File size: 2,362 Bytes
9c6594c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 |
# Copyright The Lightning AI team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import logging
import os
from typing_extensions import override
from lightning_fabric.plugins.environments.cluster_environment import ClusterEnvironment
log = logging.getLogger(__name__)
class KubeflowEnvironment(ClusterEnvironment):
"""Environment for distributed training using the `PyTorchJob`_ operator from `Kubeflow`_.
This environment, unlike others, does not get auto-detected and needs to be passed to the Fabric/Trainer
constructor manually.
.. _PyTorchJob: https://www.kubeflow.org/docs/components/trainer/legacy-v1/user-guides/pytorch/
.. _Kubeflow: https://www.kubeflow.org
"""
@property
@override
def creates_processes_externally(self) -> bool:
return True
@property
@override
def main_address(self) -> str:
return os.environ["MASTER_ADDR"]
@property
@override
def main_port(self) -> int:
return int(os.environ["MASTER_PORT"])
@staticmethod
@override
def detect() -> bool:
raise NotImplementedError("The Kubeflow environment can't be detected automatically.")
@override
def world_size(self) -> int:
return int(os.environ["WORLD_SIZE"])
@override
def set_world_size(self, size: int) -> None:
log.debug("KubeflowEnvironment.set_world_size was called, but setting world size is not allowed. Ignored.")
@override
def global_rank(self) -> int:
return int(os.environ["RANK"])
@override
def set_global_rank(self, rank: int) -> None:
log.debug("KubeflowEnvironment.set_global_rank was called, but setting global rank is not allowed. Ignored.")
@override
def local_rank(self) -> int:
return 0
@override
def node_rank(self) -> int:
return self.global_rank()
|