bluemsi/2nd
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: complete wikification of War Commander batch 1&2 and final grey dot cleanup

Browse Source
This commit is contained in:
yesung
2026-04-27 18:58:22 +09:00
parent 3424166ea2
commit 6b86b0da4c
2706 changed files with 9074 additions and 7273 deletions
Download Patch File Download Diff File Expand all files Collapse all files
10_Wiki/Topics/AI/Model-Compression-Strategies.md
+3 -3
View File
@@ -1,12 +1,12 @@
---
id: AI-COMP-001
category: "[[10_Wiki/💡 Topics/AI]]"
category: "10_Wiki/💡 Topics/AI"
confidence_score: 1.0
tags: [ai, deep-learning, model-compression, quantization, pruning, efficient-ai]
last_reinforced: 2026-04-26
---
# [[Model Compression Strategies (모델 압축 전략)]]
# Model Compression Strategies (모델 압축 전략)
## 📌 한 줄 통찰 (The Karpathy Summary)
> "모델의 지능은 보존하되 그 몸집(Parameters)을 줄여, 클라우드의 한계를 넘어 모든 기기에서 지능이 숨 쉬게 하라" — 딥러닝 모델의 크기와 연산 복잡도를 줄여 추론 속도를 높이고 메모리 사용량을 절감하는 기술적 방법론.
@@ -26,4 +26,4 @@ last_reinforced: 2026-04-26
## 🔗 지식 연결 (Graph)
- [[Mobile-AI-Optimization]], [[Knowledge-Distillation]], [[Inference-Optimization]], [[Low-Rank-Adaptation-LoRA]]
- **Raw Source:** [[10_Wiki/Topics/AI/Model-Compression-Strategies.md]]
- **Raw Source:** 10_Wiki/Topics/AI/Model-Compression-Strategies.md