Understanding LLM Architecture and GPU Utilization Strategies for AI Beginners
Understand Transformer-based LLM architectures and GPU utilization strategies, and gain hands-on experience with the actual serving process using vLLM. This course covers the entire practical workflow, from building AI system pipelines to monitoring and multi-GPU utilization, and is designed for intuitive understanding through diagrams and practice without complex formulas.
209 learners
Level Basic
Course period Unlimited
- Resolved
[참고] Cannot connect to host host.docker.internal:8080
<img src="https://cdn.inflearn.com/public/files/posts/4b701dd0-9a1a-4b51-9716-83e8006fa729/3b91079b-5254-4f7d-bff3-2fd25af79217.png" media-type="img"
gpuattention-model인공지능(ai)transformerllmlogt
・
a month ago
0
60
2
- Unresolved
40강 Multi GPU 필요성 설명이 두번 나오는 것 같아요
모델 배포 방안 쪽 Tensor Parallelism과 Pipeline Parallelism 설명이 7분 30초 기준 한번 더 설명하시는 것 같아요. 판서는 살짝 다르지만 동일한 내용과 설명인 것 같아서 글 남겨봅니다<
gpuattention-model인공지능(ai)transformerllmchongin12
・
a month ago
0
54
2
- Resolved
There are no longer any instances available with the requested specifications. Please refresh and try again.
<img src="https://cdn.inflearn.com/public/files/posts/c18e7efd-4fd9-4ba0-8b50-5bedd362c021/34da8e13-f9e9-4751-bb
gpuattention-model인공지능(ai)transformerllmlogt
・
a month ago
0
84
2
- Resolved
질문있는데요.. vLLM은 말씀하신 사양에 적용이되나요?
vLLM은 강의소개 pc사양에 적용이되나요? GPU가 제공되는 모델만 되지않는지?일반 pc에 적용되는지 궁금합니다.</stron
gpuattention-model인공지능(ai)transformerllmlasttokens55853591
・
2 months ago
0
75
2
- Unresolved
강의 영상 오류
섹션3. 9 encoder 모델 자세히 보기영상에서 9:20~9:23 이 부분 중간에 잘못 잘린거 같습니다.
gpuattention-model인공지능(ai)transformerllmkjunekjune0812
・
3 months ago
0
95
1