ARM Compute Library: A collection of low-level functions optimized for ARM CPUs and GPUs, widely used for accelerating neural networks and computer vision tasks.
Ethos-N NPU: ARM’s Neural Processing Unit designed specifically for AI inference, optimized for energy efficiency in edge devices.
TensorFlow Lite + ARM NN: ARM NN bridges TensorFlow Lite models to ARM hardware, enabling optimized inference on mobile and embedded devices.
ONNX Runtime with ARM backends: Many ARM optimizations are available for ONNX models, making deployment across devices smoother.
MicroTVM / TinyML: Lightweight ML frameworks that integrate with ARM microcontrollers for ultra-low-power AI applications.
Built With
- github
- phython
Log in or sign up for Devpost to join the conversation.