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: "2026-11-01T20:05:31Z" finalizers: - serving.kserve.io/llmisvc-finalizer generation: 1 name: e2e-distinct-2-simulated namespace: llm resourceVersion: "20925" uid: df3d1686-f0b9-42a2-8ca8-e79ba66c5b24 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 - 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/publishers/llm/models/test/e2e-distinct-model-2 - models: - name: publishers/llm/models/test/e2e-distinct-model-2 name: gateway-external-model-routing origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/ - models: - name: publishers/llm/models/test/e2e-distinct-model-2 - name: test/e2e-distinct-model-2 name: gateway-external origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/llm/e2e-distinct-2-simulated - models: - name: publishers/llm/models/test/e2e-distinct-model-2 - name: test/e2e-distinct-model-2 name: gateway-external origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/publishers/llm/models/test/e2e-distinct-model-2 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: "2026-11-01T20:05:34Z" severity: Info status: "True" type: GatewaysReady - lastTransitionTime: "2026-11-01T20:05:34Z" severity: Info status: "True" type: HTTPRoutesReady - lastTransitionTime: "2026-11-01T20:05:45Z" severity: Info status: "True" type: MainWorkloadReady - lastTransitionTime: "2026-11-01T20:05:34Z" status: "True" type: PresetsCombined - lastTransitionTime: "2026-11-01T20:05:45Z" status: "True" type: Ready - lastTransitionTime: "2026-11-01T20:05:34Z" status: "True" type: RouterReady - lastTransitionTime: "2026-11-01T20:05:45Z" 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.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/llm/e2e-distinct-2-simulated workloads: primary: apiGroup: apps kind: Deployment name: e2e-distinct-2-simulated-kserve readyReplicas: 1 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: "2026-11-01T20:05:31Z" finalizers: - serving.kserve.io/llmisvc-finalizer generation: 1 name: e2e-distinct-simulated namespace: llm resourceVersion: "20957" uid: b8b3ea2d-0105-43c9-afb2-9296d21f70ed 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 - 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/publishers/llm/models/test/e2e-distinct-model - models: - name: publishers/llm/models/test/e2e-distinct-model name: gateway-external-model-routing origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/ - models: - name: publishers/llm/models/test/e2e-distinct-model - name: test/e2e-distinct-model name: gateway-external origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/llm/e2e-distinct-simulated - models: - name: publishers/llm/models/test/e2e-distinct-model - name: test/e2e-distinct-model name: gateway-external origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/publishers/llm/models/test/e2e-distinct-model 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: "2026-11-01T20:05:35Z" severity: Info status: "True" type: GatewaysReady - lastTransitionTime: "2026-11-01T20:05:47Z" severity: Info status: "True" type: HTTPRoutesReady - lastTransitionTime: "2026-11-01T20:05:47Z" severity: Info status: "True" type: MainWorkloadReady - lastTransitionTime: "2026-11-01T20:05:35Z" status: "True" type: PresetsCombined - lastTransitionTime: "2026-11-01T20:05:47Z" status: "True" type: Ready - lastTransitionTime: "2026-11-01T20:05:47Z" status: "True" type: RouterReady - lastTransitionTime: "2026-11-01T20:05:47Z" 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.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/llm/e2e-distinct-simulated workloads: primary: apiGroup: apps kind: Deployment name: e2e-distinct-simulated-kserve readyReplicas: 1 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: "2026-11-01T20:05:32Z" finalizers: - serving.kserve.io/llmisvc-finalizer generation: 1 name: e2e-embedding-simulated namespace: llm resourceVersion: "20971" uid: 35e5696c-d477-40ee-b1ae-6dbb41b50033 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 - 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/publishers/llm/models/test/e2e-embedding-model - models: - name: publishers/llm/models/test/e2e-embedding-model name: gateway-external-model-routing origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/ - models: - name: publishers/llm/models/test/e2e-embedding-model - name: test/e2e-embedding-model name: gateway-external origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/llm/e2e-embedding-simulated - models: - name: publishers/llm/models/test/e2e-embedding-model - name: test/e2e-embedding-model name: gateway-external origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/publishers/llm/models/test/e2e-embedding-model 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: "2026-11-01T20:05:36Z" severity: Info status: "True" type: GatewaysReady - lastTransitionTime: "2026-11-01T20:05:48Z" severity: Info status: "True" type: HTTPRoutesReady - lastTransitionTime: "2026-11-01T20:05:48Z" severity: Info status: "True" type: MainWorkloadReady - lastTransitionTime: "2026-11-01T20:05:36Z" status: "True" type: PresetsCombined - lastTransitionTime: "2026-11-01T20:05:48Z" status: "True" type: Ready - lastTransitionTime: "2026-11-01T20:05:48Z" status: "True" type: RouterReady - lastTransitionTime: "2026-11-01T20:05:48Z" 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.