Dynamic Graphs

PyTorch - Tensors and Dynamic neural networks in Python with strong GPU accelerationPython

A Python package for tensor computation with GPU acceleration and dynamic neural networks built on a tape-based autograd system.

MLXC++

An array framework for machine learning on Apple silicon with unified memory and dynamic graph construction.

pytorch_geometric_temporalPython

A PyTorch library for spatiotemporal signal processing with dynamic and temporal graph neural networks.

autogradLua

Autograd automatically differentiates native Torch code, enabling automatic gradient computation for machine learning models.

red-chainerRuby

A flexible deep learning framework for Ruby, ported from Python's Chainer.

GraphStoreJava

A fast, in-memory graph data structure implementation in Java, optimized for performance and low memory usage.