Preparing CAD assets for robotics simulation requires more than converting geometry to OpenUSD: developers must configure and validate materials, collision geometry, joints, and other physics properties before testing robot behavior. NVIDIA Omniverse libraries, guided by SimReady Foundation specifications and agentic NVIDIA skills, provide a structured workflow for converting and validating…
]]>
The NVIDIA KGMON team placed second in the KDD Cup 2026 Data Agents competition with a system built around a simple idea of making an agent’s harness smaller, clearer, and easier to verify. The competition asked agents to answer natural-language questions over heterogeneous data sources, including databases, CSV and JSON files, prose documents, PDFs, and briefing videos.
]]>
How we taught robots to assemble GB300 tester trays and what it taught us about robot learning, mechanical intelligence, and good old-fashioned engineering The NVIDIA Grace Blackwell GB300 superchip is the engine of AI training and inference for modern foundation models. However, the process of assembling GB300 trays requires skilled physical labor in factories across the world.
]]>
AI factories are some of the most complex operations in the world, combining GPUs, CPUs, switches, DPUs, and SuperNICs alongside schedulers, orchestration services, security controls, and a rapidly changing software stack. Deploying this infrastructure effectively is a challenge. But so is being able to validate that the infrastructure, software, and policies work together for the workloads the…
]]>
Supply chain problems are expanding across more SKUs, lanes, and constraints than ever before, while energy grids are balancing more distributed sources in real time. To meet these challenges, teams need to evaluate larger models and more uncertainty within a practical planning window. NVIDIA cuOpt GPU-accelerated decision optimization can already deliver speedups of more than 10x over CPU…
]]>
Observatories and telescopes, lasers and X-ray light sources, and other high-throughput instruments generate image data faster than CPU-bound pipelines can process it to support timely decisions. The computational bottleneck is rarely one slow kernel. It’s the whole path from data in the sensor to a decision: read the raw data, match point-spread functions or detector responses, subtract or reduce…
]]>
Bitwise determinism makes large-scale pretraining easier to debug, validate, and resume reproducibly. These benefits become especially valuable when training models with trillions of parameters across thousands of GPUs, where multiple parallelism dimensions, low-precision computation, and distributed checkpointing complicate failure reproduction and fix validation.
]]>
GPU applications increasingly need networking and data movement to behave like first-class GPU-controlled operations rather than host-driven services. When the CPU sits in the middle of every network transaction, it becomes a bottleneck on the critical path, adding latency and limiting how efficiently distributed applications can respond in real time. NVIDIA DOCA GPUNetIO…
]]>
GPU-accelerated Kubernetes clusters depend on compatible versions across dozens of components, each on its own release cycle: host kernels, GPU drivers, container runtimes, networking, storage, operators, and workload frameworks. A configuration that works for one service, GPU generation, and Kubernetes release may silently fail for another, and tracing version conflicts after deployment is…
]]>
GPU applications increasingly consist of multiple independent components running at the same time within a single process: a latency-sensitive operator alongside a throughput-oriented background kernel; a data preprocessing stage alongside model inference; or multiple stages of a processing workflow sharing a single GPU. Controlling how GPU resources are shared between them remains difficult.
