DAOP accelerates Mixture-of-Experts inference by sequence-specific expert allocation between CPU and GPU plus one-layer-ahead predictive pre-calculation, achieving up to 1.35x over Fiddler and up to 8.20x over naive caching/prefetching baselines.
Adaptive mixtures of local experts,
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
unclear 1representative citing papers
citing papers explorer
-
DAOP: Data-Aware Offloading and Predictive Pre-Calculation for Efficient MoE Inference
DAOP accelerates Mixture-of-Experts inference by sequence-specific expert allocation between CPU and GPU plus one-layer-ahead predictive pre-calculation, achieving up to 1.35x over Fiddler and up to 8.20x over naive caching/prefetching baselines.