apiVersion: batch.volcano.sh/v1alpha1   # The value cannot be changed. The volcano API must be used.
kind: Job                               # Only the job type is supported at present.
metadata:
  name: mindx-dls-test                  # The value must be consistent with the name of ConfigMap.
  namespace: vnpu                      # Select a proper namespace based on the site requirements. (The namespaces of ConfigMap and Job must be the same. In addition, if the tjm component of MindX-add exists, the vcjob namespace cannot be used.)
  labels:
    ring-controller.atlas: ascend-310P   # The value must be the same as the label in ConfigMap and cannot be changed.
spec:
  minAvailable: 1                       # The value of minAvailable is 1 in a single-node scenario and N in an N-node distributed scenario.
  schedulerName: volcano                # Use the Volcano scheduler to schedule jobs.
  policies:
    - event: PodEvicted
      action: RestartJob
  plugins:
    ssh: []
    env: []
    svc: []
  maxRetry: 3
  queue: default
  tasks:
    - name: "default-test"
      replicas: 1                              # The value of replicas is 1 in a single-node scenario and N in an N-node scenario. The number of NPUs in the requests field is 8 in an N-node scenario.
      template:
        metadata:
          labels:
            app: infers
            ring-controller.atlas: ascend-310P # Add this Label, used to check job kind.
            vnpu-dvpp: "null"                  # For NPU dynamic segmentation,null means don't care dvpp resource,yes means used dvpp,no means ndvpp
            vnpu-level: low                    # For NPU dynamic segmentation,low means low-level configuration,high means performance first,default low.
        spec:
          schedulerName: volcano
          automountServiceAccountToken: false
          containers:
            - image: ascendhub.huawei.com/public-ascendhub/infer-modelzoo:23.0.RC1-mxvision                  # Inference image name
              imagePullPolicy: IfNotPresent
              name: resnet50infer
              command: ["/bin/bash", "-c", "bash test_model.sh"]
              resources:
                requests:
                  huawei.com/npu-core: 1             # Number of required NPUs. The maximum value is 8. You can add lines below to configure resources such as memory and CPU.
                limits:
                  huawei.com/npu-core: 1             # The value should be the same as that of requests .
              volumeMounts:
                - name: slog
                  mountPath: /var/log/npu/conf/slog/    #Log path
                - name: localtime                       #The container time must be the same as the host time.
                  mountPath: /etc/localtime
          nodeSelector:
            host-arch: huawei-arm        # Configure the label based on the actual job.
          volumes:
            - name: slog
              hostPath:
                path: /var/log/npu/conf/slog/
            - name: localtime
              hostPath:
                path: /etc/localtime
          restartPolicy: OnFailure