Update app.py

app.py

@@ -6,6 +6,8 @@ import time
 from PIL import Image
 import torch
 import spaces
+import subprocess
+subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
 tokenizer = AutoTokenizer.from_pretrained(
     'qnguyen3/nanoLLaVA',