lightning/pytorch_lightning/plugins/__init__.py

76 lines
3.5 KiB
Python
Raw Normal View History

from pathlib import Path
from typing import Union
from pytorch_lightning.plugins.environments import ClusterEnvironment
2021-08-13 16:35:31 +00:00
from pytorch_lightning.plugins.io.checkpoint_plugin import CheckpointIO
from pytorch_lightning.plugins.io.torch_plugin import TorchCheckpointIO
from pytorch_lightning.plugins.io.xla_plugin import XLACheckpointIO
from pytorch_lightning.plugins.plugins_registry import ( # noqa: F401
call_training_type_register_plugins,
TrainingTypePluginsRegistry,
)
from pytorch_lightning.plugins.precision.apex_amp import ApexMixedPrecisionPlugin
from pytorch_lightning.plugins.precision.deepspeed_precision import DeepSpeedPrecisionPlugin
from pytorch_lightning.plugins.precision.double import DoublePrecisionPlugin
from pytorch_lightning.plugins.precision.fully_sharded_native_amp import FullyShardedNativeMixedPrecisionPlugin
from pytorch_lightning.plugins.precision.ipu_precision import IPUPrecisionPlugin
from pytorch_lightning.plugins.precision.native_amp import NativeMixedPrecisionPlugin
from pytorch_lightning.plugins.precision.precision_plugin import PrecisionPlugin
from pytorch_lightning.plugins.precision.sharded_native_amp import ShardedNativeMixedPrecisionPlugin
from pytorch_lightning.plugins.precision.tpu import TPUPrecisionPlugin
from pytorch_lightning.plugins.precision.tpu_bf16 import TPUBf16PrecisionPlugin
from pytorch_lightning.plugins.training_type.ddp import DDPPlugin
from pytorch_lightning.plugins.training_type.ddp2 import DDP2Plugin
from pytorch_lightning.plugins.training_type.ddp_spawn import DDPSpawnPlugin
from pytorch_lightning.plugins.training_type.deepspeed import DeepSpeedPlugin
from pytorch_lightning.plugins.training_type.dp import DataParallelPlugin
from pytorch_lightning.plugins.training_type.fully_sharded import DDPFullyShardedPlugin
from pytorch_lightning.plugins.training_type.horovod import HorovodPlugin
from pytorch_lightning.plugins.training_type.ipu import IPUPlugin
from pytorch_lightning.plugins.training_type.parallel import ParallelPlugin
from pytorch_lightning.plugins.training_type.sharded import DDPShardedPlugin
from pytorch_lightning.plugins.training_type.sharded_spawn import DDPSpawnShardedPlugin
from pytorch_lightning.plugins.training_type.single_device import SingleDevicePlugin
from pytorch_lightning.plugins.training_type.single_tpu import SingleTPUPlugin
from pytorch_lightning.plugins.training_type.tpu_spawn import TPUSpawnPlugin
from pytorch_lightning.plugins.training_type.training_type_plugin import TrainingTypePlugin
Hardware specific parts of Accelerator Refactoring (#5719) * add basic accelerator class. Co-Authored with @awaelchi * pep8 Co-authored-by: @awaelchi * add cpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add gpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add accelerator connector Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single device training Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single tpu Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu spawn Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * make on_colab_kaggle utility func * add basic accelerator class. Co-Authored with @awaelchi * pep8 Co-authored-by: @awaelchi * add cpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add gpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add accelerator connector Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single device training Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single tpu Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu spawn Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * make on_colab_kaggle utility func * fixes * move * yapf * . * . * . * flake8 * sync accelerator connector changes from dev1.2 * changelog * fix tpu handling * tpu * aval * yapf * Update pytorch_lightning/plugins/training_type/tpu_spawn.py Co-authored-by: chaton <thomas@grid.ai> * Update pytorch_lightning/accelerators/accelerator_connector.py Co-authored-by: chaton <thomas@grid.ai> * Update pytorch_lightning/plugins/training_type/tpu_spawn.py Co-authored-by: chaton <thomas@grid.ai> * Update tpu_spawn.py * Update pytorch_lightning/accelerators/accelerator_connector.py Co-authored-by: chaton <thomas@grid.ai> * indentation Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> Co-authored-by: Jirka Borovec <jirka.borovec@seznam.cz> Co-authored-by: chaton <thomas@grid.ai>
2021-02-01 13:34:59 +00:00
PLUGIN = Union[TrainingTypePlugin, PrecisionPlugin, ClusterEnvironment, CheckpointIO]
PLUGIN_INPUT = Union[PLUGIN, str]
