apple-aiml-research/ml-upscale

Fast & Simple Resource-Constrained Learning of Deep Network Structure

FasterAI: Prune and Distill your models with FastAI and PyTorch

Prune transformer layers

Simplify your onnx model

✂️Scalpel: Recovery-Aware Layer Pruning for Faster Vision-Language Models

A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

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.

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

Neural Network Compression Framework for enhanced OpenVINO™ inference