<?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>Disaggregated Inference on Cognaptus</title>
    <link>https://cognaptus.com/tags/disaggregated-inference/</link>
    <description>Recent content in Disaggregated Inference on Cognaptus</description>
    <generator>Hugo -- 0.145.0</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 27 May 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://cognaptus.com/tags/disaggregated-inference/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>The KV Cache Is Not a Detail: Why LLM Compression Needs a Control Plane</title>
      <link>https://cognaptus.com/blog/2026-05-27-the-kv-cache-is-not-a-detail-why-llm-compression-needs-a-control-plane/</link>
      <pubDate>Wed, 27 May 2026 00:00:00 +0000</pubDate>
      <guid>https://cognaptus.com/blog/2026-05-27-the-kv-cache-is-not-a-detail-why-llm-compression-needs-a-control-plane/</guid>
      <description>KVServe shows why KV cache compression in disaggregated LLM serving should be treated as service-aware control, not a static infrastructure tweak.</description>
    </item>
  </channel>
</rss>
