[Docs] Adding multi engine support documentation

[happyandslow]

Pull Request Description

Adding documentation page for multi engine support.

Related Issues

Resolves: #843

[gemini-code-assist]

Summary of Changes

Hello @happyandslow, 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!

I've added comprehensive documentation for the new multi-engine support feature in AIBrix. This new capability allows for deploying and serving multiple LLM engines under a single AIBrix instance, enabling flexible request routing and side-by-side comparisons. The documentation covers how to configure these engines, the metrics supported for various engine types, and the process for integrating new engines into the system.

Highlights

• New Documentation File: A new documentation file, docs/source/features/multi-engine.rst, has been added to explain the new multi-engine support feature in AIBrix.
• Multi-Engine Support Explained: The documentation details how AIBrix now supports multi-engine scheduling, allowing developers to deploy and serve various engine backends (e.g., different LLMs like SGLang and xLLM) under a single AIBrix instance.
• Engine Configuration: It provides instructions on how to configure specific engines by adding model.aibrix.ai/engine labels in the deployment YAML file, along with other relevant labels like model.aibrix.ai/metric-port and model.aibrix.ai/port.
• Supported Metrics and Interpretation: The document includes a detailed table outlining the supported metrics for different engine types (vLLM, SGLang, xLLM) and how AIBrix interprets these metrics from the Prometheus API for routing decisions.
• Adding New Engines Guide: Steps are provided for extending support to new engines or metrics types, including adding engine type to metrics name mapping and updating deployment labels.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 or fill out our survey to provide feedback.

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 adds documentation for multi-engine support. The new documentation page is well-structured and provides a good overview of the feature. I've pointed out a few areas for improvement to enhance clarity and correctness, including fixing some grammatical errors, correcting list numbering, and fixing a typo in a file link.

[Jeffwan]

@happyandslow please try to build in your local env cd docs && make html check static html to see the changes.

[happyandslow]

@happyandslow please try to build in your local env cd docs && make html check static html to see the changes.

Should be fixed now.

[Jeffwan]

the change looks good to me