<?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>Mps on Rick Lamers&#39; blog</title>
    <link>https://ricklamers.io/tags/mps/</link>
    <description>Recent content in Mps on Rick Lamers&#39; blog</description>
    <image>
      <title>Rick Lamers&#39; blog</title>
      <url>https://ricklamers.io/cover.png</url>
      <link>https://ricklamers.io/cover.png</link>
    </image>
    <generator>Hugo -- 0.151.0</generator>
    <language>en</language>
    <lastBuildDate>Mon, 20 Apr 2026 12:00:00 +0200</lastBuildDate>
    <atom:link href="https://ricklamers.io/tags/mps/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>KV Cache, Made Visible: Qwen3-0.6B on Apple Silicon</title>
      <link>https://ricklamers.io/posts/kvcache-exploration/</link>
      <pubDate>Mon, 20 Apr 2026 12:00:00 +0200</pubDate>
      <guid>https://ricklamers.io/posts/kvcache-exploration/</guid>
      <description>A minimal Qwen3-0.6B in pure PyTorch, running on Apple Silicon, with a live UI that makes the memory and latency trade-offs of KV cache physically visible. Toggle the cache off and watch attention go quadratic in real time.</description>
    </item>
  </channel>
</rss>
