Akamai (News - Alert) Technologies and Neural Magic announced a partnership to enhance deep learning capabilities on Akamai's distributed computing infrastructure. This collaboration allows enterprises to run deep learning AI software on CPU-based servers efficiently and have a high-performing platform for data-intensive applications.

Neural Magic's software accelerates AI workloads using automated model sparsification technologies, This means deep learning models can run on cost-efficient CPU-based servers rather than expensive GPU resources.

"Delivering AI models efficiently at the edge is a bigger challenge than most people realize," said John O'Hara, SVP of Engineering and COO at Neural Magic. "Specialized or expensive hardware and associated power and delivery requirements are not always available or feasible, leaving organizations to effectively miss out on leveraging the benefits of running AI inference at the edge."

As an Akamai Qualified Computing Partner, Neural Magic's software will be integrated with Akamai's offerings, providing organizations with lower latency and improved performance for AI applications.

The partnership also holds the potential to drive innovation in edge-AI inference across various industries thanks to Akamai's global distributed computing infrastructure. It’s also a terrific option for applications generating massive amounts of data close to the edge, where affordable processing power and security are critical.

"We intend to make AI smarter and faster," said Ramanath Iyer, Chief Strategist at Akamai. "Scaling Neural Magic's unique capabilities to run deep learning inference models across Akamai gives organizations access to much-needed cost efficiencies and higher performance as they move swiftly to adopt AI applications."