RRTO identifies static inference operator sequences from CUDA call logs alone and replays them on an edge GPU, cutting transparent-offloading communication to 11 RPCs per inference instead of thousands, with performance approaching non-transparent offloading.
Intra-dp: A high performance collabora- tive inference system for mobile edge computing,
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.NI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
RRTO: A High-Performance Transparent Offloading System for Model Inference in Mobile Edge Computing
RRTO identifies static inference operator sequences from CUDA call logs alone and replays them on an edge GPU, cutting transparent-offloading communication to 11 RPCs per inference instead of thousands, with performance approaching non-transparent offloading.