]]>
AI agents are becoming a standard part of development workflows, but general-purpose agents weren’t built with specialized infrastructure software such as NVIDIA DOCA in mind. Without domain-specific knowledge, agents may fall back on guesswork. This is an issue in infrastructure development because every correction cycle takes time away from deployment. DOCA is the unified software platform…
]]>
Adding AI models to local applications requires a portable model format, a reliable runtime, and acceleration that works across target systems. Do Inference Now (DIN) Deploy is an open-source collection of practical C++ samples that bridges that gap. It combines ONNX Runtime with the NVIDIA TensorRT RTX execution provider to help developers move from a model checkpoint to a native…
]]>
Automatic speech recognition must handle how people actually speak, not only the languages and styles that dominate pretraining data. Regional dialects and local recording conditions are often underrepresented, so a multilingual model that performs well on broad benchmarks may still fall short in deployment. Saudi Arabic makes that concrete. A model may recognize Modern Standard Arabic or…
]]>
Generative recommender (GR) systems are emerging as a powerful new approach for large-scale personalization. Instead of treating recommendation as a set of isolated retrieval, ranking, and prediction stages, GRs reformulate recommendation as sequence modeling over user behavior. A user’s interactions, context, candidate items, and actions become tokens in a high-cardinality event stream…
]]>
AI infrastructure engineers, storage developers, and cloud service providers need fast and secure access to high-capacity file and object storage to support AI workloads. AI workloads increasingly require high-speed data access for training, fine-tuning, inference context, tool calls, searches, and database lookups. Much of this data lies in files and objects stored both on-premises and in…
]]>
An agent can finish a task and still take an inefficient path. A failed search can trigger another search. A truncated file read can lead to a command fetching the same content again. A correct final answer hides those extra steps, even though they increase latency and consume tokens. Inefficiencies create more chances for failure. To improve an agent’s behavior…
]]>
Parallel work, model-family isolation, reversible changes, and GPU-backed validation shaped an open source project designed around coding agents NVIDIA TensorRT Model Connect is an open source collection of AI model reference implementations in C++, built on top of NVIDIA TensorRT. It began with a practical question: could the performance of the NVIDIA inference stack be made accessible to…
]]>
Vision-language models have made it possible to build visual AI agents that understand video at production scale. The harder problem is turning that capability into a maintainable system that combines ingestion, stream processing, event detection, retrieval, summarization, and reporting. The NVIDIA Metropolis Blueprint for Video Search and Summarization (VSS) and its agent skills help…
]]>
To understand where agentic AI stands today, consider the last seismic shift in technology: the rise of the internet in the 90s. It was new and full of possibilities. You could build a website over a weekend and share it with the world, or chat with someone half way around the world in online chat rooms without long-distance telephone fees. It brought endless opportunity, but also a lot of risk.
]]>
AI agents can be given a goal, write code, use tools, and keep working as new information becomes available. This opens the door to applications that investigate software failures, run experiments, and carry out business-critical actions and research over days or weeks. Useful agents need access to workspaces, compute resources, data, credentials, and external services.
]]>
Every unused watt is capacity left on the table. AI factories are typically provisioned for the unlikely moment when every GPU reaches peak power, creating a protective buffer that can leave valuable infrastructure underused during normal operation. NVIDIA DSX MaxLPS uses policy-governed power sharing to allocate power across participating resources dynamically, enabling customers to deploy up to…
]]>
As language models grow, scaling dense architectures becomes increasingly expensive. In a dense transformer, every token passes through every layer, so adding capabilities increases computation for both training and inference. Mixture-of-experts (MoE) architectures take a different approach to scaling by using many subnetworks, or experts, while activating only a small subset for each token.
