github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-02 01:28:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

[bf16] add bf16 support (#3882)

Browse Source 
* [bf16] add bf16 support for fused adam (#3844)

* [bf16] fused adam kernel support bf16

* [test] update fused adam kernel test

* [test] update fused adam test

* [bf16] cpu adam and hybrid adam optimizers support bf16 (#3860)

* [bf16] implement mixed precision mixin and add bf16 support for low level zero (#3869)

* [bf16] add mixed precision mixin

* [bf16] low level zero optim support bf16

* [text] update low level zero test

* [text] fix low level zero grad acc test

* [bf16] add bf16 support for gemini (#3872)

* [bf16] gemini support bf16

* [test] update gemini bf16 test

* [doc] update gemini docstring

* [bf16] add bf16 support for plugins (#3877)

* [bf16] add bf16 support for legacy zero (#3879)

* [zero] init context support bf16

* [zero] legacy zero support bf16

* [test] add zero bf16 test

* [doc] add bf16 related docstring for legacy zero
This commit is contained in:
Hongxin Liu
2023-06-05 15:58:31 +08:00
committed by GitHub
parent 07cb21142f
commit ae02d4e4f7
27 changed files with 738 additions and 525 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
tests/test_zero/test_gemini/test_optim.py
View File

@@ -21,23 +21,40 @@ TEST_MODELS = ['gpt2']
# these models are too small, all parameters in these models are compacted into one chunk
EXAMPLE_MODELS = ['albert', 'beit', 'bert', 'hanging_param_model', 'nested_model', 'repeated_computed_layers']
# bfloat16 cannot represent them exactly
BF16_IGNORED_KEYS = [
'albert.embeddings.word_embeddings.weight',
'albert.embeddings.position_embeddings.weight',
'masked_bias',
]
def check_param(model: ZeroDDP, torch_model: torch.nn.Module):
zero_dict = model.state_dict(only_rank_0=False)
def check_param(model: ZeroDDP, torch_model: torch.nn.Module, dtype: torch.dtype):
zero_dict = model.state_dict(only_rank_0=False, dtype=dtype)
torch_dict = torch_model.state_dict()
for key, value in torch_dict.items():
# key is 'module.model.PARAMETER', so we truncate it
key = key[7:]
assert key in zero_dict, "{} not in ZeRO dictionary.".format(key)
temp_zero_value = zero_dict[key].to(device=value.device, dtype=value.dtype)
temp_zero_value = zero_dict[key].to(device=value.device)
if dtype is torch.bfloat16 and any(k in key for k in BF16_IGNORED_KEYS):
continue
rtol, atol = 1e-3, 4e-3
if dtype is torch.bfloat16:
rtol, atol = 4e-3, 8e-3
# debug_print([0], "max range: ", key, torch.max(torch.abs(value - temp_zero_value)))
assert_close(value, temp_zero_value, rtol=1e-3, atol=4e-3)
assert_close(value.float(),
temp_zero_value.float(),
rtol=rtol,
atol=atol,
msg=lambda s: s + f'\n{key}\n{temp_zero_value.dtype}')
@parameterize('placement_policy', ['cuda', 'cpu', 'auto', 'const'])
@parameterize('model_name', TEST_MODELS)
def exam_model_step(placement_policy, model_name: str):
@parameterize('mixed_precision', [torch.half, torch.bfloat16])
def exam_model_step(placement_policy, model_name: str, mixed_precision: torch.dtype):
set_seed(42)
get_components_func = non_distributed_component_funcs.get_callable(model_name)
model_builder, train_dataloader, test_dataloader, optimizer_class, criterion = get_components_func()
@@ -65,7 +82,7 @@ def exam_model_step(placement_policy, model_name: str):
init_device = None
chunk_manager = ChunkManager(config_dict, init_device=init_device)
gemini_manager = GeminiManager(placement_policy, chunk_manager)
model = ZeroDDP(model, gemini_manager, pin_memory=True)
model = ZeroDDP(model, gemini_manager, pin_memory=True, mixed_precision=mixed_precision)
optimizer = HybridAdam(model.parameters(), lr=1e-3)
zero_optim = ZeroOptimizer(optimizer, model, initial_scale=128)
@@ -74,6 +91,7 @@ def exam_model_step(placement_policy, model_name: str):
torch_model.eval()
set_seed(dist.get_rank() * 3 + 128)
rtol, atol = 1e-4, 1e-5
for i, (input_ids, label) in enumerate(train_dataloader):
if i > 2:
break
@@ -83,17 +101,18 @@ def exam_model_step(placement_policy, model_name: str):
torch_loss = run_fwd_bwd(torch_model, input_ids, label, criterion, torch_optim)
loss = run_fwd_bwd(model, input_ids, label, criterion, zero_optim)
assert_close(torch_loss, loss)
assert_close(torch_loss, loss, rtol=rtol, atol=atol)
zero_optim.step()
torch_optim.step()
check_param(model, torch_model)
check_param(model, torch_model, mixed_precision)
@parameterize('placement_policy', ['cuda', 'cpu', 'auto', 'const'])
@parameterize('model_name', EXAMPLE_MODELS)
def exam_tiny_example(placement_policy, model_name: str):
@parameterize('mixed_precision', [torch.half, torch.bfloat16])
def exam_tiny_example(placement_policy, model_name: str, mixed_precision: torch.dtype):
set_seed(2008)
get_components_func = non_distributed_component_funcs.get_callable(model_name)
model_builder, train_dataloader, test_dataloader, optimizer_class, criterion = get_components_func()
@@ -113,7 +132,7 @@ def exam_tiny_example(placement_policy, model_name: str):
chunk_manager = init_chunk_manager(model=model, init_device=get_current_device(), search_range_mb=1)
gemini_manager = GeminiManager(placement_policy, chunk_manager)
model = ZeroDDP(model, gemini_manager, pin_memory=True)
model = ZeroDDP(model, gemini_manager, pin_memory=True, mixed_precision=mixed_precision)
optimizer = HybridAdam(model.parameters(), lr=1e-3)
zero_optim = ZeroOptimizer(optimizer, model, initial_scale=2)
@@ -121,6 +140,9 @@ def exam_tiny_example(placement_policy, model_name: str):
torch_model.eval()
set_seed(dist.get_rank() * 3 + 128)
rtol, atol = 1.5e-6, 2e-5
if mixed_precision is torch.bfloat16:
rtol, atol = 2e-3, 2e-3
for i, (input_ids, label) in enumerate(train_dataloader):
if i > 2:
break
@@ -133,12 +155,12 @@ def exam_tiny_example(placement_policy, model_name: str):
torch_loss = run_fwd_bwd(torch_model, input_ids, label, criterion, torch_optim)
loss = run_fwd_bwd(model, input_ids, label, criterion, zero_optim)
assert_close(torch_loss, loss, rtol=1.5e-6, atol=2e-5) # atol should be 2e-5 for torch lower than 1.12
assert_close(torch_loss, loss, rtol=rtol, atol=atol) # atol should be 2e-5 for torch lower than 1.12
zero_optim.step()
torch_optim.step()
check_param(model, torch_model)
check_param(model, torch_model, mixed_precision)
def run_dist(rank, world_size, port):

