<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Systems &amp; Hardware on Américo Dias</title><link>https://americo.dias.pt/categories/systems--hardware/</link><description>Recent content in Systems &amp; Hardware on Américo Dias</description><generator>Hugo</generator><language>en</language><lastBuildDate>Wed, 21 Oct 2026 14:17:11 +0000</lastBuildDate><atom:link href="https://americo.dias.pt/categories/systems--hardware/index.xml" rel="self" type="application/rss+xml"/><item><title>GPU in a 180 W Box: Upgrading an HPE MicroServer Gen10 Plus for AI Workloads</title><link>https://americo.dias.pt/posts/hpe-microserver-gpu-cpu-upgrade/</link><pubDate>Sat, 16 May 2026 22:00:00 +0100</pubDate><guid>https://americo.dias.pt/posts/hpe-microserver-gpu-cpu-upgrade/</guid><description>&lt;p&gt;A GPU card and a CPU swap turned a compact, quiet homelab server into an AI
inference machine, without replacing the hardware or exceeding its 180 W power
supply. Indexing 15,000 photos dropped from roughly an hour to under ten minutes.
Embedding a 400-page book dropped from three minutes to twenty seconds. The catch:
fitting a GPU and a faster CPU inside a 180 W power budget requires software
enforcement, not just careful hardware selection.&lt;/p&gt;</description></item></channel></rss>