Update inference.py

inference.py

@@ -10,6 +10,7 @@ import os
 import requests
 import time
 from pathlib import Path
+from spaces import GPU
 
 # Check CUDA availability
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
@@ -165,7 +166,7 @@ class GenerativeInferenceModel:
         # Store the model for future use
         self.models[model_type] = model
         return model
-    
+    @GPU
     def inference(self, image, model_type, config):
         # Load model if not already loaded
         model = self.load_model(model_type)