fix: multi-Step current stream fix

Author: wonderful199082

vllm_ascend/worker/multi_step_runner.py

@@ -14,7 +14,7 @@
 from vllm.model_executor.model_loader.tensorizer import TensorizerConfig
 from vllm.sequence import (CompletionSequenceGroupOutput, IntermediateTensors,
                            Logprob, SequenceGroupMetadata, SequenceOutput)
-from vllm.utils import current_stream
+from vllm_ascend.utils import current_stream
 from vllm.worker.model_runner_base import (
     _init_attn_metadata_from_tensor_dict,
     _init_frozen_model_input_from_tensor_dict,