serving_runtime

serving_runtime.yaml

apiVersion: serving.kserve.io/v1alpha1
kind: ServingRuntime
metadata:
  name: wisdom
  namespace: modelmesh-serving
spec:
  containers:
  - env:
    - name: ACCEPT_LICENSE
      value: "true"
    - name: LOG_LEVEL
      value: info
    - name: CAPACITY
      value: "28000000000"
    - name: DEFAULT_MODEL_SIZE
      value: "1773741824"
    - name: METRICS_PORT
      value: "2113"
    - name: GATEWAY_PORT
      value: "8060"
    - name: STRICT_RPC_MODE
      value: "false"
    image: us.icr.io/watson-runtime/fmaas-runtime-wisdom-ansible:0.0.6
    imagePullPolicy: IfNotPresent
    name: runtime
    resources:
      limits:
        cpu: 2
        memory: 16Gi
      requests:
        cpu: 1
        memory: 16Gi
  grpcDataEndpoint: port:8085
  grpcEndpoint: port:8085
  multiModel: true
  storageHelper:
    disabled: false
  supportedModelFormats:
  - autoSelect: true
    name: ansible-wisdom