Update app.py

app.py

@@ -12,11 +12,6 @@ import time
 import urllib.parse
 
 # Attempt to install flash-attn
-try:
-    subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, check=True, shell=True)
-except subprocess.CalledProcessError as e:
-    print(f"Error installing flash-attn: {e}")
-    print("Continuing without flash-attn.")
 
 # Determine the device to use
 device = "cuda" if torch.cuda.is_available() else "cpu"