AIMET is a library that provides advanced model quantization and compression techniques for trained neural network models. It provides features that have been proven to improve run-time performance of deep learning neural network models with lower compute and memory requirements and minimal impact to task accuracy. AIMET is designed to work with PyTorch and TensorFlow models. Table of Contents Why AIMET? Supported features Results Getting started Contributions Team License github地址： https://github.com/quic/aimet