<?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>Llama.cpp on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/llama.cpp/</link><description>Recent content in Llama.cpp 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>Thu, 25 Jun 2026 10:00:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/llama.cpp/index.xml" rel="self" type="application/rss+xml"/><item><title>llama.cpp 完全指南：CPU 也能跑大模型</title><link>https://guijiagi.com/posts/llama-cpp-guide/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/llama-cpp-guide/</guid><description>从 GGUF 格式到量化方案，从 CPU/GPU 混合推理到移动端部署，llama.cpp 完全实践指南。</description></item></channel></rss>