Skip to main content
Version: 0.17

Quickstart Guide

Welcome to the KServe Quickstart Guide! This guide will help you set up a KServe Quickstart environment for testing and experimentation.

By the end of this guide, you will have a fully functional KServe environment ready for experimentation.

warning

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

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
  • git - for cloning the KServe repository
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 git installation, run:

git --version

Kubernetes Cluster​

Version Requirements

Kubernetes version 1.32 or higher is required.

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.

Using Kind (Kubernetes in Docker):

If you want to run a local Kubernetes cluster, you can use Kind. It allows you to create a Kubernetes cluster using Docker container nodes.

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

Using Minikube:

If you prefer to use Minikube, you can follow the Minikube Quickstart Guide to set up a local Kubernetes cluster.

First, ensure you have Minikube installed on your machine. Then, you can start a local Kubernetes cluster with the following command:

minikube start

Install KServe Quickstart Environment​

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

First, clone the KServe repository:

git clone https://github.com/kserve/kserve.git
cd kserve

Then choose your installation scenario:

Install KServe controller only without additional components.

Using Quick Install Script
# Standard mode
curl -s "https://raw.githubusercontent.com/kserve/kserve/refs/tags/v0.17.0/install/v0.17.0/kserve-standard-mode-full-install-with-manifests.sh" | bash

# Knative mode (serverless)
curl -s "https://raw.githubusercontent.com/kserve/kserve/refs/tags/v0.17.0/install/v0.17.0/kserve-knative-mode-full-install-with-manifests.sh" | bash
Using kserve-install.sh

Helm Mode:

# Standard mode
./hack/kserve-install.sh --kserve-version v0.17.0 --type kserve --standard

# Knative mode (serverless)
./hack/kserve-install.sh --kserve-version v0.17.0 --type kserve --knative

Kustomize Mode:

# Standard mode
./hack/kserve-install.sh --kustomize --standard

# Knative mode (serverless)
./hack/kserve-install.sh --kustomize --knative
More Installation Options

For detailed installation instructions, customization options, and troubleshooting:

Next Steps​

Now that you have a KServe Quickstart environment set up, you can start deploying and testing machine learning models: