Akamai and NVIDIA launch edge AI inferencing platform

Akamai has launched the Akamai Inference Cloud, a platform for providing scalable and secure AI inferencing, in partnership with NVIDIA.

The solution enables agentic AI inference at the network edge, closer to users and devices. Edge processing is expected to be a requirement of next-generation agentic workloads, which require low-latency inference, local context and the ability to scale globally on demand.

The Akamai Inference Cloud utilises NVIDIA Blackwell AI infrastructure, including RTX Pro 6000 Blackwell Server Edition GPUs, BlueField-3 DPUs and NVIDIA AI Enterprise software, as well as Akamai’s distributed cloud computing infrastructure and global edge network.

Akamai CEO and co-founder Dr Tom Leighton said the next wave of AI will require the same proximity to users that allowed the internet to scale and grow so effectively.

“Akamai solved this challenge before, and we’re doing it again,” he said. “Powered by NVIDIA AI infrastructure, Akamai Inference Cloud will meet the intensifying demand to scale AI inference capacity and performance by putting AI’s decision-making in thousands of locations around the world, enabling faster, smarter and more secure responses.”

Extending enterprise AI factories to the edge will enable capabilities such as letting streaming inference and agents provide instant financial insights and perform real-time decision-making, which could have applications in detecting fraud, accelerating secure payments, and enabling high-speed decisions for industrial edges, Leighton said.

Physical AI systems such as industrial robots and smart city infrastructure would also be able to operate at beyond human-level responsiveness.

The companies are targeting deploying the solution in 20 initial locations worldwide, with plans for an expanded rollout underway.

Image credit: iStock.com/narvo vexar