kserve/config/runtimes/kserve-mlserver.yaml

apiVersion: serving.kserve.io/v1alpha1
kind: ClusterServingRuntime
metadata:
  name: kserve-mlserver
  annotations:
    serving.kserve.io/server-type: mlserver
spec:
  annotations:
    # mlserver version 1.1.0 uses port 8082 as default instead of 8080.
    prometheus.kserve.io/port: '8080'
    prometheus.kserve.io/path: "/metrics"
  supportedModelFormats:
    - name: sklearn
      version: "0"
      autoSelect: true
      priority: 2
    - name: sklearn
      version: "1"
      autoSelect: true
      priority: 2
    - name: xgboost
      version: "1"
      autoSelect: true
      priority: 2
    - name: xgboost
      version: "2"
      autoSelect: true
      priority: 2
    - name: lightgbm
      version: "3"
      autoSelect: true
      priority: 2
    - name: lightgbm
      version: "4"
      autoSelect: true
      priority: 2
    - name: mlflow
      version: "1"
      autoSelect: true
      priority: 1
    - name: mlflow
      version: "2"
      autoSelect: true
      priority: 1
  protocolVersions:
    - v2
  containers:
    - name: kserve-container
      image: mlserver:replace
      env:
        - name: "MLSERVER_MODEL_IMPLEMENTATION"
          value: "{{.Labels.modelClass}}"
        - name: "MLSERVER_HTTP_PORT"
          value: "8080"
        - name: "MLSERVER_GRPC_PORT"
          value: "9000"
      securityContext:
        allowPrivilegeEscalation: false
        privileged: false
        runAsNonRoot: true
        capabilities:
          drop:
            - ALL
      resources:
        requests:
          cpu: "1"
          memory: 2Gi
        limits:
          cpu: "1"
          memory: 2Gi