apiVersion: v1 items: - 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":"e2e-distinct-2-simulated","namespace":"llm"},"spec":{"model":{"name":"test/e2e-distinct-model-2","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","test/e2e-distinct-model-2","--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":{"limits":{"cpu":"500m","memory":"512Mi"},"requests":{"cpu":"100m","memory":"256Mi"}}}]}}} creationTimestamp: "2026-09-19T10:01:03Z" finalizers: - serving.kserve.io/llmisvc-finalizer generation: 1 name: e2e-distinct-2-simulated namespace: llm resourceVersion: "24101" uid: d0ffea42-d87d-4eb7-8e11-d7fdd4981407 spec: model: name: test/e2e-distinct-model-2 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 - test/e2e-distinct-model-2 - --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: limits: cpu: 500m memory: 512Mi requests: cpu: 100m memory: 256Mi status: addresses: - models: - name: publishers/llm/models/test/e2e-distinct-model-2 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/test/e2e-distinct-model-2 - name: test/e2e-distinct-model-2 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/e2e-distinct-2-simulated annotations: serving.kserve.io/config-llm-decode-template: v3-5-0-ea-2-kserve-config-llm-decode-template serving.kserve.io/config-llm-decode-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-decode-worker-data-parallel serving.kserve.io/config-llm-prefill-template: v3-5-0-ea-2-kserve-config-llm-prefill-template serving.kserve.io/config-llm-prefill-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-prefill-worker-data-parallel serving.kserve.io/config-llm-router-route: v3-5-0-ea-2-kserve-config-llm-router-route serving.kserve.io/config-llm-scheduler: v3-5-0-ea-2-kserve-config-llm-scheduler serving.kserve.io/config-llm-template: v3-5-0-ea-2-kserve-config-llm-template serving.kserve.io/config-llm-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-worker-data-parallel appliedConfigs: - name: v3-5-0-ea-2-kserve-config-llm-router-route namespace: opendatahub source: Preset - name: v3-5-0-ea-2-kserve-config-llm-template namespace: opendatahub source: Preset conditions: - lastTransitionTime: "2026-09-19T10:01:11Z" severity: Info status: "True" type: GatewaysReady - lastTransitionTime: "2026-09-19T10:01:11Z" severity: Info status: "True" type: HTTPRoutesReady - lastTransitionTime: "2026-09-19T10:02:07Z" severity: Info status: "True" type: MainWorkloadReady - lastTransitionTime: "2026-09-19T10:01:11Z" severity: Info status: "True" type: PresetsCombined - lastTransitionTime: "2026-09-19T10:02:07Z" status: "True" type: Ready - lastTransitionTime: "2026-09-19T10:01:11Z" status: "True" type: RouterReady - lastTransitionTime: "2026-09-19T10:02:07Z" status: "True" type: WorkloadsReady observedGeneration: 1 router: gateways: - group: gateway.networking.k8s.io httpRoutes: - group: gateway.networking.k8s.io kind: HTTPRoute name: e2e-distinct-2-simulated-kserve-route namespace: llm kind: Gateway name: maas-default-gateway namespace: openshift-ingress url: https://maas-default-gateway-openshift-default.openshift-ingress.svc.cluster.local/llm/e2e-distinct-2-simulated workloads: primary: apiGroup: apps kind: Deployment name: e2e-distinct-2-simulated-kserve service: kind: Service name: e2e-distinct-2-simulated-kserve-workload-svc - 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":"e2e-distinct-simulated","namespace":"llm"},"spec":{"model":{"name":"test/e2e-distinct-model","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","test/e2e-distinct-model","--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":{"limits":{"cpu":"500m","memory":"512Mi"},"requests":{"cpu":"100m","memory":"256Mi"}}}]}}} creationTimestamp: "2026-09-19T10:01:03Z" finalizers: - serving.kserve.io/llmisvc-finalizer generation: 1 name: e2e-distinct-simulated namespace: llm resourceVersion: "24159" uid: 96adef0b-d41e-4b0d-afa5-f95a5e400bf6 spec: model: name: test/e2e-distinct-model 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 - test/e2e-distinct-model - --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: limits: cpu: 500m memory: 512Mi requests: cpu: 100m memory: 256Mi status: addresses: - models: - name: publishers/llm/models/test/e2e-distinct-model 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/test/e2e-distinct-model - name: test/e2e-distinct-model 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/e2e-distinct-simulated