--- apiVersion: autoscaling/v2 items: - apiVersion: autoscaling/v2 kind: HorizontalPodAutoscaler metadata: annotations: internal.serving.kserve.io/storage-initializer-sourceuri: gs://kfserving-examples/models/lightgbm/iris prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-lightgbm-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:01:25Z" labels: app: isvc.isvc-lightgbm-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-lightgbm 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":"cb6de5e4-4fe9-4a87-9cf0-2f4c739a49c0"}: {} 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: "2026-04-16T17:01:25Z" - 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: "2026-04-16T17:50:42Z" name: isvc-lightgbm-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-lightgbm uid: cb6de5e4-4fe9-4a87-9cf0-2f4c739a49c0 resourceVersion: "40927" uid: aeb134b8-bde8-42aa-a046-e41235051fa7 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-lightgbm-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:01:40Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:03:40Z" 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: "2026-04-16T17:03:40Z" 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 - apiVersion: autoscaling/v2 kind: HorizontalPodAutoscaler metadata: annotations: internal.serving.kserve.io/storage-initializer-sourceuri: gs://kfserving-examples/models/lightgbm/iris prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-lightgbm-runtime-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:03:05Z" labels: app: isvc.isvc-lightgbm-runtime-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-lightgbm-runtime 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":"a12ee8c7-c626-4dc2-8f13-a4924c8d3454"}: {} 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: "2026-04-16T17:03:05Z" - 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: "2026-04-16T17:51:23Z" name: isvc-lightgbm-runtime-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-lightgbm-runtime uid: a12ee8c7-c626-4dc2-8f13-a4924c8d3454 resourceVersion: "41216" uid: 67d1a53c-ea3f-441e-95b6-1aef696375af 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-lightgbm-runtime-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:03:20Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:05:05Z" 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: "2026-04-16T17:05:05Z" 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 - apiVersion: autoscaling/v2 kind: HorizontalPodAutoscaler metadata: annotations: internal.serving.kserve.io/storage-initializer-sourceuri: gs://kfserving-examples/models/lightgbm/v2/iris prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-lightgbm-v2-kserve-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:07:26Z" labels: app: isvc.isvc-lightgbm-v2-kserve-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-lightgbm-v2-kserve 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":"a4889cd8-da73-42a2-b00b-beef828283be"}: {} 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: "2026-04-16T17:07:26Z" - 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: "2026-04-16T17:51:13Z" name: isvc-lightgbm-v2-kserve-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-lightgbm-v2-kserve uid: a4889cd8-da73-42a2-b00b-beef828283be resourceVersion: "41146" uid: b3857168-9c11-4723-91e8-4f7aa9ad9442 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-lightgbm-v2-kserve-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:07:41Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:08:11Z" 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: "2026-04-16T17:08:11Z" 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 - apiVersion: autoscaling/v2 kind: HorizontalPodAutoscaler metadata: annotations: internal.serving.kserve.io/storage-initializer-sourceuri: gs://kfserving-examples/models/lightgbm/v2/iris prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-lightgbm-v2-runtime-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:04:25Z" labels: app: isvc.isvc-lightgbm-v2-runtime-predictor component: predictor modelClass: mlserver_lightgbm.LightGBMModel networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-lightgbm-v2-runtime 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:modelClass: {} f:networking.kserve.io/visibility: {} f:serving.kserve.io/inferenceservice: {} f:ownerReferences: .: {} k:{"uid":"273fb1a7-ba44-453e-b637-3dd8cff506cd"}: {} 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: "2026-04-16T17:04:25Z" - 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: "2026-04-16T17:51:13Z" name: isvc-lightgbm-v2-runtime-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-lightgbm-v2-runtime uid: 273fb1a7-ba44-453e-b637-3dd8cff506cd resourceVersion: "41145" uid: ffeaa638-9c20-4506-90ad-40ac243091eb 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-lightgbm-v2-runtime-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:04:40Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:07:56Z" 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: "2026-04-16T17:07:56Z" 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/logger: "true" internal.serving.kserve.io/logger-mode: all internal.serving.kserve.io/logger-sink-url: http://message-dumper-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-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:00:05Z" labels: app: isvc.isvc-logger-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-logger 