A framework that skips unimportant layers and exits early during edge MoE inference to cut latency and cross-server traffic, with quality kept within a budget.
A r e v i e w o n edge large language models: Design, execution, and applications,
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
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
TrimMoE A communication aware and adaptive depth framework for distributed edge inference
A framework that skips unimportant layers and exits early during edge MoE inference to cut latency and cross-server traffic, with quality kept within a budget.