arXiv (OAI Expanded)
open access
Dynamic HBM Repartitioning for Multi-Turn MoE Serving
Long-running multi-turn requests accumulate reusable key-value (KV) state. Once this state exceeds a fixed GPU KV-cache allocation, serving systems evict reusable prefixes, repeat prefill work, and may preempt requests. This pressure is particularly acute for Mixture-of-Experts (MoE) models: their e
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
- SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving#1119190
- BASE: Batch-Aware Selection of Experts Using Predicted Removal Error for Efficient MoE Decoding#1131064
- Trillion-Parameter MoE in a Box: Decoupling Memory Provisioning with High-Bandwidth Flash#1109618
- MoEless: Efficient MoE LLM Serving with Serverless Experts#1142637
- Joint Effects of GPU Server Topology, Parallelism, and Congestion Control on MoE Inference: A Controlled Simulation Study#1142136
Record · ID 1071318
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