diff --git a/python/paddle/distributed/auto_parallel/operators/dist_flash_attn.py b/python/paddle/distributed/auto_parallel/operators/dist_flash_attn.py index 4ebfbaeae7d50b..463372f3caf03c 100644 --- a/python/paddle/distributed/auto_parallel/operators/dist_flash_attn.py +++ b/python/paddle/distributed/auto_parallel/operators/dist_flash_attn.py @@ -16,7 +16,7 @@ from ...utils.log_utils import get_logger -_logger = get_logger(logging.INFO) +_logger = get_logger(logging.INFO, __name__) from ..random import determinate_rng, is_enable_auto_rand_ctrl from .common import ( DistributedOperatorImplContainer, diff --git a/python/paddle/distributed/auto_parallel/random.py b/python/paddle/distributed/auto_parallel/random.py index 7cddbc753abf0e..59c637c151cdad 100644 --- a/python/paddle/distributed/auto_parallel/random.py +++ b/python/paddle/distributed/auto_parallel/random.py @@ -22,7 +22,7 @@ from .process_mesh import retrieve_unique_id_for_process_mesh from .static.utils import _get_idx_in_axis -_logger = get_logger(logging.INFO) +_logger = get_logger(logging.INFO, __name__) _rng_name_to_seed = {} _rng_name_to_states = {} diff --git a/python/paddle/distributed/auto_parallel/static/cluster.py b/python/paddle/distributed/auto_parallel/static/cluster.py index a2f6d60f8afd32..03860254692994 100644 --- a/python/paddle/distributed/auto_parallel/static/cluster.py +++ b/python/paddle/distributed/auto_parallel/static/cluster.py @@ -1230,7 +1230,7 @@ def __repr__(self): return self.__str__() -logger = get_logger(logging.INFO) +logger = get_logger(logging.INFO, __name__) def get_default_cluster(json_config=None, auto_config=None): diff --git a/python/paddle/distributed/auto_parallel/static/converter.py b/python/paddle/distributed/auto_parallel/static/converter.py index 43381b778f22a9..8c59ae84f17e44 100644 --- a/python/paddle/distributed/auto_parallel/static/converter.py +++ b/python/paddle/distributed/auto_parallel/static/converter.py @@ -44,7 +44,7 @@ def __init__(self, tensors_dict, pre_strategy, cur_strategy): self._tensors_dict = self._check_tensor_dict(tensors_dict) self._pre_strategy = self._check_pre_strategy(pre_strategy) self._cur_strategy = self._check_cur_strategy(cur_strategy) - self._logger = get_logger(logging.INFO) + self._logger = get_logger(logging.INFO, __name__) def _check_tensor_dict(self, tensors_dict): if not tensors_dict: diff --git a/python/paddle/distributed/auto_parallel/static/dist_saver.py b/python/paddle/distributed/auto_parallel/static/dist_saver.py index 5affea39d6b269..f88f7b1fa1a38f 100644 --- a/python/paddle/distributed/auto_parallel/static/dist_saver.py +++ b/python/paddle/distributed/auto_parallel/static/dist_saver.py @@ -52,7 +52,7 @@ def _process_path(path): class DistributedSaver: def __init__(self): - self._logger = get_logger(logging.INFO) + self._logger = get_logger(logging.INFO, __name__) def save(self, path, serial_program, dist_main_program, dist_context): def _save_state(program, path, mode="param"): diff --git a/python/paddle/distributed/auto_parallel/static/engine.py b/python/paddle/distributed/auto_parallel/static/engine.py index 5dd4ceb8ca42ff..32708f7fb39e00 100644 --- a/python/paddle/distributed/auto_parallel/static/engine.py +++ b/python/paddle/distributed/auto_parallel/static/engine.py @@ -228,7 +228,7 @@ def __init__( ) self._strategy = strategy or Strategy() - self._logger = get_logger(logging.INFO) + self._logger = get_logger(logging.INFO, __name__) # for compute cost # TODO: remove _fwd_main_progs and _orig_optimizer and _pir_main_progs diff --git a/python/paddle/distributed/auto_parallel/static/parallelizer_v2.py b/python/paddle/distributed/auto_parallel/static/parallelizer_v2.py index 2dab310b393c8f..4c702d59208430 100644 --- a/python/paddle/distributed/auto_parallel/static/parallelizer_v2.py +++ b/python/paddle/distributed/auto_parallel/static/parallelizer_v2.py @@ -51,7 +51,7 @@ def __init__(self, mode, completer, dist_context): assert self._dist_context._is_initialized self._pass_context = self._dist_context.pass_context self._strategy = self._dist_context.strategy - self._logger = get_logger(logging.INFO) + self._logger = get_logger(logging.INFO, __name__) @property def is_train(self): diff --git a/python/paddle/distributed/auto_parallel/static/planner_v2.py b/python/paddle/distributed/auto_parallel/static/planner_v2.py index 9c33d0f260aee8..abc4eb991a5159 100755 --- a/python/paddle/distributed/auto_parallel/static/planner_v2.py +++ b/python/paddle/distributed/auto_parallel/static/planner_v2.py @@ -73,7 +73,7 @@ def completer(self): return self._completer def plan(self): - logger = get_logger(logging.INFO) + logger = get_logger(logging.INFO, __name__) path = None if self._dist_context._json_config: try: diff --git a/python/paddle/distributed/auto_parallel/static/tuner/rule_based_tuner.py b/python/paddle/distributed/auto_parallel/static/tuner/rule_based_tuner.py index 50ed66bd45347b..d3dd739fd4403e 100644 --- a/python/paddle/distributed/auto_parallel/static/tuner/rule_based_tuner.py +++ b/python/paddle/distributed/auto_parallel/static/tuner/rule_based_tuner.py @@ -1056,7 +1056,7 @@ def __init__(self, dist_context, mode="train", level="o1"): self._mode = mode assert level in ["o1", "o2"] self._level = level - self._logger = get_logger(logging.INFO) + self._logger = get_logger(logging.INFO, __name__) self._use_dp = False # forward sub program diff --git a/python/paddle/distributed/fleet/meta_parallel/sharding/group_sharded_stage2.py b/python/paddle/distributed/fleet/meta_parallel/sharding/group_sharded_stage2.py index 1afbcff1d7e48e..49e92453b662b2 100644 --- a/python/paddle/distributed/fleet/meta_parallel/sharding/group_sharded_stage2.py +++ b/python/paddle/distributed/fleet/meta_parallel/sharding/group_sharded_stage2.py @@ -37,7 +37,7 @@ from .group_sharded_storage import GradStorage from .group_sharded_utils import Type, device_guard -logger_ = get_logger(logging.WARNING) +logger_ = get_logger(logging.WARNING, __name__) def _trainable(param): diff --git a/python/paddle/distributed/passes/auto_parallel_recompute.py b/python/paddle/distributed/passes/auto_parallel_recompute.py index cb4ecb9d6d62d8..421e27831cba3e 100644 --- a/python/paddle/distributed/passes/auto_parallel_recompute.py +++ b/python/paddle/distributed/passes/auto_parallel_recompute.py @@ -41,7 +41,7 @@ from ..utils.log_utils import get_logger from .pass_base import PassBase, register_pass -logger = get_logger(logging.INFO) +logger = get_logger(logging.INFO, __name__) class RecomputeState(ProgramStats): diff --git a/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_1f1b.py b/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_1f1b.py index 5a87e2863d0254..4a456415f09102 100644 --- a/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_1f1b.py +++ b/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_1f1b.py @@ -29,7 +29,7 @@ ) from .pipeline_pass_base import PipelinePassBase -logger = get_logger(logging.INFO) +logger = get_logger(logging.INFO, __name__) @register_pass("pipeline_scheduler_1F1B") diff --git a/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_eager_1f1b.py b/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_eager_1f1b.py index 27d0c6adae8407..3b9f3fde5a1ab2 100644 --- a/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_eager_1f1b.py +++ b/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_eager_1f1b.py @@ -20,7 +20,7 @@ from ..pass_base import register_pass from .pipeline_pass_base import PipelinePassBase -logger = get_logger(logging.INFO) +logger = get_logger(logging.INFO, __name__) @register_pass("pipeline_scheduler_Eager1F1B") diff --git a/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_fthenb.py