Add GPU support and improve Docker deployment

- Add GPU deployment support with NVIDIA runtime
  - Update Dockerfile.allinone with GPU environment variables
  - Add comprehensive GPU_DEPLOYMENT.md guide

- Make port 11434 (Ollama) optional for security
  - Update DEPLOYMENT.md with CPU and GPU deployment options
  - Simplify default docker run commands
  - Update healthcheck to only check web application

- Add memory requirements documentation
  - Create MEMORY_REQUIREMENTS.md with model comparison
  - Add build-8b.sh script for lower memory usage
  - Document OOM troubleshooting steps

- Improve Docker build process
  - Add BUILD_TROUBLESHOOTING.md for common issues
  - Add DISTRIBUTION.md for image distribution methods
  - Update .gitignore to exclude large binary files
  - Improve docker-entrypoint.sh with better diagnostics

- Update .dockerignore to include ollama-linux-amd64.tgz
- Add backup file exclusions to .gitignore

build-allinone.sh

@@ -15,12 +15,18 @@ echo "=========================================="
 echo ""
 echo "This will create a Docker image containing:"
 echo "  - Python application"
-echo "  - Ollama service"
+echo "  - Ollama service (v0.13.1)"
 echo "  - qwen3:14b model"
 echo "  - qwen3-embedding:4b model"
 echo ""
+echo "Target platform: linux/amd64 (x86_64)"
+echo ""
 echo "WARNING: The final image will be 10-20GB in size!"
 echo ""
+echo "NOTE: If you're building on Apple Silicon (M1/M2/M3),"
+echo "      Docker will use emulation which may be slower."
+echo "      The image will still work on x86_64 servers."
+echo ""
 
 # Check if ollama-models directory exists
 if [ ! -d "ollama-models" ]; then
@@ -33,6 +39,19 @@ fi
 echo "✓ Found ollama-models directory"
 echo ""
 
+# Check if Ollama binary exists
+if [ ! -f "ollama-linux-amd64.tgz" ]; then
+    echo "ERROR: ollama-linux-amd64.tgz not found!"
+    echo ""
+    echo "Please download it first:"
+    echo "  curl -L -o ollama-linux-amd64.tgz https://github.com/ollama/ollama/releases/download/v0.13.1/ollama-linux-amd64.tgz"
+    echo ""
+    exit 1
+fi
+
+echo "✓ Found ollama-linux-amd64.tgz"
+echo ""
+
 # Check disk space
 AVAILABLE_SPACE=$(df -h . | awk 'NR==2 {print $4}')
 echo "Available disk space: $AVAILABLE_SPACE"
@@ -50,7 +69,12 @@ echo ""
 echo "=========================================="
 echo "Building Docker image..."
 echo "=========================================="
-docker build -f Dockerfile.allinone -t ${IMAGE_NAME}:${IMAGE_TAG} .
+echo "Platform: linux/amd64 (x86_64)"
+echo "This may take 20-40 minutes depending on your machine..."
+echo ""
+
+# Build for amd64 platform explicitly
+docker build --platform linux/amd64 -f Dockerfile.allinone -t ${IMAGE_NAME}:${IMAGE_TAG} .
 
 echo ""
 echo "=========================================="
@@ -83,14 +107,25 @@ echo "2. On target server, load the image:"
 echo "   docker load -i ${EXPORT_FILE}"
 echo ""
 echo "3. Run the container:"
+echo ""
+echo "   CPU mode:"
 echo "   docker run -d \\"
 echo "     --name system-prompt-optimizer \\"
 echo "     -p 8010:8010 \\"
-echo "     -p 11434:11434 \\"
-echo "     -v \$(pwd)/outputs:/app/outputs \\"
 echo "     --restart unless-stopped \\"
 echo "     ${IMAGE_NAME}:${IMAGE_TAG}"
 echo ""
+echo "   GPU mode (recommended if NVIDIA GPU available):"
+echo "   docker run -d \\"
+echo "     --name system-prompt-optimizer \\"
+echo "     --gpus all \\"
+echo "     -p 8010:8010 \\"
+echo "     --restart unless-stopped \\"
+echo "     ${IMAGE_NAME}:${IMAGE_TAG}"
+echo ""
+echo "   Note: Port 11434 (Ollama) is optional and only needed for debugging."
+echo "   GPU mode provides 5-10x faster inference. See GPU_DEPLOYMENT.md for details."
+echo ""
 echo "4. Access the application:"
 echo "   http://<server-ip>:8010/ui/opro.html"
 echo ""