Update app.py

app.py

@@ -39,7 +39,7 @@ ckpt = "google/gemma-3-4b-it"
 model = Gemma3ForConditionalGeneration.from_pretrained(ckpt, torch_dtype=torch.bfloat16).to("cuda")
 processor = AutoProcessor.from_pretrained(ckpt)
 
-@spaces.GPU
+@spaces.GPU(duration=duration)
 def bot_streaming(message, history, max_new_tokens=250):
     
     txt = message["text"]