<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Kai-Scheduler on Anish Bista</title><link>https://anishbista.org/tags/kai-scheduler/</link><description>Recent content in Kai-Scheduler on Anish Bista</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 15 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://anishbista.org/tags/kai-scheduler/index.xml" rel="self" type="application/rss+xml"/><item><title>NVIDIA Just Open-Sourced Run:ai. Let's Try It With 32 Fake GPUs</title><link>https://anishbista.org/blog/nvidia-runai-open-source/</link><pubDate>Thu, 15 Oct 2026 00:00:00 +0000</pubDate><guid>https://anishbista.org/blog/nvidia-runai-open-source/</guid><description>&lt;p>NVIDIA bought Run:ai in 2024. On &lt;strong>October 13, 2026&lt;/strong>, it &lt;a href="https://developer.nvidia.com/blog/nvidia-runai-is-now-open-source-as-part-of-nvidia-dsx-ai-factory-platform/">open-sourced the whole Run:ai platform&lt;/a> under Apache 2.0. Until then, the full platform needed a paid license. In this post I explain what Run:ai is and then run the whole thing, UI included, on one VM with &lt;strong>no GPU&lt;/strong>.&lt;/p>
&lt;h2 id="what-is-runai">What is Run:ai?&lt;a class="heading-anchor" href="#what-is-runai" aria-label="Link to this section">#&lt;/a>&lt;/h2>
&lt;p>Run:ai is a &lt;strong>GPU platform for AI teams that share one pool of GPUs&lt;/strong>, built on top of Kubernetes:&lt;/p></description></item></channel></rss>