Adaptive Layer Placement for Pipeline-Parallel LLM Inference at the Edge
Authors
Giandomenico Lacatena
Year
2026
Venue
Master Thesis in Ingegneria Informatica, Politecnico di Torino
Created
May 22, 2026, 8:10 p.m.
(Cong Wang)
Modified
May 22, 2026, 8:10 p.m.
(Cong Wang)