Computing is an essential tool for the modern financial services industry. Profits are won and lost based on the speed and accuracy of algorithms guiding financial decision making. Accelerated quantum computing has the potential to impact the financial services industry with new algorithms able to speed-up or enhance existing tools, such as portfolio optimization techniques.
]]>
The new release includes support for CUDA 12.9, updated library components, and performance improvements.
]]>
Master AI with Google Cloud & NVIDIA. Access an exclusive community, resources, and rewards.
]]>
AI experiences are rapidly expanding on Windows in creativity, gaming, and productivity apps. There are various frameworks available to accelerate AI inference in these apps locally on a desktop, laptop, or workstation. Developers need to navigate a broad ecosystem. They must choose between hardware-specific libraries for maximum performance, or cross-vendor frameworks like DirectML��
]]>
Imagine analyzing millions of NYC ride-share journeys��tracking patterns across boroughs, comparing service pricing, or identifying profitable pickup locations. The publicly available New York City Taxi and Limousine Commission (TLC) Trip Record Data contains valuable information that could reveal game-changing insights, but traditional processing approaches leave analysts waiting hours for results��
]]>
The world of big data analytics is constantly seeking ways to accelerate processing and reduce infrastructure costs. Apache Spark has become a leading platform for scale-out analytics, handling massive datasets for ETL, machine learning, and deep learning workloads. While traditionally CPU-based, the advent of GPU acceleration offers a compelling promise: significant speedups for data processing��
]]>
The first post in this series, Path Tracing Optimization in Indiana Jones?: Shader Execution Reordering and Live State Reductions, covered ray-gen shader level optimizations that sped up the main path-tracing pass (��TraceMain��) of Indiana Jones and the Great Circle?. This second blog post covers additional GPU optimizations that were made at the level of the ray-tracing acceleration��
]]>
This post is part of the Path Tracing Optimizations in Indiana Jones series. While adding a path-tracing mode to Indiana Jones and the Great Circle in 2024, we used Shader Execution Reordering (SER), a feature available on NVIDIA GPUs since the NVIDIA GeForce RTX 40 Series, to improve the GPU performance. To optimize the use of SER in the main path-tracing pass (), we used the NVIDIA��
]]>
A gene that can be an early indicator for Alzheimer��s disease actually is a cause of the degenerative-brain disorder, said researchers at the University of California, San Diego. That finding, which they discovered using AI, could result in new treatment options. In a paper published in April in the scientific journal Cell, a team at UCSD found that the gene PHGDH��previously considered a��
]]>
NVIDIA recently released cuEmbed, a high-performance, header-only CUDA library that accelerates embedding lookups on NVIDIA GPUs. If you��re building recommendation systems, embedding operations are likely consuming significant computational resources. Embedding lookups present a unique optimization challenge. They��re memory-intensive operations with irregular access patterns.
]]>
Synthetic data has become a standard part of large language model (LLM) post-training procedures. Using a large number of synthetically generated examples from either a single or cohort of open-source, commercially permissible LLMs, a base LLM is finetuned either with supervised finetuning or RLHF to gain instruction-following and reasoning skills. This process can be seen as a knowledge��
]]>
High-performance computing and deep learning workloads are extremely sensitive to latency. Packet loss forces retransmission or stalls in the communication pipeline, which directly increases latency and disrupts the synchronization between GPUs. This can degrade the performance of collective operations such as all-reduce or broadcast, where every GPU��s participation is required before progressing.
]]>
Join us at GTC Paris on June 10th and choose from six full-day, instructor-led workshops.
]]>
The launch of the NVIDIA Blackwell platform ushered in a new era of improvements in generative AI technology. At its forefront is the newly launched GeForce RTX 50 series GPUs for PCs and workstations that boast fifth-generation Tensor Cores with 4-bit floating point compute (FP4)��a must-have for accelerating advanced generative AI models like FLUX from Black Forest Labs. As the latest image��
]]>
NVIDIA Air enables cloud-scale efficiency by creating identical replicas of real-world data center infrastructure deployments. With NVIDIA Air, you can spin up hundreds of switches and servers and configure them with a single script. One of the many advantages of NVIDIA Air is the ability to connect your simulations with the real world. Enabling an external connection in your environment can��
]]>
NVIDIA Warp, a simulation computing framework, is now accessible to all developers.
