Deep learning AI enhanced by MIT-born Akamai and Neural Magic

  • Akamai Technologies and Neural Magic have formed a strategic partnership to enhance deep learning AI capabilities across Akamai’s distributed computing infrastructure.
  • Neural Magic’s software enables deep learning models to operate efficiently on CPU-based servers, complementing Akamai’s edge computing capabilities.
  • The collaboration aims to drive innovation in edge-AI inference, offering organizations lower latency, improved performance, and cost efficiencies for data-intensive AI applications.

Akamai Technologies, the cloud company that powers and protects life online, and Neural Magic, a software developer focusing on accelerating AI workloads, have unveiled a strategic partnership this week aimed at enhancing deep learning capabilities across Akamai’s distributed computing infrastructure. The collaboration will provide enterprises with a high-performing platform to efficiently run deep learning AI software on CPU-based servers.

Neural Magic’s solution enables deep learning models to operate on cost-effective CPU-based servers, rather than relying on expensive GPU resources. By leveraging automated model sparsification technologies, the software accelerates AI workloads, serving as a CPU inference engine. This complements Akamai’s ability to scale, protect, and deliver applications at the edge, enabling the deployment of capabilities across Akamai’s globally distributed computing infrastructure. The partnership will offer organizations lower latency and improved performance for data-intensive AI applications.

GPU vs CPU processing. Source: Cherry Servers

Furthermore, the collaboration is poised to drive innovation around edge-AI inference across various industries. The combined capabilities of Akamai and Neural Magic are particularly suitable for applications generating massive amounts of input data close to the edge, providing affordable processing power and security in proximity to data sources. Akamai recently announced its Generalized Edge Compute (Gecko) initiative, embedding cloud computing capabilities into its extensive edge network to support such applications and workloads.

John O’Hara, SVP of Engineering and COO at Neural Magic, emphasized the challenge of delivering AI models efficiently at the edge, highlighting the lack of specialized or expensive hardware as a barrier.

We intend to make AI smarter and faster. 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.

Ramanath Iyer, Chief Strategist at Akamai

Meanwhile, Ramanath Iyer, Chief Strategist at Akamai, expressed the intention to enhance AI’s efficiency and speed, offering organizations cost efficiencies and higher performance as they embrace AI applications.

Both Akamai and Neural Magic trace their roots back to the Massachusetts Institute of Technology (MIT), maintaining their corporate headquarters nearby.

The Akamai Qualified Computing Partner Program ensures the interoperability of solution-based services with Akamai’s cloud computing services, providing customers with easy access to services offered by Akamai technology partners. These services undergo a rigorous qualification process to ensure deployment and scalability across the globally distributed Akamai Connected Cloud.

Also read: Open Source in Asia: NetDEF’s Martin Winter on talent and challenges

About Akamai

Akamai, playing an important role in powering and protecting life online, offers a massively distributed edge and cloud platform to build, deliver, and secure digital experiences worldwide. The Akamai Connected Cloud brings apps and experiences closer to users while mitigating threats.

About Neural Magic

Neural Magic accelerates AI for enterprises, optimizing open-source models to run efficiently on commodity hardware. Founded by an MIT professor and an AI research scientist, the company facilitates cost-effective advancement of AI initiatives to production without compromising performance and accuracy.


Cassie Gong

Cassie is a news reporter at BTW media focusing on company profiles, interviews, podcasts, networking, sustainability, and AI. She graduated from Newcastle University, UK with a Master’s degree in Translating & Interpreting and now works in London and Hangzhou. Send tips to

Related Posts

Leave a Reply

Your email address will not be published. Required fields are marked *