Skip to navigation
Installation and ConfigurationInstallationGuided Installation (Recommended)Onboard a Tenant

Configuration Templates

View as Markdown

Use these templates to start with a complete tenant cluster config.yaml instead of building one from scratch. Choose the template that best matches your workload types and networking setup, then replace the example values with those prepared for that tenant.

TemplateUse this when
Full Cluster InstallationYou want every prerequisite and feature installed, covering both training and inference workloads.
Training InstallationThe tenant plans to run training workloads and does not need inference-specific features.
Inference InstallationThe tenant plans to run inference workloads and does not need training-specific features.
Gateway API InstallationThe tenant cluster uses Kubernetes Gateway API instead of an Ingress controller.
OpenShift InstallationYou are installing the tenant cluster on OpenShift.

Before You Use a Template

Complete Preparations before using a template. This includes completing the applicable System Requirements, registering the cluster, and having the required domain, TLS certificates, networking values, and registry credentials ready.

  • See Create a Tenant and Cluster to understand the minimum configuration needed before adapting a template.
  • See Prerequisites and Features to understand the components required, depending on the workload types that tenant plans to run - each template installs a fixed set of prerequisites and features, and depending on which one you choose, you may need to adjust versions or add customHelmValues for your environment (for example, an explicit CUDA driver version if you plan to use GPU fractions).
  • See Configuration Reference for the full set of supported fields and descriptions.

Full Cluster Installation

install:
  mode: runai_cluster_only
  connectivity: connected
registry:
  type: ngc
  tokenPath: /path/to/ngc-token # Support-Entitled Release only
cluster:
  enabled: true
  version: ""
  name: <CLUSTER_NAME>
  domain: <CLUSTER_DOMAIN>
  workloadRouting: host
  controlPlaneUrl: https://<CONTROL_PLANE_DOMAIN>
  uid: <CLUSTER_UUID>
  bootstrapTokenPath: /path/to/bootstrap-token
  tls:
    certPath: /path/to/cluster-cert.pem
    keyPath: /path/to/cluster-key.pem
  inference:
    wildcardDomain: "*.<INFERENCE_WILDCARD_DOMAIN>"
    wildcardTls:
      certPath: /path/to/inference-wildcard-cert.pem
      keyPath: /path/to/inference-wildcard-key.pem
  customHelmValues: {}
prerequisites:
  gpuOperator:
    mode: install
    version: ""
    customHelmValues: {}
  prometheus:
    mode: install
    version: ""
    customHelmValues: {}
  networkOperator:
    mode: install
    version: ""
    customHelmValues: {}
features:
  kubeflow:
    mode: install
    version: ""
  mpiOperator:
    mode: install
    version: ""
  knative:
    mode: install
    version: ""
    customHelmValues: {}
  lws:
    mode: install
    version: ""
    customHelmValues: {}
  nimOperator:
    mode: install
    version: ""
    customHelmValues: {}
  grove:
    mode: install
    version: ""
    customHelmValues: {}
  dynamo:
    mode: install
    version: ""
    customHelmValues: {}
externalConnection:
  type: ingress
  ingress:
    className: <YOUR_INGRESS_CLASS>

Training Installation

install:
  mode: runai_cluster_only
  connectivity: connected
registry:
  type: ngc
  tokenPath: /path/to/ngc-token # Support-Entitled Release only
cluster:
  enabled: true
  version: ""
  name: <CLUSTER_NAME>
  domain: <CLUSTER_DOMAIN>
  workloadRouting: host
  controlPlaneUrl: https://<CONTROL_PLANE_DOMAIN>
  uid: <CLUSTER_UUID>
  bootstrapTokenPath: /path/to/bootstrap-token
  tls:
    certPath: /path/to/cluster-cert.pem
    keyPath: /path/to/cluster-key.pem
  customHelmValues: {}
prerequisites:
  gpuOperator:
    mode: install
    version: ""
    customHelmValues: {}
  prometheus:
    mode: install
    version: ""
    customHelmValues: {}
features:
  kubeflow:
    mode: install
    version: ""
  mpiOperator:
    mode: install
    version: ""
externalConnection:
  type: ingress
  ingress:
    className: <YOUR_INGRESS_CLASS>

