[Cache] Check cache before recipe fetch, for offline mode

[ralphbean]

Previously, recipe_from_huggingface_model_id() would attempt network
requests to huggingface.co even in offline environments, causing
connection errors during model saving when trying to fetch recipe.yaml.

This change supports offline operation by:

• Checking local HuggingFace cache for recipe.yaml before attempting
  network requests using try_to_load_from_cache()
• Respecting HF_HUB_OFFLINE environment variable to skip network
  requests when explicitly in offline mode

[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 @ralphbean, 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 significantly enhances the application's ability to function seamlessly in offline environments by optimizing how model recipes are fetched from Hugging Face. It introduces a proactive check of the local cache for recipe.yaml and ensures that network requests are bypassed when the HF_HUB_OFFLINE environment variable is active, preventing connection errors during model operations. This change also streamlines the handling of cache directories, relying on Hugging Face's internal logic for more consistent and flexible caching.

Highlights

• Offline Mode Support: The application now robustly supports offline environments by first checking the local Hugging Face cache for model recipes before attempting network requests.
• HF_HUB_OFFLINE Environment Variable: The system explicitly respects the HF_HUB_OFFLINE environment variable, allowing users to completely skip network requests when operating in an offline mode.
• Cache Directory Management Simplification: Explicit cache_dir parameters have been removed or set to None across various functions, delegating cache path resolution to Hugging Face's default mechanisms and environment variables (e.g., HF_HOME, HF_HUB_CACHE).

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 enhances the application's ability to operate in offline environments by checking the local Hugging Face cache for recipe files and respecting the HF_HUB_OFFLINE environment variable. This prevents unnecessary network requests when offline. The changes involve modifying several files to remove the cache_dir argument and updating the recipe loading logic to prioritize the local cache and respect the offline mode setting.

[kylesayrs]

Awesome, great job

[brian-dellabetta]

👍