Prism optimizes expert placement and uses runtime migration for distributed MoE inference on heterogeneous edge GPUs, achieving up to 30.6% lower latency than baselines.
Sida: Sparsity-inspired data-aware serving for efficient and scalable large mixture-of-experts models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement
Prism optimizes expert placement and uses runtime migration for distributed MoE inference on heterogeneous edge GPUs, achieving up to 30.6% lower latency than baselines.