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.
291
9
장
추론 최적화
필요한 저장 공간을 줄이는 기법인 양자화를 자세히 알아보겠습니다.
9.5
저장 공간을 절약하는 기법
5
장과
6
장에서 간략히 다룬 양자화를 이제 본격적으로 알아보겠습니다.
언어 모델의 순방향 전달 과정은 입력, 가중치, 활성화를 나타내는 숫자들을 포함합니다. 이러
한 숫자들은 메모리에서 어떻게 표현될까요?
정수, 부동소수점 등과 같은 여러 타입의 수치 표현 형식이 존재합니다. 일반적으로 언어 모델
의 숫자는 단정밀도 부동소수점이라고도 하는 부동소수점
32
(
FP32
)로 표현되는데, 이는
32
비트나
4
바이트로 구성된 부동소수점 숫자를 의미합니다.
FP32
로 표현된 숫자는 다음 세 부분으로 구성됩니다.
●
부호 비트
●
지 수 (
8
비트 )
●
가수/유효숫자 (
23
비트 )
FP32
가 어떻게 작동하는지에 관한 자세한 내용은 부동소수점 정밀도 이해하기 블로그 게시
물
20
을 참조하세요.
FP32
으로 표현할 수 있는 값의 범위는 최대
3
.
4028237
×
10
38
과 최소
1
.
175494
×
10
-
38
입
니다. 마찬가지로, 반정밀도 부동소수점이라고도 하는
float16
(
FP16
)으로 표현된 숫자는 다
음 세 부분으로 구성됩니다.
●
부호 비트
●
지 수 (
5
비트 )
●
가수/유효숫자 (
10
비트 )
FP32
로 표현된 숫자를
FP16
으로 표현할 때 어떤 일이 ...
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.