Skip to content

Kubernetes Deployment Installation Guide

KServe supports RawDeployment mode to enable InferenceService deployment with Kubernetes resources Deployment, Service, Ingress and Horizontal Pod Autoscaler. Comparing to serverless deployment it unlocks Knative limitations such as mounting multiple volumes, on the other hand Scale down and from Zero is not supported in RawDeployment mode.

Kubernetes 1.20 is the minimally required version and please check the following recommended Istio versions for the corresponding Kubernetes version.

Kubernetes Version Recommended Istio Version
1.20 1.9, 1.10, 1.11
1.21 1.10, 1.11
1.22 1.11, 1.12

1. Install Istio

The minimally required Istio version is 1.9.5 and you can refer to the Istio install guide.


Istio ingress is recommended, but you can choose to install with other Ingress controllers.

2. Install Cert Manager

The minimally required Cert Manager version is 1.3.0 and you can refer to Cert Manager installation guide.


Cert manager is required to provision webhook certs for production grade installation, alternatively you can run self signed certs generation script.

3. Install KServe


The default KServe deployment mode is Serverless which depends on Knative. The following step changes the default deployment mode to RawDeployment before installing KServe.

i. Change default deployment mode

Download the KServe's install manifest yaml.

Open the kserve.yaml, find the ConfigMap with name inferenceservice-config in the manifest and modify the deploy section:
      "defaultDeploymentMode": "RawDeployment"

ii. Install KServe

kubectl apply -f kserve.yaml
Back to top