<?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>Long-Context on CharmingGroot</title>
    <link>https://charminggroot.github.io/tags/long-context/</link>
    <description>Recent content in Long-Context on CharmingGroot</description>
    <generator>Hugo</generator>
    <language>ko-kr</language>
    <lastBuildDate>Sun, 14 Jun 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://charminggroot.github.io/tags/long-context/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>086. FlashAttention — 어텐션 메모리 최적화</title>
      <link>https://charminggroot.github.io/posts/086-flash-attention/</link>
      <pubDate>Sun, 14 Jun 2026 00:00:00 +0000</pubDate>
      <guid>https://charminggroot.github.io/posts/086-flash-attention/</guid>
      <description>FlashAttention(2022)은 트랜스포머 어텐션의 메모리 병목을 IO-Aware 타일링으로 해결한다. 어텐션 행렬을 HBM에 저장하지 않고 SRAM에서 직접 계산해 메모리 사용량을 O(n)으로 줄이고 속도를 2~4배 높인다.</description>
    </item>
  </channel>
</rss>