b/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_fthenb.py index 7cbbf8e481ff69..4bd1e17563c213 100644 --- a/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_fthenb.py +++ b/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_fthenb.py @@ -23,7 +23,7 @@ ) from .pipeline_pass_base import PipelinePassBase -logger = get_logger(logging.INFO) +logger = get_logger(logging.INFO, __name__) @register_pass("pipeline_scheduler_FThenB") diff --git a/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_pass_base.py b/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_pass_base.py index 061b38ed5a0aeb..55eb62325890cf 100644 --- a/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_pass_base.py +++ b/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_pass_base.py @@ -23,7 +23,7 @@ set_skip_gc_vars, ) -logger = get_logger(logging.INFO) +logger = get_logger(logging.INFO, __name__) class PipelinePassBase(PassBase): diff --git a/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_vpp.py b/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_vpp.py index d11c61d834df98..8744a1691091c9 100644 --- a/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_vpp.py +++ b/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_vpp.py @@ -31,7 +31,7 @@ ) from .pipeline_pass_base import PipelinePassBase -logger = get_logger(logging.INFO) +logger = get_logger(logging.INFO, __name__) @register_pass("pipeline_scheduler_VPP") diff --git a/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_zero_bubble.py b/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_zero_bubble.py index 733d454ec9af4f..498e8e230631e2 100644 --- a/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_zero_bubble.py +++ b/python/paddle/distributed/passes/pipeline_scheduler_pass/pipeline_zero_bubble.py @@ -21,7 +21,7 @@ from ..pass_base import register_pass from .pipeline_pass_base import PipelinePassBase -logger = get_logger(logging.INFO) +logger = get_logger(logging.INFO, __name__) class PipelineZeroBubbleBase(PipelinePassBase): diff --git a/python/paddle/distributed/sharding/group_sharded.py b/python/paddle/distributed/sharding/group_sharded.py index 7f4d25d24b318f..94ac8b90bf23a7 100644 --- a/python/paddle/distributed/sharding/group_sharded.py +++ b/python/paddle/distributed/sharding/group_sharded.py @@ -44,7 +44,7 @@ from paddle.distributed.communication.group import Group from paddle.nn import Layer -logger_ = get_logger(logging.WARNING) +logger_ = get_logger(logging.WARNING, __name__) def group_sharded_parallel( diff --git a/python/paddle/distributed/utils/launch_utils.py b/python/paddle/distributed/utils/launch_utils.py index a9d52da552dc5d..c6a02e3a02bffa 100644 --- a/python/paddle/distributed/utils/launch_utils.py +++ b/python/paddle/distributed/utils/launch_utils.py @@ -26,7 +26,7 @@ from ..utils.log_utils import get_logger -logger = get_logger("INFO", "root") +logger = get_logger("INFO", __name__) def get_cluster_from_args(args, selected_gpus): diff --git a/python/paddle/distributed/utils/log_utils.py b/python/paddle/distributed/utils/log_utils.py index 2d7ffbffba4953..9fec4457c9c38b 100644 --- a/python/paddle/distributed/utils/log_utils.py +++ b/python/paddle/distributed/utils/log_utils.py @@ -15,7 +15,7 @@ import logging -def get_logger(log_level, name="root"): +def get_logger(log_level, name): logger = logging.getLogger(name) # Avoid printing multiple logs diff --git a/python/paddle/distributed/utils/process_utils.py b/python/paddle/distributed/utils/process_utils.py index 9e71a758a2f089..f6c7325c4edaab 100644 --- a/python/paddle/distributed/utils/process_utils.py +++ b/python/paddle/distributed/utils/process_utils.py @@ -19,7 +19,7 @@ import paddle from paddle.distributed.utils.log_utils import get_logger -logger = get_logger("INFO", "root") +logger = get_logger("INFO", __name__) SUCCESS_CODE = 0 FAIL_CODE = 1