diff --git a/python/sglang/srt/model_executor/breakable_cuda_graph_runner.py b/python/sglang/srt/model_executor/breakable_cuda_graph_runner.py
index 31206ce3c932..69426f29f359 100644
--- a/python/sglang/srt/model_executor/breakable_cuda_graph_runner.py
+++ b/python/sglang/srt/model_executor/breakable_cuda_graph_runner.py
@@ -122,12 +122,17 @@ def __init__(self, model_runner: ModelRunner):
         language_model = getattr(
             model_runner.model, "language_model", model_runner.model
         )
-        self.layer_model = (
-            language_model.model
-            if hasattr(language_model, "model")
-            and hasattr(language_model.model, "layers")
-            else language_model
-        )
+        if hasattr(language_model, "model") and hasattr(language_model.model, "layers"):
+            self.layer_model = language_model.model
+        else:
+            # If we can't find the inner layer_model, disable BCG.
+            self.layer_model = None
+            logger.warning(
+                "[BCG] Could not resolve inner layer_model on %s. BCG is "
+                "disabled for this model; prefill will fall back to eager.",
+                type(language_model).__name__,
+            )
+            return
 
         # Memory pool
         if get_global_graph_memory_pool() is None:
@@ -330,6 +335,8 @@ def _capture_all(self):
                 self.output_buffers[num_tokens] = output
 
     def can_run(self, forward_batch: "ForwardBatch"):
+        if self.layer_model is None:
+            return False
         if forward_batch.forward_mode.is_target_verify():
             return False
         if forward_batch.input_embeds is not None: