--- apiVersion: apps/v1 items: - apiVersion: apps/v1 kind: Deployment metadata: annotations: deployment.kubernetes.io/revision: "1" creationTimestamp: "2026-07-01T20:58:31Z" generation: 1 labels: gateway.istio.io/managed: openshift.io-gateway-controller-v1 gateway.networking.k8s.io/gateway-name: router-gateway-1 managedFields: - apiVersion: apps/v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:annotations: {} f:labels: f:gateway.istio.io/managed: {} f:gateway.networking.k8s.io/gateway-name: {} f:ownerReferences: k:{"uid":"8836cc11-b4a3-48e2-8dbe-f5c237dd0dae"}: {} f:spec: f:selector: {} f:template: f:metadata: f:annotations: f:istio.io/rev: {} f:prometheus.io/path: {} f:prometheus.io/port: {} f:prometheus.io/scrape: {} f:labels: f:gateway.istio.io/managed: {} f:gateway.networking.k8s.io/gateway-name: {} f:service.istio.io/canonical-name: {} f:service.istio.io/canonical-revision: {} f:sidecar.istio.io/inject: {} f:spec: f:containers: k:{"name":"istio-proxy"}: .: {} f:args: {} f:env: k:{"name":"CA_ADDR"}: .: {} f:name: {} f:value: {} k:{"name":"GOMAXPROCS"}: .: {} f:name: {} f:valueFrom: f:resourceFieldRef: {} k:{"name":"GOMEMLIMIT"}: .: {} f:name: {} f:valueFrom: f:resourceFieldRef: {} k:{"name":"HOST_IP"}: .: {} f:name: {} f:valueFrom: f:fieldRef: {} k:{"name":"INSTANCE_IP"}: .: {} f:name: {} f:valueFrom: f:fieldRef: {} k:{"name":"ISTIO_CPU_LIMIT"}: .: {} f:name: {} f:valueFrom: f:resourceFieldRef: {} k:{"name":"ISTIO_META_APP_CONTAINERS"}: .: {} f:name: {} f:value: {} k:{"name":"ISTIO_META_CLUSTER_ID"}: .: {} f:name: {} f:value: {} k:{"name":"ISTIO_META_INTERCEPTION_MODE"}: .: {} f:name: {} f:value: {} k:{"name":"ISTIO_META_MESH_ID"}: .: {} f:name: {} f:value: {} k:{"name":"ISTIO_META_NODE_NAME"}: .: {} f:name: {} f:valueFrom: f:fieldRef: {} k:{"name":"ISTIO_META_OWNER"}: .: {} f:name: {} f:value: {} k:{"name":"ISTIO_META_POD_PORTS"}: .: {} f:name: {} f:value: {} k:{"name":"ISTIO_META_WORKLOAD_NAME"}: .: {} f:name: {} f:value: {} k:{"name":"PILOT_CERT_PROVIDER"}: .: {} f:name: {} f:value: {} k:{"name":"POD_NAME"}: .: {} f:name: {} f:valueFrom: f:fieldRef: {} k:{"name":"POD_NAMESPACE"}: .: {} f:name: {} f:valueFrom: f:fieldRef: {} k:{"name":"PROXY_CONFIG"}: .: {} f:name: {} f:value: {} k:{"name":"SERVICE_ACCOUNT"}: .: {} f:name: {} f:valueFrom: f:fieldRef: {} k:{"name":"TRUST_DOMAIN"}: .: {} f:name: {} f:value: {} f:image: {} f:name: {} f:ports: k:{"containerPort":15020,"protocol":"TCP"}: .: {} f:containerPort: {} f:name: {} f:protocol: {} k:{"containerPort":15021,"protocol":"TCP"}: .: {} f:containerPort: {} f:name: {} f:protocol: {} k:{"containerPort":15090,"protocol":"TCP"}: .: {} f:containerPort: {} f:name: {} f:protocol: {} f:readinessProbe: f:failureThreshold: {} f:httpGet: f:path: {} f:port: {} f:scheme: {} f:initialDelaySeconds: {} f:periodSeconds: {} f:successThreshold: {} f:timeoutSeconds: {} f:resources: f:limits: f:cpu: {} f:memory: {} f:requests: f:cpu: {} f:memory: {} f:securityContext: f:allowPrivilegeEscalation: {} f:capabilities: f:drop: {} f:privileged: {} f:readOnlyRootFilesystem: {} f:runAsGroup: {} f:runAsNonRoot: {} f:runAsUser: {} f:startupProbe: f:failureThreshold: {} f:httpGet: f:path: {} f:port: {} f:scheme: {} f:initialDelaySeconds: {} f:periodSeconds: {} f:successThreshold: {} f:timeoutSeconds: {} f:volumeMounts: k:{"mountPath":"/etc/istio/pod"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/etc/istio/proxy"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/var/lib/istio/data"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/var/run/secrets/credential-uds"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/var/run/secrets/istio"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/var/run/secrets/tokens"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/var/run/secrets/workload-spiffe-credentials"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/var/run/secrets/workload-spiffe-uds"}: .: {} f:mountPath: {} f:name: {} f:securityContext: f:sysctls: {} f:serviceAccountName: {} f:volumes: k:{"name":"credential-socket"}: .: {} f:emptyDir: {} f:name: {} k:{"name":"istio-data"}: .: {} f:emptyDir: {} f:name: {} k:{"name":"istio-envoy"}: .: {} f:emptyDir: f:medium: {} f:name: {} k:{"name":"istio-podinfo"}: .: {} f:downwardAPI: f:items: {} f:name: {} k:{"name":"istio-token"}: .: {} f:name: {} f:projected: f:sources: {} k:{"name":"istiod-ca-cert"}: .: {} f:configMap: f:name: {} f:name: {} k:{"name":"workload-certs"}: .: {} f:emptyDir: {} f:name: {} k:{"name":"workload-socket"}: .: {} f:emptyDir: {} f:name: {} manager: openshift.io/gateway-controller/v1 operation: Apply time: "2026-07-01T20:58:31Z" - apiVersion: apps/v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:annotations: .: {} f:deployment.kubernetes.io/revision: {} f:status: f:availableReplicas: {} f:conditions: .: {} k:{"type":"Available"}: .: {} f:lastTransitionTime: {} f:lastUpdateTime: {} f:message: {} f:reason: {} f:status: {} f:type: {} k:{"type":"Progressing"}: .: {} f:lastTransitionTime: {} f:lastUpdateTime: {} f:message: {} f:reason: {} f:status: {} f:type: {} f:observedGeneration: {} f:readyReplicas: {} f:replicas: {} f:updatedReplicas: {} manager: kube-controller-manager operation: Update subresource: status time: "2026-07-01T20:59:10Z" name: router-gateway-1-openshift-default namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: gateway.networking.k8s.io/v1beta1 kind: Gateway name: router-gateway-1 uid: 8836cc11-b4a3-48e2-8dbe-f5c237dd0dae resourceVersion: "21887" uid: 8139d719-fa6f-4048-84f2-c62d97599906 spec: progressDeadlineSeconds: 600 replicas: 1 revisionHistoryLimit: 10 selector: matchLabels: gateway.networking.k8s.io/gateway-name: router-gateway-1 strategy: rollingUpdate: maxSurge: 25% maxUnavailable: 25% type: RollingUpdate template: metadata: annotations: istio.io/rev: openshift-gateway