<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Series on /sys/admin/blog</title><link>https://kre80r.com/series/</link><description>Recent content in Series on /sys/admin/blog</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 10 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://kre80r.com/series/feed.xml" rel="self" type="application/rss+xml"/><item><title>Bring your own GPU</title><link>https://kre80r.com/series/bring-your-own-gpu/</link><pubDate>Sat, 10 Oct 2026 00:00:00 +0000</pubDate><guid>https://kre80r.com/series/bring-your-own-gpu/</guid><description>&lt;p>These are my notes from running large language models on my own hardware for my
coding agents and Hermes, first on one RTX 3090 and then on two joined by NVLink.
Each part starts with a number that looked like it settled something, and ends
with what I changed once I understood it.&lt;/p></description></item></channel></rss>