add torch.compile

app.py

@@ -42,6 +42,7 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 config = AutoConfig.from_pretrained("nvidia/quality-classifier-deberta")
 tokenizer = AutoTokenizer.from_pretrained("nvidia/quality-classifier-deberta")
 model = QualityModel.from_pretrained("nvidia/quality-classifier-deberta").to(device)
+model = torch.compile(model)
 model.eval()