https://www.youngju.dev/blog 천천히 올바르게. AI Researcher & DevOps Engineer Youngju's tech blog. GPU/CUDA, LLM, MLOps, Kubernetes AI workloads, distributed training, and data engineering. ko fjvbn2003@gmail.com (Youngju Kim) fjvbn2003@gmail.com (Youngju Kim) Fri, 12 Jun 2026 00:00:00 GMT https://www.youngju.dev/blog/llm/2026-06-12-llm-from-scratch-cs336-roadmap.en https://www.youngju.dev/blog/llm/2026-06-12-llm-from-scratch-cs336-roadmap.en Stanford CS336 (Language Modeling from Scratch) keeps hitting the Hacker News front page, and from-scratch LLM building is hot again. This post dissects the full curriculum — tokenizers, attention, distributed training, scaling laws, alignment, and inference optimization — and lays out a 20-week self-study plan with mini project ideas. Fri, 12 Jun 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) llmtransformercs336deep-learningtokenizertrainingnanogpt https://www.youngju.dev/blog/llm/2026-06-12-llm-from-scratch-cs336-roadmap.ja https://www.youngju.dev/blog/llm/2026-06-12-llm-from-scratch-cs336-roadmap.ja スタンフォードのCS336（Language Modeling from Scratch）がHacker Newsの上位に登場し続け、ゼロからのLLM構築が再び話題になっています。トークナイザーからアテンション、分散学習、スケーリング則、アライメント、推論最適化までカリキュラム全体を解剖し、20週間の学習プランとミニプロジェクトのアイデアをまとめました。 Fri, 12 Jun 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) llmtransformercs336deep-learningtokenizertrainingnanogpt https://www.youngju.dev/blog/llm/2026-06-12-llm-from-scratch-cs336-roadmap https://www.youngju.dev/blog/llm/2026-06-12-llm-from-scratch-cs336-roadmap 스탠퍼드 CS336(Language Modeling from Scratch)이 해커뉴스 상위권에 오르며 from-scratch LLM 학습이 다시 화제입니다. 토크나이저부터 어텐션, 분산 학습, 스케일링 법칙, 정렬, 추론 최적화까지 전체 커리큘럼을 해부하고 20주 학습 플랜과 미니 프로젝트 아이디어를 정리했습니다. Fri, 12 Jun 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) llmtransformercs336deep-learningtokenizertrainingnanogpt