Welcome to the torchao Documentation

torchao is a library for custom data types and optimizations. Quantize and sparsify weights, gradients, optimizers, and activations for inference and training using native PyTorch. Please checkout torchao README for an overall introduction to the library and recent highlight and updates.

Getting Started

• Quick Start Guide

Developer Notes

• Quantization Overview
• Sparsity Overview
• Contributor Guide

API Reference

• torchao.dtypes
• torchao.quantization
• torchao.sparsity

Tutorials

• Serialization
• Writing Your Own Quantized Tensor
• Writing Your Own Quantized Tensor (advanced)