]]>
Radiology AI has made remarkable strides in detecting abnormalities across chest X-rays, pathology slides, and 2D scans. Yet one of the most clinically rich and data-dense modalities—the 3D computed tomography (CT) scan—remains largely underserved by modern vision language models (VLMs). Frontier general-purpose models perform poorly on volumetric imaging, and most open medical AI models lack the…
]]>
A GPU cluster can pass every health check and still fail to run an AI workload. Even when every GPU, network link, and pod reports healthy, a 512-GPU training job can underperform or fail. The cause may be one slow GPU, a link that degrades under load, or a configuration that quietly routes traffic over a slower path. Operators may not discover the problem until hours into the run or until a…
]]>
Kubernetes manages what runs on your nodes. Managing the nodes themselves is the challenge: kernel settings, system packages, storage layouts, security agents, and the host-level tuning that GPU workloads depend on. Many teams manage this with Ansible playbooks, custom scripts, and manual runbooks. That works until a new cluster comes up in a different region, a kernel upgrade breaks RDMA…
]]>
An AI coding agent’s patch can pass tests yet fail when the server loads a real model and handles requests. Evaluating changes to inference-serving software therefore requires checking the full serving path, including whether the system returns correct results through its public interface. Developed with input from the SGLang team, SWE-Serve evaluates this gap with 53 tasks derived from…
]]>
As large language model (LLM) inference increasingly processes sensitive information and proprietary model context across personal, enterprise, and regulated settings, data must be processed inside a trusted environment. NVIDIA Confidential Computing (CC) provides a pathway for running these workloads securely using memory-encrypted confidential virtual machines (CVMs), confidential GPUs…
]]>
AI factories are power-limited systems that deliver maximum value when fully optimized. GPU workload placement is a key optimization. Poor workload placement fragments topology domains and forces traffic across shared links, reducing throughput, raising job costs, and leaving GPUs consuming provisioned power while waiting on data without advancing the workload. GPUs exchange data continuously…
]]>
NVIDIA DLSS 5 introduces DLSS 3D-Guided Neural Rendering and granular controls that help game developers add lifelike lighting and material detail while preserving their artistic intent. We also look at updates to NVIDIA ACE, RTX Mega Geometry 2.0, and RTX Kit across character AI, high-density geometry, and rendering workflows. This post covers: DLSS 5 with 3D-guided…
]]>
GPU acceleration can speed up compute-intensive robotics workloads, but a fast CUDA kernel alone does not guarantee a fast ROS 2 graph. As messages move between nodes, they may continue to be serialized or copied through CPU memory, eroding the benefits of keeping perception and AI workloads on the GPU (Figure 1). With the upstream abstraction and the CUDA buffer backend that NVIDIA recently…
]]>
The compute and memory demands of generative AI increasingly exceed what a single GPU can provide. NVIDIA TensorRT multi-device inference is a new capability that enables a single TensorRT network to execute across multiple GPUs using NCCL-backed distributed collectives while retaining TensorRT inference optimizations. It is fully supported starting with TensorRT 11.0.
]]>
When you ship an AI agent, the key question is whether it can execute a chain of work across dozens of sequential tool calls against a live environment, and recover when a step fails. Scoring whether the model sounds right tells you almost nothing about whether the work finished. That gap is why agent evaluation has had to evolve from scoring a single function call to scoring an entire task…
]]>
Weather-sensitive industries increasingly have access to observations that offer an earlier, more local view of changing conditions. Energy companies collect measurements across wind and solar assets, emergency management teams rely on radar and local sensors, and satellite providers continuously observe the Earth. This data helps organizations understand and manage physical risk across sectors…
]]>
You’re deploying a model on a system. It starts up, prompts are getting responses. Now the hard question: Is this fast? Your instincts might lead you to send curl commands, hand-roll an asyncio script, or vibe code yet another one-off load generator. All of these paths have the same problem: single-process performance limits, Python’s GIL capping concurrency, or numbers measured against a…
]]>
Agentic AI workflows can be used to prepare and validate digital twins for physical AI systems. Agents can inspect 3D scenes, author simulation-relevant data in OpenUSD, add physics properties, render preflight views, and validate the result against simulation-ready (SimReady) requirements. This workflow follows that process from a scene in Blender to a simulation-ready OpenUSD handoff for NVIDIA…
]]>
AI agents are moving from cloud data centers to vehicles, robots, and other edge devices. Unlike a chatbot that answers a single prompt, an agent works through a sequence of steps. It selects tools, evaluates their results, and continues reasoning within an increasingly long conversation. This workflow places new demands on edge inference. The model must generate tokens quickly…
]]>
cuTile Rust () is a tile-based system for safe, idiomatic GPU kernel authoring in the Rust programming language. Extending the Rust ownership model to tile-based GPU kernels, it splits mutable outputs into disjoint pieces and preserves the host-side ownership contract across kernel launches. It also allows programmers to opt out locally when they need lower-level control…
]]>
How can a 30B-parameter model activate only 3B parameters per token, and still use the capacity of the larger model? Nemotron 3.5 Lightning illustrates the answer: It uses a Mixture-of-Experts (MoE) architecture that selects only a subset of its parameters for each token. There are two dominant model architectures: Dense model and MoE. How a model organizes its parameters matters as much as…
]]>
Power is a defining constraint for AI factories. As AI workloads demand a full compute platform to serve them, each component of that platform must maximize output within the factory’s limited power budget. This makes performance per watt—rather than raw, unnormalized throughput—the ultimate measure of an AI platform’s value. The NVIDIA Vera Rubin platform is designed to enable power…
]]>
For operators of large-scale AI factories, maximizing continuous output is essential for productivity. In massive-scale AI training, every GPU in the cluster must synchronize gradients across thousands of collective operations per second. Similarly, during inference, unplanned downtime directly reduces the total volume of requests served, strictly limiting revenue generation.
