---
apiVersion: autoscaling/v2
items:
- apiVersion: autoscaling/v2
  kind: HorizontalPodAutoscaler
  metadata:
    annotations:
      internal.serving.kserve.io/logger: "true"
      internal.serving.kserve.io/logger-mode: all
      internal.serving.kserve.io/logger-sink-url: http://message-dumper-raw-dc743-predictor.kserve-ci-e2e-test.svc.cluster.local
      internal.serving.kserve.io/storage-initializer-sourceuri: gs://kfserving-examples/models/sklearn/1.0/model
      prometheus.kserve.io/path: /metrics
      prometheus.kserve.io/port: "8080"
      service.beta.openshift.io/serving-cert-secret-name: isvc-logger-raw-dc743-predictor-serving-cert
      serving.kserve.io/deploymentMode: Standard
    creationTimestamp: "2026-04-16T17:02:40Z"
    labels:
      app: isvc.isvc-logger-raw-dc743-predictor
      component: predictor
      networking.kserve.io/visibility: exposed
      serving.kserve.io/inferenceservice: isvc-logger-raw-dc743
    managedFields:
    - apiVersion: autoscaling/v2
      fieldsType: FieldsV1
      fieldsV1:
        f:metadata:
          f:annotations:
            .: {}
            f:internal.serving.kserve.io/logger: {}
            f:internal.serving.kserve.io/logger-mode: {}
            f:internal.serving.kserve.io/logger-sink-url: {}
            f:internal.serving.kserve.io/storage-initializer-sourceuri: {}
            f:prometheus.kserve.io/path: {}
            f:prometheus.kserve.io/port: {}
            f:service.beta.openshift.io/serving-cert-secret-name: {}
            f:serving.kserve.io/deploymentMode: {}
          f:labels:
            .: {}
            f:app: {}
            f:component: {}
            f:networking.kserve.io/visibility: {}
            f:serving.kserve.io/inferenceservice: {}
          f:ownerReferences:
            .: {}
            k:{"uid":"a4d6a051-8164-472a-9a47-f8fa43c47151"}: {}
        f:spec:
          f:behavior:
            .: {}
            f:scaleDown:
              .: {}
              f:policies: {}
              f:selectPolicy: {}
            f:scaleUp:
              .: {}
              f:policies: {}
              f:selectPolicy: {}
              f:stabilizationWindowSeconds: {}
          f:maxReplicas: {}
          f:metrics: {}
          f:minReplicas: {}
          f:scaleTargetRef:
            f:apiVersion: {}
            f:kind: {}
            f:name: {}
      manager: manager
      operation: Update
      time: "2026-04-16T17:02:40Z"
    - apiVersion: autoscaling/v2
      fieldsType: FieldsV1
      fieldsV1:
        f:status:
          f:conditions:
            .: {}
            k:{"type":"AbleToScale"}:
              .: {}
              f:lastTransitionTime: {}
              f:message: {}
              f:reason: {}
              f:status: {}
              f:type: {}
            k:{"type":"ScalingActive"}:
              .: {}
              f:lastTransitionTime: {}
              f:message: {}
              f:reason: {}
              f:status: {}
              f:type: {}
            k:{"type":"ScalingLimited"}:
              .: {}
              f:lastTransitionTime: {}
              f:message: {}
              f:reason: {}
              f:status: {}
              f:type: {}
          f:currentMetrics: {}
          f:currentReplicas: {}
          f:desiredReplicas: {}
      manager: kube-controller-manager
      operation: Update
      subresource: status
      time: "2026-04-16T17:10:10Z"
    name: isvc-logger-raw-dc743-predictor
    namespace: kserve-ci-e2e-test
    ownerReferences:
    - apiVersion: serving.kserve.io/v1beta1
      blockOwnerDeletion: true
      controller: true
      kind: InferenceService
      name: isvc-logger-raw-dc743
      uid: a4d6a051-8164-472a-9a47-f8fa43c47151
    resourceVersion: "20108"
    uid: af61eb9c-976c-4125-ae35-1a6362210c4a
  spec:
    behavior:
      scaleDown:
        policies:
        - periodSeconds: 15
          type: Percent
          value: 100
        selectPolicy: Max
      scaleUp:
        policies:
        - periodSeconds: 15
          type: Pods
          value: 4
        - periodSeconds: 15
          type: Percent
          value: 100
        selectPolicy: Max
        stabilizationWindowSeconds: 0
    maxReplicas: 1
    metrics:
