Does FasterTransformer support multi-stream pipeline parallelism ?

[FlyingPotatoZ]

Hello guys: Because there is no dependence on computation and communication, I think multi-stream pipeline parallelism can hide communication time to improve performance. I didn't find how to configure the multi-stream feature in the code. Can anyone help? Thank you so much~ ftNcclRecv(sequence_lengths_ + id_offset, local_batch_size * beam_width, pipeline_para_.world_size_ - 1, pipeline_para_, stream_);