Knowledge catalogue
This guide covers GPU-initiated communication techniques using NVSHMEM, which allows GPUs to directly communicate with other GPU memory spaces, leveraging global address space for higher bandwidth and
NVIDIA's NeMo framework addresses the challenge of limited, imbalanced financial NLP data by generating synthetic financial news headlines to fill gaps for trading research, risk modeling, and surveil
NVIDIA Vera is a CPU designed to help AI factories scale agentic AI and reinforcement learning by shortening CPU execution time, increasing task throughput, and enabling smarter, longer-thinking agent
Nonuniform Tensor Parallelism (NTP) enables large-scale LLM training jobs to dynamically adapt tensor parallelism degree in response to transient GPU unavailability, ensuring sustained Goodput and min
NVIDIA Confidential Computing addresses data privacy and security concerns for AI workloads by protecting data during inference and engagement with models, offering high-performance protection in loca
Enterprise autonomous AI agents inspect code, run tests, search documents, and operate for extended periods on behalf of users , requiring governance frameworks to control access and actions. The Ente
PUBG Ally is an interactive co-playable character for PUBG: BATTLEGROUNDS powered by an on-device small language model built with NVIDIA ACE technology, equipped to communicate and cooperate with play
NVIDIA TensorRT's multi-device inference feature scales inference across multiple GPUs, enabling deployment of models that exceed single-GPU memory or reducing latency for memory-bound workloads. Each
DFlash is an open source block diffusion model for speculative decoding that significantly accelerates LLM inference on NVIDIA Blackwell GPUs by drafting entire token blocks in parallel and verifying
The NVIDIA BioNeMo Agent Toolkit enables AI scientists to use structure prediction, molecular generation, docking, sequence analysis, design, and genomics as callable tools , allowing AI agents to exe
Telecommunication operators deploy autonomous agents built on telecom-domain models and running inside secure execution runtimes connected to tools, digital twins, and shared skills to understand netw
DAQIRI (Data Acquisition for Integrated Real-time Instruments) is a high-performance networking library that streams data from fast detectors . DAQIRI keeps up by handling the stream as it arrives , e
Battery energy storage systems serve as grid-interactive control assets that buffer fast-changing, power-dense AI loads, improve power quality, and enable flexible interconnection with utilities and d
DiffusionGemma is an experimental open model built for exceptionally fast text generation that NVIDIA has optimized to run on GeForce RTX GPUs, RTX PRO, and DGX Spark systems. Rather than generating t
NVIDIA FLARE Auto-FL automates federated learning research by constraining agent actions through a control plane, enforcing fixed benchmark contracts, and using an experiment ledger to ensure reproduc
NVIDIA DGX Spark Enterprise Manageability enables IT administrators to plan, configure, and manage DGX Spark deployments at scale with coverage of workflows, provisioning, update procedures, and syste
This article presents a clinical automatic speech recognition workflow for generating pronunciation-aware synthetic audio, reviewing clinical terms, and evaluating recognition quality using NVIDIA age
This NVIDIA technical article addresses how low-bit mixed-precision pre-training accelerates large language model training, where optimizing numerical precision can reduce training time across distrib
NVIDIA's Nemotron 3 Ultra is a 550B-parameter Mixture-of-Experts model with 55B active parameters, optimized for orchestrating complex, long-running agent workflows by combining frontier reasoning and
NVIDIA JetPack 7.2 enables deployment of AI agents to edge devices with optimized memory and performance for real-world applications. The release directly supports one-command deployment of NVIDIA Nem
NVIDIA Cosmos 3 is a frontier foundation model for physical AI that combines physical reasoning, world generation, and action generation within a single open model. The model uses a Mixture-of-Transfo
NVIDIA DSX OS is an open source, modular software platform designed for operating and scaling multi-tenant AI factories. It provides foundational technologies for building and operating AI factories,
NVIDIA Vera is a purpose-built CPU for agentic AI and reinforcement learning, delivering twice the efficiency and 50% faster performance than traditional rack-scale CPUs. The processor helps AI factor
Step 3.7 Flash is a 198B-parameter Mixture-of-Experts vision-language model designed for enterprise-scale production workloads, featuring native image and video input, a 256k context window, and confi
NVIDIA's Blackwell GB200 NVL72 architecture achieved the fastest-ever results on the STAC-AI benchmark for financial LLM inference, delivering up to 3.2x single-GPU performance improvements over the p
NVIDIA Dynamo Snapshot introduces ModelExpress for 7x faster startup via checkpoint restore and weight streaming with NVIDIA NVLink and NIXL , enabling efficient model initialization for inference wor
NVIDIA DLSS 4.5 introduces Dynamic Multi Frame Generation and a second-generation transformer model for Super Resolution to enhance game image quality and frame rates for Unreal Engine 5. The new Tens
This NVIDIA Developer article guides developers on creating optimized GPU kernels using C++ with NVIDIA's CUDA Tile technology, which enables efficient parallel computation on graphics processors. The
The NVIDIA RTX PRO 4500 accelerates genomic sequencing and drug discovery by slashing processing times. This professional desktop GPU features 32GB of ultra-fast GDDR7 memory and Blackwell architectur
