martenlienen/torchode
A parallel ODE solver for PyTorch
This is a tool for developers who use PyTorch to build models that involve solving ordinary differential equations (ODEs). It takes your ODE definition and initial conditions, then efficiently computes the solution across many samples simultaneously. This helps machine learning engineers and researchers accelerate their scientific machine learning models, especially in areas like physics-informed neural networks or dynamical systems.
276 stars. Used by 2 other packages. No commits in the last 6 months. Available on PyPI.
Use this if you are a Python developer working with PyTorch and need to solve multiple ODEs in parallel within your machine learning models, especially when performance and JIT compilation are important.
Not ideal if you are looking for a general-purpose ODE solver for non-machine learning applications or if you are not working within the PyTorch ecosystem.
Stars
276
Forks
20
Language
Python
License
MIT
Category
Last pushed
Oct 03, 2024
Commits (30d)
0
Dependencies
3
Reverse dependents
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/martenlienen/torchode"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
lululxvi/deepxde
A library for scientific machine learning and physics-informed learning
pnnl/neuromancer
Pytorch-based framework for solving parametric constrained optimization problems,...
wilsonrljr/sysidentpy
A Python Package For System Identification Using NARMAX Models
dynamicslab/pysindy
A package for the sparse identification of nonlinear dynamical systems from data
google-research/torchsde
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.