High-efficiency floating-point neural network inference operators (libs)

 XNNPACK is a highly optimized library of floating-point neural network
 inference operators for ARM, WebAssembly, and x86 platforms. XNNPACK is not
 intended for direct use by deep learning practitioners and researchers; instead
 it provides low-level performance primitives for accelerating high-level
 machine learning frameworks, such as TensorFlow Lite, TensorFlow.js, PyTorch,
 and MediaPipe.
 .
 This package contains the shared object.