github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-21 01:24:04 +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* [legacy] remove outdated codes of pipeline (#4692)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* [legacy] remove outdated colo tensor (#4694)

* [legacy] remove outdated colo tensor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* [legacy] move outdated zero to legacy (#4696)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

20
tests/test_legacy/test_engine/test_engine.py
View File

@@ -1,8 +1,8 @@
import pytest
import colossalai
from colossalai.amp import AMP_TYPE
from colossalai.core import global_context as gpc
from colossalai.legacy.amp import AMP_TYPE
from colossalai.legacy.core import global_context as gpc
from colossalai.testing import parameterize, rerun_if_address_is_in_use, spawn
from tests.components_to_test.registry import non_distributed_component_funcs
@@ -20,10 +20,11 @@ def run_train(model_name, amp_mode):
model_builder, train_dataloader, _, optimizer_class, criterion = get_components_func()
model = model_builder(checkpoint=False)
engine, train_dataloader, *args = colossalai.initialize(model=model,
optimizer=optimizer_class(model.parameters(), lr=1e-3),
criterion=criterion,
train_dataloader=train_dataloader)
engine, train_dataloader, *args = colossalai.legacy.initialize(model=model,
optimizer=optimizer_class(model.parameters(),
lr=1e-3),
criterion=criterion,
train_dataloader=train_dataloader)
try:
engine.train()
@@ -48,7 +49,12 @@ def run_train(model_name, amp_mode):
def run_engine(rank, world_size, port):
# init dist env
colossalai.launch(config=CONFIG, rank=rank, world_size=world_size, host='localhost', port=port, backend='nccl')
colossalai.legacy.launch(config=CONFIG,
rank=rank,
world_size=world_size,
host='localhost',
port=port,
backend='nccl')
run_train()

19
tests/test_legacy/test_engine/test_gradient_accumluation.py
View File

@@ -10,10 +10,10 @@ from torchvision.datasets import CIFAR10
from torchvision.models import resnet18
import colossalai
from colossalai.core import global_context as gpc
from colossalai.legacy.core import global_context as gpc
from colossalai.legacy.utils import get_dataloader
from colossalai.logging import get_dist_logger
from colossalai.testing import rerun_if_address_is_in_use, spawn
from colossalai.utils import get_dataloader
# Config
BATCH_SIZE = 2
@@ -27,7 +27,12 @@ CONFIG = dict(parallel=dict(pipeline=dict(size=1), tensor=dict(size=1, mode=None
def run_no_pipeline(rank, world_size, port):
# init dist env
colossalai.launch(config=CONFIG, rank=rank, world_size=world_size, host='localhost', port=port, backend='nccl')
colossalai.legacy.launch(config=CONFIG,
rank=rank,
world_size=world_size,
host='localhost',
port=port,
backend='nccl')
# build model
model = resnet18(num_classes=10)
@@ -49,10 +54,10 @@ def run_no_pipeline(rank, world_size, port):
optimizer = Adam(model.parameters(), lr=0.001)
criterion = nn.CrossEntropyLoss()
engine, train_dataloader, *args = colossalai.initialize(model=model,
optimizer=optimizer,
criterion=criterion,
train_dataloader=train_dataloader)
engine, train_dataloader, *args = colossalai.legacy.initialize(model=model,
optimizer=optimizer,
criterion=criterion,
train_dataloader=train_dataloader)
logger = get_dist_logger()
rank = torch.distributed.get_rank()
param_track = []