<?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>连续批处理 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E8%BF%9E%E7%BB%AD%E6%89%B9%E5%A4%84%E7%90%86/</link><description>Recent content in 连续批处理 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 06:30:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E8%BF%9E%E7%BB%AD%E6%89%B9%E5%A4%84%E7%90%86/index.xml" rel="self" type="application/rss+xml"/><item><title>大模型推理的连续批处理技术：吞吐量翻倍的工程艺术</title><link>https://guijiagi.com/posts/article-82/</link><pubDate>Mon, 13 Jul 2026 06:30:00 +0800</pubDate><guid>https://guijiagi.com/posts/article-82/</guid><description>深入解析Continuous Batching的原理、实现与工程优化，理解vLLM/TGI等推理框架的核心技术</description></item><item><title>连续批处理内部原理</title><link>https://guijiagi.com/posts/continuous-batching-internals/</link><pubDate>Thu, 02 Jul 2026 11:09:00 +0800</pubDate><guid>https://guijiagi.com/posts/continuous-batching-internals/</guid><description>解析vLLM连续批处理的内部机制，如何动态调度请求提升GPU利用率</description></item><item><title>连续批处理：vLLM 高吞吐推理的核心技术</title><link>https://guijiagi.com/posts/continuous-batching-vllm/</link><pubDate>Sun, 28 Jun 2026 11:08:00 +0800</pubDate><guid>https://guijiagi.com/posts/continuous-batching-vllm/</guid><description>深入解析连续批处理（Continuous Batching）的原理、vLLM实现细节与2026年高吞吐推理系统设计</description></item></channel></rss>