Xilinx/brevitas
Brevitas: neural network quantization in PyTorch
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.
Stars
1,500
Forks
242
Language
Python
License
—
Category
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.
Related frameworks
open-mmlab/mmengine
OpenMMLab Foundational Library for Training Deep Learning Models
google/qkeras
QKeras: a quantization deep learning library for Tensorflow Keras
fastmachinelearning/qonnx
QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX
tensorflow/model-optimization
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization...
lucidrains/vector-quantize-pytorch
Vector (and Scalar) Quantization, in Pytorch