annotations: serving.kserve.io/config-llm-decode-template: v3-5-0-ea-2-kserve-config-llm-decode-template serving.kserve.io/config-llm-decode-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-decode-worker-data-parallel serving.kserve.io/config-llm-prefill-template: v3-5-0-ea-2-kserve-config-llm-prefill-template serving.kserve.io/config-llm-prefill-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-prefill-worker-data-parallel serving.kserve.io/config-llm-router-route: v3-5-0-ea-2-kserve-config-llm-router-route serving.kserve.io/config-llm-scheduler: v3-5-0-ea-2-kserve-config-llm-scheduler serving.kserve.io/config-llm-template: v3-5-0-ea-2-kserve-config-llm-template serving.kserve.io/config-llm-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-worker-data-parallel appliedConfigs: - name: v3-5-0-ea-2-kserve-config-llm-router-route namespace: opendatahub source: Preset - name: v3-5-0-ea-2-kserve-config-llm-template namespace: opendatahub source: Preset conditions: - lastTransitionTime: "2026-09-19T10:01:20Z" severity: Info status: "True" type: GatewaysReady - lastTransitionTime: "2026-09-19T10:02:12Z" severity: Info status: "True" type: HTTPRoutesReady - lastTransitionTime: "2026-09-19T10:02:12Z" severity: Info status: "True" type: MainWorkloadReady - lastTransitionTime: "2026-09-19T10:01:20Z" severity: Info status: "True" type: PresetsCombined - lastTransitionTime: "2026-09-19T10:02:12Z" status: "True" type: Ready - lastTransitionTime: "2026-09-19T10:02:12Z" status: "True" type: RouterReady - lastTransitionTime: "2026-09-19T10:02:12Z" status: "True" type: WorkloadsReady observedGeneration: 1 router: gateways: - group: gateway.networking.k8s.io httpRoutes: - group: gateway.networking.k8s.io kind: HTTPRoute name: e2e-distinct-simulated-kserve-route namespace: llm kind: Gateway name: maas-default-gateway namespace: openshift-ingress url: https://maas-default-gateway-openshift-default.openshift-ingress.svc.cluster.local/llm/e2e-distinct-simulated workloads: primary: apiGroup: apps kind: Deployment name: e2e-distinct-simulated-kserve service: kind: Service name: e2e-distinct-simulated-kserve-workload-svc - 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":"e2e-embedding-simulated","namespace":"llm"},"spec":{"model":{"name":"test/e2e-embedding-model","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","test/e2e-embedding-model","--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":{"limits":{"cpu":"500m","memory":"512Mi"},"requests":{"cpu":"100m","memory":"256Mi"}}}]}}} creationTimestamp: "2026-09-19T10:01:03Z" finalizers: - serving.kserve.io/llmisvc-finalizer generation: 1 name: e2e-embedding-simulated namespace: llm resourceVersion: "24214" uid: 1589e61a-594c-4173-b241-2e04f54e73dd spec: model: name: test/e2e-embedding-model 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 - test/e2e-embedding-model - --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: limits: cpu: 500m memory: 512Mi requests: cpu: 100m memory: 256Mi status: addresses: - models: - name: publishers/llm/models/test/e2e-embedding-model 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/test/e2e-embedding-model - name: test/e2e-embedding-model 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/e2e-embedding-simulated annotations: serving.kserve.io/config-llm-decode-template: v3-5-0-ea-2-kserve-config-llm-decode-template serving.kserve.io/config-llm-decode-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-decode-worker-data-parallel serving.kserve.io/config-llm-prefill-template: v3-5-0-ea-2-kserve-config-llm-prefill-template serving.kserve.io/config-llm-prefill-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-prefill-worker-data-parallel serving.kserve.io/config-llm-router-route: v3-5-0-ea-2-kserve-config-llm-router-route serving.kserve.io/config-llm-scheduler: v3-5-0-ea-2-kserve-config-llm-scheduler serving.kserve.io/config-llm-template: v3-5-0-ea-2-kserve-config-llm-template serving.kserve.io/config-llm-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-worker-data-parallel appliedConfigs: - name: v3-5-0-ea-2-kserve-config-llm-router-route namespace: opendatahub source: Preset - name: v3-5-0-ea-2-kserve-config-llm-template namespace: opendatahub source: Preset conditions: - lastTransitionTime: "2026-09-19T10:01:25Z" severity: Info status: "True" type: GatewaysReady - lastTransitionTime: "2026-09-19T10:01:25Z" severity: Info status: "True" type: HTTPRoutesReady - lastTransitionTime: "2026-09-19T10:02:17Z" severity: Info status: "True" type: MainWorkloadReady - lastTransitionTime: "2026-09-19T10:01:25Z" severity: Info status: "True" type: PresetsCombined - lastTransitionTime: "2026-09-19T10:02:17Z" status: "True" type: Ready - lastTransitionTime: "2026-09-19T10:01:25Z" status: "True" type: RouterReady - lastTransitionTime: "2026-09-19T10:02:17Z" status: "True" type: WorkloadsReady observedGeneration: 1 router: gateways: - group: gateway.networking.k8s.io httpRoutes: - group: gateway.networking.k8s.io kind: HTTPRoute name: e2e-embedding-simulated-kserve-route namespace: llm kind: Gateway name: maas-default-gateway namespace: openshift-ingress url: https://maas-default-gateway-openshift-default.openshift-ingress.svc.cluster.local/llm/e2e-embedding-simulated workloads: primary: apiGroup: apps kind: Deployment name: e2e-embedding-simulated-kserve service: kind: Service name: e2e-embedding-simulated-kserve-workload-svc - 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":"e2e-trlp-test-simulated","namespace":"llm"},"spec":{"model":{"name":"test/e2e-trlp-test-model","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","test/e2e-trlp-test-model","--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":{"limits":{"cpu":"500m","memory":"512Mi"},"requests":{"cpu":"100m","memory":"256Mi"}}}]}}} creationTimestamp: "2026-09-19T10:01:03Z" finalizers: - serving.kserve.io/llmisvc-finalizer generation: 1 name: e2e-trlp-test-simulated namespace: llm resourceVersion: "24302" uid: 3e1f5319-6f27-4804-990e-2a8e29e22b65 spec: model: name: test/e2e-trlp-test-model 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 - test/e2e-trlp-test-model - --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: limits: cpu: 500m memory: 512Mi requests: cpu: 100m memory: 256Mi status: addresses: - models: - name: publishers/llm/models/test/e2e-trlp-test-model 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/test/e2e-trlp-test-model - name: test/e2e-trlp-test-model 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/e2e-trlp-test-simulated annotations: serving.kserve.io/config-llm-decode-template: v3-5-0-ea-2-kserve-config-llm-decode-template serving.kserve.io/config-llm-decode-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-decode-worker-data-parallel serving.kserve.io/config-llm-prefill-template: v3-5-0-ea-2-kserve-config-llm-prefill-template serving.kserve.io/config-llm-prefill-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-prefill-worker-data-parallel serving.kserve.io/config-llm-router-route: v3-5-0-ea-2-kserve-config-llm-router-route serving.kserve.io/config-llm-scheduler: v3-5-0-ea-2-kserve-config-llm-scheduler serving.kserve.io/config-llm-template: v3-5-0-ea-2-kserve-config-llm-template serving.kserve.io/config-llm-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-worker-data-parallel appliedConfigs: - name: v3-5-0-ea-2-kserve-config-llm-router-route namespace: opendatahub source: Preset - name: v3-5-0-ea-2-kserve-config-llm-template namespace: opendatahub source: Preset conditions: - lastTransitionTime: "2026-09-19T10:01:37Z" severity: Info status: "True" type: GatewaysReady - lastTransitionTime: "2026-09-19T10:01:37Z" severity: Info status: "True" type: HTTPRoutesReady - lastTransitionTime: "2026-09-19T10:02:26Z" severity: Info status: "True" type: MainWorkloadReady - lastTransitionTime: "2026-09-19T10:01:37Z" severity: Info status: "True" type: PresetsCombined - lastTransitionTime: "2026-09-19T10:02:26Z" status: "True" type: Ready - lastTransitionTime: "2026-09-19T10:01:37Z" status: "True" type: RouterReady - lastTransitionTime: "2026-09-19T10:02:26Z" status: "True" type: WorkloadsReady observedGeneration: 1 router: gateways: - group: gateway.networking.k8s.io httpRoutes: - group: gateway.networking.k8s.io kind: HTTPRoute name: e2e-trlp-test-simulated-kserve-route namespace: llm kind: Gateway name: maas-default-gateway namespace: openshift-ingress url: https://maas-default-gateway-openshift-default.openshift-ingress.svc.cluster.local/llm/e2e-trlp-test-simulated workloads: primary: apiGroup: apps kind: Deployment name: e2e-trlp-test-simulated-kserve service: kind: Service name: e2e-trlp-test-simulated-kserve-workload-svc - 