FIELD NOTES TOPIC
hot expert residency mapping
1 note, newest first.
HCRMap: Pressure-Aware Hot-Expert Residency Mapping for 3.5D MoE Chiplet Inference
The paper proposes HCRMap, a framework for managing hot expert replicas in 3.5D Mixture-of-Experts (MoE) inference systems. The aim is to dynamically place and reuse hot experts across different memory tiers to…
