diff --git a/vllm/v1/worker/gpu_worker.py b/vllm/v1/worker/gpu_worker.py
index e02a22093b29b..9e7e44d068612 100644
--- a/vllm/v1/worker/gpu_worker.py
+++ b/vllm/v1/worker/gpu_worker.py
@@ -328,7 +328,6 @@ class Worker(WorkerBase):
                 sort_by="self_cuda_time_total"))
 
     def execute_dummy_batch(self) -> None:
-        # TODO: adding allow_microbatching will break non-gpu backends
         self.model_runner._dummy_run(1)
 
     def add_lora(self, lora_request: LoRARequest) -> bool: