NVIDIA Corporation ORG

Run agents like Hermes and OpenClaw more securely inside NVIDIA OpenShell with managed inference

A secure sandbox for running autonomous AI agents locally, with Linux kernel-level isolation to prevent agents from accessing your files or network without permission.

Build and run Docker containers leveraging NVIDIA GPUs

Deprecated and archived wrapper that gave Docker containers access to NVIDIA GPUs. Superseded by the NVIDIA Container Toolkit, which is the current supported path.

NVIDIA Linux open GPU kernel module source

Ongoing research training transformer models at scale

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

NVIDIA reference collection of training and deployment scripts for well-known deep learning models tuned for Tensor Core GPUs and NGC Docker containers.

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

Style transfer, deep learning, feature transform

NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

PersonaPlex code.

CUDA Templates and Python DSLs for High-Performance Linear Algebra

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.

the LLM vulnerability scanner

NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.

OpenShell is the safe, private runtime for autonomous AI agents.

Synthesizing and manipulating 2048x1024 images with conditional GANs

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

Transformer related optimization, including BERT, GPT

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

Optimized primitives for collective multi-GPU communication

Build and run containers leveraging NVIDIA GPUs

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

NVIDIA device plugin for Kubernetes

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.

CUDA Python: Performance meets Productivity

Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.

NeMo Retriever Library is a scalable, performance-oriented document content and metadata extraction microservice. NeMo Retriever Library uses specialized NVIDIA NIM microservices to find, contextualize, and extract text, tables, charts and images that you can use in downstream generative applications.

NVIDIA GPU Operator creates, configures, and manages GPUs in Kubernetes

CUDA Library Samples

The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.

CUDA Core Compute Libraries

`std::execution`, the standard C++ framework for asynchronous and parallel programming.

cuTile is a programming model for writing parallel kernels for NVIDIA GPUs

TensorRT Extension for Stable Diffusion Web UI

AIStore: scalable storage for AI applications

[ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl

NVIDIA GPU metrics exporter for Prometheus leveraging DCGM

NVIDIA curated collection of educational resources related to general purpose GPU programming.

Simple samples for TensorRT programming

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

NCCL Tests

Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP

Tools for building GPU clusters

An efficient C++20 GPU numerical computing library with Python-like syntax

A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology

AI agent skills published by NVIDIA

NVIDIA DLSS is a new and improved deep learning neural network that boosts frame rates and generates beautiful, sharp images for your games

NVIDIA’s implementation of RTX ray-tracing in Quake II

Official PyTorch implementation of BigVGAN (ICLR 2023)

PyTorch implementation of Audio Flamingo: Series of Advanced Audio Understanding Language Models

LLM KV cache compression made easy

NVIDIA container runtime library

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

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

Open-source deep-learning framework for exploring, building and deploying AI weather/climate workflows.

Collection of step-by-step playbooks for setting up AI/ML workloads on NVIDIA DGX Spark devices with Blackwell architecture.

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.

Spark RAPIDS plugin - accelerate Apache Spark with GPUs

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

GPU accelerated decision optimization

Official Codebase for "DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos" (ICML 2026)

NVIDIA Federated Learning Application Runtime Environment

Flowtron is an auto-regressive flow-based generative network for text to speech synthesis with control over speech variation and style transfer

Examples demonstrating available options to program multiple GPUs in a single node or a cluster

CUDA Kernel Benchmarking Library

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

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

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

A tool for bandwidth measurements on NVIDIA GPUs.

Differentiable signal processing on the sphere for PyTorch

No description.

Repository for nvCOMP docs and examples. nvCOMP is a library for fast lossless compression/decompression on the GPU that can be downloaded from https://developer.nvidia.com/nvcomp.

NVIDIA Math Libraries for the Python Ecosystem

DreamGen: Nvidia GEAR Lab's initiative to solve the robotics data problem using world models

NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process communication and coordination overheads by allowing programmers to perform one-sided communication from within CUDA kernels and on CUDA streams.

NVIDIA Material Definition Language SDK

Home for cuQuantum Python & NVIDIA cuQuantum SDK C++ samples

Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.

NeMo text processing for ASR and TTS

High-performance, light-weight C++ LLM and VLM Inference Software for Physical AI

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

JAX-Toolbox

cuEquivariance is a math library that is a collective of low-level primitives and tensor ops to accelerate widely-used models, like DiffDock, MACE, Allegro and NEQUIP, based on equivariant neural networks. Also includes kernels for accelerated structure prediction.

