github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-13 21:22:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

adapted for sequence parallel (#163)

Browse Source
This commit is contained in:
Frank Lee
2022-01-20 13:44:51 +08:00
committed by GitHub
parent a2e649da39
commit e2089c5c15
17 changed files with 432 additions and 119 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
colossalai/utils/__init__.py
View File

@@ -1,8 +1,8 @@
from .activation_checkpoint import checkpoint
from .common import (clip_grad_norm_fp32, conditional_context, copy_tensor_parallel_attributes, count_zeros_fp32,
free_port, is_dp_rank_0, is_model_parallel_parameter, is_no_pp_or_last_stage, is_tp_rank_0,
is_using_ddp, is_using_pp, multi_tensor_applier, param_is_not_tensor_parallel_duplicate,
print_rank_0, switch_virtual_pipeline_parallel_rank, sync_model_param_in_dp)
is_using_ddp, is_using_pp, is_using_sequence, multi_tensor_applier, param_is_not_tensor_parallel_duplicate,
print_rank_0, switch_virtual_pipeline_parallel_rank, sync_model_param)
from .cuda import empty_cache, get_current_device, set_to_cuda, synchronize
from .data_sampler import DataParallelSampler, get_dataloader
from .gradient_accumulation import accumulate_gradient
@@ -10,9 +10,9 @@ from .memory import report_memory_usage
from .timer import MultiTimer, Timer
__all__ = [
'checkpoint', 'free_port', 'print_rank_0', 'sync_model_param_in_dp', 'is_dp_rank_0', 'is_tp_rank_0',
'is_no_pp_or_last_stage', 'is_using_ddp', 'is_using_pp', 'conditional_context', 'is_model_parallel_parameter',
'clip_grad_norm_fp32', 'count_zeros_fp32', 'copy_tensor_parallel_attributes',
'checkpoint', 'free_port', 'print_rank_0', 'sync_model_param', 'is_dp_rank_0', 'is_tp_rank_0',
'is_no_pp_or_last_stage', 'is_using_ddp', 'is_using_pp', 'is_using_sequence', 'conditional_context',
'is_model_parallel_parameter', 'clip_grad_norm_fp32', 'count_zeros_fp32', 'copy_tensor_parallel_attributes',
'param_is_not_tensor_parallel_duplicate', 'get_current_device', 'synchronize', 'empty_cache', 'set_to_cuda',
'report_memory_usage', 'Timer', 'MultiTimer', 'multi_tensor_applier', 'accumulate_gradient', 'DataParallelSampler',
'get_dataloader', 'switch_virtual_pipeline_parallel_rank'