arXiv (All)
open access
Efficient Expert-Parallel Communication on PCIe-Connected Consumer GPUs
Expert parallelism (EP) enables inference of large Mixture-of-Experts (MoE) models by placing their experts across multiple GPUs, but requires substantial communication between GPUs at every MoE layer. As contemporary MoE models activate more experts per token, this communication accounts for a grow
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
- Efficient Expert-Parallel Communication on PCIe-Connected Consumer GPUs#1136838
- Training-Free Halving of Activated Experts in Fine-Grained Mixture-of-Experts Models#927851
- Improving machine learning models through enrichment of training data#247969
- SeqMoE: Toward Full-Load Performance via Predictive and Graph-Compatible MoE Offloading#1070420
- SeqMoE: Toward Full-Load Performance via Predictive and Graph-Compatible MoE Offloading#919504
Record · ID 1154362
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