]]>
Federated learning (FL) projects often begin with a straightforward setup: one server, a few clients, and one dataset at each site. As those projects grow, the challenge shifts from running an algorithm to operating shared infrastructure. GPUs must be allocated when jobs need them, multiple research studies must remain separated, and every participating organization must retain control of its own…
]]>
Mixture of experts (MoE) has become one of the defining architectural trends in large-scale AI model training. DeepSeek, Qwen, and Mixtral are examples of MoE models that match or exceed the performance of dense model counterparts at a fraction of the training compute. MoE models provide efficient training through conditional computation. Instead of one dense feed-forward network (FFN) shared…
]]>
Deploying a large language model is only the first step toward production-ready serving. Production teams also need to serve as many concurrent users as possible on available GPU infrastructure while preserving the interactivity that keeps applications responsive. That tradeoff matters even more for agentic AI workloads, where prompts can be long, context can be reused across steps…
]]>
Biomolecular structure prediction is now often run at proteome scale, where the goal is to move an entire worklist through the pipeline efficiently. NVIDIA BioNeMo Inference Runtime (BioIR) helps accelerate supported biomolecular structure-prediction models on NVIDIA GPUs while keeping the familiar PyTorch workflow. It uses optimized kernels and, where applicable, CUDA Graphs to speed model…
]]>
NVIDIA has one of the largest and most complex supply chains in the world, and its performance is measured from wafer-out to first token. The interval is in two parts. Time-to-rack runs from silicon leaving the fab to an assembled system arriving on a data center floor. Time-to-token covers everything thereafter: power, cooling, networking, and the software stack that makes the infrastructure…
]]>
Encode-prefill-decode (EPD) disaggregation is an inference optimization technique for multimodal models that separates the vision encoder stage from the prefill and decode stages. It is most effective for image-heavy prompts, short-to-medium outputs, and quantized mixture-of-experts (MoE) models. This post shows when and how to use EPD disaggregation with NVIDIA Dynamo to achieve up to 5x…
]]>
Every NVIDIA CUDA Toolkit release adds functionality and performance improvements that help developers get more from NVIDIA GPUs and the broader NVIDIA software platform. CUDA Toolkit 13.4 adds support for Windows on Arm. CUDA applications have long been supported on Arm platforms through Linux; this release extends that capability to the Windows on Arm platform.
]]>
In September 2026, NVIDIA announced it is leaning into native GPU programming in Rust. CUDA C++ and CUDA Python are mature, enterprise-grade toolchains, and NVIDIA will be growing and maturing CUDA Rust into 2027 and beyond The systems layer of AI spans inference engines, serving infrastructure, drivers, and agent runtimes, and it churns constantly as models and techniques change.
]]>
Enterprise work spans messages, decisions, projects, and obligations that change over time. An AI agent that starts without this context must reconstruct it before contributing. To provide agents with this necessary context, our team used NVIDIA NemoClaw to build a memory-driven Chief of Staff. It maintains a human-readable knowledge layer called the self model: an agent memory of relevant…
]]>
Running reasoning and agentic AI at the edge has been harder than it needs to be. Until recently, models capable of multi-step reasoning were too large to run locally on edge hardware. Developers building agents have had to route inference through a data center, adding network dependency, increasing costs, and exposing data that may need to stay on device. That constraint is lifting.
