--- apiVersion: autoscaling/v2 items: - apiVersion: autoscaling/v2 kind: HorizontalPodAutoscaler metadata: annotations: service.beta.openshift.io/serving-cert-secret-name: success-200-isvc-82b82-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-22T18:45:48Z" labels: app: isvc.success-200-isvc-82b82-predictor component: predictor serving.kserve.io/inferenceservice: success-200-isvc-82b82 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:serving.kserve.io/inferenceservice: {} f:ownerReferences: .: {} k:{"uid":"07141bb0-7b25-46d5-83b9-1509230944b6"}: {} 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: "2026-04-22T18:45:48Z" - 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: "2026-04-22T19:42:06Z" name: success-200-isvc-82b82-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: success-200-isvc-82b82 uid: 07141bb0-7b25-46d5-83b9-1509230944b6 resourceVersion: "37020" uid: a6def932-4ee4-4ae3-8f7d-fb92e2352c3f 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: success-200-isvc-82b82-predictor status: conditions: - lastTransitionTime: "2026-04-22T18:46:03Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-22T18:47:34Z" 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: "2026-04-22T18:47:34Z" message: the desired count is within the acceptable range reason: DesiredWithinRange status: "False" type: ScalingLimited currentMetrics: - resource: current: averageUtilization: 2 averageValue: 1m name: cpu type: Resource currentReplicas: 1 desiredReplicas: 1 kind: HorizontalPodAutoscalerList metadata: resourceVersion: "39070"