diff --git a/vllm/executor/neuron_executor.py b/vllm/executor/neuron_executor.py
index 53107dada9962..6b2cb3e2403f2 100644
--- a/vllm/executor/neuron_executor.py
+++ b/vllm/executor/neuron_executor.py
@@ -70,6 +70,22 @@ class NeuronExecutor(ExecutorBase):
     def list_loras(self) -> Set[int]:
         return self.driver_worker.list_loras()
 
+    def add_prompt_adapter(self, prompt_adapter_request) -> bool:
+        raise NotImplementedError(
+            "Soft prompt is currently not supported by the Neuron backend.")
+
+    def remove_prompt_adapter(self, prompt_adapter_id: int) -> bool:
+        raise NotImplementedError(
+            "Soft prompt is currently not supported by the Neuron backend.")
+
+    def pin_prompt_adapter(self, prompt_adapter_id: int) -> bool:
+        raise NotImplementedError(
+            "Soft prompt is currently not supported by the Neuron backend.")
+
+    def list_prompt_adapters(self) -> Set[int]:
+        raise NotImplementedError(
+            "Soft prompt is currently not supported by the Neuron backend.")
+
     def check_health(self) -> None:
         # NeuronExecutor will always be healthy as long as
         # it's running.