CUDA

HoVer-Netvqdang/hover_net

A PyTorch-based deep learning model for simultaneous nuclear instance segmentation and classification in histopathology images.

VexCLddemidov/vexcl

A C++ vector expression template library for OpenCL, CUDA, and OpenMP that simplifies GPGPU development.

ThunderGBMXtra-Computing/thundergbm

A fast GPU-accelerated library for training Gradient Boosting Decision Trees (GBDT) and Random Forests.

Minerva - a fast and flexible tool for deep learning on multi-GPUdmlc/minerva

A fast and flexible deep learning system with NumPy-like NDarray interface and easy multi-GPU support.

cuda-pclNVIDIA-AI-IOT/cuda-pcl

A CUDA-accelerated library collection for point cloud processing, providing GPU-optimized alternatives to PCL functions.

3d-vehicle-trackingucbdrive/3d-vehicle-tracking

Official PyTorch implementation for joint monocular 3D vehicle detection and tracking from ICCV 2019.

MGLmelisgl/mgl

A Common Lisp machine learning library focusing on neural networks, Boltzmann machines, and Gaussian processes with BLAS and CUDA support.

hugotknights-analytics/hugot

Run ONNX transformer pipelines (like Hugging Face) natively in Go for inference and fine-tuning, with support for CPU, GPU, and TPU.

DiffSharpDiffSharp/DiffSharp

A tensor library for differentiable functional programming in F#, with PyTorch-like APIs and GPU support.

LEDNetxiaoyufenfei/LEDNet

A lightweight encoder-decoder neural network for real-time semantic segmentation on resource-constrained devices.

TorontoDeepLEarning convnetTorontoDeepLearning/convnet

A fast C++ GPU implementation of Convolutional Neural Networks with multi-GPU support.

SalsaNextTiagoCortinhal/SalsaNext

A real-time, uncertainty-aware deep learning model for semantic segmentation of 3D LiDAR point clouds in autonomous driving.

Deep Diamonduncomplicate/deep-diamond

A fast Clojure library for tensor operations and deep learning with optimized CPU/GPU support.

PathMLDana-Farber-AIOS/pathml

An open-source toolkit for scalable, standardized computational pathology analysis, enabling AI and machine learning on large imaging datasets.

vilibuzh-rpg/vilib

A GPU-accelerated C++ library for visual-inertial odometry frontend tasks, optimized for high-speed robotics.

CameraRadarFusionNetTUMFTM/CameraRadarFusionNet

A neural network for object detection using multi-level fusion of camera and radar data, built on Keras RetinaNet.

Marvin - A Minimalist GPU-only N-Dimensional ConvNets FrameworkPrincetonVision/marvin

A minimalist GPU-only framework for N-dimensional convolutional neural networks focused on speed and hackability.

JAX ToolboxNVIDIA/JAX-Toolbox

A collection of CI pipelines, Docker images, and optimized examples to simplify JAX development on NVIDIA GPUs.

GitHub repositoryedwardzhou130/PolarSeg

A lightweight neural network for near-real-time semantic segmentation of LiDAR point clouds using polar coordinate quantization.

Extending JAX with custom C++ and CUDA code by Dan Foreman-Mackeydfm/extending-jax

A tutorial demonstrating how to extend JAX with custom C++ and CUDA operations for high-performance computing.

MFCMFlowCode/MFC

An exascale many-physics flow solver for compressible multi-phase simulations, scaling to 200 trillion grid points on 43K+ GPUs.

DeepLearningNotesAlphaSmartDog/DeepLearningNotes

A collection of open-source machine learning and quantitative analysis models implemented in TensorFlow and PyTorch.

REINVENTMolecularAI/Reinvent

A reinforcement learning framework for de novo drug design that generates novel molecular structures with desired properties.

SiaNetSciSharp/SiaNet

An easy-to-use C# deep learning library with support for multiple backends including TensorFlow, PyTorch, and CUDA/OpenCL.

GitHub repositoryPRBonn/rangenet_lib

A C++/TensorRT inference module for RangeNet++, enabling fast LiDAR semantic segmentation for robotics applications.

StaticMappingEdwardLiuyc/StaticMapping

A full LiDAR SLAM system for static environment mapping using LiDAR with optional GPS, IMU, and odometry support.

TargetDiffguanjq/targetdiff

Official implementation of a 3D equivariant diffusion model for generating drug-like molecules that bind to specific protein targets and predicting their binding affinity.

kinfu_remake: Lightweight, reworked and optimized version of Kinfu.Nerei/kinfu_remake

An optimized, lightweight CUDA-based 3D reconstruction implementation derived from the original Kinfu algorithm.

cutorchtorch/cutorch

A CUDA backend for Torch7 that enables GPU-accelerated tensor operations with a familiar Torch API.

zed-ros2-wrapperstereolabs/zed-ros2-wrapper

ROS 2 wrapper for Stereolabs ZED cameras, providing access to depth, point clouds, object detection, and spatial mapping.

SPUsecretflow/spu

A provable, measurable secure computation device that enables privacy-preserving tensor operations using multi-party computation (MPC).

Flarearia42/flare

A Clojure library for dynamic neural network graphs with pluggable tensor backends, inspired by PyTorch.

elbenchobreuner/elbencho

A distributed storage benchmark tool for file systems, object stores, and block devices with GPU support.

somoclupeterwittek/somoclu

A massively parallel library for training self-organizing maps on multicore CPUs, GPUs, and clusters with support for dense and sparse data.

scirscool-japan/scirs

A comprehensive scientific computing and AI/ML library in pure Rust, offering SciPy-compatible APIs with 10-100x performance gains.

BIDMatBIDData/BIDMat

A CPU and GPU-accelerated matrix library optimized for high-performance data mining operations.