快速安装 gpu operator(kind)

gistfile1.txt

参考
- https://docs.nvidia.com/datacenter/cloud-native/gpu-operator/latest/getting-started.html#operator-install-guide
- https://www.substratus.ai/blog/kind-with-gpus
- https://gist.github.com/yankay/aebce68e1a53f3086a5d1aac0dd67554

kubectl create ns gpu-operator
kubectl label --overwrite ns gpu-operator pod-security.kubernetes.io/enforce=privileged

helm repo add nvidia https://helm.ngc.nvidia.com/nvidia \
    && helm repo update

helm upgrade --install --wait gpu-operator \
    -n gpu-operator --create-namespace \
    nvidia/gpu-operator \
    --set driver.enabled=false \
    --set dcgm.repository=m.daocloud.io/nvcr.io/nvidia/cloud-native \
    --set validator.repository=m.daocloud.io/nvcr.io/nvidia/cloud-native \
    --set operator.repository=m.daocloud.io/nvcr.io/nvidia \
    --set operator.initContainer.repository=m.daocloud.io/nvcr.io/nvidia \
    --set driver.repository=m.daocloud.io/nvcr.io/nvidia \
    --set manager.repository=m.daocloud.io/nvcr.io/nvidia/cloud-native \
    --set toolkit.repository=m.daocloud.io/nvcr.io/nvidia/k8s \
    --set devicePlugin.repository=m.daocloud.io/nvcr.io/nvidia \
    --set dcgm.repository=m.daocloud.io/nvcr.io/nvidia/cloud-native \
    --set dcgmExporter.repository=m.daocloud.io/nvcr.io/nvidia/k8s \
    --set gfd.repository=m.daocloud.io/nvcr.io/nvidia \
    --set migManager.repository=m.daocloud.io/nvcr.io/nvidia/cloud-native \
    --set nodeStatusExporter.repository=m.daocloud.io/nvcr.io/nvidia/cloud-native \
    --set node-feature-discovery.image.repository=m.daocloud.io/registry.k8s.io/nfd/node-feature-discovery