Use in `AllGatherv` in `mpi_allgather`

[mrava87]

So far the mpi_allgather method uses the _prepare_allgather_inputs method to prepare inputs such that they are all of the same size (via zero-padding). Whilst this is strictly needed for NCCL, we should instead consider leveraging MPI `AllGatherv' instead to avoid extra padding and cutting of arrays.