<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
  <id>https://gattic.com/articles/</id>
  <title>Gattic Articles</title>
  <subtitle>Technical guides and field notes from Gattic on machine learning infrastructure, self-hosted AI models, and the open-source software we build with.</subtitle>
  <link rel="self" type="application/atom+xml" href="https://gattic.com/articles/feed.xml" />
  <link rel="alternate" type="text/html" href="https://gattic.com/articles/" />
  <updated>2026-11-02T00:00:00Z</updated>
  <author>
    <name>Gattic</name>
    <uri>https://gattic.com/</uri>
  </author>
  <icon>https://gattic.com/images/gattic-logo.png</icon>
  <entry>
    <id>https://gattic.com/articles/two-dgx-sparks-deepseek-headless-guide/</id>
    <title>DeepSeek on Two NVIDIA DGX Sparks: The Complete Headless Installation and Operations Guide</title>
    <link rel="alternate" type="text/html" href="https://gattic.com/articles/two-dgx-sparks-deepseek-headless-guide/" />
    <published>2026-11-02T00:00:00Z</published>
    <updated>2026-11-02T00:00:00Z</updated>
    <summary>An SSH-first walkthrough for building a private, multimodal DeepSeek-V4.1-Flash-1017 inference cluster, then adding chat, coding agents, queues, caching, monitoring, and reliable upgrades.</summary>
  </entry>
</feed>
