<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Linear Attention on Cognaptus</title>
    <link>https://cognaptus.com/tags/linear-attention/</link>
    <description>Recent content in Linear Attention on Cognaptus</description>
    <generator>Hugo -- 0.145.0</generator>
    <language>en-us</language>
    <lastBuildDate>Sat, 06 Jun 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://cognaptus.com/tags/linear-attention/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>State of Delay: KVBuffer and the Memory Tax of Linear Attention</title>
      <link>https://cognaptus.com/blog/2026-06-06-state-of-delay-kvbuffer-and-the-memory-tax-of-linear-attention/</link>
      <pubDate>Sat, 06 Jun 2026 00:00:00 +0000</pubDate>
      <guid>https://cognaptus.com/blog/2026-06-06-state-of-delay-kvbuffer-and-the-memory-tax-of-linear-attention/</guid>
      <description>A mechanism-first reading of KVBuffer, showing why constant-time linear attention still needs IO-aware serving design before it becomes operationally cheap.</description>
    </item>
  </channel>
</rss>
