<?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>DSpark on zo0043</title><link>http://blog.zero43.top/tags/dspark/</link><description>Recent content in DSpark on zo0043</description><image><title>zo0043</title><url>https://i.postimg.cc/7hwBy7VS/calcr.png</url><link>https://i.postimg.cc/7hwBy7VS/calcr.png</link></image><generator>Hugo -- 0.130.0</generator><language>zh</language><copyright>©2024 zo0043</copyright><lastBuildDate>Wed, 30 Sep 2026 16:54:00 +0800</lastBuildDate><atom:link href="http://blog.zero43.top/tags/dspark/index.xml" rel="self" type="application/rss+xml"/><item><title>DeepSeek 论文课（十五）：让模型说话更快：投机解码与 DSpark</title><link>http://blog.zero43.top/posts/deepseek-paper-course-15-dspark/</link><pubDate>Wed, 30 Sep 2026 16:54:00 +0800</pubDate><guid>http://blog.zero43.top/posts/deepseek-paper-course-15-dspark/</guid><description>让模型说话更快：投机解码与 DSpark 先给结论： 模型回答时是一个词一个词往外吐的，每个词都要走一遍完整的大模型计算——这是推理慢的根本原因。DSpar</description></item></channel></rss>