Skip to main content
Qualcomm AI Runtime SDK is an all-in-one SDK to port ML models to run on Qualcomm hardware accelerators. The SDK contains Qualcomm Neural Processing Engine (also known as SNPE) and AI Engine Direct (also known as QNN) which offer tools to convert and quantize models trained in PyTorch and TensorFlow and runtimes to run these models on CPU, GPU, and HTP. Learn more about SNPE and QNN. QAIRT workflow

​
Setup

Download SDK

Download and install the Qualcomm AI Runtime SDK.

Setup SDK

Configure the SDK environment for model optimization.

​
Convert and quantize models

Convert and quantize models

Convert models from PyTorch, TensorFlow, ONNX, or LiteRT and quantize them for deployment using SNPE or QNN.

​
Run inference

Run models

Run inference on converted models using SNPE or QNN on CPU, GPU, or HTP.

​
API reference

Qualcomm Neural Processing Engine C/C++

SNPE C/C++ API reference documentation.

Qualcomm AI Engine Direct C/C++

QNN C/C++ API reference documentation.