mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-05-28 01:53:37 +00:00
* 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 commit2e0b0b7699
. * 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 commit2e0b0b7699
. * 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 commit2e0b0b7699
. * 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>
36 lines
901 B
Python
36 lines
901 B
Python
#!/usr/bin/env python
|
|
# -*- encoding: utf-8 -*-
|
|
|
|
ALLOWED_MODES = [None, '1d', '2d', '2.5d', '3d', 'sequence']
|
|
|
|
# intializer
|
|
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',
|
|
'sequence': 'Initializer_Sequence'
|
|
}
|
|
|
|
# 2D paralllel
|
|
SUMMA_DIM = 'SUMMA_DIM'
|
|
|
|
# 2.5D paralllel
|
|
TESSERACT_DIM = 'TESSERACT_DIM'
|
|
TESSERACT_DEP = 'TESSERACT_DEP'
|
|
|
|
# 3D parallel
|
|
DEPTH_3D = 'DEPTH_3D'
|
|
INPUT_GROUP_3D = 'PARALLEL_3D_INPUT'
|
|
WEIGHT_GROUP_3D = 'PARALLEL_3D_WEIGHT'
|
|
OUTPUT_GROUP_3D = 'PARALLEL_3D_OUTPUT'
|
|
|
|
# Tensor parallel attributes
|
|
IS_TENSOR_PARALLEL = 'is_tensor_parallel'
|
|
NUM_PARTITIONS = 'num_partitions'
|
|
TENSOR_PARALLEL_ATTRIBUTES = [IS_TENSOR_PARALLEL, NUM_PARTITIONS]
|