    - resource:
        name: cpu
        target:
          averageUtilization: 80
          type: Utilization
      type: Resource
    minReplicas: 1
    scaleTargetRef:
      apiVersion: apps/v1
      kind: Deployment
      name: isvc-logger-raw-dc743-predictor
  status:
    conditions:
    - lastTransitionTime: "2026-04-16T17:02:55Z"
      message: recommended size matches current size
      reason: ReadyForNewScale
      status: "True"
      type: AbleToScale
    - lastTransitionTime: "2026-04-16T17:04:55Z"
      message: the HPA was able to successfully calculate a replica count from cpu
        resource utilization (percentage of request)
      reason: ValidMetricFound
      status: "True"
      type: ScalingActive
    - lastTransitionTime: "2026-04-16T17:04:55Z"
      message: the desired count is within the acceptable range
      reason: DesiredWithinRange
      status: "False"
      type: ScalingLimited
    currentMetrics:
    - resource:
        current:
          averageUtilization: 2
          averageValue: 3m
        name: cpu
      type: Resource
    currentReplicas: 1
    desiredReplicas: 1
- apiVersion: autoscaling/v2
  kind: HorizontalPodAutoscaler
  metadata:
    annotations:
      internal.serving.kserve.io/batcher: "true"
      internal.serving.kserve.io/batcher-max-batchsize: "32"
      internal.serving.kserve.io/batcher-max-latency: "5000"
      internal.serving.kserve.io/storage-initializer-sourceuri: gs://kfserving-examples/models/sklearn/1.0/model
      prometheus.kserve.io/path: /metrics
      prometheus.kserve.io/port: "8080"
      service.beta.openshift.io/serving-cert-secret-name: isvc-raw-sklearn-batcher-4801b-predictor-serving-cert
      serving.kserve.io/deploymentMode: Standard
    creationTimestamp: "2026-04-16T16:57:39Z"
    labels:
      app: isvc.isvc-raw-sklearn-batcher-4801b-predictor
      component: predictor
      networking.kserve.io/visibility: exposed
      serving.kserve.io/inferenceservice: isvc-raw-sklearn-batcher-4801b
    managedFields:
    - apiVersion: autoscaling/v2
      fieldsType: FieldsV1
      fieldsV1:
        f:metadata:
          f:annotations:
            .: {}
            f:internal.serving.kserve.io/batcher: {}
            f:internal.serving.kserve.io/batcher-max-batchsize: {}
            f:internal.serving.kserve.io/batcher-max-latency: {}
            f:internal.serving.kserve.io/storage-initializer-sourceuri: {}
            f:prometheus.kserve.io/path: {}
            f:prometheus.kserve.io/port: {}
            f:service.beta.openshift.io/serving-cert-secret-name: {}
            f:serving.kserve.io/deploymentMode: {}
          f:labels:
            .: {}
            f:app: {}
            f:component: {}
            f:networking.kserve.io/visibility: {}
            f:serving.kserve.io/inferenceservice: {}
          f:ownerReferences:
            .: {}
            k:{"uid":"062b81a4-0a2e-4e3c-b5a8-3e018aaec8f1"}: {}
        f:spec:
          f:behavior:
            .: {}
            f:scaleDown:
              .: {}
              f:policies: {}
              f:selectPolicy: {}
            f:scaleUp:
              .: {}
              f:policies: {}
              f:selectPolicy: {}
              f:stabilizationWindowSeconds: {}
          f:maxReplicas: {}
          f:metrics: {}
          f:minReplicas: {}
          f:scaleTargetRef:
            f:apiVersion: {}
            f:kind: {}
            f:name: {}
      manager: manager
      operation: Update
      time: "2026-04-16T16:57:39Z"
    - apiVersion: autoscaling/v2
      fieldsType: FieldsV1
      fieldsV1:
        f:status:
          f:conditions:
            .: {}
            k:{"type":"AbleToScale"}:
              .: {}
              f:lastTransitionTime: {}
              f:message: {}
              f:reason: {}
              f:status: {}
              f:type: {}
            k:{"type":"ScalingActive"}:
              .: {}
              f:lastTransitionTime: {}
              f:message: {}
              f:reason: {}
              f:status: {}
              f:type: {}
            k:{"type":"ScalingLimited"}:
              .: {}
              f:lastTransitionTime: {}
              f:message: {}
              f:reason: {}
              f:status: {}
