Summary of All YAML Resources
The following manifests appear in this chapter:
Resource name |
Resource type |
Scope |
Purpose |
|---|---|---|---|
|
Namespace, OperatorGroup, Subscription |
|
Installs the LVM Storage Operator. |
|
LVMCluster |
|
Pools spare disks and creates the default dynamic |
|
Namespace, OperatorGroup, Subscription |
|
Installs the Local Storage Operator, as an alternative to LVM Storage. |
|
LocalVolumeDiscovery |
|
Discovers available local disks automatically. |
|
LocalVolume |
|
Provisions static persistent volumes from dedicated local disks. |
|
Namespace, OperatorGroup, Subscription |
|
Installs the Red Hat build of Kueue Operator, required for the |
|
Namespace, OperatorGroup, Subscription |
|
Installs the OpenShift AI Operator from the |
|
DSCInitialization ( |
Cluster-scoped |
Configures cluster-level RHOAI settings. Auto-created by the operator. |
|
DataScienceCluster ( |
Cluster-scoped |
Enables the required RHOAI components. |
|
HardwareProfile ( |
|
Exposes DRA-managed Intel GPUs to RHOAI workloads. |
|
HardwareProfile ( |
|
Exposes device-plugin Intel GPUs to RHOAI workloads. |
|
PersistentVolumeClaim |
User namespace |
Stores downloaded models on persistent storage. |
|
ServingRuntime |
User namespace |
Defines the Intel vLLM serving runtime with the XPU backend. |
|
InferenceService |
User namespace |
Deploys GPU-accelerated LLM inference in |
|
Service, Route |
User namespace |
Exposes the inference endpoint outside the cluster, because the KServe predictor service is headless. |
|
ResourceClaimTemplate |
User namespace |
Requests an Intel GPU through DRA on DRA-only clusters. |
|
Deployment, Service, Route |
User namespace |
Deploys vLLM with a DRA claim, for clusters without the device plugin. |
Note
Models are served through KServe RawDeployment and the dashboard is routed through a Gateway API Gateway, so this chapter installs neither OpenShift Serverless nor OpenShift Service Mesh and defines no KnativeServing or ServiceMeshControlPlane resource.