<?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>Moonshot-Ai on martinuke0&#39;s Blog</title>
    <link>https://martinuke0.github.io/tags/moonshot-ai/</link>
    <description>Recent content in Moonshot-Ai on martinuke0&#39;s Blog</description>
    <image>
      <title>martinuke0&#39;s Blog</title>
      <url>https://martinuke0.github.io/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E</url>
      <link>https://martinuke0.github.io/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E</link>
    </image>
    <generator>Hugo -- 0.152.2</generator>
    <language>en</language>
    <lastBuildDate>Sat, 05 Sep 2026 18:59:47 +0000</lastBuildDate>
    <atom:link href="https://martinuke0.github.io/tags/moonshot-ai/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Mooncake: Turning KV Cache into a Distributed LLM Serving Layer</title>
      <link>https://martinuke0.github.io/posts/2026-09-05-mooncake-turning-kv-cache-into-a-distributed-llm-serving-layer/</link>
      <pubDate>Sat, 05 Sep 2026 18:59:47 +0000</pubDate>
      <guid>https://martinuke0.github.io/posts/2026-09-05-mooncake-turning-kv-cache-into-a-distributed-llm-serving-layer/</guid>
      <description>How Moonshot AI&amp;#39;s Mooncake architecture decouples KV cache from GPU memory to slash LLM inference latency and cost.</description>
    </item>
  </channel>
</rss>
