AI ToolsWrite

HYSEN LABS DIRECTORY

NVIDIA

Verified repositories, classifications and analysis from the NVIDIA organization.

71 curated open-source projects
NVIDIA

kvpress

★ 1,252

LLM KV cache compression made easy

Python199 forks5 min read
★ 1,196

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

C++496 forks7 min read
NVIDIA

enroot

★ 1,123

A simple yet powerful tool to turn traditional container/OS images into unprivileged sandboxes.

Shell142 forks4 min read
NVIDIA

cuopt

★ 1,112

GPU accelerated decision optimization

Cuda260 forks5 min read
★ 1,086

Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

Python124 forks6 min read
★ 1,082

A Python library that enables the use of Jetson's GPIOs

Python264 forks9 min read
NVIDIA

cuda-tile

★ 1,056

CUDA Tile IR is an MLIR-based intermediate representation and compiler infrastructure for CUDA kernel optimization, focusing on tile-based computation patterns and optimizations targeting NVIDIA tensor core units.

C++93 forks8 min read
NVIDIA

raft

★ 1,054

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 high performance applications.

Cuda258 forks7 min read
NVIDIA

NVFlare

★ 1,016

NVIDIA Federated Learning Application Runtime Environment

Python310 forks6 min read
★ 1,014

NVIDIA cuDF for Apache Spark plugin - accelerate Apache Spark with GPUs

Scala317 forks9 min read
★ 998

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

Python338 forks6 min read
NVIDIA

nvbench

★ 946

CUDA Kernel Benchmarking Library

Cuda135 forks9 min read
NVIDIA

cuvs

★ 895

cuVS - a library for vector search and clustering on the GPU

Cuda266 forks7 min read
NVIDIA

TileGym

★ 840

Helpful kernel tutorials, examples and SKILLs for tile-based GPU programming

Python91 forks8 min read
NVIDIA

DCGM

★ 817

NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs

C++115 forks8 min read
★ 803

A tool for bandwidth measurements on NVIDIA GPUs.

C++102 forks9 min read
★ 729

Differentiable signal processing on the sphere for PyTorch

Jupyter Notebook80 forks6 min read
★ 718

SOMA BVH to humanoid robot motion retargeting library built with Newton and NVIDIA Warp

Python109 forks9 min read