From Cloud to Crowd: Democratizing LLM Service with Decentralized Edge Collaboration for RAG
- 类型:arxiv
- 标识:2608.00922
- 链接:http://arxiv.org/abs/2608.00922v1
- 主分类:rag
- 形态:application
- 被引:0
- 被引来源:Semantic Scholar + OpenAlex
- S2被引:0
- OpenAlex被引:0
- 影响力被引:0
- TLDR:Results show that DEFRAG narrows the SLM-LLM accuracy gap, while reducing cost by up to 98.4% and increasing peak throughput by up to 97.8% over centralized services, demonstrating the potential of DEFRAG for democratized LLM services at the edge.
- OpenAlex ID:W7172391923
- OpenAlex DOI:10.48550/arxiv.2608.00922
- DOI:10.48550/arxiv.2608.00922
- DOI来源:OpenAlex
- 开放获取:green
- 开放获取链接:https://doi.org/10.48550/arxiv.2608.00922
- OpenAlex更新:2026-08-26
- 待LLM分类:否
- 标题中文:从云到群:通过去中心化边缘协作实现 LLM 服务民主化以支持 RAG
- TLDR中文:结果表明DEFRAG缩小了SLM与LLM之间的准确度差距,同时相比集中式服务成本降低最高达98.4%,峰值吞吐提升最高达97.8%,展现其在边缘实现民主化LLM服务的潜力。
- 来源文件:
- /inbox/tom/_candidates/2026-08-04-rag-retrieval-reranking-candidates.json
- [S2 enrich]
- [OpenAlex backfill]