<?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>PagedAttention on Hellokitty&#39;s Blog</title>
    <link>https://yangyang233333.github.io/tags/pagedattention/</link>
    <description>Recent content in PagedAttention on Hellokitty&#39;s Blog</description>
    <generator>Hugo</generator>
    <language>zh-CN</language>
    <lastBuildDate>Fri, 04 Sep 2026 21:00:00 +0800</lastBuildDate>
    <atom:link href="https://yangyang233333.github.io/tags/pagedattention/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>PagedAttention 与 RadixCache 原理：从分页 KV 管理到跨请求前缀复用</title>
      <link>https://yangyang233333.github.io/posts/pagedattention-radixcache-principles/</link>
      <pubDate>Fri, 04 Sep 2026 21:00:00 +0800</pubDate>
      <guid>https://yangyang233333.github.io/posts/pagedattention-radixcache-principles/</guid>
      <description>用操作系统虚拟内存和压缩前缀树两个类比，解释 PagedAttention 如何管理 KV 物理块、RadixCache 如何发现并复用公共前缀，并给出可运行的纯 Python 简化实现。</description>
    </item>
  </channel>
</rss>
