Chenxu Niu, Batuhan Sencer, Wei Zhang, Yong Chen · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28576 · open-access PDF
大型语言模型的节能部署需要了解模型架构、硬件和服务设置如何塑造每种生成的代币的能量。我们引入了代币能量法,这是一种可解释的 GPU 板能量每种输出代币的紧凑型模型,用于密集的完整历史解码。它将代币能量与两个核心维度有关:活跃字节和实现解码时间。活跃字节描述每种输出的逻辑字节需求,将解码迭代中共享的密集重量从私钥 - 值 (KV) 历史读取和更新到每个请求。
Machine translation (Meta M2M100); the English original follows.
Energy-efficient deployment of large language models requires understanding how model architecture, hardware, and serving settings shape energy per generated token. We introduce the Token-Energy Law, a compact, interpretable model of GPU-board energy per output token for dense, full-history decoding. It relates token energy to two core dimensions: active bytes and realized decode time. Active bytes describe logical byte demand per output, separating dense weights shared within a decode iteration from private key--value (KV) histories read and updated for each request. Realized decode time is t
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28576, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange