Can we do autoregressive using pad_packed_sequence?

I’m curious about if we want to do the autoregressive manner. Is it possible to do with implemented using pad_packed_sequence and pack_padded_sequence input to some recurrent network? Because we need to wait for the output of timestep t. Given this scenario we cannot gather all prediction and packed them. Then what should I do with this. Is there any way to do this without looping to each time step? Also If i want to do it in batch processing is it possible?

Thank you