Update config.py

Change the inference device for Mac to accelerate inference and reduce memory leak

config.py

@@ -20,7 +20,7 @@ python_exec = sys.executable or "python"
 if torch.cuda.is_available():
     infer_device = "cuda"
 elif torch.backends.mps.is_available():
-    infer_device = "mps"
+    infer_device = "cpu"
 else:
     infer_device = "cpu"