mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-04-29 04:05:35 +00:00
27061426f7
* [gemini] remove distributed-related part from colotensor (#4379) * [gemini] remove process group dependency * [gemini] remove tp part from colo tensor * [gemini] patch inplace op * [gemini] fix param op hook and update tests * [test] remove useless tests * [test] remove useless tests * [misc] fix requirements * [test] fix model zoo * [test] fix model zoo * [test] fix model zoo * [test] fix model zoo * [test] fix model zoo * [misc] update requirements * [gemini] refactor gemini optimizer and gemini ddp (#4398) * [gemini] update optimizer interface * [gemini] renaming gemini optimizer * [gemini] refactor gemini ddp class * [example] update gemini related example * [example] update gemini related example * [plugin] fix gemini plugin args * [test] update gemini ckpt tests * [gemini] fix checkpoint io * [example] fix opt example requirements * [example] fix opt example * [example] fix opt example * [example] fix opt example * [gemini] add static placement policy (#4443) * [gemini] add static placement policy * [gemini] fix param offload * [test] update gemini tests * [plugin] update gemini plugin * [plugin] update gemini plugin docstr * [misc] fix flash attn requirement * [test] fix gemini checkpoint io test * [example] update resnet example result (#4457) * [example] update bert example result (#4458) * [doc] update gemini doc (#4468) * [example] update gemini related examples (#4473) * [example] update gpt example * [example] update dreambooth example * [example] update vit * [example] update opt * [example] update palm * [example] update vit and opt benchmark * [hotfix] fix bert in model zoo (#4480) * [hotfix] fix bert in model zoo * [test] remove chatglm gemini test * [test] remove sam gemini test * [test] remove vit gemini test * [hotfix] fix opt tutorial example (#4497) * [hotfix] fix opt tutorial example * [hotfix] fix opt tutorial example
60 lines
1.7 KiB
Python
60 lines
1.7 KiB
Python
import pytest
|
|
import torch
|
|
|
|
from colossalai.pipeline.pipelinable import PipelinableContext
|
|
from colossalai.testing import rerun_if_address_is_in_use, rerun_on_exception, spawn
|
|
|
|
NUM_CHUNKS = 1
|
|
PIPELINE_SIZE = 2
|
|
|
|
|
|
class MLP(torch.nn.Module):
|
|
|
|
def __init__(self, dim: int = 256):
|
|
super().__init__()
|
|
intermediate_dim = dim * 4
|
|
self.dense_1 = torch.nn.Linear(dim, intermediate_dim)
|
|
self.activation = torch.nn.GELU()
|
|
self.dense_2 = torch.nn.Linear(intermediate_dim, dim)
|
|
self.dropout = torch.nn.Dropout(0.1)
|
|
|
|
def forward(self, x):
|
|
x = self.dense_1(x)
|
|
x = self.activation(x)
|
|
x = self.dense_2(x)
|
|
x = self.dropout(x)
|
|
return x
|
|
|
|
|
|
def run_pipelinable(rank, world_size, port):
|
|
pipelinable = PipelinableContext()
|
|
with pipelinable:
|
|
model = MLP()
|
|
|
|
assert pipelinable.policy == "balanced"
|
|
pipelinable.policy = "uniform"
|
|
assert pipelinable.policy == "uniform"
|
|
pipelinable.to_layer_list()
|
|
|
|
assert pipelinable.layers_count == len(list(model.children()))
|
|
|
|
pipeline_model_part_0 = pipelinable.partition(NUM_CHUNKS, PIPELINE_SIZE, 0)
|
|
assert isinstance(pipeline_model_part_0, torch.nn.Module)
|
|
pipeline_model_part_1 = pipelinable.partition(NUM_CHUNKS, PIPELINE_SIZE, 1)
|
|
assert isinstance(pipeline_model_part_1, torch.nn.Module)
|
|
|
|
layers_count_in_part_0 = len(list(pipeline_model_part_0._module_list))
|
|
layers_count_in_part_1 = len(list(pipeline_model_part_1._module_list))
|
|
|
|
assert layers_count_in_part_0 + layers_count_in_part_1 == pipelinable.layers_count
|
|
|
|
|
|
@pytest.mark.skip(reason="this is useless")
|
|
@rerun_if_address_is_in_use()
|
|
def test_pipelinable():
|
|
spawn(run_pipelinable, 1)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
test_pipelinable()
|