[Bugfix] QAC with basic pipeline

[kylesayrs]

Purpose

• Support modifiers which disable quantization-aware-calibration like GPTQ in the basic pipeline

Changes

• Disable QAC in the basic pipeline for DISABLE_QAC_MODIFIERS

[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, 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 addresses a bug by enhancing the basic pipeline to support modifiers that necessitate the disabling of Quantization-Aware Calibration (QAC). The changes ensure that the calibration process correctly adapts to specific quantization techniques, such as GPTQ, by providing a mechanism to selectively bypass QAC when required, thereby improving the robustness and compatibility of the compression pipeline.

Highlights

• Quantization-Aware Calibration (QAC) Control: Introduced functionality to conditionally disable Quantization-Aware Calibration (QAC) within the basic pipeline.
• Modifier Compatibility: Implemented a mechanism to detect specific modifiers (e.g., GPTQ) that require QAC to be disabled, ensuring proper compatibility.
• Dynamic Quantization Disablement: Added a conditional context manager to disable quantization during calibration if QAC is not desired or if a disabling modifier is present.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog

• src/llmcompressor/pipelines/basic/pipeline.py
  • Imported DISABLE_QAC_MODIFIERS and DisableQuantization from llmcompressor.utils.helpers.
  • Added logic to check for modifiers that disable QAC and conditionally apply a DisableQuantization context during calibration.

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 aims to disable quantization-aware calibration (QAC) for certain modifiers like GPTQ in the basic pipeline. The implementation correctly identifies when to disable QAC based on the active modifiers. However, I found a critical issue where the code does not handle cases where dataset_args is None, which will lead to a crash. I've provided a suggestion to fix this.

[gemini-code-assist]

The dataset_args object can be None, for example when the run_calibration helper function is used. In that case, accessing dataset_args.quantization_aware_calibration will raise an AttributeError.

You should handle the case where dataset_args is None. Based on the DatasetArguments definition, the default value for quantization_aware_calibration is True, which should be used when dataset_args is not provided.

Suggested change

	if not dataset_args.quantization_aware_calibration or disable_qac:
	if not (dataset_args.quantization_aware_calibration if dataset_args else True) or disable_qac:

[mergify]

The quality checks have failed. Please run make style and make quality under
the root directory to adddress the lint failures. You will need to install the
dev optional install to get the required linting packages:
https://github.com/vllm-project/llm-compressor/blob/main/CONTRIBUTING.md