Skip to main content

Quickstart Guide

Welcome to the KServe Quickstart Guide! This guide will help you set up a KServe Quickstart environment for testing and experimentation. KServe Quickstart is designed to provide a simple and quick way to get started with KServe, allowing you to deploy and test machine learning models on Kubernetes with minimal setup. This guide will walk you through the prerequisites, installation steps, and how to verify your KServe Quickstart environment is up and running. By the end of this guide, you will have a fully functional KServe Quickstart environment ready for experimentation.

Prerequisites

Before you can get started with a KServe Quickstart deployment, you will need to ensure you have the following prerequisites installed:

Tools

Make sure you have the following tools installed:

  • kubectl - The Kubernetes command-line tool
  • helm - for installing KServe and other Kubernetes operators
  • curl - for the quickstart script and for testing API endpoints (installed by default on most systems)
Verify Installations

Run the following commands to verify that you have the required tools installed:

To verify kubectl installation, run:

kubectl version --client

To verify helm installation, run:

helm version

To verify curl installation, run:

curl --version

Kubernetes Cluster

Version Requirements

KServe requires a Kubernetes version 1.29 or higher. Ensure your cluster meets this requirement before proceeding with the installation.

You will need a running Kubernetes cluster with properly configured kubeconfig to run KServe. You can use any Kubernetes cluster, but for local development and testing, we recommend using kind (Kubernetes in Docker) or minikube.

If you want to run a local Kubernetes cluster, you can use Kind (Kubernetes in Docker). It allows you to create a Kubernetes cluster using Docker container nodes. This is ideal for local development and testing.

First, ensure you have Docker installed on your machine. Install Kind by following the Kind Quick Start Guide if you haven't done so already.

Then, you can create a local Kubernetes cluster with the following command:

kind create cluster

Install KServe Quickstart Environment

Once you have the prerequisites installed and a Kubernetes cluster running, you can proceed with the KServe Quickstart installation.

warning

KServe Quickstart Environments are for experimentation use only. For production installation, see our Administrator's Guide.

   curl -s "https://raw.githubusercontent.com/kserve/kserve/release-0.15/hack/quick_install.sh" | bash -r

Verify the installation by checking the status of the KServe components:

kubectl get pods -n kserve
Verify Installation

You should see the KServe controller up and running:

NAME                                                   READY   STATUS    RESTARTS   AGE
kserve-controller-manager-7f5b6c4d8f-abcde 1/1 Running 0 2m
kserve-localmodel-controller-manager-5b8b6574c7-jz42m 1/1 Running 0 2m

Next Steps

Now that you have a KServe Quickstart environment set up, you can start deploying and testing machine learning models. Here are some recommended next steps: