--- apiVersion: autoscaling/v2 kind: HorizontalPodAutoscaler metadata: creationTimestamp: "2026-10-31T00:35:12Z" labels: gateway.istio.io/managed: openshift.io-gateway-controller-v1 gateway.networking.k8s.io/gateway-class-name: openshift-default gateway.networking.k8s.io/gateway-name: openshift-ai-inference serving.kserve.io/gateway: kserve-ingress-gateway managedFields: - apiVersion: autoscaling/v2 fieldsType: FieldsV1 fieldsV1: f:metadata: f:annotations: {} f:labels: f:gateway.istio.io/managed: {} f:gateway.networking.k8s.io/gateway-class-name: {} f:gateway.networking.k8s.io/gateway-name: {} f:serving.kserve.io/gateway: {} f:ownerReferences: k:{"uid":"35614edb-9066-46f1-b3df-3f86722a43a9"}: {} f:spec: f:maxReplicas: {} f:minReplicas: {} f:scaleTargetRef: f:apiVersion: {} f:kind: {} f:name: {} manager: openshift.io/gateway-controller/v1 operation: Apply time: "2026-10-31T00:35:12Z" - 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: {} f:lastScaleTime: {} manager: kube-controller-manager operation: Update subresource: status time: "2026-10-31T01:35:52Z" name: openshift-ai-inference-openshift-default namespace: openshift-ingress ownerReferences: - apiVersion: gateway.networking.k8s.io/v1beta1 kind: Gateway name: openshift-ai-inference uid: 35614edb-9066-46f1-b3df-3f86722a43a9 resourceVersion: "66956" uid: 7abac9d7-8601-448a-a68a-299269c3c019 spec: maxReplicas: 10 metrics: - resource: name: cpu target: averageUtilization: 80 type: Utilization type: Resource minReplicas: 1 scaleTargetRef: apiVersion: apps/v1 kind: Deployment name: openshift-ai-inference-openshift-default status: conditions: - lastTransitionTime: "2026-10-31T00:35:27Z" message: recent recommendations were higher than current one, applying the highest recent recommendation reason: ScaleDownStabilized status: "True" type: AbleToScale - lastTransitionTime: "2026-10-31T00:46:02Z" 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: "2026-10-31T01:34:52Z" message: the desired count is within the acceptable range reason: DesiredWithinRange status: "False" type: ScalingLimited currentMetrics: - resource: current: averageUtilization: 1 averageValue: 1m name: cpu type: Resource currentReplicas: 6 desiredReplicas: 6 lastScaleTime: "2026-10-31T01:35:07Z"