Education & Research Logistics & Supply Chain Industrial Manufacturing Software & Algorithm Provider Cloud & Data
NVIDIA Vera Rubin NVL72 Achieves Gigascale Performance with Lowest Token Cost for Partners
Original from NvidiaNews: NVIDIA Vera Rubin Driving Performance Per Watt, Lowest Token Cost for Partners Worldwide

NVIDIA Vera Rubin NVL72 Achieves Gigascale Performance with Lowest Token Cost for Partners

NVIDIA has launched the Vera Rubin NVL72, which is ramping up production across partners including CoreWeave, Google Cloud, Microsoft Azure, and Oracle Cloud Infrastructure. This platform boasts the largest rack-scale supply chain, spanning over 350 factory sites in 30 countries, designed to meet the increasing compute demands of AI applications.

The Vera Rubin platform is engineered for optimal performance, delivering the highest performance per watt and the lowest token cost. CoreWeave's benchmark indicates a tenfold increase in throughput per megawatt compared to the Grace Blackwell NVL72, highlighting its efficiency for power-constrained AI factories. The system integrates seven chips and five rack trays, including the NVIDIA Vera CPU, which enhances single-threaded performance and reduces memory latency significantly.

Looking ahead, NVIDIA's innovations in networking and cooling technologies, such as the sixth-generation NVLink and Spectrum-X Ethernet, promise to further enhance AI infrastructure capabilities. No further timeline was disclosed at the time of publication.

Editor's Note

NVIDIA's Vera Rubin NVL72 represents a significant advancement in AI infrastructure, particularly for enterprises focused on maximizing efficiency and performance. The integration of advanced cooling and networking technologies positions it as a competitive solution in the rapidly evolving landscape of AI and cloud computing.

RobotToday Initiative

Robotics needs a service framework.

RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.

Share

Related Articles/News

NVIDIA Spectrum-6 Launches in Gigascale AI Factories to Enhance Performance

NVIDIA Spectrum-6 Launches in Gigascale AI Factories to Enhance Performance

NVIDIA has introduced the Spectrum-6, a 102.4-terabit-per-second Ethernet switch system, to the world's gigascale AI factories. This new system, part of the NVIDIA Vera Rubin platform, offers double the capacity of its predecessors, enhancing the networking capabilities essential for training advanced AI models and generating intelligence at scale. The de...

WAIC 2026 Ten Flagship Exhibits

WAIC 2026 Ten Flagship Exhibits

WAIC 2026 named ten Flagship Exhibits from 3,000+ products — spanning domestic AI superclusters, humanoid robots, general-purpose agents, AI wearables, and protein design AI. Engineering breakdown by RobotToday.

Market and Business News
Bristol Myers Squibb Launches Advanced AI Factory with NVIDIA Vera Rubin Technology

Bristol Myers Squibb Launches Advanced AI Factory with NVIDIA Vera Rubin Technology

Bristol Myers Squibb (BMS) has announced the deployment of its second NVIDIA DGX SuperPOD, featuring eight DGX Vera Rubin NVL72 systems. This new AI cluster is touted as the most powerful and energy-efficient in the life sciences sector, significantly enhancing researchers' access to AI capabilities. BMS aims to democratize AI access among its scientists,...

AI for Science 2026: The Global Race for Scientific Discovery

AI for Science 2026: The Global Race for Scientific Discovery

2026 AI for Science landscape report: WAIC 2026 exhibitor breakdown, MIT Boltz-2 and CMU Coscientist case studies, US/China/EU policy comparison, Anthropic Claude Science, and US academic cautionary views.

Artificial Intelligence
Nvidia and Hugging Face Enhance LeRobot with Advanced Open Robotics AI Tools

Nvidia and Hugging Face Enhance LeRobot with Advanced Open Robotics AI Tools

Nvidia and Hugging Face have expanded their partnership to introduce new AI models and robotics frameworks to the LeRobot platform, enhancing accessibility for developers. The integration of Nvidia Isaac GR00T 1.7, a vision-language-action foundation model, and the Isaac Teleop framework aims to streamline the development process for AI-powered robots. Th...

Artificial Intelligence Computing ai
Fujitsu Collaborates with Fanuc, Yaskawa, and Kawasaki to Enhance Physical AI with Nvidia

Fujitsu Collaborates with Fanuc, Yaskawa, and Kawasaki to Enhance Physical AI with Nvidia

Fujitsu has initiated a partnership with Japanese robotics firms Fanuc, Yaskawa Electric, and Kawasaki Heavy Industries to advance the development and deployment of physical AI in sectors such as manufacturing, logistics, and healthcare. This collaboration will leverage Nvidia's physical AI technologies to create a collaborative control platform that conn...

Artificial Intelligence Industry News
Toyota and Nvidia Enhance Collaboration to Advance AI in Vehicles, Manufacturing, and Urban Infrastructure

Toyota and Nvidia Enhance Collaboration to Advance AI in Vehicles, Manufacturing, and Urban Infrastructure

Toyota and Nvidia have broadened their partnership to develop physical AI technologies that encompass next-generation vehicles, manufacturing, robotics, and urban infrastructure. This collaboration builds on a previous agreement, focusing on advanced driver-assistance systems using Nvidia's DRIVE AGX platform and DriveOS operating system. The significance...

Computing News advanced driver assistance systems
ROBOTTODAY Weekly July 13 – 17, 2026

ROBOTTODAY Weekly July 13 – 17, 2026

This week in robotics: Hyundai takes full ownership of Boston Dynamics, Xpeng targets 1,000 Iron humanoids a month, LimX Dynamics raises $200M pre-IPO, and Agility opens a Silicon Valley physical-AI hub. July 13–17, 2026.

RobotToday Weekly
WAIC 2026: Embodied Intelligence Enters Industrial Deployment Era

WAIC 2026: Embodied Intelligence Enters Industrial Deployment Era

WAIC 2026 in Shanghai (July 17–20) saw 200+ embodied intelligence companies, 300+ live robots, and first confirmed humanoid deployments in logistics and pharmacy. RobotToday engineering analysis.

Market and Business News
Japan Allocates $2.4 Billion for AI Development with NVIDIA Chip Acquisition

Japan Allocates $2.4 Billion for AI Development with NVIDIA Chip Acquisition

On July 16, Japan's Ministry of Economy, Trade and Industry announced a significant investment of 387.3 billion yen (approximately $2.4 billion) to support the AI company Noetra. This funding will be used to procure around 27,500 NVIDIA Rubin GPUs for the establishment of a national AI data center, marking one of the largest single-country chip procuremen...

AI Technology Robotics NVIDIA Chips
NVIDIA's Vera Rubin Enhances Intelligence per Dollar for Continuous Agentic AI Post-Training

NVIDIA's Vera Rubin Enhances Intelligence per Dollar for Continuous Agentic AI Post-Training

NVIDIA's Vera Rubin is redefining post-training workloads for agentic AI, emphasizing continuous adaptation and refinement. Unlike traditional models, agentic AI requires ongoing adjustments as environments and tools evolve, making post-training a critical, never-ending process. This shift necessitates a new compute pattern, focusing on maximizing intelli...

Japan Plans Acquisition of 27,500 Nvidia Rubin Chips for Domestic AI Robotics Development

Japan Plans Acquisition of 27,500 Nvidia Rubin Chips for Domestic AI Robotics Development

Japan is set to purchase 27,500 next-generation Rubin chips from Nvidia Corp. to develop a foundational AI model tailored for robotics. This initiative aims to enhance Japan's capabilities in creating sovereign AI systems that can be integrated into various robotic applications. The acquisition of these chips is significant as it represents Japan's commit...

