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.
294
2
부
LLM 활용하기
추론 속도를 높이지만, 양자화 오류를 더 많이 발생시킬 수 있습니다.
양자화 구현에 관한 자세한 내용은 마르턴 흐루턴도르스트
Maarten
Grootendorst
의 「양자화에 대한 시
각적 가이드」
21
블로그 게시물을 참조하세요.
연습 문제 ●●●
이 책의 깃허브 저장소
22
에 있는 데이터셋 중 하나에서
Llama
3
.
1
을
float32
,
float16
,
bf16
,
int8
모드로 실행해 보세요.
다음 사항을 계산하세요.
●
모델 추론 시간에 미치는 영향
●
성능에 미치는 영향
●
저장 공간 요구 사항에 미치는 영향
선택한 데이터셋에서 양자화가 실제로 유용할까요?
9.6
마치며
이 장에서는
LLM
추론 시 발생하는 병목 현상의 원인에 관해 논의했습니다. 계산 요구량 감소,
저장 공간 요구량 감소, 디코딩 과정 가속화 기법을 포함하여
LLM
추론을 더 효율적으로 만드
는 다양한 기법을 살펴봤습니다. 캐싱, 조기 종료, 지식 증류, 스페큘러티브 디코딩과 병렬 디
코딩 기법, 양자화와 같은 방법을 탐구했습니다. 책의 다음이자 마지막인
3
부에는
LLM
애플리
케이션 패러다임을 살펴보고 완전한 애플리케이션을 구축하는 데 관련된 미묘한 차이점에 관
해 논의할 것입니다.
21
https
://
oreil
.
ly
/
bpi3b
22
https
://
github
.
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.