print hw info

app.py

@@ -7,6 +7,8 @@ from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM, AutoMo
 
 
 torch_device = "cuda" if torch.cuda.is_available() else "cpu"
+print("Running on device:", torch_device)
+print("CPU threads:", torch.get_num_threads())
 
 
 @lru_cache(maxsize=1)  # only cache the latest model