diff --git a/vllm/v1/engine/core.py b/vllm/v1/engine/core.py index a90ffbe58b98c..bf51ebc709f96 100644 --- a/vllm/v1/engine/core.py +++ b/vllm/v1/engine/core.py @@ -330,7 +330,7 @@ class EngineCore: # Blocking until the first result is available. model_output = self.execute_model_with_error_logging( - future.result, scheduler_output) + lambda _: future.result(), scheduler_output) assert model_output is not None self.batch_queue.task_done()