Hardware specific parts of Accelerator Refactoring (#5719) * add basic accelerator class. Co-Authored with @awaelchi * pep8 Co-authored-by: @awaelchi * add cpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add gpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add accelerator connector Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single device training Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single tpu Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu spawn Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * make on_colab_kaggle utility func * add basic accelerator class. Co-Authored with @awaelchi * pep8 Co-authored-by: @awaelchi * add cpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add gpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add accelerator connector Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single device training Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single tpu Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu spawn Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * make on_colab_kaggle utility func * fixes * move * yapf * . * . * . * flake8 * sync accelerator connector changes from dev1.2 * changelog * fix tpu handling * tpu * aval * yapf * Update pytorch_lightning/plugins/training_type/tpu_spawn.py Co-authored-by: chaton <thomas@grid.ai> * Update pytorch_lightning/accelerators/accelerator_connector.py Co-authored-by: chaton <thomas@grid.ai> * Update pytorch_lightning/plugins/training_type/tpu_spawn.py Co-authored-by: chaton <thomas@grid.ai> * Update tpu_spawn.py * Update pytorch_lightning/accelerators/accelerator_connector.py Co-authored-by: chaton <thomas@grid.ai> * indentation Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> Co-authored-by: Jirka Borovec <jirka.borovec@seznam.cz> Co-authored-by: chaton <thomas@grid.ai>
2021-02-01 13:34:59 +00:00
__all__ = [
2021-08-13 16:35:31 +00:00
"CheckpointIO",
"TorchCheckpointIO",
"XLACheckpointIO",
Hardware specific parts of Accelerator Refactoring (#5719) * add basic accelerator class. Co-Authored with @awaelchi * pep8 Co-authored-by: @awaelchi * add cpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add gpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add accelerator connector Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single device training Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single tpu Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu spawn Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * make on_colab_kaggle utility func * add basic accelerator class. Co-Authored with @awaelchi * pep8 Co-authored-by: @awaelchi * add cpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add gpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add accelerator connector Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single device training Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single tpu Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu spawn Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * make on_colab_kaggle utility func * fixes * move * yapf * . * . * . * flake8 * sync accelerator connector changes from dev1.2 * changelog * fix tpu handling * tpu * aval * yapf * Update pytorch_lightning/plugins/training_type/tpu_spawn.py Co-authored-by: chaton <thomas@grid.ai> * Update pytorch_lightning/accelerators/accelerator_connector.py Co-authored-by: chaton <thomas@grid.ai> * Update pytorch_lightning/plugins/training_type/tpu_spawn.py Co-authored-by: chaton <thomas@grid.ai> * Update tpu_spawn.py * Update pytorch_lightning/accelerators/accelerator_connector.py Co-authored-by: chaton <thomas@grid.ai> * indentation Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> Co-authored-by: Jirka Borovec <jirka.borovec@seznam.cz> Co-authored-by: chaton <thomas@grid.ai>
2021-02-01 13:34:59 +00:00
"ApexMixedPrecisionPlugin",
"DataParallelPlugin",
"DDP2Plugin",
"DDPPlugin",
"DDPSpawnPlugin",
