thuml/Neural-Solver-Library

A Library for Advanced Neural PDE Solvers.

51
/ 100
Established

This library is designed for deep learning researchers working on complex scientific models. It takes in data from various physical simulations or industrial design tasks, like fluid dynamics or shape analysis, and outputs predictions about how systems will behave or helps optimize designs. The primary users are researchers focused on developing and benchmarking advanced neural network models for solving partial differential equations (PDEs).

281 stars.

Use this if you are a deep learning researcher prototyping, benchmarking, or developing new neural PDE solvers and need a robust framework with existing state-of-the-art models.

Not ideal if you are a practitioner looking for a ready-to-use solution to solve a specific PDE without deep learning research experience.

computational-science physics-simulation scientific-modeling neural-networks applied-mathematics
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

281

Forks

26

Language

Python

License

MIT

Last pushed

Mar 10, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/thuml/Neural-Solver-Library"

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