update utils.py

vllm/v1/attention/backends/utils.py

@@ -18,7 +18,6 @@ if TYPE_CHECKING:
     from vllm.attention.backends.abstract import AttentionImpl
     from vllm.v1.core.sched.output import SchedulerOutput
     from vllm.v1.worker.gpu_input_batch import InputBatch
-    from vllm.v1.attention.backends.mla.common import MLACommonMetadataBuilder
 
 import vllm.envs as envs
 from vllm.attention.backends.abstract import AttentionBackend
@@ -631,7 +630,6 @@ def reorder_batch_to_split_decodes_and_prefills(
     input_batch: "InputBatch",
     scheduler_output: "SchedulerOutput",
     decode_threshold: int = 1,
-    # num_scheduled_tokens_np: np.ndarray = np.zeros(256, dtype=np.int32),
 ) -> bool:
     """
     Reorders the batch to split into prefill and decode requests; places all