Improving inference time in multi-TPU systems with profiled model segmentation
Konferenzberichte:
Proceedings - 2023 31st Euromicro International Conference on Parallel, Distributed and Network-Based Processing, PDP 2023
ISBN: 9798350337631
Datum der Publikation: 2023
Seiten: 84-91
Art: Konferenz-Beitrag