Cloud company Akamai Technologies announced a strategic partnership with Neural Magic, a software developer focused on accelerating AI, to supercharge deep learning capabilities on Akamai’s distributed computing infrastructure. The combined solution gives enterprises a high-performance platform to run deep-learning AI software on CPU-based servers.
As an Akamai qualified computing partner, Neural Magic’s software will be made available alongside the products and services that power its distributed platform for cloud computing, security and content delivery.
Specifically, Neural Magic’s solution enables deep-learning models to run on cost-efficient CPU-based servers, rather than on expensive GPU resources. The software accelerates AI workloads using automated model sparsification technology, available as a CPU inference engine and complementing Akamai’s ability to scale, protect and deliver applications at the edge. This allows the companies to deploy the capabilities across Akamai’s globally distributed computing infrastructure, offering organizations lower latency and improved performance for data-intensive AI applications.
The partnership can also help foster innovation around edge-AI inference across a host of industries. The combined capabilities of Akamai and Neural Magic are suited for applications in which massive amounts of input data are generated close to the edge, placing affordable processing power and security closer to the data sources.
Akamai recently announced a new generalized edge compute (Gecko) initiative to embed cloud computing capabilities into its massive edge network to support applications and workloads among many others.
“Delivering AI models efficiently at the edge is a bigger challenge than most people realize,” said John O’Hara, SVP of engineering and COO, 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.”
“We intend to make AI smarter and faster,” said Ramanath Iyer, Akamai chief strategist. “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.”
Akamai and Neural Magic share a common origin, both having been born out of Massachusetts Institute of Technology (MIT), and continue to maintain their respective corporate headquarters nearby.
The Akamai qualified computing partner program is designed to make solution-based services that are interoperable with Akamai’s cloud computing services easily accessible to Akamai customers. The services are provided by Akamai technology partners that complete a rigorous qualification process to ensure they are readily available to deploy and scale across the globally distributed Akamai Connected Cloud.