PulseAugur
中
实时 10:55:45
English(EN) ATEST: Adaptive Resource-Aware Test-Time Scaling for LLM Inference

新的ATEST框架通过适应GPU负载和能源成本来优化大语言模型推理

作者 PulseAugur 编辑部 · [1 个来源] ·

研究人员开发了ATEST，一个用于大语言模型推理的自适应资源感知测试时推理的新框架。该系统通过根据查询难度和实时GPU条件（包括能源成本）动态调整推理工作量，解决了传统方法中固定采样预算的问题。ATEST-Online模式无需离线校准，可逐步生成样本，监控GPU负载，并学习能源成本以确定何时停止，在不同负载下展示了准确性和能源效率的显著提升。 AI

影响 通过动态适应实时资源约束和能源成本来优化大语言模型推理效率。

排序理由 该项目是一篇研究论文，详细介绍了一个用于大语言模型推理的新框架。[lever_c_demoted from research: ic=1 ai=1.0]

在 Hugging Face Daily Papers 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ATEST框架通过适应GPU负载和能源成本来优化大语言模型推理

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
该项目是一篇研究论文，详细介绍了一个用于大语言模型推理的新框架。[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
7 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. Hugging Face Daily Papers TIER_1 English(EN) ·

    ATEST：LLM推理的自适应资源感知测试时扩展

    Test-time scaling (TTS) improves large language model (LLM) reasoning by sampling multiple answers, but fixed sampling budgets ignore both query difficulty and the changing energy cost of inference under GPU contention. We measure up to a 4.1-fold increase in energy for the same …

相关实体

相关话题