NVIDIA Data Science stack tools

Efficient LLM Inference over Long Sequences

Massively parallel training of machine-learning based weather and climate models

Megatron's multi-modal data loader

This repo contains CUDA-Q Academic materials, including self-paced Jupyter notebook modules for building and optimizing hybrid quantum-classical algorithms using CUDA-Q.

NVIDIA driver control panel

high-performance inference and serving library for interactive autoregressive video and world models

Tooling for optimized, validated, and reproducible GPU-accelerated AI runtime in Kubernetes

repo collection for NVIDIA Audio2Face-3D models and tools

NVSentinel is a cross-platform fault remediation service designed to rapidly remediate runtime node-level issues in GPU-accelerated computing environments

Ancillary open source software to support confidential computing on NVIDIA GPUs

NVIDIA ACE samples, workflows, and resources

A service to convert audio to facial blendshapes for lipsyncing and facial performances.

NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the effective training time by minimizing the downtime due to failures and interruptions.

Deep Learning tools and applications for NVIDIA AGX platforms.

Examples for Recommenders - easy to train and deploy on accelerated infrastructure.

NVIDIA OptiX based implementation of ANARI

Our inference and training framework to run on the Cosmos Models

The unified framework for sim & real robot teleoperation

Accelerate your Gen AI with NVIDIA NIM and NVIDIA AI Workbench

A collection of YAML files, Helm Charts, Operator code, and guides to act as an example reference implementation for NVIDIA NIM deployment.

Help shape the future of Project G-Assist

A benchmark of real-world DL kernel problems

NVAPI is NVIDIA's core software development kit that allows direct access to NVIDIA GPUs and drivers on supported platforms.

Minimal HW-based demo of GPUDirect RDMA on NVIDIA Jetson AGX Xavier running L4T

Cosmos Curator is a powerful video curation system that processes, analyzes, and organizes video content using advanced AI models and distributed computing.

Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation

3D Object Reconstruction project is a workflow that takes a set of stereo images and camera info and outputs a textured mesh (i.e., .OBJ file). The purpose is to translate physical items into the digital world in a photorealistic way

Normalized Transformer (nGPT)

No description.

Nsight Python is a Python kernel profiling interface based on NVIDIA Nsight Tools

ALCHEMI Toolkit-Ops is a collection of optimized batch kernels to accelerate computational chemistry and material science workflows.

NVIDIA Infra Controller - Hardware Lifecycle Management and multitenant networking

An Online Deep Learning Interface for HPC programs on NVIDIA GPUs

High-performance C++/CUDA SDK for running Audio2Emotion and Audio2Face inference with integrated post-processing.

The developer-first platform for scaling complex Physical AI workloads across heterogeneous compute—unifying training GPUs, simulation clusters, and edge devices in a simple YAML

The NVIDIA GPU driver container allows the provisioning of the NVIDIA driver through the use of containers.

A repo for all spark examples using Rapids Accelerator including ETL, ML/DL, etc.

Data representations, APIs, and tools for high quality AV and robotics applications

Platform for deploying and routing GPU-accelerated inference, streaming, and batch workloads at scale.

An NVIDIA AI Workbench example project for an Agentic Retrieval Augmented Generation (RAG)

OpenShell is the safe, private runtime for autonomous AI agents.

GPU Stress Test is a tool to stress the compute engine of NVIDIA Tesla GPU’s by running a BLAS matrix multiply using different data types. It can be compiled and run on both Linux and Windows.

Ubuntu kernels which are optimized for NVIDIA server systems

The NVIDIA NeMo Agent Toolkit UI streamlines interacting with NeMo Agent Toolkit workflows in an easy-to-use web application.

An Optimizer for Nvidia Compilers.

ALCHEMI Toolkit is a developer toolkit for accelerating training and inference for AI in chemistry and material science.

DGXC Benchmarking provides recipes in ready-to-use templates for evaluating performance of specific AI use cases across hardware and software combinations.

Spark RAPIDS MLlib – accelerate Apache Spark MLlib with GPUs

DOCA Platform manages provisioning and service orchestration for Bluefield DPUs

Context-Aware RAG library for Knowledge Graph ingestion and retrieval functions.

JaxPP is a library for JAX that enables flexible MPMD pipeline parallelism for large-scale LLM training

Unified high-performance Python client for object and file stores.

Extended and advanced applications to the Rivermax SDK (Networking SDK for Media and Data Streaming).

A TUI-based utility for real-time monitoring of InfiniBand traffic and performance metrics on the local node

NVIDIA BioNeMo

A CUDA BVH Build And Query Library

Multi-language agent runtime for execution scope management, lifecycle events, and middleware on tool and LLM calls.

