diff --git a/vllm/model_executor/layers/ple_offload_layer.py b/vllm/model_executor/layers/ple_offload_layer.py
index ff581b205a..cc8bd73bfe 100644
--- a/vllm/model_executor/layers/ple_offload_layer.py
+++ b/vllm/model_executor/layers/ple_offload_layer.py
@@ -428,7 +428,21 @@ class PleOffloadLayer(nn.Module, ABC):
         self._host_output_ptr = host_output_ptr
         self._host_row_bytes = int(host_row_bytes)
         if host_output_ptr is not None:
-            _PULL_LAYERS[self._ple_offload_name] = self
+            # Hardening: the registry key is the name the
+            # traced graph carries, so it must be a real, unique layer name.
+            name = self._ple_offload_name
+            if name == "<unbound>":
+                raise RuntimeError(
+                    "PLE pull: setup_cross_process_offload on a layer with no "
+                    "_ple_offload_name; the op would resolve nothing by name"
+                )
+            prior = _PULL_LAYERS.get(name)
+            if prior is not None and prior is not self:
+                raise RuntimeError(
+                    f"PLE pull: two layers armed under the name {name!r}; the op "
+                    "would resolve the wrong layer's pointers"
+                )
+            _PULL_LAYERS[name] = self
 
     def forward(
         self,