<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Inference on Eknix — Web security &amp; performance for the enterprise</title><link>https://www.eknix.com/tags/inference/</link><description>Recent content in Inference on Eknix — Web security &amp; performance for the enterprise</description><generator>Hugo</generator><language>en-us</language><copyright>© {year} EKNIX LTD. All rights reserved.</copyright><lastBuildDate>Fri, 18 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.eknix.com/tags/inference/index.xml" rel="self" type="application/rss+xml"/><item><title>The Average Enterprise GPU Is Busy 5% of the Time. Price Your Cluster Accordingly.</title><link>https://www.eknix.com/blog/run-rent-or-build-gpu-cluster/</link><pubDate>Fri, 18 Sep 2026 00:00:00 +0000</pubDate><guid>https://www.eknix.com/blog/run-rent-or-build-gpu-cluster/</guid><description>&lt;p&gt;The spreadsheet always wins the first meeting.&lt;/p&gt;
&lt;p&gt;Someone takes the purchase price of eight GPUs, divides it by three years of hours, sets the result against a cloud provider&amp;rsquo;s on-demand rate, and arrives at a number that makes owning look obviously cheaper. Two dollars an hour against six. Nobody argues, because the arithmetic is correct.&lt;/p&gt;
&lt;p&gt;The arithmetic is correct and the conclusion is usually wrong, because the denominator is fiction. Dividing by three years of hours assumes the GPU is busy for three years of hours.&lt;/p&gt;</description></item></channel></rss>