]]>
Modern AI platforms are no longer a single application behind one login screen. A user may start in a central portal, open a governed dataset, launch a notebook where that data resides, and invoke an assistant that calls services in another cluster. The workflow feels unified, but identity crosses control-plane and data-plane boundaries at every step. That is where conventional single sign-on…
]]>
AI agents are learning to do more by working together. A lead agent can break a complex task into smaller jobs and assign those jobs to specialized subagents. Additionally, users are starting to run multiple agent sessions at the same time. Multi-agent workflows for accomplishing complex tasks are also becoming more common. This breadth-first approach can improve the speed of task completion…
]]>
]]>This post is the third in a series on AI model co-design. It explores how to accelerate LLM inference while maintaining accuracy using speculative decoding and offers five guidelines for selecting draft length and draft mechanism across the Pareto frontier. For a discussion of how model design choices impact both throughput and interactivity without sacrificing accuracy, see AI Model Co…
]]>
AI is changing the pace of cybersecurity. Agentic systems can coordinate work and pursue complex objectives over long horizons. Security teams are beginning to apply agents across security operations, but many implementations remain anchored to existing alerts, predefined workflows, and known attack behaviors. The harder problem is identifying what defenses miss and turning those gaps into…
]]>
The surge in AI adoption is transforming everything from chatbots to content generation. Still, a common pain point remains: How can organizations confidently size GPU resources for inference workloads and optimize Total Cost of Ownership (TCO)? With a dizzying mix of latency targets, model choices, quirky traffic patterns, and budget constraints, it’s easy to feel lost in the weeds…
]]>
Agentic AI is changing how research is done. AI scientists can read papers, propose hypotheses, call models, and determine which experiments to prioritize next. First proving their value in software engineering, coding agents now write, test, and ship production code. Scientific research can be more demanding and iterative. Researchers continually evaluate evidence, refine hypotheses…
]]>
A perception stack is shaped by the vehicle that carries it. Move the same software to a new carline—for example, from an SUV to a sedan or another vehicle variant in the portfolio—and its perception of the world changes. The sensor placement, calibration, fields of view, occlusions, body geometry, timing, and coverage all shift. A traffic light may appear in a different part of the frame.
]]>
Open AI models are evolving faster than ever, but bringing them into native applications can still require model-specific conversion, preprocessing, post-processing, and runtime code. NVIDIA TensorRT Model Connect open collection of reference implementations helps to address this challenge. TensorRT Model Connect shows you how to run supported models with NVIDIA TensorRT in native C++…
]]>
AI factories must support increasingly large models and more complex reasoning workloads. To keep up with the insatiable compute demands of AI workloads, hyperscalers and AI-native companies are developing custom AI accelerators, or XPUs. Deploying these accelerators at scale requires high-bandwidth memory (HBM) to keep compute fed, sufficient package and silicon area for more compute…
]]>
Navigation enables a robot to turn perception and motion into purposeful autonomy. Unlike locomotion, which produces stable movement, navigation must be used to continuously localize the robot, interpret changing surroundings, select a route, and avoid obstacles to reach a goal safely. Moving this capability to a new robot or scene can require new data, simulation assets, robot interfaces…
]]>
Alibaba released the model weights for Qwen3.8-Flash-Next as a preview of the upcoming Qwen4 architecture for developers to experiment with and evaluate. It’s a multimodal mixture-of-experts (MoE) model with a 125B-parameter main model supplemented by an additional 51B N-gram embeddings, with 6B parameters activated per token. It has a native 262,144-token context window, extensible to 1M tokens…
]]>
When an LLM engine process fails, the standard recovery path involves a cold restart. This requires loading weights into HBM from storage, compiling kernels, and capturing NVIDIA CUDA graphs. For large models, initialization can take several minutes, during which surviving workers must absorb the displaced traffic. Shadow engine recovery, available as a preview feature in NVIDIA Dynamo…
]]>
For years, a Python developer who needed a GPU had two realistic choices: Learn NVIDIA CUDA C++ well enough to write an extension, set up a build toolchain, and maintain bindings back to Python, which most people never did; or move up the stack and let someone else’s library do it, namely PyTorch, CuPy, or RAPIDS. The second option is why the Python GPU ecosystem thrives. But it has limits.
