CUDA

Thrustthrust/thrust

A C++ parallel algorithms library that enables high-performance computing on GPUs and multicore CPUs with a productivity-focused interface.

ArrayFirearrayfire/arrayfire

A general-purpose tensor library for parallel computing across CPUs, GPUs, and hardware accelerators.

NCCLNVIDIA/nccl

A library of optimized communication primitives for multi-GPU and multi-node collective operations.

Warp-CTCbaidu-research/warp-ctc

A fast parallel implementation of the Connectionist Temporal Classification (CTC) loss function for CPU and GPU.

Boltz-1jwohlwend/boltz

A family of open-source deep learning models for accurate biomolecular interaction and binding affinity prediction, rivaling AlphaFold3 and physics-based methods.

ruvectorruvnet/ruvector

A self-learning vector database with graph intelligence, local AI, and PostgreSQL integration, built for real-time adaptation.

TurboPilotravenscroftj/turbopilot

An open-source, locally-runnable code completion engine using large language models that works on CPU.

implicitbenfred/implicit

Fast Python library for collaborative filtering recommendation algorithms on implicit feedback datasets.

doradora-rs/dora

A Rust-based middleware framework for building low-latency, composable, and distributed AI robotic applications using dataflow graphs.

StringZillaashvardanian/StringZilla

A high-performance string library leveraging SIMD and SWAR to accelerate search, hashing, sorting, and edit distances across C, C++, Python, Rust, and more.

flownet2-pytorchNVIDIA/flownet2-pytorch

PyTorch implementation of FlowNet 2.0 for optical flow estimation using deep neural networks.

Fast-PlannerHKUST-Aerial-Robotics/Fast-Planner

A robust and efficient trajectory planner enabling quadrotor fast flight in complex unknown environments.

captcha_trainerkerlomz/captcha_trainer

A deep learning framework for training image classification models to solve complex captcha and OCR tasks.

FalcorNVIDIAGameWorks/Falcor

A real-time rendering framework for DirectX 12 and Vulkan that improves productivity in graphics research and prototyping.

Neural Stylecysmith/neural-style-tf

A TensorFlow implementation of neural style transfer for images and videos, blending content and artistic styles using convolutional neural networks.

simpledettusimple/simpledet

A simple and versatile framework for object detection and instance recognition with extensive model coverage and distributed training.

OpenSubdivPixarAnimationStudios/OpenSubdiv

An open-source library for high-performance subdivision surface evaluation on CPU and GPU, matching Pixar's Renderman precision.

ChatbotConchylicultor/DeepQA

A TensorFlow implementation of a neural conversational model (seq2seq) for building deep learning chatbots.

nnablasony/nnabla

A deep learning framework for research, development, and production with flexible Python API and C++ core.

InvoiceNetnaiveHobo/InvoiceNet

Deep neural network to extract structured information from invoice documents with a customizable UI and training tools.

Kokkoskokkos/kokkos

A C++ programming model for writing performance-portable applications targeting all major HPC platforms.

Decorddmlc/decord

An efficient video and audio loader for deep learning with hardware-accelerated decoding and smart shuffling.

darknet_rosleggedrobotics/darknet_ros

A ROS package for real-time object detection in camera images using YOLO (V3) on GPU and CPU.

darknet_rosleggedrobotics/darknet_ros

A ROS package for real-time object detection in camera images using YOLO (V3) on GPU and CPU.

EGO-PlannerZJU-FAST-Lab/ego-planner

A lightweight gradient-based local planner for quadrotors that eliminates ESDF construction, achieving planning times around 1ms.

libcudacxxNVIDIA/libcudacxx

NVIDIA's implementation of the C++ Standard Library for CUDA C++ development.

RAPIDS cuGraphrapidsai/cugraph

A collection of GPU-accelerated graph analytics libraries for creating, manipulating, and executing scalable graph algorithms.

GNSS-SDRgnss-sdr/gnss-sdr

An open-source software-defined receiver for GPS, Galileo, GLONASS, and BeiDou signals, enabling custom GNSS processing.

OpenImageDenoiseOpenImageDenoise/oidn

An open-source library of high-performance, high-quality denoising filters for ray-traced images using deep learning.

SfMLearnertinghuiz/SfMLearner

An unsupervised learning framework for depth and ego-motion estimation from monocular videos using TensorFlow.

Chai-1chaidiscovery/chai-lab

A multi-modal foundation model for state-of-the-art molecular structure prediction of proteins, small molecules, DNA, RNA, and glycosylations.

dfdxcoreylowman/dfdx

A deep learning library for Rust featuring shape-checked tensors and neural networks with compile-time safety.

dfdxchelsea0x3b/dfdx

A deep learning library in Rust featuring shape-checked tensors and neural networks with compile-time safety.

The original code from the DeepMind article + tweakskuz/DeepMind-Atari-Deep-Q-Learner

Original DeepMind DQN 3.0 implementation for Atari game reinforcement learning, with community tweaks.

nndeploynndeploy/nndeploy

A visual workflow-based AI deployment framework for multi-platform and multi-backend inference, supporting large models and edge devices.

moderngpumoderngpu/moderngpu

A header-only C++ library for CUDA providing accelerated primitives for solving irregularly parallel problems on GPUs.