Verizon, Nvidia To Power AI Workloads On 5G Private Networks With Mobile Edge Compute
The AI-powered private 5G platform stack will handle compute-intensive apps such as generative AI large language models, video streaming and IoT.
Verizon has announced a new solution developed with Nvidia that enables artificial intelligence applications to run over Verizon’s 5G private network with private mobile edge compute.
Verizon’s 5G Private Network with Enterprise AI solution brings together the company’s low-latency 5G private network and private MEC with Nvidia AI Enterprise software platform and Nvidia NIM microservices to deliver real-time AI services on premises for enterprise customers.
The AI-powered private 5G platform stack will enable third-party developers to innovate, while supporting developments in AI computing and AI and connectivity applications. It can support multi-tenancy for multiple use cases or customers, is modular, and can provide services remotely via portable private network solutions or on a customer’s premise with a permanent private network on site.
The stack is being built to handle compute-intensive apps including generative AI large language models and vision language models, video streaming, broadcast management, computer vision, augmented/virtual/extended reality, autonomous mobile robot/automated guided vehicle, and internet of things.
“We're leveraging our network's unique strengths including private networks and Verizon’s global industry leadership in private MEC, combined with Nvidia’s AI compute capabilities to enable real-time AI applications that require security, ultra-low latency, and high bandwidth,” said Srini Kalapala, senior vice president of technology and product development at Verizon.
According to Verizon, the solution will provide ultra-low latency required for real-time AI processing at the edge. The high bandwidth and reliability of a private 5G network improves performance for data-intensive AI workloads. Private 5G networks further offer improved security and control over data and applications.
The solution can be tailored to meet specific needs of different industries and use cases. Additionally, Verizon private network customers can run their AI application workloads and services at the premise edge with MEC. This can help prevent compute-intensive applications from traversing the internet, expediting decision making with local processing and inferencing.
“Verizon’s integration of Nvidia’s full stack AI platform into its new solution for running AI workloads on private 5G networks is a big step forward in helping enterprises of all sizes reach their business objectives faster with AI,” said Ronnie Vasishta, senior vice president of telecom at Nvidia.