RAPIDS Accelerator JNI For Apache Spark

Complete Python bindings for the OptiX host API

Pipecat framework based orchestrator for building real-time, voice-enabled, and multimodal conversational AI agents

A Kubernetes Operator to manage Node OS customizations.

Our repository of community driven examples, showcases, and integrations

GPU Memory Reservation Library

XGBoost GPU accelerated on Spark example applications

NVIDIA’s repository for enabling trustworthy AI.

SimReady Foundation is a central repository for defining simulation content specifications based on various runtime use cases.

XR AI

C++ SDK that provides resources for implementing and validating Trusted Computing Solutions on NVIDIA hardware

A Python CLI workflow orchestrator with pluggable backends (e.g. local, Slurm) for running declarative YAML DAGs, collecting logs, and organizing outputs consistently.

The OptiX Wrappers Library

Harmonizer is an online generative enhancement framework that transforms renderings from imperfect scenes into temporally consistent outputs while improving their realism.

Python utilities for NVIDIA Jetson

LLM extensions for Sphinx Documentation

K8s-test-infra

A Scalable (and Optionally, Data-Parallel) ANARI Multi-GPU Path Tracer

Cosmos Evaluator is an automated evaluation & grading system for synthetic video output generated by Cosmos models

High-performance distributed rate limiting library for Go with Redis backend, sliding window algorithm, and dynamic configuration support

An OptiX/CUDA code sample showing how to quickly build ray-tracing acceleration structures for dynamic subdivision surfaces

InstantNuRec: Feed-Forward 3D Gaussian Reconstruction from Driving Logs

A comprehensive Helm chart for monitoring GPU resources in Kubernetes clusters. This tool provides real-time visibility into GPU allocation, utilization, memory usage, and pod status through an integrated Prometheus and Grafana monitoring stack.

Spark RAPIDS Container – Docker containers for Spark RAPIDS

Starting October 1, 2025, NVIDIA PSIRT will publish an initial set of security bulletins on GitHub in Markdown, CSAF, and CVE formats. Coverage will expand over time, while all bulletins remain available on the Product Security website.

The NVIDIA TensorRT RTX Execution Provider (EP) is an inference deployment solution designed specifically for NVIDIA RTX GPUs, optimized for client-centric use cases.

Linux kernel source tree

NVIDIA NMOS (Networked Media Open Specifications) Library

Validation and management tools for NVIDIA AI Cloud environments.

Synthetic Data Generation Workflows for Physical AI

DAQIRI connects high bandwidth streaming sensor data to the NVIDIA software ecosystem

The Design System and UI Agent Harness for AI/ML Factories, Robotics, and Autonomous Vehicles

Metropolis Smart-City Synthetic Data Generation Recipe allows you to generate synthetic data and then augment them. The generated data then can be used to fine-tune VLM models such as Cosmos Reason (CR).

NVIDIA fork of tianocore/edk2-platforms

User space Block device access API

NVMesh by NVIDIA provides remote shared storage facilities with in-server flash performance characteristics while using commodity off-the-shelf components.

The code distributed provides a set of utilities to facilitate the development of applications using the Rivermax API

Fork of texlive which allows hooking latex to capture structural information

K8s Launch Kit (l8k) is a CLI tool for deploying and managing NVIDIA cloud-native solutions on Kubernetes. The tool helps provide flexible deployment workflows for optimal network performance with SR-IOV, RDMA, and other networking technologies.

Monitor and react to platform events

NVIDIA Halos Outside-In Safety Blueprint extends robot perception beyond on-board sensors by using external infrastructure cameras and AI agents to dynamically control robot behavior and perform at maximum efficiency.

Agent skills for Neural Reconstruction Engine

NVIDIA Rack Management Service Rust language client crate

GFMBench-API offers a unified middleware that decouples genomic foundation model architectures from diverse tasks, standardizes data streams and metrics, & enables users to submit models through a single interface for reproducible evaluation and reporting

DeepStream OSS

Comprehensive suite for evaluating perturbation prediction models

Aerial Omniverse Digital Twin (AODT)

Reusable GitHub Actions workflows and common scripts for Spark RAPIDS

NVIDIA fork of tianocore/edk2-redfish-client

This repository contains simple examples demonstrating the use of the low-level Rivermax API

Orchestrator for LLM coding agents in Docker and Kubernetes pods

NVIDIA Game Agent SDK

This repository provides tools to ease the use of Rivermax such as tuning scripts.

NVIDIA Digital Health skills repo for agent-guided healthcare AI workflows, including evaluation, data generation, model adaptation, deployment guidance, and developer best practices.

Media Function Operator Kit