--- apiVersion: v1 items: - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:14:55Z" labels: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: auth-disabled-test app.kubernetes.io/part-of: llminferenceservice managedFields: - apiVersion: 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":"ce7c4c80-56a3-44d8-a8c1-056804de3ef9"}: {} f:spec: f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":5557,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9002,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9003,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9090,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: manager operation: Update time: "2026-07-08T07:14:55Z" name: auth-disabled-test-epp-service namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: auth-disabled-test uid: ce7c4c80-56a3-44d8-a8c1-056804de3ef9 resourceVersion: "28583" uid: 289d2df9-8d35-490f-8c2a-cdcbf8bcf7fb spec: clusterIP: 172.31.34.251 clusterIPs: - 172.31.34.251 internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - name: grpc port: 9002 protocol: TCP targetPort: grpc - name: grpc-health port: 9003 protocol: TCP targetPort: grpc-health - name: metrics port: 9090 protocol: TCP targetPort: metrics - name: zmq port: 5557 protocol: TCP targetPort: zmq selector: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: auth-disabled-test app.kubernetes.io/part-of: llminferenceservice sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:15:36Z" labels: internal.istio.io/service-semantics: inferencepool istio.io/inferencepool-extension-failure-mode: FailOpen istio.io/inferencepool-extension-port: "9002" istio.io/inferencepool-extension-service: auth-disabled-test-epp-service istio.io/inferencepool-name: auth-disabled-test-inference-pool managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:labels: .: {} f:internal.istio.io/service-semantics: {} f:istio.io/inferencepool-extension-failure-mode: {} f:istio.io/inferencepool-extension-port: {} f:istio.io/inferencepool-extension-service: {} f:istio.io/inferencepool-name: {} f:ownerReferences: .: {} k:{"uid":"37f5ae2b-eb1b-410d-8d9c-c5cd03732e06"}: {} f:spec: f:clusterIP: {} f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":54321,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: pilot-discovery operation: Update time: "2026-07-08T07:15:36Z" name: auth-disabled-test-inference-pool-ip-5f67cff2 namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: inference.networking.k8s.io/v1 kind: InferencePool name: auth-disabled-test-inference-pool uid: 37f5ae2b-eb1b-410d-8d9c-c5cd03732e06 resourceVersion: "29207" uid: 4e71e349-8692-4f40-a48c-02a69f78eed2 spec: clusterIP: None clusterIPs: - None internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - name: port0 port: 54321 protocol: TCP targetPort: 8000 selector: app.kubernetes.io/name: auth-disabled-test app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:14:55Z" labels: app.kubernetes.io/component: llminferenceservice-workload app.kubernetes.io/name: auth-disabled-test app.kubernetes.io/part-of: llminferenceservice managedFields: - apiVersion: 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":"ce7c4c80-56a3-44d8-a8c1-056804de3ef9"}: {} f:spec: f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":8000,"protocol":"TCP"}: .: {} f:appProtocol: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: manager operation: Update time: "2026-07-08T07:14:55Z" name: auth-disabled-test-kserve-workload-svc namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: auth-disabled-test uid: ce7c4c80-56a3-44d8-a8c1-056804de3ef9 resourceVersion: "28547" uid: 7d27cac5-82d1-47fd-aa8f-81304c7061cb spec: clusterIP: 172.31.93.18 clusterIPs: - 172.31.93.18 internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - appProtocol: https name: https port: 8000 protocol: TCP targetPort: 8000 selector: app.kubernetes.io/name: auth-disabled-test app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:38:22Z" labels: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: custom-route-timeout-test app.kubernetes.io/part-of: llminferenceservice managedFields: - apiVersion: 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":"5fd98af4-ea51-4e8c-95c6-4ab08c991e2c"}: {} f:spec: