--- apiVersion: apps/v1 items: - apiVersion: apps/v1 kind: StatefulSet metadata: annotations: leaderworkerset.sigs.k8s.io/replicas: "1" creationTimestamp: "2026-07-02T13:58:29Z" generation: 1 labels: leaderworkerset.sigs.k8s.io/name: llmisvc-model-pvc-router-manage-2577e794-kserve-mn leaderworkerset.sigs.k8s.io/template-revision-hash: 686d468674 managedFields: - apiVersion: apps/v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:annotations: f:leaderworkerset.sigs.k8s.io/replicas: {} f:labels: f:leaderworkerset.sigs.k8s.io/name: {} f:leaderworkerset.sigs.k8s.io/template-revision-hash: {} f:ownerReferences: k:{"uid":"7ab2f756-b06f-43a6-9d57-4f1ab7aed086"}: {} f:spec: f:podManagementPolicy: {} f:replicas: {} f:selector: {} f:serviceName: {} f:template: f:metadata: f:annotations: f:leaderworkerset.sigs.k8s.io/size: {} f:labels: f:app.kubernetes.io/component: {} f:app.kubernetes.io/name: {} f:app.kubernetes.io/part-of: {} f:kserve.io/component: {} f:leaderworkerset.sigs.k8s.io/name: {} f:leaderworkerset.sigs.k8s.io/template-revision-hash: {} f:leaderworkerset.sigs.k8s.io/worker-index: {} 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":"TORCHINDUCTOR_CACHE_DIR"}: .: {} f:name: {} f:value: {} k:{"name":"USER"}: .: {} f:name: {} f:value: {} k:{"name":"VLLM_CPU_KVCACHE_SPACE"}: .: {} f:name: {} f:value: {} k:{"name":"VLLM_ENABLE_V1_MULTIPROCESSING"}: .: {} 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: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:timeoutSeconds: {} f:resources: f:limits: f:cpu: {} f:memory: {} f:requests: f:cpu: {} f:memory: {} f:securityContext: f:allowPrivilegeEscalation: {} f:capabilities: f:add: {} 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:terminationMessagePath: {} f:terminationMessagePolicy: {} f:volumeMounts: k:{"mountPath":"/dev/shm"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/home"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/mnt/models"}: .: {} f:mountPath: {} f:name: {} f:readOnly: {} 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: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":"kserve-pvc-source"}: .: {} f:name: {} f:persistentVolumeClaim: f:claimName: {} k:{"name":"model-cache"}: .: {} f:emptyDir: {} f:name: {} k:{"name":"tls-certs"}: .: {} f:name: {} f:secret: f:secretName: {} k:{"name":"tmp-dir"}: .: {} f:emptyDir: {} f:name: {} f:updateStrategy: f:rollingUpdate: f:maxUnavailable: {} f:partition: {} f:type: {} manager: lws operation: Apply time: "2026-07-02T13:58:29Z" - apiVersion: apps/v1 fieldsType: FieldsV1 fieldsV1: f:status: f:collisionCount: {} f:currentReplicas: {} f:currentRevision: {} f:observedGeneration: {} f:replicas: {} f:updateRevision: {} f:updatedReplicas: {} manager: kube-controller-manager operation: Update subresource: status time: "2026-07-02T13:58:29Z" name: llmisvc-model-pvc-router-manage-2577e794-kserve-mn namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: leaderworkerset.x-k8s.io/v1 blockOwnerDeletion: true controller: true kind: LeaderWorkerSet name: llmisvc-model-pvc-router-manage-2577e794-kserve-mn uid: 7ab2f756-b06f-43a6-9d57-4f1ab7aed086 resourceVersion: "48826" uid: 3ec48b8e-8461-416e-82e4-b4d0ae2219a4 spec: persistentVolumeClaimRetentionPolicy: whenDeleted: Retain whenScaled: Retain podManagementPolicy: Parallel replicas: 1 revisionHistoryLimit: 10 selector: matchLabels: leaderworkerset.sigs.k8s.io/name: llmisvc-model-pvc-router-manage-2577e794-kserve-mn leaderworkerset.sigs.k8s.io/worker-index: "0" serviceName: llmisvc-model-pvc-router-manage-2577e794-kserve-mn template: metadata: annotations: leaderworkerset.sigs.k8s.io/size: "2" labels: app.kubernetes.io/component: llminferenceservice-workload-leader app.kubernetes.io/name: llmisvc-model-pvc-router-manage-2577e794 app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload leaderworkerset.sigs.k8s.io/name: llmisvc-model-pvc-router-manage-2577e794-kserve-mn leaderworkerset.sigs.k8s.io/template-revision-hash: 686d468674 leaderworkerset.sigs.k8s.io/worker-index: "0" llm-d.ai/role: both spec: containers: - args: - --served-model-name - facebook/opt-125m - --port - "8000" - --enable-ssl-refresh - --ssl-certfile - /var/run/kserve/tls/tls.crt - --ssl-keyfile - /var/run/kserve/tls/tls.key command: - vllm - serve - /mnt/models env: - name: VLLM_CPU_KVCACHE_SPACE value: "1" - name: VLLM_ENABLE_V1_MULTIPROCESSING value: "0" - name: USER value: nonroot - name: TORCHINDUCTOR_CACHE_DIR value: /tmp/torchinductor-cache - name: HOME value: /home - name: VLLM_LOGGING_LEVEL value: INFO - name: HF_HUB_CACHE value: /models image: public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v0.19.0 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: "2" memory: 7Gi requests: cpu: 200m memory: 2Gi securityContext: allowPrivilegeEscalation: false capabilities: add: - IPC_LOCK - SYS_RAWIO - NET_RAW 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: 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: /mnt/models name: kserve-pvc-source readOnly: true dnsPolicy: ClusterFirst restartPolicy: Always schedulerName: default-scheduler securityContext: {} serviceAccount: llmisvc-model-pvc-router-manage-2577e794-kserve-mn serviceAccountName: llmisvc-model-pvc-router-manage-2577e794-kserve-mn terminationGracePeriodSeconds: 60 volumes: - emptyDir: {} name: home - emptyDir: {} name: tmp-dir - emptyDir: medium: Memory sizeLimit: 8Gi name: dshm - emptyDir: {} name: model-cache - name: tls-certs secret: defaultMode: 420 secretName: llmisv1dc4269d1ada5f2d28562215d180c57f-kserve-self-signed-certs - name: kserve-pvc-source persistentVolumeClaim: claimName: e2e-pvc-model-storage updateStrategy: rollingUpdate: partition: 0 type: RollingUpdate status: availableReplicas: 0 collisionCount: 0 currentReplicas: 1 currentRevision: llmisvc-model-pvc-router-manage-2577e794-kserve-mn-7b97d8cc8b observedGeneration: 1 replicas: 1 updateRevision: llmisvc-model-pvc-router-manage-2577e794-kserve-mn-7b97d8cc8b updatedReplicas: 1 - apiVersion: apps/v1 kind: StatefulSet metadata: creationTimestamp: "2026-07-02T13:58:29Z" generation: 1 labels: leaderworkerset.sigs.k8s.io/group-index: "0" leaderworkerset.sigs.k8s.io/group-key: dc52feed9d7e0b6abd87bf4d45c9409765943cd8 leaderworkerset.sigs.k8s.io/name: llmisvc-model-pvc-router-manage-2577e794-kserve-mn leaderworkerset.sigs.k8s.io/template-revision-hash: 686d468674 managedFields: - apiVersion: apps/v1 fieldsType: FieldsV1 fieldsV1: f:status: f:collisionCount: {} f:currentReplicas: {} f:currentRevision: {} f:observedGeneration: {} f:replicas: {} f:updateRevision: {} f:updatedReplicas: {} manager: kube-controller-manager operation: Update subresource: status time: "2026-07-02T13:58:29Z" - apiVersion: apps/v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:labels: .: {} f:leaderworkerset.sigs.k8s.io/group-index: {} f:leaderworkerset.sigs.k8s.io/group-key: {} f:leaderworkerset.sigs.k8s.io/name: {} f:leaderworkerset.sigs.k8s.io/template-revision-hash: {} f:ownerReferences: .: {} k:{"uid":"d3f69700-0389-4c20-8fd5-d1d9d1608bf9"}: {} f:spec: f:ordinals: .: {} f:start: {} f:persistentVolumeClaimRetentionPolicy: .: {} f:whenDeleted: {} f:whenScaled: {} f:podManagementPolicy: {} f:replicas: {} f:revisionHistoryLimit: {} f:selector: {} f:serviceName: {} f:template: f:metadata: f:annotations: .: {} f:leaderworkerset.sigs.k8s.io/leader-name: {} f:leaderworkerset.sigs.k8s.io/size: {} f:labels: .: {} f:app.kubernetes.io/component: {} f:app.kubernetes.io/name: {} f:app.kubernetes.io/part-of: {} f:leaderworkerset.sigs.k8s.io/group-index: {} f:leaderworkerset.sigs.k8s.io/group-key: {} f:leaderworkerset.sigs.k8s.io/name: {} f:leaderworkerset.sigs.k8s.io/template-revision-hash: {} 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":"TORCHINDUCTOR_CACHE_DIR"}: .: {} f:name: {} f:value: {} k:{"name":"USER"}: .: {} f:name: {} f:value: {} k:{"name":"VLLM_CPU_KVCACHE_SPACE"}: .: {} f:name: {} f:value: {} k:{"name":"VLLM_ENABLE_V1_MULTIPROCESSING"}: .: {} 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:name: {} f:ports: .: {} k:{"containerPort":8000,"protocol":"TCP"}: .: {} f:containerPort: {} f:protocol: {} f:resources: .: {} f:limits: .: {} f:cpu: {} f:memory: {} f:requests: .: {} f:cpu: {} f:memory: {} f:securityContext: .: {} f:allowPrivilegeEscalation: {} f:capabilities: .: {} f:add: {} f:drop: {} f:readOnlyRootFilesystem: {} f:runAsNonRoot: {} f:seccompProfile: .: {} f:type: {} f:terminationMessagePath: {} f:terminationMessagePolicy: {} f:volumeMounts: .: {} k:{"mountPath":"/dev/shm"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/home"}: .: {} f:mountPath: {} f:name: {} k:{"mountPath":"/mnt/models"}: .: {} f:mountPath: {} f:name: {} f:readOnly: {} 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: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":"kserve-pvc-source"}: .: {} f:name: {} f:persistentVolumeClaim: .: {} f:claimName: {} 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: {} f:updateStrategy: f:rollingUpdate: .: {} f:partition: {} f:type: {} manager: lws operation: Update time: "2026-07-02T13:58:29Z" name: llmisvc-model-pvc-router-manage-2577e794-kserve-mn-0 namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: v1 blockOwnerDeletion: true controller: true kind: Pod name: llmisvc-model-pvc-router-manage-2577e794-kserve-mn-0 uid: d3f69700-0389-4c20-8fd5-d1d9d1608bf9 resourceVersion: "48855" uid: eb9f5127-8de9-4ba6-99dd-6fee25b73812 spec: ordinals: start: 1 persistentVolumeClaimRetentionPolicy: whenDeleted: Retain whenScaled: Retain podManagementPolicy: Parallel replicas: 1 revisionHistoryLimit: 10 selector: matchLabels: leaderworkerset.sigs.k8s.io/group-index: "0" leaderworkerset.sigs.k8s.io/group-key: dc52feed9d7e0b6abd87bf4d45c9409765943cd8 leaderworkerset.sigs.k8s.io/name: llmisvc-model-pvc-router-manage-2577e794-kserve-mn serviceName: llmisvc-model-pvc-router-manage-2577e794-kserve-mn template: metadata: annotations: leaderworkerset.sigs.k8s.io/leader-name: llmisvc-model-pvc-router-manage-2577e794-kserve-mn-0 leaderworkerset.sigs.k8s.io/size: "2" labels: app.kubernetes.io/component: llminferenceservice-workload-worker app.kubernetes.io/name: llmisvc-model-pvc-router-manage-2577e794 app.kubernetes.io/part-of: llminferenceservice leaderworkerset.sigs.k8s.io/group-index: "0" leaderworkerset.sigs.k8s.io/group-key: dc52feed9d7e0b6abd87bf4d45c9409765943cd8 leaderworkerset.sigs.k8s.io/name: llmisvc-model-pvc-router-manage-2577e794-kserve-mn leaderworkerset.sigs.k8s.io/template-revision-hash: 686d468674 spec: containers: - args: - --served-model-name - facebook/opt-125m - --port - "8000" - --enable-ssl-refresh - --ssl-certfile - /var/run/kserve/tls/tls.crt - --ssl-keyfile - /var/run/kserve/tls/tls.key command: - vllm - serve - /mnt/models env: - name: VLLM_CPU_KVCACHE_SPACE value: "1" - name: VLLM_ENABLE_V1_MULTIPROCESSING value: "0" - name: USER value: nonroot - name: TORCHINDUCTOR_CACHE_DIR value: /tmp/torchinductor-cache - name: HOME value: /home - name: VLLM_LOGGING_LEVEL value: INFO - name: HF_HUB_CACHE value: /models image: public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v0.19.0 imagePullPolicy: IfNotPresent lifecycle: preStop: exec: command: - /bin/sleep - "15" name: main ports: - containerPort: 8000 protocol: TCP resources: limits: cpu: "2" memory: 7Gi requests: cpu: 200m memory: 2Gi securityContext: allowPrivilegeEscalation: false capabilities: add: - IPC_LOCK - SYS_RAWIO - NET_RAW drop: - ALL readOnlyRootFilesystem: true runAsNonRoot: true seccompProfile: type: RuntimeDefault 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: /mnt/models name: kserve-pvc-source readOnly: true dnsPolicy: ClusterFirst restartPolicy: Always schedulerName: default-scheduler securityContext: {} serviceAccount: llmisvc-model-pvc-router-manage-2577e794-kserve-mn serviceAccountName: llmisvc-model-pvc-router-manage-2577e794-kserve-mn terminationGracePeriodSeconds: 60 volumes: - emptyDir: {} name: home - emptyDir: {} name: tmp-dir - emptyDir: medium: Memory sizeLimit: 8Gi name: dshm - emptyDir: {} name: model-cache - name: tls-certs secret: defaultMode: 420 secretName: llmisv1dc4269d1ada5f2d28562215d180c57f-kserve-self-signed-certs - name: kserve-pvc-source persistentVolumeClaim: claimName: e2e-pvc-model-storage updateStrategy: rollingUpdate: partition: 0 type: RollingUpdate status: availableReplicas: 0 collisionCount: 0 currentReplicas: 1 currentRevision: llmisvc-model-pvc-router-manage-2577e794-kserve-mn-0-579bcdf848 observedGeneration: 1 replicas: 1 updateRevision: llmisvc-model-pvc-router-manage-2577e794-kserve-mn-0-579bcdf848 updatedReplicas: 1 kind: StatefulSetList metadata: resourceVersion: "81356"