在 Ubuntu 安裝 Nvidia Docker

sudo systemctl stop docker
sudo apt remove --purge -y docker-ce docker-ce-cli containerd.io
sudo rm -rf /var/lib/docker
sudo rm -rf /etc/docker
sudo rm -rf /etc/apt/sources.list.d/docker.list
sudo rm -rf /usr/share/keyrings/docker-archive-keyring.gpg
sudo apt update
docker --version

sudo apt update

sudo apt install -y \
    apt-transport-https \
    ca-certificates \
    curl \
    gnupg-agent \
    software-properties-common

curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg

echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null

sudo apt update
sudo apt install -y docker-ce docker-ce-cli containerd.io

# post install
sudo systemctl status docker
sudo usermod -aG docker ${USER}

sudo systemctl stop docker
sudo systemctl status docker

# ex: /data/ is another disk, don't create docker-data folder in advanced
sudo rsync -avxP /var/lib/docker/  /data/docker-data

# edit daemon.json with `data-root` line
sudo nano /etc/docker/daemon.json

{
    "data-root": "/data/docker-data",
    "runtimes": {
        "nvidia": {
            "args": [],
            "path": "nvidia-container-runtime"
        }
    }
}

sudo systemctl restart docker
sudo systemctl enable docker
# verify
docker info -f '{{ .DockerRootDir}}'

wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-ubuntu2204.pin
sudo mv cuda-ubuntu2204.pin /etc/apt/preferences.d/cuda-repository-pin-600
wget https://developer.download.nvidia.com/compute/cuda/12.2.2/local_installers/cuda-repo-ubuntu2204-12-2-local_12.2.2-535.104.05-1_amd64.deb
sudo dpkg -i cuda-repo-ubuntu2204-12-2-local_12.2.2-535.104.05-1_amd64.deb
sudo cp /var/cuda-repo-ubuntu2204-12-2-local/cuda-*-keyring.gpg /usr/share/keyrings/
sudo apt-get update
sudo apt-get -y install cuda

curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
  && curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
    sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
    sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list \
  && \
    sudo apt-get update

sudo apt-get install -y nvidia-container-toolkit

sudo systemctl restart docker


# verify
docker run --rm --gpus all nvidia/cuda:11.6.2-base-ubuntu20.04 nvidia-smi

# https://docs.docker.com/compose/install/
sudo curl -L "https://github.com/docker/compose/releases/download/1.29.2/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose

sudo chmod +x /usr/local/bin/docker-compose