[BugFix] Spec decode with VLLM_ENABLE_V1_MULTIPROCESSING=0 (#30319)

Signed-off-by: Chen Zhang <zhangch99@outlook.com>

vllm/v1/engine/core_client.py

@@ -268,7 +268,8 @@ class InprocClient(EngineCoreClient):
         self.engine_core = EngineCore(*args, **kwargs)
 
     def get_output(self) -> EngineCoreOutputs:
-        outputs, _ = self.engine_core.step_fn()
+        outputs, model_executed = self.engine_core.step_fn()
+        self.engine_core.post_step(model_executed=model_executed)
         return outputs and outputs.get(0) or EngineCoreOutputs()
 
     def get_supported_tasks(self) -> tuple[SupportedTask, ...]: