Update app.py

app.py

@@ -1,5 +1,12 @@
 import spaces
 
+# Install flash attention, skipping CUDA build if necessary
+subprocess.run(
+    "pip install flash-attn --no-build-isolation",
+    env={"FLASH_ATTENTION_SKIP_CUDA_BUILD": "TRUE"},
+    shell=True,
+)
+
 import os
 import time