<?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>自回归 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E8%87%AA%E5%9B%9E%E5%BD%92/</link><description>Recent content in 自回归 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>Tue, 30 Jun 2026 09:20:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E8%87%AA%E5%9B%9E%E5%BD%92/index.xml" rel="self" type="application/rss+xml"/><item><title>多Token预测：大模型推理加速的新范式</title><link>https://guijiagi.com/posts/multi-token-prediction/</link><pubDate>Tue, 30 Jun 2026 09:20:00 +0800</pubDate><guid>https://guijiagi.com/posts/multi-token-prediction/</guid><description>深入介绍多Token预测（MTP/Multi-Token Prediction）技术，如何通过将每次生成多个token来加速大模型推理</description></item></channel></rss>