<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI推理芯片 on 没用知识库</title><link>https://blog.alansun.host/tags/ai%E6%8E%A8%E7%90%86%E8%8A%AF%E7%89%87/</link><description>Recent content in AI推理芯片 on 没用知识库</description><generator>Hugo -- gohugo.io</generator><language>zh-cn</language><managingEditor>alansundy@gmail.com (羊羊羊)</managingEditor><webMaster>alansundy@gmail.com (羊羊羊)</webMaster><copyright>© 2026 羊羊羊</copyright><lastBuildDate>Wed, 01 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.alansun.host/tags/ai%E6%8E%A8%E7%90%86%E8%8A%AF%E7%89%87/index.xml" rel="self" type="application/rss+xml"/><item><title>AI 推理芯片架构图谱：三类瓶颈与十二家初创公司路线对比</title><link>https://blog.alansun.host/posts/20260701_%E6%8E%A8%E7%90%86%E8%8A%AF%E7%89%87%E6%9E%B6%E6%9E%84%E5%9B%BE%E8%B0%B1_%E4%B8%89%E7%B1%BB%E7%93%B6%E9%A2%88%E4%B8%8E%E5%8D%81%E4%BA%8C%E5%AE%B6%E5%85%AC%E5%8F%B8/</link><pubDate>Wed, 01 Jul 2026 00:00:00 +0000</pubDate><author>alansundy@gmail.com (羊羊羊)</author><guid>https://blog.alansun.host/posts/20260701_%E6%8E%A8%E7%90%86%E8%8A%AF%E7%89%87%E6%9E%B6%E6%9E%84%E5%9B%BE%E8%B0%B1_%E4%B8%89%E7%B1%BB%E7%93%B6%E9%A2%88%E4%B8%8E%E5%8D%81%E4%BA%8C%E5%AE%B6%E5%85%AC%E5%8F%B8/</guid><description>围绕存储带宽、计算灵活性与部署功耗三大核心约束，横评 Groq、Cerebras、Tenstorrent、SambaNova、Etched 等 12 家 AI 推理芯片公司的四大存储架构路线与生存空间。</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://blog.alansun.host/posts/20260701_%E6%8E%A8%E7%90%86%E8%8A%AF%E7%89%87%E6%9E%B6%E6%9E%84%E5%9B%BE%E8%B0%B1_%E4%B8%89%E7%B1%BB%E7%93%B6%E9%A2%88%E4%B8%8E%E5%8D%81%E4%BA%8C%E5%AE%B6%E5%85%AC%E5%8F%B8/featured.jpg"/></item></channel></rss>