By Ken Briodagh, Senior Technology Editor | Embedded Computing Design

Unigen has leveraged its capabilities in hardware and software design, along with its vertically integrated manufacturing to deliver a complete Edge AI HW solution to the market. Through its partnerships with multiple hardware and software AI partners, Unigen offers a menu of choices to fit the needs of various end customers and markets.

Unigen’s Cupcake Edge AI Server delivers a reliable, high-performance, low-latency, low-power platform for Machine Learning and Inference AI in a compact and rugged enclosure. Cupcake integrates a flexible combination of I/O Interfaces and expansion capabilities to capture and process video and multiple types of signals through its Power-Over-Ethernet (POE) ports, and then delivers the processed data to the client either over a wired or wireless network. Neural Networks are supported from the leading ISV providers allowing for a highly customizable solution for multiple applications.

The compact Cupcake Edge AI server is powered by an Intel Elkhart Lake 4-core Atom Processor matched to AI modules from multiple leading companies building the latest cutting-edge AI processors. At launch, Unigen has announced partnerships with AI companies including Blaize, Hailo, Degirum and MemryX.

Cupcake is a small form factor fanless design in a ruggedized case perfect for environments where Visual Security is important (e.g., secure buildings, transportation, warehouses, or public spaces). External interfaces included are Ethernet, POE, HDMI, USB 3.0, USB Type-C, CANbus, RS232, SDCard, antennas for WIFI, and internal interfaces for optional M.2 SATA III, M.2 NVMe and SO-DIMMs. The flexibility in IO renders the Cupcake Edge AI Server suitable for multiple applications and markets.

“Our Cupcake Compact Edge AI Server is the first in a new line of products for Unigen,” said Paul Heng, President and CEO of Unigen. “By bringing Unigen’s world-class design and manufacturing capabilities to bear upon the world of Edge AI combined with software for a complete solution, we believe we can help our customers solve some of the largest issues that they are facing using modern low-latency Edge AI.”