2nd/10_Wiki/Topics/AI_and_ML/Adaptive Compute (적응형 계산량 조절).md

id, title, category, status, canonical_id, duplicate_of, aliases, source_trust_level, confidence_score, verification_status, tags, last_reinforced, github_commit

id	title	category	status	canonical_id	duplicate_of	aliases	source_trust_level	confidence_score	verification_status	tags	last_reinforced	github_commit
wiki-2026-0508-adaptive-compute-적응형-계산량-조절	Adaptive Compute (적응형 계산량 조절)	10_Wiki/Topics	duplicate	wiki-2026-0508-adaptive-compute	Adaptive Compute		A	0.9	redirected	duplicate adaptive-compute inference efficiency	2026-05-10	pending

Adaptive Compute (적응형 계산량 조절)

이 문서는 Adaptive Compute 의 중복본입니다. Canonical 문서로 redirect.

핵심 요약

• Adaptive compute = 매 input difficulty 의 따라 의 inference compute 의 dynamic 의 allocate.
• 매 동일 concept — 매 Korean parenthetical translation 의 only difference.
• Test-time scaling, early-exit, mixture-of-depths, adaptive thinking budget (Claude extended thinking 2024+) 의 family.

🔗 Graph

• 부모: Adaptive Compute (canonical)

🕓 변경 이력

날짜	변경
2026-05-08	Phase 1
2026-05-10	중복 처리 — canonical 문서로 redirect (Korean parenthetical variant)