]]>
The massive growth of generative AI has fundamentally altered data center design. As distributed model training scales to span hundreds of thousands of GPUs, the scale-out network connecting these nodes has emerged as a first-order performance bottleneck. For decades, traditional off-the-shelf Ethernet has been the undisputed king of enterprise and cloud networking. It is cheap, standardized…
]]>
AI agents have expanded inference from single-turn interactions into multi-step workflows that reason, invoke tools, coordinate subagents, and carry growing context from one turn to the next. The scale of this shift is now visible in raw consumption: across 100 trillion tokens of real-world usage, OpenRouter’s State of AI report found that average prompt tokens per request grew roughly fourfold…
]]>
AI factories are power-constrained industrial systems. The question is no longer how many GPUs fit in a data center, but how much AI output each available megawatt can deliver. For AI inference workloads, this makes application-level performance per watt the key metric for measuring AI factory efficiency. Not every megawatt translates to revenue-generating compute. Power distribution, cooling…
]]>
Traditional cloud infrastructure was designed for predictable, general-purpose workloads and standard interfaces. Agentic AI factories connect diverse users, agents, applications, data sources, and storage systems to massively accelerated compute at multi-terabit bandwidth per server, making dedicated DPU processing essential for line-rate networking, storage, and security.
]]>
AI factories are interconnected systems where fleet economics depend on how efficiently the entire stack converts power and capital into completed agent tasks. While GPUs run the models, CPUs handle orchestration, tool execution, and sandboxed computation. Unlike conventional computing with stable runtime profiles, agentic workloads are unpredictable and highly variable. Based on telemetry from…
]]>NVIDIA Groq 3 LPX is the interactive AI inference accelerator for the NVIDIA Vera Rubin platform. At the core of the platform is NVIDIA Vera Rubin NVL72, the most versatile machine ever built, delivering high throughput and interactivity across the widest range of AI workloads—from small to large models, both open and closed. Groq 3 LPX, when paired with Vera Rubin NVL72, extends the platform’s…
]]>
Use AdaptGrow, a GPU-accelerated matrix factorization algorithm, to turn rolling correlation and tail-dependence matrices into hard clusters, soft factor loadings, and structural-break signals at single-GPU and multi-node scale Quant strategies routinely group instruments for portfolio construction, risk aggregation, statistical arbitrage, and trade surveillance. Incorrect groupings can make…
]]>
As AI agents become more capable and operate over longer horizons, building security and trust into the applications they power becomes increasingly important. Drawing on work with NVIDIA OpenShell, agent developers, open-source projects, and partners across the ecosystem, AI safety and security teams at NVIDIA offer their perspective on the emerging agent stack—including the role of each layer…
]]>
A frontier language model is only one component of an AI agent. The surrounding agent system—often called a harness—determines how the model receives context, uses tools, maintains state, responds to feedback, recovers from failure, and sustains progress over long-running tasks. The challenge is how to build the agent architecture that makes frontier language models work reliably on extended…
]]>
Recommender systems (RecSys) are one of the most ubiquitous machine learning problems in the consumer internet industry yet notoriously difficult to train and serve at scale. The advent of LLMs has inspired a shift from the traditional embedding-similarity-based objective to a generative one, where the goal is to predict the next action or item in a large catalog given a sequence of user histories.
