[Docs] add pd-model deployment example in quickstart doc #1395
Conversation
Signed-off-by: Ning Wang <[email protected]>
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Summary of Changes
Hello @nwangfw, 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 enhanced the quickstart documentation by providing a comprehensive example for deploying and testing a Prefill-Decode (PD) disaggregation model. This includes a new YAML configuration file for the model's deployment and updated documentation with clear instructions and a curl example to demonstrate its usage.
Highlights
- New PD Model Deployment Example: I've added a new YAML configuration file,
pd-model.yaml, which defines aStormServicefor deploying a vLLM Prefill-Decode (PD) disaggregation model. This file specifies both 'prefill' and 'decode' roles, each configured to run a specific vLLM OpenAI API server instance for thedeepseek-ai/DeepSeek-R1-Distill-Llama-8Bmodel. - Documentation for PD Model Deployment: I've updated the
quickstart.rstdocumentation to include a new section that guides users on how to deploy the Prefill-Decode (PD) disaggregation model using the newly addedpd-model.yaml. This makes it easier for users to get started with this specific deployment strategy. - Curl Example for Testing PD Disaggregation: To complement the new deployment instructions, I've also added a
curlcommand example to thequickstart.rstdocumentation. This example demonstrates how to interact with and test the deployed PD disaggregation model by including the necessaryrouting-strategy: pdheader in the API request.
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
-
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. ↩
There was a problem hiding this comment.
Code Review
This pull request adds a valuable example for deploying a Prefill-Decode (PD) disaggregation model to the quickstart documentation. The changes are generally clear and provide a concrete example for users. My review includes a few suggestions to enhance the documentation's clarity and the example YAML's maintainability. Specifically, I recommend a minor wording adjustment in the quickstart guide for clarity and a significant refactoring of the pd-model.yaml to eliminate code duplication using YAML anchors and aliases. I've also highlighted a potential issue with the container image being from a private registry, which could be a blocker for users.
| .. note:: | ||
|
|
||
| To test PD disaggregation, add the ``routing-strategy`` header to ``pd``. For example: |
There was a problem hiding this comment.
The phrasing "add the routing-strategy header to pd" is slightly ambiguous. It could be misinterpreted by users. For improved clarity, I suggest rephrasing to make it explicit that pd is the value for the routing-strategy header.
To test PD disaggregation, set the ``routing-strategy`` header to ``pd``. For example:
Signed-off-by: Ning Wang <[email protected]>
samples/quickstart/pd-model.yaml
Outdated
| --uvicorn-log-level warning \ | ||
| --model deepseek-ai/DeepSeek-R1-Distill-Llama-8B \ | ||
| --served-model-name deepseek-r1-distill-llama-8b \ | ||
| --kv-transfer-config '{"kv_connector":"PyNcclConnector","kv_role":"kv_both"}' |
There was a problem hiding this comment.
why do you use PyNcclConnector?
There was a problem hiding this comment.
I try to follow this PD example from vllm https://github.com/vllm-project/vllm/blob/main/examples/online_serving/disaggregated_prefill.sh, Do you suggest that we use mooncake with RDMA instead?
There was a problem hiding this comment.
there's no mooncake in vllm.. why do not you follow our own guidance? https://github.com/vllm-project/aibrix/tree/main/samples/disaggregation/vllm
There was a problem hiding this comment.
I thought we want to use official vllm image in Quickstart section so that people can try very quickly. Sure, we can use our images and nixl connector then.
There was a problem hiding this comment.
if you are not sure, please ask in advance. you can give reference on the image build. I do not understand why that's a concern on your side
There was a problem hiding this comment.
@Jeffwan Updated. Feel free to check it one more time.
Signed-off-by: Ning Wang <[email protected]>
2 participants
Pull Request Description
added pd deployment and curl example in the quickstart doc.
Related Issues
Resolves: #[1375]
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
By submitting this PR, you confirm that you've read these guidelines and your changes align with the project's contribution standards.