github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-03 01:55:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

[legacy] clean up legacy code (#4743)

Browse Source 
* [legacy] remove outdated codes of pipeline (#4692)

* [legacy] remove cli of benchmark and update optim (#4690)

* [legacy] remove cli of benchmark and update optim

* [doc] fix cli doc test

* [legacy] fix engine clip grad norm

* [legacy] remove outdated colo tensor (#4694)

* [legacy] remove outdated colo tensor

* [test] fix test import

* [legacy] move outdated zero to legacy (#4696)

* [legacy] clean up utils (#4700)

* [legacy] clean up utils

* [example] update examples

* [legacy] clean up amp

* [legacy] fix amp module

* [legacy] clean up gpc (#4742)

* [legacy] clean up context

* [legacy] clean core, constants and global vars

* [legacy] refactor initialize

* [example] fix examples ci

* [example] fix examples ci

* [legacy] fix tests

* [example] fix gpt example

* [example] fix examples ci

* [devops] fix ci installation

* [example] fix examples ci
This commit is contained in:
Hongxin Liu
2023-09-18 16:31:06 +08:00
committed by GitHub
parent 32e7f99416
commit b5f9e37c70
342 changed files with 2919 additions and 4182 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/language/gpt/titans/model/embed.py
View File

@@ -6,8 +6,8 @@ from torch import nn as nn
from torch.nn import functional as F
from torch.nn.parameter import Parameter
from colossalai.context import ParallelMode, seed
from colossalai.core import global_context as gpc
from colossalai.legacy.context import ParallelMode, seed
from colossalai.legacy.core import global_context as gpc
from colossalai.legacy.nn.layer.base_layer import ParallelLayer
from colossalai.legacy.nn.layer.parallel_1d._utils import gather_forward_split_backward, reduce_grad, reduce_input
from colossalai.legacy.nn.layer.parallel_1d.layers import Linear1D_Row

4
examples/language/gpt/titans/model/gpt1d.py
View File

@@ -9,13 +9,13 @@ from torch import nn as nn
from colossalai import kernel
from colossalai import nn as col_nn
from colossalai.core import global_context as gpc
from colossalai.kernel.cuda_native.scaled_softmax import AttnMaskType
from colossalai.legacy.core import global_context as gpc
from colossalai.legacy.nn.layer import Linear1D_Col, Linear1D_Row
from colossalai.legacy.nn.layer.base_layer import ParallelLayer
from colossalai.legacy.nn.layer.utils import ACT2FN, divide
from colossalai.legacy.utils.activation_checkpoint import checkpoint
from colossalai.utils import checkpoint
from colossalai.utils.activation_checkpoint import checkpoint
__all__ = [
'GPTMLP1D', 'GPTSelfAttention1D', 'GPTTransformerLayer1D', 'FusedGPTSelfAttention1D', 'FusedGPTTransformerLayer1D'

6
examples/language/gpt/titans/model/pipeline_gpt1d.py
View File

@@ -7,11 +7,11 @@ import torch.nn as nn
from colossalai import kernel
from colossalai import nn as col_nn
from colossalai.context.parallel_mode import ParallelMode
from colossalai.core import global_context as gpc
from colossalai.legacy.context.parallel_mode import ParallelMode
from colossalai.legacy.core import global_context as gpc
from colossalai.legacy.nn.layer.wrapper import PipelineSharedModuleWrapper
from colossalai.legacy.pipeline.utils import partition_uniform
from colossalai.logging import get_dist_logger
from colossalai.pipeline.utils import partition_uniform
from .embed import HiddenParallelEmbedding, HiddenParallelGPTLMHead1D, VocabParallelEmbedding, VocabParallelGPTLMHead1D
from .gpt1d import FusedGPTTransformerLayer1D, GPTTransformerLayer1D

6
examples/language/gpt/titans/train_gpt.py
View File

@@ -8,14 +8,14 @@ from titans.model.gpt import GPTLMLoss
import colossalai
import colossalai.utils as utils
from colossalai.context.parallel_mode import ParallelMode
from colossalai.core import global_context as gpc
from colossalai.legacy.context.parallel_mode import ParallelMode
from colossalai.legacy.core import global_context as gpc
from colossalai.legacy.trainer import Trainer, hooks
from colossalai.legacy.zero.init_ctx import ZeroInitContext
from colossalai.logging import disable_existing_loggers, get_dist_logger
from colossalai.nn import LinearWarmupLR
from colossalai.utils import colo_set_process_memory_fraction, is_using_pp
from colossalai.utils.timer import MultiTimer
from colossalai.zero.legacy.init_ctx import ZeroInitContext
def calc_local_model_size(model: torch.nn.Module):