HCRMap: Pressure-Aware Hot-Expert Residency Mapping for 3.5D MoE Chiplet Inference

The paper introduces HCRMap, a mapping framework designed to mitigate compute and communication imbalances caused by uneven expert activation in Mixture-of-Experts models on multi-chiplet systems.

Firefly links to the original publisher. The summary above is AI-generated for orientation and may differ from the source. The “current rank score” decays over time so newer significant stories surface first.