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":"d9fad840-70db-4b42-99b0-6b0beec200c1"}: {} 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: "2026-04-16T17:00:05Z" - 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: "2026-04-16T17:02:20Z" name: isvc-logger-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-logger uid: d9fad840-70db-4b42-99b0-6b0beec200c1 resourceVersion: "16278" uid: 41603f3d-b103-470d-89ac-e6a2995e885b 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-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:00:20Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:02:20Z" 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: "2026-04-16T17:02:20Z" 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/storage-initializer-sourceuri: gs://kfserving-examples/models/mlflow/wine prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-mlflow-v2-runtime-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:07:46Z" labels: app: isvc.isvc-mlflow-v2-runtime-predictor component: predictor modelClass: mlserver_mlflow.MLflowRuntime networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-mlflow-v2-runtime 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:modelClass: {} f:networking.kserve.io/visibility: {} f:serving.kserve.io/inferenceservice: {} f:ownerReferences: .: {} k:{"uid":"40a180d1-c28f-4a93-9e9a-1efe9cf87424"}: {} 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: "2026-04-16T17:07:46Z" - 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: "2026-04-16T17:50:33Z" name: isvc-mlflow-v2-runtime-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-mlflow-v2-runtime uid: 40a180d1-c28f-4a93-9e9a-1efe9cf87424 resourceVersion: "40868" uid: 74007e77-2000-40d1-9324-69cfaff3a7f1 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-mlflow-v2-runtime-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:08:01Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:09:01Z" 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: "2026-04-16T17:09:01Z" 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 - apiVersion: autoscaling/v2 kind: HorizontalPodAutoscaler metadata: annotations: internal.serving.kserve.io/storage-initializer-sourceuri: gs://kfserving-examples/models/paddle/resnet prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-paddle-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:09:36Z" labels: app: isvc.isvc-paddle-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-paddle 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":"72ee0cb1-19fd-4806-bb7d-affe585206fa"}: {} 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: "2026-04-16T17:09:36Z" - 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: "2026-04-16T17:11:36Z" name: isvc-paddle-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-paddle uid: 72ee0cb1-19fd-4806-bb7d-affe585206fa resourceVersion: "20751" uid: 99569964-2b54-46fa-aa6b-9175aa3b69e4 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-paddle-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:09:51Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:11:36Z" 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: "2026-04-16T17:11:36Z" message: the desired count is within the acceptable range reason: DesiredWithinRange status: "False" type: ScalingLimited currentMetrics: - resource: current: averageUtilization: 1 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/paddle/resnet prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-paddle-runtime-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:10:47Z" labels: app: isvc.isvc-paddle-runtime-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-paddle-runtime 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":"de10213d-094b-48d9-9f4a-9513bbf83a2f"}: {} 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: "2026-04-16T17:10:47Z" - 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: "2026-04-16T17:12:17Z" name: isvc-paddle-runtime-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-paddle-runtime uid: de10213d-094b-48d9-9f4a-9513bbf83a2f resourceVersion: "21102" uid: 195e1d37-ec83-4320-95b5-fd14a35b66a3 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-paddle-runtime-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:11:02Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:12:17Z" 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: "2026-04-16T17:12:17Z" message: the desired count is within the acceptable range reason: DesiredWithinRange status: "False" type: ScalingLimited currentMetrics: - resource: current: averageUtilization: 1 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/paddle/resnet prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-paddle-v2-kserve-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:11:37Z" labels: app: isvc.isvc-paddle-v2-kserve-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-paddle-v2-kserve 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":"c9a10b25-cbc5-42be-bdfa-10e9d0635195"}: {} 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: "2026-04-16T17:11:37Z" - 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: "2026-04-16T17:13:23Z" name: isvc-paddle-v2-kserve-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-paddle-v2-kserve uid: c9a10b25-cbc5-42be-bdfa-10e9d0635195 resourceVersion: "21647" uid: 41c3e3f4-5b9b-402e-9e52-2ccb04d2be71 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-paddle-v2-kserve-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:11:52Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:13:23Z" 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: "2026-04-16T17:13:23Z" message: the desired count is within the acceptable range reason: DesiredWithinRange status: "False" type: ScalingLimited currentMetrics: - resource: current: averageUtilization: 1 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/pmml prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-pmml-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:12:38Z" labels: app: isvc.isvc-pmml-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-pmml 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":"d48578ff-9102-4f42-916c-de35ccc44851"}: {} 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: "2026-04-16T17:12:38Z" - 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: "2026-04-16T17:14:53Z" name: isvc-pmml-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-pmml uid: d48578ff-9102-4f42-916c-de35ccc44851 resourceVersion: "22362" uid: 28012bf2-f24c-4985-a920-042913869859 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-pmml-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:12:53Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:14:53Z" 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: "2026-04-16T17:14:53Z" message: the desired count is within the acceptable range reason: DesiredWithinRange status: "False" type: ScalingLimited currentMetrics: - resource: current: averageUtilization: 20 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/pmml prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-pmml-runtime-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:14:08Z" labels: app: isvc.isvc-pmml-runtime-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-pmml-runtime 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":"c93ca6eb-c8a4-4745-b625-7289edde0dd5"}: {} 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: "2026-04-16T17:14:08Z" - 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: "2026-04-16T17:16:08Z" name: isvc-pmml-runtime-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-pmml-runtime uid: c93ca6eb-c8a4-4745-b625-7289edde0dd5 resourceVersion: "22974" uid: 8cf6196c-7e68-4dcf-9835-86106db30d90 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-pmml-runtime-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:14:23Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:16:08Z" 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: "2026-04-16T17:16:08Z" message: the desired count is within the acceptable range reason: DesiredWithinRange status: "False" type: ScalingLimited currentMetrics: - resource: current: averageUtilization: 20 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/pmml prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-pmml-v2-kserve-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:15:28Z" labels: app: isvc.isvc-pmml-v2-kserve-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-pmml-v2-kserve 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":"50712905-aba0-43cf-8952-d8f8ddbdc116"}: {} 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: "2026-04-16T17:15:28Z" - 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: "2026-04-16T17:17:29Z" name: isvc-pmml-v2-kserve-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-pmml-v2-kserve uid: 50712905-aba0-43cf-8952-d8f8ddbdc116 resourceVersion: "23617" uid: 25dba903-c3c7-4936-a99a-0756932cf712 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-pmml-v2-kserve-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:15:43Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:17:29Z" 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: "2026-04-16T17:17:29Z" message: the desired count is within the acceptable range reason: DesiredWithinRange status: "False" type: ScalingLimited currentMetrics: - resource: current: averageUtilization: 20 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/lightgbm/iris prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-predictive-lightgbm-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:22:21Z" labels: app: isvc.isvc-predictive-lightgbm-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-predictive-lightgbm 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":"f9c98bd4-33d2-4dde-8896-0c9c0dbcab60"}: {} 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: "2026-04-16T17:22:21Z" - 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: "2026-04-16T17:51:07Z" name: isvc-predictive-lightgbm-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-predictive-lightgbm uid: f9c98bd4-33d2-4dde-8896-0c9c0dbcab60 resourceVersion: "41106" uid: 761bc118-d6ac-4f0d-92c8-54f1e87843fc 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-predictive-lightgbm-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:22:36Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:24:36Z" 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: "2026-04-16T17:24:36Z" 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/lightgbm/iris prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-predictive-lightgbm-v2-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:27:01Z" labels: app: isvc.isvc-predictive-lightgbm-v2-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-predictive-lightgbm-v2 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":"487bfd88-9ac9-41b2-a17e-7a43bc539073"}: {} 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: "2026-04-16T17:27:01Z" - 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: "2026-04-16T17:49:33Z" name: isvc-predictive-lightgbm-v2-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-predictive-lightgbm-v2 uid: 487bfd88-9ac9-41b2-a17e-7a43bc539073 resourceVersion: "40412" uid: 9ccfb754-85f6-4028-9014-be49d65bb68a 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-predictive-lightgbm-v2-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:27:16Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:28:47Z" 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: "2026-04-16T17:28:47Z" 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: isvc-predictive-sklearn-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:18:50Z" labels: app: isvc.isvc-predictive-sklearn-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-predictive-sklearn 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":"6416a723-2966-48f4-b9a5-e28c2197fa8c"}: {} 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: "2026-04-16T17:18:50Z" - 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: "2026-04-16T17:49:52Z" name: isvc-predictive-sklearn-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-predictive-sklearn uid: 6416a723-2966-48f4-b9a5-e28c2197fa8c resourceVersion: "40549" uid: 67546d32-cd5e-423d-b6c2-431557590d46 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-predictive-sklearn-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:19:05Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:21:20Z" 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: "2026-04-16T17:21:20Z" 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: isvc-predictive-sklearn-v2-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:23:41Z" labels: app: isvc.isvc-predictive-sklearn-v2-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-predictive-sklearn-v2 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":"2a931ff9-affa-4c92-9d92-f4f80e30357f"}: {} 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: "2026-04-16T17:23:41Z" - 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: "2026-04-16T17:25:41Z" name: isvc-predictive-sklearn-v2-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-predictive-sklearn-v2 uid: 2a931ff9-affa-4c92-9d92-f4f80e30357f resourceVersion: "27984" uid: 5025c972-727d-42b7-a34a-e911ca180de2 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-predictive-sklearn-v2-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:23:56Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:25:41Z" 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: "2026-04-16T17:25:41Z" 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/xgboost/1.5/model prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-predictive-xgboost-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:20:31Z" labels: app: isvc.isvc-predictive-xgboost-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-predictive-xgboost 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":"2c0325d2-1e00-4e95-b6d0-c7ca600db9c3"}: {} 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: "2026-04-16T17:20:31Z" - 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: "2026-04-16T17:23:01Z" name: isvc-predictive-xgboost-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-predictive-xgboost uid: 2c0325d2-1e00-4e95-b6d0-c7ca600db9c3 resourceVersion: "26701" uid: f0fe9ac7-f588-48e6-b7d5-347b07ee8170 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-predictive-xgboost-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:20:46Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:23:01Z" 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: "2026-04-16T17:23:01Z" 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/xgboost/1.5/model prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-predictive-xgboost-v2-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:25:11Z" labels: app: isvc.isvc-predictive-xgboost-v2-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-predictive-xgboost-v2 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":"dbf21356-7ece-48ab-9a10-99325f5c5a0a"}: {} 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: "2026-04-16T17:25:11Z" - 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: "2026-04-16T17:45:27Z" name: isvc-predictive-xgboost-v2-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-predictive-xgboost-v2 uid: dbf21356-7ece-48ab-9a10-99325f5c5a0a resourceVersion: "38066" uid: 625533b8-27ac-4672-be5d-14ad2ab613a9 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-predictive-xgboost-v2-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:25:26Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:27:26Z" 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: "2026-04-16T17:27:26Z" 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/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-sklearn-batcher-custom-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T16:58:34Z" labels: app: isvc.isvc-sklearn-batcher-custom-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-sklearn-batcher-custom 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":"c8791899-14c9-410b-9287-78384a54eaa1"}: {} 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: "2026-04-16T16:58:34Z" - 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: "2026-04-16T17:51:07Z" name: isvc-sklearn-batcher-custom-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-sklearn-batcher-custom uid: c8791899-14c9-410b-9287-78384a54eaa1 resourceVersion: "41108" uid: d611c43a-511b-4271-b0c2-41e7cfa370d2 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-sklearn-batcher-custom-predictor status: conditions: - lastTransitionTime: "2026-04-16T16:58:50Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:00:20Z" 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: "2026-04-16T17:00:20Z" 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/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-sklearn-batcher-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T16:57:04Z" labels: app: isvc.isvc-sklearn-batcher-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-sklearn-batcher 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":"741effd1-2e6d-440e-b924-66ffb4557ed0"}: {} 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: "2026-04-16T16:57:04Z" - 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: {} 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: "2026-04-16T17:50:22Z" name: isvc-sklearn-batcher-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-sklearn-batcher uid: 741effd1-2e6d-440e-b924-66ffb4557ed0 resourceVersion: "40788" uid: 19030eca-bb2f-4c4b-9717-4990517454d3 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-sklearn-batcher-predictor status: conditions: - lastTransitionTime: "2026-04-16T16:57:19Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T16:59:19Z" 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: "2026-04-16T16:59:19Z" 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-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:28:24Z" labels: app: isvc.isvc-sklearn-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-sklearn 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":"c30a30dc-a53d-46ec-984b-61a065365716"}: {} 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: "2026-04-16T17:28:24Z" - 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: "2026-04-16T17:30:24Z" name: isvc-sklearn-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-sklearn uid: c30a30dc-a53d-46ec-984b-61a065365716 resourceVersion: "30320" uid: d26ee8f3-7812-45e0-af01-7c8fd5927211 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-sklearn-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:28:39Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:30:24Z" 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: "2026-04-16T17:30:24Z" 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/newsgroup/model.joblib prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-sklearn-runtime-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:30:34Z" labels: app: isvc.isvc-sklearn-runtime-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-sklearn-runtime 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":"45a5c1a9-a465-46dc-b4d8-7bdc9291ff09"}: {} 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: "2026-04-16T17:30:34Z" - 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: "2026-04-16T17:35:49Z" name: isvc-sklearn-runtime-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-sklearn-runtime uid: 45a5c1a9-a465-46dc-b4d8-7bdc9291ff09 resourceVersion: "33231" uid: 98a5e61e-625d-4b72-8da5-575cf46fd422 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-sklearn-runtime-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:30:49Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:31:49Z" 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: "2026-04-16T17:35:49Z" message: the desired replica count is less than the minimum replica count reason: TooFewReplicas status: "True" type: ScalingLimited currentMetrics: - resource: current: averageUtilization: 0 averageValue: 3m name: cpu type: Resource currentReplicas: 1 desiredReplicas: 1 - apiVersion: autoscaling/v2 kind: HorizontalPodAutoscaler metadata: annotations: internal.serving.kserve.io/storage-initializer-sourceuri: ://sklearn internal.serving.kserve.io/storage-spec: "true" internal.serving.kserve.io/storage-spec-key: localS3 internal.serving.kserve.io/storage-spec-param: '{"bucket":"example-models"}' prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-sklearn-s3-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:43:48Z" labels: app: isvc.isvc-sklearn-s3-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-sklearn-s3 managedFields: - apiVersion: autoscaling/v2 fieldsType: FieldsV1 fieldsV1: f:metadata: f:annotations: .: {} f:internal.serving.kserve.io/storage-initializer-sourceuri: {} f:internal.serving.kserve.io/storage-spec: {} f:internal.serving.kserve.io/storage-spec-key: {} f:internal.serving.kserve.io/storage-spec-param: {} 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":"325a7275-3f31-4f68-bf23-29913dd9178b"}: {} 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: "2026-04-16T17:43:48Z" - 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: "2026-04-16T17:50:03Z" name: isvc-sklearn-s3-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-sklearn-s3 uid: 325a7275-3f31-4f68-bf23-29913dd9178b resourceVersion: "40640" uid: 8ad74a82-df77-4088-932d-e6b26ad2e9d6 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-sklearn-s3-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:44:03Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:45:33Z" 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: "2026-04-16T17:45:33Z" 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/1.3/mixedtype prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-sklearn-v2-mixed-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:33:26Z" labels: app: isvc.isvc-sklearn-v2-mixed-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-sklearn-v2-mixed 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":"6d0e9e44-935e-46b3-ad5c-0b2a82faaa8f"}: {} 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: "2026-04-16T17:33:26Z" - 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: "2026-04-16T17:49:57Z" name: isvc-sklearn-v2-mixed-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-sklearn-v2-mixed uid: 6d0e9e44-935e-46b3-ad5c-0b2a82faaa8f resourceVersion: "40587" uid: 6842b2d5-632b-466c-b95d-d41c2867dcec 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-sklearn-v2-mixed-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:33:41Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:35:11Z" 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: "2026-04-16T17:35:11Z" 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: isvc-sklearn-v2-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:32:05Z" labels: app: isvc.isvc-sklearn-v2-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-sklearn-v2 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":"11adbef9-d610-4050-8854-ac57b6cce4d5"}: {} 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: "2026-04-16T17:32:05Z" - 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: "2026-04-16T17:49:51Z" name: isvc-sklearn-v2-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-sklearn-v2 uid: 11adbef9-d610-4050-8854-ac57b6cce4d5 resourceVersion: "40543" uid: 4978e17a-0114-4040-8150-f590c003a796 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-sklearn-v2-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:32:20Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:34:06Z" 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: "2026-04-16T17:34:06Z" 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: isvc-sklearn-v2-runtime-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:31:15Z" labels: app: isvc.isvc-sklearn-v2-runtime-predictor component: predictor modelClass: mlserver_sklearn.SKLearnModel networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-sklearn-v2-runtime 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:modelClass: {} f:networking.kserve.io/visibility: {} f:serving.kserve.io/inferenceservice: {} f:ownerReferences: .: {} k:{"uid":"076acd25-f004-4ca4-afa7-01ad9dbd09bd"}: {} 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: "2026-04-16T17:31:15Z" - 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: "2026-04-16T17:51:16Z" name: isvc-sklearn-v2-runtime-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-sklearn-v2-runtime uid: 076acd25-f004-4ca4-afa7-01ad9dbd09bd resourceVersion: "41171" uid: 2cd5e869-2df2-48e5-bf56-0111538da693 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-sklearn-v2-runtime-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:31:30Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:32:30Z" 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: "2026-04-16T17:32:30Z" 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 - apiVersion: autoscaling/v2 kind: HorizontalPodAutoscaler metadata: annotations: internal.serving.kserve.io/storage-initializer-sourceuri: gs://kfserving-examples/models/tensorflow/flowers prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-tensorflow-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:34:36Z" labels: app: isvc.isvc-tensorflow-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-tensorflow 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":"1ff2f8f0-11e8-4299-af65-f3db4101157f"}: {} 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: "2026-04-16T17:34:36Z" - 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: "2026-04-16T17:35:36Z" name: isvc-tensorflow-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-tensorflow uid: 1ff2f8f0-11e8-4299-af65-f3db4101157f resourceVersion: "33124" uid: 15cd104a-659d-4478-b046-a151b7c6a7c4 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-tensorflow-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:34:51Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:35:36Z" 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: "2026-04-16T17:35:36Z" 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/tensorflow/flowers prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-tensorflow-runtime-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:35:06Z" labels: app: isvc.isvc-tensorflow-runtime-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-tensorflow-runtime 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":"9e676199-0fab-47d8-8f56-b27b5d4ae7a3"}: {} 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: "2026-04-16T17:35:06Z" - 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: "2026-04-16T17:36:06Z" name: isvc-tensorflow-runtime-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-tensorflow-runtime uid: 9e676199-0fab-47d8-8f56-b27b5d4ae7a3 resourceVersion: "33349" uid: 295b0eeb-673e-4414-bc34-d1214bb1b018 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-tensorflow-runtime-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:35:21Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:36:06Z" 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: "2026-04-16T17:36:06Z" 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/torchscript prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8002" service.beta.openshift.io/serving-cert-secret-name: isvc-triton-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:35:26Z" labels: app: isvc.isvc-triton-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-triton 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":"141ff680-c8da-44f5-a9ec-612fd91bfff0"}: {} 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: "2026-04-16T17:35:26Z" - 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: "2026-04-16T17:38:11Z" name: isvc-triton-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-triton uid: 141ff680-c8da-44f5-a9ec-612fd91bfff0 resourceVersion: "34320" uid: 6ee858f0-b5c2-42cd-9c69-863fd6be62c0 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-triton-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:35:41Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:38:11Z" 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: "2026-04-16T17:38:11Z" 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/xgboost/1.5/model prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-xgboost-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:37:47Z" labels: app: isvc.isvc-xgboost-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-xgboost 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":"45e3cecf-9e4b-4859-bbcb-6ee90dffaf95"}: {} 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: "2026-04-16T17:37:47Z" - 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: "2026-04-16T17:50:02Z" name: isvc-xgboost-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-xgboost uid: 45e3cecf-9e4b-4859-bbcb-6ee90dffaf95 resourceVersion: "40631" uid: f5d012a5-d330-4a25-8672-44f2b5749141 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-xgboost-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:38:02Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:39:47Z" 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: "2026-04-16T17:39:47Z" 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/xgboost/1.5/model prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-xgboost-runtime-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:40:37Z" labels: app: isvc.isvc-xgboost-runtime-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-xgboost-runtime 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":"1af5b24d-9020-4f53-b4ea-54346e62060d"}: {} 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: "2026-04-16T17:40:37Z" - 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: "2026-04-16T17:49:53Z" name: isvc-xgboost-runtime-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-xgboost-runtime uid: 1af5b24d-9020-4f53-b4ea-54346e62060d resourceVersion: "40556" uid: 980bdfce-4349-46a4-b283-cd877f539f21 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-xgboost-runtime-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:40:52Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:42:22Z" 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: "2026-04-16T17:42:22Z" 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/xgboost/iris prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-xgboost-v2-mlserver-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:39:17Z" labels: app: isvc.isvc-xgboost-v2-mlserver-predictor component: predictor modelClass: mlserver_xgboost.XGBoostModel networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-xgboost-v2-mlserver 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:modelClass: {} f:networking.kserve.io/visibility: {} f:serving.kserve.io/inferenceservice: {} f:ownerReferences: .: {} k:{"uid":"11376acb-31c9-43ac-aac1-b93b325e3ba0"}: {} 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: "2026-04-16T17:39:17Z" - 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: "2026-04-16T17:50:18Z" name: isvc-xgboost-v2-mlserver-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-xgboost-v2-mlserver uid: 11376acb-31c9-43ac-aac1-b93b325e3ba0 resourceVersion: "40738" uid: 37799ecf-35d6-41ab-b687-be589deee402 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-xgboost-v2-mlserver-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:39:32Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:40:32Z" 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: "2026-04-16T17:40:32Z" 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 - apiVersion: autoscaling/v2 kind: HorizontalPodAutoscaler metadata: annotations: internal.serving.kserve.io/storage-initializer-sourceuri: gs://kfserving-examples/models/xgboost/iris prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-xgboost-v2-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:42:38Z" labels: app: isvc.isvc-xgboost-v2-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-xgboost-v2 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":"d9e28243-b847-4bec-afee-ec48fa812e33"}: {} 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: "2026-04-16T17:42:38Z" - 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: "2026-04-16T17:49:53Z" name: isvc-xgboost-v2-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-xgboost-v2 uid: d9e28243-b847-4bec-afee-ec48fa812e33 resourceVersion: "40560" uid: 290616ef-b246-4301-ac22-b45999fc6772 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-xgboost-v2-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:42:53Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:44:38Z" 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: "2026-04-16T17:44:38Z" 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/xgboost/iris prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: isvc-xgboost-v2-runtime-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:41:47Z" labels: app: isvc.isvc-xgboost-v2-runtime-predictor component: predictor modelClass: mlserver_xgboost.XGBoostModel networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: isvc-xgboost-v2-runtime 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:modelClass: {} f:networking.kserve.io/visibility: {} f:serving.kserve.io/inferenceservice: {} f:ownerReferences: .: {} k:{"uid":"5db551b9-a99c-4cf1-9200-f52f4a355471"}: {} 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: "2026-04-16T17:41:47Z" - 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: "2026-04-16T17:50:48Z" name: isvc-xgboost-v2-runtime-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: isvc-xgboost-v2-runtime uid: 5db551b9-a99c-4cf1-9200-f52f4a355471 resourceVersion: "40971" uid: ba988150-1bd2-4839-be5d-3deaa91906ce 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-xgboost-v2-runtime-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:42:02Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:43:17Z" 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: "2026-04-16T17:43:17Z" 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: service.beta.openshift.io/serving-cert-secret-name: message-dumper-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T16:59:55Z" labels: app: isvc.message-dumper-predictor component: predictor networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: message-dumper 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":"aa9fbb8e-40df-4c76-8736-d7de7fc1623f"}: {} 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: "2026-04-16T16:59:55Z" - 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: "2026-04-16T17:00:40Z" name: message-dumper-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: message-dumper uid: aa9fbb8e-40df-4c76-8736-d7de7fc1623f resourceVersion: "15486" uid: a7781d48-52be-4cd3-9173-c4b88e31eebd 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-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:00:10Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:00:40Z" 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: "2026-04-16T17:00:40Z" 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: sklearn-v2-mlserver-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:29:44Z" labels: app: isvc.sklearn-v2-mlserver-predictor component: predictor modelClass: mlserver_sklearn.SKLearnModel networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: sklearn-v2-mlserver 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:modelClass: {} f:networking.kserve.io/visibility: {} f:serving.kserve.io/inferenceservice: {} f:ownerReferences: .: {} k:{"uid":"84643644-0710-4bf6-a1c6-1846a85f06b1"}: {} 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: "2026-04-16T17:29:44Z" - 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: "2026-04-16T17:50:45Z" name: sklearn-v2-mlserver-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: sklearn-v2-mlserver uid: 84643644-0710-4bf6-a1c6-1846a85f06b1 resourceVersion: "40949" uid: 599c1efa-043e-4dfd-b220-670bc37eae9c 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: sklearn-v2-mlserver-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:29:59Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:30:59Z" 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: "2026-04-16T17:30:59Z" 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 - apiVersion: autoscaling/v2 kind: HorizontalPodAutoscaler metadata: annotations: internal.serving.kserve.io/storage-initializer-sourceuri: gs://kfserving-examples/models/xgboost/iris/model.bst prometheus.kserve.io/path: /metrics prometheus.kserve.io/port: "8080" service.beta.openshift.io/serving-cert-secret-name: xgboost-v2-mlserver-predictor-serving-cert serving.kserve.io/deploymentMode: Standard creationTimestamp: "2026-04-16T17:39:57Z" labels: app: isvc.xgboost-v2-mlserver-predictor component: predictor modelClass: mlserver_xgboost.XGBoostModel networking.kserve.io/visibility: exposed serving.kserve.io/inferenceservice: xgboost-v2-mlserver 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:modelClass: {} f:networking.kserve.io/visibility: {} f:serving.kserve.io/inferenceservice: {} f:ownerReferences: .: {} k:{"uid":"44febf4b-aeff-4c41-84b0-f4e873f93c0f"}: {} 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: "2026-04-16T17:39:57Z" - 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: "2026-04-16T17:51:28Z" name: xgboost-v2-mlserver-predictor namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1beta1 blockOwnerDeletion: true controller: true kind: InferenceService name: xgboost-v2-mlserver uid: 44febf4b-aeff-4c41-84b0-f4e873f93c0f resourceVersion: "41252" uid: 471a7118-45f3-48a4-b408-80202fd39a0b 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: xgboost-v2-mlserver-predictor status: conditions: - lastTransitionTime: "2026-04-16T17:40:12Z" message: recommended size matches current size reason: ReadyForNewScale status: "True" type: AbleToScale - lastTransitionTime: "2026-04-16T17:41:12Z" 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: "2026-04-16T17:41:12Z" 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 kind: HorizontalPodAutoscalerList metadata: resourceVersion: "41253"