# AKSCluster Source: https://main.docs.modelplane.ai/reference/aksclusters/ An AKSCluster provisions an Azure Kubernetes Service cluster with a dedicated resource group, virtual network, and node pools for GPU inference and system workloads. It outputs a Secret containing the cluster kubeconfig that consumers use to target the cluster. The kubeconfig embeds a client certificate, so consumers need no separate cloud identity. Apply instances as `apiVersion: infrastructure.modelplane.ai/v1alpha1`, `kind: AKSCluster`. ## Example ```yaml apiVersion: infrastructure.modelplane.ai/v1alpha1 kind: AKSCluster metadata: name: inference-westeurope namespace: platform spec: location: westeurope kubernetesVersion: "1.34" nodePools: - name: system role: System vmSize: Standard_D8s_v5 nodeCount: 2 - name: gpuh100 role: GPU vmSize: Standard_ND96isr_H100_v5 diskSizeGb: 200 # GPU pools need at least one node: the AKS cluster autoscaler cannot # scale a pool whose GPUs bind through DRA up from zero. nodeCount: 1 minNodeCount: 1 maxNodeCount: 8 # The pool's VM Scale Set placement group lands its nodes on one # physical InfiniBand fabric. Requires the AKSInfinibandSupport # feature flag registered on the subscription. fabric: InfiniBand gpu: acceleratorType: nvidia-h100 ``` ## Definition The CompositeResourceDefinition this reference is generated from, with the complete OpenAPI schema, validation rules, and defaults: ```yaml apiVersion: apiextensions.crossplane.io/v2 kind: CompositeResourceDefinition metadata: name: aksclusters.infrastructure.modelplane.ai spec: group: infrastructure.modelplane.ai names: categories: - crossplane - modelplane kind: AKSCluster plural: aksclusters shortNames: - aks scope: Namespaced versions: - name: v1alpha1 referenceable: true additionalPrinterColumns: - name: LOCATION type: string jsonPath: .spec.location schema: openAPIV3Schema: description: >- An AKSCluster provisions an Azure Kubernetes Service cluster with a dedicated resource group, virtual network, and node pools for GPU inference and system workloads. It outputs a Secret containing the cluster kubeconfig that consumers use to target the cluster. The kubeconfig embeds a client certificate, so consumers need no separate cloud identity. properties: spec: description: AKSClusterSpec defines the desired state of AKSCluster. required: - location - nodePools properties: location: type: string description: >- Azure region for the cluster (e.g. westeurope, eastus2). minLength: 1 maxLength: 32 kubernetesVersion: type: string default: "1.34" description: >- AKS cluster Kubernetes version. Must be a version AKS currently supports. Defaults to a version where Dynamic Resource Allocation (how GPUs bind to pods) is generally available. minLength: 1 maxLength: 16 networking: type: object description: >- Virtual network configuration. Azure subnets span all Availability Zones in a region, so one subnet serves every node pool. Override when peering multiple clusters to avoid CIDR collisions. CIDRs must not overlap the cluster's service CIDR (10.96.0.0/16) or the overlay pod CIDR (10.244.0.0/16). properties: vnetCidr: type: string default: "10.0.0.0/16" description: Address space for the virtual network. maxLength: 18 subnetCidr: type: string default: "10.0.0.0/20" description: >- CIDR of the node subnet, carved from vnetCidr. maxLength: 18 nodePools: type: array description: >- Node pools for the cluster. At least one System pool is required for controllers and infrastructure workloads. minItems: 1 maxItems: 8 x-kubernetes-list-type: map x-kubernetes-list-map-keys: - name items: type: object required: - name - role - vmSize x-kubernetes-validations: - rule: "self.role != 'GPU' || has(self.gpu)" message: gpu is required when role is GPU. properties: name: type: string description: >- Unique name for this node pool, used as the AKS agent pool name. AKS restricts Linux pool names to at most 12 lowercase alphanumeric characters starting with a letter. pattern: "^[a-z][a-z0-9]{0,11}$" minLength: 1 maxLength: 12 role: type: string description: >- Determines what workloads this pool runs. System pools host controllers, gateways, and infrastructure. GPU pools host inference workloads and get the NVIDIA driver installed by AKS. enum: - System - GPU vmSize: type: string description: >- Azure VM size (e.g. Standard_D4s_v5, Standard_NC24ads_A100_v4, Standard_ND96isr_H100_v5). minLength: 1 maxLength: 63 diskSizeGb: type: integer default: 100 description: OS disk size in GB. minimum: 10 maximum: 65536 nodeCount: type: integer default: 1 description: Initial number of nodes. minimum: 0 maximum: 1000 minNodeCount: type: integer default: 0 description: >- Minimum number of nodes for autoscaling. Set it to 1 or higher for GPU pools: the AKS cluster autoscaler currently cannot scale a pool whose GPUs bind through DRA up from zero nodes, so a pod scheduled to an empty pool waits forever. minimum: 0 maximum: 1000 maxNodeCount: type: integer default: 8 description: Maximum number of nodes for autoscaling. minimum: 0 maximum: 1000 zones: type: array description: >- Availability Zones to restrict this pool to (e.g. ["1"]). Optional because many GPU VM sizes are not zonal. minItems: 1 maxItems: 3 items: type: string minLength: 1 maxLength: 8 gpu: type: object description: >- GPU configuration. Required when role is GPU. required: - acceleratorType properties: acceleratorType: type: string description: >- GPU accelerator type (e.g. nvidia-a100, nvidia-h100). Used to label GPU nodes; the actual GPU and count are determined by the VM size. minLength: 1 maxLength: 63 fabric: type: string default: None description: >- High-performance node-to-node fabric for multi-node engines. None uses standard VNet networking (TCP). InfiniBand relies on the pool's VM Scale Set placement group landing all nodes on one physical InfiniBand fabric. It requires the AKSInfinibandSupport feature flag on the subscription and an InfiniBand-capable VM size (e.g. Standard_ND96isr_H100_v5), and needs the NVIDIA network operator on the cluster to expose RDMA devices to pods, which Modelplane installs when any pool sets InfiniBand. enum: - None - InfiniBand type: object status: description: AKSClusterStatus defines the observed state of AKSCluster. properties: secrets: type: array description: >- Secrets produced by this cluster. Consumers use these to authenticate to the cluster. All secrets are in the same namespace as this AKSCluster. items: type: object required: - type - name - key properties: type: type: string description: >- The type of credential this secret contains. Kubeconfig contains a kubeconfig file with the cluster endpoint, CA certificate, and a client certificate for a cluster-admin local account. enum: - Kubeconfig name: type: string description: Name of the Secret. maxLength: 253 key: type: string description: >- Key within the Secret that holds the credential data. maxLength: 253 cache: type: object description: >- Observed ModelCache RWX storage state. properties: storageClassName: type: string description: >- Name of the Modelplane-managed ReadWriteMany StorageClass composed on this cluster for ModelCache PVCs. ModelCache reads this to target the cache PVC. maxLength: 253 type: object required: - spec type: object served: true ```