust test for its resolution.

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 introduces a new end-to-end test configuration for AWQ symmetric quantization, which is a valuable addition for regression testing. The configuration is mostly well-defined. My review includes a couple of suggestions to improve the test's performance within the CI environment and enhance the configuration's maintainability by leveraging automatic value generation from the test framework.

[fynnsu]

Hi @WenheLI, this looks great, thank you for submitting! I left a couple comments below for things to fix before we merge this.

Also it looks like the DCO check if failing currently. We require contributors to sign their commits. There's more info on the failing check for how to fix this.

Once those changes are in, I will approve the pr.

[fynnsu]

Great job!

[brian-dellabetta]

Thanks for the contribution! the default num_calibration_samples=256 should be fine