<?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>INT8 on Ge Zhang · 技术笔记</title>
    <link>https://blog-shf.pages.dev/tags/int8/</link>
    <description>Recent content in INT8 on Ge Zhang · 技术笔记</description>
    <image>
      <title>Ge Zhang · 技术笔记</title>
      <url>https://blog-shf.pages.dev/images/site-card.png</url>
      <link>https://blog-shf.pages.dev/images/site-card.png</link>
    </image>
    <generator>Hugo</generator>
    <language>zh-CN</language>
    <copyright>2026 Ge Zhang</copyright>
    <lastBuildDate>Tue, 28 Jul 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://blog-shf.pages.dev/tags/int8/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>大模型量化粒度详解：逐层、逐通道与逐组量化</title>
      <link>https://blog-shf.pages.dev/model-inference/quantization-granularity/</link>
      <pubDate>Tue, 28 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://blog-shf.pages.dev/model-inference/quantization-granularity/</guid>
      <description>从同一权重矩阵的数值分布出发，理解逐层、逐通道与逐组量化如何划分 scale 和 zero point，以及量化粒度对误差、元数据和计算内核的影响。</description>
    </item>
    <item>
      <title>量化基本概念</title>
      <link>https://blog-shf.pages.dev/model-inference/model-quantization-fundamentals/</link>
      <pubDate>Tue, 28 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://blog-shf.pages.dev/model-inference/model-quantization-fundamentals/</guid>
      <description>从数值表示、线性量化公式和矩阵乘法出发，理解模型量化的误差来源、静态与动态量化、PTQ 与 QAT，以及精度和性能评估方法。</description>
    </item>
  </channel>
</rss>