              f:type: {}
          f:currentMetrics: {}
          f:currentReplicas: {}
          f:desiredReplicas: {}
      manager: kube-controller-manager
      operation: Update
      subresource: status
      time: "2026-04-16T17:10:25Z"
    name: isvc-raw-sklearn-batcher-4801b-predictor
    namespace: kserve-ci-e2e-test
    ownerReferences:
    - apiVersion: serving.kserve.io/v1beta1
      blockOwnerDeletion: true
      controller: true
      kind: InferenceService
      name: isvc-raw-sklearn-batcher-4801b
      uid: 062b81a4-0a2e-4e3c-b5a8-3e018aaec8f1
    resourceVersion: "20222"
    uid: 9f9675d0-d7f4-40f1-b9d6-fad226f4108a
  spec:
    behavior:
      scaleDown:
        policies:
        - periodSeconds: 15
          type: Percent
          value: 100
        selectPolicy: Max
      scaleUp:
        policies:
        - periodSeconds: 15
          type: Pods
          value: 4
        - periodSeconds: 15
          type: Percent
          value: 100
        selectPolicy: Max
        stabilizationWindowSeconds: 0
    maxReplicas: 1
    metrics:
    - resource:
        name: cpu
        target:
          averageUtilization: 80
          type: Utilization
      type: Resource
    minReplicas: 1
    scaleTargetRef:
      apiVersion: apps/v1
      kind: Deployment
      name: isvc-raw-sklearn-batcher-4801b-predictor
  status:
    conditions:
    - lastTransitionTime: "2026-04-16T16:57:54Z"
      message: recommended size matches current size
      reason: ReadyForNewScale
      status: "True"
      type: AbleToScale
    - lastTransitionTime: "2026-04-16T16:59:54Z"
      message: the HPA was able to successfully calculate a replica count from cpu
        resource utilization (percentage of request)
      reason: ValidMetricFound
      status: "True"
      type: ScalingActive
    - lastTransitionTime: "2026-04-16T16:59:54Z"
      message: the desired count is within the acceptable range
      reason: DesiredWithinRange
      status: "False"
      type: ScalingLimited
    currentMetrics:
    - resource:
        current:
          averageUtilization: 14
          averageValue: 21m
        name: cpu
      type: Resource
    currentReplicas: 1
    desiredReplicas: 1
- apiVersion: autoscaling/v2
  kind: HorizontalPodAutoscaler
  metadata:
    annotations:
      internal.serving.kserve.io/storage-initializer-sourceuri: gs://kfserving-examples/models/sklearn/1.0/model
      prometheus.kserve.io/path: /metrics
      prometheus.kserve.io/port: "8080"
      service.beta.openshift.io/serving-cert-secret-name: isvc-sklearn-scale-raw-ae117-predictor-serving-cert
      serving.kserve.io/deploymentMode: Standard
    creationTimestamp: "2026-04-16T17:03:50Z"
    labels:
      app: isvc.isvc-sklearn-scale-raw-ae117-predictor
      component: predictor
      networking.kserve.io/visibility: exposed
      serving.kserve.io/inferenceservice: isvc-sklearn-scale-raw-ae117
    managedFields:
    - apiVersion: autoscaling/v2
      fieldsType: FieldsV1
      fieldsV1:
        f:metadata:
          f:annotations:
            .: {}
            f:internal.serving.kserve.io/storage-initializer-sourceuri: {}
            f:prometheus.kserve.io/path: {}
            f:prometheus.kserve.io/port: {}
            f:service.beta.openshift.io/serving-cert-secret-name: {}
            f:serving.kserve.io/deploymentMode: {}
          f:labels:
            .: {}
            f:app: {}
            f:component: {}
            f:networking.kserve.io/visibility: {}
            f:serving.kserve.io/inferenceservice: {}
          f:ownerReferences:
            .: {}
            k:{"uid":"d9f74a7f-6370-407f-a98f-1dd58db5a2ce"}: {}
        f:spec:
          f:behavior:
            .: {}
            f:scaleDown:
              .: {}
              f:policies: {}
              f:selectPolicy: {}
            f:scaleUp:
              .: {}
              f:policies: {}
              f:selectPolicy: {}
              f:stabilizationWindowSeconds: {}
          f:maxReplicas: {}
          f:metrics: {}
          f:minReplicas: {}
          f:scaleTargetRef:
            f:apiVersion: {}
            f:kind: {}
            f:name: {}
      manager: manager
      operation: Update
      time: "2026-04-16T17:03:50Z"
