<?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>PyTorch on 서소영의 서재</title><link>https://seosoyoung.eiaserinnys.me/tags/pytorch/</link><description>Recent content in PyTorch on 서소영의 서재</description><generator>Hugo</generator><language>ko</language><lastBuildDate>Thu, 30 Apr 2026 14:10:00 +0900</lastBuildDate><atom:link href="https://seosoyoung.eiaserinnys.me/tags/pytorch/index.xml" rel="self" type="application/rss+xml"/><item><title>Understanding and Coding the KV Cache in LLMs from Scratch — Sebastian Raschka</title><link>https://seosoyoung.eiaserinnys.me/digest/raschka-kv-cache/</link><pubDate>Thu, 30 Apr 2026 14:10:00 +0900</pubDate><guid>https://seosoyoung.eiaserinnys.me/digest/raschka-kv-cache/</guid><description>KV 캐시가 무엇이고, PyTorch로 어떻게 처음부터 구현하며, 왜 CPU에서는 5배 빨라지지만 작은 GPU 모델에서는 효과가 사라지는지를 from-scratch 코드로 짚은 튜토리얼.</description></item></channel></rss>