Telcos are building sovereign AI factories based on the NVIDIA Cloud Partner reference architecture to provide secure, in-country AI infrastructure with controls and performance suited for enterprise
The NVIDIA GB200 NVL72 is a rack-scale GPU supercomputer leveraging Blackwell architecture with NVLink switches for high-density computing , and topology-aware block scheduling in Slurm can align larg
This article covers the NVIDIA AI-Q Blueprint for building specialized deep research agents that empower AI systems to gather context, synthesize information, and support complex decision-making acros
NVIDIA agent skills enable specialized agents to deliver targeted capabilities across enterprise workflows , with governance provided through verified, scanned, and signed skills. JFrog AI Catalog aut
The NVIDIA Vera Rubin Platform is a rack-scale AI supercomputer designed to power agentic AI and reasoning models at scale by eliminating bottlenecks in communication and memory movement for efficient
XANI (X-ray Analysis for Nanoscale Imaging) is an accelerated computing pipeline developed by NVIDIA engineers for rapid X-ray data analysis. NVIDIA's accelerated computing enables real-time experimen
NVIDIA's video analytics AI agents analyze and process large volumes of video data through natural language tasks to provide critical insights , powered by vision language models, large language model
Grammar-constrained decoding modifies language model generation by applying grammar constraints at each step to block structurally invalid tokens , ensuring syntactically correct Bash command generati
This article discusses optimization techniques for maximizing efficiency on NVIDIA's GB200 NVL72 system using Slurm block scheduling, a job scheduling approach designed to improve resource utilization
Post-training quantization is a technique that reduces model size and improves inference performance by converting weights and activations to lower precision formats after training is complete. NVIDIA
NCCL Inspector is a profiling plugin that provides detailed, per-communicator, per-collective performance and metadata logging, designed to help users analyze and debug NCCL collective operations by g
The automotive cockpit is undergoing a fundamental shift from rule-based interfaces to agentic, multimodal AI systems capable of reasoning, planning, and acting. This is enabled by an agentic AI pipel
NVIDIA cuOpt Agent Skills integrate LLM reasoning with GPU-accelerated solvers to enable AI agents to translate natural language supply chain problems into optimized mathematical models, with skills e
The TileGym project developed an AI-driven skill-based workflow that encodes 17 critical translation rules, static validation scripts, and example kernels, enabling automated conversion of cuTile Pyth
NVIDIA DLSS 4.5 introduces Dynamic Multi Frame Generation and a second-generation transformer model, improving game image quality and frame rates while maintaining responsiveness. A new TensorRT for R
The TensorRT for RTX plugin provides a runtime for Unreal Engine's Neural Network Engine (NNE), enabling efficient deployment of AI models directly within real-time applications. Developers can see 1.
NVIDIA and SLB are collaborating to build generative AI models using NVIDIA NeMo and NIM for subsurface exploration, production operations, and data management in the energy industry. This approach ac
NVIDIA Nemotron 3 Nano Omni is a 30B hybrid mixture-of-experts model that brings multimodal perception and reasoning into a single system, natively supporting text, image, video, and audio inputs whil
Developers can build with DeepSeek V4 through NVIDIA GPU-accelerated endpoints on build.nvidia.com, with hosted endpoints providing a fast way to prototype before moving to self-hosted deployment. Dee
This blog post discusses higher-order optimization algorithms such as Shampoo that have been applied in neural network training for at least a decade. The article explores how these emerging optimizer
NVIDIA researchers discovered a vulnerability in AI coding assistants where malicious software dependencies can inject harmful instructions into AGENTS.md configuration files, allowing attackers to re
NVIDIA released PhysicsNeMo, an open-source AI framework designed to speed up nuclear reactor design through physics-based simulations. The framework uses machine learning-based multiphysics emulators
NVIDIA's ALCHEMI Toolkit is a PyTorch-native framework that lets researchers build custom GPU-accelerated atomistic simulation workflows for chemistry and materials science applications. The initial r
NVIDIA Ising is the world's first family of open-source quantum AI models, designed to help researchers and enterprises build quantum processors capable of running useful applications. The family span
NVIDIA NVbandwidth is a performance analysis tool designed to measure memory bandwidth and latency between various components in GPU-equipped systems, providing detailed measurements of data transfer
MiniMax M2.7 is an enhancement of the MiniMax M2.5 model, built as a 230B-parameter Mixture-of-Experts (MoE) model with 10B active parameters per token and a 200K context length, designed for agentic
Training LLMs requires periodic checkpoints — full snapshots of model weights, optimizer states, and gradients — whose storage costs can reach $200,000/month for a 405B model on 128 NVIDIA DGX B200...
NVIDIA, Google DeepMind, EMBL-EBI, and Seoul National University collaborated to extend the AlphaFold Protein Structure Database (AFDB) beyond monomeric structures to proteome-scale quaternary stru...
NVIDIA's open-source project **Slinky** (developed by SchedMD, now part of NVIDIA) enables organizations to run full Slurm clusters directly on Kubernetes infrastructure by managing the complete li...
NVIDIA has introduced a modular, library-based architecture for Omniverse, exposing core components—RTX rendering, PhysX-based simulation, and data storage pipelines—as standalone, headless-first C...