Add model manager that automatically manage model across processes

[AMOOOMA]

Added Model Manager as a util class that offers managed access to models, the client can request models without having to worry about managing GPU OOMs.
Also added various tests that checks the functions of all classes.

Classes

GPUMonitor

• start(): Begins background memory polling.
• stop(): Stops polling.
• reset_peak(): Resets peak usage tracking.
• get_stats() -> (current, peak, total): Returns memory stats.

ResourceEstimator

• is_unknown(model_tag: str) -> bool: Checks if model needs profiling.
• get_estimate(model_tag: str, default_mb: float) -> float: Returns memory cost.
• set_initial_estimate(model_tag: str, cost: float): Manually sets cost.
• add_observation(active_snapshot, peak_memory): Updates cost model via NNLS solver.

ModelManager

• acquire_model(tag: str, loader_func: Callable) -> Any: Gets model instance (handles isolation/concurrency).
• release_model(tag: str, instance: Any): Returns model to pool.
• force_reset(): Clears all models and caches.
• shutdown(): Cleans up resources.

---

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 introduces a sophisticated model management system for Apache Beam's ML inference capabilities. The core "ModelManager" class, supported by "GPUMonitor" and "ResourceEstimator", intelligently handles the lifecycle of machine learning models, particularly on GPU-accelerated environments. It aims to prevent out-of-memory errors by dynamically estimating model memory requirements, isolating unknown models for profiling, and implementing a demand-aware eviction strategy. This system ensures efficient and concurrent execution of diverse ML models within Beam pipelines, optimizing GPU resource utilization and improving overall stability.

Highlights

• ModelManager Introduction: A new "ModelManager" class is added to provide managed access to ML models, handling GPU OOMs and optimizing resource usage.
• GPUMonitor for Memory Tracking: Implements "GPUMonitor" to continuously poll and track GPU memory usage, including current, peak, and total memory.
• ResourceEstimator for Cost Estimation: Introduces "ResourceEstimator" which uses Non-Negative Least Squares (NNLS) to dynamically estimate the memory cost of models and adapt to fluctuating usage.
• Intelligent Model Eviction: The "ModelManager" includes an eviction strategy that prioritizes models based on demand, age, and surplus copies to free up GPU memory when needed.
• Isolation Mode for Unknown Models: Unknown models are loaded in an isolated environment to accurately profile their memory footprint without affecting other active models.
• Comprehensive Testing: New unit tests are added to validate the functionality of "GPUMonitor", "ResourceEstimator", and "ModelManager", covering capacity checks, isolation, concurrent execution, OOM recovery, and eviction logic.

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. ↩

[AMOOOMA]

R: @damccorm

[github-actions]

Stopping reviewer notifications for this pull request: review requested by someone other than the bot, ceding control. If you'd like to restart, comment assign set of reviewers

[damccorm]

I've been looking at it for a while today and I am still having a hard time understanding the full scope of this PR (even with this being the second long look), and it will probably take a few more passes.

For now, added some things that will help me review better, but if there are pieces we can separate out further to make this more reviewable (either by splitting large functions apart or by pulling classes out of the PR), that would be quite helpful.

[damccorm]

What is loader_func here - is this spawning the model in process?

[AMOOOMA]

Yep! This depends on what the user pass in which in the RunInference case would be spawning a model in process with the new MultiProcessShared util.

[damccorm]

Is self._pending_isolation_count ever non-zero?

[AMOOOMA]

Good catch! This is some old code from older iterations. Removed now.

[damccorm]

Could you add more info on what makes a model low-priority here?

[AMOOOMA]

Done.

[codecov]

Codecov Report

❌ Patch coverage is 4.35835% with 395 lines in your changes missing coverage. Please review.
✅ Project coverage is 54.88%. Comparing base (b1cf96d) to head (858ebda).

Files with missing lines	Patch %	Lines
...s/python/apache_beam/ml/inference/model_manager.py	4.35%	395 Missing ⚠️

Additional details and impacted files

@@              Coverage Diff              @@
##             master   #37113       +/-   ##
=============================================
+ Coverage     35.95%   54.88%   +18.92%     
  Complexity     1676     1676               
=============================================
  Files          1062     1063        +1     
  Lines        166037   166450      +413     
  Branches       1208     1208               
=============================================
+ Hits          59705    91354    +31649     
+ Misses       104151    72915    -31236     
  Partials       2181     2181               

Flag	Coverage Δ
python	80.44% <4.35%> (+40.55%)	⬆️

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.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[damccorm]

Didn't get to the tests yet, but overall things generally look good. Left some comments below and I'll ask gemini to review as well

[damccorm]

/gemini review

[gemini-code-assist]

Code Review

This pull request introduces a sophisticated ModelManager for handling ML models, with a strong focus on GPU memory management. The implementation is well-structured, separating concerns into GPUMonitor, ResourceEstimator, and the ModelManager itself. The logic for concurrency, resource contention, and model eviction is complex but appears robust. The accompanying tests are thorough and cover a wide range of scenarios. My review includes several suggestions to enhance security, code clarity, and efficiency in specific areas.

[damccorm]

From the doc precommit:

/runner/_work/beam/beam/sdks/python/test-suites/tox/pycommon/build/srcs/sdks/python/target/.tox-docs/docs/lib/python3.10/site-packages/apache_beam/ml/inference/model_manager.py:docstring of apache_beam.ml.inference.model_manager.ModelManager:8: ERROR: Unexpected indentation.

I think this needs an extra indent to handle lists like

beam/sdks/python/apache_beam/transforms/core.py

Line 1071 in 183ecd3

initial "accumulator" value representing the combination of zero values.

[AMOOOMA]

Thanks for the catch! Updated.

[damccorm]

Thanks!