<?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>온프레미스-AI-인프라 on gnosyslambda&#39;s log</title>
    <link>https://gnosyslambda.github.io/tags/%EC%98%A8%ED%94%84%EB%A0%88%EB%AF%B8%EC%8A%A4-ai-%EC%9D%B8%ED%94%84%EB%9D%BC/</link>
    <description>Recent content in 온프레미스-AI-인프라 on gnosyslambda&#39;s log</description>
    <image>
      <title>gnosyslambda&#39;s log</title>
      <url>https://gnosyslambda.github.io/images/og-image.png</url>
      <link>https://gnosyslambda.github.io/images/og-image.png</link>
    </image>
    <generator>Hugo</generator>
    <language>ko-KR</language>
    <lastBuildDate>Sun, 05 Jul 2026 07:07:57 +0900</lastBuildDate>
    <atom:link href="https://gnosyslambda.github.io/tags/%EC%98%A8%ED%94%84%EB%A0%88%EB%AF%B8%EC%8A%A4-ai-%EC%9D%B8%ED%94%84%EB%9D%BC/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>로컬 LLM 인프라 구축 비용과 GPU 병목</title>
      <link>https://gnosyslambda.github.io/posts/2026-07-05-local-llm-gpu-infra/</link>
      <pubDate>Sun, 05 Jul 2026 07:07:57 +0900</pubDate>
      <guid>https://gnosyslambda.github.io/posts/2026-07-05-local-llm-gpu-infra/</guid>
      <description>로컬 LLM 구축을 GPU, VRAM, PCIe, vLLM 관점에서 정리하고 클라우드 API 대비 비용·보안·운영 리스크와 도입 조건을 비교합니다.</description>
    </item>
  </channel>
</rss>
