disable cascade_attn

vllm/config.py

@@ -326,7 +326,7 @@ class ModelConfig:
     """Whether to disable sliding window. If True, we will disable the sliding
     window functionality of the model, capping to sliding window size. If the
     model does not support sliding window, this argument is ignored."""
-    disable_cascade_attn: bool = False
+    disable_cascade_attn: bool = True
     """Disable cascade attention for V1. While cascade attention does not
     change the mathematical correctness, disabling it could be useful for
     preventing potential numerical issues. Note that even if this is set to