]]>
NVIDIA Holoscan is a platform for building real-time AI applications at the edge, from medical imaging to robotics. HoloHub is its companion repository: a growing collection of reference applications and components that demonstrate what’s possible. We wanted to explore how a general-purpose coding agent could use the same examples, documentation, and development tools available to an engineer…
]]>
Modern vision-language models (VLMs) can support tasks such as visual question answering, captioning, and image-text reasoning. In practice, however, the data needed to adapt these models may be distributed across institutions or organizations that cannot centralize their raw records. Federated learning provides a way to coordinate training across these data-local sites. For VLMs…
]]>
Robots need policies that can adapt to their sensors, environments, and tasks while running on onboard computing hardware. World models offer a foundation for learning physical interactions, but their size can make on-device deployment difficult. This changes with the new NVIDIA Cosmos 3 Edge. Cosmos 3 Edge is a 4B omni-model (with a 2B NVIDIA Nemotron-based reasoner) in the Cosmos 3 family.
]]>
AI agents are only as effective as the context they receive. Even with capable models and well-documented NVIDIA libraries, agents can spend extra steps finding the right tools, burn tokens on dead ends, or struggle with specialized tasks. Skills package the instructions, examples, and tool guidance for agents to move faster from intent to solution. To measure whether these skills improve agent…
]]>
Atomistic simulation requires three things: knowledge of the science, compute-efficient implementation of simulations, and accessible interfaces to the simulation stack. The first remains the researcher’s domain, as no tool substitutes for knowing what to simulate or recognizing a physically meaningful result. NVIDIA ALCHEMI Toolkit, introduced earlier this year, has dramatically reduced the…
]]>
Uniform Manifold Approximation and Projection (UMAP) is a dimensionality reduction technique widely used for visualization and feature extraction. Applications range across exploratory data analysis, topic modeling, and single-cell analysis. Many of these workflows are iterative and exploratory, requiring UMAP to be run repeatedly as users analyze their data or tune parameters. As datasets grow…
]]>
Teams customize their models to hit their targets for latency, speed, memory, and compute. With the open NVIDIA Nemotron family of models, developers can find the right-sized model for their needs. The new Nemotron 3.5 Lightning NVFP4 checkpoint, for example, preserves accuracy while unlocking up to 4x faster throughput. It’s compressed down to 22 GB from the 66 GB full precision checkpoint…
]]>
Alibaba released the open weights for Qwen3.8-2.4T-A95B (Qwen3.8-Max), its largest open-weight model, bringing near-frontier capabilities to the open ecosystem. It has 2.4T total parameters with 95B activated per token. It’s a fine-grained mixture of experts (MoE) architecture with a hybrid of full and linear attention, a context window of up to one million tokens, and an output length of up to…
]]>
AI infrastructure spans multiple layers, from compute and networking to storage, orchestration, and applications. When performance degrades, identifying the source can be difficult because a symptom observed at one layer may originate elsewhere in the stack. A full-stack observability strategy connects telemetry across these layers, helping infrastructure and operations teams detect problems…
]]>
Video is a core data path across NVIDIA Jetson applications, from robotics and intelligent video analytics to industrial automation, healthcare, media processing, and remote operations. A system may capture several cameras, decode network streams, run AI inference or conventional vision processing, draw results, and encode video for storage or delivery. The individual calls are…
]]>
Long-running AI agents spend most of their time on high-volume execution: tool calls, result validation, and subagent delegation. Using a frontier reasoning model for every execution step adds cost and latency. NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for that execution layer of always-on agents. It is designed for harnesses…
]]>
Building an AI agent does not end with choosing a single model. Each model has its own strengths, weaknesses, and cost profile, which can shift from one workload to another—or even within the same workload. For example, an agentic task may need classification for one step, reasoning for the next, and a smaller model for routine follow-up tasks. Sending every request to the largest model can…
]]>
Meta returns to the open source ecosystem with the release of Muse Glimmer, a 30B open-weight dense model with a 120K+ context window built for local AI agentic work. Optimized to run across a range of NVIDIA edge, desktop, and workstation AI platforms, Muse Glimmer delivers 20K tokens/sec on a single GPU, enabling always-on agents to process data locally and execute complex…
]]>
A central challenge in robotics is building policies that generalize beyond the demonstrations they’re trained on. A policy that succeeds in a training scene often fails when object shapes, positions, or lighting change. Generalizing to these new conditions requires the policy to understand the tasks underlying physics, not just mimic the demonstrations. This ability comes from the backbone it’s…
]]>
Autonomous vehicle (AV) development often relies on separate models for trajectory generation, high-level intent prediction, scene understanding, and data labeling. This separation makes it hard to compare related outputs, investigate model behavior, and reuse the same representations across the development workflow. NVIDIA Alpamayo 2 Super is an open 34-billion-parameter reasoning vision…
]]>
Running a dedicated Kubernetes cluster per team often results in more isolation than an organization requires. While one cluster can be successfully shared across many teams, the coordination costs increase as the number of teams grows. Challenges include conflicting CRD versions, overlapping RBAC, and no clean way to carve GPU capacity into team-level budgets. At a certain scale…
]]>
Storage is an active part of every agentic AI workflow. As agents retrieve enterprise knowledge, access persistent memory, reuse key-value (KV) cache data, execute tools, and generate new results, storage systems must continuously supply and preserve the data that moves the agent reasoning loop. Each agent step can trigger multiple storage operations, and those operations can repeat across…
]]>As agentic and long-context workloads become common, the context lengths increase and attention consumes a larger share of inference time (Figure 1). Because attention now dominates that cost, how it is designed—not just how it is implemented—increasingly determines a model’s inference performance. Shaping model architecture around how GPUs execute it is the premise of AI model co-design.
]]>
The demand for high-quality video continues to accelerate across industries, powering everything from immersive streaming experiences to remote collaboration, generative AI media tools, and large-scale content delivery. Behind these experiences is a growing need for video pipelines that are faster, more efficient, and capable of handling increasingly complex formats and workloads.
]]>
NVIDIA nvmath-python is a library designed to bridge the gap between the Python scientific community and NVIDIA CUDA-X math libraries. It gives Python users access to CUDA-X performance for common math operations without disrupting existing workflows. Depending on the API, operations can run on a CPU, CUDA-enabled GPU, or distributed multi-GPU, multi-node systems.
]]>
Knowledge workers are increasingly integrating AI agents into their workflows. Agents that function as “digital coworkers” offer clear benefits. For example, they can review a bug report, implement and test a fix, push a patch, and ping a human for review. By handling routine tasks, agents have the potential to deliver large productivity gains. On the other hand, connecting a large language model…
]]>
Two AI computing clusters built from identical NVIDIA H100, GB200 NVL72, or GB300 NVL72 systems can deliver materially different training throughput. We routinely see 8% to 12% gaps between partner deployments and the corresponding NVIDIA reference architecture (RA) on the same workload, same model, same global batch size. The cause is often a stack of configuration choices in the kernel…
]]>
Deploying an AI coding assistant in a regulated, sovereign, or source-sensitive environment, often comes with challenges. Three common issues are: the source cannot leave the network, the assistant occasionally invents package names that introduce supply-chain risk, and there is no audit trail when a generated change ships a defect. This tutorial walks you through how to self-host a validated…
]]>
Unlike autonomous driving or industrial robotics, healthcare robotics can’t rely on internet-scale data collection or unlimited real-world experimentation. Every demonstration requires specialized equipment, clinical expertise, and access to patients or laboratory environments. This creates three fundamental challenges for developers. First is the data gap. Training modern robotic policies…
]]>
NVIDIA Ising Calibration is an open source vision language model (VLM) designed to interpret diagnostic outputs from quantum processors and determine how they should be tuned to continue operating. This post introduces the latest model release, NVIDIA Ising Calibration 1.5, which advances AI-based QPU calibration by analyzing unfamiliar diagnostic results without prior training examples.
]]>
Building a great AI agent isn’t just about choosing the right models. The harness is the architecture surrounding the model. How it renders context, executes actions, manages state, and decides when a task is done shapes outcomes just as much as the model itself. Harness design alone can account for double-digit swings in benchmark results and significant differences in token cost…
]]>