Qualcomm Neural Network, abbreviated as QNN, is a software framework for Artificial Intelligence (AI) on QTIs chipsets and AI acceleration cores. This framework is designed to provide a unified API and modular and extensible per-accelerator libraries which form a reusable basis for full stack AI solutions, both QTI’s own and third party frameworks. QNN Software Development Kit (SDK) provides tools and libraries to initialize, set up, and execute convolutional and recurrent neural networks on the Snapdragon IP cores (Kryo CPU, Adreno GPU, Hexagon DSP/HTP). It supports common deep learning model frameworks, such as TensorFlow, Caffe and others. QNN SDK enables companies in a broad range of industries, from mobile, healthcare to automotive, to run their own proprietary-trained neural network models on portable devices.