From Nvidia's newsroom - japan partners to take tech hi-road w3hile India takes the masses road
NVIDIA AI Summit Japan—NVIDIA today announced that Japan cloud leaders SoftBank Corp., GMO Internet Group, Highreso, KDDI, Rutilea and SAKURA internet are building AI infrastructure with NVIDIA accelerated computing, networking and software to accelerate transformation across the nation’s robotics, automotive, healthcare and telecom industries.
The services from Japan’s cloud providers are supported through a Japan Ministry of Economy, Trade and Industry (METI) program to supply critical compute resources across industries. The cloud providers are operating their AI data centers across the country’s central, northern and western regions to support development with national and regional NVIDIA accelerated computing infrastructure.
“Japan’s companies stand to benefit tremendously from the new industrial revolution powered by AI,” said Jensen Huang, founder and CEO of NVIDIA. “Company employees will supercharge their speed and productivity by automating work with AI agents. Industrial companies of tomorrow will operate dual factories — new AI factories to produce software intelligence for the products and machines their factories make today. Working with NVIDIA, Japan’s cloud providers are building the AI factories essential to reinvent the country’s automotive, robotics, telecommunications and healthcare industries for the age of AI.”
Japan Cloud Services Across Nation Support Industries With NVIDIA AI
SoftBank Corp. has adopted the NVIDIA Blackwell platforms to build Japan’s most powerful AI supercomputers, including the world’s first NVIDIA DGX SuperPOD™ with NVIDIA DGX B200 systems.
SoftBank Corp. is using its NVIDIA AI infrastructure to accelerate a broad range of industries, including its subsidiary SB Intuitions, which is using NVIDIA AI for the research and development of high-performance Japanese-native large language models (LLMs).
GMO Internet Group is launching its GMO GPU Cloud, which will be the first local cloud offering in Japan featuring full-stack NVIDIA H200 Tensor Core GPUs, the NVIDIA Spectrum-X™ Ethernet platform for AI, NVIDIA BlueField™-3 DPUs and the NVIDIA AI Enterprise software suite. Built on Dell PowerEdge servers, the service is expected to come online this month to provide cloud-based AI computing for businesses in Japan.
GMO GPU Cloud customers will be able to use NVIDIA AI Enterprise software to accelerate their generative AI applications running in production on the platform.
Highreso is accelerating AI development in Japan with the establishment of Highreso Kagawa, a dedicated AI data center powered by NVIDIA accelerated computing. Built with NVIDIA H200 Tensor Core GPUs, the Kagawa data center is expected to begin operations next month and will provide high-performance infrastructure for Highreso’s GPUSOROBAN AI Supercomputer Cloud service.
A second Highreso AI data center is scheduled to come online next summer. Together, they will provide researchers and businesses across Japan with access to 1,600 NVIDIA GPUs, helping foster AI development in manufacturing, research and educational institutes.
KDDI is launching AI computing infrastructure built with NVIDIA HGX™ systems to support generative AI and specialized LLM development in collaboration with its ELYZA business group. With NVIDIA software, KDDI customers can use the infrastructure to accelerate AI model training and inference, build digital twins and run simulation workloads for autonomous vehicles, robotic motion control and sensor data processing.
KDDI is also planning a liquid-cooled data center that is expected to feature the NVIDIA GB200 NVL72 platform with NVIDIA GB200 Grace Blackwell Superchips.
Rutilea, an NVIDIA Inception member based in Kyoto, is doubling the NVIDIA Hopper™ computing available in its AI cloud data center. The startup is providing more than 1,000 NVIDIA Hopper GPUs, which will be used for LLM development by customers building foundation models for animation, retail and food services, vision-based editing and data extraction.
Additionally, Rutilea subsidiary AI Fukushima began operations of a new data center in Okuma, Fukushima, in September to support continued industry recovery following the 2011 Tohoku earthquake. AI Fukushima, which operates the infrastructure implemented by Rutilea, aims to contribute to the revitalization of the regional economy and local development by providing cutting-edge AI computing platforms.
SAKURA internet plans to expand its Koukaryoku cloud services for generative AI from 2,000 to nearly 4,000 NVIDIA Hopper GPUs. It also plans to install NVIDIA HGX B200 infrastructure with Blackwell GPUs at its Ishikari data center, which is expected to be fully powered by renewable energy by 2027. SAKURA internet intends to provide approximately 10,800 GPUs as part of its high-performance AI computing offering.
SAKURA internet customers include the National Institute of Informatics (NII), a public-sector research organization. NII has established the Research and Development Center for Large Language Models and is promoting collaboration among industry, government and academia in Japan through open generative AI research and development activities, including the development of Japanese-centric medical LLMs. Japan-based driving software startup TIER IV is also using NVIDIA-accelerated SAKURA internet computing in its vision to develop intelligent vehicles with its open-source software.
