PulseAugur
中
实时 19:21:00
English(EN) The Token-Energy Law of LLM Decode: Active Bytes and Realized Time Account for Joules per Token

新的Token-能量定律量化LLM解码能耗

研究人员引入了Token-能量定律,这是一个量化大型语言模型(LLM)在解码过程中能耗的模型。该定律将每Token的能耗与“活跃字节”(逻辑字节需求)和“已实现解码时间”(每Token的经过时间)联系起来。该模型旨在提供一个可解释的框架,以理解模型架构、硬件和服务配置等因素如何影响能效。使用该定律在NVIDIA Hopper和Blackwell GPU上进行的实验证明了预测能耗的高准确性。 AI

影响 为优化LLM部署以提高能效提供了框架,可能降低运营成本和环境影响。

排序理由 学术论文,引入了LLM能效的新理论框架。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新的Token-能量定律量化LLM解码能耗

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
学术论文,引入了LLM能效的新理论框架。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
32 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Chenxu Niu, Batuhan Sencer, Wei Zhang, Yong Chen ·

    LLM解码的Token-能量定律:活跃字节和已实现时间决定每Token焦耳数

    arXiv:2610.28576v1 Announce Type: new Abstract: 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 o…