--- apiVersion: serving.kserve.io/v1alpha2 kind: LLMInferenceServiceConfig metadata: annotations: internal.config.kubernetes.io/previousKinds: LLMInferenceServiceConfig internal.config.kubernetes.io/previousNames: kserve-config-llm-template-cpu internal.config.kubernetes.io/previousNamespaces: opendatahub opendatahub.io/recommended-accelerators: '[]' opendatahub.io/runtime-version: 0.18.0+rhaiv.11 opendatahub.io/supported-topologies: '["workload-single-node"]' openshift.io/description: vLLM CPU LLMInferenceServiceConfig for LLMInferenceService on x86_64 CPU-only nodes. openshift.io/display-name: vLLM CPU LLMInferenceServiceConfig serving.kserve.io/well-known-config: "true" creationTimestamp: "2026-10-30T21:35:21Z" 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:env: k:{"name":"OMP_NUM_THREADS"}: .: {} f:name: {} f:value: {} k:{"name":"VLLM_CPU_KVCACHE_SPACE"}: .: {} f:name: {} f:value: {} f:image: {} f:name: {} f:nodeSelector: {} manager: kserve-module-controller operation: Apply time: "2026-10-30T21:35:21Z" - 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: {} manager: manager operation: Update time: "2026-10-30T21:35:22Z" - apiVersion: serving.kserve.io/v1alpha2 fieldsType: FieldsV1 fieldsV1: f:status: .: {} f:conditions: {} f:observedGeneration: {} manager: manager operation: Update subresource: status time: "2026-10-30T21:35:22Z" name: v3-6-0-ea-2-kserve-config-llm-template-cpu namespace: opendatahub resourceVersion: "18431" uid: a25f80b3-4ae9-41c6-82f7-be666e624eb6 spec: model: uri: "" template: containers: - env: - name: VLLM_CPU_KVCACHE_SPACE value: "4" - name: OMP_NUM_THREADS value: "4" image: registry.redhat.io/rhaii/vllm-cpu-rhel9@sha256:0ec0f5ff9a5ff263f58db0cfb19e3d7eef24b94c2d8629fe5145f5a8747e28c9 name: main resources: {} nodeSelector: kubernetes.io/arch: amd64 status: conditions: - lastTransitionTime: "2026-10-30T21:35:22Z" message: not referenced by any LLMInferenceService reason: NotInUse severity: Info status: "False" type: ConfigInUse - lastTransitionTime: "2026-10-30T21:35:22Z" status: "True" type: Ready observedGeneration: 2