docker部署

0,ubuntu下安装docker环境

    sudo apt-get remove -y docker docker-engine docker.io && sudo apt-get update && sudo apt-get install -y apt-transport-https ca-certificates curl software-properties-common && curl -fsSL 'https://download.docker.com/linux/ubuntu/gpg' | sudo apt-key add - && sudo add-apt-repository "deb [arch=amd64] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" && sudo apt-get update && sudo apt-get install -y docker-ce && sudo docker run hello-world && sudo docker volume ls -q -f driver=nvidia-docker | xargs -r -I{} -n1 docker ps -q -a -f volume={} | xargs -r docker rm -f && sudo apt-get purge -y nvidia-docker || true && curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add - && curl -s -L "https://nvidia.github.io/nvidia-docker/$(. /etc/os-release; echo $ID$VERSION_ID)/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 pkill -SIGKILL dockerd && sudo docker run --runtime=nvidia --rm nvidia/cuda:9.0-base nvidia-smi

 

1,下载docker-compose

curl -L https://get.daocloud.io/docker/compose/releases/download/v2.4.1/docker-compose-`uname -s`-`uname -m` > /usr/local/bin/docker-compose

 

2,安装；依赖

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
apt-get update
apt-get install nvidia-container-toolkit

3,启动规则

#version: ''
services:
  pytorch:
    image: pytorch/pytorch:1.13.0-cuda11.6-cudnn8-devel
    container_name: pytorch
    restart: always
    tty: true
    volumes:
      - ./work:/work
    deploy:
      resources:
        reservations:
          devices:
            - driver: "nvidia"
              count: "all"
              capabilities: ["gpu"]
    networks:
      - ai
networks:
  ai:
    external: true