arXiv CS
open access
Who Should Own the Expert Cache? Kernel-Managed Tiering for Trillion-Parameter MoE Inference
Mixture-of-experts models whose expert pools exceed DRAM capacity require a weight-residency tier. Existing systems manage it in user space with expert-granular placement, frequency-based admission, and explicit pinning. We evaluate whether the operating system page cache can instead serve as the ex
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
- Who Should Own the Expert Cache? Kernel-Managed Tiering for Trillion-Parameter MoE Inference#793848
- Who Should Own the Expert Cache? Kernel-Managed Tiering for Trillion-Parameter MoE Inference#448009
- ExaGEMM: Exploration Framework for CPU-Driven ML Inference via Associative In-Register Computing for Low-Bit GEMM#373477
- SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving#1119190
- SeqMoE: Toward Full-Load Performance via Predictive and Graph-Compatible MoE Offloading#1070420
Record · ID 1043174
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