PINA and XPINNs
PINA provides a general-purpose framework for physics-informed neural networks, while XPINNs extends this approach with domain decomposition techniques for solving large-scale nonlinear PDEs, making them complements that can be used together for different problem scales and complexities.
About PINA
mathLab/PINA
Physics-Informed Neural networks for Advanced modeling
Builds on PyTorch, PyTorch Lightning, and PyTorch Geometric to provide modular Problem, Model, Solver, and Trainer APIs for both supervised learning and physics-informed tasks. Supports Neural Operators and graph-based architectures, with automatic differentiation for constraint enforcement (e.g., differential equations, boundary conditions) and multi-device training via PyTorch Lightning's distributed backend.
About XPINNs
AmeyaJagtap/XPINNs
Extended Physics-Informed Neural Networks (XPINNs): A Generalized Space-Time Domain Decomposition Based Deep Learning Framework for Nonlinear Partial Differential Equations
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work