FSDP with full state dict (#7487) * Fix some test errors Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: * checkpoint consolidation * Update ddp_spawn.py * Update test_metric_result_integration.py * Update test_results.py * Update utils.py * Update utils.py * Update test_all_gather_grad.py * Update test_all_gather_grad.py * Update test_results.py * Revert "Update test_results.py" This reverts commit 9d4a2b891d2a4b37e21529a444bda1883d1b5ed1. * Revert "Merge pull request #1 from shuyingsunshine21/shuyingsunshine21-checkpoint_consolidate" This reverts commit c5053da789f9d04d2c967a65adf4fb026dc134b8, reversing changes made to 0d23d75bc91e4e0b7805712e394cb093fac22841. * Revert "Update test_all_gather_grad.py" This reverts commit 0d23d75bc91e4e0b7805712e394cb093fac22841. * Revert "Update utils.py" This reverts commit 70fe5da9c66ceff2fcf4be5b9efdd23a9af8389c. * Revert "Update utils.py" This reverts commit a9aae99f6ed6e9388ecf1d8a7bd79966176a65af. * Revert "Update test_results.py" This reverts commit ea749068785bbad689a12066544893b1605f20c5. * Revert "Update test_metric_result_integration.py" This reverts commit bf70e431b3ce4893de804e0f3b5d59e79346d6d7. * Revert "Update ddp_spawn.py" This reverts commit f17210183b84f90c9a62d1ff9b3e05e1fbe5f33b. * Revert "checkpoint consolidation" This reverts commit 536c1323b0e6715fb5919196ea48b0fcddddcd66. * Revert "Revert "checkpoint consolidation"" This reverts commit 3a9fde915ad4c69620a6ccc411f5890cb38ba5ac. * Revert "Revert "Revert "checkpoint consolidation""" This reverts commit 7a369f47e1a94d701fce48c994cc3f2da266dad0. * Revert "Revert "Update ddp_spawn.py"" This reverts commit 8222dc98ead37d961a52b7366070aa10f66d92d1. * Revert "Revert "Update test_metric_result_integration.py"" This reverts commit 6c095b2370a2afe9d24918a5798ce1ebffed7e0d. * Revert "Revert "Update test_results.py"" This reverts commit 250d0aaaa2e6c6a6a3407bc6c8b83c0fe2479c0b. * Revert "Revert "Update utils.py"" This reverts commit 8651d54d79396eaaba16d7eb1e769a1e91d5702e. * Revert "Revert "Update test_all_gather_grad.py"" This reverts commit dcdcd29731061c919b15ab0b56669259817a81c4. * modify distributed environment to make test pass * fix version for ddp plugin test * fix * fix * changelog * Update CHANGELOG.md * fsdp with full state dict * fix missing import * modify unitest * fix * fix * fix typo * modify test and add changelog * fix * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * limit max_epoch to 1 for testing * test * fix * update * testing remove special for multi gpu * assert gpu * add assertion for gpu * fix * Re-enable special test, use ModelCheckpoint * Fix paths * Fix path passing * test * test * fix test * fix * pre-commit format * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci Co-authored-by: Carlos Mocholí <carlossmocholi@gmail.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: SeanNaren <sean@grid.ai>
2021-05-24 07:11:45 +00:00
"DDPFullyShardedPlugin",
DeepSpeed Integration (#5954) * Add initial deepspeed changes * Address code review * Move static method outside of function * Fixes * Add missing annotation * Remove seed setting * Doc changes * Doc changes, add address reviews * Fix docs * Try fixing issue by moving to torch adam * Clean up check * Changes, better APIs! * Add wrapper, swap to git install revision * Add special test * Add warning * Address review * Add better disclaimer * Turn off ZeRO for testing due to compilation * Add description on modifying parameters via the plugin * Doc strings clear * Small doc fixes * Fix hash, reduce test * Added CI change * Move to azure pipeline * Fix test name * Add missing flag * Remove sudo... * Try conda instead * Swap to conda base * Try suggested install * Apply suggestions from code review * Apply suggestions from code review * Revert "Apply suggestions from code review" This reverts commit 41cca05a * Revert "Apply suggestions from code review" This reverts commit e06ec29e * Remove setter * Address most review * Move out function, remove DeepSpeed from requirements * Install deepspeed/mpi4py within container * Use special tests, move to master commit for deepspeed * Export path * Force compile to happen first * Remove! * Debugging ninja * Fix error in optimizer step logic * Attempt to fix symbolic link * Reverse to aid debugging * Export path again * Clean up mess * var * Revert "var" This reverts commit 3450eaca * Address review, add todo * Add note about unsupported functionality Co-authored-by: Jirka Borovec <Borda@users.noreply.github.com> Co-authored-by: tchaton <thomas@grid.ai> Co-authored-by: Jirka Borovec <jirka.borovec@seznam.cz>
2021-02-17 20:23:42 +00:00
"DeepSpeedPlugin",
"DeepSpeedPrecisionPlugin",
"DoublePrecisionPlugin",
