October 2025
Intermediate
424 pages
10h 19m
Korean
Content preview from 실무로 통하는 LLM 애플리케이션 설계
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
191
5
장
사용 목적에 맞게 LLM 활용하기
이 책의 깃허브 저장소에는
Ollama
와 그
UI
통합 기능을 활용해 구현한 샘플 엔드 투 엔드 애
플리케이션이 있습니다. 또한
LM
Studio
48
나
GPT4All
49
과 같은 유사한 도구들도 직접 실험
해 볼 수 있습니다.
TIP
Ollama
는
GGUF
GPT
-
Generated
Unified
Format
형식의 모델도 지원하므로 해당 형식의 커스텀 모델을 직접 로딩
해 사용할 수 있습니다.
5.3.3
LLM
추론
API
LLM
을 직접 배포할 수도 있지만, 현대의 추론은 매우 많은 최적화로 이루어지며 그중 많은 부
분이 독점적입니다. 따라서 추론 속도를 상업적으로 이용 가능한 솔루션과 동등한 수준으로 끌
어올리는 데는 많은 노력이 필요합니다. 투게더
AI
와 같은 서비스에서는 오픈 소스나 커스텀
모델을 손쉽게 사용할 수 있도록 서버리스 엔드포인트나 전용 인스턴스를 제공합니다. 또 다른
옵션으로는 허깅 페이스의
TGI
Text
Generation
Inference
가 있으며, 최근에는 제한 없는 오픈 소스 라
이선스로 다시 제공되어 더 자유롭게 활용할 수 있게 되었습니다.
5.4
디코딩 전략
모델을 로딩하는 방법을 익혔으니, 다음으로는 텍스트 생성을 어떻게 효과적으로 수행하는지
를 알아보겠습니다. 최근 몇 년 사이 다양한
디코딩
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.