apiVersion: ai-factory.suse.com/v1alpha1 kind: Blueprint metadata: name: arm64-ai-stack-0-0-6 spec: components: - chartName: gpu-operator chartRepo: nvidia chartVersion: v26.7.2 values: ccManager: defaultMode: "on" enabled: true hostNetwork: false image: k8s-cc-manager imagePullPolicy: IfNotPresent imagePullSecrets: [] repository: nvcr.io/nvidia/cloud-native resources: {} version: v0.4.4 cdi: enabled: true nriPluginEnabled: false clusterPolicy: deployCR: true daemonsets: annotations: {} labels: {} priorityClassName: system-node-critical rollingUpdate: maxUnavailable: "1" tolerations: - effect: NoSchedule key: nvidia.com/gpu operator: Exists updateStrategy: RollingUpdate dcgm: args: [] enabled: false env: [] hostNetwork: false image: dcgm imagePullPolicy: IfNotPresent repository: nvcr.io/nvidia/cloud-native resources: {} version: 4.6.1-1-ubuntu24.04 dcgmExporter: annotations: {} enablePodLabels: false enablePodUID: false enabled: true env: [] hostNetwork: false hostPID: false image: dcgm-exporter imagePullPolicy: IfNotPresent repository: nvcr.io/nvidia/k8s resources: {} service: internalTrafficPolicy: Cluster serviceMonitor: additionalLabels: {} enabled: true honorLabels: false interval: 15s relabelings: [] scrapeTimeout: 10s version: 4.6.1-4.8.4-distroless devicePlugin: args: [] config: create: false data: {} default: "" name: "" enabled: true env: [] hostNetwork: false image: k8s-device-plugin imagePullPolicy: IfNotPresent imagePullSecrets: [] mps: root: /run/nvidia/mps repository: nvcr.io/nvidia resources: {} version: v0.20.1 draDriver: computeDomains: controller: {} enabled: true kubeletPlugin: {} featureGates: {} gpus: kubeletPlugin: {} image: dra-driver-nvidia-gpu imagePullPolicy: IfNotPresent imagePullSecrets: [] repository: nvcr.io/nvidia version: v0.5.1 driver: certConfig: name: "" enabled: true env: [] hostNetwork: false image: driver imagePullPolicy: IfNotPresent imagePullSecrets: [] kernelModuleConfig: name: "" kernelModuleType: auto licensingConfig: nlsEnabled: true secretName: "" manager: env: [] image: k8s-driver-manager imagePullPolicy: IfNotPresent repository: nvcr.io/nvidia/cloud-native version: v0.12.1 nvidiaDriverCRD: deployDefaultCR: true driverType: gpu enabled: false nodeSelector: {} rdma: enabled: false useHostMofed: false repoConfig: configMapName: "" repository: registry.suse.com/third-party/nvidia resources: {} secretEnv: "" startupProbe: failureThreshold: 120 initialDelaySeconds: 60 periodSeconds: 10 timeoutSeconds: 60 upgradePolicy: autoUpgrade: true drain: deleteEmptyDir: false enable: false force: false podSelector: "" timeoutSeconds: 300 gpuPodDeletion: deleteEmptyDir: false force: false timeoutSeconds: 300 maxParallelUpgrades: 1 maxUnavailable: 25% waitForCompletion: podSelector: "" timeoutSeconds: 0 usePrecompiled: true version: "595" virtualTopology: config: "" extraObjects: [] gdrcopy: args: [] enabled: false env: [] image: gdrdrv imagePullPolicy: IfNotPresent imagePullSecrets: [] repository: nvcr.io/nvidia/cloud-native version: v2.6 gds: args: [] enabled: false env: [] image: nvidia-fs imagePullPolicy: IfNotPresent imagePullSecrets: [] repository: nvcr.io/nvidia/cloud-native version: 2.29.4 gfd: enabled: true env: [] hostNetwork: false image: k8s-device-plugin imagePullPolicy: IfNotPresent imagePullSecrets: [] repository: nvcr.io/nvidia resources: {} version: v0.20.1 gpuCluster: deployCR: false hostPaths: driverInstallDir: /run/nvidia/driver rootFS: / kataManager: config: {} enabled: false env: [] hostNetwork: false imagePullPolicy: IfNotPresent imagePullSecrets: [] resources: {} kataSandboxDevicePlugin: args: [] enabled: true env: [] hostNetwork: false image: nvidia-sandbox-device-plugin imagePullPolicy: IfNotPresent imagePullSecrets: [] repository: nvcr.io/nvidia/cloud-native resources: {} version: v0.0.5 mig: strategy: single migManager: config: create: false data: {} default: all-disabled name: "" enabled: true env: [] gpuClientsConfig: name: "" hostNetwork: false image: k8s-mig-manager imagePullPolicy: IfNotPresent imagePullSecrets: [] repository: nvcr.io/nvidia/cloud-native resources: {} version: v0.15.1 nfd: enabled: true nodefeaturerules: false node-feature-discovery: gc: enable: true replicaCount: 1 serviceAccount: create: false name: node-feature-discovery master: config: extraLabelNs: - nvidia.com serviceAccount: create: true name: node-feature-discovery priorityClassName: system-node-critical worker: config: sources: pci: deviceClassWhitelist: - "02" - "0200" - "0207" - "0300" - "0302" deviceLabelFields: - vendor serviceAccount: create: false name: node-feature-discovery tolerations: - effect: NoSchedule key: node-role.kubernetes.io/control-plane operator: Equal value: "" - effect: NoSchedule key: nvidia.com/gpu operator: Exists nodeStatusExporter: enabled: false hostNetwork: false image: gpu-operator imagePullPolicy: IfNotPresent imagePullSecrets: [] repository: nvcr.io/nvidia resources: {} operator: affinity: nodeAffinity: preferredDuringSchedulingIgnoredDuringExecution: - preference: matchExpressions: - key: node-role.kubernetes.io/control-plane operator: In values: - "" weight: 1 annotations: openshift.io/scc: restricted-readonly cleanupCRD: false env: [] image: gpu-operator imagePullPolicy: IfNotPresent imagePullSecrets: [] logging: develMode: false level: info timeEncoding: epoch nodeSelector: kubernetes.io/os: linux priorityClassName: system-node-critical repository: nvcr.io/nvidia resources: limits: cpu: 500m memory: 350Mi requests: cpu: 200m memory: 100Mi runtimeClass: nvidia tolerations: - effect: NoSchedule key: node-role.kubernetes.io/control-plane operator: Equal value: "" upgradeCRD: true use_ocp_driver_toolkit: false platform: openshift: false psa: enabled: false sandboxDevicePlugin: args: [] enabled: true env: [] hostNetwork: false image: kubevirt-gpu-device-plugin imagePullPolicy: IfNotPresent imagePullSecrets: [] repository: nvcr.io/nvidia resources: {} version: v1.6.0 sandboxWorkloads: defaultWorkload: container enabled: false mode: kubevirt toolkit: enabled: true env: - name: CONTAINERD_SOCKET value: /run/k3s/containerd/containerd.sock validator: args: [] env: [] hostNetwork: false image: gpu-operator imagePullPolicy: IfNotPresent imagePullSecrets: [] plugin: env: [] repository: nvcr.io/nvidia resources: {} vfioManager: driverManager: env: [] image: k8s-driver-manager imagePullPolicy: IfNotPresent repository: nvcr.io/nvidia/cloud-native version: v0.12.1 enabled: true env: [] hostNetwork: false image: k8s-driver-manager imagePullPolicy: IfNotPresent imagePullSecrets: [] repository: nvcr.io/nvidia/cloud-native resources: {} version: v0.12.1 vgpuDeviceManager: config: default: default name: "" enabled: true env: [] hostNetwork: false image: vgpu-device-manager imagePullPolicy: IfNotPresent imagePullSecrets: [] repository: nvcr.io/nvidia/cloud-native version: v0.5.1 vgpuManager: driverManager: env: [] image: k8s-driver-manager imagePullPolicy: IfNotPresent repository: nvcr.io/nvidia/cloud-native version: v0.12.1 enabled: false env: [] hostNetwork: false image: vgpu-manager imagePullPolicy: IfNotPresent imagePullSecrets: [] kernelModuleConfig: name: "" repository: "" resources: {} version: "" vendor: nvidia - chartName: network-operator chartRepo: nvidia chartVersion: 26.7.1 values: imagePullSecrets: [] keepNCP: true maintenance-operator-chart: operator: admissionController: certificates: certManager: enable: false generateSelfSigned: false custom: enable: false secretNames: operator: maintenance-webhook-cert enable: false image: name: maintenance-operator repository: nvcr.io/nvidia/mellanox tag: network-operator-v26.7.1 operatorConfig: deploy: false maintenanceOperator: enabled: false nfd: deployNodeFeatureRules: true enabled: false node-feature-discovery: enableNodeFeatureApi: true featureGates: NodeFeatureAPI: true gc: enable: true replicaCount: 1 serviceAccount: create: false name: node-feature-discovery image: pullPolicy: IfNotPresent repository: nvcr.io/nvidia/mellanox/node-feature-discovery tag: network-operator-v26.7.1 master: config: extraLabelNs: - nvidia.com