<?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>WideEP on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/wideep/</link><description>Recent content in WideEP 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, 08 Oct 2026 16:06:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/wideep/index.xml" rel="self" type="application/rss+xml"/><item><title>MoE 推理的隐形瓶颈：专家加载与 WideEP 为什么要把专家摊到更多卡上</title><link>https://guijiagi.com/posts/2026-10-08-12-moe-wideep-expert-parallel/</link><pubDate>Thu, 08 Oct 2026 16:06:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-08-12-moe-wideep-expert-parallel/</guid><description>MoE 模型 decode 阶段被专家权重加载时间卡住。NVIDIA 的 WideEP 把专家跨 NVL72 节点分片，是 2026 年 MoE 部署的关键工程。</description></item></channel></rss>