RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing …

Python SQL Parser and Transpiler

CUDA Kernel Benchmarking Library

cuGraph - RAPIDS Graph Analytics Library

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

You like pytorch? You like micrograd? You love tinygrad! ❤️

C++ and Python support for the CUDA Quantum programming model for heterogeneous quantum-classical workflows

Scalable data pre processing and curation toolkit for LLMs

cuML - RAPIDS Machine Learning Library

Some CUDA example code with READMEs.

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

Lightning fast C++/CUDA neural network framework

AMD's Machine Intelligence Library

CUDA Core Compute Libraries

`std::execution`, the proposed C++ framework for asynchronous and parallel programming.

Spark RAPIDS plugin - accelerate Apache Spark with GPUs

nmon utility with updates for monitoring GPU memory

OpenCL SDK

Scripts to setup NVMe over TCP in Linux

TPC-H benchmark kit with some modifications/additions

Dataframes powered by a multithreaded, vectorized query engine, written in Rust

NVIDIA Linux open GPU kernel module source

📊 A simple command-line utility for querying and monitoring GPU status

The Legion Parallel Programming System

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

Header-only C++/python library for fast approximate nearest neighbors