本地升級stable-diffusion diffuser docker CUDA11.7 RTX2060

1.0 前言

本地搭建stable-diffusion diffuser docker CUDA10.2 RTX2060

上次安裝的cuda10.2太舊了，升級cuda11.7順便填一下漏了的點。

2.0 卸載

sudo apt-get remove --purge '^nvidia-.*'
sudo apt-get remove --purge '^libnvidia-.*'
sudo apt-get remove --purge '^cuda-.*'
sudo apt-get remove --purge '^cudnn-.*'
sudo apt-get remove --purge '^libcudnn7-.*'
sudo apt-get remove --purge '^libcudnn7*'

　　卸載

2.1 檢查

dpkg -l | grep nvidia
dpkg -l | grep cuda
dpkg -l | grep cudnn

　　檢查是否已成功卸載

 

3.0 CUDA

https://developer.nvidia.com/cuda-10.2-download-archive?target_os=Linux&target_arch=x86_64&target_distro=Ubuntu&target_version=1804&target_type=deblocal

wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-ubuntu1804.pin
sudo mv cuda-ubuntu1804.pin /etc/apt/preferences.d/cuda-repository-pin-600
wget https://developer.download.nvidia.com/compute/cuda/11.7.0/local_installers/cuda-repo-ubuntu1804-11-7-local_11.7.0-515.43.04-1_amd64.deb
sudo dpkg -i cuda-repo-ubuntu1804-11-7-local_11.7.0-515.43.04-1_amd64.deb
sudo cp /var/cuda-repo-ubuntu1804-11-7-local/cuda-*-keyring.gpg /usr/share/keyrings/
sudo apt-get update
sudo apt-get -y install cuda

　　安裝CUDA

3.1 rmmod & lsof cuda

https://comzyh.com/blog/archives/967/

sudo rmmod nvidia_drm
sudo rmmod nvidia_modeset
sudo rmmod nvidia_uvm
sudo rmmod nvidia

　　重新restart服務器，或手動rmmod kernel mod

sudo lsof /dev/nvidia*

　　重新加載cuda

3.2 vncc

export PATH=/usr/local/cuda-11.7/bin${PATH:+:${PATH}}
export LD_LIBRARY_PATH=/usr/local/cuda/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}

　　 vncc動態鏈

3.4 檢查

nvidia-smi

　　

4.0 cudnn

sudo dpkg -i cudnn-local-repo-ubuntu1804-8.9.0.131_1.0-1_amd64.deb
sudo cp /var/cudnn-local-repo-*/cudnn-local-*-keyring.gpg /usr/share/keyrings/
sudo apt-get update
sudo apt-get install libcudnn8=8.9.0.131-1+cuda11.8
sudo apt-get install libcudnn8-dev=8.9.0.131-1+cuda11.8
sudo apt-get install libcudnn8-samples=8.9.0.131-1+cuda11.8

　　安裝cudnn

$cp -r /usr/src/cudnn_samples_v8/ $HOME
cd ~/cudnn_samples_v8/mnistCUDNN
make clean && make
./mnistCUDNN

　　測試cudnn

4.1 檢查

 

5.0 安裝libnvidia-container

https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#setting-up-nvidia-container-toolkit

distribution=$(. /etc/os-release;echo $ID$VERSION_ID) \
      && 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/experimental/$distribution/libnvidia-container.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 nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker

　　安裝libnvidia-container

 

6.0 docker部署

sudo docker build -t diffusers/cuda/v4:11.7-cudnn8-runtime-ubuntu18.04 .
sudo docker run --rm --runtime=nvidia --gpus all diffusers/cuda/v5:11.7-cudnn8-runtime-ubuntu18.04 nvidia-smi