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/tuning/tune_exact.mjs

@@ -0,0 +1,72 @@
+import { exec, spawn } from 'child_process';
+
+const delay = ms => new Promise(res => setTimeout(res, ms));
+
+async function runTest(modelArgs, envVars, name) {
+    console.log(`\n===========================================`);
+    console.log(`Testing: ${name}`);
+    console.log(`Env: ${JSON.stringify(envVars)}`);
+    console.log(`Args: ${modelArgs}`);
+    
+    return new Promise(async (resolve) => {
+        await new Promise(r => exec('taskkill /F /IM llama-server.exe', r));
+        await delay(2000);
+
+        const env = { ...process.env, ...envVars };
+        const server = spawn('llama_bin_run\\llama-server.exe', modelArgs.split(' '), {
+            detached: true,
+            stdio: 'ignore',
+            env
+        });
+
+        let ready = false;
+        
+        for (let i = 0; i < 40; i++) {
+            try {
+                const res = await fetch('http://127.0.0.1:8000/health', { timeout: 2000 });
+                if (res.status === 200) {
+                    ready = true;
+                    break;
+                }
+            } catch (e) {}
+            await delay(3000);
+        }
+
+        if (!ready) {
+            console.log(`[${name}] FAILED TO BOOT`);
+            exec('taskkill /F /IM llama-server.exe');
+            resolve({ success: false });
+            return;
+        }
+
+        console.log(`[${name}] Server Ready! Running speed test...`);
+        exec('node scripts/quick_pptest.mjs', (err, stdout, stderr) => {
+            console.log(stdout || stderr);
+            exec('taskkill /F /IM llama-server.exe');
+            resolve({ success: true });
+        });
+    });
+}
+
+async function main() {
+    // 1. 122B-A10B: Pure GPU offload (No n-cpu-moe at all)
+    // -ngl 999 will offload all 48 layers to the NVIDIA driver (triggering Shared VRAM fallback on Windows)
+    const args122B = `--model models\\Q4_K_M\\Qwen3.5-122B-A10B-Q4_K_M-00001-of-00003.gguf -ngl 999 -c 32768 -np 1 -fa on --cache-type-k q4_0 --cache-type-v q4_0 -ub 512 -b 2048 -t 6 -tb 6 --prio 3 --fit off --port 8000 --host 0.0.0.0`;
+    await runTest(args122B, {}, "122B-A10B: Pure GPU (NVIDIA Shared Memory Fallback)");
+
+    // 2. 35B-A3B: Pure GPU tuning to hit 70 t/s
+    // Base configuration from previous full-gpu run:
+    const args35B = `--model models\\Qwen3.5-35B-A3B-Q4_K_M.gguf -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 --fit off --port 8000 --host 0.0.0.0`;
+    
+    // We already got ~64 t/s basically. 
+    // Let's try MMQ for custom matrix multiplication which is often faster on Ampere for low batch generation
+    await runTest(args35B, { GGML_CUDA_FORCE_MMQ: "1" }, "35B-A3B: Force MMQ = 1");
+    
+    // Try increasing threads to 12 just in case
+    const args35B_t12 = args35B.replace("-t 6 -tb 6", "-t 12 -tb 12");
+    await runTest(args35B_t12, { GGML_CUDA_FORCE_MMQ: "1" }, "35B-A3B: Threads 12 + MMQ");
+
+    console.log("\nALL TESTS COMPLETED");
+}
+
+main();