PulseAugur
实时 09:32:21

新的POLCA系统优化LLM服务的能效和延迟

研究人员开发了一种名为POLCA的新型功率控制系统,用于分离式LLM服务,旨在优化能效和延迟。与英伟达的Max-Q等现有方法不同,后者只能带来适度的收益并可能增加延迟,POLCA采用了一种相位解耦和模型校准的方法。该系统允许预填充和解码通道以独立的功率设置运行,从而在每焦耳的令牌数方面取得显著改进,并减少端到端延迟,尤其对于专家混合(MoE)模型而言。 AI

影响 优化LLM服务基础设施,可能降低大型模型运营成本并改善响应时间。

排序理由 该集群包含一篇详细介绍LLM服务新技术的学术论文。[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POLCA系统优化LLM服务的能效和延迟

本文如何被排名

Signal score
13 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇详细介绍LLM服务新技术的学术论文。[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
infra, paper
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
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

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) · Jae Gon Kim, Donghoon Yoo, Hanyul Ryu, Sungho Ha, Juyeon Lee, Soojung Ryu ·

    解耦相位、模型校准的分布式大模型服务功率控制

    arXiv:2609.11133v1 Announce Type: new Abstract: Datacenter GPU power is the binding constraint on LLM serving capacity, and production serving has shifted to prefill/decode (PD) disaggregation. Deploying NVIDIA's Max-Q inference profile on a disaggregated B200 system, we found it…