Update app.py

app.py

@@ -27,14 +27,7 @@ tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased-distilled-squ
 # Set model to evaluation mode
 model.eval()
 
-# Compile the model with torch.compile for faster inference (PyTorch 2.0+)
-# Use backend="inductor" for CPU optimization
-try:
-    model = torch.compile(model, backend="inductor")
-except Exception as e:
-    print(f"Warning: torch.compile failed with error: {str(e)}. Proceeding without compilation.")
-
-# Apply quantization to the model for additional speedup on CPU
+# Apply quantization to the model for faster inference on CPU
 model = torch.quantization.quantize_dynamic(
     model, {torch.nn.Linear}, dtype=torch.qint8
 )