Llama 2 Everywhere (L2E)

Minimal runtime core of Caffe, Forward only, GPU support and Memory efficiency.

V library to develop Artificial Intelligence and High-Performance Scientific Computations

💥 Fast matrix-multiplication as a self-contained Python library – no system dependencies!

[ARCHIVED] PHP library for scientific computing powered by C. See https://github.com/NumPower/numpower

🔥🔥🔥 A collection of some awesome public CUDA, cuBLAS, TensorRT and High Performance Computing (HPC) projects.

Fast Unit Root Tests and OLS regression in C++ with wrappers for R and Python

LibN3L: A light-weight neural network package for natural language

Neural networks library for machine learning on PHP

A LAPACK implementation for Go [DEPRECATED]

An easy Windows installer for GFortran and the Fortran Package Manager

Wrapper package for OpenCV with Inference Engine python bindings.

PowerShell automation to rebuild llama.cpp for a Windows environment.

64-bit R for Windows compiled with openblas

CMake FindLAPACK.cmake that works with Intel MKL, Atlas, OpenBLAS, Netlib, LAPACK95 for C / C++ / Fortran

The fundamental package for scientific matrix operation

PHP extension of universal buffer for 1-dimension and OpenBLAS and mathematical library

a lightweight C++ LLaMA inference engine for mobile devices

R is said to get way faster if you change the BLAS library it is linked to. Is it true?