Inference Installation

install:
  mode: runai_cluster_only
  connectivity: connected
registry:
  type: ngc
  tokenPath: /path/to/ngc-token # Support-Entitled Release only
cluster:
  enabled: true
  version: ""
  name: <CLUSTER_NAME>
  domain: <CLUSTER_DOMAIN>
  workloadRouting: host
  controlPlaneUrl: https://<CONTROL_PLANE_DOMAIN>
  uid: <CLUSTER_UUID>
  bootstrapTokenPath: /path/to/bootstrap-token
  tls:
    certPath: /path/to/cluster-cert.pem
    keyPath: /path/to/cluster-key.pem
  inference:
    wildcardDomain: "*.<INFERENCE_WILDCARD_DOMAIN>"
    wildcardTls:
      certPath: /path/to/inference-wildcard-cert.pem
      keyPath: /path/to/inference-wildcard-key.pem
  customHelmValues: {}
prerequisites:
  gpuOperator:
    mode: install
    version: ""
    customHelmValues: {}
  prometheus:
    mode: install
    version: ""
    customHelmValues: {}
features:
  knative:
    mode: install
    version: ""
    customHelmValues: {}
  lws:
    mode: install
    version: ""
    customHelmValues: {}
  nimOperator:
    mode: install
    version: ""
    customHelmValues: {}
  grove:
    mode: install
    version: ""
    customHelmValues: {}
  dynamo:
    mode: install
    version: ""
    customHelmValues: {}
externalConnection:
  type: ingress
  ingress:
    className: <YOUR_INGRESS_CLASS>

Gateway API Installation

install:
  mode: runai_cluster_only
  connectivity: connected
registry:
  type: ngc
  tokenPath: /path/to/ngc-token # Support-Entitled Release only
cluster:
  enabled: true
  version: ""
  name: <CLUSTER_NAME>
  domain: <CLUSTER_DOMAIN>
  controlPlaneUrl: https://<CONTROL_PLANE_DOMAIN>
  uid: <CLUSTER_UUID>
  bootstrapTokenPath: /path/to/bootstrap-token
  tls:
    certPath: /path/to/cluster-cert.pem
    keyPath: /path/to/cluster-key.pem
  customHelmValues: {}
prerequisites:
  gpuOperator:
    mode: install
    version: ""
    customHelmValues: {}
  prometheus:
    mode: install
    version: ""
    customHelmValues: {}
externalConnection:
  type: gatewayApi
  gatewayApi:
    name: <GATEWAY_NAME>
    namespace: <GATEWAY_NAMESPACE>

OpenShift Installation

install:
  mode: runai_cluster_only
  connectivity: connected
  kubernetesDistribution: openshift
registry:
  type: ngc
  tokenPath: /path/to/ngc-token # Support-Entitled Release only
cluster:
  enabled: true
  version: ""
  name: <CLUSTER_NAME>
  domain: <CLUSTER_DOMAIN>
  controlPlaneUrl: https://<CONTROL_PLANE_DOMAIN>
  uid: <CLUSTER_UUID>
  bootstrapTokenPath: /path/to/bootstrap-token
  inference:
    wildcardDomain: "*.<INFERENCE_WILDCARD_DOMAIN>"
  customHelmValues: {}
prerequisites:
  skip: false
  gpuOperator:
    mode: install
    version: ""
  prometheus:
    mode: skip
  networkOperator:
    mode: install
    version: ""
features:
  skip: false
  kubeflow:
    mode: install
    version: ""
  mpiOperator:
    mode: install
    version: ""
  knative:
    mode: install
    version: ""
    customHelmValues: {}
  lws:
    mode: install
    version: ""
    customHelmValues: {}
  nimOperator:
    mode: install
    version: ""
    customHelmValues: {}
  grove:
    mode: install
    version: ""
    customHelmValues: {}
  dynamo:
    mode: install
    version: ""
    customHelmValues: {}