Update app.py

app.py

@@ -22,7 +22,7 @@ os.environ['USE_FLASH_ATTENTION'] = '1'
 
 import torch
 
-torch.set_float32_matmul_precision('high')
+torch.set_float32_matmul_precision('medium')
 torch.backends.cuda.matmul.allow_tf32 = True # allow tf32 on matmul
 torch.backends.cudnn.allow_tf32 = True # allow tf32 on cudnn
 torch.backends.cuda.enable_mem_efficient_sdp(True)