Qualcomm-AI-research/fastforward

Brevitas: neural network quantization in PyTorch

LSQ+ or LSQplus

PyTorch native quantization for training and inference

Research publication code for "Least Squares Binary Quantization of Neural Networks"

A pytorch quantization backend for optimum

FasterAI: Prune and Distill your models with FastAI and PyTorch

SD.Next Quantization Engine

Model Compression Toolkit (MCT) is an open source project for neural network model optimization under efficient, constrained hardware. This project provides researchers, developers, and engineers advanced quantization and compression tools for deploying state-of-the-art neural networks.

QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX