#cuda

PyTorch native quantization and sparsity for training and inference

CUDA Core Compute Libraries

A Python framework for GPU-accelerated simulation, robotics, and machine learning.

SGLang is a high-performance serving framework for large language models and multimodal models.

Making it easier to work with shaders

Main repository for QMCPACK, an open-source production level many-body ab initio Quantum Monte Carlo code for computing the electronic structure of atoms, molecules, and solids with full performance portable GPU support

Open security scanner and self-hosted control plane for AI, MCP, and cloud. One evidence model — run scans in your environment, centralize findings, govern in your VPC.

CUDA Templates and Python DSLs for High-Performance Linear Algebra

An electronic structure package based on either plane wave basis or numerical atomic orbitals.

A streamlined CMake build system foundation for developing HPC software

Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.

Performance-portable geometric search library

Fast inference engine for Transformer models

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 🦖

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.