Update app.py

app.py

@@ -6,14 +6,14 @@ from threading import Thread
 import gradio as gr
 from gradio import FileData
 import time
-import spaces
+#import spaces
 ckpt = "meta-llama/Llama-3.2-11B-Vision-Instruct"
 model = MllamaForConditionalGeneration.from_pretrained(ckpt,
     torch_dtype=torch.bfloat16).to("cuda")
 processor = AutoProcessor.from_pretrained(ckpt)
 
 
-@spaces.GPU
+#@spaces.GPU
 def bot_streaming(message, history, max_new_tokens=250):
     
     txt = message["text"]