curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add -
echo 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 # note that this always shows 18.04, which is ok.
# curl -s -L https://nvidia.github.io/nvidia-docker/ubuntu22.04/nvidia-docker.list > /etc/apt/sources.list.d/nvidia-docker.list # also gives 18.04 in text, also ok.

sudo apt-get update && \
sudo apt-get install -y nvidia-container-toolkit-base
sudo apt-get install -y nvidia-docker2 # adds runtime
sudo systemctl daemon-reload && \
sudo systemctl restart docker

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

cd ~/langchain-ChatGLM/models/
ln ~/path/to/THUDM/chatglm-6b/ .

docker build -f Dockerfile-cuda -t chatglm-cuda:latest .  # 20min with ~6MBps network

#若要使用离线模型，请配置好模型路径，然后此repo挂载到Container
docker run --gpus all -d --name im-chatglm -p 7860:7860 -v ~/langchain-ChatGLM:/chatGLM  chatglm-cuda:latest

# 若要使用在线模型：
#docker run --gpus all -d --name im-glm -p 7860:7860  chatglm-cuda:latest