<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Rollouts on Rik Kisnah - Blog</title><link>https://www.rik-kisnah.ai/tags/rollouts/</link><description>Recent content in Rollouts on Rik Kisnah - Blog</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 17 Mar 2026 09:00:00 -0700</lastBuildDate><atom:link href="https://www.rik-kisnah.ai/tags/rollouts/feed.xml" rel="self" type="application/rss+xml"/><item><title>Design Model Weight Distribution to a Thousand Hosts</title><link>https://www.rik-kisnah.ai/teach/gpu-ai/design-model-weight-distribution/</link><pubDate>Tue, 17 Mar 2026 09:00:00 -0700</pubDate><guid>https://www.rik-kisnah.ai/teach/gpu-ai/design-model-weight-distribution/</guid><description>A 500 GB model sits in one repository behind a 10 Gbps link. A thousand GPU hosts need it, each with a 10 Gbps card, and a few of them will die while you copy. Say the lower bound, then design the swarm that gets close to it, then the part that actually matters in production: verifying every copy and never serving from a half-loaded host.</description></item></channel></rss>