update gradio

app.py

@@ -5,6 +5,7 @@ dotenv.load_dotenv(override=True)
 import subprocess
 subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
+import spaces
 import gradio as gr
 
 import os
@@ -43,7 +44,7 @@ def load_pipeline(accelerator, weight_dtype, args):
         pipeline = pipeline.to(accelerator.device)
     return pipeline
 
-
+@spaces.GPU(duration=180)
 def run(
     instruction,
     width_input,