Skip to main content

Kubeflow


Installation#

  • Minimum system requirements
    • 4 CPU
    • 12 GB memory
    • 50 GB storage
warning

Kubeflow๋ฅผ HTTP๋กœ ๋…ธ์ถœํ•ด์•ผํ•˜๋Š” ๊ฒฝ์šฐ, ๊ด€๋ จ ์›น ์•ฑ์— ๋Œ€ํ•˜์—ฌ ํ™˜๊ฒฝ๋ณ€์ˆ˜ APP_SECURE_COOKIES๋ฅผ false๋กœ ์„ค์ •ํ•˜์—ฌ Secure Cookies feature๋ฅผ ๋น„ํ™œ์„ฑํ™” ํ•ด์•ผํ•ฉ๋‹ˆ๋‹ค.

kustomize#

wget https://github.com/kubernetes-sigs/kustomize/releases/download/v3.2.0/kustomize_3.2.0_linux_amd64 \&& sudo chmod 755 kustomize_3.2.0_linux_amd64 \&& sudo mv kustomize_3.2.0_linux_amd64 /usr/local/bin/kustomize

kubeflow#

git clone https://github.com/kubeflow/manifests.git

์›ํ•˜๋Š” ๋ฒ„์ „์œผ๋กœ checkout ํ•œ ํ›„, README.md ์ฐธ๊ณ 

Nvidia GPU node#

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
sudo apt-get update && sudo apt-get install -y nvidia-docker2
/etc/docker/daemon.json
{  ...  "default-runtime": "nvidia",  "runtimes": {    "nvidia": {      "path": "/usr/bin/nvidia-container-runtime",      "runtimeArgs": []    }  }}
sudo systemctl restart docker
kubectl apply -f https://raw.githubusercontent.com/NVIDIA/k8s-device-plugin/v0.9.0/nvidia-device-plugin.yml

Reference#