feat: Variet Engine v1.0 + 5-model tuning complete

Phase 01 (LLM Tuning):
- Gemma4 26B: 74.65 t/s (fast)
- Qwen 35B: 61.62 t/s (balanced)
- Gemma4 31B: 16.0 t/s (deep-coder)
- Qwen 27B: 16.7 t/s (deep-logic)
- Qwen 122B: 8.95 t/s (ultra, GPU 1 only)

Phase 02 (API Engine):
- FastAPI reverse proxy on port 8000
- /engine/switch hot-swap with 503 protection
- config/engine_models.json as single source of truth
- Replaced 4 individual .bat files with unified engine

File cleanup:
- scripts/ 85 files -> 9 + _archive/
- Root .bat files -> _archive/

scripts/_archive/results/split_test_result.txt

@@ -0,0 +1,8 @@
+
+==================================================
+ TS=0.5,0.5  5-Run Results (with --mlock --poll 50):
+   AVG:  61.94 t/s
+   BEST: 62.06 t/s
+   MIN:  61.74 t/s
+   Runs: ['62.06', '61.74', '61.92', '62.00', '61.96']
+==================================================