English(EN) PACE: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent States

新的PACE量化器大幅削减四位循环状态的内存占用

作者 PulseAugur 编辑部 · [2 个来源] · 2026-10-21 00:00

研究人员开发了PACE，一种用于线性注意力语言模型中四位循环状态的新型事后量化器。PACE降低了状态舍入的频率，并采用逐列量化尺度来最小化精度损失。这种方法在无需模型微调的情况下显著降低了内存使用量，使其能够与现有的八位方法竞争。 AI

影响能够更有效地利用大型语言模型的内存，可能允许在加速器上同时处理更多序列。

排序理由该集群描述了一种用于语言模型中循环状态量化器的新方法，该方法在研究论文中有详细介绍。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

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: Research; 该集群描述了一种用于语言模型中循环状态量化器的新方法，该方法在研究论文中有详细介绍。
Source corroboration: 2 independent sources; Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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: 5 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。

arXiv cs.CL TIER_1 English(EN) · Patrick Haller, Filipe Laitenberger, Alan Akbik · 2026-10-22 04:00

PACE: 四位循环状态的周期性和通道对齐编码

arXiv:2610.29545v1 Announce Type: new Abstract: Linear-attention language models keep their context in a recurrent state of fixed size, where an inference system stores one copy of this state for every sequence it decodes at the same time. Storing the state at lower precision the…
Hugging Face Daily Papers TIER_1 English(EN) · 2026-10-21 00:00

PACE: 四位循环状态的周期性和通道对齐编码

PACE is a post-hoc four-bit quantizer for linear-attention recurrent states that rounds less frequently and uses column-wise scales to reduce error, enabling lower memory usage without fine-tuning.