<?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>Speculative Decoding on Richelieu's Blog</title><link>https://beaiera.top/tags/speculative-decoding/</link><description>Recent content in Speculative Decoding on Richelieu's Blog</description><generator>Hugo</generator><language>zh-cn</language><lastBuildDate>Wed, 17 Jun 2026 00:00:00 +0800</lastBuildDate><atom:link href="https://beaiera.top/tags/speculative-decoding/index.xml" rel="self" type="application/rss+xml"/><item><title>vLLM 投机采样（Speculative Decoding）深度解析</title><link>https://beaiera.top/posts/vllm-speculative-decoding/</link><pubDate>Wed, 17 Jun 2026 00:00:00 +0800</pubDate><guid>https://beaiera.top/posts/vllm-speculative-decoding/</guid><description>&lt;p&gt;通过阅读 vLLM 源码和业界最新资料，系统梳理投机采样的原理、方法对比和在 vLLM 中的实现。&lt;/p&gt;</description></item></channel></rss>