HiAI is one of the world's first mobile AI computing platforms with a dedicated Neural-network Processing Unit (NPU).
The HiAI API library, released as a unified binary file, is set to enable fast neural network-based computing through HiAI Heterogeneous Computing Platform, which is integrated within Kirin SoC.
With the HiAI APIs, developers can focus on developing new AI applications instead of focusing on performance tuning.
Provides frequently used artificial intelligence function APIs which can be efficiently run on mobile devices.
Provides processor-independent acceleration APIs to allow the Kirin hardware to accelerate model and operator computing.
Provides model management APIs, including model compilation, model loading, model running, and model destruction.
Provides basic operator computing APIs, including convolution layer, pooling layer, full connection layer, matrix computing, and others.