Autograd Python Packages

torch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

autograd-gamma

NotImplementedError: VJP of gammainc wrt argnum 0 not defined

pennylane

PennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaningful quantum algorithms, from inspiration to implementation.

torch-sparse

PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations

lucid-dl

Lumerico's Comprehensive Interface for Deep Learning

neuralengine

An open-source framework/library for building and training neural networks in Python with support for GPUs (CUDA).

datarax

A Differentiable Data Pipeline Framework for JAX

pyerrors

Error propagation and statistical analysis for Monte Carlo simulations in lattice QCD and statistical mechanics using autograd.

mygrad

Drop-in automatic differentiation to NumPy

nabla-ml

Nabla: High-Performance Scientific Computing

agent-torch

large population models

pyember

ML Library from scratch with only standard libraries

norse

Deep learning with spiking neural networks (SNNs) in PyTorch.

boost-loss

Utilities for easy use of custom losses in CatBoost, LightGBM, XGBoost.

legume-gme

Differentiable plane-wave and guided-mode expansion for photonic crystals

nnetflow

A minimal neural network framework with autodiff and NumPy

torchvine

Pure-PyTorch vine copula modelling — GPU-ready, differentiable, and API-compatible with pyvinecopulib

nets

Recreating PyTorch from scratch, using Numpy. Supports FCN, CNN, RNN layers.

neuralforge

Documented and Unit Tested educational Deep Learning framework with Autograd from scratch.

loupe

Parametric optimization with built-in autograd

vistan

Library to run VI algorithms on Stan models.

torch-yottaxx

a simple autograd library

pydynet

NumPy-based Dynamic Deep Learning Framework

pytorch-gpu

Tensors and Dynamic neural networks in Python with strong GPU acceleration