Akamai launches edge AI inference platform with NVIDIA technology

Akamai Technologies Inc. (NASDAQ: AKAM) launched Akamai Inference Cloud, a platform designed to process artificial intelligence inference at the edge of the internet rather than in centralized data centers.

The platform combines NVIDIA RTX PRO Servers with RTX PRO 6000 Blackwell Server Edition GPUs, NVIDIA BlueField-3 data processing units, and NVIDIA AI Enterprise software. The system operates across Akamai's global network of over 4,200 locations worldwide.

"The next wave of AI requires the same proximity to users that allowed the internet to scale to become the pervasive global platform that it is today," said Tom Leighton, Akamai CEO and co-founder. "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."

Jensen Huang, founder and CEO of NVIDIA, stated: "Inference has become the most compute-intensive phase of AI — demanding real-time reasoning at planetary scale. Together, NVIDIA and Akamai are moving inference closer to users everywhere, delivering faster, more scalable generative AI."

The platform targets applications including enterprise AI systems, real-time financial decisioning, autonomous vehicles, industrial robots, and smart city infrastructure. The system routes routine inference tasks to edge locations through NVIDIA's NIM microservices while directing complex reasoning to centralized AI facilities.

Akamai Inference Cloud is available in 20 initial locations globally, with plans for expanded deployment. The company plans to incorporate NVIDIA's upcoming BlueField-4 DPU technology to further enhance data access and AI inference processing capabilities.

You May Also Be Interested In