<?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>Roofline on CctoctoFX</title>
    <link>https://pillumina.github.io/tags/roofline/</link>
    <description>Recent content in Roofline on CctoctoFX</description>
    <image>
      <title>CctoctoFX</title>
      <url>https://pillumina.github.io/imgs/icon_head.png</url>
      <link>https://pillumina.github.io/imgs/icon_head.png</link>
    </image>
    <generator>Hugo -- 0.148.2</generator>
    <language>en</language>
    <lastBuildDate>Mon, 22 Jun 2026 09:03:00 +0800</lastBuildDate>
    <atom:link href="https://pillumina.github.io/tags/roofline/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>LLM 系统分析方法论（四）：M3 实战推演与 Roofline 模型</title>
      <link>https://pillumina.github.io/posts/aiinfra/llm-computation-methodology/part-4/</link>
      <pubDate>Mon, 22 Jun 2026 09:03:00 +0800</pubDate>
      <guid>https://pillumina.github.io/posts/aiinfra/llm-computation-methodology/part-4/</guid>
      <description>MiniMax M3 完整推演：从 config.json 到参数量、FLOPs、KV Cache、推理显存的全链路计算。Roofline 模型分析推理延迟，理解 FP8/INT4 量化的性能收益。</description>
    </item>
  </channel>
</rss>
