<?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>Qps on Tenu Tech Brief</title>
    <link>https://cluster-site.onrender.com/tags/qps/</link>
    <description>Recent content in Qps on Tenu Tech Brief</description>
    <generator>Hugo -- 0.146.0</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 25 Feb 2026 07:59:06 +0000</lastBuildDate>
    <atom:link href="https://cluster-site.onrender.com/tags/qps/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Best Practices for High QPS Model Serving on Databricks</title>
      <link>https://cluster-site.onrender.com/posts/best-practices-for-high-qps-model-serving-on-databricks/</link>
      <pubDate>Tue, 17 Feb 2026 18:15:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/best-practices-for-high-qps-model-serving-on-databricks/</guid>
      <description>• Share this post Keep up with us Summary Model Serving supports real-time endpoints that scale to 300K+ QPS (CPU), with an enhanced engine specialized for low latency, real-time M</description>
    </item>
  </channel>
</rss>