f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":5557,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9002,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9003,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9090,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: manager operation: Update time: "2026-07-08T07:38:22Z" name: custom-route-timeout-test-epp-service namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: custom-route-timeout-test uid: 5fd98af4-ea51-4e8c-95c6-4ab08c991e2c resourceVersion: "51381" uid: 2bef2dab-e721-4ae4-ad2d-14da00c6fb21 spec: clusterIP: 172.31.104.110 clusterIPs: - 172.31.104.110 internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - name: grpc port: 9002 protocol: TCP targetPort: grpc - name: grpc-health port: 9003 protocol: TCP targetPort: grpc-health - name: metrics port: 9090 protocol: TCP targetPort: metrics - name: zmq port: 5557 protocol: TCP targetPort: zmq selector: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: custom-route-timeout-test app.kubernetes.io/part-of: llminferenceservice sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:38:34Z" labels: internal.istio.io/service-semantics: inferencepool istio.io/inferencepool-extension-failure-mode: FailOpen istio.io/inferencepool-extension-port: "9002" istio.io/inferencepool-extension-service: custom-route-timeout-test-epp-service istio.io/inferencepool-name: custom-route-timeout-test-inference-pool managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:labels: .: {} f:internal.istio.io/service-semantics: {} f:istio.io/inferencepool-extension-failure-mode: {} f:istio.io/inferencepool-extension-port: {} f:istio.io/inferencepool-extension-service: {} f:istio.io/inferencepool-name: {} f:ownerReferences: .: {} k:{"uid":"70673015-44fb-4544-bab7-57dd3fb85201"}: {} f:spec: f:clusterIP: {} f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":54321,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: pilot-discovery operation: Update time: "2026-07-08T07:38:34Z" name: custom-route-timeout-test-inference-pool-ip-45342e47 namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: inference.networking.k8s.io/v1 kind: InferencePool name: custom-route-timeout-test-inference-pool uid: 70673015-44fb-4544-bab7-57dd3fb85201 resourceVersion: "51652" uid: 5f77dce3-909b-40c1-acf1-3dd4836d7845 spec: clusterIP: None clusterIPs: - None internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - name: port0 port: 54321 protocol: TCP targetPort: 8000 selector: app.kubernetes.io/name: custom-route-timeout-test app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:38:21Z" labels: app.kubernetes.io/component: llminferenceservice-workload app.kubernetes.io/name: custom-route-timeout-test app.kubernetes.io/part-of: llminferenceservice managedFields: - apiVersion: 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":"5fd98af4-ea51-4e8c-95c6-4ab08c991e2c"}: {} f:spec: f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":8000,"protocol":"TCP"}: .: {} f:appProtocol: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: manager operation: Update time: "2026-07-08T07:38:21Z" name: custom-route-timeout-test-kserve-workload-svc namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: custom-route-timeout-test uid: 5fd98af4-ea51-4e8c-95c6-4ab08c991e2c resourceVersion: "51346" uid: 271881a5-1aa7-47c5-9876-398c1e79b045 spec: clusterIP: 172.31.98.102 clusterIPs: - 172.31.98.102 internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - appProtocol: https name: https port: 8000 protocol: TCP targetPort: 8000 selector: app.kubernetes.io/name: custom-route-timeout-test app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:21:02Z" labels: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: llmisvc-model-fb-opt-125m-route-87882a8e app.kubernetes.io/part-of: llminferenceservice managedFields: - apiVersion: 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":"565176bb-ec06-4726-bd46-befcc78f8c33"}: {} f:spec: f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":5557,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9002,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9003,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9090,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: manager operation: Update time: "2026-07-08T07:21:02Z" name: llmisvc-model-fb-opt-125m-route-87882a8e-epp-service namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: llmisvc-model-fb-opt-125m-route-87882a8e uid: 565176bb-ec06-4726-bd46-befcc78f8c33 resourceVersion: "34760" uid: cda22e9b-30ee-4cfe-a72b-478d3d3d1902 spec: clusterIP: 172.31.99.193 clusterIPs: - 172.31.99.193 internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - name: grpc port: 9002 protocol: TCP targetPort: grpc - name: grpc-health port: 9003 protocol: TCP targetPort: grpc-health - name: metrics port: 9090 protocol: TCP targetPort: metrics - name: zmq port: 5557 protocol: TCP targetPort: zmq selector: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: llmisvc-model-fb-opt-125m-route-87882a8e app.kubernetes.io/part-of: llminferenceservice sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:21:11Z" labels: internal.istio.io/service-semantics: inferencepool istio.io/inferencepool-extension-failure-mode: FailOpen istio.io/inferencepool-extension-port: "9002" istio.io/inferencepool-extension-service: llmisvc-model-fb-opt-125m-route-87882a8e-epp-service istio.io/inferencepool-name: llmisvc-model-fb-opt-125m-route-87882a8e-inference-pool managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:labels: .: {} f:internal.istio.io/service-semantics: {} f:istio.io/inferencepool-extension-failure-mode: {} f:istio.io/inferencepool-extension-port: {} f:istio.io/inferencepool-extension-service: {} f:istio.io/inferencepool-name: {} f:ownerReferences: .: {} k:{"uid":"fab1aedd-b1e6-4c7c-947e-b4d20de73b13"}: {} f:spec: f:clusterIP: {} f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":54321,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: pilot-discovery operation: Update time: "2026-07-08T07:21:11Z" name: llmisvc-model-fb-opt-125m-route-87882a8e-inference--ip-aaa905cb namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: inference.networking.k8s.io/v1 kind: InferencePool name: llmisvc-model-fb-opt-125m-route-87882a8e-inference-pool uid: fab1aedd-b1e6-4c7c-947e-b4d20de73b13 resourceVersion: "35017" uid: 4c84cd94-cf5e-4ee3-bba4-08728f0faead spec: clusterIP: None clusterIPs: - None internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - name: port0 port: 54321 protocol: TCP targetPort: 8000 selector: app.kubernetes.io/name: llmisvc-model-fb-opt-125m-route-87882a8e app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:21:02Z" labels: app.kubernetes.io/component: llminferenceservice-workload app.kubernetes.io/name: llmisvc-model-fb-opt-125m-route-87882a8e app.kubernetes.io/part-of: llminferenceservice managedFields: - apiVersion: 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":"565176bb-ec06-4726-bd46-befcc78f8c33"}: {} f:spec: f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":8000,"protocol":"TCP"}: .: {} f:appProtocol: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: manager operation: Update time: "2026-07-08T07:21:02Z" name: llmisvc-model-fb-opt-125m-route-87882a8e-kserve-workload-svc namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: llmisvc-model-fb-opt-125m-route-87882a8e uid: 565176bb-ec06-4726-bd46-befcc78f8c33 resourceVersion: "34734" uid: 37bd207c-ff89-4a43-a089-083582c09756 spec: clusterIP: 172.31.177.225 clusterIPs: - 172.31.177.225 internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - appProtocol: https name: https port: 8000 protocol: TCP targetPort: 8000 selector: app.kubernetes.io/name: llmisvc-model-fb-opt-125m-route-87882a8e app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:16:26Z" labels: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: llmisvc-model-fb-opt-125m-with-7ca60146 app.kubernetes.io/part-of: llminferenceservice managedFields: - apiVersion: 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":"43d7de34-80f8-461c-8576-1e03984be0d5"}: {} f:spec: f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":5557,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9002,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9003,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9090,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: manager operation: Update time: "2026-07-08T07:16:26Z" name: llmisvc-model-fb-opt-125m-with-7ca60146-epp-service namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: llmisvc-model-fb-opt-125m-with-7ca60146 uid: 