added gpu to GemmaLLMInterface

interface.py

@@ -5,7 +5,11 @@ from typing import Any
 import torch
 from transformers import TextIteratorStreamer
 from threading import Thread
+import spaces
 
+
+
+@spaces.GPU(duration=120)
 class GemmaLLMInterface(CustomLLM):
     model: Any
     tokenizer: Any