2021-10-28 16:21:23 +00:00
|
|
|
#!/usr/bin/env python
|
|
|
|
# -*- encoding: utf-8 -*-
|
|
|
|
|
|
|
|
ALLOWED_MODES = [None, '1d', '2d', '2.5d', '3d', 'sequence']
|
2021-12-29 15:32:10 +00:00
|
|
|
TENSOR_PARALLEL_MODE = 'tensor_parallel_mode'
|
2021-10-28 16:21:23 +00:00
|
|
|
|
2022-05-26 00:45:08 +00:00
|
|
|
# initializer
|
2021-10-28 16:21:23 +00:00
|
|
|
INITIALIZER_MAPPING = {
|
|
|
|
'data': 'Initializer_Data',
|
|
|
|
'tensor': 'Initializer_Tensor',
|
|
|
|
'pipeline': 'Initializer_Pipeline',
|
|
|
|
'embedding': 'Initializer_Embedding',
|
|
|
|
'1d': 'Initializer_1D',
|
|
|
|
'2d': 'Initializer_2D',
|
|
|
|
'2.5d': 'Initializer_2p5D',
|
|
|
|
'3d': 'Initializer_3D',
|
2021-12-30 07:56:46 +00:00
|
|
|
'sequence': 'Initializer_Sequence',
|
2022-01-07 07:08:36 +00:00
|
|
|
'model': 'Initializer_Model',
|
|
|
|
'moe': 'Initializer_Moe'
|
2021-10-28 16:21:23 +00:00
|
|
|
}
|
|
|
|
|
2022-02-14 03:15:02 +00:00
|
|
|
# 3D parallelism groups
|
|
|
|
INPUT_GROUP_3D = 'input_group_3d'
|
|
|
|
WEIGHT_GROUP_3D = 'weight_group_3d'
|
|
|
|
OUTPUT_GROUP_3D = 'output_group_3d'
|
2022-10-26 12:54:39 +00:00
|
|
|
INPUT_X_WEIGHT_3D = 'input_x_weight_group_3d'
|
|
|
|
OUTPUT_X_WEIGHT_3D = 'output_x_weight_group_3d'
|
2021-12-29 15:32:10 +00:00
|
|
|
|
2022-03-09 15:35:41 +00:00
|
|
|
# Attributes of tensor parallel parameters
|
2021-10-28 16:21:23 +00:00
|
|
|
IS_TENSOR_PARALLEL = 'is_tensor_parallel'
|
Develop/experiments (#59)
* Add gradient accumulation, fix lr scheduler
* fix FP16 optimizer and adapted torch amp with tensor parallel (#18)
* fixed bugs in compatibility between torch amp and tensor parallel and performed some minor fixes
* fixed trainer
* Revert "fixed trainer"
This reverts commit 2e0b0b76990e8d4e337add483d878c0f61cf5097.
* improved consistency between trainer, engine and schedule (#23)
Co-authored-by: 1SAA <c2h214748@gmail.com>
* Split conv2d, class token, positional embedding in 2d, Fix random number in ddp
Fix convergence in cifar10, Imagenet1000
* Integrate 1d tensor parallel in Colossal-AI (#39)
* fixed 1D and 2D convergence (#38)
* optimized 2D operations
* fixed 1D ViT convergence problem
* Feature/ddp (#49)
* remove redundancy func in setup (#19) (#20)
* use env to control the language of doc (#24) (#25)
* Support TP-compatible Torch AMP and Update trainer API (#27)
* Add gradient accumulation, fix lr scheduler
* fix FP16 optimizer and adapted torch amp with tensor parallel (#18)
* fixed bugs in compatibility between torch amp and tensor parallel and performed some minor fixes
* fixed trainer
* Revert "fixed trainer"
This reverts commit 2e0b0b76990e8d4e337add483d878c0f61cf5097.
* improved consistency between trainer, engine and schedule (#23)
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: ver217 <lhx0217@gmail.com>
* add an example of ViT-B/16 and remove w_norm clipping in LAMB (#29)
* add explanation for ViT example (#35) (#36)
* support torch ddp
* fix loss accumulation
* add log for ddp
* change seed
* modify timing hook
Co-authored-by: Frank Lee <somerlee.9@gmail.com>
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: binmakeswell <binmakeswell@gmail.com>
* Feature/pipeline (#40)
* remove redundancy func in setup (#19) (#20)
* use env to control the language of doc (#24) (#25)
* Support TP-compatible Torch AMP and Update trainer API (#27)
* Add gradient accumulation, fix lr scheduler
* fix FP16 optimizer and adapted torch amp with tensor parallel (#18)
* fixed bugs in compatibility between torch amp and tensor parallel and performed some minor fixes
* fixed trainer
* Revert "fixed trainer"
This reverts commit 2e0b0b76990e8d4e337add483d878c0f61cf5097.
* improved consistency between trainer, engine and schedule (#23)
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: ver217 <lhx0217@gmail.com>
* add an example of ViT-B/16 and remove w_norm clipping in LAMB (#29)
* add explanation for ViT example (#35) (#36)
* optimize communication of pipeline parallel
* fix grad clip for pipeline
Co-authored-by: Frank Lee <somerlee.9@gmail.com>
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: binmakeswell <binmakeswell@gmail.com>
* optimized 3d layer to fix slow computation ; tested imagenet performance with 3d; reworked lr_scheduler config definition; fixed launch args; fixed some printing issues; simplified apis of 3d layers (#51)
* Update 2.5d layer code to get a similar accuracy on imagenet-1k dataset
* update api for better usability (#58)
update api for better usability
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: ver217 <lhx0217@gmail.com>
Co-authored-by: puck_WCR <46049915+WANG-CR@users.noreply.github.com>
Co-authored-by: binmakeswell <binmakeswell@gmail.com>
Co-authored-by: アマデウス <kurisusnowdeng@users.noreply.github.com>
Co-authored-by: BoxiangW <45734921+BoxiangW@users.noreply.github.com>
2021-12-09 07:08:29 +00:00
|
|
|
NUM_PARTITIONS = 'num_partitions'
|
|
|
|
TENSOR_PARALLEL_ATTRIBUTES = [IS_TENSOR_PARALLEL, NUM_PARTITIONS]
|