PyRank

Auto Differentiation Python Packages

Python packages with the GitHub topic auto-differentiation. Sorted by relevance, with stars and monthly downloads.
GalacticDynamics
unxt

Unitful Quantities in JAX

9K 64 4
oberbichler
hyperjet

Algorithmic differentiation with hyper-dual numbers in C++ and Python

4K 17 4
NVIDIA
minkowskiengine

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

3K 3K 479
GalacticDynamics
unxt-api

Unitful Quantities in JAX

2K 64 4
adxorg
astrodynx

A modern astrodynamics library powered by JAX: differentiate, vectorize, JIT to GPU/TPU, and more

2K 11 6
abess-team
skscope

skscope: Sparse-Constrained OPtimization via itErative-solvers

1K 320 16
oberbichler
hypergraph

Reversed mode second order automatic differentiation for python (WIP)

1K 4 0
GalacticDynamics
unxt-hypothesis

Unitful Quantities in JAX

594 64 4
GalacticDynamics
jax-quantity

Quantities in JAX

334 64 4
WeiXuanChan
autod

autoD is a lightweight, flexible automatic differentiation for python3 based on numpy.

293 0 0
GalacticDynamics
galax

Galactic and Gravitational Dynamics in Python (+ GPU and autodiff)

288 45 8
mntsx
thoad

**thoad** (Torch High Order Automatic Differentiation) is a lightweight reverse-mode autodifferentiation engine written entirely in Python that works over PyTorch’s computational graph to compute **high order partial derivatives**. Unlike PyTorch’s native autograd - which is limited to first-order native partial derivatives - **thoad** is able to performantly propagate arbitray-order derivatives throughout the graph, enabling more advanced gradient-based computations.

103 6 1