Education & Research Software & Algorithm Provider Cloud & Data
NVIDIA Vera Rubin NVL72 Achieves Exceptional Performance in MLPerf Inference v6.1 Launch
Original from NvidiaNews: NVIDIA Vera Rubin NVL72 Delivers Leading Performance in MLPerf Inference v6.1 Debut

NVIDIA Vera Rubin NVL72 Achieves Exceptional Performance in MLPerf Inference v6.1 Launch

NVIDIA has unveiled the Vera Rubin NVL72, showcasing its impressive performance in the MLPerf Inference v6.1 benchmarks. The NVL72 demonstrates up to 3.7 times higher throughput than the GB300 NVL72 on the Qwen3-VL benchmark and up to 2.5 times higher on DeepSeek-R1, highlighting its efficiency in AI inference tasks.

This advancement is significant for organizations focusing on AI infrastructure, as it emphasizes the importance of performance, scaling efficiency, and software optimization in driving long-term inference economics. The Vera Rubin NVL72's design allows for high utilization across various workloads, enhancing revenue generation while reducing costs per token.

Looking ahead, the introduction of the MLPerf Endpoints benchmark will provide standardized metrics for evaluating agentic inference workloads, further refining performance measurement in AI. The ongoing innovations from NVIDIA, particularly in disaggregated serving and expert parallelism, are expected to continue shaping the future of AI inference performance.

Editor's Note

The launch of the NVIDIA Vera Rubin NVL72 marks a pivotal moment in AI inference technology, emphasizing the need for robust performance and efficient scaling in enterprise applications. As organizations increasingly rely on AI for decision-making, the ability to optimize infrastructure and software will be crucial for maintaining competitive advantage. The advancements in performance metrics and benchmarks will likely influence procurement strategies in the robotics and AI sectors.

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

DeepCybo Releases PhysBrain 1.5 with 72.5 Average on 28 Benchmarks as Open Source

DeepCybo Releases PhysBrain 1.5 with 72.5 Average on 28 Benchmarks as Open Source

DeepCybo has announced the open-source release of PhysBrain 1.5, achieving an impressive average score of 72.5 across 28 public embodied benchmarks. This model, which features both 2B and 8B parameters, is designed to enhance unified understanding, action, and future-state token capabilities, alongside an evaluation kit. The significance of this release l...

Nvidia's Les Karpas Discusses Robotics' Need for a Breakthrough at TechCrunch Disrupt 2026

Nvidia's Les Karpas Discusses Robotics' Need for a Breakthrough at TechCrunch Disrupt 2026

At TechCrunch Disrupt 2026, Les Karpas, Nvidia Inception’s Global Head of Physical AI, will explore the robotics industry's quest for a transformative moment akin to ChatGPT's impact on AI. He will address the current limitations in robotics, particularly the lack of comprehensive datasets for physical AI, which hinders progress. The significance of Karpa...

Startups AI Robotics
Emerald AI, Google, and NVIDIA Form Alliance to Enhance AI Data Center Flexibility

Emerald AI, Google, and NVIDIA Form Alliance to Enhance AI Data Center Flexibility

Emerald AI, Google, and NVIDIA have announced the formation of the AI Energy Management Alliance (AEMA), aimed at advancing data centers that can dynamically manage electricity usage based on grid conditions. This initiative seeks to enhance AI infrastructure by enabling more efficient energy use, ultimately supporting community energy systems and reducin...

Rhoda AI Evaluates Impact of Web-Video Pretraining on Industrial Robot Performance

Rhoda AI Evaluates Impact of Web-Video Pretraining on Industrial Robot Performance

Rhoda AI has reported enhancements in industrial manipulation capabilities through scaled web-video pretraining, as detailed in a study released on September 10. The research tested various model sizes, achieving completion rates of 3.7%, 65.0%, 75.3%, and 84.7% in under 100 seconds for tasks like unpacking bearings and sorting waste, with the largest mod...

US rhoda-ai
NVIDIA Highlights AI Factory Efficiency and Energy Optimization at AI Infra Summit

NVIDIA Highlights AI Factory Efficiency and Energy Optimization at AI Infra Summit

Ian Buck, NVIDIA's vice president of hyperscale and high-performance computing, presented on AI factory efficiency at the AI Infra Summit held at the Santa Clara Convention Center. The event attracted over 8,000 attendees, a significant increase from 3,500 last year. Buck emphasized the need for AI infrastructure to evolve as agentic AI workloads demand e...

Major Children's Hospital Implements Open Source NVIDIA AI for Enhanced Cardiac Care

Major Children's Hospital Implements Open Source NVIDIA AI for Enhanced Cardiac Care

A prominent children's hospital has adopted open source NVIDIA AI technology to improve its cardiac care services. This integration allows for advanced data processing and analysis, enhancing the hospital's ability to provide accurate diagnoses and treatment plans for pediatric patients. The use of NVIDIA AI is significant as it enables healthcare profess...