Hardware specific parts of Accelerator Refactoring (#5719) * add basic accelerator class. Co-Authored with @awaelchi * pep8 Co-authored-by: @awaelchi * add cpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add gpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add accelerator connector Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single device training Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single tpu Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu spawn Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * make on_colab_kaggle utility func * add basic accelerator class. Co-Authored with @awaelchi * pep8 Co-authored-by: @awaelchi * add cpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add gpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add accelerator connector Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single device training Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single tpu Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu spawn Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * make on_colab_kaggle utility func * fixes * move * yapf * . * . * . * flake8 * sync accelerator connector changes from dev1.2 * changelog * fix tpu handling * tpu * aval * yapf * Update pytorch_lightning/plugins/training_type/tpu_spawn.py Co-authored-by: chaton <thomas@grid.ai> * Update pytorch_lightning/accelerators/accelerator_connector.py Co-authored-by: chaton <thomas@grid.ai> * Update pytorch_lightning/plugins/training_type/tpu_spawn.py Co-authored-by: chaton <thomas@grid.ai> * Update tpu_spawn.py * Update pytorch_lightning/accelerators/accelerator_connector.py Co-authored-by: chaton <thomas@grid.ai> * indentation Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> Co-authored-by: Jirka Borovec <jirka.borovec@seznam.cz> Co-authored-by: chaton <thomas@grid.ai>
2021-02-01 13:34:59 +00:00
"HorovodPlugin",
IPU Integration 5/5 (#7867) * Initial changes * Add broken example for now * Fix reference * Fix format * Code runs * Fixes * Clear up files * Add tests, helpers, fixes * Small cleanups * Refactors based on review * Swap to special tests * Add special tests * Add source * Cleanups * Add logic to attach/detach model from devices * Fixes for tests * Fixes for tests * Move earlier * Cleanups * Add check for nvcc * Add tests, cleanups * Fix errors * fix * Try condition * Add missing annotation * Clearer * Clearer message * Fix variable * Cleanups * Add comment * CHANGELOG.md * Add simple selection test * Remove special=True to see what happens * Fix test * Update tests/accelerators/test_ipu.py Co-authored-by: Kaushik B <45285388+kaushikb11@users.noreply.github.com> * Convert ipu_cores -> ipus * Add typing, fail earlier * simplify precision * Add test, add helper * fix accum * Update pytorch_lightning/plugins/training_type/ipu.py Co-authored-by: thomas chaton <thomas@grid.ai> * Use stages * Make sure warning message returned * thorw error * Add more tests, use fs * add comment * Clean * Address feedback, add IPU tests * Fixes * Fix signature * Add types * Remove autoround * Add docstring * ipu_cores -> ipus * Add test, remove unnecessary precision set * Add optimizer test * Add precision back with test * Address code review * Change to probs * Move some of the asserts earlier Co-authored-by: Kaushik B <45285388+kaushikb11@users.noreply.github.com> Co-authored-by: thomas chaton <thomas@grid.ai>
2021-06-11 15:07:04 +00:00
"IPUPlugin",
"IPUPrecisionPlugin",
Hardware specific parts of Accelerator Refactoring (#5719) * add basic accelerator class. Co-Authored with @awaelchi * pep8 Co-authored-by: @awaelchi * add cpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add gpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add accelerator connector Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single device training Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single tpu Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu spawn Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * make on_colab_kaggle utility func * add basic accelerator class. Co-Authored with @awaelchi * pep8 Co-authored-by: @awaelchi * add cpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add gpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add accelerator connector Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single device training Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single tpu Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu spawn Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * make on_colab_kaggle utility func * fixes * move * yapf * . * . * . * flake8 * sync accelerator connector changes from dev1.2 * changelog * fix tpu handling * tpu * aval * yapf * Update pytorch_lightning/plugins/training_type/tpu_spawn.py Co-authored-by: chaton <thomas@grid.ai> * Update pytorch_lightning/accelerators/accelerator_connector.py Co-authored-by: chaton <thomas@grid.ai> * Update pytorch_lightning/plugins/training_type/tpu_spawn.py Co-authored-by: chaton <thomas@grid.ai> * Update tpu_spawn.py * Update pytorch_lightning/accelerators/accelerator_connector.py Co-authored-by: chaton <thomas@grid.ai> * indentation Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> Co-authored-by: Jirka Borovec <jirka.borovec@seznam.cz> Co-authored-by: chaton <thomas@grid.ai>
