AI-centric Server on Chip for increasing complexity and scale of AI inference applications, enabling the scale of real-life AI applications.

ended

AI holds immense promise across a wide range of applications, however, putting AI to work at scale remains a challenge. The main problem with implementing scalable AI deployment is that the current AI inference architecture is unsuitable for performing hyperscale computations due to complexity of deployment and total cost of ownership. New AI computing architecture is needed to enable the deployment of AI applications to realize its complete potential. NeuReality has developed NR1, an innovative Server-on-a-Chip solution in an AI Centric architecture and NR1 SDK, to facilitate the deployment of AI at scale. The unique architecture allows AI-optimized, simplified and democratized infrastructure with cost, power and performance optimization of access to AI computing resources, thereby enabling the deployment of AI inference. During the EIC project, NeuReality will finalise the development of NR1 and validate the optimized chip in operational settings for further commercialisation.