feat: add KEP: ResourceScalingGroup (RSG) - Advanced Scaling API for …

[Mag-FelixFelicis]

…Distributed AI Inference

Ⅰ. Motivation

add KEP: ResourceScalingGroup (RSG)

Ⅱ. Modifications

Ⅲ. Does this pull request fix one issue?

fixes #XXXX

Ⅳ. List the added test cases (unit test/integration test) if any, please explain if no tests are needed.

Ⅴ. Describe how to verify it

VI. Special notes for reviews

Checklist

• [ ] Format your code make fmt.
• [ ] Add unit tests or integration tests.
• [ ] Update the documentation related to the change.

[gemini-code-assist[bot]]

Summary of Changes

Hello @Mag-FelixFelicis, I'm Gemini Code Assist[^1]! 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 KEP-98, proposing a new ResourceScalingGroup (RSG) API designed to enhance scaling capabilities for distributed AI inference workloads. It aims to overcome limitations in existing Kubernetes scaling by enabling complex, ratio-based scaling for interdependent components, allowing non-intrusive management of pre-existing deployments, and providing granular control over graceful scale-down operations. The KEP outlines a flexible design supporting both group-based replication and in-place proportional scaling, along with a new CRD and controller interfaces.

Highlights

• Introduction of KEP-98: This pull request introduces KEP-98, proposing a new ResourceScalingGroup (RSG) API to address advanced scaling requirements for distributed AI inference workloads.
• Dual Scaling Strategies: The RSG API supports two distinct scaling strategies: 'GroupReplication' for managing cloned resource groups and 'InplaceScaling' for proportional scaling of existing workloads based on defined ratios.
• Addressing Scaling Limitations: The KEP aims to overcome current limitations in Kubernetes scaling, specifically focusing on enabling multi-role coupled scaling, non-intrusive adoption of existing workloads, and providing deterministic, state-aware scale-down control for graceful termination.
• New CRD Definition: A new Custom Resource Definition (CRD) for 'ResourceScalingGroup' is defined, including specifications for target resources, scaling strategy configurations (GroupConfig and InplaceConfig), and status reporting.

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 :thumbsup: and :thumbsdown: 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.

[^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.