[Misc] Add SGLang P/D disaggregation examples

[Jeffwan]

Pull Request Description

[Please provide a clear and concise description of your changes here]

Related Issues

Resolves: #[Insert issue number(s)]

Important: Before submitting, please complete the description above and review the checklist below.

---

Contribution Guidelines (Expand for Details)

We appreciate your contribution to aibrix! To ensure a smooth review process and maintain high code quality, please adhere to the following guidelines:

Pull Request Title Format

Your PR title should start with one of these prefixes to indicate the nature of the change:

• [Bug]: Corrections to existing functionality
• [CI]: Changes to build process or CI pipeline
• [Docs]: Updates or additions to documentation
• [API]: Modifications to aibrix's API or interface
• [CLI]: Changes or additions to the Command Line Interface
• [Misc]: For changes not covered above (use sparingly)

Note: For changes spanning multiple categories, use multiple prefixes in order of importance.

Submission Checklist

• PR title includes appropriate prefix(es)
• Changes are clearly explained in the PR description
• New and existing tests pass successfully
• Code adheres to project style and best practices
• Documentation updated to reflect changes (if applicable)
• Thorough testing completed, no regressions introduced

By submitting this PR, you confirm that you've read these guidelines and your changes align with the project's contribution standards.

[gemini-code-assist]

Summary of Changes

Hello @Jeffwan, 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 new set of examples demonstrating how to deploy SGLang with Prefill/Decode (P/D) disaggregation on Kubernetes, leveraging AIBrix's StormService. These examples showcase different deployment patterns, including pool mode, replica mode, and configurations for tensor parallelism, providing a comprehensive guide for setting up high-performance LLM inference.

Highlights

• New SGLang Disaggregation Examples: I've added a new directory (samples/disaggregation/sglang) containing detailed Kubernetes YAML configurations for SGLang Prefill/Decode (P/D) disaggregation.
• Comprehensive Documentation: A README.md is included to guide users through building necessary Docker images (SGLang with Nixl, SGLang Router), configuring Kubernetes RBAC, and running example queries against the disaggregated setup.
• Diverse Deployment Patterns: Three distinct StormService examples are provided: pool.yaml for a pooled disaggregation setup, replica.yaml for a replica-based disaggregation with a standalone router, and tp-1p1d.yaml showcasing advanced disaggregation with tensor parallelism across multiple nodes for both prefill and decode stages.
• High-Performance Configuration: All examples are configured for high-performance LLM inference, utilizing nixl as the disaggregation transfer backend, specifying RDMA network annotations, and allocating GPU resources.

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 several examples for SGLang P/D disaggregation. The examples are well-structured and cover different modes like pool, replica, and tensor parallelism. I've identified areas for improvement concerning portability and robustness, including hardcoded values in Kubernetes manifests and the use of hostPath volumes. Addressing these points will make the examples more robust, secure, and easier to use.

[Xunzhuo]

@Jeffwan this is going to use mini_lb instead of the gateway to do p/d disaggregation?

[Jeffwan]

@Xunzhuo No, this is not the ideal state—it's just the initial phase. Once the router capability is ready, we can switch over to using the router.

[nwangfw]

lgtm