--- apiVersion: serving.kserve.io/v1alpha2 kind: LLMInferenceService metadata: annotations: kubectl.kubernetes.io/last-applied-configuration: | {"apiVersion":"serving.kserve.io/v1alpha1","kind":"LLMInferenceService","metadata":{"annotations":{},"name":"premium-simulated-simulated-premium","namespace":"llm"},"spec":{"model":{"name":"facebook/opt-125m-premium","uri":"hf://placeholder/no-model"},"replicas":1,"router":{"gateway":{"refs":[{"name":"maas-default-gateway","namespace":"openshift-ingress"}]},"route":{}},"storageInitializer":{"enabled":false},"template":{"containers":[{"args":["--port","8000","--model","facebook/opt-125m-premium","--mode","random","--no-mm-encoder-only","--ssl-certfile","/var/run/kserve/tls/tls.crt","--ssl-keyfile","/var/run/kserve/tls/tls.key"],"command":["/app/llm-d-inference-sim"],"env":[{"name":"POD_NAME","valueFrom":{"fieldRef":{"apiVersion":"v1","fieldPath":"metadata.name"}}},{"name":"POD_NAMESPACE","valueFrom":{"fieldRef":{"apiVersion":"v1","fieldPath":"metadata.namespace"}}},{"name":"POD_IP","valueFrom":{"fieldRef":{"apiVersion":"v1","fieldPath":"status.podIP"}}}],"image":"ghcr.io/llm-d/llm-d-inference-sim:v0.8.2","imagePullPolicy":"Always","livenessProbe":{"httpGet":{"path":"/health","port":"https","scheme":"HTTPS"}},"name":"main","ports":[{"containerPort":8000,"name":"https","protocol":"TCP"}],"readinessProbe":{"httpGet":{"path":"/ready","port":"https","scheme":"HTTPS"}}}]}}} creationTimestamp: "2026-11-03T23:11:19Z" finalizers: - serving.kserve.io/llmisvc-finalizer generation: 1 managedFields: - apiVersion: serving.kserve.io/v1alpha1 fieldsType: FieldsV1 fieldsV1: f:metadata: f:annotations: .: {} f:kubectl.kubernetes.io/last-applied-configuration: {} f:spec: .: {} f:model: .: {} f:name: {} f:uri: {} f:replicas: {} f:router: .: {} f:gateway: .: {} f:refs: {} f:route: {} f:storageInitializer: .: {} f:enabled: {} f:template: .: {} f:containers: .: {} k:{"name":"main"}: .: {} f:args: {} f:command: {} f:env: .: {} k:{"name":"POD_IP"}: .: {} f:name: {} f:valueFrom: .: {} f:fieldRef: {} k:{"name":"POD_NAME"}: .: {} f:name: {} f:valueFrom: .: {} f:fieldRef: {} k:{"name":"POD_NAMESPACE"}: .: {} f:name: {} f:valueFrom: .: {} f:fieldRef: {} f:image: {} f:imagePullPolicy: {} f:livenessProbe: .: {} f:httpGet: .: {} f:path: {} f:port: {} f:scheme: {} f:name: {} f:ports: .: {} k:{"containerPort":8000,"protocol":"TCP"}: .: {} f:containerPort: {} f:name: {} f:protocol: {} f:readinessProbe: .: {} f:httpGet: .: {} f:path: {} f:port: {} f:scheme: {} manager: kubectl-client-side-apply operation: Update time: "2026-11-03T23:11:19Z" - apiVersion: serving.kserve.io/v1alpha2 fieldsType: FieldsV1 fieldsV1: f:metadata: f:finalizers: .: {} v:"serving.kserve.io/llmisvc-finalizer": {} manager: manager operation: Update time: "2026-11-03T23:11:31Z" - apiVersion: serving.kserve.io/v1alpha2 fieldsType: FieldsV1 fieldsV1: f:status: f:addresses: {} f:annotations: .: {} f:serving.kserve.io/accelerator-type: {} f:serving.kserve.io/config-llm-decode-template: {} f:serving.kserve.io/config-llm-decode-worker-data-parallel: {} f:serving.kserve.io/config-llm-prefill-template: {} f:serving.kserve.io/config-llm-prefill-worker-data-parallel: {} f:serving.kserve.io/config-llm-router-route: {} f:serving.kserve.io/config-llm-scheduler: {} f:serving.kserve.io/config-llm-scheduler-eppconfig-default: {} f:serving.kserve.io/config-llm-scheduler-eppconfig-default-pd: {} f:serving.kserve.io/config-llm-template: {} f:serving.kserve.io/config-llm-tokenizer: {} f:serving.kserve.io/config-llm-tracing: {} f:serving.kserve.io/config-llm-worker-data-parallel: {} f:serving.kserve.io/config-sglang-template: {} f:appliedConfigs: {} f:conditions: {} f:observedGeneration: {} f:router: .: {} f:gateways: {} f:url: {} f:workloads: .: {} f:primary: {} f:service: {} manager: manager operation: Update subresource: status time: "2026-11-03T23:11:44Z" name: premium-simulated-simulated-premium namespace: llm resourceVersion: "27476" uid: 60532b71-3423-4841-b2fe-00aeed2cd039 spec: model: name: facebook/opt-125m-premium uri: hf://placeholder/no-model replicas: 1 router: gateway: refs: - name: maas-default-gateway namespace: openshift-ingress route: {} storageInitializer: enabled: false template: containers: - args: - --port - "8000" - --model - facebook/opt-125m-premium - --mode - random - --no-mm-encoder-only - --ssl-certfile - /var/run/kserve/tls/tls.crt - --ssl-keyfile - /var/run/kserve/tls/tls.key command: - /app/llm-d-inference-sim env: - name: POD_NAME valueFrom: fieldRef: apiVersion: v1 fieldPath: metadata.name - name: POD_NAMESPACE valueFrom: fieldRef: apiVersion: v1 fieldPath: metadata.namespace - name: POD_IP valueFrom: fieldRef: apiVersion: v1 fieldPath: status.podIP image: ghcr.io/llm-d/llm-d-inference-sim:v0.8.2 imagePullPolicy: Always livenessProbe: httpGet: path: /health port: https scheme: HTTPS name: main ports: - containerPort: 8000 name: https protocol: TCP readinessProbe: httpGet: path: /ready port: https scheme: HTTPS resources: {} status: addresses: - models: - name: publishers/llm/models/facebook/opt-125m-premium name: gateway-internal-model-routing origin: group: gateway.networking.k8s.io kind: Gateway name: maas-default-gateway namespace: openshift-ingress url: https://maas-default-gateway-openshift-default.openshift-ingress.svc.cluster.local/ - models: - name: publishers/llm/models/facebook/opt-125m-premium - name: facebook/opt-125m-premium name: gateway-internal origin: group: gateway.networking.k8s.io kind: Gateway name: maas-default-gateway namespace: openshift-ingress url: https://maas-default-gateway-openshift-default.openshift-ingress.svc.cluster.local/llm/premium-simulated-simulated-premium - models: - name: publishers/llm/models/facebook/opt-125m-premium - name: facebook/opt-125m-premium name: gateway-internal origin: group: gateway.networking.k8s.io kind: Gateway name: maas-default-gateway namespace: openshift-ingress url: https://maas-default-gateway-openshift-default.openshift-ingress.svc.cluster.local/publishers/llm/models/facebook/opt-125m-premium - models: - name: publishers/llm/models/facebook/opt-125m-premium name: gateway-external-model-routing origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.a755049388262a210c0b.prod.konflux-ocp-ci.dev/ - models: - name: publishers/llm/models/facebook/opt-125m-premium - name: facebook/opt-125m-premium name: gateway-external origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.a755049388262a210c0b.prod.konflux-ocp-ci.dev/llm/premium-simulated-simulated-premium - models: - name: publishers/llm/models/facebook/opt-125m-premium - name: facebook/opt-125m-premium name: gateway-external origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.a755049388262a210c0b.prod.konflux-ocp-ci.dev/publishers/llm/models/facebook/opt-125m-premium annotations: serving.kserve.io/accelerator-type: cpu serving.kserve.io/config-llm-decode-template: v3-6-0-ea-2-kserve-config-llm-decode-template serving.kserve.io/config-llm-decode-worker-data-parallel: v3-6-0-ea-2-kserve-config-llm-decode-worker-data-parallel serving.kserve.io/config-llm-prefill-template: v3-6-0-ea-2-kserve-config-llm-prefill-template serving.kserve.io/config-llm-prefill-worker-data-parallel: v3-6-0-ea-2-kserve-config-llm-prefill-worker-data-parallel serving.kserve.io/config-llm-router-route: v3-6-0-ea-2-kserve-config-llm-router-route serving.kserve.io/config-llm-scheduler: v3-6-0-ea-2-kserve-config-llm-scheduler serving.kserve.io/config-llm-scheduler-eppconfig-default: v3-6-0-ea-2-kserve-config-llm-scheduler-eppconfig-default serving.kserve.io/config-llm-scheduler-eppconfig-default-pd: v3-6-0-ea-2-kserve-config-llm-scheduler-eppconfig-default-pd serving.kserve.io/config-llm-template: v3-6-0-ea-2-kserve-config-llm-template serving.kserve.io/config-llm-tokenizer: v3-6-0-ea-2-kserve-config-llm-tokenizer serving.kserve.io/config-llm-tracing: v3-6-0-ea-2-kserve-config-llm-tracing serving.kserve.io/config-llm-worker-data-parallel: v3-6-0-ea-2-kserve-config-llm-worker-data-parallel serving.kserve.io/config-sglang-template: v3-6-0-ea-2-kserve-config-sglang-template appliedConfigs: - name: v3-6-0-ea-2-kserve-config-llm-router-route namespace: opendatahub source: Preset - name: v3-6-0-ea-2-kserve-config-llm-template namespace: opendatahub source: Preset conditions: - lastTransitionTime: "2026-11-03T23:11:32Z" severity: Info status: "True" type: GatewaysReady - lastTransitionTime: "2026-11-03T23:11:42Z" severity: Info status: "True" type: HTTPRoutesReady - lastTransitionTime: "2026-11-03T23:11:44Z" severity: Info status: "True" type: MainWorkloadReady - lastTransitionTime: "2026-11-03T23:11:32Z" status: "True" type: PresetsCombined - lastTransitionTime: "2026-11-03T23:11:44Z" status: "True" type: Ready - lastTransitionTime: "2026-11-03T23:11:42Z" status: "True" type: RouterReady - lastTransitionTime: "2026-11-03T23:11:44Z" status: "True" type: WorkloadsReady observedGeneration: 1 router: gateways: - group: gateway.networking.k8s.io httpRoutes: - group: gateway.networking.k8s.io kind: HTTPRoute name: premium-simulated-simulated-premium-kserve-route namespace: llm kind: Gateway name: maas-default-gateway namespace: openshift-ingress url: https://maas.apps.a755049388262a210c0b.prod.konflux-ocp-ci.dev/llm/premium-simulated-simulated-premium workloads: primary: apiGroup: apps kind: Deployment name: premium-simulated-simulated-premium-kserve readyReplicas: 1 service: kind: Service name: premium-simulated-simulated-premium-kserve-workload-svc