locuslab/qpth

A fast and differentiable QP solver for PyTorch.

56
/ 100
Established

This is a tool for developers building optimization models within PyTorch. It helps incorporate quadratic programming (QP) problems directly into neural networks or other differentiable programs. Developers input QP problem parameters (like cost functions and constraints) and get back optimized solutions, allowing for end-to-end learning systems.

785 stars. No commits in the last 6 months. Available on PyPI.

Use this if you are a machine learning engineer or researcher who needs to embed and solve quadratic programs efficiently within a PyTorch model, maintaining differentiability for backpropagation.

Not ideal if you are looking for a standalone quadratic programming solver without integration into a deep learning framework, or if you are not working with PyTorch.

deep-learning optimization machine-learning-engineering neural-networks differentiable-programming
Stale 6m No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

785

Forks

112

Language

Python

License

Apache-2.0

Last pushed

Sep 03, 2024

Commits (30d)

0

Get this data via API

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

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