search

kserve / modelmesh-serving

Controller for ModelMesh
Apache License 2.0
205 stars 114 forks source link

InferenceSerivce must have either the storageUri or the storage.path #510

Open gujingit opened 5 months ago

gujingit commented 5 months ago

Describe the bug

InferenceSerivce must have either the storageUri or the storage.path

To Reproduce Steps to reproduce the behavior:

apiVersion: "serving.kserve.io/v1beta1"
kind: "InferenceService"
metadata:
  name: "sklearn-iris-zibai"
  namespace: modelmesh-serving
  annotations:
    serving.kserve.io/deploymentMode: ModelMesh
spec:
  predictor:
    model:
      modelFormat:
        name: sklearn
      image: kube-ai-registry.cn-shanghai.cr.aliyuncs.com/ai-sample/kserve-sklearn-server:v0.12.0
      command:
      - sh
      - -c
      - "python -m sklearnserver --model_name=sklearn-iris --model_dir=/models --http_port=8080"
      resources:
        limits:
          memory: 2Gi
        requests:
          memory: 100Mi

errors in modelmesh-controller

"error":"failed to fetch CR from kubebuilder cache for predictor sklearn-iris-zibai: the InferenceService modelmesh-serving/sklearn-iris-zibai must have either the storageUri or the storage.path"

The image already contains the data, no need to pull the data again.

Expected behavior

No errors.