<?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>오픈웨이트LLM on TechLLM</title><link>https://techllm.github.io/tags/%EC%98%A4%ED%94%88%EC%9B%A8%EC%9D%B4%ED%8A%B8llm/</link><description>Recent content in 오픈웨이트LLM on TechLLM</description><generator>Hugo</generator><language>ko</language><lastBuildDate>Sat, 13 Jun 2026 19:42:00 +0900</lastBuildDate><atom:link href="https://techllm.github.io/tags/%EC%98%A4%ED%94%88%EC%9B%A8%EC%9D%B4%ED%8A%B8llm/index.xml" rel="self" type="application/rss+xml"/><item><title>MiniMax-M3 로컬 배포 실전: vLLM·SGLang·Docker로 428B MoE 돌리기</title><link>https://techllm.github.io/posts/minimax-m3-local-deployment-vllm-sglang/</link><pubDate>Sat, 13 Jun 2026 19:42:00 +0900</pubDate><guid>https://techllm.github.io/posts/minimax-m3-local-deployment-vllm-sglang/</guid><description>MiniMax-M3가 HuggingFace에 풀렸습니다. 428B 파라미터·23B 활성·1M 컨텍스트 멀티모달 모델을 vLLM, SGLang, Transformers, Docker로 띄우는 실전 가이드와 11종 양자화 옵션, 권장 추론 파라미터를 정리합니다.</description></item></channel></rss>