]]>
The integration of NVIDIA NIM microservices into Azure AI Foundry marks a major leap forward in enterprise AI development. By combining NIM microservices with Azure��s scalable, secure infrastructure, organizations can now deploy powerful, ready-to-use AI models more efficiently than ever before. NIM microservices are containerized for GPU-accelerated inferencing for pretrained and customized��
]]>
As organizations strive to maximize the value of their generative AI investments, accessing the latest model developments is crucial to continued success. By using state-of-the-art models on Day-0, teams can harness these innovations efficiently, maintain relevance, and be competitive. The past year has seen a flurry of exciting model series releases in the open-source community��
]]>
]]>
Scientific research in complex fields like battery innovation is often slowed by manual evaluation of materials, limiting progress to just dozens of candidates per day. In this blog post, we explore how domain-adapted large language models (LLMs), enhanced with reasoning capabilities, are transforming scientific research, especially in high-stakes, complex domains like battery innovation.
]]>
As modern enterprise and cloud environments scale, the complexity and volume of network traffic increase dramatically. NetFlow is used to record metadata about the traffic flows traversing a network device such as a router, switch, or host. NetFlow data, essential for understanding network traffic, can be effectively modeled as graphs where edges capture properties such as connection duration and��
]]>
NVIDIA Agent Intelligence toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents. It focuses on enabling developers to quickly build, evaluate, profile, and accelerate complex agentic AI workflows?��?systems in which multiple AI agents collaborate to perform tasks. The Agent Intelligence toolkit acts as a unifying framework that integrates existing��
]]>
Multi-data center training is becoming essential for AI factories as pretraining scaling fuels the creation of even larger models, leading the demand for computing performance to outpace the capabilities of a single facility. By distributing workloads across multiple data centers, organizations can overcome limitations in power, cooling, and space, enabling the training of even larger��
]]>
Realistic 3D simulation is becoming a cornerstone of modern AI and graphics, from training autonomous vehicles (AV) to powering robotics and digital twins. Neural rendering techniques like NeRFs and 3D Gaussian Splatting (3DGS) have revolutionized how 3D scenes are reconstructed and visualized from raw sensor data. In this post, we introduce the implementation of 3D Gaussian Unscented��
]]>
Apache Spark is an industry-leading platform for big data processing and analytics. With the increasing prevalence of unstructured data��documents, emails, multimedia content��deep learning (DL) and large language models (LLMs) have become core components of the modern data analytics pipeline. These models enable a variety of downstream tasks, such as image captioning, semantic tagging��
]]>
From the Stone Age to the digital era, materials have been the foundation of our civilization across all epochs. Today, finding new materials leads to progress in energy, medicine, and advancements in technology. This creates a future of endless possibilities, however, there are still challenges. Human-powered approaches to finding new materials have been slow, costly, unexpected, and limited to a��
]]>
In today��s educational landscape, generative AI tools have become both a blessing and a challenge. While these tools offer unprecedented access to information, they��ve also created new concerns about academic integrity. Increasingly, students rely on AI to generate direct answers to homework questions, often at the expense of developing critical thinking skills and mastering core concepts.
]]>
Curating high-quality pretraining datasets is critical for enterprise developers aiming to train state-of-the-art large language models (LLMs). To enable developers to build highly accurate LLMs, NVIDIA previously released Nemotron-CC, a 6.3-trillion-token English language Common Crawl (CC) dataset. Today, the NVIDIA NeMo Curator team is excited to share that the pipeline used to build the��
]]>
Universal Scene Description (OpenUSD) offers a powerful, open, and extensible ecosystem for describing, composing, simulating, and collaborating within complex 3D worlds. From handling massive datasets and automating workflows for digital twins to enabling real-time rendering for games and streamlining industrial operations in manufacturing and energy, it is transforming how industries work with��
]]>
This is the second post in the LLM Benchmarking series, which shows how to use GenAI-Perf to benchmark the Meta Llama 3 model when deployed with NVIDIA NIM. When building LLM-based applications, it is critical to understand the performance characteristics of these models on a given hardware. This serves multiple purposes: As a client-side LLM-focused benchmarking tool��
]]>
Time-series data has evolved from a simple historical record into a real-time engine for critical decisions across industries. Whether it��s streamlining logistics, forecasting markets, or anticipating machine failures, organizations need more sophisticated tools than traditional methods can offer. NVIDIA GPU-accelerated deep learning is enabling industries to gain real-time analytics.
