Xilinx/brevitas

Brevitas: neural network quantization in PyTorch

69
/ 100
Established

This library helps machine learning engineers optimize their neural networks by reducing their size and computational demands. You provide a trained neural network, and it outputs a more efficient, quantized version. It's designed for machine learning researchers and practitioners working with PyTorch models.

1,500 stars. Used by 1 other package. Available on PyPI.

Use this if you need to deploy large PyTorch neural networks on resource-constrained hardware or improve their inference speed without significant loss in accuracy.

Not ideal if you are looking for a plug-and-play solution for non-PyTorch models or if you need certified production-ready tools.

deep-learning-optimization neural-network-deployment edge-ai model-compression pytorch-development
Maintenance 10 / 25
Adoption 11 / 25
Maturity 25 / 25
Community 23 / 25

How are scores calculated?

Stars

1,500

Forks

242

Language

Python

License

Last pushed

Mar 11, 2026

Commits (30d)

0

Dependencies

8

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Xilinx/brevitas"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.