Skip to main content

Intel CPU + NVIDIA GPU version - download and installation

Introduction

This download is primarily intended for users running a bare-metal version of Ubuntu on a PC with an Intel CPU and an NVIDIA GPU. The NVIDIA GPU will be used to accelerate the included analytics.

If you don't have an NVIDIA GPU, you should use the Intel CPU version.


​

Download

This preview release is only available as a .DEB installation file.

Download

Warning: This download is > 6.5GB
​
​

Pre-Installation - setting up your NVIDIA GPU

  1. You need to make sure you have the NVIDIA drivers installed:
    ​
    ​https://linuxconfig.org/how-to-install-nvidia-drivers-on-ubuntu-24-04
    ​

  2. If you successfully installed the NVIDIA driver, you should be able to run nvidia-smi. As of writing, this is CUDA Version 13.2.
    ​

    image-20260717-070716.png

  3. You also need to install the NVIDIA Docker runtime:
    ​
    ​Installing the NVIDIA Container Toolkit — NVIDIA Container Toolkit
    ​

  4. It is important to make nvidia the default runtime for docker. This is done by editing the /etc/docker/daemon.json:

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


    ...and restarting the service:

    # Restart Docker
    sudo systemctl restart docker

  5. You can check that your NVIDIA Docker runtime is working as expected by running the following command:

    docker run --rm nvidia/cuda:12.3.2-base-ubuntu22.04 nvidia-smi


    You should expect to see the normal nvidia-smi output.
    ​

Installation

This version will not work if you upgrade from an earlier version! It is also not upgradable, and should be uninstalled once testing is complete

  1. If you already have any version of EVVR Container installed, you must uninstall it:

    sudo apt remove --purge edgevis-encoder

  2. Install the current version of the DEB file (replacing XX with the version number in your downloaded file):

    sudo apt install ./edgevis-analytics_9.3.90-TCXX_amd64_gpu.deb

  3. The next step is to optimise the new analytics:

    sudo edgevis-encoder-analytics --prepare

  4. You can, if desired, customise your installation using configuration options in your container's compose file.
    ​

  5. Log in to your container's web interface using the usual mechanism.

Did this answer your question?