<?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>HBM4E on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/hbm4e/</link><description>Recent content in HBM4E 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>Wed, 07 Oct 2026 10:00:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/hbm4e/index.xml" rel="self" type="application/rss+xml"/><item><title>韩国FuriosaAI发布第三代推理加速器：2nm工艺+32倍性能跃升，挑战英伟达</title><link>https://guijiagi.com/posts/2026-10-07-furiosaai-third-gen-inference-accelerator/</link><pubDate>Wed, 07 Oct 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-07-furiosaai-third-gen-inference-accelerator/</guid><description>韩国AI芯片公司FuriosaAI与博通合作推出第三代推理加速器：2nm计算die、12个HBM4E堆栈、PCIe Gen7，计算与内存带宽提升32倍。</description></item></channel></rss>