NVIDIA Nsight™ Systems is a system-wide performance analysis tool designed to visualize an application’s algorithms, identify the largest opportunities to optimize, and tune to scale efficiently across any quantity or size of CPUs and GPUs, from large servers to our smallest systems-on-a-chip (SoCs).

NVIDIA DLSS is a suite of neural rendering technologies powered by GeForce RTX™ Tensor Cores that boosts frame rates while delivering crisp, high-quality images that rival native resolution. 

Reference container for Holoscan for Media, built on DeepStream, with NMOS registration and control of ST 2110 sinks and sources.

NVIDIA Cosmos™ is a platform of state-of-the-art generative world foundation models (WFMs), advanced tokenizers, guardrails, and an accelerated data processing and curation pipeline. It is built to power world model training and accelerate physical AI development for autonomous vehicles (AVs) and robots.

The NVIDIA Collective Communication Library (NCCL) implements multi-GPU and multi-node communication primitives optimized for NVIDIA GPUs and Networking. NCCL provides routines such as all-gather, all-reduce, broadcast, reduce, reduce-scatter as well as point-to-point send and receive that are optimized to achieve high bandwidth and low latency over PCIe and NVLink high-speed interconnects within a node and over NVIDIA Mellanox Network across nodes.

Nsight Cloud is a suite of cloud-native components that enable Nsight tools to profile and operate in containerized cloud, cluster, data center, and HPC environments. It streamlines the deployment of Nsight tools so you can easily profile and capture data from the CPU, GPU, network, storage, workload, API, and more.

Benchmark suite for measuring how fast systems can run models in various deployment scenarios.

A Kubernetes-aware package manager for cluster administrators to safely modify and maintain underlying hosts declaratively at scale.

Deploy NVTabular workflows and HugeCTR or TensorFlow models to Triton Inference server for production.

NVIDIA Nsight™ Compute is an interactive profiler for CUDA® and NVIDIA OptiX™ that provides detailed performance metrics and API debugging via a user interface and command-line tool. Users can run guided analysis and compare results with a customizable and data-driven user interface, as well as post-process and analyze results in their own workflows.

Explore the NVIDIA® Cumulus® Linux architecture, the industry’s most innovative open network operating system, which was developed under the guiding principles of easy implementation and management, customization, and scalability.

Simplifies cross-compilation of JetPack components on x86 hosts with pre-configured tools and environment.

Enables preprocessing, feature engineering with NVTabular, and training deep-learning recommenders with PyTorch.

The RAPIDS™ Accelerator for Apache Spark is a plug-in that leverages RAPIDS libraries and GPUs to accelerate data processing and machine learning pipelines on Apache Spark. It transforms existing pipelines without any code change.

A suite of management utilities for InfiniBand fabrics, including diagnostic tools and simulators.

Verifies that the container runtime is set up correctly for GPUs and InfiniBand before running HPC or Deep Learning models.

NVIDIA Mission Control™ powers every aspect of AI factory operations — from developer workloads to infrastructure to facilities — with the skills of a world-class operations team delivered as software. 

Achieve world-record speed on large-scale problems with millions of constraints and variables—saving time and reducing costs. NVIDIA® cuOpt™ is an open-source, GPU-accelerated solver for decision optimization, excelling in mixed-integer linear programming (MILP), linear programming (LP), and vehicle routing problems (VRPs).

NVIDIA IndeX™ is a leading volume visualization tool for HPC that helps to meet this challenge. It takes advantage of the GPU’s computational horsepower to deliver real-time performance on large datasets by distributing visualization workloads across a GPU-accelerated cluster.

GeForce NOW is NVIDIA's cloud gaming service that transforms your devices into powerful gaming rigs with RTX performance.

NVIDIA DriveOS™ is an automotive operating system developed with industry-standard safety and security methodologies certified by the globally renowned automotive certification organization, TÜV SÜD.

Tokkio Envoy is a proxy service used in the Tokkio application for efficient communication and data handling.

NVIDIA Nsight™ tools are a powerful set of libraries, SDKs, and developer tools spanning across desktop and mobile targets that enable developers to build, debug, profile, and develop software that utilizes the latest accelerated computing hardware.

The NVIDIA CUDA® Deep Neural Network library (cuDNN) is a GPU-accelerated library of primitives for deep neural networks. cuDNN provides highly tuned implementations for standard routines such as forward and backward convolution, attention, matmul, pooling, and normalization.

Hyper-personalize large language models for enterprise AI applications and deploy them at scale.

NVIDIA NeMo™ Retriever is a collection of microservices for building multimodal extraction, reranking, and embedding pipelines with high accuracy and maximum data privacy. It delivers quick, context-aware responses for AI applications like advanced retrieval-augmented generation (RAG) and agentic AI workflows. 

NVIDIA JetPack SDK powering the Jetson modules is the most comprehensive solution for building end-to-end accelerated AI applications, significantly reducing time to market.

ACE Agent UI Client provides a web interface for interacting with ACE Agent bots through a browser.

The NVIDIA App is the essential companion for PC gamers and creators. Keep your PC up to date with the latest NVIDIA drivers and technology. Optimize games and applications with a new unified GPU control center, capture your favorite moments with powerful recording tools through the in-game overlay, and discover the latest NVIDIA tools and software.

NVIDIA Compute Sanitizer ensures GPU code correctness with tools for memory checks, race condition detection, and synchronization validation.

Accelerate edge AI development with real-time sensor data processing on NVIDIA hardware.

The DOCA Flow Inspector service allows monitoring real-time data and extracting telemetry components for security, big data, and other telemetry-based services.

NVIDIA cuTENSOR is a GPU-accelerated tensor linear algebra library for tensor contraction, reduction, and elementwise operations. Using cuTENSOR, applications can harness the specialized tensor cores on NVIDIA GPUs for high-performance tensor computations and accelerate deep learning training and inference, computer vision, quantum chemistry, and computational physics workloads.

The NVIDIA CUDA Profiling Tools Interface (CUPTI) is a library that enables the creation of profiling and tracing tools that target CUDA applications. 

NVIDIA DGX Cloud Benchmarking optimizes AI workload performance with standardized tools, recipes, and services for measuring AI infrastructure.

Deep neural network training and inference framework for recommender systems with distributed training and model-parallel embedding tables.

Sionna is a GPU-accelerated open-source library for research in communication systems. It is differentiable and features a lightning-fast ray tracer for radio propagation, a versatile link-level simulator, and system-level simulation capabilities.

NVIDIA Driver Manager for Kubernetes ensures seamless upgrades of NVIDIA drivers on each node in a Kubernetes cluster.

A comprehensive set of APIs including high-performance tools, samples and documentation for hardware-accelerated video encode and decode on Windows and Linux.

An application framework for achieving optimal ray tracing performance on the GPU. It provides a simple, recursive, and flexible pipeline for accelerating ray tracing algorithms. Bring the power of NVIDIA GPUs to your ray tracing applications with programmable intersection, ray generation, and shading.

NVIDIA Kaolin Library accelerates 3D deep learning research with GPU-optimized operations and modular differentiable rendering.

DCGM Exporter monitors NVIDIA GPUs in Kubernetes using Prometheus for health and metrics collection.

NVIDIA Base CommandTM powers the NVIDIA DGXTM platform, enabling organizations to leverage the best of NVIDIA AI innovation. With it, every organization can tap the full potential of their DGX infrastructure with a proven platform that includes AI workflow management, enterprise-grade cluster management, libraries that accelerate compute, storage, and network infrastructure, and system software optimized for running AI workloads.

Tokkio Reference ACE Controller utilizes Pipecat for real-time, voice-enabled, multimodal conversational AI agents.

NVIDIA Air enables cloud-scale efficiency by creating identical replicas of real-world data center infrastructure deployments. NVIDIA Air allows users to model data center deployments with full software functionality, creating a digital twin. Transform and accelerate time to AI by simulating, validating, and automating changes and updates.

NVIDIA DGX Cloud Lepton connects developers to global GPU compute, simplifying multi-cloud AI development and deployment.

NVIDIA Magnum IO™ is the architecture for parallel, intelligent data center IO. It maximizes storage, network, and multi-node, multi-GPU communications for the world’s most important applications, using large language models, recommender systems, imaging, simulation, and scientific research.

NVIDIA virtual GPU (vGPU) software enables powerful GPU performance for workloads ranging from graphics-rich virtual workstations to data science and AI, enabling IT to leverage the management and security benefits of virtualization as well as the performance of NVIDIA GPUs required for modern workloads.

NVIDIA Reflex enables game developers to optimize the rendering pipeline for click-to-photon latency, providing responsive gameplay for esports and latency sensitive single player games.

Accelerate drug discovery with NVIDIA BioNeMo™ for biopharma, a collection of frameworks, applications, generative AI solutions, and pretrained models.

NVIDIA SDK Manager provides an end-to-end development environment setup solution for NVIDIA’s Jetson, Holoscan, Rivermax, DeepStream, GXF Runtime, Aerial Research Cloud (ARC-OTA), Ethernet Switch, RAPIDS, DRIVE and DOCA SDKs for both host and target devices.

NVIDIA cuSPARSE provides GPU-accelerated basic linear algebra routines for sparse matrix computations, enhancing performance in various applications.

NVIDIA DIGITS rapidly trains deep neural networks for image classification, segmentation, and object detection tasks.

NVIDIA GPUDirect Storage creates a direct data path between storage and GPU memory, enhancing application performance by reducing CPU load.

NVIDIA nvTIFF is a GPU-accelerated TIFF encode/decode library optimized for handling large, complex image datasets.

NVIDIA AI on RTX delivers cutting-edge AI capabilities on RTX GPUs, enhancing productivity, creativity, and gaming experiences.

Drives conversation flow for bots built using ACE Agent, maintaining user context and conversational history.

NVIDIA NeMo™ Agent toolkit is an open-source library that provides framework-agnostic profiling and optimization for production AI agent systems. By exposing hidden bottlenecks and costs, it helps enterprises scale agentic systems efficiently while maintaining reliability.

NVIDIA SHARP accelerates data processing by offloading collective operations to the network, reducing latency and increasing throughput.

