
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>Chaos and Order</title>
      <link>https://www.youngju.dev/blog</link>
      <description>천천히 올바르게. AI Researcher &amp; DevOps Engineer Youngju&#39;s blog. GPU/CUDA, LLM, MLOps, Kubernetes AI workloads, and data engineering — plus mindset essays on confidence, routines, health, and sport psychology.</description>
      <language>ko</language>
      <managingEditor>fjvbn2003@gmail.com (Youngju Kim)</managingEditor>
      <webMaster>fjvbn2003@gmail.com (Youngju Kim)</webMaster>
      <lastBuildDate>Wed, 12 Aug 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://www.youngju.dev/tags/qk-norm/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://www.youngju.dev/blog/ai-papers/2026-08-12-model-internals-normalization-and-activation.en</guid>
    <title>Normalization and Activation — Keeping Training From Falling Apart</title>
    <link>https://www.youngju.dev/blog/ai-papers/2026-08-12-model-internals-normalization-and-activation.en</link>
    <description>Confirming from config values why RMSNorm, pre-norm, and SwiGLU became the defaults, then walking through the newer devices that stop attention logits from exploding — the QK-Norm of Qwen3 and the QK-Clip of Kimi K2 — with the figures their reports state. What gets added for stability, and what gets accepted in return.</description>
    <pubDate>Wed, 12 Aug 2026 00:00:00 GMT</pubDate>
    <author>fjvbn2003@gmail.com (Youngju Kim)</author>
    <category>ai-papers</category><category>model-internals</category><category>rmsnorm</category><category>swiglu</category><category>training-stability</category><category>qk-norm</category>
  </item>

  <item>
    <guid>https://www.youngju.dev/blog/ai-papers/2026-08-12-model-internals-normalization-and-activation.ja</guid>
    <title>正規化と活性化 — 学習を壊さないために</title>
    <link>https://www.youngju.dev/blog/ai-papers/2026-08-12-model-internals-normalization-and-activation.ja</link>
    <description>RMSNorm とプレノルム、SwiGLU がなぜ現在の標準になったのかを config の値で確認し、Qwen3 の QK-Norm や Kimi K2 の QK-Clip のようにアテンションロジットの暴走を止める新しい仕組みを、各レポートが記す数値とともに整理します。安定性のために何を足し、何を引き受けるのかを扱います。</description>
    <pubDate>Wed, 12 Aug 2026 00:00:00 GMT</pubDate>
    <author>fjvbn2003@gmail.com (Youngju Kim)</author>
    <category>ai-papers</category><category>model-internals</category><category>rmsnorm</category><category>swiglu</category><category>training-stability</category><category>qk-norm</category>
  </item>

  <item>
    <guid>https://www.youngju.dev/blog/ai-papers/2026-08-12-model-internals-normalization-and-activation</guid>
    <title>정규화와 활성화 — 학습을 무너뜨리지 않는 법</title>
    <link>https://www.youngju.dev/blog/ai-papers/2026-08-12-model-internals-normalization-and-activation</link>
    <description>RMSNorm과 프리노름, SwiGLU가 왜 지금의 표준이 되었는지 config 값으로 확인하고, Qwen3의 QK-Norm과 Kimi K2의 QK-Clip처럼 어텐션 로짓 폭주를 막는 최신 장치를 실제 리포트의 수치와 함께 정리합니다. 안정성을 위해 무엇을 추가하고 무엇을 감수하는지 다룹니다.</description>
    <pubDate>Wed, 12 Aug 2026 00:00:00 GMT</pubDate>
    <author>fjvbn2003@gmail.com (Youngju Kim)</author>
    <category>ai-papers</category><category>model-internals</category><category>rmsnorm</category><category>swiglu</category><category>training-stability</category><category>qk-norm</category>
  </item>

    </channel>
  </rss>
