TORRENT - Throughput ORchestration for Resource-Efficient Neural Transformers

Research unit

INNOSUISSE

Project number

138.404 INNO-ICT

Project title

TORRENT - Throughput ORchestration for Resource-Efficient Neural Transformers

Texts for this project

	German	French	Italian	English
Key words	-	-	-
Abstract	-	-	-

Category	Text
Key words (English)	ICT, Artificial/local/extended/networked intelligence
Abstract (English)	Klepsydra provides a highly efficient AI inference engine for edge AI based on a lock-free and asynchronous programming approach. This feasibility study investigates whether it can be further developed for server-based AI, to increase throughput, energy and operational efficiency of data centres.