Throughput ORchestration for Resource-Efficient Neural Transformers (TORRENT)
Description
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 inference, to increase throughput, energy and operational efficiency of data centres.
Key data
Projectlead
Deputy Projectlead
Project team
Project partners
Klepsydra Technologies AG
Project status
ongoing, started 10/2026
Institute/Centre
Centre for Artificial Intelligence (CAI); Institute for Data Science (IDS)
Funding partner
Innosuisse Innovationsscheck
Project budget
15'000 CHF
School of Engineering
Technikumstrasse 71
8400 Winterthur