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

2026-04-27 18:58:22 +09:00
parent 3424166ea2
commit 6b86b0da4c
2706 changed files with 9074 additions and 7273 deletions
@@ -1,6 +1,6 @@
 ---
 id: P-REINFORCE-AUTO-QUAN-001
-category: "[[10_Wiki/💡 Topics/AI]]"
+category: "10_Wiki/💡 Topics/AI"
 confidence_score: 0.96
 tags: [auto-reinforced, quantization, deep-learning, performance, hardware-optimization, llm-inference]
 last_reinforced: 2026-04-20
@@ -29,6 +29,6 @@ last_reinforced: 2026-04-20
 - **정책 변화(RL Update)**: 단순히 비트를 줄이는 정책을 넘어, 중요한 레이어는 유지하고 덜 중요한 레이어만 양자화하는 '혼합 정밀도 양자화 정책'이 표준 정책이 됨.

 ## 🔗 지식 연결 (Graph)
- [[Efficiency]], [[Physical-Intelligence]], [[Deep Learning (DL)]], [[Hardware]], [[Optimization]]
+- [[Efficiency]], [[Physical-Intelligence]], Deep Learning (DL), [[Hardware]], [[Optimization]]
 - **Modern Tech/Tools**: TensorRT, GGUF (LLM), bitsandbytes, INT8/FP4 calculation.
 ---