NVIDIA's AI Factory Achieves Power Efficiency with Emerald AI's Conductor Platform

NVIDIA's AI Factory Achieves Power Efficiency with Emerald AI's Conductor Platform

In August, Silicon Valley Power prompted an AI factory to adjust its power consumption, showcasing the capabilities of Emerald AI's Conductor platform. This grid-orchestration tool, developed in partnership with NVIDIA, allows data centers to manage workloads flexibly, ensuring critical AI operations continue while reducing electricity demand during peak ...

University of Manchester Leverages NVIDIA Earth-2 for UK Air Pollution Forecasting

University of Manchester Leverages NVIDIA Earth-2 for UK Air Pollution Forecasting

The University of Manchester has developed a new air pollution forecasting model using NVIDIA Earth-2 technology, addressing a significant public health issue in the UK. With air pollution contributing to approximately 30,000 deaths annually, the integration of generative frameworks from NVIDIA aims to enhance the accuracy and frequency of air quality pre...

IMTS 2026 Preview: Record Orders and the Automation Story

IMTS 2026 Preview: Record Orders and the Automation Story

IMTS 2026 opens in Chicago with 1,788 exhibitors and record H1 machine tool orders. What the USMTO data says about automation, and the booths to see.

Market and Business News
Geekplus Launches Next-Generation RoboShuttle Hyper for High-Throughput Operations

Geekplus Launches Next-Generation RoboShuttle Hyper for High-Throughput Operations

Geekplus (HKEX: 2590) has introduced RoboShuttle Hyper, a cutting-edge tote-to-person climbing autonomous mobile robot (AMR) solution. Designed for high-throughput applications such as B2C e-commerce and cold-chain fulfillment, RoboShuttle Hyper can handle up to 6,000 totes per hour per 1,000 square meters, significantly enhancing operational efficiency. ...

Order Picking & Sortation
China’s Dexterous Hand Industry, 2026 Part 3 — The Players

China’s Dexterous Hand Industry, 2026 Part 3 — The Players

Five vendor archetypes, MIR’s composite top ten, eight company profiles and six field deployments — every firm linked to the RobotToday supplier directory.

Components and Hardware Humanoids
HII Aims for 15% Increase in Shipyard Throughput Using Robotics for Navy Warships

HII Aims for 15% Increase in Shipyard Throughput Using Robotics for Navy Warships

HII, the largest military shipbuilder in the US, is targeting a 15% increase in shipyard throughput this year to expedite deliveries to the US Navy. The strategy involves workforce expansion, infrastructure upgrades, and enhanced use of technology, particularly physical AI, in shipbuilding operations. Currently, around 40 ships are under construction or m...

Military

Related Suppliers

NVIDIA Robotics

NVIDIA robotics division delivering Isaac simulation and training tools, Jetson edge compute modules, and Omniverse digital twin frameworks for physical AI.

Core Component Supplier Software & Algorithm Provider

Deci AI (Acquired by NVIDIA)

Israeli deep learning optimization startup acquired by NVIDIA in May 2024 for ~$300M; known for AutoNAC neural architecture search technology.

Nscale

London-based Nscale runs a full-stack AI/GPU cloud platform and on Aug 1, 2026 agreed to acquire Anyscale for $1.65 billion.

Super Micro Computer, Inc.

San Jose AI server and edge computing leader; NVIDIA-Certified Systems from data center to industrial edge enabling robotics inference and automation AI.

Crusoe

Denver-based AI infrastructure company operating energy-first GPU cloud data centers, including a nuclear-powered facility built with Aalo Atomics.

Weldon Solutions

FANUC-certified robotic system integrator and CNC cylindrical grinder manufacturer based in York, PA.

Modular

Modular built the Mojo language and MAX AI-inference platform for GPUs/CPUs before Qualcomm completed its acquisition of the firm in July 2026.

Apptronik

Austin-based humanoid robotics company; Apollo humanoid (1.73m, 25 kg payload) deployed at Mercedes-Benz and GXO Logistics; NASA JSC spinout; $935M+ raised.

Humanoid

AMESA

Walnut Creek CA AI startup (formerly Composabl, 2023); intelligence engineering platform for designing and deploying multi-agent autonomous systems.

Yaskawa America Inc., Drives and Motion Division

U.S. division of Yaskawa Electric (Japan, est. 1915) supplying AC inverter drives, servo motors, and motion controllers to North and South America.

ReSim

US virtual testing platform that runs parallel simulation, log replay, and hardware tests in the cloud for autonomous robots and vehicles.

Cloud & Data Software & Algorithm Provider

Polestar

Swedish electric performance car brand deploying ADAS and Level-3-capable autonomous driving tech in its EVs.

inJoin the RobotToday community on LinkedIn

Daily robotics news, in-depth analysis, conference highlights, and discussions with professionals worldwide.