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/llm/e2e-embedding-simulated workloads: primary: apiGroup: apps kind: Deployment name: e2e-embedding-simulated-kserve readyReplicas: 1 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: "2026-11-01T20:05:32Z" finalizers: - serving.kserve.io/llmisvc-finalizer generation: 1 name: e2e-trlp-test-simulated namespace: llm resourceVersion: "20988" uid: d76672b4-ddcd-40db-aec2-393123ef438a 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 - 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/publishers/llm/models/test/e2e-trlp-test-model - models: - name: publishers/llm/models/test/e2e-trlp-test-model name: gateway-external-model-routing origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/ - models: - name: publishers/llm/models/test/e2e-trlp-test-model - name: test/e2e-trlp-test-model name: gateway-external origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/llm/e2e-trlp-test-simulated - models: - name: publishers/llm/models/test/e2e-trlp-test-model - name: test/e2e-trlp-test-model name: gateway-external origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/publishers/llm/models/test/e2e-trlp-test-model 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: "2026-11-01T20:05:38Z" severity: Info status: "True" type: GatewaysReady - lastTransitionTime: "2026-11-01T20:05:49Z" severity: Info status: "True" type: HTTPRoutesReady - lastTransitionTime: "2026-11-01T20:05:49Z" severity: Info status: "True" type: MainWorkloadReady - lastTransitionTime: "2026-11-01T20:05:38Z" status: "True" type: PresetsCombined - lastTransitionTime: "2026-11-01T20:05:49Z" status: "True" type: Ready - lastTransitionTime: "2026-11-01T20:05:49Z" status: "True" type: RouterReady - lastTransitionTime: "2026-11-01T20:05:49Z" 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.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/llm/e2e-trlp-test-simulated workloads: primary: apiGroup: apps kind: Deployment name: e2e-trlp-test-simulated-kserve readyReplicas: 1 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: "2026-11-01T20:05:32Z" finalizers: - serving.kserve.io/llmisvc-finalizer generation: 1 name: e2e-unconfigured-facebook-opt-125m-simulated namespace: llm resourceVersion: "21088" uid: c2b84c1e-5901-4bb3-8bca-cbd5506f8ec4 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 - 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/publishers/llm/models/test/e2e-unconfigured-model - models: - name: publishers/llm/models/test/e2e-unconfigured-model name: gateway-external-model-routing origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/ - models: - name: publishers/llm/models/test/e2e-unconfigured-model - name: test/e2e-unconfigured-model name: gateway-external origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/llm/e2e-unconfigured-facebook-opt-125m-simulated - models: - name: publishers/llm/models/test/e2e-unconfigured-model - name: test/e2e-unconfigured-model name: gateway-external origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/publishers/llm/models/test/e2e-unconfigured-model 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: "2026-11-01T20:05:39Z" severity: Info status: "True" type: GatewaysReady - lastTransitionTime: "2026-11-01T20:05:50Z" severity: Info status: "True" type: HTTPRoutesReady - lastTransitionTime: "2026-11-01T20:05:54Z" severity: Info status: "True" type: MainWorkloadReady - lastTransitionTime: "2026-11-01T20:05:39Z" status: "True" type: PresetsCombined - lastTransitionTime: "2026-11-01T20:05:54Z" status: "True" type: Ready - lastTransitionTime: "2026-11-01T20:05:50Z" status: "True" type: RouterReady - lastTransitionTime: "2026-11-01T20:05:54Z" 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.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/llm/e2e-unconfigured-facebook-opt-125m-simulated workloads: primary: apiGroup: apps kind: Deployment name: e2e-unconfigured-facebook-opt-125m-simulated-kserve readyReplicas: 1 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":"echo-simulator","namespace":"llm"},"spec":{"model":{"name":"test/e2e-echo-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-echo-model","--mode","echo","--max-model-len","131072","--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:v0.9.0","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: "2026-11-01T20:05:32Z" finalizers: - serving.kserve.io/llmisvc-finalizer generation: 1 name: echo-simulator namespace: llm resourceVersion: "21093" uid: 194bdd64-357a-4e7e-942f-4af4e5d5a12f spec: model: name: test/e2e-echo-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-echo-model - --mode - echo - --max-model-len - "131072" - --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:v0.9.0 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-echo-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-echo-model - name: test/e2e-echo-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/echo-simulator - models: - name: publishers/llm/models/test/e2e-echo-model - name: test/e2e-echo-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/publishers/llm/models/test/e2e-echo-model - models: - name: publishers/llm/models/test/e2e-echo-model name: gateway-external-model-routing origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/ - models: - name: publishers/llm/models/test/e2e-echo-model - name: test/e2e-echo-model name: gateway-external origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/llm/echo-simulator - models: - name: publishers/llm/models/test/e2e-echo-model - name: test/e2e-echo-model name: gateway-external origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/publishers/llm/models/test/e2e-echo-model 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: "2026-11-01T20:05:40Z" severity: Info status: "True" type: GatewaysReady - lastTransitionTime: "2026-11-01T20:05:51Z" severity: Info status: "True" type: HTTPRoutesReady - lastTransitionTime: "2026-11-01T20:05:54Z" severity: Info status: "True" type: MainWorkloadReady - lastTransitionTime: "2026-11-01T20:05:40Z" status: "True" type: PresetsCombined - lastTransitionTime: "2026-11-01T20:05:54Z" status: "True" type: Ready - lastTransitionTime: "2026-11-01T20:05:51Z" status: "True" type: RouterReady - lastTransitionTime: "2026-11-01T20:05:54Z" status: "True" type: WorkloadsReady observedGeneration: 1 router: gateways: - group: gateway.networking.k8s.io httpRoutes: - group: gateway.networking.k8s.io kind: HTTPRoute name: echo-simulator-kserve-route namespace: llm kind: Gateway name: maas-default-gateway namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/llm/echo-simulator workloads: primary: apiGroup: apps kind: Deployment name: echo-simulator-kserve readyReplicas: 1 service: kind: Service name: echo-simulator-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: "2026-11-01T20:05:32Z" finalizers: - serving.kserve.io/llmisvc-finalizer generation: 1 name: facebook-opt-125m-simulated namespace: llm resourceVersion: "21054" uid: d2c5fdf7-3553-4c12-982e-fabfddc8fd9c 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 - 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/publishers/llm/models/facebook/opt-125m - models: - name: publishers/llm/models/facebook/opt-125m name: gateway-external-model-routing origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/ - models: - name: publishers/llm/models/facebook/opt-125m - name: facebook/opt-125m name: gateway-external origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/llm/facebook-opt-125m-simulated - models: - name: publishers/llm/models/facebook/opt-125m - name: facebook/opt-125m name: gateway-external origin: group: route.openshift.io kind: Route name: maas-gateway-route namespace: openshift-ingress url: https://maas.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/publishers/llm/models/facebook/opt-125m 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: "2026-11-01T20:05:41Z" severity: Info status: "True" type: GatewaysReady - lastTransitionTime: "2026-11-01T20:05:52Z" severity: Info status: "True" type: HTTPRoutesReady - lastTransitionTime: "2026-11-01T20:05:52Z" severity: Info status: "True" type: MainWorkloadReady - lastTransitionTime: "2026-11-01T20:05:41Z" status: "True" type: PresetsCombined - lastTransitionTime: "2026-11-01T20:05:52Z" status: "True" type: Ready - lastTransitionTime: "2026-11-01T20:05:52Z" status: "True" type: RouterReady - lastTransitionTime: "2026-11-01T20:05:52Z" 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.apps.4ec91afccb26205cb961.prod.konflux-ocp-ci.dev/llm/facebook-opt-125m-simulated workloads: primary: apiGroup: apps kind: Deployment name: facebook-opt-125m-simulated-kserve readyReplicas: 1 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: "2026-11-01T20:05:32Z" finalizers: - serving.kserve.io/llmisvc-finalizer generation: 1 name: premium-simulated-simulated-premium namespace: llm resourceVersion: "77147" uid: e7b79aa5-e394-4730-b5c4-0021b918cc1f 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.4ec91afccb26205cb961.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.4ec91afccb26205cb961.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.4ec91afccb26205cb961.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: "2026-11-01T20:05:42Z" severity: Info status: "True" type: GatewaysReady - lastTransitionTime: "2026-11-01T20:05:53Z" severity: Info status: "True" type: HTTPRoutesReady - lastTransitionTime: "2026-11-01T20:20:30Z" severity: Info status: "True" type: MainWorkloadReady - lastTransitionTime: "2026-11-01T20:05:42Z" status: "True" type: PresetsCombined - lastTransitionTime: "2026-11-01T20:20:30Z" status: "True" type: Ready - lastTransitionTime: "2026-11-01T20:05:53Z" status: "True" type: RouterReady - lastTransitionTime: "2026-11-01T20:20:30Z" 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.4ec91afccb26205cb961.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 kind: List metadata: resourceVersion: ""