]]>
For professionals pushing the boundaries of XR, creating the most immersive and highest fidelity experiences is always challenging. Demanding XR workflows push the performance limits when rendering massive datasets and driving the latest ultra-high-resolution advanced XR headsets. Simultaneously integrating advanced artificial intelligence capabilities for more interactive and intuitive��
]]>
New features include enhancements to confidential computing and family-specific features and targets supported by NVCC.
]]>
Alibaba recently released Tongyi Qwen3, a family of open-source hybrid-reasoning large language models (LLMs). The Qwen3 family consists of two MoE models, 235B-A22B (235B total parameters and 22B active parameters) and 30B-A3B, and six dense models, including the 0.6B, 1.7B, 4B, 8B, 14B, 32B versions. With ultra-fast token generation, developers can efficiently integrate and deploy Qwen3��
]]>
]]>
Explore the groundbreaking projects and real-world impacts of the HackAI Challenge powered by NVIDIA AI Workbench and Dell Precision.
]]>
]]>
The NVIDIA CUDA-X math libraries empower developers to build accelerated applications for AI, scientific computing, data processing, and more. Two of the most important applications of CUDA-X libraries are training and inference LLMs, whether for use in everyday consumer applications or highly specialized scientific domains like drug discovery. Multiple CUDA-X libraries are indispensable��
]]>
Stacking generalization is a widely used technique among machine learning (ML) engineers, where multiple models are combined to boost overall predictive performance. On the other hand, hyperparameter optimization (HPO) involves systematically searching for the best set of hyperparameters to maximize the performance of a given ML algorithm. A common challenge when using both stacking and HPO��
]]>
It��s 10 p.m. on a Tuesday when the phone rings at the Sapochnick Law Firm, a specialized law practice in San Diego, California. The caller, a client of the firm, is anxious as the phone rings. They received an important letter containing? potentially life-changing news, and had urgent questions for their lawyer. The client quickly realizes the Sapochnick team likely left the office hours ago��
]]>
When interacting with transformer-based models like large language models (LLMs) and vision-language models (VLMs), the structure of the input shapes the model��s output. But prompts are often more than a simple user query. In practice, they optimize the response by dynamically assembling data from various sources such as system instructions, context data, and user input.
]]>
Kaggle Grandmasters David Austin and Chris Deotte from NVIDIA and Ruchi Bhatia from HP joined Brenda Flynn from Kaggle at this year��s Google Cloud Next conference in Las Vegas. They shared a bit about who they are, what motivates them to compete, and how they contribute to and win competitions on the world��s largest data science competition platform. This blog post captures a glimpse of��
]]>
AI is rapidly moving beyond centralized cloud and data centers, becoming a powerful tool deployable directly on professional workstations. Thanks to advanced hardware and optimized software, you can build, run, and experiment with sophisticated AI models at your desk or on the go. Welcome to the world of local AI development! Running and developing AI locally on a workstation offers��
]]>
The first release of NVIDIA NIM Operator simplified the deployment and lifecycle management of inference pipelines for NVIDIA NIM microservices, reducing the workload for MLOps, LLMOps engineers, and Kubernetes admins. It enabled easy and fast deployment, auto-scaling, and upgrading of NIM on Kubernetes clusters. Learn more about the first release. Our customers and partners have been using��
]]>
A researcher from the SETI Institute described to a packed audience at GTC 2025 how SETI had successfully trialed a novel method to identify interstellar radio waves which, theoretically, can also be used to identify communication from intelligent extraterrestrial life. Luigi Cruz, a staff engineer at SETI, the world��s foremost organization looking for signs of intelligent life on other��
]]>
The age of passive AI is over. A new era is beginning, where AI doesn��t just respond��it thinks, plans, and acts. The rapid advancement of large language models (LLMs) has unlocked the potential of agentic AI systems, enabling the automation of tedious tasks across many fields, including cybersecurity. Traditionally, AI applications in cybersecurity have focused primarily on detecting��
]]>
Robotic arms are used today for assembly, packaging, inspection, and many more applications. However, they are still preprogrammed to perform specific and often repetitive tasks. To meet the increasing need for adaptability in most environments, perceptive arms are needed to make decisions and adjust behavior based on real-time data. This leads to more flexibility across tasks in collaborative��
]]>
Real-time ray tracing is a powerful rendering technique that can create incredibly realistic images. NVIDIA OptiX and RTX technology make this possible, even for scenes with a massive amount of detail. However, when these detailed scenes involve movement and animation, maintaining real-time ray tracing performance can be challenging. This post explores how the new RTX Mega Geometry features��
]]>
This is the first post in the LLM Benchmarking series, which shows how to use GenAI-Perf to benchmark the Meta Llama 3 model when deployed with NVIDIA NIM. Researchers from the University College London (UCL) Deciding, Acting, and Reasoning with Knowledge (DARK) Lab leverage NVIDIA NIM microservices in their new game-based benchmark suite, Benchmarking Agentic LLM and VLM Reasoning On Games��
]]>
Large language models (LLMs) have enabled AI tools that help you write more code faster, but as we ask these tools to take on more and more complex tasks, there are limitations that become apparent. Challenges such as understanding the nuances of programming languages, complex dependencies, and adapting to codebase-specific context can lead to lower-quality code and cause bottlenecks down the line.
]]>
As many enterprises move to running AI training or inference on their data, the data and the code need to be protected, especially for large language models (LLMs). Many customers can��t risk placing their data in the cloud because of data sensitivity. Such data may contain personally identifiable information (PII) or company proprietary information, and the trained model has valuable intellectual��
]]>
Gaussian splatting is a novel approach to rendering complex 3D scenes by representing them as a collection of anisotropic Gaussians in 3D space. This technique enables real-time rendering of photorealistic scenes learned from small sets of images, making it ideal for applications in gaming, virtual reality, and real-time professional visualization. vk_gaussian_splatting is a new Vulkan-based��
]]>
NVIDIA cuPyNumeric is a library that aims to provide a distributed and accelerated drop-in replacement for NumPy built on top of the Legate framework. It brings zero-code-change scaling to multi-GPU and multinode (MGMN) accelerated computing. cuPyNumeric 25.03 is a milestone update that introduces powerful new capabilities and enhanced accessibility for users and developers alike��
]]>
Enterprise data is constantly changing. This presents significant challenges for maintaining AI system accuracy over time. As organizations increasingly rely on agentic AI systems to optimize business processes, keeping these systems aligned with evolving business needs and new data becomes crucial. This post dives into how to build an iteration of a data flywheel using NVIDIA NeMo��
]]>
Missed GTC? This year��s training labs are now available on demand to watch anywhere, anytime.
]]>
Can AI guide us toward a more sustainable future, or is it exacerbating global energy and climate challenges? This critical question was recently posed to a panel of sustainability and AI experts from Columbia University, Deloitte, and the Wilson Center at NVIDIA GTC 2025. In a packed room moderated by Josh Parker, senior director of Corporate Sustainability at NVIDIA��
]]>
State-of-the-art image diffusion models take tens of seconds to process a single image. This makes video diffusion even more challenging, requiring significant computational resources and high costs. By leveraging the latest FP8 quantization features on NVIDIA Hopper GPUs with NVIDIA TensorRT, it��s possible to significantly reduce inference costs and serve more users with fewer GPUs.
]]>
AI has become nearly synonymous with innovation. As it rushes onto the world stage, AI is seeding inspiration in creators and problem-solvers of all stripes��from artists to more traditional industrial inventors. One of the world��s leading AI-first artists, Alexander Reben, has spent his career integrating AI into different artistic mediums. His current work explores AI and robotics and��
]]>
Build a high-performance agentic AI system using the open-source NVIDIA Agent Intelligence toolkit �� contest runs May 12 to May 23.
