Update app.py

app.py

@@ -12,6 +12,10 @@ import subprocess
 # Install necessary packages
 subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
+torch.backends.cudnn.deterministic = True
+torch.backends.cudnn.benchmark = False
+torch.backends.cuda.matmul.allow_tf32 = True
+
 # Initialize Llama Cleaner model
 device = 'cuda' if torch.cuda.is_available() else 'cpu'