Add dual GPU support with web UI selector

Features:
- Built custom ROCm container for AMD RX 6800 GPU
- Added GPU selection toggle in web UI (NVIDIA/AMD)
- Unified model names across both GPUs for seamless switching
- Vision model always uses NVIDIA GPU (optimal performance)
- Text models (llama3.1, darkidol) can use either GPU
- Added /gpu-status and /gpu-select API endpoints
- Implemented GPU state persistence in memory/gpu_state.json

Technical details:
- Multi-stage Dockerfile.llamaswap-rocm with ROCm 6.2.4
- llama.cpp compiled with GGML_HIP=ON for gfx1030 (RX 6800)
- Proper GPU permissions without root (groups 187/989)
- AMD container on port 8091, NVIDIA on port 8090
- Updated bot/utils/llm.py with get_current_gpu_url() and get_vision_gpu_url()
- Modified bot/utils/image_handling.py to always use NVIDIA for vision
- Enhanced web UI with GPU selector button (blue=NVIDIA, red=AMD)

Files modified:
- docker-compose.yml (added llama-swap-amd service)
- bot/globals.py (added LLAMA_AMD_URL)
- bot/api.py (added GPU selection endpoints and helper function)
- bot/utils/llm.py (GPU routing for text models)
- bot/utils/image_handling.py (GPU routing for vision models)
- bot/static/index.html (GPU selector UI)
- llama-swap-rocm-config.yaml (unified model names)

New files:
- Dockerfile.llamaswap-rocm
- bot/memory/gpu_state.json
- bot/utils/gpu_router.py (load balancing utility)
- setup-dual-gpu.sh (setup verification script)
- DUAL_GPU_*.md (documentation files)

bot/utils/gpu_preload.py

@@ -0,0 +1,69 @@
+"""
+GPU Model Preloading Utility
+Preloads models on AMD GPU to take advantage of 16GB VRAM
+"""
+import aiohttp
+import asyncio
+import json
+import globals
+
+async def preload_amd_models():
+    """
+    Preload both text and vision models on AMD GPU
+    Since AMD RX 6800 has 16GB VRAM, we can keep both loaded simultaneously
+    """
+    print("🔧 Preloading models on AMD GPU...")
+    
+    # Preload text model
+    try:
+        async with aiohttp.ClientSession() as session:
+            payload = {
+                "model": "llama3.1",
+                "messages": [{"role": "user", "content": "Hi"}],
+                "max_tokens": 1
+            }
+            async with session.post(
+                f"{globals.LLAMA_AMD_URL}/v1/chat/completions",
+                json=payload,
+                timeout=aiohttp.ClientTimeout(total=60)
+            ) as response:
+                if response.status == 200:
+                    print("✅ Text model (llama3.1) preloaded on AMD GPU")
+                else:
+                    print(f"⚠️ Text model preload returned status {response.status}")
+    except Exception as e:
+        print(f"⚠️ Failed to preload text model on AMD: {e}")
+    
+    # Preload vision model
+    try:
+        async with aiohttp.ClientSession() as session:
+            # Create a minimal test image (1x1 white pixel)
+            import base64
+            test_image = "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mP8z8DwHwAFBQIAX8jx0gAAAABJRU5ErkJggg=="
+            
+            payload = {
+                "model": "vision",
+                "messages": [
+                    {
+                        "role": "user",
+                        "content": [
+                            {"type": "text", "text": "What do you see?"},
+                            {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{test_image}"}}
+                        ]
+                    }
+                ],
+                "max_tokens": 1
+            }
+            async with session.post(
+                f"{globals.LLAMA_AMD_URL}/v1/chat/completions",
+                json=payload,
+                timeout=aiohttp.ClientTimeout(total=120)
+            ) as response:
+                if response.status == 200:
+                    print("✅ Vision model preloaded on AMD GPU")
+                else:
+                    print(f"⚠️ Vision model preload returned status {response.status}")
+    except Exception as e:
+        print(f"⚠️ Failed to preload vision model on AMD: {e}")
+    
+    print("✅ AMD GPU preload complete - both models ready")