<?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>成本控制 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E6%88%90%E6%9C%AC%E6%8E%A7%E5%88%B6/</link><description>Recent content in 成本控制 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>Sun, 12 Jul 2026 19:20:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E6%88%90%E6%9C%AC%E6%8E%A7%E5%88%B6/index.xml" rel="self" type="application/rss+xml"/><item><title>大模型推理成本优化：从理论到实践</title><link>https://guijiagi.com/posts/article-15/</link><pubDate>Sun, 12 Jul 2026 19:20:00 +0800</pubDate><guid>https://guijiagi.com/posts/article-15/</guid><description>系统性地介绍大模型推理成本优化的各种技术手段，从量化压缩到请求调度的全栈优化方案</description></item><item><title>大模型推理成本优化：从理论到实践</title><link>https://guijiagi.com/posts/b2-5902a9c6/</link><pubDate>Sun, 12 Jul 2026 19:20:00 +0800</pubDate><guid>https://guijiagi.com/posts/b2-5902a9c6/</guid><description>系统性地介绍大模型推理成本优化的各种技术手段，从量化压缩到请求调度的全栈优化方案</description></item><item><title>Agent缓存架构设计：让智能体又快又省的秘密武器</title><link>https://guijiagi.com/posts/agent-cache-architecture/</link><pubDate>Thu, 02 Jul 2026 10:12:00 +0800</pubDate><guid>https://guijiagi.com/posts/agent-cache-architecture/</guid><description>深入探讨Agent系统中的多层缓存设计、缓存策略与一致性保障机制</description></item></channel></rss>