serviceAccount: create: true name: node-feature-discovery postDeleteCleanup: false worker: config: sources: pci: deviceClassWhitelist: - "0300" - "0302" deviceLabelFields: - vendor serviceAccount: create: false name: node-feature-discovery tolerations: - effect: NoSchedule key: node-role.kubernetes.io/master operator: Exists - effect: NoSchedule key: node-role.kubernetes.io/control-plane operator: Exists - effect: NoSchedule key: nvidia.com/gpu operator: Exists operator: admissionController: enabled: false useCertManager: true affinity: nodeAffinity: preferredDuringSchedulingIgnoredDuringExecution: - preference: matchExpressions: - key: node-role.kubernetes.io/master operator: In values: - "" weight: 1 - preference: matchExpressions: - key: node-role.kubernetes.io/control-plane operator: In values: - "" weight: 1 cniBinDirectory: /opt/cni/bin cniNetworkDirectory: /etc/cni/net.d coverage: enabled: false fullnameOverride: "" image: network-operator maintenanceOperator: drainControllerRequestorID: nvidia.network-operator-drain-controller nodeMaintenanceNamePrefix: network-operator nodeMaintenanceNamespace: default requestorID: nvidia.doca-driver-upgrade useDrainControllerRequestor: false useRequestor: false nameOverride: "" nodeSelector: {} ofedDriver: initContainer: enable: true image: network-operator-init-container repository: nvcr.io/nvidia/mellanox version: network-operator-v26.7.1 preStopSleepSeconds: 25 priorityClassName: system-node-critical repository: nvcr.io/nvidia/cloud-native resources: limits: cpu: 500m memory: 128Mi requests: cpu: 5m memory: 64Mi terminationGracePeriodSeconds: 30 tolerations: - effect: NoSchedule key: node-role.kubernetes.io/master operator: Equal value: "" - effect: NoSchedule key: node-role.kubernetes.io/control-plane operator: Equal value: "" useDTK: true imagePullSecrets: - ngc-secret sriov-network-operator: images: ibSriovCni: nvcr.io/nvidia/mellanox/ib-sriov-cni:network-operator-v26.7.1 operator: nvcr.io/nvidia/mellanox/sriov-network-operator:network-operator-v26.7.1 ovsCni: nvcr.io/nvidia/mellanox/ovs-cni-plugin:network-operator-v26.7.1 rdmaCni: nvcr.io/nvidia/mellanox/rdma-cni:network-operator-v26.7.1 resourcesInjector: ghcr.io/k8snetworkplumbingwg/network-resources-injector:v1.7.0 sriovCni: nvcr.io/nvidia/mellanox/sriov-cni:network-operator-v26.7.1 sriovConfigDaemon: nvcr.io/nvidia/mellanox/sriov-network-operator-config-daemon:network-operator-v26.7.1 sriovDevicePlugin: nvcr.io/nvidia/mellanox/sriov-network-device-plugin:network-operator-v26.7.1 sriovDraDriver: nvcr.io/nvidia/mellanox/dra-driver-sriov:network-operator-v26.7.1 webhook: nvcr.io/nvidia/mellanox/sriov-network-operator-webhook:network-operator-v26.7.1 operator: admissionControllers: certificates: certManager: enabled: true generateSelfSigned: true custom: enabled: false secretNames: injector: network-resources-injector-cert operator: operator-webhook-cert enabled: false resourcePrefix: nvidia.com sriovOperatorConfig: configDaemonNodeSelector: beta.kubernetes.io/os: linux network.nvidia.com/operator.mofed.wait: "false" deploy: true sriovNetworkOperator: enabled: false test: pf: ens2f0 upgradeCRDs: true vendor: nvidia - chartName: vllm chartRepo: application-collection chartVersion: 0.1.10 values: servingEngineSpec: enableEngine: true modelSpec: - limitMemory: 20Gi modelURL: Qwen/Qwen2.5-3B-Instruct name: qwen2-5-3b-instruct pvcStorage: 20Gi replicaCount: 1 repository: vllm/vllm-openai requestCPU: 4 requestGPU: 1 requestMemory: 16Gi tag: latest vllmConfig: dtype: bfloat16 extraArgs: - --enable-auto-tool-choice - --tool-call-parser - hermes gpuMemoryUtilization: 0.85 maxModelLen: 8192 vendor: suse - chartName: open-webui chartRepo: application-collection chartVersion: 18.0.0 values: enableOpenaiApi: true extraEnvFrom: - secretRef: name: open-webui-admin-credentials openaiBaseApiUrl: http://vllm-router-service.arm64-ai-stack.svc.cluster.local/v1 service: type: NodePort vendor: suse description: Local Inference using Open-WebUI displayName: arm64 AI Stack source: Custom version: 0.0.6