#cuda

Multi-platform high-performance compute language extension for Rust.

Numbast is a tool to build an automated pipeline that converts CUDA APIs into Numba bindings.

A visualization library for many-threaded devices.

A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.

A streamlined CMake build system foundation for developing HPC software

High-performance multi-platform compiler for physics simulation

Molecular dynamics and Monte Carlo soft matter simulation on GPUs.

Optimized primitives for collective multi-GPU communication

cuTile Rust provides a safe, tile-based kernel programming DSL for the Rust programming language. It features a safe host-side API for passing tensors to asynchronously executed kernel functions.

The Arbor multi-compartment neural network simulation library.

Self-hosted, local only NVR and AI Computer Vision software. With features such as object detection, motion detection, face recognition and more, it gives you the power to keep an eye on your home, office or any other place you want to monitor.

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

Fast inference engine for Transformer models

PixlStash helps you find things in an image library that's gotten out of hand. It imports and tags your images automatically, then lets you search by content or face, sort the keepers from the rubbish, and serve data to other tools (like ComfyUI) with a REST API. Use the desktop version or run it headless as a server.

An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.

Open3D: A Modern Library for 3D Data Processing

Performance-portable geometric search library

Large-scale LLM inference engine

Up to 100x faster strings for C, C++, CUDA, Python, Rust, Swift, JS, & Go, leveraging NEON, AVX2, AVX-512, SVE, GPGPU, & SWAR to accelerate search, hashing, sorting, edit distances, sketches, and memory ops 🦖

CUDA ecosystem wrappers for Rust

Cumo (pronounced like "koomo") is CUDA aware numerical library whose interface is highly compatible with Ruby Numo

Fast kernel library for Diffusion inference with multiple compute backends.

LuxCore source repository

Consumer-aware compression for embedding indexes and LLM KV caches — compress by the metric the downstream consumer actually uses. PCA-Matryoshka + TurboQuant (27x @ 99.8% recall@10), asymmetric K/V, CUDA/Triton kernels, vLLM plugin, replayable CI-gated claims. MIT.

Accelerate, Optimize performance with streamlined training and serving options with JAX.

LUPINE is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.

CubeK: high-performance multi-platform kernels in CubeCL