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

automatic differentiation made easier for C++

Iterative Linear Quadratic Regulator with auto-differentiatiable dynamics models

Fast, easy automatic differentiation in C++

Computational graphs with reverse automatic differentation in the GPU

skscope: Sparse-Constrained OPtimization via itErative-solvers

tiny torch, but close to metal

FastAD is a C++ implementation of automatic differentiation both forward and reverse mode.

Enzyme integration into Rust. Experimental, do not use.

Сustom torch style machine learning framework with automatic differentiation implemented on numpy, allows build GANs, VAEs, etc.

AutoDiff DAG constructor, built on numpy and Cython. A Neural Turing Machine and DeepQ agent run on it. Clean code for educational purpose.

Differentiable Reacting Flow Modeling Software

Unitful Quantities in JAX

도서 머신러닝·딥러닝에 필요한 기초 수학 with 파이썬의 예제 코드와 그래프 그리는 코드 및 웹앱 저장소

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

variational quantum circuit simulator in Julia, under GPLv3

Differentiable Gaussian Process implementation for PyTorch

No description provided.

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

Auto-differentiation library for C++

JutulDarcyRules: ChainRules extension to Jutul and JutulDarcy

Fortran backward (reverse) mode automatic differentiation.

Tiny calculation graph library

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

Auto-differentiable methods for Cosmology

Define-by-run arbitrary higher order autodiff for scalars in Rust. Deferred: tensor calculus implementation.

🎈 A C++ code generator for the automatic derivation of tensors with linear indexes. Implementation for the lesson Compiling Technology(2020 Spring, advised by Yun Liang) in Peking University.

Backpropagation in BQN.

Lightweight performat Python 3.12+ automatic differentiation system that leverages PyTorch’s computational graph to compute arbitrary-order partial derivatives.

Reversed mode second order automatic differentiation for python (WIP)