机器学习筑基篇，容器调用显卡计算资源，Ubuntu 24.04 快速安装 NVIDIA Container Toolkit！

# 为 apt 获取 HTTPS 支持
apt install apt-transport-https curl

# 添加 NVIDIA 软件存储库
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

# 更新软件包列表
systemctl daemon-reload
sudo apt-get update

# 常规安装（由于是在github速度稍慢）
sudo apt-get install -y nvidia-container-toolkit

# 代理方式（科学上网）
sudo apt-get -o Acquire::http::proxy="http://10.10.10.12:10809/" install -y nvidia-container-toolkit

$ docker --version
  Docker version 27.0.3, build 7d4bcd8

$ containerd --version
  containerd containerd.io 1.7.18 ae71819c4f5e67bb4d5ae76a6b735f29cc25774e

# 使用 nvidia-ctk 命令修改主机上的 /etc/docker/daemon.json 文件
$ sudo nvidia-ctk runtime configure --runtime=docker
  # INFO[0000] Loading config from /etc/docker/daemon.json
  # INFO[0000] Wrote updated config to /etc/docker/daemon.json
  # INFO[0000] It is recommended that docker daemon be restarted.

# 新增配置：
"runtimes": {
  "nvidia": {
    "args": [],
    "path": "nvidia-container-runtime"
  }
},

# 服务重启
sudo systemctl daemon-reload
sudo systemctl restart containerd docker

# 验证运行时
docker info | grep "Runtimes"
  # Runtimes: io.containerd.runc.v2 nvidia runc

sudo docker run --rm --runtime=nvidia --gpus all ubuntu nvidia-smi