Related Suppliers

Deci AI (Acquired by NVIDIA)

NVIDIA's product suite encompasses advanced GPU architectures, including the Ampere and Ada Lovelace series, designed for high-performance computing and AI workloads. The CUDA parallel computing platform enables developers to leverage GPU acceleration for complex algorithms. Additionally, NVIDIA's deep learning frameworks, such as TensorRT, optimize inference performance across diverse applications, enhancing computational efficiency in data centers and edge devices.

NVIDIA Robotics

NVIDIA's architecture leverages parallel processing capabilities through CUDA cores, optimizing performance for AI and deep learning applications. The platform integrates Tensor Cores for enhanced matrix operations, facilitating efficient neural network training. Additionally, real-time ray tracing technology improves rendering quality in graphics applications. The ecosystem supports various APIs, including DirectX and Vulkan, ensuring compatibility across diverse software environments.

Core Component Supplier Software & Algorithm Provider

Spectrum Design, LLC

Spectrum Design LLC engineers custom machinery, system integration, and industrial automation solutions including robotic integration, machine vision, welding, motion control, conveying, and tooling systems.

Industrial Manufacturing System Integrator

Baraja

Australian deep technology company developing the Spectrum-Scan LiDAR platform for autonomous vehicles. Uses optical dispersion through prisms instead of mechanical moving parts to scan environments, delivering high precision, long range, and reliability without oscillating mirrors or fragile components.

Real Time Automation

Its products can move data between EtherNet/IP, PROFINET, Modbus TCP, Modbus RTU, BACnet, SNMP and other networks. The company builds industrial protocol gateways, edge data historians and embedded connectivity software used on factory floors and inside OEM devices worldwide.

Industrial Manufacturing Software & Algorithm Provider System Integrator

Moxa Inc.

Moxa is a Taiwanese manufacturer of industrial networking, computing, and automation hardware enabling Industrial IoT (IIoT) connectivity. Products include industrial Ethernet switches, serial servers, embedded computers, and automation controllers serving energy, transportation, and factory automation sectors globally.

Industrial Manufacturing Robot Manufacturer Software & Algorithm Provider

Jibang Precision 惠州吉邦

Jibang Precision manufactures and supplies high-precision, high-reliability, complex-structure metal components via casting, machining and multi-process integration, serving industries such as automotive, AI data-centre liquid cooling, new energy and industrial equipment. jbcasting.com+1

HRL Laboratories, LLC

US private research laboratory advancing semiconductor, photonic, and defence technologies for automotive, aerospace, and national security. Conducts R&D in GaN chips, quantum computing, liquid cooling, and emerging hardware technologies since 1997.

Education & Research Research Institute Software & Algorithm Provider

Kindred Systems (CA)

Canadian developer of persistent multi-agent AI infrastructure providing cryptographic identity, layered memory, and ethical coordination protocols for autonomous AI systems. Focuses on governance and accountability frameworks for AI agent ecosystems.

Software & Algorithm Provider Control & Software Systems Human-Machine Interaction

Lightwheel

Lightwheel develops a Physical AI infrastructure, focusing on SimReady assets, synthetic data, and evaluation platforms. The architecture comprises three layers: World, Behavior, and Evaluation. The World Layer utilizes SimReady assets to create physically accurate environments, while the Behavior Layer generates training data for robots. The Evaluation Layer addresses the challenges of scaling robot-agnostic pretraining data.

QNX

QNX offers a high-performance, safety-ready microkernel Real-Time Operating System (RTOS) designed for embedded systems in automotive applications. The platform supports modular development through the QNX Software Development Platform (SDP) and General Embedded Development Platform (GEDP), facilitating secure, scalable solutions. With a proven track record in safety certification, QNX is integral to mission-critical systems across the automotive industry.

Swift Navigation

Skylark is a cloud-based GNSS correction service designed for mass market applications, providing precise positioning through Network RTK and atmospheric modeling techniques. The Swift Automotive Suite offers a modular software solution for vehicle localization, adhering to ISO 26262 standards for functional safety. Key industries served include automotive, mobile robotics, drones, fleet management, and GIS mapping.