Shortcuts

Source code for pytorch_lightning.plugins.environments.kubeflow_environment

# Copyright The PyTorch Lightning 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 pytorch_lightning.plugins.environments.cluster_environment import ClusterEnvironment

log = logging.getLogger(__name__)


[docs]class KubeflowEnvironment(ClusterEnvironment): """Environment for distributed training using the `PyTorchJob`_ operator from `Kubeflow`_ .. _PyTorchJob: https://www.kubeflow.org/docs/components/training/pytorch/ .. _Kubeflow: https://www.kubeflow.org """
[docs] @staticmethod def is_using_kubeflow() -> bool: """Returns ``True`` if the current process was launched using Kubeflow PyTorchJob.""" required_env_vars = ("KUBERNETES_PORT", "MASTER_ADDR", "MASTER_PORT", "WORLD_SIZE", "RANK") # torchelastic sets these. Make sure we're not in torchelastic excluded_env_vars = ("GROUP_RANK", "LOCAL_RANK", "LOCAL_WORLD_SIZE") return all(v in os.environ for v in required_env_vars) and not any(v in os.environ for v in excluded_env_vars)
@property def creates_processes_externally(self) -> bool: return True
[docs] def master_address(self) -> str: return os.environ["MASTER_ADDR"]
[docs] def master_port(self) -> int: return int(os.environ["MASTER_PORT"])
[docs] def world_size(self) -> int: return int(os.environ["WORLD_SIZE"])
def set_world_size(self, size: int) -> None: log.debug("KubeflowEnvironment.set_world_size was called, but setting world size is not allowed. Ignored.")
[docs] def global_rank(self) -> int: return int(os.environ["RANK"])
def set_global_rank(self, rank: int) -> None: log.debug("KubeflowEnvironment.set_global_rank was called, but setting global rank is not allowed. Ignored.")
[docs] def local_rank(self) -> int: return 0
[docs] def node_rank(self) -> int: return self.global_rank()

© Copyright Copyright (c) 2018-2022, William Falcon et al... Revision ab1c2ff2.

Built with Sphinx using a theme provided by Read the Docs.
Read the Docs v: stable
Versions
latest
stable
1.5.9
1.5.8
1.5.7
1.5.6
1.5.5
1.5.4
1.5.3
1.5.2
1.5.1
1.5.0
1.4.9
1.4.8
1.4.7
1.4.6
1.4.5
1.4.4
1.4.3
1.4.2
1.4.1
1.4.0
1.3.8
1.3.7
1.3.6
1.3.5
1.3.4
1.3.3
1.3.2
1.3.1
1.3.0
1.2.10
1.2.8
1.2.7
1.2.6
1.2.5
1.2.4
1.2.3
1.2.2
1.2.1
1.2.0
1.1.8
1.1.7
1.1.6
1.1.5
1.1.4
1.1.3
1.1.2
1.1.1
1.1.0
1.0.8
1.0.7
1.0.6
1.0.5
1.0.4
1.0.3
1.0.2
1.0.1
1.0.0
0.10.0
0.9.0
0.8.5
0.8.4
0.8.3
0.8.2
0.8.1
0.8.0
0.7.6
0.7.5
0.7.4
0.7.3
0.7.2
0.7.1
0.7.0
0.6.0
0.5.3
0.4.9
ipynb-update
docs-search
Downloads
html
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.