"""
:mod:`torch.distributed.optim` exposes DistributedOptimizer, which takes a list
of remote parameters (:class:`~torch.distributed.rpc.RRef`) and runs the
optimizer locally on the workers where the parameters live.  The distributed
optimizer can use any of the local optimizer :ref:`optimizer-algorithms` to
apply the gradients on each worker.
"""
from .optimizer import DistributedOptimizer
from .zero_redundancy_optimizer import ZeroRedundancyOptimizer