<?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>TTFT on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/ttft/</link><description>Recent content in TTFT 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/ttft/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></channel></rss>