Skip to content

Conversation

Jeffwan
Copy link
Collaborator

@Jeffwan Jeffwan commented Jul 27, 2025

Pull Request Description

This is the initial helm chart support.

  • New Helm Chart Structure: A complete Helm chart is added under dist/chart/, including Chart.yaml, values.yaml, README.md, and a templates/ directory containing all Kubernetes manifests for aibrix components.
  • Leverage Helm's --install-crds to separate the crds.
  • The chart defines components including the controller-manager, gateway-plugins, gpu-optimizer, and metadata-service, ensuring their proper setup and operation.
  • I wrote a README.md but have not updated doc site yet. the relationship between kuberay is not finalized yet. It's kind of hard to install dependencies including kuberay and envoy gateway in CN envs. We need to find better ways.

Related Issues

Resolves: #452 and #762 and #66

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.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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 comprehensive Helm chart support for the aibrix project, enabling streamlined, Kubernetes-native deployment and management of all its core components. This significantly simplifies the installation, configuration, and lifecycle management of the aibrix ecosystem within a Kubernetes cluster.

Highlights

  • New Helm Chart Structure: A complete Helm chart is added under dist/chart/, including Chart.yaml, values.yaml, README.md, and a templates/ directory containing all Kubernetes manifests for aibrix components.
  • Custom Resource Definitions (CRDs): New CRDs for PodAutoscaler and ModelAdapter are introduced, allowing aibrix to manage custom autoscaling and AI model resources natively within Kubernetes.
  • Core Component Deployments: The chart defines deployments, services, and RBAC for key aibrix components, including the controller-manager, gateway-plugins, gpu-optimizer, and metadata-service, ensuring their proper setup and operation.
  • Kubernetes Gateway API Integration: Configuration for an Envoy-based Gateway is included, leveraging Gateway API resources (GatewayClass, Gateway, EnvoyProxy, ClientTrafficPolicy, EnvoyPatchPolicy, HTTPRoute) to manage external traffic and routing for aibrix services.
  • Embedded Redis Instance: A Redis master deployment and service are included within the chart to serve as a backend for the gateway-plugins and metadata-service components, simplifying their dependency management.
  • Observability and Security Integrations: The chart provides conditional support for cert-manager for secure webhook and metrics communication, and Prometheus ServiceMonitor for metrics scraping, enhancing the project's operational capabilities.
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.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request introduces Helm chart support for deploying the aibrix project, which is a great addition for Kubernetes users. The chart is comprehensive and covers many components of the system.

My review has identified several critical and high-severity issues that need to be addressed. These include YAML syntax errors, incorrect service selectors which will break functionality, and security concerns like using latest image tags and reusing service accounts. There are also inconsistencies in resource labeling and configuration that should be fixed to improve maintainability. Once these issues are resolved, the Helm chart will be much more robust and ready for use.

Comment on lines +4 to +6
labels:
app.kubernetes.io/name: aibrix
app.kubernetes.io/managed-by: Helm
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The labels for this ServiceAccount are hardcoded. For consistency with other resources in this chart, it's better to use the chart.labels helper template. This also applies to the ClusterRoleBinding in this file.

    {{- include "chart.labels" . | nindent 4 }}

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

won't address in initial PR.

type: application
version: 0.3.0
appVersion: "0.3.0"
icon: "https://example.com/icon.png"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The icon field points to a placeholder URL. This should be updated to a real URL for the project's logo or removed if no icon is available.

@Jeffwan Jeffwan force-pushed the jiaxin/helm-support branch 4 times, most recently from 207aa57 to ae49a66 Compare July 27, 2025 02:23
repository: aibrix/controller-manager
tag: nightly
imagePullPolicy: IfNotPresent
resources:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think this should be configurable too no? I can help out with the chart in a follow up PRs if you'd like

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@omerap12 that would be great. This is an initial PR and feel free to help expose more configurable options as needed.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Cool. once this get merged Ill help :)

@Jeffwan Jeffwan force-pushed the jiaxin/helm-support branch from ae49a66 to 1568660 Compare July 27, 2025 18:17
@Jeffwan
Copy link
Collaborator Author

Jeffwan commented Jul 27, 2025

@omerap12 if overall looks good to you, I will merge this one and you can find follow up PRs to improve it

@omerap12
Copy link
Contributor

@omerap12 if overall looks good to you, I will merge this one and you can find follow up PRs to improve it

Cool. I'll review tomorrow :)

Copy link
Contributor

@omerap12 omerap12 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Overall looks okay to me for now (we can improve it later in future PRs as discussed).
About the connection with KubeRay, maybe we can use a Helm dependency: https://helm.sh/docs/helm/helm_dependency/#helm-dependency.
I’m not sure if KubeRay has an official chart, but they probably do, and we could use that with this Helm feature.

Signed-off-by: Jiaxin Shan <seedjeffwan@gmail.com>
@Jeffwan Jeffwan force-pushed the jiaxin/helm-support branch from 1568660 to f37e380 Compare July 28, 2025 17:43
@Jeffwan Jeffwan merged commit 3c6e294 into vllm-project:main Jul 28, 2025
3 checks passed
@Jeffwan
Copy link
Collaborator Author

Jeffwan commented Jul 28, 2025

@omerap12 KubeRay does have a helm chart. current manifest is generated from its chart. https://github.com/vllm-project/aibrix/blob/main/config/dependency/kuberay-operator/README.md

@Jeffwan Jeffwan deleted the jiaxin/helm-support branch July 28, 2025 17:44
ae86zhizhi pushed a commit to ae86zhizhi/aibrix that referenced this pull request Jul 30, 2025
Signed-off-by: Jiaxin Shan <seedjeffwan@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Replace our cloned 3rd-party yamls with helm charts
2 participants