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":"e2e-unconfigured-facebook-opt-125m-simulated","namespace":"llm"},"spec":{"model":{"name":"test/e2e-unconfigured-model","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","test/e2e-unconfigured-model","--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":{"limits":{"cpu":"500m","memory":"512Mi"},"requests":{"cpu":"100m","memory":"256Mi"}}}]}}} creationTimestamp: "2026-09-19T10:01:03Z" finalizers: - serving.kserve.io/llmisvc-finalizer generation: 1 name: e2e-unconfigured-facebook-opt-125m-simulated namespace: llm resourceVersion: "24380" uid: 08f3bfaf-69af-4f49-94db-c27537aa268a spec: model: name: test/e2e-unconfigured-model 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 - test/e2e-unconfigured-model - --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: limits: cpu: 500m memory: 512Mi requests: cpu: 100m memory: 256Mi status: addresses: - models: - name: publishers/llm/models/test/e2e-unconfigured-model 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/test/e2e-unconfigured-model - name: test/e2e-unconfigured-model 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/e2e-unconfigured-facebook-opt-125m-simulated annotations: serving.kserve.io/config-llm-decode-template: v3-5-0-ea-2-kserve-config-llm-decode-template serving.kserve.io/config-llm-decode-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-decode-worker-data-parallel serving.kserve.io/config-llm-prefill-template: v3-5-0-ea-2-kserve-config-llm-prefill-template serving.kserve.io/config-llm-prefill-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-prefill-worker-data-parallel serving.kserve.io/config-llm-router-route: v3-5-0-ea-2-kserve-config-llm-router-route serving.kserve.io/config-llm-scheduler: v3-5-0-ea-2-kserve-config-llm-scheduler serving.kserve.io/config-llm-template: v3-5-0-ea-2-kserve-config-llm-template serving.kserve.io/config-llm-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-worker-data-parallel appliedConfigs: - name: v3-5-0-ea-2-kserve-config-llm-router-route namespace: opendatahub source: Preset - name: v3-5-0-ea-2-kserve-config-llm-template namespace: opendatahub source: Preset conditions: - lastTransitionTime: "2026-09-19T10:01:43Z" severity: Info status: "True" type: GatewaysReady - lastTransitionTime: "2026-09-19T10:02:33Z" severity: Info status: "True" type: HTTPRoutesReady - lastTransitionTime: "2026-09-19T10:02:33Z" severity: Info status: "True" type: MainWorkloadReady - lastTransitionTime: "2026-09-19T10:01:43Z" severity: Info status: "True" type: PresetsCombined - lastTransitionTime: "2026-09-19T10:02:33Z" status: "True" type: Ready - lastTransitionTime: "2026-09-19T10:02:33Z" status: "True" type: RouterReady - lastTransitionTime: "2026-09-19T10:02:33Z" status: "True" type: WorkloadsReady observedGeneration: 1 router: gateways: - group: gateway.networking.k8s.io httpRoutes: - group: gateway.networking.k8s.io kind: HTTPRoute name: e2e-unconfigured-facebook-opt-125m-simulated-kserve-route namespace: llm kind: Gateway name: maas-default-gateway namespace: openshift-ingress url: https://maas-default-gateway-openshift-default.openshift-ingress.svc.cluster.local/llm/e2e-unconfigured-facebook-opt-125m-simulated workloads: primary: apiGroup: apps kind: Deployment name: e2e-unconfigured-facebook-opt-125m-simulated-kserve service: kind: Service name: e2e-unconfiab60ef4d3a239b5143b412cab04acac3-kserve-workload-svc - 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":"facebook-opt-125m-simulated","namespace":"llm"},"spec":{"model":{"name":"facebook/opt-125m","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","--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":{"limits":{"cpu":"500m","memory":"512Mi"},"requests":{"cpu":"100m","memory":"256Mi"}}}]}}} creationTimestamp: "2026-09-19T10:01:04Z" finalizers: - serving.kserve.io/llmisvc-finalizer generation: 1 name: facebook-opt-125m-simulated namespace: llm resourceVersion: "24480" uid: 87fad408-ea45-4974-bf8d-e8d10de85e49 spec: model: name: facebook/opt-125m 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 - --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: limits: cpu: 500m memory: 512Mi requests: cpu: 100m memory: 256Mi status: addresses: - models: - name: publishers/llm/models/facebook/opt-125m 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 - name: facebook/opt-125m 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/facebook-opt-125m-simulated annotations: serving.kserve.io/config-llm-decode-template: v3-5-0-ea-2-kserve-config-llm-decode-template serving.kserve.io/config-llm-decode-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-decode-worker-data-parallel serving.kserve.io/config-llm-prefill-template: v3-5-0-ea-2-kserve-config-llm-prefill-template serving.kserve.io/config-llm-prefill-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-prefill-worker-data-parallel serving.kserve.io/config-llm-router-route: v3-5-0-ea-2-kserve-config-llm-router-route serving.kserve.io/config-llm-scheduler: v3-5-0-ea-2-kserve-config-llm-scheduler serving.kserve.io/config-llm-template: v3-5-0-ea-2-kserve-config-llm-template serving.kserve.io/config-llm-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-worker-data-parallel appliedConfigs: - name: v3-5-0-ea-2-kserve-config-llm-router-route namespace: opendatahub source: Preset - name: v3-5-0-ea-2-kserve-config-llm-template namespace: opendatahub source: Preset conditions: - lastTransitionTime: "2026-09-19T10:01:52Z" severity: Info status: "True" type: GatewaysReady - lastTransitionTime: "2026-09-19T10:02:42Z" severity: Info status: "True" type: HTTPRoutesReady - lastTransitionTime: "2026-09-19T10:02:42Z" severity: Info status: "True" type: MainWorkloadReady - lastTransitionTime: "2026-09-19T10:01:52Z" severity: Info status: "True" type: PresetsCombined - lastTransitionTime: "2026-09-19T10:02:42Z" status: "True" type: Ready - lastTransitionTime: "2026-09-19T10:02:42Z" status: "True" type: RouterReady - lastTransitionTime: "2026-09-19T10:02:42Z" status: "True" type: WorkloadsReady observedGeneration: 1 router: gateways: - group: gateway.networking.k8s.io httpRoutes: - group: gateway.networking.k8s.io kind: HTTPRoute name: facebook-opt-125m-simulated-kserve-route namespace: llm kind: Gateway name: maas-default-gateway namespace: openshift-ingress url: https://maas-default-gateway-openshift-default.openshift-ingress.svc.cluster.local/llm/facebook-opt-125m-simulated workloads: primary: apiGroup: apps kind: Deployment name: facebook-opt-125m-simulated-kserve service: kind: Service name: facebook-opt-125m-simulated-kserve-workload-svc - 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: "2026-09-19T10:01:04Z" finalizers: - serving.kserve.io/llmisvc-finalizer generation: 1 name: premium-simulated-simulated-premium namespace: llm resourceVersion: "24540" uid: 13d80c29-ce94-44d5-9c15-f37a89802df1 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 annotations: serving.kserve.io/config-llm-decode-template: v3-5-0-ea-2-kserve-config-llm-decode-template serving.kserve.io/config-llm-decode-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-decode-worker-data-parallel serving.kserve.io/config-llm-prefill-template: v3-5-0-ea-2-kserve-config-llm-prefill-template serving.kserve.io/config-llm-prefill-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-prefill-worker-data-parallel serving.kserve.io/config-llm-router-route: v3-5-0-ea-2-kserve-config-llm-router-route serving.kserve.io/config-llm-scheduler: v3-5-0-ea-2-kserve-config-llm-scheduler serving.kserve.io/config-llm-template: v3-5-0-ea-2-kserve-config-llm-template serving.kserve.io/config-llm-worker-data-parallel: v3-5-0-ea-2-kserve-config-llm-worker-data-parallel appliedConfigs: - name: v3-5-0-ea-2-kserve-config-llm-router-route namespace: opendatahub source: Preset - name: v3-5-0-ea-2-kserve-config-llm-template namespace: opendatahub source: Preset conditions: - lastTransitionTime: "2026-09-19T10:02:01Z" severity: Info status: "True" type: GatewaysReady - lastTransitionTime: "2026-09-19T10:02:48Z" severity: Info status: "True" type: HTTPRoutesReady - lastTransitionTime: "2026-09-19T10:02:48Z" severity: Info status: "True" type: MainWorkloadReady - lastTransitionTime: "2026-09-19T10:02:01Z" severity: Info status: "True" type: PresetsCombined - lastTransitionTime: "2026-09-19T10:02:48Z" status: "True" type: Ready - lastTransitionTime: "2026-09-19T10:02:48Z" status: "True" type: RouterReady - lastTransitionTime: "2026-09-19T10:02:48Z" 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-default-gateway-openshift-default.openshift-ingress.svc.cluster.local/llm/premium-simulated-simulated-premium workloads: primary: apiGroup: apps kind: Deployment name: premium-simulated-simulated-premium-kserve service: kind: Service name: premium-simulated-simulated-premium-kserve-workload-svc kind: List metadata: resourceVersion: ""