Tensors and Dynamic neural networks in Python with strong GPU acceleration

SymProp is a C++ software tool for computing the Tucker decomposition of high-order sparse symmetric tensors.

Github repository of VerHem project source tree. A tensor-valued (up to 18 components) solving, post-processing and visualization parallel suite for 3D GL equations and complex geometries with adaptive mesh.

Fork of ggml, Much Machine Learning.

ANT is a NdArray which is developing in c++ and Cuda. It is an educational project for self-learning.

A high-performance tensor library written in C++17, designed specifically for financial data processing and quantitative analysis.

A minimalist tensor library built in c++ with no external libraries

Assignment for Advanced algorithms and programming methods [CM0470] course.

Repo for AMX + FAST

Build Dynamic Neural Networks in Wirikuta, an Automatic Differentiation via Jacobian-Vector-Product Backpropagation Engine.

My attempt to implement multidimensional arrays in C++ without using pointers to heap memory.

Multi-dimensional arrays (or tensors) for performing numpy like operations (Fun Project in Development)

A from-scratch PyTorch's Tensor reimplementation in C++

It is a minimalist Tensor library.

Library for block-sparse symmetric tensors

Tensor library

Numerical Linear Algebra C++/Template Library.

Index-driven BLAS-based compile-time C++ tensor library

micrograd projected to multi-dimensional tensor for computing grads & values

symmetric tensor indexing algorithm