Don't miss our #SC24 session on the future of InfiniBand. Industry leaders will highlight how the latest #networking developments are bridging scientific computing with mainstream generative transformer models, natural language processing, and data analytics. Register today➡️ https://nvda.ws/3O0tYSZ
NVIDIA Networking
Computer Networking Products
Santa Clara, California 31,827 followers
Accelerated Networks for Modern Workloads
About us
Data center networking is essential in confronting the challenges of modern-day computing. NVIDIA networking delivers accelerated software-defined networking, storage, security, and management services that are turning the data center into one compute unit.
- Website
-
https://www.nvidia.com/en-us/networking/
External link for NVIDIA Networking
- Industry
- Computer Networking Products
- Company size
- 10,001+ employees
- Headquarters
- Santa Clara, California
Updates
-
Join NVIDIA at #VMwareExplore to discover how NVIDIA BlueField-3 DPUs transform your VMware Cloud Foundation, enhancing scale and security. Don't miss this chance to elevate your cloud strategy. Check out this session➡️ https://nvda.ws/4fbEJOq
-
NVIDIA Networking reposted this
📣 We unveiled Enterprise Reference Architectures, the comprehensive blueprints to help OEMs and joint customers build their own #AI factories — high-performance, scalable and secure #datacenters for manufacturing intelligence. Read the blog to learn more ➡️ https://nvda.ws/48yt2P9
-
NVIDIA Networking reposted this
Supermicro is extremely excited to be the main system supplier to xAI in powering Colossus – the world’s largest AI supercomputer. The very dense, cutting-edge liquid-cooled Supermicro 4U GPU System is optimized to provide state-of-the-art performance, and the storage servers are designed to deliver the massive amounts of data that the next-gen AI chatbot Grok requires to provide accurate responses to a wide range of inquiries. xAI’s Colossus AI supercomputer achieves massive scale using the NVIDIA Spectrum-X Ethernet networking platform to connect 100,000 NVIDIA HGX H100 GPUs, allowing ultra-fast communications to achieve Grok’s interactive responses. Experience the future of AI with Supermicro’s innovative solutions at the heart of Colossus: https://hubs.la/Q02W0kll0 #Supermicro #LiquidCooling #RackScale #xAI #Colossus #AI #Supercomputer
-
NVIDIA Networking reposted this
The xAI Colossus supercomputer cluster in Memphis, the largest AI supercomputer in the world, powered by 100,000 NVIDIA Hopper GPUs, has reached unprecedented scale thanks to the NVIDIA Spectrum-X Ethernet networking platform. This milestone underscores NVIDIA's commitment to advancing #AI sustainability and efficiency. Read more: https://nvda.ws/48nrgQG
-
NVIDIA SHARP optimizes collective communications and boosts your AI workloads. Read our latest tech blog to discover the impact of in-network computing technology ➡️ https://nvda.ws/3A3fpLf
-
NVIDIA Networking reposted this
At last week's Open Compute Project Foundation Summit, Supermicro and NVIDIA discuss their collaboration and release of the new petascale JBOF all-flash storage system. This cutting-edge solution is designed for high performance AI training, inference and HPC workloads, utilizing NVIDIA BlueField®-3 DPUs. ➡️ Learn more about our storage solutions for AI: https://hubs.la/Q02VT4CQ0 #OCPSummit2024 #Supermicro #NVIDIA #AI #HPC
-
Announced today at the NVIDIA #AISummit: NVIDIA BlueField-3 DPUs enhance F5 BIG-IP Next for Kubernetes, allowing industries to adopt #AI while meeting the strict data governance needs of sovereign clouds. Read our blog to learn how NVIDIA and F5 are turbocharging AI efficiency ➡️ https://nvda.ws/3BXpNog
-
NVIDIA Networking reposted this
The rise of #AI has brought with it a surge in demand for #AI chipsets and enabling technologies. Companies are essentially building AI data centers—or AI factories—to train their large language models and provide the data processing power to offer AI services at the required scale and speed. Combining the reach of F5 application delivery and security services with the efficient data processing of NVIDIA gives customers superior visibility, control, and performance over their AI applications. Today, we’re excited to announce BIG-IP Next for Kubernetes deployed on NVIDIA BlueFIeld-3 DPUs, designed specifically for high-demand service providers, enterprises, and large-scale AI infrastructures. Key benefits of BIG-IP Next for Kubernetes deployed on NVIDIA BlueFIeld-3 DPUs include: - Enhanced control of AI deployments: Centralized integration with rich observability and support for multiple L7 protocols, ensuring high-performance ingress and egress control. - Reduced complexity in delivering AI services: Seamless integration with front-end networks, reducing latency and providing high-performance load balancing for massive AI models. - Protection for the evolving AI landscape: Automates security for AI endpoints, isolates applications from threats, and ensures strong encryption and data integrity. Read our latest blog to learn more: https://lnkd.in/gXife7bg
-
NVIDIA Networking reposted this
With our new collaboration with NVIDIA, deploy F5 BIG-IP Next for Kubernetes on NVIDIA BlueField-3 DPUs, improving data movement for AI factories and large-scale AI infrastructure. Achieve high-volume Kubernetes ingress speeds, performance, and throughput by offloading network and security functions to NVIDIA's BlueField-3 programmable Data Processing Unit (DPU). Read more here: https://go.f5.net/azvoadf6 #AI