Audio2Face converts speech into facial animation using ARKit blendshapes, integrating server and client functionalities.

NVIDIA MLNX\_OFED supports high-performance I/O with InfiniBand and Ethernet, optimized for RDMA and kernel bypass APIs.

Nsight Deep Learning (DL) Designer is an integrated development environment that helps developers efficiently design and optimize deep neural networks for high-performance inference. It's built atop the industry standard ONNX model format and popular inference solutions like TensorRT™ and ONNX Runtime.

NVIDIA Virtual Reality Capture and Replay (VCR) enables developers and users to accurately capture and replay VR sessions for performance testing, scene troubleshooting, and more. The tool records time-stamped HMD and controller inputs during an immersive VR session; the user can subsequently replay that recording, without an HMD attached, to precisely reproduce the session.

The Kickstart RT SDK enables developers to get more realistic dynamic lighting into their game engines in a much shorter timespan than traditional methods. It is a cross-API, cross platform solution that brings real-time ray-traced reflections, shadows, ambient occlusion and global illumination to game engines.

NVIDIA Data Center GPU Manager (DCGM) is a suite of tools for managing and monitoring NVIDIA Datacenter GPUs in cluster environments. It includes active health monitoring, comprehensive diagnostics, system alerts, and governance policies including power and clock management. 

The NVIDIA® CUDA® Toolkit provides a development environment for creating high-performance, GPU-accelerated applications. With it, you can develop, optimize, and deploy your applications on GPU-accelerated embedded systems, desktop workstations, enterprise data centers, cloud-based platforms, and supercomputers. 

NVIDIA NPP is a library of over 5,000 GPU-accelerated image and signal processing primitives, enhancing performance up to 30X faster than CPU-only implementations.

NVIDIA GPU Driver containerizes the NVIDIA driver for easy deployment, fast installation, and reproducibility in Linux environments.

Container for Tokkio ingress, providing routing, authentication, authorization, and session management.

NVIDIA Merlin NVTabular accelerates feature engineering and preprocessing for GPU-accelerated recommender systems.

NVIDIA cuQuantum is an SDK of optimized libraries and tools that accelerate quantum computing emulations at both the circuit and device level by orders of magnitude.

NVIDIA AI Aerial is a suite of accelerated computing platforms, software, and services for designing, simulating, and operating wireless networks. 

The NVIDIA Data Loading Library (DALI) is a portable, open-source software library for decoding and augmenting images, videos, and speech to accelerate deep learning applications. DALI reduces data access latency and training time, mitigating bottlenecks by overlapping AI training and data pre-processing.

NVIDIA NIM™ provides prebuilt, optimized inference microservices for rapidly deploying the latest AI models on any NVIDIA-accelerated infrastructure—cloud, data center, workstation, and edge.

NVIDIA cuDSS is a GPU-accelerated Direct Sparse Solver library for solving linear systems with very sparse matrices, optimized for real-time applications.

Streamline is an open-sourced cross-IHV solution that simplifies integration of the latest NVIDIA and other independent hardware vendors’ super resolution technologies into applications and games. This framework allows developers to easily implement one single integration and enable multiple super-resolution technologies and other graphics effects supported by the hardware vendor.

NVIDIA CUDA-X, built on top of CUDA®, is a collection of microservices, libraries, tools, and technologies for building applications that deliver dramatically higher performance than alternatives across data processing, AI, and high-performance computing (HPC).

A development sandbox for researchers, data scientists, developers, and clinical teams to build medical AI workflows.

The nvImageCodec is a library of accelerated codecs with a unified interface. It is designed as a framework for extension modules that deliver codec plugins. The library supports GPU-accelerated image processing codecs, including nvJPEG, nvJPEG2000, and nvTIFF, along with fallback options to provide comprehensive support for CPU-based codecs.

Standardized toolkit for evaluating Retrieval Augmented Generation (RAG) and Retriever pipelines.

NVIDIA NeMo™ framework supports enterprise development of LLMs and generative AI models with automated data processing, model training techniques, and flexible deployment options.

Nvblox is a library for real-time 3D reconstruction and mapping, optimized for NVIDIA GPUs and Jetson devices.

CUDA-Q is an open-source quantum development platform orchestrating the hardware and software needed to run useful, large-scale quantum computing applications.

RAPIDS cuCIM is an open-source, GPU-accelerated library for multidimensional image processing in biomedical, geospatial, and life sciences.

NVIDIA DGX Cloud is a unified AI platform optimized for performance with software, services, and AI expertise for evolving workloads.

Power unprecedented speed and accuracy in precision genomics with the NVIDIA Clara™ for Genomics software suite.

Create block-compressed textures and write custom asset pipelines using NVTT 3, an SDK for CUDA-accelerated texture compression and image processing.

NVIDIA Halos is a full-stack, comprehensive safety system that unifies vehicle architecture, AI models, chips, software, tools, and services to ensure the safe development and deployment of autonomous vehicles (AVs) from cloud to car.

NVIDIA Windows Management Instrumentation (NVWMI) is a scripting and management tool that allows IT administrators to configure GPU settings, retrieve GPU information, perform automated tasks, and build instrumentation panels across networks.

