Disables implicit GPTQ quantization using dtype_policy setter

[JyotinderSingh]

GPTQ requires a sophisticated config and a calibration dataset to function, which makes the implicit quantization behavior using the dtype_policy setter unsuitable.

[gemini-code-assist]

Summary of Changes

Hello @JyotinderSingh, 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 safeguard to prevent the implicit application of GPTQ quantization through the dtype_policy setter. Given GPTQ's specific requirements for configuration and calibration data, this change ensures that users are guided towards the explicit .quantize() method, thereby avoiding potential misconfigurations or unexpected behavior when attempting to use GPTQ.

Highlights

• Prevent GPTQ via dtype_policy setter: The dtype_policy setter in keras/src/layers/layer.py now explicitly disallows setting GPTQ quantization mode. Attempting to set dtype_policy to a GPTQ-related string (e.g., "gptq/4/-1_from_float32") will now raise a ValueError.
• Improved Error Messaging: A ValueError is raised with a clear message indicating that GPTQ quantization is unsupported via dtype_policy due to its requirements for a calibration dataset and GPTQConfig, directing users to the .quantize() method instead.
• New Test Case: A new test, test_gptq_quantization_by_setting_dtype, has been added to keras/src/layers/layer_test.py to verify that setting the dtype_policy to a GPTQ string correctly raises the expected ValueError.

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 correctly disables implicit GPTQ quantization via the dtype_policy setter by raising a ValueError. My review focuses on improving the user-facing error message to be more informative and align with the Keras API design guidelines for error messages. I've also updated the corresponding test to be more robust and match the improved error message.

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 82.36%. Comparing base (9fc8185) to head (75b54c3).

Additional details and impacted files

@@           Coverage Diff           @@
##           master   #21895   +/-   ##
=======================================
  Coverage   82.36%   82.36%           
=======================================
  Files         578      578           
  Lines       59816    59818    +2     
  Branches     9387     9388    +1     
=======================================
+ Hits        49270    49272    +2     
  Misses       8147     8147           
  Partials     2399     2399           

Flag	Coverage Δ
keras	82.19% <100.00%> (+<0.01%)	⬆️
keras-jax	62.77% <100.00%> (+<0.01%)	⬆️
keras-numpy	57.44% <100.00%> (+<0.01%)	⬆️
keras-openvino	34.32% <0.00%> (-0.01%)	⬇️
keras-tensorflow	64.33% <100.00%> (+<0.01%)	⬆️
keras-torch	63.37% <100.00%> (+<0.01%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.