<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Consolidation on nanta - Data Engineering</title><link>https://nanta-data.dev/en/tags/consolidation/</link><description>Recent content in Consolidation on nanta - Data Engineering</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 nanta</copyright><lastBuildDate>Thu, 05 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://nanta-data.dev/en/tags/consolidation/index.xml" rel="self" type="application/rss+xml"/><item><title>EKS AI Serving Node Cost Reduction: Instance Diversification, Consolidation, and Scheduled Scaling</title><link>https://nanta-data.dev/en/posts/eks-ai-platform-cost-saving/</link><pubDate>Thu, 05 Mar 2026 00:00:00 +0000</pubDate><guid>https://nanta-data.dev/en/posts/eks-ai-platform-cost-saving/</guid><description>An AI platform team&amp;rsquo;s serving API was running 500 fixed pods on only two on-demand instance types (c6i.2xlarge, m6i.2xlarge). We applied instance type diversification and Karpenter consolidation as phase 1, then KEDA cron-trigger scheduled scaling as phase 2. Key finding: consolidation alone has limited effect when pod count is fixed — it needs scale-in to actually reduce node count.</description></item></channel></rss>