在Kubernetes环境下使用Docker实现GPU支持的完整方案

distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add -
curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list
sudo apt-get update
sudo apt-get install -y nvidia-docker2

sudo nano /etc/docker/daemon.json

{
  "default-runtime": "nvidia",
  "runtimes": {
    "nvidia": {
      "path": "nvidia-container-runtime",
      "runtimeArgs": []
    }
  }
}

sudo systemctl restart docker

sudo docker run --rm --gpus all nvidia/12.8.1-cudnn-devel-ubuntu22.04 nvidia-smi

kubectl apply -f https://raw.githubusercontent.com/NVIDIA/k8s-device-plugin/v0.14.1/nvidia-device-plugin.yml

apiVersion: v1
kind: Pod
metadata:
  name: gpu-test
spec:
  containers:
  - name: cuda
    image: nvidia/cuda:12.8.1-base
    resources:
      limits:
        nvidia.com/gpu: 1
    command: ["nvidia-smi"]

kubectl apply -f gpu-pod.yaml
kubectl logs gpu-test