Öffentlicher GitHub-Footprint von NVIDIA Corporation

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

Build and run Docker containers leveraging NVIDIA GPUs

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.

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

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

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.

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

Transformer related optimization, including BERT, GPT

[ARCHIVED] The C++ parallel algorithms library. See https://github.com/NVIDIA/cccl

Optimized primitives for collective multi-GPU communication

Deep Learning GPU Training System

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

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.

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.

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

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.

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

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

CUDA Core Compute Libraries

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

NVIDIA GPU metrics exporter for Prometheus leveraging DCGM

A suite of image and video neural tokenizers

Simple samples for TensorRT programming

NCCL Tests

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

AI agent skills published by NVIDIA

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.

Spark RAPIDS plugin - accelerate Apache Spark with GPUs

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

GPU accelerated decision optimization

NVIDIA Federated Learning Application Runtime Environment

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

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

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

NVIDIA Material Definition Language SDK

Provides end-to-end model development pipelines for LLMs and Multimodal models that can be launched on-prem or cloud-native.

NeMo text processing for ASR and TTS

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

An SDK (Software Development Kit) for building commercial-grade, AI-native, 3GPP, and O-RAN compliant 5G/6G gNB software on NVIDIA-accelerated computing platforms.

Advanced Samples for the NVIDIA OptiX 7 Ray Tracing SDK

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

repo collection for NVIDIA Audio2Face-3D models and tools

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

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

NVIDIA OptiX based implementation of ANARI

Accelerate your Gen AI with NVIDIA NIM and NVIDIA AI Workbench

The unified framework for sim & real robot teleoperation

Our inference and training framework to run on the Cosmos Models

A benchmark of real-world DL kernel problems

Real-time rendering research framework

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

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

NVIDIA Infra Controller - Hardware Lifecycle Management and multitenant networking

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

Training material for Nsight developer tools

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

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.

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

Golang bindings for Nvidia Datacenter GPU Manager (DCGM)

Set of utilities supporting workflows common in GPU raytracing applications

Kubernetes Operator, Helm Charts, Ansible Playbooks, and utility scripts for large-scale AIStore deployments on Kubernetes.

Accelerated libraries for quantum-classical computing built on CUDA-Q.

Ubuntu kernels which are optimized for NVIDIA server systems

l2fwd-nv provides an example of how to leverage your DPDK network application with the NVIDIA GPUDirect RDMA techonology.

DOCA Platform manages provisioning and service orchestration for Bluefield DPUs

GPU Admin Tools. Includes Confidential Computing controls for H100, and other functionality

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

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

RAPIDS Accelerator JNI For Apache Spark

A Kubernetes Operator to manage Node OS customizations.

The NVIDIA Driver Manager is a Kubernetes component which assist in seamless upgrades of NVIDIA Driver on each node of the cluster.

Spark RAPIDS Benchmarks – benchmark sets and utilities for the RAPIDS Accelerator for Apache Spark

Industrial SOP Monitoring Blueprints for Training & Inference

The OptiX Wrappers Library

repo for Numba-CUDA-MLIR

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

NVIDIA's Redfish next generation redfish crate

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

Linux kernel source tree

Validation and management tools for NVIDIA ISV Lab environments.

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

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

A Rust Crate for interacting with DTMF Redfish endpoints

DSX Exchange

Packages for the Skyhook Kubernetes Operator.