--- apiVersion: v1 kind: Pod metadata: annotations: k8s.ovn.org/pod-networks: '{"default":{"ip_addresses":["10.134.0.69/23"],"mac_address":"0a:58:0a:86:00:45","gateway_ips":["10.134.0.1"],"routes":[{"dest":"10.132.0.0/14","nextHop":"10.134.0.1"},{"dest":"172.31.0.0/16","nextHop":"10.134.0.1"},{"dest":"169.254.0.5/32","nextHop":"10.134.0.1"},{"dest":"100.64.0.0/16","nextHop":"10.134.0.1"}],"ip_address":"10.134.0.69/23","gateway_ip":"10.134.0.1","role":"primary"}}' k8s.v1.cni.cncf.io/network-status: |- [{ "name": "ovn-kubernetes", "interface": "eth0", "ips": [ "10.134.0.69" ], "mac": "0a:58:0a:86:00:45", "default": true, "dns": {} }] openshift.io/scc: restricted-v2 seccomp.security.alpha.kubernetes.io/pod: runtime/default security.openshift.io/validated-scc-subject-type: user creationTimestamp: "2026-07-01T22:03:26Z" generateName: scheduler-v06-pd-migration-test-kserve-5c87756974- 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 pod-template-hash: 5c87756974 managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:annotations: f:k8s.ovn.org/pod-networks: {} manager: ip-10-0-132-117 operation: Update subresource: status time: "2026-07-01T22:03:26Z" - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:generateName: {} 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:pod-template-hash: {} f:ownerReferences: .: {} k:{"uid":"fc9762ae-c2a9-4761-892f-6e9d9be95307"}: {} 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:enableServiceLinks: {} 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: kube-controller-manager operation: Update time: "2026-07-01T22:03:26Z" - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:annotations: f:k8s.v1.cni.cncf.io/network-status: {} manager: multus-daemon operation: Update subresource: status time: "2026-07-01T22:03:26Z" - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:status: f:conditions: k:{"type":"ContainersReady"}: .: {} f:lastProbeTime: {} f:lastTransitionTime: {} f:observedGeneration: {} f:status: {} f:type: {} k:{"type":"Initialized"}: .: {} f:lastProbeTime: {} f:lastTransitionTime: {} f:observedGeneration: {} f:status: {} f:type: {} k:{"type":"PodReadyToStartContainers"}: .: {} f:lastProbeTime: {} f:lastTransitionTime: {} f:observedGeneration: {} f:status: {} f:type: {} k:{"type":"PodScheduled"}: f:observedGeneration: {} k:{"type":"Ready"}: .: {} f:lastProbeTime: {} f:lastTransitionTime: {} f:observedGeneration: {} f:status: {} f:type: {} f:containerStatuses: {} f:hostIP: {} f:hostIPs: {} f:initContainerStatuses: {} f:observedGeneration: {} f:phase: {} f:podIP: {} f:podIPs: .: {} k:{"ip":"10.134.0.69"}: .: {} f:ip: {} f:startTime: {} manager: kubelet operation: Update subresource: status time: "2026-07-01T22:03:38Z" name: scheduler-v06-pd-migration-test-kserve-5c87756974-j2gzz namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: apps/v1 blockOwnerDeletion: true controller: true kind: ReplicaSet name: scheduler-v06-pd-migration-test-kserve-5c87756974 uid: fc9762ae-c2a9-4761-892f-6e9d9be95307 resourceVersion: "81843" uid: 70d7b504-f4b5-4838-8df9-c3629355aa72 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 runAsUser: 1000690000 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 - mountPath: /var/run/secrets/kubernetes.io/serviceaccount name: kube-api-access-czsgj readOnly: true dnsPolicy: ClusterFirst enableServiceLinks: true imagePullSecrets: - name: default-dockercfg-76tz7 - name: scheduler-v06-pd-migration-test-kserve-dockercfg-srv9x 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 runAsUser: 1000690000 terminationMessagePath: /dev/termination-log terminationMessagePolicy: FallbackToLogsOnError volumeMounts: - mountPath: /var/run/kserve/tls name: tls-certs readOnly: true - mountPath: /var/run/secrets/kubernetes.io/serviceaccount name: kube-api-access-czsgj readOnly: true nodeName: ip-10-0-132-117.ec2.internal preemptionPolicy: PreemptLowerPriority priority: 0 restartPolicy: Always schedulerName: default-scheduler securityContext: fsGroup: 1000690000 seLinuxOptions: level: s0:c26,c20 seccompProfile: type: RuntimeDefault serviceAccount: scheduler-v06-pd-migration-test-kserve serviceAccountName: scheduler-v06-pd-migration-test-kserve terminationGracePeriodSeconds: 60 tolerations: - effect: NoExecute key: node.kubernetes.io/not-ready operator: Exists tolerationSeconds: 300 - effect: NoExecute key: node.kubernetes.io/unreachable operator: Exists tolerationSeconds: 300 - effect: NoSchedule key: node.kubernetes.io/memory-pressure operator: Exists 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 - name: kube-api-access-czsgj projected: defaultMode: 420 sources: - serviceAccountToken: expirationSeconds: 3607 path: token - configMap: items: - key: ca.crt path: ca.crt name: kube-root-ca.crt - downwardAPI: items: - fieldRef: apiVersion: v1 fieldPath: metadata.namespace path: namespace - configMap: items: - key: service-ca.crt path: service-ca.crt name: openshift-service-ca.crt status: conditions: - lastProbeTime: null lastTransitionTime: "2026-07-01T22:03:27Z" status: "True" type: PodReadyToStartContainers - lastProbeTime: null lastTransitionTime: "2026-07-01T22:03:27Z" status: "True" type: Initialized - lastProbeTime: null lastTransitionTime: "2026-07-01T22:03:38Z" status: "True" type: Ready - lastProbeTime: null lastTransitionTime: "2026-07-01T22:03:38Z" status: "True" type: ContainersReady - lastProbeTime: null lastTransitionTime: "2026-07-01T22:03:26Z" status: "True" type: PodScheduled containerStatuses: - allocatedResources: cpu: 200m memory: 2Gi containerID: cri-o://70e6b3d82670e8c0f0d049bad6cc8c6b2f0ca01ea609c5499a00df7cba72e511 image: ghcr.io/llm-d/llm-d-inference-sim:v0.8.2 imageID: ghcr.io/llm-d/llm-d-inference-sim@sha256:bab162bd25e2ed8b15022387cdb223023aeb33be49476af9f0115c0398fb8ff5 lastState: {} name: main ready: true resources: limits: cpu: "1" memory: 2Gi requests: cpu: 200m memory: 2Gi restartCount: 0 started: true state: running: startedAt: "2026-07-01T22:03:27Z" user: linux: gid: 0 supplementalGroups: - 0 - 1000690000 uid: 1000690000 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 recursiveReadOnly: Disabled - mountPath: /var/run/secrets/kubernetes.io/serviceaccount name: kube-api-access-czsgj readOnly: true recursiveReadOnly: Disabled hostIP: 10.0.132.117 hostIPs: - ip: 10.0.132.117 initContainerStatuses: - containerID: cri-o://cba610fa38e690fecb0ab799e0eb2e77a105ef84a0e05f86340a190db1ececc1 image: ghcr.io/llm-d/llm-d-router-disagg-sidecar:v0.9.0-rc.2 imageID: ghcr.io/llm-d/llm-d-router-disagg-sidecar@sha256:1ec2c035216ea0a4f8a6f7ccda55398fc3d9f71f487c135f49ba0dea08163f12 lastState: {} name: llm-d-routing-sidecar ready: true resources: {} restartCount: 0 started: true state: running: startedAt: "2026-07-01T22:03:27Z" user: linux: gid: 0 supplementalGroups: - 0 - 1000690000 uid: 1000690000 volumeMounts: - mountPath: /var/run/kserve/tls name: tls-certs readOnly: true recursiveReadOnly: Disabled - mountPath: /var/run/secrets/kubernetes.io/serviceaccount name: kube-api-access-czsgj readOnly: true recursiveReadOnly: Disabled phase: Running podIP: 10.134.0.69 podIPs: - ip: 10.134.0.69 qosClass: Burstable startTime: "2026-07-01T22:03:26Z"