NVIDIA Clara™—fast-track healthcare with digital human technologies for patient engagement and multimodal AI agents for clinical development.

RAPIDS cuDF is a Python GPU DataFrame library for fast data manipulation, built on Apache Arrow for data engineers and scientists.

The NVIDIA cuSOLVER library provides a collection of dense and sparse direct linear solvers and Eigen solvers which deliver significant acceleration for Computer Vision, CFD, Computational Chemistry, and Linear Optimization applications. 

A dermatology reference application for the Clara AGX platform using computer vision models for mole detection and classification.

Facilitates management and integration of A2F microservice with a bi-directional API for streamlined workflows.

NVIDIA GPU Operator manages GPU resources in Kubernetes, automating tasks like driver installation and monitoring.

The NVIDIA® Nsight™ Perf SDK is a graphics profiling toolbox for DirectX, Vulkan, and OpenGL enabling you to collect GPU performance metrics directly from your application.

Zero-code-change scaling to multi-GPU and multi-node accelerated computing for Python and NumPy.

AmgX provides a simple path to accelerated core solver technology on NVIDIA GPUs. AmgX provides up to 10x acceleration to the computationally intense linear solver portion of simulations, and is especially well suited for implicit unstructured methods.

NVIDIA DGX Platform is a unified AI development solution, combining NVIDIA software, infrastructure, and expertise for enterprise AI.

NVIDIA Nsight™ Visual Studio Code Edition (VSCE) is an application development environment for heterogeneous platforms that brings CUDA® development for GPUs on Linux and QNX target systems into Microsoft Visual Studio Code. NVIDIA Nsight™ VSCE enables you to build and debug GPU kernels and native CPU code as well as inspect the state of the GPU and memory.

NVIDIA Nsight™ Graphics is a standalone developer tool with ray-tracing support that enables you to debug, profile, and export frames built with Direct3D, Vulkan, OpenGL, OpenVR, and the Oculus SDK.

Provides HTTP endpoint to monitor system health and track system capacity for Tokkio application.

NVIDIA Base Command Manager offers fast deployment and end-to-end management for AI and HPC clusters across edge, data center, and multi-cloud environments.

DOCA UROM offloads High-Performance Computing computations from the host to the DPU, managing resources and workers.

NVIDIA Warp is an open-source developer framework for building and accelerating data generation and spatial computing in Python. Warp gives coders an easy way to write GPU-accelerated, kernel-based programs for simulation AI, robotics, and machine learning (ML).

Tokkio UI Server provides an interface for the Tokkio UI to interact with the rest of the application.

NVIDIA HPC-Benchmarks provides four accelerated benchmarks for high-performance computing on NVIDIA GPUs and CPUs.

GPU-accelerated cross-filtering dashboards from notebooks with Python, integrated with HoloViz ecosystem.

OSMO is a cloud-native orchestration platform for scaling complex, multi-stage, and multi-container ‌robotics workloads, across on-premises, private, and public clouds.

Nsight Streamer for Nsight Systems enables remote access to NVIDIA Nsight Tools GUI via a Docker container.

NVIDIA RTX Virtual Workstation (vWS) software combined with our world-leading GPUs is a dynamic force to accelerate graphics-intensive, engineering, data science, and AI workloads from the data center or cloud to any device.

NVIDIA Rivermax SDK offers optimized networking for media and data streaming with minimal CPU utilization and high throughput.

NVIDIA Parabricks accelerates genomics workflows, supporting DNA, RNA, and somatic mutation detection with industry-leading compute times.

Wraps the Omniverse RTX real-time renderer to render a single avatar and its scene in real-time.

GDRCopy is a low-latency GPU memory copy library based on GPUDirect RDMA technology that allows the CPU to directly map and access GPU memory. GDRCopy also provides optimized copy APIs and is widely used in high-performance communication runtimes like UCX, OpenMPI, MVAPICH, and NVSHMEM.

A set of APIs for computing the relative motion of pixels between images using NVIDIA GPUs.

Facilitates training, evaluation, and performance comparison of ASR models with domain-specific data.

NVIDIA cuLitho is a library with optimized tools and algorithms for GPU-accelerating computational lithography and the manufacturing process of semiconductors by orders of magnitude over current CPU-based methods.

nvJPEG is a high-performance GPU-accelerated library for decoding, encoding, and transcoding JPEG format images.

Framework for developing, training, and deploying large-scale bio-based models with pre-trained models and custom workflows.

NVIDIA Merlin is an open-source framework for building high-performing recommender systems at scale, streamlining the entire pipeline.

NVIDIA Omniverse Enterprise integrates OpenUSD, RTX rendering, and generative AI into production-grade physical AI applications for industrial digitalization.

NVIDIA DGX Cloud Create is a fully managed AI training platform on leading clouds, delivering productivity from day one.

Process streaming data in real time with scalable, software-defined devices built with the NVIDIA Clara™ for Medical Devices platform.

Train object 3D pose estimation models using Isaac Sim for simulation and real-world testing.

RAPIDS cuGraph is a GPU-accelerated library for graph analytics, seamlessly integrating with RAPIDS data science ecosystem.

Visualize 4D image-based feature map data with detailed numerical information for deep learning model insights.

