<?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>延迟优化 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E5%BB%B6%E8%BF%9F%E4%BC%98%E5%8C%96/</link><description>Recent content in 延迟优化 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, 02 Jul 2026 11:35:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%BB%B6%E8%BF%9F%E4%BC%98%E5%8C%96/index.xml" rel="self" type="application/rss+xml"/><item><title>LLM服务延迟优化</title><link>https://guijiagi.com/posts/latency-optimization-llm-serving/</link><pubDate>Thu, 02 Jul 2026 11:35:00 +0800</pubDate><guid>https://guijiagi.com/posts/latency-optimization-llm-serving/</guid><description>从首Token延迟到生成速度，LLM服务延迟优化的完整技术栈</description></item><item><title>Speculative Decoding实战：推理速度提升3倍</title><link>https://guijiagi.com/posts/speculative-decoding-practice/</link><pubDate>Tue, 30 Jun 2026 11:45:00 +0800</pubDate><guid>https://guijiagi.com/posts/speculative-decoding-practice/</guid><description>深入实践Speculative Decoding技术，实现大模型推理速度3倍提升</description></item></channel></rss>