Test stopping criteria effectiveness

- Temporarily modify CancelStoppingCriteria to always return True
- This will test if stopping criteria are being checked during generation
- If generation stops after first token, stopping criteria work; if not, they are ignored

app.py

@@ -28,7 +28,7 @@ cancel_event = threading.Event()
 # ------------------------------
 class CancelStoppingCriteria(StoppingCriteria):
     def __call__(self, input_ids, scores, **kwargs):
-        return cancel_event.is_set()
+        return True
 
 # ------------------------------
 # Torch-Compatible Model Definitions with Adjusted Descriptions