    - apiVersion: autoscaling/v2
      fieldsType: FieldsV1
      fieldsV1:
        f:status:
          f:conditions:
            .: {}
            k:{"type":"AbleToScale"}:
              .: {}
              f:lastTransitionTime: {}
              f:message: {}
              f:reason: {}
              f:status: {}
              f:type: {}
            k:{"type":"ScalingActive"}:
              .: {}
              f:lastTransitionTime: {}
              f:message: {}
              f:reason: {}
              f:status: {}
              f:type: {}
            k:{"type":"ScalingLimited"}:
              .: {}
              f:lastTransitionTime: {}
              f:message: {}
              f:reason: {}
              f:status: {}
              f:type: {}
          f:currentMetrics: {}
          f:currentReplicas: {}
          f:desiredReplicas: {}
      manager: kube-controller-manager
      operation: Update
      subresource: status
      time: "2026-04-16T17:10:20Z"
    name: isvc-sklearn-scale-raw-ae117-predictor
    namespace: kserve-ci-e2e-test
    ownerReferences:
    - apiVersion: serving.kserve.io/v1beta1
      blockOwnerDeletion: true
      controller: true
      kind: InferenceService
      name: isvc-sklearn-scale-raw-ae117
      uid: d9f74a7f-6370-407f-a98f-1dd58db5a2ce
    resourceVersion: "20184"
    uid: 56573859-b86e-4545-b895-5b7eea2cc65d
  spec:
    behavior:
      scaleDown:
        policies:
        - periodSeconds: 15
          type: Percent
          value: 100
        selectPolicy: Max
      scaleUp:
        policies:
        - periodSeconds: 15
          type: Pods
          value: 4
        - periodSeconds: 15
          type: Percent
          value: 100
        selectPolicy: Max
        stabilizationWindowSeconds: 0
    maxReplicas: 1
    metrics:
    - resource:
        name: cpu
        target:
          averageUtilization: 50
          type: Utilization
      type: Resource
    minReplicas: 1
    scaleTargetRef:
      apiVersion: apps/v1
      kind: Deployment
      name: isvc-sklearn-scale-raw-ae117-predictor
  status:
    conditions:
    - lastTransitionTime: "2026-04-16T17:04:05Z"
      message: recommended size matches current size
      reason: ReadyForNewScale
      status: "True"
      type: AbleToScale
    - lastTransitionTime: "2026-04-16T17:06:35Z"
      message: the HPA was able to successfully calculate a replica count from cpu
        resource utilization (percentage of request)
      reason: ValidMetricFound
      status: "True"
      type: ScalingActive
    - lastTransitionTime: "2026-04-16T17:06:35Z"
      message: the desired count is within the acceptable range
      reason: DesiredWithinRange
      status: "False"
      type: ScalingLimited
    currentMetrics:
    - resource:
        current:
          averageUtilization: 8
          averageValue: 2m
        name: cpu
      type: Resource
    currentReplicas: 1
    desiredReplicas: 1
- apiVersion: autoscaling/v2
  kind: HorizontalPodAutoscaler
  metadata:
    annotations:
      service.beta.openshift.io/serving-cert-secret-name: message-dumper-raw-dc743-predictor-serving-cert
      serving.kserve.io/deploymentMode: Standard
    creationTimestamp: "2026-04-16T17:02:30Z"
    labels:
      app: isvc.message-dumper-raw-dc743-predictor
      component: predictor
      networking.kserve.io/visibility: exposed
      serving.kserve.io/inferenceservice: message-dumper-raw-dc743
    managedFields:
    - apiVersion: autoscaling/v2
      fieldsType: FieldsV1
      fieldsV1:
        f:metadata:
          f:annotations:
            .: {}
            f:service.beta.openshift.io/serving-cert-secret-name: {}
            f:serving.kserve.io/deploymentMode: {}
          f:labels:
            .: {}
            f:app: {}
            f:component: {}
            f:networking.kserve.io/visibility: {}
            f:serving.kserve.io/inferenceservice: {}
          f:ownerReferences:
            .: {}
            k:{"uid":"facd8c35-cb20-4008-974e-a7f73555c8ef"}: {}
        f:spec:
          f:behavior:
            .: {}
            f:scaleDown:
              .: {}
              f:policies: {}
              f:selectPolicy: {}
            f:scaleUp:
              .: {}
              f:policies: {}
              f:selectPolicy: {}
              f:stabilizationWindowSeconds: {}
          f:maxReplicas: {}
          f:metrics: {}
          f:minReplicas: {}
          f:scaleTargetRef:
            f:apiVersion: {}
            f:kind: {}
            f:name: {}
      manager: manager
      operation: Update
      time: "2026-04-16T17:02:30Z"
    - apiVersion: autoscaling/v2
      fieldsType: FieldsV1
      fieldsV1:
        f:status:
          f:conditions:
            .: {}
            k:{"type":"AbleToScale"}:
              .: {}
              f:lastTransitionTime: {}
              f:message: {}
              f:reason: {}
              f:status: {}
              f:type: {}
            k:{"type":"ScalingActive"}:
              .: {}
              f:lastTransitionTime: {}
              f:message: {}
              f:reason: {}
              f:status: {}
              f:type: {}
            k:{"type":"ScalingLimited"}:
              .: {}
              f:lastTransitionTime: {}
              f:message: {}
              f:reason: {}
              f:status: {}
              f:type: {}
          f:currentMetrics: {}
          f:currentReplicas: {}
          f:desiredReplicas: {}
      manager: kube-controller-manager
      operation: Update
      subresource: status
      time: "2026-04-16T17:03:15Z"
    name: message-dumper-raw-dc743-predictor
    namespace: kserve-ci-e2e-test
    ownerReferences:
    - apiVersion: serving.kserve.io/v1beta1
      blockOwnerDeletion: true
      controller: true
      kind: InferenceService
      name: message-dumper-raw-dc743
      uid: facd8c35-cb20-4008-974e-a7f73555c8ef
    resourceVersion: "16684"
    uid: 395c4343-3894-4ada-b895-a3a54a99c255
  spec:
    behavior:
      scaleDown:
        policies:
        - periodSeconds: 15
          type: Percent
          value: 100
        selectPolicy: Max
      scaleUp:
        policies:
        - periodSeconds: 15
          type: Pods
          value: 4
        - periodSeconds: 15
          type: Percent
          value: 100
        selectPolicy: Max
        stabilizationWindowSeconds: 0
    maxReplicas: 1
    metrics:
    - resource:
        name: cpu
        target:
          averageUtilization: 80
          type: Utilization
      type: Resource
    minReplicas: 1
    scaleTargetRef:
      apiVersion: apps/v1
      kind: Deployment
      name: message-dumper-raw-dc743-predictor
  status:
    conditions:
    - lastTransitionTime: "2026-04-16T17:02:45Z"
      message: recommended size matches current size
      reason: ReadyForNewScale
      status: "True"
      type: AbleToScale
    - lastTransitionTime: "2026-04-16T17:03:15Z"
      message: the HPA was able to successfully calculate a replica count from cpu
        resource utilization (percentage of request)
      reason: ValidMetricFound
      status: "True"
      type: ScalingActive
    - lastTransitionTime: "2026-04-16T17:03:15Z"
      message: the desired count is within the acceptable range
      reason: DesiredWithinRange
      status: "False"
      type: ScalingLimited
    currentMetrics:
    - resource:
        current:
          averageUtilization: 10
          averageValue: 1m
        name: cpu
      type: Resource
    currentReplicas: 1
    desiredReplicas: 1
- apiVersion: autoscaling/v2
  kind: HorizontalPodAutoscaler
  metadata:
    annotations:
      internal.serving.kserve.io/storage-initializer-sourceuri: gs://kfserving-examples/models/sklearn/1.0/model
      prometheus.kserve.io/path: /metrics
      prometheus.kserve.io/port: "8080"
      service.beta.openshift.io/serving-cert-secret-name: raw-sklearn-19113-predictor-serving-cert
      serving.kserve.io/deploymentMode: Standard
    creationTimestamp: "2026-04-16T17:07:44Z"
    labels:
      app: isvc.raw-sklearn-19113-predictor
      component: predictor
      networking.kserve.io/visibility: exposed
      serving.kserve.io/inferenceservice: raw-sklearn-19113
    managedFields:
    - apiVersion: autoscaling/v2
      fieldsType: FieldsV1
      fieldsV1:
        f:metadata:
          f:annotations:
            .: {}
            f:internal.serving.kserve.io/storage-initializer-sourceuri: {}
            f:prometheus.kserve.io/path: {}
