arXiv (All)
open access
ISER-MoE: Dynamic In-Switch Replication of Hot Experts for Load Balancing in Expert-Parallel
Expert-parallel mixture-of-experts (MoE) layers run at the pace of the most loaded GPU, and a few hot experts carry most of the excess load. Replicating them at every MoE layer balances the load only if their weights arrive within the layer, and broadcasting from the owner is the bottleneck: point-t
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- ISER-MoE: Dynamic In-Switch Replication of Hot Experts for Load Balancing in Expert-Parallel#1598837
- SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving#1119190
- RankLane: Efficient MoE Prefill on Accelerators with Ranked Expert Capacities#1536251
- Memory-Efficient Expert Routing for Distributed MoE Training#1216708
- Memory-Efficient Expert Routing for Distributed MoE Training#1210249
Record · ID 1625171
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive