重裝 nvidia-docker2
apt-get remove docker docker-engine docker.io containerd runc
apt-get install apt-transport-https ca-certificates curl gnupg-agent software-properties-common
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo apt-key add -
add-apt-repository "deb [arch=amd64] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"
apt-get update
apt-get install docker-ce docker-ce-cli containerd.io
docker run hello-world
curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add -
distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
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 -y nvidia-docker2
pkill -SIGHUP dockerd
apt-get install nvidia-cuda-toolkit
nvcc --version
此時查看 nvidia-smi 提示驅動失敗
重裝 nvida-linux 驅動
cd /root/ && NVIDIA-Linux-x86_64-470.63.01.run -s -q
在容器內驗證 nvidia-smi
容器啓動的時候不帶 --gpus all 參數進入容器，，查看 nvidia-smi 失敗
docker run --runtime=nvidia --rm nvidia/cuda:9.1-base nvidia-smi
容器啓動的時候帶 --gpus all 參數進入容器，查看 nvidia-smi 成功
docker run --rm --gpus all nvidia/cuda:11.0.3-base-ubuntu18.04 nvidia-smi
cd /root/ && NVIDIA-Linux-x86_64-470.63.01.run -s -q
nvidia-smi