            f:prometheus.kserve.io/port: {}
            f:service.beta.openshift.io/serving-cert-secret-name: {}
            f:serving.kserve.io/deploymentMode: {}
          f:labels:
            .: {}
            f:app: {}
            f:component: {}
            f:networking.kserve.io/visibility: {}
            f:serving.kserve.io/inferenceservice: {}
          f:ownerReferences:
            .: {}
            k:{"uid":"ae29fa18-a5b3-40c5-b54d-67fad170f8d0"}: {}
        f:spec:
          f:behavior:
            .: {}
            f:scaleDown:
              .: {}
              f:policies: {}
              f:selectPolicy: {}
            f:scaleUp:
              .: {}
              f:policies: {}
              f:selectPolicy: {}
              f:stabilizationWindowSeconds: {}
          f:maxReplicas: {}
          f:metrics: {}
          f:minReplicas: {}
          f:scaleTargetRef:
            f:apiVersion: {}
            f:kind: {}
            f:name: {}
      manager: manager
      operation: Update
      time: "2026-04-16T17:07:44Z"
    - apiVersion: autoscaling/v2
      fieldsType: FieldsV1
      fieldsV1:
        f:status:
          f:conditions:
            .: {}
            k:{"type":"AbleToScale"}:
              .: {}
              f:lastTransitionTime: {}
              f:message: {}
              f:reason: {}
              f:status: {}
              f:type: {}
            k:{"type":"ScalingActive"}:
              .: {}
              f:lastTransitionTime: {}
              f:message: {}
              f:reason: {}
              f:status: {}
              f:type: {}
            k:{"type":"ScalingLimited"}:
              .: {}
              f:lastTransitionTime: {}
              f:message: {}
              f:reason: {}
              f:status: {}
              f:type: {}
          f:currentMetrics: {}
          f:currentReplicas: {}
          f:desiredReplicas: {}
      manager: kube-controller-manager
      operation: Update
      subresource: status
      time: "2026-04-16T17:09:59Z"
    name: raw-sklearn-19113-predictor
    namespace: kserve-ci-e2e-test
    ownerReferences:
    - apiVersion: serving.kserve.io/v1beta1
      blockOwnerDeletion: true
      controller: true
      kind: InferenceService
      name: raw-sklearn-19113
      uid: ae29fa18-a5b3-40c5-b54d-67fad170f8d0
    resourceVersion: "20031"
    uid: d589fa8b-0dd4-46ac-ab50-a34b3e02d469
  spec:
    behavior:
      scaleDown:
        policies:
        - periodSeconds: 15
          type: Percent
          value: 100
        selectPolicy: Max
      scaleUp:
        policies:
        - periodSeconds: 15
          type: Pods
          value: 4
        - periodSeconds: 15
          type: Percent
          value: 100
        selectPolicy: Max
        stabilizationWindowSeconds: 0
    maxReplicas: 1
    metrics:
    - resource:
        name: cpu
        target:
          averageUtilization: 80
          type: Utilization
      type: Resource
    minReplicas: 1
    scaleTargetRef:
      apiVersion: apps/v1
      kind: Deployment
      name: raw-sklearn-19113-predictor
  status:
    conditions:
    - lastTransitionTime: "2026-04-16T17:07:59Z"
      message: recommended size matches current size
      reason: ReadyForNewScale
      status: "True"
      type: AbleToScale
    - lastTransitionTime: "2026-04-16T17:09:44Z"
      message: the HPA was able to successfully calculate a replica count from cpu
        resource utilization (percentage of request)
      reason: ValidMetricFound
      status: "True"
      type: ScalingActive
    - lastTransitionTime: "2026-04-16T17:09:44Z"
      message: the desired count is within the acceptable range
      reason: DesiredWithinRange
      status: "False"
      type: ScalingLimited
    currentMetrics:
    - resource:
        current:
          averageUtilization: 4
          averageValue: 2m
        name: cpu
      type: Resource
    currentReplicas: 1
    desiredReplicas: 1
- apiVersion: autoscaling/v2
  kind: HorizontalPodAutoscaler
  metadata:
    annotations:
      internal.serving.kserve.io/storage-initializer-sourceuri: gs://kfserving-examples/models/sklearn/1.0/model
      prometheus.kserve.io/path: /metrics
      prometheus.kserve.io/port: "8080"