prometheus.io/path: /stats/prometheus prometheus.io/port: "15020" prometheus.io/scrape: "true" labels: gateway.istio.io/managed: istio.io-gateway-controller gateway.networking.k8s.io/gateway-name: router-gateway-1 service.istio.io/canonical-name: router-gateway-1-openshift-default service.istio.io/canonical-revision: latest sidecar.istio.io/inject: "false" spec: containers: - args: - proxy - router - --domain - $(POD_NAMESPACE).svc.cluster.local - --proxyLogLevel - warning - --proxyComponentLogLevel - misc:error - --log_output_level - default:info env: - name: PILOT_CERT_PROVIDER value: istiod - name: CA_ADDR value: istiod-openshift-gateway.openshift-ingress.svc:15012 - name: POD_NAME valueFrom: fieldRef: apiVersion: v1 fieldPath: metadata.name - name: POD_NAMESPACE valueFrom: fieldRef: apiVersion: v1 fieldPath: metadata.namespace - name: INSTANCE_IP valueFrom: fieldRef: apiVersion: v1 fieldPath: status.podIP - name: SERVICE_ACCOUNT valueFrom: fieldRef: apiVersion: v1 fieldPath: spec.serviceAccountName - name: HOST_IP valueFrom: fieldRef: apiVersion: v1 fieldPath: status.hostIP - name: ISTIO_CPU_LIMIT valueFrom: resourceFieldRef: divisor: "0" resource: limits.cpu - name: PROXY_CONFIG value: | {"discoveryAddress":"istiod-openshift-gateway.openshift-ingress.svc:15012","proxyHeaders":{"server":{"disabled":true},"envoyDebugHeaders":{"disabled":true},"metadataExchangeHeaders":{"mode":"IN_MESH"}}} - name: ISTIO_META_POD_PORTS value: '[]' - name: ISTIO_META_APP_CONTAINERS - name: GOMEMLIMIT valueFrom: resourceFieldRef: divisor: "0" resource: limits.memory - name: GOMAXPROCS valueFrom: resourceFieldRef: divisor: "0" resource: limits.cpu - name: ISTIO_META_CLUSTER_ID value: Kubernetes - name: ISTIO_META_NODE_NAME valueFrom: fieldRef: apiVersion: v1 fieldPath: spec.nodeName - name: ISTIO_META_INTERCEPTION_MODE value: REDIRECT - name: ISTIO_META_WORKLOAD_NAME value: router-gateway-1-openshift-default - name: ISTIO_META_OWNER value: kubernetes://apis/apps/v1/namespaces/kserve-ci-e2e-test/deployments/router-gateway-1-openshift-default - name: ISTIO_META_MESH_ID value: cluster.local - name: TRUST_DOMAIN value: cluster.local image: registry.redhat.io/openshift-service-mesh/istio-proxyv2-rhel9@sha256:7d15cebf9b62f3f235c0eab5158ac8ff2fda86a1d193490dc94c301402c99da8 imagePullPolicy: IfNotPresent name: istio-proxy ports: - containerPort: 15020 name: metrics protocol: TCP - containerPort: 15021 name: status-port protocol: TCP - containerPort: 15090 name: http-envoy-prom protocol: TCP readinessProbe: failureThreshold: 4 httpGet: path: /healthz/ready port: 15021 scheme: HTTP periodSeconds: 15 successThreshold: 1 timeoutSeconds: 1 resources: limits: cpu: "2" memory: 2Gi requests: cpu: 100m memory: 256Mi securityContext: allowPrivilegeEscalation: false capabilities: drop: - ALL privileged: false readOnlyRootFilesystem: true runAsGroup: 1000699999 runAsNonRoot: true runAsUser: 1000699999 startupProbe: failureThreshold: 30 httpGet: path: /healthz/ready port: 15021 scheme: HTTP initialDelaySeconds: 1 periodSeconds: 1 successThreshold: 1 timeoutSeconds: 1 terminationMessagePath: /dev/termination-log terminationMessagePolicy: File volumeMounts: - mountPath: /var/run/secrets/workload-spiffe-uds name: workload-socket - mountPath: /var/run/secrets/credential-uds name: credential-socket - mountPath: /var/run/secrets/workload-spiffe-credentials name: workload-certs - mountPath: /var/run/secrets/istio name: istiod-ca-cert - mountPath: /var/lib/istio/data name: istio-data - mountPath: /etc/istio/proxy name: istio-envoy - mountPath: /var/run/secrets/tokens name: istio-token - mountPath: /etc/istio/pod name: istio-podinfo dnsPolicy: ClusterFirst restartPolicy: Always schedulerName: default-scheduler securityContext: sysctls: - name: net.ipv4.ip_unprivileged_port_start value: "0" serviceAccount: router-gateway-1-openshift-default serviceAccountName: router-gateway-1-openshift-default terminationGracePeriodSeconds: 30 volumes: - emptyDir: {} name: workload-socket - emptyDir: {} name: credential-socket - emptyDir: {} name: workload-certs - emptyDir: medium: Memory name: istio-envoy - emptyDir: {} name: istio-data - downwardAPI: defaultMode: 420 items: - fieldRef: apiVersion: v1 fieldPath: metadata.labels path: labels - fieldRef: apiVersion: v1 fieldPath: metadata.annotations path: annotations name: istio-podinfo - name: istio-token projected: defaultMode: 420 sources: - serviceAccountToken: audience: istio-ca expirationSeconds: 43200 path: istio-token - configMap: defaultMode: 420 name: openshift-gw-ca-root-cert name: istiod-ca-cert status: availableReplicas: 1 conditions: - lastTransitionTime: "2026-07-01T20:58:31Z" lastUpdateTime: "2026-07-01T20:58:37Z" message: ReplicaSet "router-gateway-1-openshift-default-54c47cdfc7" has successfully progressed. reason: NewReplicaSetAvailable status: "True" type: Progressing - lastTransitionTime: "2026-07-01T20:59:10Z" lastUpdateTime: "2026-07-01T20:59:10Z" message: Deployment has minimum availability. reason: MinimumReplicasAvailable status: "True" type: Available observedGeneration: 1 readyReplicas: 1 replicas: 1 updatedReplicas: 1 - apiVersion: apps/v1 kind: Deployment metadata: annotations: deployment.kubernetes.io/revision: "1" creationTimestamp: "2026-07-01T21:26:06Z" generation: 1 labels: gateway.istio.io/managed: openshift.io-gateway-controller-v1 gateway.networking.k8s.io/gateway-name: router-gateway-2 managedFields: - apiVersion: apps/v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:annotations: {} f:labels: f:gateway.istio.io/managed: {} f:gateway.networking.k8s.io/gateway-name: {} f:ownerReferences: k:{"uid":"b76314d9-abb1-4fa6-8f3e-713a423b2ad6"}: {} f:spec: f:selector: {} f:template: f:metadata: f:annotations: f:istio.io/rev: {} f:prometheus.io/path: {} f:prometheus.io/port: {} f:prometheus.io/scrape: {} f:labels: f:gateway.istio.io/managed: {} f:gateway.networking.k8s.io/gateway-name: {} f:service.istio.io/canonical-name: {} f:service.istio.io/canonical-revision: {} f:sidecar.istio.io/inject: {} f:spec: f:containers: k:{"name":"istio-proxy"}: .: {} f:args: {} f:env: k:{"name":"CA_ADDR"}: .: {} f:name: {} f:value: {} k:{"name":"GOMAXPROCS"}: .: {} f:name: {} f:valueFrom: f:resourceFieldRef: {} k:{"name":"GOMEMLIMIT"}: .: {} f:name: {} f:valueFrom: f:resourceFieldRef: {} k:{"name":"HOST_IP"}: .: {} f:name: {} f:valueFrom: f:fieldRef: {} k:{"name":"INSTANCE_IP"}: .: {} f:name: {} f:valueFrom: f:fieldRef: {} k:{"name":"ISTIO_CPU_LIMIT"}: .: {} f:name: {} f:valueFrom: f:resourceFieldRef: {} k:{"name":"ISTIO_META_APP_CONTAINERS"}: .: {} f:name: {} f:value: {} k:{"name":"ISTIO_META_CLUSTER_ID"}: .: {} f:name: {} f:value: {} k:{"name":"ISTIO_META_INTERCEPTION_MODE"}: .: {} f:name: {} f:value: {} k:{"name":"ISTIO_META_MESH_ID"}: .: {} f:name: {} f:value: {} k:{"name":"ISTIO_META_NODE_NAME"}: .: {} f:name: {} f:valueFrom: f:fieldRef: {} k:{"name":"ISTIO_META_OWNER"}: .: {} f:name: {} f:value: {} k:{"name":"ISTIO_META_POD_PORTS"}: .: {} f:name: {} f:value: {} k:{"name":"ISTIO_META_WORKLOAD_NAME"}: .: {} f:name: {} f:value: {} k:{"name":"PILOT_CERT_PROVIDER"}: .: {} f:name: {} f:value: {} k:{"name":"POD_NAME"}: .: {} f:name: {} f:valueFrom: f:fieldRef: {} k:{"name":"POD_NAMESPACE"}: .: {} f:name: {} f:valueFrom: f:fieldRef: {} k:{"name":"PROXY_CONFIG"}: .: {} f:name: {} f:value: {} k:{"name":"SERVICE_ACCOUNT"}: .: {} f:name: {} f:valueFrom: f:fieldRef: {} k:{"name":"TRUST_DOMAIN"}: .: {} f:name: {} f:value: {} f:image: {} f:name: {} f:ports: k:{"containerPort":15020,"protocol":"TCP"}: .: {} f:containerPort: {} f:name: {} f:protocol: {} k:{"containerPort":15021,"protocol":"TCP"}: .: {} f:containerPort: {} f:name: {} f:protocol: {} k:{"containerPort":15090,"protocol":"TCP"}: .: {} f:containerPort: {} f:name: {} f:protocol: {} f:readinessProbe: f:failureThreshold: {} f:httpGet: f:path: {} f:port: {} f:scheme: {} f:initialDelaySeconds: {} f:periodSeconds: {} f:successThreshold: {} f:timeoutSeconds: {} f:resources: f:limits: f:cpu: {} f:memory: {} f:requests: f:cpu: {} f:memory: {} f:securityContext: f:allowPrivilegeEscalation: {} f:capabilities: f:drop: {} f:privileged: {} f:readOnlyRootFilesystem: {} f:runAsGroup: {} f:runAsNonRoot: {} f:runAsUser: {} f:startupProbe: f:failureThreshold: {} f:httpGet: f:path: {} f:port: {} f:scheme: {} f:initialDelaySeconds: {} f:periodSeconds: {} f:successThreshold: {} f:timeoutSeconds: {} f:volumeMounts: k:{"mountPath":"/etc/istio/pod"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/etc/istio/proxy"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/var/lib/istio/data"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/var/run/secrets/credential-uds"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/var/run/secrets/istio"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/var/run/secrets/tokens"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/var/run/secrets/workload-spiffe-credentials"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/var/run/secrets/workload-spiffe-uds"}: .: {} f:mountPath: {} f:name: {} f:securityContext: f:sysctls: {} f:serviceAccountName: {} f:volumes: k:{"name":"credential-socket"}: .: {} f:emptyDir: {} f:name: {} k:{"name":"istio-data"}: .: {} f:emptyDir: {} f:name: {} k:{"name":"istio-envoy"}: .: {} f:emptyDir: f:medium: {} f:name: {} k:{"name":"istio-podinfo"}: .: {} f:downwardAPI: f:items: {} f:name: {} k:{"name":"istio-token"}: .: {} f:name: {} f:projected: f:sources: {} k:{"name":"istiod-ca-cert"}: .: {} f:configMap: f:name: {} f:name: {} k:{"name":"workload-certs"}: .: {} f:emptyDir: {} f:name: {} k:{"name":"workload-socket"}: .: {} f:emptyDir: {} f:name: {} manager: openshift.io/gateway-controller/v1 operation: Apply time: "2026-07-01T21:26:06Z" - apiVersion: apps/v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:annotations: .: {} f:deployment.kubernetes.io/revision: {} f:status: f:availableReplicas: {} f:conditions: .: {} k:{"type":"Available"}: .: {} f:lastTransitionTime: {} f:lastUpdateTime: {} f:message: {} f:reason: {} f:status: {} f:type: {} k:{"type":"Progressing"}: .: {} f:lastTransitionTime: {} f:lastUpdateTime: {} f:message: {} f:reason: {} f:status: {} f:type: {} f:observedGeneration: {} f:readyReplicas: {} f:replicas: {} f:updatedReplicas: {} manager: kube-controller-manager operation: Update subresource: status time: "2026-07-01T21:26:25Z" name: router-gateway-2-openshift-default namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: gateway.networking.k8s.io/v1beta1 kind: Gateway name: router-gateway-2 uid: b76314d9-abb1-4fa6-8f3e-713a423b2ad6 resourceVersion: "47264" uid: 23b40aa1-a37e-4653-808e-2a4860b8b9ab spec: progressDeadlineSeconds: 600 replicas: 1 revisionHistoryLimit: 10 selector: matchLabels: gateway.networking.k8s.io/gateway-name: router-gateway-2 strategy: rollingUpdate: maxSurge: 25% maxUnavailable: 25% type: RollingUpdate template: metadata: annotations: istio.io/rev: openshift-gateway prometheus.io/path: /stats/prometheus prometheus.io/port: "15020" prometheus.io/scrape: "true" labels: gateway.istio.io/managed: istio.io-gateway-controller gateway.networking.k8s.io/gateway-name: router-gateway-2 service.istio.io/canonical-name: router-gateway-2-openshift-default service.istio.io/canonical-revision: latest sidecar.istio.io/inject: "false" spec: containers: - args: - proxy - router - --domain - $(POD_NAMESPACE).svc.cluster.local - --proxyLogLevel - warning - --proxyComponentLogLevel - misc:error - --log_output_level - default:info env: - name: PILOT_CERT_PROVIDER value: istiod - name: CA_ADDR value: istiod-openshift-gateway.openshift-ingress.svc:15012 - name: POD_NAME valueFrom: fieldRef: apiVersion: v1 fieldPath: metadata.name - name: POD_NAMESPACE valueFrom: fieldRef: apiVersion: v1 fieldPath: metadata.namespace - name: INSTANCE_IP valueFrom: fieldRef: apiVersion: v1 fieldPath: status.podIP - name: SERVICE_ACCOUNT valueFrom: fieldRef: apiVersion: v1 fieldPath: spec.serviceAccountName - name: HOST_IP valueFrom: fieldRef: apiVersion: v1 fieldPath: status.hostIP - name: ISTIO_CPU_LIMIT valueFrom: resourceFieldRef: divisor: "0" resource: limits.cpu - name: PROXY_CONFIG value: | {"discoveryAddress":"istiod-openshift-gateway.openshift-ingress.svc:15012","proxyHeaders":{"server":{"disabled":true},"envoyDebugHeaders":{"disabled":true},"metadataExchangeHeaders":{"mode":"IN_MESH"}}} - name: ISTIO_META_POD_PORTS value: '[]' - name: ISTIO_META_APP_CONTAINERS - name: GOMEMLIMIT valueFrom: resourceFieldRef: divisor: "0" resource: limits.memory - name: GOMAXPROCS valueFrom: resourceFieldRef: divisor: "0" resource: limits.cpu - name: ISTIO_META_CLUSTER_ID value: Kubernetes - name: ISTIO_META_NODE_NAME valueFrom: fieldRef: apiVersion: v1 fieldPath: spec.nodeName - name: ISTIO_META_INTERCEPTION_MODE value: REDIRECT - name: ISTIO_META_WORKLOAD_NAME value: router-gateway-2-openshift-default - name: ISTIO_META_OWNER value: kubernetes://apis/apps/v1/namespaces/kserve-ci-e2e-test/deployments/router-gateway-2-openshift-default - name: ISTIO_META_MESH_ID value: cluster.local - name: TRUST_DOMAIN value: cluster.local image: registry.redhat.io/openshift-service-mesh/istio-proxyv2-rhel9@sha256:7d15cebf9b62f3f235c0eab5158ac8ff2fda86a1d193490dc94c301402c99da8 imagePullPolicy: IfNotPresent name: istio-proxy ports: - containerPort: 15020 name: metrics protocol: TCP - containerPort: 15021 name: status-port protocol: TCP - containerPort: 15090 name: http-envoy-prom protocol: TCP readinessProbe: failureThreshold: 4 httpGet: path: /healthz/ready port: 15021 scheme: HTTP periodSeconds: 15 successThreshold: 1 timeoutSeconds: 1 resources: limits: cpu: "2" memory: 2Gi requests: cpu: 100m memory: 256Mi securityContext: allowPrivilegeEscalation: false capabilities: drop: - ALL privileged: false readOnlyRootFilesystem: true runAsGroup: 1000699999 runAsNonRoot: true runAsUser: 1000699999 startupProbe: failureThreshold: 30 httpGet: path: /healthz/ready port: 15021 scheme: HTTP initialDelaySeconds: 1 periodSeconds: 1 successThreshold: 1 timeoutSeconds: 1 terminationMessagePath: /dev/termination-log terminationMessagePolicy: File volumeMounts: - mountPath: /var/run/secrets/workload-spiffe-uds name: workload-socket - mountPath: /var/run/secrets/credential-uds name: credential-socket - mountPath: /var/run/secrets/workload-spiffe-credentials name: workload-certs - mountPath: /var/run/secrets/istio name: istiod-ca-cert - mountPath: /var/lib/istio/data name: istio-data - mountPath: /etc/istio/proxy name: istio-envoy - mountPath: /var/run/secrets/tokens name: istio-token - mountPath: /etc/istio/pod name: istio-podinfo dnsPolicy: ClusterFirst restartPolicy: Always schedulerName: default-scheduler securityContext: sysctls: - name: net.ipv4.ip_unprivileged_port_start value: "0" serviceAccount: router-gateway-2-openshift-default serviceAccountName: router-gateway-2-openshift-default terminationGracePeriodSeconds: 30 volumes: - emptyDir: {} name: workload-socket - emptyDir: {} name: credential-socket - emptyDir: {} name: workload-certs - emptyDir: medium: Memory name: istio-envoy - emptyDir: {} name: istio-data - downwardAPI: defaultMode: 420 items: - fieldRef: apiVersion: v1 fieldPath: metadata.labels path: labels - fieldRef: apiVersion: v1 fieldPath: metadata.annotations path: annotations name: istio-podinfo - name: istio-token projected: defaultMode: 420 sources: - serviceAccountToken: audience: istio-ca expirationSeconds: 43200 path: istio-token - configMap: defaultMode: 420 name: openshift-gw-ca-root-cert name: istiod-ca-cert status: availableReplicas: 1 conditions: - lastTransitionTime: "2026-07-01T21:26:06Z" lastUpdateTime: "2026-07-01T21:26:09Z" message: ReplicaSet "router-gateway-2-openshift-default-684dc9b4b9" has successfully progressed. reason: NewReplicaSetAvailable status: "True" type: Progressing - lastTransitionTime: "2026-07-01T21:26:25Z" lastUpdateTime: "2026-07-01T21:26:25Z" message: Deployment has minimum availability. reason: MinimumReplicasAvailable status: "True" type: Available observedGeneration: 1 readyReplicas: 1 replicas: 1 updatedReplicas: 1 - apiVersion: apps/v1 kind: Deployment metadata: annotations: deployment.kubernetes.io/revision: "1" creationTimestamp: "2026-07-01T22:03:26Z" generation: 1 labels: app.kubernetes.io/component: llminferenceservice-workload app.kubernetes.io/name: scheduler-v06-pd-migration-test app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload llm-d.ai/role: decode managedFields: - apiVersion: apps/v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:labels: .: {} f:app.kubernetes.io/component: {} f:app.kubernetes.io/name: {} f:app.kubernetes.io/part-of: {} f:kserve.io/component: {} f:llm-d.ai/role: {} f:ownerReferences: .: {} k:{"uid":"479dcd87-3e82-4860-9050-eeae1af22ec3"}: {} f:spec: f:progressDeadlineSeconds: {} f:replicas: {} f:revisionHistoryLimit: {} f:selector: {} f:strategy: f:rollingUpdate: .: {} f:maxSurge: {} f:maxUnavailable: {} f:type: {} f:template: f:metadata: f:labels: .: {} f:app.kubernetes.io/component: {} f:app.kubernetes.io/name: {} f:app.kubernetes.io/part-of: {} f:kserve.io/component: {} f:llm-d.ai/role: {} f:spec: f:containers: k:{"name":"main"}: .: {} f:args: {} f:command: {} f:env: .: {} k:{"name":"HF_HUB_CACHE"}: .: {} f:name: {} f:value: {} k:{"name":"HOME"}: .: {} f:name: {} f:value: {} k:{"name":"VLLM_LOGGING_LEVEL"}: .: {} f:name: {} f:value: {} f:image: {} f:imagePullPolicy: {} f:lifecycle: .: {} f:preStop: .: {} f:exec: .: {} f:command: {} f:livenessProbe: .: {} f:failureThreshold: {} f:httpGet: .: {} f:path: {} f:port: {} f:scheme: {} f:periodSeconds: {} f:successThreshold: {} f:timeoutSeconds: {} f:name: {} f:ports: .: {} k:{"containerPort":8001,"protocol":"TCP"}: .: {} f:containerPort: {} f:protocol: {} f:readinessProbe: .: {} f:failureThreshold: {} f:httpGet: .: {} f:path: {} f:port: {} f:scheme: {} f:periodSeconds: {} f:successThreshold: {} f:timeoutSeconds: {} f:resources: .: {} f:limits: .: {} f:cpu: {} f:memory: {} f:requests: .: {} f:cpu: {} f:memory: {} f:securityContext: .: {} f:allowPrivilegeEscalation: {} f:capabilities: .: {} f:drop: {} f:readOnlyRootFilesystem: {} f:runAsNonRoot: {} f:seccompProfile: .: {} f:type: {} f:startupProbe: .: {} f:failureThreshold: {} f:httpGet: .: {} f:path: {} f:port: {} f:scheme: {} f:periodSeconds: {} f:successThreshold: {} f:timeoutSeconds: {} f:terminationMessagePath: {} f:terminationMessagePolicy: {} f:volumeMounts: .: {} k:{"mountPath":"/dev/shm"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/home"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/models"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/tmp"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/var/run/kserve/tls"}: .: {} f:mountPath: {} f:name: {} f:readOnly: {} f:dnsPolicy: {} f:initContainers: .: {} k:{"name":"llm-d-routing-sidecar"}: .: {} f:command: {} f:env: .: {} k:{"name":"INFERENCE_POOL_NAME"}: .: {} f:name: {} f:value: {} k:{"name":"INFERENCE_POOL_NAMESPACE"}: .: {} f:name: {} f:valueFrom: .: {} f:fieldRef: {} k:{"name":"SSL_CERT_DIR"}: .: {} f:name: {} f:value: {} f:image: {} f:imagePullPolicy: {} f:livenessProbe: .: {} f:failureThreshold: {} f:httpGet: .: {} f:path: {} f:port: {} f:scheme: {} f:initialDelaySeconds: {} f:periodSeconds: {} f:successThreshold: {} f:timeoutSeconds: {} f:name: {} f:ports: .: {} k:{"containerPort":8000,"protocol":"TCP"}: .: {} f:containerPort: {} f:protocol: {} f:readinessProbe: .: {} f:failureThreshold: {} f:httpGet: .: {} f:path: {} f:port: {} f:scheme: {} f:initialDelaySeconds: {} f:periodSeconds: {} f:successThreshold: {} f:timeoutSeconds: {} f:resources: {} f:restartPolicy: {} f:securityContext: .: {} f:allowPrivilegeEscalation: {} f:capabilities: .: {} f:drop: {} f:readOnlyRootFilesystem: {} f:runAsNonRoot: {} f:terminationMessagePath: {} f:terminationMessagePolicy: {} f:volumeMounts: .: {} k:{"mountPath":"/var/run/kserve/tls"}: .: {} f:mountPath: {} f:name: {} f:readOnly: {} f:restartPolicy: {} f:schedulerName: {} f:securityContext: {} f:serviceAccount: {} f:serviceAccountName: {} f:terminationGracePeriodSeconds: {} f:volumes: .: {} k:{"name":"dshm"}: .: {} f:emptyDir: .: {} f:medium: {} f:sizeLimit: {} f:name: {} k:{"name":"home"}: .: {} f:emptyDir: {} f:name: {} k:{"name":"model-cache"}: .: {} f:emptyDir: {} f:name: {} k:{"name":"tls-certs"}: .: {} f:name: {} f:secret: .: {} f:defaultMode: {} f:secretName: {} k:{"name":"tmp-dir"}: .: {} f:emptyDir: {} f:name: {} manager: manager operation: Update time: "2026-07-01T22:03:26Z" - apiVersion: apps/v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:annotations: .: {} f:deployment.kubernetes.io/revision: {} f:status: f:availableReplicas: {} f:conditions: .: {} k:{"type":"Available"}: .: {} f:lastTransitionTime: {} f:lastUpdateTime: {} f:message: {} f:reason: {} f:status: {} f:type: {} k:{"type":"Progressing"}: .: {} f:lastTransitionTime: {} f:lastUpdateTime: {} f:message: {} f:reason: {} f:status: {} f:type: {} f:observedGeneration: {} f:readyReplicas: {} f:replicas: {} f:updatedReplicas: {} manager: kube-controller-manager operation: Update subresource: status time: "2026-07-01T22:03:38Z" name: scheduler-v06-pd-migration-test-kserve namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: scheduler-v06-pd-migration-test uid: 479dcd87-3e82-4860-9050-eeae1af22ec3 resourceVersion: "81849" uid: 55109cbc-e00f-4f3b-8082-f9b8319501fd spec: progressDeadlineSeconds: 600 replicas: 1 revisionHistoryLimit: 10 selector: matchLabels: app.kubernetes.io/component: llminferenceservice-workload app.kubernetes.io/name: scheduler-v06-pd-migration-test app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload llm-d.ai/role: decode strategy: rollingUpdate: maxSurge: 25% maxUnavailable: 25% type: RollingUpdate template: metadata: labels: app.kubernetes.io/component: llminferenceservice-workload app.kubernetes.io/name: scheduler-v06-pd-migration-test app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload llm-d.ai/role: decode spec: containers: - args: - --port - "8001" - --model - facebook/opt-125m - --mode - random - --ssl-certfile - /var/run/kserve/tls/tls.crt - --ssl-keyfile - /var/run/kserve/tls/tls.key command: - /app/llm-d-inference-sim env: - name: HOME value: /home - name: VLLM_LOGGING_LEVEL value: INFO - name: HF_HUB_CACHE value: /models image: ghcr.io/llm-d/llm-d-inference-sim:v0.8.2 imagePullPolicy: IfNotPresent lifecycle: preStop: exec: command: - /bin/sleep - "15" livenessProbe: failureThreshold: 10 httpGet: path: /health port: 8001 scheme: HTTPS periodSeconds: 10 successThreshold: 1 timeoutSeconds: 1 name: main ports: - containerPort: 8001 protocol: TCP readinessProbe: failureThreshold: 2 httpGet: path: /health port: 8001 scheme: HTTPS periodSeconds: 1 successThreshold: 1 timeoutSeconds: 1 resources: limits: cpu: "1" memory: 2Gi requests: cpu: 200m memory: 2Gi securityContext: allowPrivilegeEscalation: false capabilities: drop: - ALL readOnlyRootFilesystem: true runAsNonRoot: true seccompProfile: type: RuntimeDefault startupProbe: failureThreshold: 60 httpGet: path: /health port: 8001 scheme: HTTPS periodSeconds: 10 successThreshold: 1 timeoutSeconds: 1 terminationMessagePath: /dev/termination-log terminationMessagePolicy: FallbackToLogsOnError volumeMounts: - mountPath: /home name: home - mountPath: /tmp name: tmp-dir - mountPath: /dev/shm name: dshm - mountPath: /models name: model-cache - mountPath: /var/run/kserve/tls name: tls-certs readOnly: true dnsPolicy: ClusterFirst initContainers: - command: - /app/pd-sidecar - --port=8000 - --vllm-port=8001 - --kv-connector=nixlv2 - --enable-ssrf-protection=true - --pool-group=inference.networking.x-k8s.io - --inference-pool=kserve-ci-e2e-test/scheduler-v06-pd-migration-test-inference-pool - --secure-proxy=true - --cert-path=/var/run/kserve/tls - --decoder-use-tls=true - --prefiller-use-tls=true env: - name: INFERENCE_POOL_NAMESPACE valueFrom: fieldRef: apiVersion: v1 fieldPath: metadata.namespace - name: SSL_CERT_DIR value: /var/run/kserve/tls:/var/run/secrets/kubernetes.io/serviceaccount:/etc/pki/tls/certs - name: INFERENCE_POOL_NAME value: scheduler-v06-pd-migration-test-inference-pool image: ghcr.io/llm-d/llm-d-router-disagg-sidecar:v0.9.0-rc.2 imagePullPolicy: IfNotPresent livenessProbe: failureThreshold: 3 httpGet: path: /health port: 8000 scheme: HTTPS initialDelaySeconds: 10 periodSeconds: 10 successThreshold: 1 timeoutSeconds: 10 name: llm-d-routing-sidecar ports: - containerPort: 8000 protocol: TCP readinessProbe: failureThreshold: 10 httpGet: path: /health port: 8000 scheme: HTTPS initialDelaySeconds: 10 periodSeconds: 10 successThreshold: 1 timeoutSeconds: 5 resources: {} restartPolicy: Always securityContext: allowPrivilegeEscalation: false capabilities: drop: - ALL readOnlyRootFilesystem: true runAsNonRoot: true terminationMessagePath: /dev/termination-log terminationMessagePolicy: FallbackToLogsOnError volumeMounts: - mountPath: /var/run/kserve/tls name: tls-certs readOnly: true restartPolicy: Always schedulerName: default-scheduler securityContext: {} serviceAccount: scheduler-v06-pd-migration-test-kserve serviceAccountName: scheduler-v06-pd-migration-test-kserve terminationGracePeriodSeconds: 60 volumes: - emptyDir: {} name: home - emptyDir: {} name: tmp-dir - emptyDir: medium: Memory sizeLimit: 1Gi name: dshm - emptyDir: {} name: model-cache - name: tls-certs secret: defaultMode: 420 secretName: scheduler-v06-pd-migration-test-kserve-self-signed-certs status: availableReplicas: 1 conditions: - lastTransitionTime: "2026-07-01T22:03:38Z" lastUpdateTime: "2026-07-01T22:03:38Z" message: Deployment has minimum availability. reason: MinimumReplicasAvailable status: "True" type: Available - lastTransitionTime: "2026-07-01T22:03:26Z" lastUpdateTime: "2026-07-01T22:03:38Z" message: ReplicaSet "scheduler-v06-pd-migration-test-kserve-5c87756974" has successfully progressed. reason: NewReplicaSetAvailable status: "True" type: Progressing observedGeneration: 1 readyReplicas: 1 replicas: 1 updatedReplicas: 1 - apiVersion: apps/v1 kind: Deployment metadata: annotations: deployment.kubernetes.io/revision: "1" creationTimestamp: "2026-07-01T22:03:26Z" generation: 1 labels: app.kubernetes.io/component: llminferenceservice-workload-prefill app.kubernetes.io/name: scheduler-v06-pd-migration-test app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload llm-d.ai/role: prefill managedFields: - apiVersion: apps/v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:labels: .: {} f:app.kubernetes.io/component: {} f:app.kubernetes.io/name: {} f:app.kubernetes.io/part-of: {} f:kserve.io/component: {} f:llm-d.ai/role: {} f:ownerReferences: .: {} k:{"uid":"479dcd87-3e82-4860-9050-eeae1af22ec3"}: {} f:spec: f:progressDeadlineSeconds: {} f:replicas: {} f:revisionHistoryLimit: {} f:selector: {} f:strategy: f:rollingUpdate: .: {} f:maxSurge: {} f:maxUnavailable: {} f:type: {} f:template: f:metadata: f:labels: .: {} f:app.kubernetes.io/component: {} f:app.kubernetes.io/name: {} f:app.kubernetes.io/part-of: {} f:kserve.io/component: {} f:llm-d.ai/role: {} f:spec: f:containers: k:{"name":"main"}: .: {} f:args: {} f:command: {} f:env: .: {} k:{"name":"HF_HUB_CACHE"}: .: {} f:name: {} f:value: {} k:{"name":"HOME"}: .: {} f:name: {} f:value: {} k:{"name":"VLLM_LOGGING_LEVEL"}: .: {} f:name: {} f:value: {} f:image: {} f:imagePullPolicy: {} f:lifecycle: .: {} f:preStop: .: {} f:exec: .: {} f:command: {} f:livenessProbe: .: {} f:failureThreshold: {} f:httpGet: .: {} f:path: {} f:port: {} f:scheme: {} f:periodSeconds: {} f:successThreshold: {} f:timeoutSeconds: {} f:name: {} f:ports: .: {} k:{"containerPort":8000,"protocol":"TCP"}: .: {} f:containerPort: {} f:protocol: {} f:readinessProbe: .: {} f:failureThreshold: {} f:httpGet: .: {} f:path: {} f:port: {} f:scheme: {} f:periodSeconds: {} f:successThreshold: {} f:timeoutSeconds: {} f:resources: .: {} f:limits: .: {} f:cpu: {} f:memory: {} f:requests: .: {} f:cpu: {} f:memory: {} f:securityContext: .: {} f:allowPrivilegeEscalation: {} f:capabilities: .: {} f:drop: {} f:readOnlyRootFilesystem: {} f:runAsNonRoot: {} f:seccompProfile: .: {} f:type: {} f:startupProbe: .: {} f:failureThreshold: {} f:httpGet: .: {} f:path: {} f:port: {} f:scheme: {} f:periodSeconds: {} f:successThreshold: {} f:timeoutSeconds: {} f:terminationMessagePath: {} f:terminationMessagePolicy: {} f:volumeMounts: .: {} k:{"mountPath":"/dev/shm"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/home"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/models"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/tmp"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/var/run/kserve/tls"}: .: {} f:mountPath: {} f:name: {} f:readOnly: {} f:dnsPolicy: {} f:restartPolicy: {} f:schedulerName: {} f:securityContext: {} f:terminationGracePeriodSeconds: {} f:volumes: .: {} k:{"name":"dshm"}: .: {} f:emptyDir: .: {} f:medium: {} f:sizeLimit: {} f:name: {} k:{"name":"home"}: .: {} f:emptyDir: {} f:name: {} k:{"name":"model-cache"}: .: {} f:emptyDir: {} f:name: {} k:{"name":"tls-certs"}: .: {} f:name: {} f:secret: .: {} f:defaultMode: {} f:secretName: {} k:{"name":"tmp-dir"}: .: {} f:emptyDir: {} f:name: {} manager: manager operation: Update time: "2026-07-01T22:03:26Z" - apiVersion: apps/v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:annotations: .: {} f:deployment.kubernetes.io/revision: {} f:status: f:availableReplicas: {} f:conditions: .: {} k:{"type":"Available"}: .: {} f:lastTransitionTime: {} f:lastUpdateTime: {} f:message: {} f:reason: {} f:status: {} f:type: {} k:{"type":"Progressing"}: .: {} f:lastTransitionTime: {} f:lastUpdateTime: {} f:message: {} f:reason: {} f:status: {} f:type: {} f:observedGeneration: {} f:readyReplicas: {} f:replicas: {} f:updatedReplicas: {} manager: kube-controller-manager operation: Update subresource: status time: "2026-07-01T22:03:36Z" name: scheduler-v06-pd-migration-test-kserve-prefill namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: scheduler-v06-pd-migration-test uid: 479dcd87-3e82-4860-9050-eeae1af22ec3 resourceVersion: "81828" uid: edaa0147-87a5-4f5c-b294-f1fc2b34a7ef spec: progressDeadlineSeconds: 600 replicas: 1 revisionHistoryLimit: 10 selector: matchLabels: app.kubernetes.io/component: llminferenceservice-workload-prefill app.kubernetes.io/name: scheduler-v06-pd-migration-test app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload llm-d.ai/role: prefill strategy: rollingUpdate: maxSurge: 25% maxUnavailable: 25% type: RollingUpdate template: metadata: labels: app.kubernetes.io/component: llminferenceservice-workload-prefill app.kubernetes.io/name: scheduler-v06-pd-migration-test app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload llm-d.ai/role: prefill spec: containers: - args: - --port - "8000" - --model - facebook/opt-125m - --mode - random - --ssl-certfile - /var/run/kserve/tls/tls.crt - --ssl-keyfile - /var/run/kserve/tls/tls.key command: - /app/llm-d-inference-sim env: - name: HOME value: /home - name: VLLM_LOGGING_LEVEL value: INFO - name: HF_HUB_CACHE value: /models image: ghcr.io/llm-d/llm-d-inference-sim:v0.8.2 imagePullPolicy: IfNotPresent lifecycle: preStop: exec: command: - /bin/sleep - "15" livenessProbe: failureThreshold: 10 httpGet: path: /health port: 8000 scheme: HTTPS periodSeconds: 10 successThreshold: 1 timeoutSeconds: 1 name: main ports: - containerPort: 8000 protocol: TCP readinessProbe: failureThreshold: 2 httpGet: path: /health port: 8000 scheme: HTTPS periodSeconds: 1 successThreshold: 1 timeoutSeconds: 1 resources: limits: cpu: "1" memory: 2Gi requests: cpu: 200m memory: 2Gi securityContext: allowPrivilegeEscalation: false capabilities: drop: - ALL readOnlyRootFilesystem: true runAsNonRoot: true seccompProfile: type: RuntimeDefault startupProbe: failureThreshold: 60 httpGet: path: /health port: 8000 scheme: HTTPS periodSeconds: 10 successThreshold: 1 timeoutSeconds: 1 terminationMessagePath: /dev/termination-log terminationMessagePolicy: File volumeMounts: - mountPath: /home name: home - mountPath: /tmp name: tmp-dir - mountPath: /dev/shm name: dshm - mountPath: /models name: model-cache - mountPath: /var/run/kserve/tls name: tls-certs readOnly: true dnsPolicy: ClusterFirst restartPolicy: Always schedulerName: default-scheduler securityContext: {} terminationGracePeriodSeconds: 60 volumes: - emptyDir: {} name: home - emptyDir: {} name: tmp-dir - emptyDir: medium: Memory sizeLimit: 1Gi name: dshm - emptyDir: {} name: model-cache - name: tls-certs secret: defaultMode: 420 secretName: scheduler-v06-pd-migration-test-kserve-self-signed-certs status: availableReplicas: 1 conditions: - lastTransitionTime: "2026-07-01T22:03:36Z" lastUpdateTime: "2026-07-01T22:03:36Z" message: Deployment has minimum availability. reason: MinimumReplicasAvailable status: "True" type: Available - lastTransitionTime: "2026-07-01T22:03:26Z" lastUpdateTime: "2026-07-01T22:03:36Z" message: ReplicaSet "scheduler-v06-pd-migration-test-kserve-prefill-78b7f4c847" has successfully progressed. reason: NewReplicaSetAvailable status: "True" type: Progressing observedGeneration: 1 readyReplicas: 1 replicas: 1 updatedReplicas: 1 - apiVersion: apps/v1 kind: Deployment metadata: annotations: deployment.kubernetes.io/revision: "1" creationTimestamp: "2026-07-01T22:03:26Z" generation: 1 labels: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: scheduler-v06-pd-migration-test app.kubernetes.io/part-of: llminferenceservice managedFields: - apiVersion: apps/v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:labels: .: {} f:app.kubernetes.io/component: {} f:app.kubernetes.io/name: {} f:app.kubernetes.io/part-of: {} f:ownerReferences: .: {} k:{"uid":"479dcd87-3e82-4860-9050-eeae1af22ec3"}: {} f:spec: f:progressDeadlineSeconds: {} f:replicas: {} f:revisionHistoryLimit: {} f:selector: {} f:strategy: f:type: {} f:template: f:metadata: f:annotations: .: {} f:app.kubernetes.io/version: {} f:certificates.kserve.io/expiration-v2: {} f:labels: .: {} f:app.kubernetes.io/component: {} f:app.kubernetes.io/name: {} f:app.kubernetes.io/part-of: {} f:spec: f:containers: k:{"name":"main"}: .: {} f:args: {} f:command: {} f:env: .: {} k:{"name":"SSL_CERT_DIR"}: .: {} f:name: {} f:value: {} f:image: {} f:imagePullPolicy: {} f:lifecycle: .: {} f:preStop: .: {} f:exec: .: {} f:command: {} f:livenessProbe: .: {} f:failureThreshold: {} f:grpc: .: {} f:port: {} f:service: {} f:initialDelaySeconds: {} f:periodSeconds: {} f:successThreshold: {} f:timeoutSeconds: {} f:name: {} f:ports: .: {} k:{"containerPort":5557,"protocol":"TCP"}: .: {} f:containerPort: {} f:name: {} f:protocol: {} k:{"containerPort":9002,"protocol":"TCP"}: .: {} f:containerPort: {} f:name: {} f:protocol: {} k:{"containerPort":9003,"protocol":"TCP"}: .: {} f:containerPort: {} f:name: {} f:protocol: {} k:{"containerPort":9090,"protocol":"TCP"}: .: {} f:containerPort: {} f:name: {} f:protocol: {} f:readinessProbe: .: {} f:failureThreshold: {} f:grpc: .: {} f:port: {} f:service: {} f:initialDelaySeconds: {} f:periodSeconds: {} f:successThreshold: {} f:timeoutSeconds: {} f:resources: .: {} f:requests: .: {} f:cpu: {} f:memory: {} f:securityContext: .: {} f:allowPrivilegeEscalation: {} f:capabilities: .: {} f:drop: {} f:readOnlyRootFilesystem: {} f:runAsNonRoot: {} f:seccompProfile: .: {} f:type: {} f:terminationMessagePath: {} f:terminationMessagePolicy: {} f:volumeMounts: .: {} k:{"mountPath":"/tmp/tokenizer"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/var/run/kserve/tls"}: .: {} f:mountPath: {} f:name: {} f:readOnly: {} f:dnsPolicy: {} f:restartPolicy: {} f:schedulerName: {} f:securityContext: {} f:serviceAccount: {} f:serviceAccountName: {} f:terminationGracePeriodSeconds: {} f:volumes: .: {} k:{"name":"tls-certs"}: .: {} f:name: {} f:secret: .: {} f:defaultMode: {} f:secretName: {} k:{"name":"tokenizer-cache"}: .: {} f:emptyDir: {} f:name: {} k:{"name":"tokenizer-tmp"}: .: {} f:emptyDir: {} f:name: {} k:{"name":"tokenizer-uds"}: .: {} f:emptyDir: {} f:name: {} manager: manager operation: Update time: "2026-07-01T22:03:26Z" - apiVersion: apps/v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:annotations: .: {} f:deployment.kubernetes.io/revision: {} f:status: f:availableReplicas: {} f:conditions: .: {} k:{"type":"Available"}: .: {} f:lastTransitionTime: {} f:lastUpdateTime: {} f:message: {} f:reason: {} f:status: {} f:type: {} k:{"type":"Progressing"}: .: {} f:lastTransitionTime: {} f:lastUpdateTime: {} f:message: {} f:reason: {} f:status: {} f:type: {} f:observedGeneration: {} f:readyReplicas: {} f:replicas: {} f:updatedReplicas: {} manager: kube-controller-manager operation: Update subresource: status time: "2026-07-01T22:03:58Z" name: scheduler-v06-pd-migration-test-kserve-router-scheduler namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: scheduler-v06-pd-migration-test uid: 479dcd87-3e82-4860-9050-eeae1af22ec3 resourceVersion: "82089" uid: 7e82c7d7-5e3e-47cd-b049-57f9e0ea9ed7 spec: progressDeadlineSeconds: 600 replicas: 1 revisionHistoryLimit: 10 selector: matchLabels: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: scheduler-v06-pd-migration-test app.kubernetes.io/part-of: llminferenceservice strategy: type: Recreate template: metadata: annotations: app.kubernetes.io/version: 0.9.0 certificates.kserve.io/expiration-v2: "true" labels: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: scheduler-v06-pd-migration-test app.kubernetes.io/part-of: llminferenceservice spec: containers: - args: - --config-text - | apiVersion: inference.networking.x-k8s.io/v1alpha1 kind: EndpointPickerConfig plugins: - type: disagg-headers-handler - type: prefill-filter - type: decode-filter - type: always-disagg-pd-decider - parameters: deciders: prefill: always-disagg-pd-decider type: disagg-profile-handler - type: prefix-cache-scorer - type: queue-scorer - type: max-score-picker schedulingProfiles: - name: prefill plugins: - pluginRef: prefill-filter - pluginRef: queue-scorer weight: 2 - pluginRef: prefix-cache-scorer weight: 3 - pluginRef: max-score-picker - name: decode plugins: - pluginRef: decode-filter - pluginRef: queue-scorer weight: 2 - pluginRef: prefix-cache-scorer weight: 3 - pluginRef: max-score-picker command: - /app/epp - --pool-name - scheduler-v06-pd-migration-test-inference-pool - --pool-namespace - kserve-ci-e2e-test - --zap-encoder - json - --grpc-port - "9002" - --grpc-health-port - "9003" - --enable-cert-reload=true - --secure-serving=true - --model-server-metrics-scheme=https - --cert-path=/var/run/kserve/tls env: - name: SSL_CERT_DIR value: /var/run/kserve/tls:/var/run/secrets/kubernetes.io/serviceaccount:/etc/pki/tls/certs image: ghcr.io/llm-d/llm-d-router-endpoint-picker:v0.9.0-rc.2 imagePullPolicy: IfNotPresent lifecycle: preStop: exec: command: - /bin/sleep - "15" livenessProbe: failureThreshold: 3 grpc: port: 9003 service: liveness initialDelaySeconds: 5 periodSeconds: 10 successThreshold: 1 timeoutSeconds: 1 name: main ports: - containerPort: 9002 name: grpc protocol: TCP - containerPort: 9003 name: grpc-health protocol: TCP - containerPort: 9090 name: metrics protocol: TCP - containerPort: 5557 name: zmq protocol: TCP readinessProbe: failureThreshold: 3 grpc: port: 9003 service: readiness initialDelaySeconds: 30 periodSeconds: 10 successThreshold: 1 timeoutSeconds: 1 resources: requests: cpu: 256m memory: 500Mi securityContext: allowPrivilegeEscalation: false capabilities: drop: - ALL readOnlyRootFilesystem: true runAsNonRoot: true seccompProfile: type: RuntimeDefault terminationMessagePath: /dev/termination-log terminationMessagePolicy: FallbackToLogsOnError volumeMounts: - mountPath: /var/run/kserve/tls name: tls-certs readOnly: true - mountPath: /tmp/tokenizer name: tokenizer-uds dnsPolicy: ClusterFirst restartPolicy: Always schedulerName: default-scheduler securityContext: {} serviceAccount: scheduler-v06-pd-migration-test-epp-sa serviceAccountName: scheduler-v06-pd-migration-test-epp-sa terminationGracePeriodSeconds: 60 volumes: - name: tls-certs secret: defaultMode: 420 secretName: scheduler-v06-pd-migration-test-kserve-self-signed-certs - emptyDir: {} name: tokenizer-uds - emptyDir: {} name: tokenizer-tmp - emptyDir: {} name: tokenizer-cache status: availableReplicas: 1 conditions: - lastTransitionTime: "2026-07-01T22:03:58Z" lastUpdateTime: "2026-07-01T22:03:58Z" message: Deployment has minimum availability. reason: MinimumReplicasAvailable status: "True" type: Available - lastTransitionTime: "2026-07-01T22:03:26Z" lastUpdateTime: "2026-07-01T22:03:58Z" message: ReplicaSet "scheduler-v06-pd-migration-test-kserve-router-scheduler-59dc679cd" has successfully progressed. reason: NewReplicaSetAvailable status: "True" type: Progressing observedGeneration: 1 readyReplicas: 1 replicas: 1 updatedReplicas: 1 kind: DeploymentList metadata: resourceVersion: "100747"