NVIDIA FLARE™ (NVIDIA Federated Learning Application Runtime Environment) is a domain-agnostic, open-source, and extensible SDK for Federated Learning. It allows researchers and data scientists to adapt existing ML/DL workflow to a federated paradigm and enables platform developers to build a secure, privacy-preserving offering for a distributed multi-party collaboration.

The open-source TAO for AI training and optimization delivers everything you need, putting the power of the world’s best Vision Transformers (ViTs) in the hands of every developer and service provider. You can now create state-of-the-art computer vision models and deploy them on any device—GPUs, CPUs, and MCUs—whether at the edge or in the cloud.

Injects NVIDIA Nsight Tools into Kubernetes pods for profiling and analyzing applications.

The NVIDIA® DriveWorks SDK is the foundation for autonomous vehicle (AV) software development. It provides an automotive-grade middleware with accelerated algorithms and versatile tools.

CV-CUDA™ is an open-source library that enables building high-performance, GPU-accelerated pre- and post-processing for AI computer vision applications in the cloud at reduced cost and energy.

NVIDIA Capture SDK (formerly GRID SDK) enables developers to easily and efficiently capture, and optionally encode, the display content.

NVIDIA PhysicsNeMo is an open-source Python framework for building, training, and fine-tuning physics AI models at scale. NVIDIA PhysicsNeMo provides utilities that enable developers to build AI surrogate models that combine physics-driven causality with simulation and observed data, enabling real-time predictions.

MONAI Label accelerates medical imaging AI with intelligent image annotation and active learning for faster, accurate, and consistent results.

Complete streaming analytics toolkit for AI-based multi-sensor processing, video, audio, and image understanding.

The MONAI Model Zoo is a collection of pre-trained medical imaging models, ready for research and clinical deployment. Each model is packaged in the MONAI Bundle format, ensuring reproducibility and ease of use.

ACE Agent Chat Controller orchestrates the end-to-end bot pipeline for a speech IO-based bot.

NVIDIA cuBLAS is a GPU-accelerated library for accelerating AI and HPC applications. It includes several API extensions for providing drop-in industry standard BLAS APIs and GEMM APIs with support for fusions that are highly optimized for NVIDIA GPUs. The cuBLAS library also contains extensions for batched operations, execution across multiple GPUs, and mixed- and low-precision execution with additional tuning for the best performance.

Tokkio SDR handles stream distribution and routing logic in the Tokkio application.

NVIDIA cuVS is an open-source library for GPU-accelerated vector search and data clustering that enables faster vector searches and index builds. It supports scalable data analysis, enhances semantic search efficiency, and helps developers accelerate existing systems or compose new ones from the ground up. 

NVIDIA® Nsight™ Aftermath is a library that integrates into a D3D12 or Vulkan game’s crash reporter to generate GPU “mini-dumps” when an exception or TDR occurs, exposing pipeline information to resolve an unexpected crash.

NVIDIA CloudXR™ is designed to provide seamless, high-fidelity immersive streaming to extended reality (XR) devices over any network. The CloudXR Suite is a set of tools that enables developers to stream XR applications.

Thrust is a powerful library of parallel algorithms and data structures. Thrust provides a flexible, high-level interface for GPU programming that greatly enhances developer productivity.

A set of firmware management tools for generating, querying, and burning NVIDIA firmware images.

NVIDIA vMaterials is a curated collection of MDL materials and lights for design, architecture, engineering, and construction workflows.

An Operator for deploying and maintaining NVIDIA NIMs and NeMo microservices in Kubernetes environments.

NVIDIA Omniverse for Developers is a modular platform of SDKs, APIs, and microservices for building 3D applications powered by OpenUSD and RTX.

Build and seamlessly integrate advanced simulation and generative AI technologies into your existing complex 3D workflows.

NVIDIA Virtual PC accelerates productivity apps and delivers an incredible user experience for remote work with NVIDIA GPUs.

NVIDIA PhysX® is a powerful, open-source multi-physics SDK that provides scalable simulation and modeling capabilities for robotics and autonomous vehicle applications.

NVIDIA AI Enterprise is a cloud-native suite of software tools, libraries, and frameworks for developing, deploying, and scaling AI applications.

NVIDIA App for Enterprise optimizes GPU settings, records desktops in up to 8K, and provides driver updates for NVIDIA RTX™ graphics cards.

NVIDIA AI Workbench is a free development environment manager for data scientists and developers to create, customize, and collaborate on AI applications on GPU systems. Focus on execution and let AI Workbench manage your containers, environment, and configurations.

Deploy and scale models on your GPU infrastructure of choice with NVIDIA NIM inference microservices.

NVIDIA Transformer Engine accelerates Transformer models on NVIDIA GPUs, using FP8 precision for better performance and lower memory utilization.

nvJPEG2000 is a high-performance GPU-accelerated library for decoding JPEG 2000 format images, ideal for deep learning and medical imaging.

Tokkio Context Injector maintains application context within the Tokkio application, ensuring seamless operation and integration.

MONAI Deploy provides a standardized framework that simplifies deployment while ensuring reliability, performance, and seamless integration with existing healthcare infrastructure.

