Add OOM handling for RunInference with model manager

[AMOOOMA]

Make sure the code is resilient against failures.
Also made logging info optional so that we don't incur cost with the model manager by default.

---

Thank you for your contribution! Follow this checklist to help us incorporate your contribution quickly and easily:

• Mention the appropriate issue in your description (for example: addresses #123), if applicable. This will automatically add a link to the pull request in the issue. If you would like the issue to automatically close on merging the pull request, comment fixes #<ISSUE NUMBER> instead.
• Update CHANGES.md with noteworthy changes.
• If this contribution is large, please file an Apache Individual Contributor License Agreement.

See the Contributor Guide for more tips on how to make review process smoother.

To check the build health, please visit https://github.com/apache/beam/blob/master/.test-infra/BUILD_STATUS.md

GitHub Actions Tests Status (on master branch)

See CI.md for more information about GitHub Actions CI or the workflows README to see a list of phrases to trigger workflows.

[gemini-code-assist]

Summary of Changes

Hello @AMOOOMA, 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 robustness of the RunInference transform within Apache Beam's ML inference capabilities. By introducing a dedicated Out-Of-Memory (OOM) protection mechanism, it ensures that model loading and inference execution can gracefully handle CUDA OOM errors, attempting memory cleanup and guaranteeing resource release to prevent system instability and improve overall reliability.

Highlights

• OOM Protection Mechanism: Introduced a new OOMProtectedFn class designed to wrap functions and catch CUDA Out-Of-Memory exceptions. Upon catching such an exception, it attempts to clean up memory using gc.collect() and torch.cuda.empty_cache() before re-raising the original exception.
• Robust Model Loading: The loader_func used for acquiring models via MultiProcessShared is now wrapped with OOMProtectedFn, ensuring that model loading operations are resilient to CUDA OOM errors.
• Resilient Inference Execution: The _model_handler.run_inference method, responsible for executing inference, is now also wrapped with OOMProtectedFn to handle potential CUDA OOM errors during the inference process.
• Guaranteed Model Release: Modified the _run_inference method to use a try...finally block around the inference execution. This ensures that the model is always released, even if an exception (including OOM) occurs during run_inference.

🧠 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

• sdks/python/apache_beam/ml/inference/base.py
  • Added OOMProtectedFn class to handle CUDA OOM exceptions and perform memory cleanup.
  • Wrapped loader_func with OOMProtectedFn for resilient model loading.
  • Wrapped _model_handler.run_inference with OOMProtectedFn for robust inference execution.
  • Refactored model release logic into a try...finally block to ensure consistent resource cleanup.

Activity

• No specific activity (comments, reviews, etc.) was provided in the context.

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. ↩