43d7de34-80f8-461c-8576-1e03984be0d5 resourceVersion: "29950" uid: 369b4234-be65-4d0d-81e6-b922b7dc81b4 spec: clusterIP: 172.31.221.21 clusterIPs: - 172.31.221.21 internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - name: grpc port: 9002 protocol: TCP targetPort: grpc - name: grpc-health port: 9003 protocol: TCP targetPort: grpc-health - name: metrics port: 9090 protocol: TCP targetPort: metrics - name: zmq port: 5557 protocol: TCP targetPort: zmq selector: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: llmisvc-model-fb-opt-125m-with-7ca60146 app.kubernetes.io/part-of: llminferenceservice sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:16:34Z" labels: internal.istio.io/service-semantics: inferencepool istio.io/inferencepool-extension-failure-mode: FailOpen istio.io/inferencepool-extension-port: "9002" istio.io/inferencepool-extension-service: llmisvc-model-fb-opt-125m-with-7ca60146-epp-service istio.io/inferencepool-name: llmisvc-model-fb-opt-125m-with-7ca60146-inference-pool managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:labels: .: {} f:internal.istio.io/service-semantics: {} f:istio.io/inferencepool-extension-failure-mode: {} f:istio.io/inferencepool-extension-port: {} f:istio.io/inferencepool-extension-service: {} f:istio.io/inferencepool-name: {} f:ownerReferences: .: {} k:{"uid":"e7767ee3-062e-4c32-8edb-a86d0fd8f5e0"}: {} f:spec: f:clusterIP: {} f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":54321,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: pilot-discovery operation: Update time: "2026-07-08T07:16:34Z" name: llmisvc-model-fb-opt-125m-with-7ca60146-inference-p-ip-16c62f55 namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: inference.networking.k8s.io/v1 kind: InferencePool name: llmisvc-model-fb-opt-125m-with-7ca60146-inference-pool uid: e7767ee3-062e-4c32-8edb-a86d0fd8f5e0 resourceVersion: "30188" uid: a38d94ef-d078-4e19-b06b-a072dd0bf2f5 spec: clusterIP: None clusterIPs: - None internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - name: port0 port: 54321 protocol: TCP targetPort: 8000 selector: app.kubernetes.io/name: llmisvc-model-fb-opt-125m-with-7ca60146 app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:16:26Z" labels: app.kubernetes.io/component: llminferenceservice-workload app.kubernetes.io/name: llmisvc-model-fb-opt-125m-with-7ca60146 app.kubernetes.io/part-of: llminferenceservice managedFields: - apiVersion: 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":"43d7de34-80f8-461c-8576-1e03984be0d5"}: {} f:spec: f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":8000,"protocol":"TCP"}: .: {} f:appProtocol: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: manager operation: Update time: "2026-07-08T07:16:26Z" name: llmisvc-model-fb-opt-125m-with-7ca60146-kserve-workload-svc namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: llmisvc-model-fb-opt-125m-with-7ca60146 uid: 43d7de34-80f8-461c-8576-1e03984be0d5 resourceVersion: "29916" uid: f3ffe853-0b04-4be8-b0a7-f59eed9ce914 spec: clusterIP: 172.31.23.135 clusterIPs: - 172.31.23.135 internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - appProtocol: https name: https port: 8000 protocol: TCP targetPort: 8000 selector: app.kubernetes.io/name: llmisvc-model-fb-opt-125m-with-7ca60146 app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:33:12Z" labels: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: llmisvc-model-fb-opt-125m-with-ba4d693a app.kubernetes.io/part-of: llminferenceservice managedFields: - apiVersion: 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":"79fa8820-032c-4f6b-aef9-01746be29eab"}: {} f:spec: f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":5557,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9002,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9003,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9090,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: manager operation: Update time: "2026-07-08T07:33:12Z" name: llmisvc-model-fb-opt-125m-with-ba4d693a-epp-service namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: llmisvc-model-fb-opt-125m-with-ba4d693a uid: 79fa8820-032c-4f6b-aef9-01746be29eab resourceVersion: "46602" uid: 8b7d23f5-ebdc-48c9-a7c5-b56c75a1c0bb spec: clusterIP: 172.31.30.104 clusterIPs: - 172.31.30.104 internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - name: grpc port: 9002 protocol: TCP targetPort: grpc - name: grpc-health port: 9003 protocol: TCP targetPort: grpc-health - name: metrics port: 9090 protocol: TCP targetPort: metrics - name: zmq port: 5557 protocol: TCP targetPort: zmq selector: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: llmisvc-model-fb-opt-125m-with-ba4d693a app.kubernetes.io/part-of: llminferenceservice sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:33:23Z" labels: internal.istio.io/service-semantics: inferencepool istio.io/inferencepool-extension-failure-mode: FailOpen istio.io/inferencepool-extension-port: "9002" istio.io/inferencepool-extension-service: llmisvc-model-fb-opt-125m-with-ba4d693a-epp-service istio.io/inferencepool-name: llmisvc-model-fb-opt-125m-with-ba4d693a-inference-pool managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:labels: .: {} f:internal.istio.io/service-semantics: {} f:istio.io/inferencepool-extension-failure-mode: {} f:istio.io/inferencepool-extension-port: {} f:istio.io/inferencepool-extension-service: {} f:istio.io/inferencepool-name: {} f:ownerReferences: .: {} k:{"uid":"ede306d2-f3b0-44ee-8a6d-662c400d477a"}: {} f:spec: f:clusterIP: {} f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":54321,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: pilot-discovery operation: Update time: "2026-07-08T07:33:23Z" name: llmisvc-model-fb-opt-125m-with-ba4d693a-inference-p-ip-f5162b44 namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: inference.networking.k8s.io/v1 kind: InferencePool name: llmisvc-model-fb-opt-125m-with-ba4d693a-inference-pool uid: ede306d2-f3b0-44ee-8a6d-662c400d477a resourceVersion: "46876" uid: 2d0d1f80-d703-43d2-a708-1e6270929571 spec: clusterIP: None clusterIPs: - None internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - name: port0 port: 54321 protocol: TCP targetPort: 8000 selector: app.kubernetes.io/name: llmisvc-model-fb-opt-125m-with-ba4d693a app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:33:12Z" labels: app.kubernetes.io/component: llminferenceservice-workload app.kubernetes.io/name: llmisvc-model-fb-opt-125m-with-ba4d693a app.kubernetes.io/part-of: llminferenceservice managedFields: - apiVersion: 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":"79fa8820-032c-4f6b-aef9-01746be29eab"}: {} f:spec: f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":8000,"protocol":"TCP"}: .: {} f:appProtocol: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: manager operation: Update time: "2026-07-08T07:33:12Z" name: llmisvc-model-fb-opt-125m-with-ba4d693a-kserve-workload-svc namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: llmisvc-model-fb-opt-125m-with-ba4d693a uid: 79fa8820-032c-4f6b-aef9-01746be29eab resourceVersion: "46577" uid: 3e4abc26-faa7-46f8-a18d-945fc81fb145 spec: clusterIP: 172.31.82.175 clusterIPs: - 172.31.82.175 internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - appProtocol: https name: https port: 8000 protocol: TCP targetPort: 8000 selector: app.kubernetes.io/name: llmisvc-model-fb-opt-125m-with-ba4d693a app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:54:26Z" labels: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: llmisvc-model-pvc-router-manage-2577e794 app.kubernetes.io/part-of: llminferenceservice managedFields: - apiVersion: 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":"f79149f0-62e1-4029-a269-01f75473f7f7"}: {} f:spec: f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":5557,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9002,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9003,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9090,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: manager operation: Update time: "2026-07-08T07:54:26Z" name: llmisvc-model-pvc-router-manage-2577e794-epp-service namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: llmisvc-model-pvc-router-manage-2577e794 uid: f79149f0-62e1-4029-a269-01f75473f7f7 resourceVersion: "64591" uid: 902e51d4-a748-40cd-8dfa-5140409eccd6 spec: clusterIP: 172.31.233.210 clusterIPs: - 172.31.233.210 internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - name: grpc port: 9002 protocol: TCP targetPort: grpc - name: grpc-health port: 9003 protocol: TCP