<?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>Inductor on Richelieu's Blog</title><link>https://beaiera.top/tags/inductor/</link><description>Recent content in Inductor on Richelieu's Blog</description><generator>Hugo</generator><language>zh-cn</language><lastBuildDate>Tue, 02 Jun 2026 00:00:00 +0800</lastBuildDate><atom:link href="https://beaiera.top/tags/inductor/index.xml" rel="self" type="application/rss+xml"/><item><title>vLLM 编译系统完全解析</title><link>https://beaiera.top/posts/2026-06-02-vllm-compilation-system/</link><pubDate>Tue, 02 Jun 2026 00:00:00 +0800</pubDate><guid>https://beaiera.top/posts/2026-06-02-vllm-compilation-system/</guid><description>&lt;p&gt;vLLM 的编译系统在标准 PyTorch &lt;code&gt;torch.compile&lt;/code&gt; 之上做了大量定制：分段编译（Piecewise Compilation）、字节码 Hook、AOT 缓存、动态形状管 理等。本文从多个实际调试问题出发，系统梳理 vLLM 编译系统的核心机制。&lt;/p&gt;</description></item></channel></rss>