<?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>批处理 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E6%89%B9%E5%A4%84%E7%90%86/</link><description>Recent content in 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>Thu, 25 Jun 2026 12:00:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E6%89%B9%E5%A4%84%E7%90%86/index.xml" rel="self" type="application/rss+xml"/><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/</link><pubDate>Thu, 25 Jun 2026 12:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/continuous-batching/</guid><description>深度解析 vLLM 连续批处理（Continuous Batching）如何通过动态请求调度和 PagedAttention 实现高吞吐 LLM 推理服务。</description></item></channel></rss>