Update app.py

app.py

@@ -28,7 +28,7 @@ def download_model(repo_id, model_name):
 
 import glob
 
-subprocess.run(["pip", "install", "flash-attn", "--no-build-isolation"])
+subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
 @spaces.GPU(duration=280)
 def run_inference(prompt_text):