NVIDIA DOCA™ unlocks the potential of the NVIDIA® BlueField® networking platform. By harnessing the power of BlueField DPUs and SuperNICs, DOCA enables the rapid creation of applications and services that offload, accelerate, and isolate data center workloads.

GPU-accelerated library for vector search and clustering, optimized for high performance and scalability.

NVIDIA® TensorRT™ is an ecosystem of tools for developers to achieve high-performance deep learning inference. TensorRT includes inference compilers, runtimes, and model optimizations that deliver low latency and high throughput for production applications. 

Tokkio UMIM Action Server provides UMIM compatibility for Tokkio, working with ACE Agent Chat Controller.

Streamline the provisioning and deployment of systems and AI applications at the edge with NVIDIA Fleet Command. A managed platform for container orchestration, it simplifies the management of distributed computing environments with the scale and resiliency of the cloud, turning every site into a secure, intelligent location.

Injects NVIDIA DevTools into Kubernetes pods to facilitate profiling and analyzing applications inside these pods.

Falcor is an open-source real-time rendering framework designed for rapid prototyping with advanced graphics features.

Integrates various NLP models in bots built using ACE Agent with a unified RESTful interface.

Accelerate the development of medical AI applications to streamline clinical workflows and drive innovation.

NVIDIA Isaac™ Manipulator, built on Isaac ROS, is a collection of NVIDIA® CUDA®-accelerated libraries, AI models, and reference workflows. It’s designed to help robotics software developers build AI-enabled robot arms—or manipulators—that can perceive, understand, and interact with their environments. 

NVIDIA Magnum IO Developer Environment scales applications on laptops, desktops, workstations, or in the cloud with comprehensive I/O tools.

Video Storage Toolkit (VST) efficiently manages cameras and videos on Jetson platforms with hardware-accelerated video decoding, streaming, and storage.

NVAPI is NVIDIA's core software development kit, designed for direct access to NVIDIA GPUs and drivers on supported Windows platforms. It supports a wide range of operations that go beyond the typical capabilities of graphics APIs like DirectX and OpenGL.

The NVIDIA Dynamo Platform is a high-performance, low-latency inference platform designed to serve all AI models across any framework, architecture, or deployment scale.

NVIDIA HPC Software Development Kit (SDK) includes the proven compilers, libraries and software tools essential to maximizing developer productivity and the performance and portability of HPC applications.

NVIDIA RTX™ Kit is a suite of neural rendering technologies to ray trace games with AI, render scenes with immense geometry, and create game characters with photo-realistic visuals.

NVIDIA Run:ai accelerates AI and machine learning operations by addressing key infrastructure challenges through dynamic resource allocation, comprehensive AI life-cycle support, and strategic resource management. 

NVIDIA vGPU Device Manager manages vGPU devices on GPU nodes in Kubernetes clusters, defining and applying vGPU configurations.

The NVIDIA Broadcast app transforms any room into a home studio. Take your livestreams, voice chats, and video conference calls to the next level with AI-enhanced voice and video.

NVIDIA® Nsight™ Visual Studio Edition is an application development environment for heterogeneous platforms which brings GPU computing into Microsoft Visual Studio. NVIDIA® Nsight™ VSE allows you to build and debug integrated GPU kernels and native CPU code as well as inspect the state of the GPU and memory.

Triton Inference Server deploys AI models from any framework on any GPU or CPU infrastructure, supporting cloud and edge inferencing.

Provides a lightweight environment to flash Jetson Linux without installing prerequisites on your host.

Your low-code framework for developing cloud-native, real-time, and multimodal AI applications.

NVIDIA Isaac™ Perceptor, built on Isaac ROS, is a collection of NVIDIA® CUDA®-accelerated libraries, AI models, and reference workflows for the development of autonomous mobile robots (AMRs). These robots are designed to perceive, localize, and operate in unstructured environments like warehouses, factories, and outdoor settings.

NVIDIA Network Operator simplifies provisioning and managing NVIDIA networking resources in Kubernetes clusters.

Run inference and post-training on Cosmos-Predict2 models for future state prediction and visual simulation.

NVIDIA ACE brings game characters and digital assistants to life with generative AI, offering state-of-the-art models and flexible deployment.

Manages Confidential Computing modes on NVIDIA GPUs in a Kubernetes cluster.

NVIDIA Metropolis is a vision AI application platform and partner ecosystem that simplifies the development, deployment, and scalability of visual AI agents deployed from the edge to the cloud.

NVIDIA vApps accelerates application streaming with GPU sharing, enabling full performance on any device, anywhere.

NVIDIA nvCOMP is a high-speed data compression and decompression library optimized for NVIDIA GPUs. Data compression is an essential part of applications for AI training, high-performance computing (HPC), data science, and analytics. As these applications grow in size and complexity, they demand highly optimized and performant compression and decompression capabilities.

RAPIDS cuML is a suite of fast, GPU-accelerated machine learning algorithms designed for data science and analytical tasks.

Reusable Accelerated Functions and Tools for CUDA-accelerated machine learning and information retrieval.

GeForce Game Ready Drivers deliver the best gaming experience, optimized for performance and reliability.

