Skip to main content
Version: 2.12.1 (latest)

System requirements

Minimum system requirements​

Hardware​

CPURAMSSD/HDD
  • 6 cores (12 threads)
  • 2.8GHz
  • AVX/AVX2 support
6GB (when launching one instance of each service)
  • 30+ GB free space
  • 20%+ available space in the file system

Software​

  • Ubuntu 22.04
  • Docker 20.10.17
  • Kubernetes 1.23.8
  • Helm 3.10.2
  • Python 3.8.10
note

To install Docker, Kubernetes and Helm, use the command from para. Install Dependencies of Installation instructions (the Internet connection is required).

GPU requirements (optionally)​

Nvidia graphics card with CUDA 11.6 support.

System settings for GPU usage (optionally)​

Installing Nvidia Container Toolkit​

To install Nvidia Container Toolkit, run the commands below: 

distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
curl -s -L https://nvidia.github.io/libnvidia-container/gpgkey | sudo apt-key add -
curl -s -L https://nvidia.github.io/libnvidia-container/$distribution/libnvidia-container.list | sudo tee /etc/apt/sources.list.d/libnvidia-container.list

sudo apt-get update && sudo apt-get install -y nvidia-container-toolkit

Docker configuration​

To set nvidia-container-runtime as the default low-level runtime, add the following lines to the configuration file located at /etc/docker/daemon.json:

"default-runtime": "nvidia",
"runtimes": {
    "nvidia": {
        "path": "/usr/bin/nvidia-container-runtime",
        "runtimeArgs": []
    }
}

Applying configuration​

To apply configuration, restart docker-service using the command below:

$ sudo systemctl restart docker

Installation health check​

To check the installation validity, run the following command:

$ sudo docker run --rm --runtime=nvidia --gpus all nvidia/cuda:11.6.2-base-ubuntu20.04 nvidia-smi

As a result, the following output will be displayed in the terminal:

+-----------------------------------------------------------------------------+
| NVIDIA-SMI 525.78.01    Driver Version: 525.78.01    CUDA Version: 12.0     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  NVIDIA GeForce ...  Off  | 00000000:00:10.0 Off |                  N/A |
|  0%   27C    P8     9W / 280W |      6MiB / 11264MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
+-----------------------------------------------------------------------------+