mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-10-21 23:02:07 +00:00
5a560a060a
* add zero1 (#209) * add zero1 * add test zero1 * update zero stage 1 develop (#212) * Implement naive zero3 (#240) * naive zero3 works well * add zero3 param manager * add TODOs in comments * add gather full param ctx * fix sub module streams * add offload * fix bugs of hook and add unit tests * fix bugs of hook and add unit tests (#252) * add gather full param ctx * fix sub module streams * add offload * fix bugs of hook and add unit tests * polish code and add state dict hook * fix bug * update unit test * refactor reconstructed zero code * clip_grad support zero3 and add unit test * add unit test for Zero3ParameterManager * [WIP] initialize the shard param class * [WIP] Yet another sharded model implementation (#274) * [WIP] initialize the shard param class * [WIP] Yes another implementation of shardModel. Using a better hook method. * torch.concat -> torch.cat * fix test_zero_level_1.py::test_zero_level_1 unitest * remove deepspeed implementation and refactor for the reconstructed zero module * polish zero dp unittests Co-authored-by: ver217 <lhx0217@gmail.com> Co-authored-by: Frank Lee <somerlee.9@gmail.com>
25 lines
1.5 KiB
Python
25 lines
1.5 KiB
Python
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_moe_parallel_parameter, is_no_pp_or_last_stage,
|
|
is_tp_rank_0, 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
|
|
from .memory import report_memory_usage
|
|
from .timer import MultiTimer, Timer
|
|
|
|
__all__ = [
|
|
'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', 'is_moe_parallel_parameter'
|
|
]
|