Early-Signal Detector

method · first seen 11 Oct 2026

paged attention

Also: PagedAttention, vLLM paged attention

A KV-cache memory management technique that stores attention keys and values in fixed-size blocks.

Mentions per week

0219 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Rank 152 on 9 Nov 2026 · 6 mentions in 28 days · 6 independent groups · papers → code · first seen 4 weeks ago · acceleration +0.10

Earliest sources

Latest sources

Mentioned together with

LLM serving systemsstate space modelsvLLMprefill phaseKV cache reusecontinuous batchingKV cache compressionattention matchingmixture of expertsKV cache memory safety