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/

config/engine_models.json

@@ -0,0 +1,120 @@
+{
+  "version": "1.0",
+  "default_role": "fast",
+  "llama_server": {
+    "path": "llama_bin_run/llama-server.exe",
+    "internal_port": 8080,
+    "internal_host": "127.0.0.1"
+  },
+  "engine": {
+    "external_port": 8000,
+    "external_host": "0.0.0.0"
+  },
+  "roles": {
+    "fast": {
+      "display_name": "Gemma 4 26B (Fast)",
+      "model_path": "models/gemma-4-26B-A4B-it-Q4_K_M.gguf",
+      "measured_tps": 74.65,
+      "args": [
+        "-ngl", "999",
+        "-c", "262144",
+        "-np", "1",
+        "-fa", "on",
+        "--cache-type-k", "f16",
+        "--cache-type-v", "f16",
+        "-ub", "512",
+        "-b", "2048",
+        "-t", "6",
+        "-tb", "6",
+        "--prio", "3",
+        "--mlock",
+        "--poll", "50"
+      ]
+    },
+    "balanced": {
+      "display_name": "Qwen 3.5 35B (Balanced)",
+      "model_path": "models/Qwen3.5-35B-A3B-Q4_K_M.gguf",
+      "measured_tps": 61.62,
+      "args": [
+        "-ngl", "999",
+        "-c", "262144",
+        "-np", "1",
+        "-fa", "on",
+        "--cache-type-k", "q4_0",
+        "--cache-type-v", "q4_0",
+        "-ub", "128",
+        "-b", "512",
+        "-t", "6",
+        "-tb", "6",
+        "--prio", "3",
+        "--mlock",
+        "--poll", "50",
+        "-ts", "0.5,0.5"
+      ]
+    },
+    "deep-coder": {
+      "display_name": "Gemma 4 31B (Deep Coder)",
+      "model_path": "models/gemma-4-31B-it-Q4_K_M.gguf",
+      "measured_tps": 16.0,
+      "args": [
+        "-ngl", "999",
+        "-c", "196608",
+        "-np", "1",
+        "-fa", "on",
+        "--cache-type-k", "q4_0",
+        "--cache-type-v", "q4_0",
+        "-ub", "128",
+        "-b", "512",
+        "-t", "6",
+        "-tb", "6",
+        "--prio", "3",
+        "--mlock",
+        "--poll", "50"
+      ]
+    },
+    "deep-logic": {
+      "display_name": "Qwen 3.5 27B (Deep Logic)",
+      "model_path": "models/Qwen3.5-27B-Q4_K_M.gguf",
+      "measured_tps": 16.7,
+      "args": [
+        "-ngl", "999",
+        "-c", "262144",
+        "-np", "1",
+        "-fa", "on",
+        "--cache-type-k", "q4_0",
+        "--cache-type-v", "q4_0",
+        "-ub", "512",
+        "-b", "1024",
+        "-t", "6",
+        "-tb", "6",
+        "--prio", "3",
+        "--mlock",
+        "--poll", "50",
+        "-ts", "0.5,0.5"
+      ]
+    },
+    "ultra": {
+      "display_name": "Qwen 3.5 122B (Ultra Heavy)",
+      "model_path": "models/Q4_K_M/Qwen3.5-122B-A10B-Q4_K_M-00001-of-00003.gguf",
+      "measured_tps": 8.95,
+      "args": [
+        "-ngl", "999",
+        "-ncmoe", "48",
+        "-c", "262144",
+        "-np", "1",
+        "-fa", "on",
+        "--cache-type-k", "q4_0",
+        "--cache-type-v", "q4_0",
+        "-ub", "512",
+        "-b", "2048",
+        "-t", "8",
+        "-tb", "8",
+        "--prio", "3",
+        "--poll", "50",
+        "--main-gpu", "1",
+        "-sm", "none",
+        "--no-mmap"
+      ]
+    }
+  }
+}