Neural Magic

Sparsity-aware deep learning inference runtime for CPUs

neuralmagic

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

neuralmagic

Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes

neuralmagic

ML model optimization product to accelerate inference.

neuralmagic

Top-level directory for documentation and general content

neuralmagic

Notebooks using the Neural Magic libraries 📓

neuralmagic

A high-throughput and memory-efficient inference and serving engine for LLMs

neuralmagic

YOLOv5 in PyTorch > ONNX > CoreML > TFLite

neuralmagic