]]>
Feature engineering remains one of the most effective ways to improve model accuracy when working with tabular data. Unlike domains such as NLP and computer vision, where neural networks can extract rich patterns from raw inputs, the best-performing tabular models��particularly gradient-boosted decision trees��still gain a significant advantage from well-crafted features. However��
]]>
The release of NVIDIA OptiX 9.0 introduces a new feature called cooperative vectors that enables AI workflows as part of ray tracing kernels. The feature leverages NVIDIA RTX Tensor Cores for hardware-accelerated matrix operations and neural net computations during shading. This unlocks AI rendering techniques such as NVIDIA RTX Neural Shaders and NVIDIA RTX Neural Texture Compression (NTC) and��
]]>
By 2030, more than one in five Americans will be 65 or older, becoming the United States�� largest group of seniors ever. Silicon Valley-based startup Butlr has developed an AI platform designed to keep seniors safe while preserving their privacy. Their AI-based platform uses a neural network to interpret different temperature data that its sensors, which are strategically placed in��
]]>
Large language models (LLMs) are revolutionizing how developers code and how they learn to code. For seasoned or junior developers alike, today��s state-of-the-art models can generate Python scripts, React-based websites, and more. In the future, powerful AI models will assist developers in writing high-performance GPU code. This raises an important question: How can it be determined whether an LLM��
]]>
The accuracy of citations is crucial for maintaining the integrity of both academic and AI-generated content. When citations are inaccurate or wrong, they can mislead readers and spread false information. As a team of researchers from the University of Sydney specializing in machine learning and AI, we are developing an AI-powered tool capable of efficiently cross-checking and analyzing semantic��
]]>
Federated learning (FL) has emerged as a promising approach for training machine learning models across distributed data sources while preserving data privacy. However, FL faces significant challenges related to communication overhead and local resource constraints when balancing model requirements and communication capabilities. Particularly in the current era of large language models��
]]>
AI is no longer just about generating text or images��it��s about deep reasoning, detailed problem-solving, and powerful adaptability for real-world applications in business and in financial, customer, and healthcare services. Available today, the latest Llama Nemotron Ultra reasoning model from NVIDIA delivers leading accuracy among open-source models across intelligence and coding benchmarks��
]]>
You��re invited to join the challenge. Develop and apply innovative data filtering techniques to curate datasets that enhance edge LM performance.
]]>
NVIDIA Run:ai 2.21 adds GB200 NVL72 support, rolling inference updates and smarter resource controls.
]]>
NVIDIA and the PyTorch team at Meta announced a groundbreaking collaboration that brings federated learning (FL) capabilities to mobile devices through the integration of NVIDIA FLARE and ExecuTorch. NVIDIA FLARE is a domain-agnostic, open-source, extensible SDK that enables researchers and data scientists to adapt existing machine learning or deep learning workflows to a federated paradigm.
]]>
In a cavernous room at an undisclosed location in Japan, a digital revolution is unfolding. Racks of servers stand like giants, their sleek frames linked by thousands of cables humming with potential. Until last year, this sprawling AI factory didn��t exist. Now it��s poised to anchor SoftBank Corporation��s vision for AI-powered innovation, a vision rooted in creating a society that coexists��
]]>
A simple brain scan may soon be all that��s needed to accurately diagnose Parkinson��s disease, thanks to a new AI-powered tool. The advancement could help doctors expedite detection and treatment, getting patients the care they need and improving their quality of life. Developed by teams from the University of Florida (UF) and top-tier medical centers, the machine learning model analyzes MRI��
]]>
The HPC SDK v25.3 release includes support for NVIDIA Blackwell GPUs and an optimized allocator for Arm CPUs.