DOCA Telemetry Service (DTS) collects and exports telemetry data using Prometheus, Fluent Bit, Open Telemetry, and netflow.

High-performance file I/O library with C++ and Python bindings for GPUDirect Storage (GDS).

NeMo Retriever Extraction is a scalable microservice for document content and metadata extraction, supporting various document types.

A toolkit for building native Omniverse applications and microservices with a wide variety of functionality through light-weight extensions.

The NVIDIA Material Definition Language (MDL) SDK is a set of tools to enable quick integration of physically-based materials into rendering applications. It contains comprehensive C++ and Python APIs that allow applications to load MDL modules, analyze, and understand the structure of a material so it can build a UI for material editing and render the results. 

A powerful and flexible node-based system for creating animation state machines and blend trees.

nvmath-python (Beta) is an open source library that gives Python applications high-performance pythonic access to the core mathematical operations implemented in the NVIDIA CUDA-X™ Math Libraries for accelerated library, framework, deep learning compiler, and application development.

NVIDIA Clara™ is a suite of computing platforms, software, and services that powers AI solutions for healthcare and life sciences, from imaging and instruments to genomics and drug discovery.

NVIDIA NeMo™ Curator improves generative AI model accuracy by processing text, image, and video data at scale for training and customization. It also provides pre-built pipelines for generating synthetic data to customize and evaluate generative AI systems.

With game-changing speed, NVIDIA Studio delivers transformative performance in video editing, 3D rendering, and design. Accelerate your most demanding workflows with exclusive RTX™ and AI-powered tools. Studio Drivers deliver exceptional stability and ensure your creative apps are always up to date. Unlock creativity without limits.

Pure SONiC through NVIDIA removes distribution limitations and lets enterprises take full advantage of the benefits of open networking—as well as the NVIDIA expertise, experience, training, documentation, professional services, and support that best guarantee success.

NVIDIA Blueprints offer preconfigured AI reference workflows with sample applications, AI agents, and deployment instructions.

NVIDIA NeMo™ Guardrails simplifies scalable AI guardrail orchestration for safeguarding generative AI applications. With NeMo Guardrails, you can define, orchestrate, and enforce multiple AI guardrails to ensure the safety, security, accuracy, and topical relevance of large language model (LLM) interactions.

VRWorks™ is a comprehensive suite of APIs, libraries, and engines that enable application and headset developers to create amazing virtual reality experiences. VRWorks enables a new level of presence by bringing physically realistic visuals, sound, touch interactions, and simulated environments to virtual reality.

NVIDIA Omniverse Farm™ orchestrates and distributes tasks across computing clusters for rendering, simulation, and more.

NVIDIA cuFFT, a library that provides GPU-accelerated Fast Fourier Transform (FFT) implementations, is used for building applications across disciplines, such as deep learning, computer vision, computational physics, molecular dynamics, quantum chemistry, and seismic and medical imaging.

NVSHMEM™ is a parallel programming interface based on OpenSHMEM that provides efficient and scalable communication for NVIDIA GPU clusters. NVSHMEM creates a global address space for data that spans the memory of multiple GPUs and can be accessed with fine-grained GPU-initiated operations, CPU-initiated operations, and operations on CUDA® streams.

NVIDIA DGX™ Cloud Serverless Inference is a high-performance, serverless AI inference solution that accelerates AI innovation with auto-scaling, cost-efficient GPU utilization, multi-cloud flexibility, and seamless scalability.

Allows preprocessing, feature engineering with NVTabular, and training deep-learning recommenders with TensorFlow.

NVIDIA NetQ™ is a highly scalable, modern network operations toolset that provides visibility, troubleshooting, and validation of your Cumulus fabrics in real time. NetQ utilizes telemetry and delivers actionable insights about the health of your data center network, ensuring your AI network fabric is operating smoothly.

NVIDIA XLIO accelerates network processing by offloading tasks to the network interface card (NIC), reducing latency and increasing throughput.

ACE Agent Model Utils deploys models for conversational AI agents, including training and downloading from NGC.

NVIDIA Isaac Sim™ is a reference application built on NVIDIA Omniverse™ that enables developers to simulate and test AI-driven robotics solutions in physically based virtual environments.

NVIDIA GPU Feature Discovery automatically generates labels for GPUs in Kubernetes nodes using Node Feature Discovery.

NVIDIA Isaac™ Lab is an open-source, unified framework for robot learning designed to help train robot policies. Isaac Lab is developed on NVIDIA Isaac Sim™, providing high-fidelity physics simulation using NVIDIA PhysX® and physically based NVIDIA RTX™ rendering. 

A high-performance multi-GPU, multi-node solution for quantum circuit simulation with NVIDIA’s cuStateVec and cuTensorNet libraries.

NVIDIA® HPC-X® is a comprehensive software package that includes Message Passing Interface (MPI), Symmetrical Hierarchical Memory (SHMEM) and Partitioned Global Address Space (PGAS) communications libraries, and various acceleration packages. 

Riva Speech Skills is a scalable Conversational AI service platform with pre-trained models for real-time performance.

