Skip to main content

Application Launch Guide

This guide explains how to launch an Application through the Cordatus Platform.
Cordatus enables users to easily start, configure, and manage AI models or custom software while efficiently utilizing system resources.

See details → Application Hub Overview | Application Hub Quickstart | Container Management Guide | User Models Guide

Selecting an Application​

Accessing from the Menu​

  1. From the left-side menu, click Containers.
  2. In the dropdown list, select Applications.
  3. Choose the application you wish to run.

    Example: In the reference video, the vLLM Application is selected.

Create Application with Single GPU

 

Create Application with Multiple GPUs

 

Create Application with Model Not Downloaded

 

Application Detail Page​

The Application Detail Page is the central information panel where you can view all relevant data about the selected application.
On this page, you will find:

  • Supported platforms (Server / Workstation or Jetson)
  • A brief description of the selected application
  • Technical summary provided by Cordatus

The following tabs are also available on this page:

  • Description: General information about the selected application
  • Versions: Docker images and tags registered within Cordatus
  • Containers: Lists of containers previously launched under your account for the same application
  • Models: Available only for LLM Engine Applications, displaying the models associated with that engine

4. Launching the Application​

4.1 Launching from the Detail Page​

  1. Click the Start Application button.
  2. In the modal window that appears:
    • Select the device you wish to run the application on and connect to it.
    • Proceed to the Version step, where available Docker image versions are displayed.
      • If the Docker image is already present on your device, a downloaded icon appears.
      • If not, a to be downloaded icon is shown.
  3. You will then be redirected to the Advanced Settings screen — the configuration area for your container in Cordatus.

5. Advanced Settings​

5.1 General Settings​

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

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

    • Selecting All GPU grants access to all GPUs on your device.
    • At least one GPU must be selected to proceed.

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

    CPU Core Assignment:
    You can limit the maximum number of CPU cores that your container will use.

    • Setting Limits:
      Manually specify how many CPU cores the container can utilize.

    • Host Reserved:
      Cordatus automatically reserves a certain amount of CPU cores for system operations to ensure your device continues functioning normally.
      Therefore, you cannot assign all CPU cores to the container as the maximum limit.

    • No Limit Option:
      If you want to allocate all CPU resources to the container, check the No Limit option in the upper right corner.
      This removes the Host Reserved restriction and makes all resources available to the container.

    RAM Assignment:
    You can specify how much of your system's total RAM can be allocated to the container as the maximum limit.

    • Setting Limits:
      Manually define the amount of RAM the container can use.

    • Host Reserved:
      Cordatus automatically reserves a certain amount of RAM for system stability to ensure your device operates properly.
      Therefore, you cannot assign all RAM capacity to the container as the maximum limit.

    • No Limit Option:
      If you want to allocate all RAM resources to the container, check the No Limit option in the upper right corner.
      This removes the Host Reserved restriction and makes all RAM available to the container.

    ⚠️ Warning: Using the No Limit option allocates the entire system to the container, which may negatively impact your device's performance and stability. Use this option with caution.

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

5.2 Settings for LLM Engine Applications​

This section only applies to LLM Engine Applications.
If you are launching a standard application, you may skip this part.

  • Enable Open Web UI:
    When enabled, Cordatus automatically creates an additional Open Web UI Container, allowing you to interact with the model directly through your browser.

 

  • Model Selection:
    On the right side, choose which model you want to run. There are three options:

    1. Cordatus Models: Displays models that have been tested and pre-registered in the Cordatus system, along with their tags.

      💡 Smart Volume Detection: If you have configured model paths on your device, Cordatus automatically detects installed models and checks whether the selected Cordatus Model already exists on your device. If found, Cordatus automatically configures the volume mount to use your local copy. If the model is not found locally, the default volume mount path will be used (model will be downloaded during container launch), but you can manually modify this in the Docker Options section if needed.

    2. Custom Model:
      If you wish to run a model that does not exist in Cordatus, enter its name manually in the Model Name or Model URL field.

    1. User Models:
      Displays models that you have previously defined and added to your Cordatus account.

      💡 Note: To use a model from Device X on Device Y, you must first add the model to User Models.
      Learn more: User Models and Model Transfer Guide If the selected device and the device where the model is located are the same, the model will be used directly without any transfer process. Cordatus automatically detects this and skips the transfer step.

    Create Application By Using User Model on Same Device
    Create Application And Model Transfer Structure

    Model Transfer Feature:
    When the model needs to be transferred to a different device, Cordatus enables seamless model transfer between devices on the same network.

    • If the transfer is interrupted, it will automatically resume from where it left off
    • Once the transfer completes, you can continue with the application launch process

    Automatic Volume Configuration:
    Based on the selected inference engine, Cordatus automatically configures the volume mapping according to your predefined model paths.

    Model paths can be defined for three different inference engines:

    • Huggingface
    • Ollama
    • NVIDIA NIM

    ⚠️ Important: To use User Models, you must first configure model paths on your device.
    Navigate to Metrics > Model Info after connecting to your device, and define the model paths for each inference engine.

5.3 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.

5.4 Environment Variables​

The Environment Variables section defines the environment parameters for your application.

  • Cordatus automatically displays the default variables associated with the selected application.
  • To add your own variables, use the Add your own Environment Variable option.
  • If your environment variable is a Token, you can select one of your pre-defined tokens from your Cordatus account.

    (You can refer to this section to learn how to add tokens to Cordatus.)

This mechanism enables you to securely manage access keys, configuration values, and authentication parameters within your containers.

5.5 Engine Arguments​

The Engine Arguments section lets you configure the operational parameters of your Cordatus application — particularly for LLM engines.

  • Cordatus automatically provides the default engine arguments for the selected application.
  • To add new ones, use the Add your own Engine Argument option.
  • These arguments may include parameters such as model optimization levels, batch size, token limits, or execution modes.

6. Launching the Container​

Once you complete all configurations, the Start Environment button becomes active.

The following configurations must be completed:

  • GPU selection
  • Docker Options setup
  • Environment Variables (optional)
  • Engine Arguments (optional)

6.1 Container Creation Process​

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

6.2 Monitoring the Container​

You can monitor the status and logs of your container from the following sections:

  • Application > Containers tab
  • Containers section in the main sidebar

Here, Cordatus displays container runtime information, health status, and resource usage metrics.