---
apiVersion: serving.kserve.io/v1alpha2
kind: LLMInferenceServiceConfig
metadata:
  annotations:
    internal.config.kubernetes.io/previousKinds: LLMInferenceServiceConfig
    internal.config.kubernetes.io/previousNames: kserve-config-llm-multi-node-template-nvidia-cuda
    internal.config.kubernetes.io/previousNamespaces: opendatahub
    opendatahub.io/recommended-accelerators: '["nvidia.com/gpu"]'
    opendatahub.io/runtime-version: 0.11.0+rhai5
    opendatahub.io/supported-topologies: '["workload-multi-node-data-parallel"]'
    openshift.io/description: vLLM NVIDIA CUDA GPU LLMInferenceServiceConfig Multi
      Node for LLMInferenceService.
    openshift.io/display-name: vLLM NVIDIA CUDA GPU LLMInferenceServiceConfig Multi
      Node
    serving.kserve.io/well-known-config: "true"
  creationTimestamp: "2026-11-03T18:46:30Z"
  finalizers:
  - serving.kserve.io/llmisvcconfig-finalizer
  generation: 2
  labels:
    opendatahub.io/config-type: accelerator
    platform.opendatahub.io/part-of: kserve
  managedFields:
  - apiVersion: serving.kserve.io/v1alpha2
    fieldsType: FieldsV1
    fieldsV1:
      f:metadata:
        f:annotations:
          f:internal.config.kubernetes.io/previousKinds: {}
          f:internal.config.kubernetes.io/previousNames: {}
          f:internal.config.kubernetes.io/previousNamespaces: {}
          f:opendatahub.io/recommended-accelerators: {}
          f:opendatahub.io/runtime-version: {}
          f:opendatahub.io/supported-topologies: {}
          f:openshift.io/description: {}
          f:openshift.io/display-name: {}
          f:serving.kserve.io/well-known-config: {}
        f:labels:
          f:opendatahub.io/config-type: {}
          f:platform.opendatahub.io/part-of: {}
      f:spec:
        f:template:
          f:containers:
            k:{"name":"main"}:
              .: {}
              f:image: {}
              f:name: {}
        f:worker:
          f:containers:
            k:{"name":"main"}:
              .: {}
              f:image: {}
              f:name: {}
    manager: kserve-module-controller
    operation: Apply
    time: "2026-11-03T18:46:30Z"
  - apiVersion: serving.kserve.io/v1alpha2
    fieldsType: FieldsV1
    fieldsV1:
      f:metadata:
        f:finalizers:
          .: {}
          v:"serving.kserve.io/llmisvcconfig-finalizer": {}
      f:spec:
        f:model:
          .: {}
          f:uri: {}
        f:template:
          f:containers:
            k:{"name":"main"}:
              f:resources: {}
        f:worker:
          f:containers:
            k:{"name":"main"}:
              f:resources: {}
    manager: manager
    operation: Update
    time: "2026-11-03T18:46:30Z"
  - apiVersion: serving.kserve.io/v1alpha2
    fieldsType: FieldsV1
    fieldsV1:
      f:status:
        .: {}
        f:conditions: {}
        f:observedGeneration: {}
    manager: manager
    operation: Update
    subresource: status
    time: "2026-11-03T18:46:31Z"
  name: v3-6-0-ea-2-kserve-config-llm-multi-node-template-nvidia-cuda
  namespace: opendatahub
  resourceVersion: "18384"
  uid: bb9fca3d-6325-4f7c-ab39-3c263f1b99c3
spec:
  model:
    uri: ""
  template:
    containers:
    - image: registry.redhat.io/rhaiis/vllm-cuda-rhel9@sha256:fc68d623d1bfc36c8cb2fe4a71f19c8578cfb420ce8ce07b20a02c1ee0be0cf3
      name: main
      resources: {}
  worker:
    containers:
    - image: registry.redhat.io/rhaiis/vllm-cuda-rhel9@sha256:fc68d623d1bfc36c8cb2fe4a71f19c8578cfb420ce8ce07b20a02c1ee0be0cf3
      name: main
      resources: {}
status:
  conditions:
  - lastTransitionTime: "2026-11-03T18:46:31Z"
    message: not referenced by any LLMInferenceService
    reason: NotInUse
    severity: Info
    status: "False"
    type: ConfigInUse
  - lastTransitionTime: "2026-11-03T18:46:31Z"
    status: "True"
    type: Ready
  observedGeneration: 2