      service.beta.openshift.io/serving-cert-secret-name: raw-sklearn-runtime-aa36c-predictor-serving-cert
      serving.kserve.io/deploymentMode: Standard
    creationTimestamp: "2026-04-16T17:09:04Z"
    labels:
      app: isvc.raw-sklearn-runtime-aa36c-predictor
      component: predictor
      networking.kserve.io/visibility: exposed
      serving.kserve.io/inferenceservice: raw-sklearn-runtime-aa36c
    managedFields:
    - apiVersion: autoscaling/v2
      fieldsType: FieldsV1
      fieldsV1:
        f:metadata:
          f:annotations:
            .: {}
            f:internal.serving.kserve.io/storage-initializer-sourceuri: {}
            f:prometheus.kserve.io/path: {}
            f:prometheus.kserve.io/port: {}
            f:service.beta.openshift.io/serving-cert-secret-name: {}
            f:serving.kserve.io/deploymentMode: {}
          f:labels:
            .: {}
            f:app: {}
            f:component: {}
            f:networking.kserve.io/visibility: {}
            f:serving.kserve.io/inferenceservice: {}
          f:ownerReferences:
            .: {}
            k:{"uid":"4b5e1cc8-804a-4928-a68e-02176bb54aad"}: {}
        f:spec:
          f:behavior:
            .: {}
            f:scaleDown:
              .: {}
              f:policies: {}
              f:selectPolicy: {}
            f:scaleUp:
              .: {}
              f:policies: {}
              f:selectPolicy: {}
              f:stabilizationWindowSeconds: {}
          f:maxReplicas: {}
          f:metrics: {}
          f:minReplicas: {}
          f:scaleTargetRef:
            f:apiVersion: {}
            f:kind: {}
            f:name: {}
      manager: manager
      operation: Update
      time: "2026-04-16T17:09:04Z"
    - apiVersion: autoscaling/v2
      fieldsType: FieldsV1
      fieldsV1:
        f:status:
          f:conditions:
            .: {}
            k:{"type":"AbleToScale"}:
              .: {}
              f:lastTransitionTime: {}
              f:message: {}
              f:reason: {}
              f:status: {}
              f:type: {}
            k:{"type":"ScalingActive"}:
              .: {}
              f:lastTransitionTime: {}
              f:message: {}
              f:reason: {}
              f:status: {}
              f:type: {}
          f:currentMetrics: {}
          f:currentReplicas: {}
      manager: kube-controller-manager
      operation: Update
      subresource: status
      time: "2026-04-16T17:09:49Z"
    name: raw-sklearn-runtime-aa36c-predictor
    namespace: kserve-ci-e2e-test
    ownerReferences:
    - apiVersion: serving.kserve.io/v1beta1
      blockOwnerDeletion: true
      controller: true
      kind: InferenceService
      name: raw-sklearn-runtime-aa36c
      uid: 4b5e1cc8-804a-4928-a68e-02176bb54aad
    resourceVersion: "19962"
    uid: ec7351ba-6325-442b-99f1-2b46baa342c0
  spec:
    behavior:
      scaleDown:
        policies:
        - periodSeconds: 15
          type: Percent
          value: 100
        selectPolicy: Max
      scaleUp:
        policies:
        - periodSeconds: 15
          type: Pods
          value: 4
        - periodSeconds: 15
          type: Percent
          value: 100
        selectPolicy: Max
        stabilizationWindowSeconds: 0
    maxReplicas: 1
    metrics:
    - resource:
        name: cpu
        target:
          averageUtilization: 80
          type: Utilization
      type: Resource
    minReplicas: 1
    scaleTargetRef:
      apiVersion: apps/v1
      kind: Deployment
      name: raw-sklearn-runtime-aa36c-predictor
  status:
    conditions:
    - lastTransitionTime: "2026-04-16T17:09:19Z"
      message: the HPA controller was able to get the target's current scale
      reason: SucceededGetScale
      status: "True"
      type: AbleToScale
    - lastTransitionTime: "2026-04-16T17:09:19Z"
      message: 'the HPA was unable to compute the replica count: failed to get cpu
        utilization: did not receive metrics for targeted pods (pods might be unready)'
      reason: FailedGetResourceMetric
      status: "False"
      type: ScalingActive
    currentMetrics:
    - type: ""
    currentReplicas: 1
    desiredReplicas: 0
kind: HorizontalPodAutoscalerList
metadata:
  resourceVersion: "20458"