addressed Jareds comments

                              temperature=1.0,

                              add_BOS=False,

                              use_eod_token_for_early_termination=True):

    """Run inferecne and post-process outputs, i.e., detokenize,

    """Run inference and post-process outputs, i.e., detokenize,

    move to cpu and convert to list."""

    # Main inference.

                                                max_sequence_len)

        # Pipelining arguments.

        args = get_args()

        self.pipeline_size_larger_than_one = args.pipeline_model_parallel_size

        self.pipeline_size_larger_than_one = (

            args.pipeline_model_parallel_size > 1)

        # Threshold of pipelining.

        self.pipelining_batch_x_seqlen = \

            args.inference_batch_times_seqlen_threshold