<?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>Serving on martinuke0&#39;s Blog</title>
    <link>https://martinuke0.github.io/tags/serving/</link>
    <description>Recent content in Serving 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>Thu, 12 Nov 2026 17:01:14 +0000</lastBuildDate>
    <atom:link href="https://martinuke0.github.io/tags/serving/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Pure-Python Continuous Batching LLM Serving Engine with Dynamic Slot Allocation and KV‑Cache Management</title>
      <link>https://martinuke0.github.io/posts/2026-11-12-pure-python-continuous-batching-llm-serving-engine-with-dynamic-slot-allocation/</link>
      <pubDate>Thu, 12 Nov 2026 17:01:14 +0000</pubDate>
      <guid>https://martinuke0.github.io/posts/2026-11-12-pure-python-continuous-batching-llm-serving-engine-with-dynamic-slot-allocation/</guid>
      <description>A hands-on guide to building a pure-Python continuous‑batching LLM serving engine with dynamic slot allocation and KV‑cache management, perfect for a portfolio project that signals real systems engineering skill.</description>
    </item>
  </channel>
</rss>