2021-02-01 13:34:59 +00:00
"NativeMixedPrecisionPlugin",
"PrecisionPlugin",
"ShardedNativeMixedPrecisionPlugin",
"FullyShardedNativeMixedPrecisionPlugin",
Hardware specific parts of Accelerator Refactoring (#5719) * add basic accelerator class. Co-Authored with @awaelchi * pep8 Co-authored-by: @awaelchi * add cpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add gpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add accelerator connector Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single device training Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single tpu Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu spawn Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * make on_colab_kaggle utility func * add basic accelerator class. Co-Authored with @awaelchi * pep8 Co-authored-by: @awaelchi * add cpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add gpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add accelerator connector Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single device training Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single tpu Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu spawn Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * make on_colab_kaggle utility func * fixes * move * yapf * . * . * . * flake8 * sync accelerator connector changes from dev1.2 * changelog * fix tpu handling * tpu * aval * yapf * Update pytorch_lightning/plugins/training_type/tpu_spawn.py Co-authored-by: chaton <thomas@grid.ai> * Update pytorch_lightning/accelerators/accelerator_connector.py Co-authored-by: chaton <thomas@grid.ai> * Update pytorch_lightning/plugins/training_type/tpu_spawn.py Co-authored-by: chaton <thomas@grid.ai> * Update tpu_spawn.py * Update pytorch_lightning/accelerators/accelerator_connector.py Co-authored-by: chaton <thomas@grid.ai> * indentation Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> Co-authored-by: Jirka Borovec <jirka.borovec@seznam.cz> Co-authored-by: chaton <thomas@grid.ai>
2021-02-01 13:34:59 +00:00
"SingleDevicePlugin",
"SingleTPUPlugin",
"TPUPrecisionPlugin",
"TPUBf16PrecisionPlugin",
Hardware specific parts of Accelerator Refactoring (#5719) * add basic accelerator class. Co-Authored with @awaelchi * pep8 Co-authored-by: @awaelchi * add cpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add gpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add accelerator connector Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single device training Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single tpu Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu spawn Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * make on_colab_kaggle utility func * add basic accelerator class. Co-Authored with @awaelchi * pep8 Co-authored-by: @awaelchi * add cpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add gpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add accelerator connector Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single device training Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single tpu Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu spawn Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * make on_colab_kaggle utility func * fixes * move * yapf * . * . * . * flake8 * sync accelerator connector changes from dev1.2 * changelog * fix tpu handling * tpu * aval * yapf * Update pytorch_lightning/plugins/training_type/tpu_spawn.py Co-authored-by: chaton <thomas@grid.ai> * Update pytorch_lightning/accelerators/accelerator_connector.py Co-authored-by: chaton <thomas@grid.ai> * Update pytorch_lightning/plugins/training_type/tpu_spawn.py Co-authored-by: chaton <thomas@grid.ai> * Update tpu_spawn.py * Update pytorch_lightning/accelerators/accelerator_connector.py Co-authored-by: chaton <thomas@grid.ai> * indentation Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> Co-authored-by: Jirka Borovec <jirka.borovec@seznam.cz> Co-authored-by: chaton <thomas@grid.ai>
2021-02-01 13:34:59 +00:00
"TPUSpawnPlugin",
FSDP with full state dict (#7487) * Fix some test errors Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: * checkpoint consolidation * Update ddp_spawn.py * Update test_metric_result_integration.py * Update test_results.py * Update utils.py * Update utils.py * Update test_all_gather_grad.py * Update test_all_gather_grad.py * Update test_results.py * Revert "Update test_results.py" This reverts commit 9d4a2b891d2a4b37e21529a444bda1883d1b5ed1. * Revert "Merge pull request #1 from shuyingsunshine21/shuyingsunshine21-checkpoint_consolidate" This reverts commit c5053da789f9d04d2c967a65adf4fb026dc134b8, reversing changes made to 0d23d75bc91e4e0b7805712e394cb093fac22841. * Revert "Update test_all_gather_grad.py" This reverts commit 0d23d75bc91e4e0b7805712e394cb093fac22841. * Revert "Update utils.py" This reverts commit 70fe5da9c66ceff2fcf4be5b9efdd23a9af8389c. * Revert "Update utils.py" This reverts commit a9aae99f6ed6e9388ecf1d8a7bd79966176a65af. * Revert "Update test_results.py" This reverts commit ea749068785bbad689a12066544893b1605f20c5. * Revert "Update test_metric_result_integration.py" This reverts commit bf70e431b3ce4893de804e0f3b5d59e79346d6d7. * Revert "Update ddp_spawn.py" This reverts commit f17210183b84f90c9a62d1ff9b3e05e1fbe5f33b. * Revert "checkpoint consolidation" This reverts commit 536c1323b0e6715fb5919196ea48b0fcddddcd66. * Revert "Revert "checkpoint consolidation"" This reverts commit 3a9fde915ad4c69620a6ccc411f5890cb38ba5ac. * Revert "Revert "Revert "checkpoint consolidation""" This reverts commit 7a369f47e1a94d701fce48c994cc3f2da266dad0. * Revert "Revert "Update ddp_spawn.py"" This reverts commit 8222dc98ead37d961a52b7366070aa10f66d92d1. * Revert "Revert "Update test_metric_result_integration.py"" This reverts commit 6c095b2370a2afe9d24918a5798ce1ebffed7e0d. * Revert "Revert "Update test_results.py"" This reverts commit 250d0aaaa2e6c6a6a3407bc6c8b83c0fe2479c0b. * Revert "Revert "Update utils.py"" This reverts commit 8651d54d79396eaaba16d7eb1e769a1e91d5702e. * Revert "Revert "Update test_all_gather_grad.py"" This reverts commit dcdcd29731061c919b15ab0b56669259817a81c4. * modify distributed environment to make test pass * fix version for ddp plugin test * fix * fix * changelog * Update CHANGELOG.md * fsdp with full state dict * fix missing import * modify unitest * fix * fix * fix typo * modify test and add changelog * fix * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * limit max_epoch to 1 for testing * test * fix * update * testing remove special for multi gpu * assert gpu * add assertion for gpu * fix * Re-enable special test, use ModelCheckpoint * Fix paths * Fix path passing * test * test * fix test * fix * pre-commit format * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci Co-authored-by: Carlos Mocholí <carlossmocholi@gmail.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: SeanNaren <sean@grid.ai>
2021-05-24 07:11:45 +00:00
"TrainingTypePlugin",
"ParallelPlugin",
"DDPShardedPlugin",
"DDPSpawnShardedPlugin",
Hardware specific parts of Accelerator Refactoring (#5719) * add basic accelerator class. Co-Authored with @awaelchi * pep8 Co-authored-by: @awaelchi * add cpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add gpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add accelerator connector Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single device training Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single tpu Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu spawn Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * make on_colab_kaggle utility func * add basic accelerator class. Co-Authored with @awaelchi * pep8 Co-authored-by: @awaelchi * add cpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add gpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu accelerator Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add accelerator connector Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single device training Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add single tpu Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * add tpu spawn Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> * make on_colab_kaggle utility func * fixes * move * yapf * . * . * . * flake8 * sync accelerator connector changes from dev1.2 * changelog * fix tpu handling * tpu * aval * yapf * Update pytorch_lightning/plugins/training_type/tpu_spawn.py Co-authored-by: chaton <thomas@grid.ai> * Update pytorch_lightning/accelerators/accelerator_connector.py Co-authored-by: chaton <thomas@grid.ai> * Update pytorch_lightning/plugins/training_type/tpu_spawn.py Co-authored-by: chaton <thomas@grid.ai> * Update tpu_spawn.py * Update pytorch_lightning/accelerators/accelerator_connector.py Co-authored-by: chaton <thomas@grid.ai> * indentation Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com> Co-authored-by: Jirka Borovec <jirka.borovec@seznam.cz> Co-authored-by: chaton <thomas@grid.ai>
2021-02-01 13:34:59 +00:00
]
FILE_ROOT = Path(__file__).parent
TRAINING_TYPE_BASE_MODULE = "pytorch_lightning.plugins.training_type"
call_training_type_register_plugins(FILE_ROOT, TRAINING_TYPE_BASE_MODULE)