Popular GitHub Repositories for Sparse Tensors

Tensors and Dynamic neural networks in Python with strong GPU acceleration

C++ tensors with broadcasting and lazy computing

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

Deep learning in Rust, with shape checked tensors and neural networks

A package for the sparse identification of nonlinear dynamical systems from data

High Performance Computation for N-D Tensors in .NET, similar API to NumPy.

Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

[ICLR'23 Spotlight?] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"

Tensors, for human consumption

A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).

Tensors and dynamic neural networks in pure Rust.

PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations

Programmable CUDA/C++ GPU Graph Analytics

Library for specialized dense and sparse matrix operations, and deep learning primitives.

SPLADE: sparse neural search (SIGIR21, SIGIR22)

A Redis module for serving tensors and executing deep learning graphs

VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking (CVPR 2023)

A lightweight high performance tensor algebra framework for modern C++

From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)