Welcome to the torchao Documentation

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

1. API Reference

2. Developer Contribution Guide

3. Tutorials

API Reference

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

Contributor Guide

• torchao Contributor Guide

Tutorials

• Serialization