torch.compile()

app.py

@@ -17,6 +17,7 @@ model_name = "google/madlad400-3b-mt"
 tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
 model = AutoModelForSeq2SeqLM.from_pretrained(
     model_name, device_map="auto", torch_dtype=torch.float16)
+model = torch.compile(model)
 
 #
 # Translate given input text in given target language