<?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>Edge-Computing on The Telemetry Forge</title>
    <link>https://telemetry-forge.t-security.org/tags/edge-computing/</link>
    <description>Recent content in Edge-Computing on The Telemetry Forge</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Thu, 07 May 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://telemetry-forge.t-security.org/tags/edge-computing/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>From Kubernetes Dreams to Docker Reality: Building an ML Inference Cluster on Jetson Nano (Part 1 of 5)</title>
      <link>https://telemetry-forge.t-security.org/posts/jetson-nano-k8s-to-docker-inference/</link>
      <pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
      <guid>https://telemetry-forge.t-security.org/posts/jetson-nano-k8s-to-docker-inference/</guid>
      <description>I set out to run a Kubernetes cluster on four Jetson Nano modules to serve ML model inference for Splunk&amp;#39;s Deep Learning Toolkit. Here&amp;#39;s the honest story of why that didn&amp;#39;t work as planned, what kernel limitations forced us to rethink the architecture, and why a Docker-based approach turned out to be the right call for fixed-function edge inference nodes.
</description>
    </item>
  </channel>
</rss>
