<?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>StepFun on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/stepfun/</link><description>Recent content in StepFun on AI 实战派 · 从技术到赚钱</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, 15 Oct 2026 16:42:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/stepfun/index.xml" rel="self" type="application/rss+xml"/><item><title>Step 5 Preview 权重十月十五日开源：阶跃星辰跳代开放</title><link>https://guijiagi.com/posts/2026-10-15-18-step5-preview-weights-oct15-open/</link><pubDate>Thu, 15 Oct 2026 16:42:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-15-18-step5-preview-weights-oct15-open/</guid><description>SegmentFault 十月十五日更新：Step 5 Preview 模型权重当天开源，可自行部署，跳过 Step 4 直接对外发 Preview。</description></item><item><title>Step 3.7 Flash 的 MTP-3 提速：vLLM 和 SGLang 的开关为什么不一样？</title><link>https://guijiagi.com/posts/2026-10-15-06-step-37-flash-mtp3-serving-stack/</link><pubDate>Thu, 15 Oct 2026 15:30:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-15-06-step-37-flash-mtp3-serving-stack/</guid><description>StepFun Step 3.7 Flash 用 3 路多 token 预测把吞吐拉到 100 到 300 tok/s，但 vLLM 和 SGLang 的 speculative 配置口径不统一。</description></item></channel></rss>