diff --git a/tensorrt_llm/_torch/auto_deploy/shim/ad_executor.py b/tensorrt_llm/_torch/auto_deploy/shim/ad_executor.py
index 6cee4311beec..b272740deab4 100644
--- a/tensorrt_llm/_torch/auto_deploy/shim/ad_executor.py
+++ b/tensorrt_llm/_torch/auto_deploy/shim/ad_executor.py
@@ -494,6 +494,11 @@ def __init__(
         else:
             self.max_total_draft_tokens = 0
 
+        # ADEngine skips PyTorchModelEngine.__init__, so set the spec-decode
+        # flags that shared PyExecutor code expects on a ModelEngine.
+        self.is_spec_decode = self.spec_config is not None
+        self.enable_spec_decode = self.is_spec_decode
+
         # For compatibility with PyTorchModelEngine utilities
         self.batch_size = cache_seq_interface.info.max_batch_size