<?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>CapacityEfficiency on TechLLM</title><link>https://techllm.github.io/tags/capacityefficiency/</link><description>Recent content in CapacityEfficiency on TechLLM</description><generator>Hugo</generator><language>ko</language><lastBuildDate>Sat, 02 May 2026 11:10:00 +0900</lastBuildDate><atom:link href="https://techllm.github.io/tags/capacityefficiency/index.xml" rel="self" type="application/rss+xml"/><item><title>Meta는 AI 에이전트로 데이터센터 전력 낭비를 줄이고 있다</title><link>https://techllm.github.io/posts/meta-capacity-efficiency-ai-agents/</link><pubDate>Sat, 02 May 2026 11:10:00 +0900</pubDate><guid>https://techllm.github.io/posts/meta-capacity-efficiency-ai-agents/</guid><description>Meta의 Capacity Efficiency Program 사례를 통해, 통합 AI 에이전트가 하이퍼스케일 인프라의 성능 회귀와 최적화 기회를 어떻게 자동화하는지 정리한다.</description></item></channel></rss>