]]>
Scientific papers are highly heterogeneous, often employing diverse terminologies for the same entities, using varied methodologies to study biological phenomena, and presenting findings within distinct contexts. Extracting meaningful insights from these papers requires a profound understanding of biology, a critical evaluation of methodologies, and the ability to discern robust findings from��
]]>
When working with large datasets, the performance of your data processing tools becomes critical. Polars, an open-source library for data manipulation known for its speed and efficiency, offers a GPU-accelerated backend powered by cuDF that can significantly boost performance. However, to fully leverage the power of the Polars GPU backend, it��s essential to optimize the data loading process��
]]>
The worldwide adoption of generative AI has driven massive demand for accelerated compute hardware globally. In enterprises, this has accelerated the deployment of accelerated private cloud infrastructure. At the regional level, this demand for compute infrastructure has given rise to a new category of cloud providers who offer accelerated compute (GPU) capacity for AI workloads, also known as GPU��
]]>
As more enterprises integrate LLMs into their applications, they face a critical challenge: LLMs can generate plausible but incorrect responses, known as hallucinations. AI guardrails��or safeguarding mechanisms enforced in AI models and applications��are a popular technique to ensure the reliability of AI applications. This post demonstrates how to build safer��
]]>
NVIDIA AI Workbench 2025.03.10 features streamlined onboarding and enhanced UX for multicontainer projects.
]]>
The Das Lab at Stanford is revolutionizing RNA folding research with a unique approach that leverages community involvement and accelerated computing. With the support of NVIDIA DGX Cloud through the NAIRR Pilot program, the lab gained access to 32 NVIDIA A100 DGX Cloud nodes with eight GPUs each for three months, enabling the team to transition from small-scale experiments to large-scale��
]]>
This updated post was originally published on March 18, 2025. Organizations are embracing AI agents to enhance productivity and streamline operations. To maximize their impact, these agents need strong reasoning abilities to navigate complex problems, uncover hidden connections, and make logical decisions autonomously in dynamic environments. Due to their ability to tackle complex��
]]>
Humans know more about deep space than we know about Earth��s deepest oceans. But scientists have plans to change that��with the help of AI. ��We have better maps of Mars than we do of our own exclusive economic zone,�� said Nick Rotker, chief BlueTech strategist at MITRE, a US government-sponsored nonprofit research organization. ��Around 70% of the Earth is covered in water and we��ve explored��
]]>
As large language models (LLM) gain popularity in various question-answering systems, retrieval-augmented generation (RAG) pipelines have also become a focal point. RAG pipelines combine the generation power of LLMs with external data sources and retrieval mechanisms, enabling models to access domain-specific information that may not have existed during fine-tuning.
]]>
Nearly 300,000 women across the globe die each year due to complications arising from pregnancy or childbirth. The number of stillborns and babies that die within their first month tops nearly 4M every year. April 7 marks World Health Day, which this year focuses on raising awareness about efforts to end preventable maternal and newborn deaths. Giving women and infants better access to��
]]>
Join the hackathon to build open-source AI solutions, optimize models, enhance workflows, connect with peers, and win prizes.
]]>
The newest generation of the popular Llama AI models is here with Llama 4 Scout and Llama 4 Maverick. Accelerated by NVIDIA open-source software, they can achieve over 40K output tokens per second on NVIDIA Blackwell B200 GPUs, and are available to try as NVIDIA NIM microservices. The Llama 4 models are now natively multimodal and multilingual using a mixture-of-experts (MoE) architecture.
]]>
As data sizes have grown in enterprises across industries, Apache Parquet has become a prominent format for storing data. Apache Parquet is a columnar storage format designed for efficient data processing at scale. By organizing data by columns rather than rows, Parquet enables high-performance querying and analysis, as it can read only the necessary columns for a query instead of scanning entire��
]]>
The compute demands for large language model (LLM) inference are growing rapidly, fueled by the combination of growing model sizes, real-time latency requirements, and, most recently, AI reasoning. At the same time, as AI adoption grows, the ability of an AI factory to serve as many users as possible, all while maintaining good per-user experiences, is key to maximizing the value it generates.
]]>
This is the first post in the large language model latency-throughput benchmarking series, which aims to instruct developers on common metrics used for LLM benchmarking, fundamental concepts, and how to benchmark your LLM applications. The past few years have witnessed the rise in popularity of generative AI and large language models (LLMs), as part of a broad AI revolution.
]]>
At GTC 2025, a panel of industry leaders from across the tech ecosystem shared how they��re using AI to mitigate and prepare customers for the increasingly disruptive impact of climate change. Tenika Versey, the global head of sustainable futures for the NVIDIA Inception program, led a panel that included Colin le Duc, founding partner at Generation Investment Management, Suzanne DiBianca��
]]>
Today, NVIDIA announced the open-source release of the KAI Scheduler, a Kubernetes-native GPU scheduling solution, now available under the Apache 2.0 license. Originally developed within the Run:ai platform, KAI Scheduler is now available to the community while also continuing to be packaged and delivered as part of the NVIDIA Run:ai platform. This initiative underscores NVIDIA��s commitment to��
]]>
At NVIDIA, we take pride in tackling complex infrastructure challenges with precision and innovation. When Volcano faced GPU underutilization in their NVIDIA DGX Cloud-provisioned Kubernetes cluster, we stepped in to deliver a solution that not only met but exceeded expectations. By combining advanced scheduling techniques with a deep understanding of distributed workloads��
]]>
Industrial enterprises are embracing physical AI and autonomous systems to transform their operations. This involves deploying heterogeneous robot fleets that include mobile robots, humanoid assistants, intelligent cameras, and AI agents throughout factories and warehouses. To harness the full potential of these physical AI enabled systems, companies rely on digital twins of their facilities��
]]>
NVIDIA is breaking new ground by integrating silicon photonics directly with its NVIDIA Quantum and NVIDIA Spectrum switch ICs. At GTC 2025, we announced the world��s most advanced Silicon Photonics Switch systems, powered by cutting-edge 200G SerDes technology. This innovation, known as co-packaged silicon photonics, delivers significant benefits such as 3.5x lower power consumption��
]]>
Welcome to the first edition of the NVIDIA Robotics Research and Development Digest (R2D2). This technical blog series will give developers and researchers deeper insight and access to the latest physical AI and robotics research breakthroughs across various NVIDIA Research labs. Developing robust robots presents significant challenges, such as: We address these challenges through��
]]>
Since the release of ChatGPT in November 2022, the capabilities of large language models (LLMs) have surged, and the number of available models has grown exponentially. With this expansion, LLMs now vary widely in cost, performance, and specialization. For example, straightforward tasks like text summarization can be efficiently handled by smaller, general-purpose models. In contrast��
]]>
Large language models (LLMs) often struggle with accuracy when handling domain-specific questions, especially those requiring multi-hop reasoning or access to proprietary data. While retrieval-augmented generation (RAG) can help, traditional vector search methods often fall short. In this tutorial, we show you how to implement GraphRAG in combination with fine-tuned GNN+LLM models to achieve��
]]>
From hyperlocal forecasts that guide daily operations to planet-scale models illuminating new climate insights, the world is entering a new frontier in weather and climate resilience. The combination of space-based observations and GPU-accelerated AI delivers near-instant, context-rich insights to enterprises, governments, researchers, and solution providers worldwide. It also marks a rare��
]]>
Kit SDK 107.0 is a major update release with primary updates for robotics development.
]]>
Inland flooding causes significant economic and societal impacts annually. Of the eight natural disasters costing the insurance industry over $1 billion in 2024, six of these were categorized as flood events, with three of these occurring in Europe alone. Catastrophe modeling aims to quantify the risk of flood events to enable preparedness for the financial and insurance industries.
]]>
Advanced AI models such as DeepSeek-R1 are proving that enterprises can now build cutting-edge AI models specialized with their own data and expertise. These models can be tailored to unique use cases, tackling diverse challenges like never before. Based on the success of early AI adopters, many organizations are shifting their focus to full-scale production AI factories. Yet the process of��
]]>
Large ensembles are essential for predicting rare, high-impact events that cannot be fully understood through historical data alone. By simulating thousands of potential scenarios, they provide the statistical depth necessary to assess risks, prepare for extremes, and build resilience against once-in-a-century disasters. Global insurance group AXA is conducting simulations with cutting-edge��
]]>