← Back to the feed
Mobility & logisticsResearch findings

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

Original published 2026.07.13 23:05 KSTAdded to Blackdeck 2026.11.17 06:17 KST

What has changed?

Dynamically manages hot expert residency across memory tiers to balance compute and communication load.

Key points

  1. HCRMap is proposed to address hot expert skew in 3.5D MoE chiplet systems by dynamically managing expert residency.
  2. It selects expert replicas based on hotness, loading cost, and runtime pressure to reduce communication and memory bottlenecks.
  3. End-to-end latency is reduced by up to 46.7% over PIMoE and 43.6% over Hydra in prefill and decode stages.

Connect it to your work

Proposes HCRMap, a framework that dynamically maps hot expert replicas to mitigate imbalance in 3.5D MoE inference systems.

What remains unproven

This research note is based on an abstract; check the original for test conditions and application scope.

Originals used for this note

Links open the original publisher in a new tab.

  1. arxivHCRMap: Pressure-Aware Hot-Expert Residency Mapping for 3.5D MoE Chiplet Inference