Prerequisites
- Host OS: Ubuntu 22.04 LTS
If the host computer uses Windows or macOS,
install a virtual machine. Subsequent steps must be run in the virtual machine running Ubuntu 22.04 LTS.
- Enable Wi-Fi and SSH on the device. The device requires an internet connection to download the artifacts needed to run sample applications. If SSH and Wi-Fi are already configured, skip this step. Follow Setup an SSH connection to enable Wi-Fi and SSH on the device.
-
Sign in to the host computer:
-
For the rest of the document, the
QAIRT_ROOTenvironment variable represents the full path to the Qualcomm AI Runtime SDK root directory.-
If installed using the direct download method,
${QAIRT_ROOT}is the path to the unzipped SDK. -
If installed using QPM, the SDK is installed
under
/opt/qcom/aistack/qairt/<version>
-
If installed using the direct download method,
-
Python: v3.10
If Python is already installed, ensure that the environment path is
updated with the Python 3.10 path. If Python 3.10 isn’t installed on
your system, you may install it with the following commands:
-
System Dependencies:
Run the following command as administrator/root to install the system libraries. The command takes time to fully complete.
-
Virtual environment (VENV)
<venv_path>is the path for the new virtual environment. -
Run the following script to check and install missing dependencies:
Expected output:
Setup ML Frameworks
To convert ML models trained on different frameworks into intermediate representations consumable by the Qualcomm AI Runtime SDK, you may need to download and install the corresponding frameworks on your host computer. This Qualcomm AI Runtime SDK release is verified to work with the following versions of the ML training frameworks:| Framework | Version |
|---|---|
| TensorFlow | 2.10.1 |
| TFLite | 2.18.0 |
| PyTorch | 2.4.1 |
| ONNX | 1.19.1 |
-
Install TensorFlow
-
Install TFLite
-
Install PyTorch
-
Install ONNX
Setup Qualcomm AI Runtime SDK environment
Source the environment setup script provided by Qualcomm AI Runtime SDK to ensure all necessary tools and libraries are available in$PATH
for the workflow.