targetPort: grpc-health - name: metrics port: 9090 protocol: TCP targetPort: metrics - name: zmq port: 5557 protocol: TCP targetPort: zmq selector: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: llmisvc-model-pvc-router-manage-2577e794 app.kubernetes.io/part-of: llminferenceservice sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:54:41Z" labels: internal.istio.io/service-semantics: inferencepool istio.io/inferencepool-extension-failure-mode: FailOpen istio.io/inferencepool-extension-port: "9002" istio.io/inferencepool-extension-service: llmisvc-model-pvc-router-manage-2577e794-epp-service istio.io/inferencepool-name: llmisvc-model-pvc-router-manage-2577e794-inference-pool managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:labels: .: {} f:internal.istio.io/service-semantics: {} f:istio.io/inferencepool-extension-failure-mode: {} f:istio.io/inferencepool-extension-port: {} f:istio.io/inferencepool-extension-service: {} f:istio.io/inferencepool-name: {} f:ownerReferences: .: {} k:{"uid":"ff720ece-9894-4485-8a27-448904777539"}: {} f:spec: f:clusterIP: {} f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":54321,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: pilot-discovery operation: Update time: "2026-07-08T07:54:41Z" name: llmisvc-model-pvc-router-manage-2577e794-inference--ip-950f33a3 namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: inference.networking.k8s.io/v1 kind: InferencePool name: llmisvc-model-pvc-router-manage-2577e794-inference-pool uid: ff720ece-9894-4485-8a27-448904777539 resourceVersion: "64900" uid: 1f974cfe-acca-41b0-8e06-a6e2d29f6927 spec: clusterIP: None clusterIPs: - None internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - name: port0 port: 54321 protocol: TCP targetPort: 8000 selector: app.kubernetes.io/name: llmisvc-model-pvc-router-manage-2577e794 app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:54:26Z" labels: leaderworkerset.sigs.k8s.io/name: llmisvc-model-pvc-router-manage-2577e794-kserve-mn managedFields: - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:labels: .: {} f:leaderworkerset.sigs.k8s.io/name: {} f:ownerReferences: .: {} k:{"uid":"7212fc32-0bd2-4dc4-9263-bdae474c7b38"}: {} f:spec: f:clusterIP: {} f:internalTrafficPolicy: {} f:publishNotReadyAddresses: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: lws operation: Update time: "2026-07-08T07:54:26Z" 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: 7212fc32-0bd2-4dc4-9263-bdae474c7b38 resourceVersion: "64554" uid: 587be841-eaf3-46ac-bfc8-51bd21cc5b7d spec: clusterIP: None clusterIPs: - None internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack publishNotReadyAddresses: true selector: leaderworkerset.sigs.k8s.io/name: llmisvc-model-pvc-router-manage-2577e794-kserve-mn sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:54:26Z" labels: app.kubernetes.io/component: llminferenceservice-workload app.kubernetes.io/name: llmisvc-model-pvc-router-manage-2577e794 app.kubernetes.io/part-of: llminferenceservice managedFields: - apiVersion: 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":"f79149f0-62e1-4029-a269-01f75473f7f7"}: {} f:spec: f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":8000,"protocol":"TCP"}: .: {} f:appProtocol: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: manager operation: Update time: "2026-07-08T07:54:26Z" name: llmisvc-model-pvc-router-manage-2577e794-kserve-workload-svc namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: llmisvc-model-pvc-router-manage-2577e794 uid: f79149f0-62e1-4029-a269-01f75473f7f7 resourceVersion: "64539" uid: a94686b4-70db-4e60-acfa-5905711f8ed9 spec: clusterIP: 172.31.36.18 clusterIPs: - 172.31.36.18 internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - appProtocol: https name: https port: 8000 protocol: TCP targetPort: 8000 selector: app.kubernetes.io/name: llmisvc-model-pvc-router-manage-2577e794 app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:07:58Z" finalizers: - service.kubernetes.io/load-balancer-cleanup labels: gateway.istio.io/managed: openshift.io-gateway-controller-v1 gateway.networking.k8s.io/gateway-name: router-gateway-1 managedFields: - apiVersion: 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":"b9e516c8-3eb0-4bc2-8b12-7f29f4f24e92"}: {} f:spec: f:ipFamilyPolicy: {} f:ports: k:{"port":80,"protocol":"TCP"}: .: {} f:appProtocol: {} f:name: {} f:port: {} f:protocol: {} k:{"port":15021,"protocol":"TCP"}: .: {} f:appProtocol: {} f:name: {} f:port: {} f:protocol: {} f:selector: {} f:type: {} manager: openshift.io/gateway-controller/v1 operation: Apply time: "2026-07-08T07:07:58Z" - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:finalizers: .: {} v:"service.kubernetes.io/load-balancer-cleanup": {} f:status: f:loadBalancer: f:ingress: {} manager: aws-cloud-controller-manager operation: Update subresource: status time: "2026-07-08T07:08:02Z" 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: b9e516c8-3eb0-4bc2-8b12-7f29f4f24e92 resourceVersion: "21890" uid: 4a570714-51d6-4d3f-8101-3e4f28888b7a spec: allocateLoadBalancerNodePorts: true clusterIP: 172.31.22.197 clusterIPs: - 172.31.22.197 externalTrafficPolicy: Cluster internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: PreferDualStack ports: - appProtocol: tcp name: status-port nodePort: 31061 port: 15021 protocol: TCP targetPort: 15021 - appProtocol: http name: http nodePort: 30401 port: 80 protocol: TCP targetPort: 80 selector: gateway.networking.k8s.io/gateway-name: router-gateway-1 sessionAffinity: None type: LoadBalancer status: loadBalancer: ingress: - hostname: a4a57071451d64d3f81013e4f28888b7-1617786295.us-east-1.elb.amazonaws.com - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T08:18:27Z" finalizers: - service.kubernetes.io/load-balancer-cleanup labels: gateway.istio.io/managed: openshift.io-gateway-controller-v1 gateway.networking.k8s.io/gateway-name: router-gateway-2 managedFields: - apiVersion: 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":"bad4569c-993d-4e23-874f-add0a3f9fcbb"}: {} f:spec: f:ipFamilyPolicy: {} f:ports: k:{"port":80,"protocol":"TCP"}: .: {} f:appProtocol: {} f:name: {} f:port: {} f:protocol: {} k:{"port":15021,"protocol":"TCP"}: .: {} f:appProtocol: {} f:name: {} f:port: {} f:protocol: {} f:selector: {} f:type: {} manager: openshift.io/gateway-controller/v1 operation: Apply time: "2026-07-08T08:18:27Z" - apiVersion: v1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:finalizers: .: {} v:"service.kubernetes.io/load-balancer-cleanup": {} f:status: f:loadBalancer: f:ingress: {} manager: aws-cloud-controller-manager operation: Update subresource: status time: "2026-07-08T08:18:31Z" 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: bad4569c-993d-4e23-874f-add0a3f9fcbb resourceVersion: "84768" uid: 1978d492-dc6b-42a4-b38c-771049a3ff2d spec: allocateLoadBalancerNodePorts: true clusterIP: 172.31.63.225 clusterIPs: - 172.31.63.225 externalTrafficPolicy: Cluster internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: PreferDualStack ports: - appProtocol: tcp name: status-port nodePort: 31309 port: 15021 protocol: TCP targetPort: 15021 - appProtocol: http name: http nodePort: 31331 port: 80 protocol: TCP targetPort: 80 selector: gateway.networking.k8s.io/gateway-name: router-gateway-2 sessionAffinity: None type: LoadBalancer status: loadBalancer: ingress: - hostname: a1978d492dc6b42a4b38c771049a3ff2-1772104149.us-east-1.elb.amazonaws.com - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T08:19:03Z" labels: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: router-with-refs-pd-test app.kubernetes.io/part-of: llminferenceservice managedFields: - apiVersion: 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":"5071849d-29aa-4402-acb7-9d9bfa4d0c2a"}: {} f:spec: f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":5557,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9002,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9003,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9090,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: manager operation: Update time: "2026-07-08T08:19:03Z" name: router-with-refs-pd-test-epp-service namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: router-with-refs-pd-test uid: 5071849d-29aa-4402-acb7-9d9bfa4d0c2a resourceVersion: "85296" uid: 32e4422a-b429-44fe-a586-f29184471b12 spec: clusterIP: 172.31.134.201 clusterIPs: - 172.31.134.201 internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - name: grpc port: 9002 protocol: TCP targetPort: grpc - name: grpc-health port: 9003 protocol: TCP targetPort: grpc-health - name: metrics port: 9090 protocol: TCP targetPort: metrics - name: zmq port: 5557 protocol: TCP targetPort: zmq selector: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: router-with-refs-pd-test app.kubernetes.io/part-of: llminferenceservice sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T08:19:02Z" labels: app.kubernetes.io/component: llminferenceservice-workload app.kubernetes.io/name: router-with-refs-pd-test app.kubernetes.io/part-of: llminferenceservice managedFields: - apiVersion: 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":"5071849d-29aa-4402-acb7-9d9bfa4d0c2a"}: {} f:spec: f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":8000,"protocol":"TCP"}: .: {} f:appProtocol: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: manager operation: Update time: "2026-07-08T08:19:02Z" name: router-with-refs-pd-test-kserve-workload-svc namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: router-with-refs-pd-test uid: 5071849d-29aa-4402-acb7-9d9bfa4d0c2a resourceVersion: "85223" uid: 1bb56456-2d0c-406d-aff4-404149cda683 spec: clusterIP: 172.31.124.140 clusterIPs: - 172.31.124.140 internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - appProtocol: https name: https port: 8000 protocol: TCP targetPort: 8000 selector: app.kubernetes.io/name: router-with-refs-pd-test app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:55:59Z" labels: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: router-with-refs-test app.kubernetes.io/part-of: llminferenceservice managedFields: - apiVersion: 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":"cb3afc0b-477a-4222-a441-67bfedc83c98"}: {} f:spec: f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":5557,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9002,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9003,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} k:{"port":9090,"protocol":"TCP"}: .: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: manager operation: Update time: "2026-07-08T07:55:59Z" name: router-with-refs-test-epp-service namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: router-with-refs-test uid: cb3afc0b-477a-4222-a441-67bfedc83c98 resourceVersion: "66018" uid: a07817be-18bd-4acb-94f3-f1176f58b676 spec: clusterIP: 172.31.21.208 clusterIPs: - 172.31.21.208 internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - name: grpc port: 9002 protocol: TCP targetPort: grpc - name: grpc-health port: 9003 protocol: TCP targetPort: grpc-health - name: metrics port: 9090 protocol: TCP targetPort: metrics - name: zmq port: 5557 protocol: TCP targetPort: zmq selector: app.kubernetes.io/component: llminferenceservice-router-scheduler app.kubernetes.io/name: router-with-refs-test app.kubernetes.io/part-of: llminferenceservice sessionAffinity: None type: ClusterIP status: loadBalancer: {} - apiVersion: v1 kind: Service metadata: creationTimestamp: "2026-07-08T07:55:58Z" labels: app.kubernetes.io/component: llminferenceservice-workload app.kubernetes.io/name: router-with-refs-test app.kubernetes.io/part-of: llminferenceservice managedFields: - apiVersion: 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":"cb3afc0b-477a-4222-a441-67bfedc83c98"}: {} f:spec: f:internalTrafficPolicy: {} f:ports: .: {} k:{"port":8000,"protocol":"TCP"}: .: {} f:appProtocol: {} f:name: {} f:port: {} f:protocol: {} f:targetPort: {} f:selector: {} f:sessionAffinity: {} f:type: {} manager: manager operation: Update time: "2026-07-08T07:55:58Z" name: router-with-refs-test-kserve-workload-svc namespace: kserve-ci-e2e-test ownerReferences: - apiVersion: serving.kserve.io/v1alpha2 blockOwnerDeletion: true controller: true kind: LLMInferenceService name: router-with-refs-test uid: cb3afc0b-477a-4222-a441-67bfedc83c98 resourceVersion: "65979" uid: 40619c30-50d3-46da-b1ce-22c072b5f1f6 spec: clusterIP: 172.31.254.66 clusterIPs: - 172.31.254.66 internalTrafficPolicy: Cluster ipFamilies: - IPv4 ipFamilyPolicy: SingleStack ports: - appProtocol: https name: https port: 8000 protocol: TCP targetPort: 8000 selector: app.kubernetes.io/name: router-with-refs-test app.kubernetes.io/part-of: llminferenceservice kserve.io/component: workload sessionAffinity: None type: ClusterIP status: loadBalancer: {} kind: ServiceList metadata: resourceVersion: "98434"