NVIDIA Isaac™ ROS (Robot Operating System) is a collection of NVIDIA® CUDA®-accelerated computing packages and AI models designed to streamline and expedite the development of advanced AI robotics applications.

Tokkio Ingress Manager routes and secures incoming requests to the backend server, managing traffic, authentication, and session handling.

Validator for NVIDIA GPU Operator ensures all components of NVIDIA GPU Operator are functioning correctly in Kubernetes clusters.

NVIDIA Maxine™ is a collection of high-performance, easy-to-use, NVIDIA NIM™ microservices and SDKs for deploying AI features that enhance audio, video, and augmented reality (AR) effects for video conferencing and telepresence. 

NGC Catalog offers GPU-accelerated AI models, SDKs, and tools for building and deploying AI applications at lightning speed.

NVIDIA RTX™ Desktop Manager software allows you to manage single or multi-monitor workspaces with ease, giving you maximum flexibility and control over your display real estate and desktops.

NVIDIA Isaac™ GR00T is a research initiative and development platform for developing general-purpose robot foundation models and data pipelines to accelerate humanoid robotics research and development.

NVIDIA UFM revolutionizes data center networking management with real-time telemetry, AI-powered cyber intelligence, and analytics.

Downloads resource files (e.g., avatar USD scene) onto the persistent volume of the microservice pod from NGC.

NVIDIA-maintained fork of BVLC Caffe, optimized for NVIDIA GPUs, especially in multi-GPU configurations.

Enables preprocessing, feature engineering with NVTabular, and training deep-learning recommenders with TensorFlow.

NVIDIA’s Project Mellon adds natural language commands to interactive applications. Project Mellon is a lightweight Python package harnessing the power of large language models (LLM) and speech AI to transform user experiences. NVIDIA Speech AI has the power to dramatically enhance the human-software interface.

NVIDIA DPDK provides fast packet processing and low latency with optimized NIC drivers for high-speed networking applications.

MONAI Core is a freely available, community-supported, PyTorch-based framework for deep learning in healthcare imaging. It provides domain-optimized foundational capabilities for developing healthcare imaging training workflows in a native PyTorch paradigm.

NVIDIA VMA accelerates messaging applications by offloading network processing to the network interface card (NIC).

The NVIDIA CUDA Random Number Generation library (cuRAND) delivers high performance GPU-accelerated random number generation (RNG). The cuRAND library delivers high quality random numbers 8x faster using hundreds of processor cores available in NVIDIA GPUs. The cuRAND library is included in both the NVIDIA HPC SDK and the CUDA Toolkit.

NVIDIA Morpheus is a GPU-accelerated, end-to-end AI framework for enterprise developers to build, customize, and scale cybersecurity applications anywhere—at a lower cost. 

RTX Remix is an open-sourced platform that allows modders to easily capture game assets, automatically enhance materials with generative AI tools, and create stunning RTX remasters that feature full ray tracing and neural rendering technologies including DLSS 4 with Multi Frame Generation.

A software framework for monitoring NVIDIA DGX nodes, providing health monitoring, system alerts, and log generation.

NVIDIA WaveWorks delivers cinematic-quality ocean simulation for interactive applications using spectral wave models and FFT transformations.

NVIDIA® Riva is a collection of GPU-accelerated multilingual speech and translation microservices for building fully customizable, real-time conversational AI pipelines.

Enables preprocessing, feature engineering, training with HugeCTR, and serving models with Triton Inference Server.

When developing massively parallel applications on the GPU, you need a debugger capable of handling thousands of threads running simultaneously on each GPU in the system. CUDA-GDB delivers a seamless debugging experience that allows you to debug both the CPU and GPU portions of your application simultaneously.

NVIDIA Brev provides streamlined access to NVIDIA GPU instances on popular cloud platforms, automatic environment setup, and flexible deployment options, enabling developers to start experimenting instantly.

NVIDIA Kubernetes Device Plugin registers GPUs as compute resources in Kubernetes clusters, enabling GPU-accelerated workloads.

NVIDIA MIG Manager for Kubernetes manages MIG partitions with simple label changes to nodes, ensuring seamless GPU configuration.

Allows preprocessing, feature engineering with NVTabular, and training deep-learning recommenders with PyTorch.

NVIDIA cuPQC is an SDK of optimized libraries for implementing GPU-accelerated Post-Quantum Cryptography (PQC) workflows—especially crucial in high-throughput data environments.

Allows adding use case or domain-specific business logic in bots using a FastAPI-based server.

Kubevirt GPU Device Plugin discovers and exposes NVIDIA GPUs and vGPUs on Kubernetes nodes for Kubevirt VMs.

NVIDIA Cluster Agent (NVCA) orchestrates GPU clusters for NVIDIA Cloud Functions, bridging on-premises and cloud-based GPU infrastructure.

RAPIDS™, part of NVIDIA CUDA-X, is an open-source suite of GPU-accelerated data science and AI libraries with APIs that match the most popular open-source data tools. It accelerates performance by orders of magnitude, at scale, across data pipelines.

NVIDIA Container Toolkit enables building and running GPU-accelerated Docker containers with automatic configuration for NVIDIA GPUs.

Provides time synchronization services leveraging the hardware acceleration of NVIDIA DPUs.