Skip to main content

Environments

Cordatus Platform offers access to popular state-of-the-art Deep Learning and Machine Learning frameworks without the need for additional installations. It provides access to both NVIDIA NGC Containers and Cordatus Containers, all containerized and highly optimized for various use cases.

With Cordatus, you can quickly establish your own AI cloud, enabling seamless model training and development remotely within minutes, eliminating the challenges of dealing with dependency installations.

warning

Training models on the NVIDIA Jetson platform may lead to overheating and damage the Jetson module. It is advisable to use NVIDIA RTX Workstations for model training to ensure optimal performance and prevent potential damage to the Jetson module.

Supported Environments​

Cordatus currently supports following development environments:

  • Python
  • OpenCV
  • PyTorch
  • TensorFlow
  • ONNX
  • TensorRT
  • Torchvision
  • Caffe
  • Chainer
  • CUDA
  • cuDNN
  • Dali
  • DLib
  • MS CNTK
  • MXNet

Start an Environment​

Accessing from the Menu​

  1. From the left-side menu, click Containers.
  2. In the dropdown list, select Environments.
  3. Find your preferred environment and click the List Environments button.
  4. Click the Details button below the version you want to use.
    • Some environments have different versions for different hardware configurations.
    • Specific distributions may be available, optimized for certain hardware (e.g., L4T versions for NVIDIA Jetson devices).
Start an Environment

 

note

The video demonstrates launching an LLM Engine, which requires model selection during the setup process. When starting a standard Development Environment, there is no model selection step. All other configuration steps remain the same.

Advanced Settings​

Environment Name:
You can assign a custom name to your environment container.
If left blank, Cordatus automatically generates a name.

Select GPU:
Choose which GPUs the environment container can access.

  • Selecting All GPU grants access to all GPUs on your device.
  • At least one GPU must be selected to proceed.
  • If the device has multiple GPUs, you can isolate them at the environment level.

Resource Limits:
Control how much CPU and RAM your environment container can use.
The Resource Limits section allows you to optimize container performance and manage system resources efficiently.

💡 Recommendation: For optimal performance and system stability, it is recommended to maintain the Host Reserved values automatically set by Cordatus when allocating resources.

Docker Options:

The Docker Options section allows you to configure classic docker run parameters through Cordatus’s intuitive interface — without manually writing terminal commands.

  • On the left, under Choose Options, you can add or modify Docker run parameters such as:
    --volume, --network, --env, --restart, --device, and others.
  • Cordatus provides a clear graphical interface to simplify configuration and ensure proper parameter formatting.

Port Mapping​

Cordatus automatically suggests an available port number.
You can modify this manually if necessary.
If you enter a port already in use, you will see a Port is Allocated warning.

Volume Mapping​

Cordatus offers a built-in file explorer interface where you can:

  • Browse available disks and directories,
  • Create new folders, and
  • Assign directory paths for Docker volume mappings.

This feature allows secure linkage between container data and local directories.

Launching the Environment​

  1. Once you complete all configurations, click Start Environment.
  2. Before launching, Cordatus will request your Sudo Password to authorize the process.
  3. If the selected Docker image is not present on your device, Cordatus will ask whether you want to download it.
  4. If the image is already available, Cordatus will launch the environment container automatically using your configured settings.