<?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>Prefix Cache on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/prefix-cache/</link><description>Recent content in Prefix Cache on 硅基 AGI · 智能体学习与测评</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Mon, 13 Jul 2026 07:20:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/prefix-cache/index.xml" rel="self" type="application/rss+xml"/><item><title>大模型推理的Prefix Cache优化：让首token延迟减半</title><link>https://guijiagi.com/posts/article-87/</link><pubDate>Mon, 13 Jul 2026 07:20:00 +0800</pubDate><guid>https://guijiagi.com/posts/article-87/</guid><description>深入解析Prefix Cache的原理、实现与工程优化，大幅降低大模型推理的首token延迟</description></item></channel></rss>