Adding priority weights to the multi-source model-distributed inference objective and scheduling each layer-group by a greedy delay-to-priority ratio shortens average inference time for high-priority sources on edge testbeds.
Improving ml applications in shared computing environ- ments,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.DC 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Priority-Aware Model-Distributed Inference at Edge Networks
Adding priority weights to the multi-source model-distributed inference objective and scheduling each layer-group by a greedy delay-to-priority ratio shortens average inference time for high-priority sources on edge testbeds.