OpenShift AI workshop

openshift/node-feature-discovery-instance.yaml

@@ -0,0 +1,127 @@
+kind: NodeFeatureDiscovery
+apiVersion: nfd.openshift.io/v1
+metadata:
+  name: nfd-instance
+  namespace: openshift-nfd
+spec:
+  customConfig:
+    configData: |
+      #    - name: "more.kernel.features"
+      #      matchOn:
+      #      - loadedKMod: ["example_kmod3"]
+      #    - name: "more.features.by.nodename"
+      #      value: customValue
+      #      matchOn:
+      #      - nodename: ["special-.*-node-.*"]
+  operand:
+    image: >-
+      registry.redhat.io/openshift4/ose-node-feature-discovery@sha256:07658ef3df4b264b02396e67af813a52ba416b47ab6e1d2d08025a350ccd2b7b
+    servicePort: 12000
+  workerConfig:
+    configData: |
+      core:
+      #  labelWhiteList:
+      #  noPublish: false
+        sleepInterval: 60s
+      #  sources: [all]
+      #  klog:
+      #    addDirHeader: false
+      #    alsologtostderr: false
+      #    logBacktraceAt:
+      #    logtostderr: true
+      #    skipHeaders: false
+      #    stderrthreshold: 2
+      #    v: 0
+      #    vmodule:
+      ##   NOTE: the following options are not dynamically run-time
+      ##          configurable and require a nfd-worker restart to take effect
+      ##          after being changed
+      #    logDir:
+      #    logFile:
+      #    logFileMaxSize: 1800
+      #    skipLogHeaders: false
+      sources:
+      #  cpu:
+      #    cpuid:
+      ##     NOTE: attributeWhitelist has priority over attributeBlacklist
+      #      attributeBlacklist:
+      #        - "BMI1"
+      #        - "BMI2"
+      #        - "CLMUL"
+      #        - "CMOV"
+      #        - "CX16"
+      #        - "ERMS"
+      #        - "F16C"
+      #        - "HTT"
+      #        - "LZCNT"
+      #        - "MMX"
+      #        - "MMXEXT"
+      #        - "NX"
+      #        - "POPCNT"
+      #        - "RDRAND"
+      #        - "RDSEED"
+      #        - "RDTSCP"
+      #        - "SGX"
+      #        - "SSE"
+      #        - "SSE2"
+      #        - "SSE3"
+      #        - "SSE4.1"
+      #        - "SSE4.2"
+      #        - "SSSE3"
+      #      attributeWhitelist:
+      #  kernel:
+      #    kconfigFile: "/path/to/kconfig"
+      #    configOpts:
+      #      - "NO_HZ"
+      #      - "X86"
+      #      - "DMI"
+        pci:
+          deviceClassWhitelist:
+            - "0200"
+            - "03"
+            - "12"
+          deviceLabelFields:
+      #      - "class"
+            - "vendor"
+      #      - "device"
+      #      - "subsystem_vendor"
+      #      - "subsystem_device"
+      #  usb:
+      #    deviceClassWhitelist:
+      #      - "0e"
+      #      - "ef"
+      #      - "fe"
+      #      - "ff"
+      #    deviceLabelFields:
+      #      - "class"
+      #      - "vendor"
+      #      - "device"
+      #  custom:
+      #    - name: "my.kernel.feature"
+      #      matchOn:
+      #        - loadedKMod: ["example_kmod1", "example_kmod2"]
+      #    - name: "my.pci.feature"
+      #      matchOn:
+      #        - pciId:
+      #            class: ["0200"]
+      #            vendor: ["15b3"]
+      #            device: ["1014", "1017"]
+      #        - pciId :
+      #            vendor: ["8086"]
+      #            device: ["1000", "1100"]
+      #    - name: "my.usb.feature"
+      #      matchOn:
+      #        - usbId:
+      #          class: ["ff"]
+      #          vendor: ["03e7"]
+      #          device: ["2485"]
+      #        - usbId:
+      #          class: ["fe"]
+      #          vendor: ["1a6e"]
+      #          device: ["089a"]
+      #    - name: "my.combined.feature"
+      #      matchOn:
+      #        - pciId:
+      #            vendor: ["15b3"]
+      #            device: ["1014", "1017"]
+      #          loadedKMod : ["vendor_kmod1", "vendor_kmod2"]

openshift/node-feature-discovery-operator.yaml

@@ -0,0 +1,23 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: openshift-nfd
+---
+apiVersion: operators.coreos.com/v1
+kind: OperatorGroup
+metadata:
+  generateName: openshift-nfd-
+  name: openshift-nfd
+  namespace: openshift-nfd
+---
+apiVersion: operators.coreos.com/v1alpha1
+kind: Subscription
+metadata:
+  name: nfd
+  namespace: openshift-nfd
+spec:
+  channel: "stable"
+  installPlanApproval: Automatic
+  name: nfd
+  source: redhat-operators
+  sourceNamespace: openshift-marketplace

openshift/nvidia-cluster-config.yaml

@@ -0,0 +1,45 @@
+apiVersion: nvidia.com/v1
+kind: ClusterPolicy
+metadata:
+  name: gpu-cluster-policy
+spec:
+  migManager:
+    enabled: true
+  operator:
+    defaultRuntime: crio
+    initContainer: {}
+    runtimeClass: nvidia
+    deployGFD: true
+  dcgm:
+    enabled: true
+  gfd: {}
+  dcgmExporter:
+    config:
+      name: ''
+  driver:
+    licensingConfig:
+      nlsEnabled: false
+      configMapName: ''
+    certConfig:
+      name: ''
+    kernelModuleConfig:
+      name: ''
+    repoConfig:
+      configMapName: ''
+    virtualTopology:
+      config: ''
+    enabled: true
+    use_ocp_driver_toolkit: true
+  devicePlugin: {}
+  mig:
+    strategy: single
+  validator:
+    plugin:
+      env:
+        - name: WITH_WORKLOAD
+          value: 'true'
+  nodeStatusExporter:
+    enabled: true
+  daemonsets: {}
+  toolkit:
+    enabled: true

openshift/nvidia-gpu-operator.yaml

@@ -0,0 +1,26 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: nvidia-gpu-operator
+---
+apiVersion: operators.coreos.com/v1
+kind: OperatorGroup
+metadata:
+  name: nvidia-gpu-operator-group
+  namespace: nvidia-gpu-operator
+spec:
+ targetNamespaces:
+ - nvidia-gpu-operator
+---
+apiVersion: operators.coreos.com/v1alpha1
+kind: Subscription
+metadata:
+  name: gpu-operator-certified
+  namespace: nvidia-gpu-operator
+spec:
+  channel: "v23.3"
+  installPlanApproval: Automatic
+  name: gpu-operator-certified
+  source: certified-operators
+  sourceNamespace: openshift-marketplace
+  startingCSV: "gpu-operator-certified.v23.3.2"