revert

Signed-off-by: Lucas Wilkinson <[email protected]>

Author: LucasWilkinson

vllm/v1/worker/gpu_model_runner.py

@@ -2826,7 +2826,7 @@ def execute_model(
                         # returns True. before returning early here we call
                         # dummy run to ensure coordinate_batch_across_dp
                         # is called into to avoid out of sync issues.
-                        self._dummy_run(self._get_num_input_tokens(1))
+                        self._dummy_run(1)
                     if not has_kv_transfer_group():
                         # Return empty ModelRunnerOutput if no work to do.
                         return EMPTY_MODEL_RUNNER_OUTPUT