Fix Dockerfile CMD to start uvicorn server instead of inference script

Dockerfile

@@ -21,7 +21,7 @@ USER appuser
 # Expose port if needed (for server apps)
 EXPOSE 7860
 
-# Default command: run your inference
-CMD ["python", "inference.py"]
+# Start the FastAPI server
+CMD ["uvicorn", "server.app:app", "--host", "0.0.0.0", "--port", "7860"]