21
tests/test_zero/test_legacy/test_zero_engine.py
View File

@@ -16,7 +16,11 @@ from colossalai.zero.low_level._utils import has_inf_or_nan
from tests.components_to_test.registry import non_distributed_component_funcs
def run_dist(rank, world_size, port, parallel_config):
def run_dist(rank, world_size, port, parallel_config, bf16):
is_mp_config = parallel_config == MP_PARALLEL_CONFIG
is_zero_config = parallel_config == ZERO_PARALLEL_CONFIG
if bf16:
parallel_config['zero']['model_config']['bf16'] = True
colossalai.launch(config=parallel_config,
rank=rank,
world_size=world_size,
@@ -30,7 +34,8 @@ def run_dist(rank, world_size, port, parallel_config):
model_builder, train_dataloader, _, optimizer_class, criterion = get_components_func()
with ZeroInitContext(target_device=torch.cuda.current_device(),
shard_strategy=gpc.config.zero.model_config.shard_strategy,
shard_param=True):
shard_param=True,
bf16=bf16):
colo_model = model_builder(checkpoint=True)
colo_optimizer = optimizer_class(colo_model.parameters(), lr=1e-3)
@@ -38,7 +43,8 @@ def run_dist(rank, world_size, port, parallel_config):
optimizer=colo_optimizer,
criterion=criterion,
train_dataloader=train_dataloader)
torch_model = model_builder(checkpoint=True).half()
dtype = torch.bfloat16 if bf16 else torch.float16
torch_model = model_builder(checkpoint=True).to(dtype)
col_model_deepcopy(engine.model, torch_model)
torch_model = torch_model.cuda().float()
@@ -80,9 +86,9 @@ def run_dist(rank, world_size, port, parallel_config):
torch_optimizer.step()
i += 1
if parallel_config == MP_PARALLEL_CONFIG:
if is_mp_config:
check_params(torch_model, colo_model, loose=True)
elif parallel_config == ZERO_PARALLEL_CONFIG:
elif is_zero_config:
check_sharded_model_params(torch_model, colo_model, loose=True)
@@ -97,9 +103,10 @@ def test_mp_engine(world_size):
@pytest.mark.dist
@pytest.mark.parametrize("world_size", [1, 2])
@pytest.mark.parametrize("bf16", [True, False])
@rerun_if_address_is_in_use()
def test_zero_engine(world_size):
spawn(run_dist, world_size, parallel_config=ZERO_PARALLEL_CONFIG)
def test_zero_engine(world_size, bf16):
spawn(run_dist, world_size, parallel_config=ZERO_PARALLEL_CONFIG, bf16=bf16)
if __name__ == '__main__':

5
tests/test_zero/test_low_level/test_grad_acc.py
View File

@@ -82,7 +82,6 @@ def exam_zero_1_2_grad_acc():
def exam_zero_1_grad_acc():
local_rank = torch.distributed.get_rank()
grad_scale = 32
seed_all(2008)
# create models
@@ -101,7 +100,6 @@ def exam_zero_1_grad_acc():
# level 1 and 2 will produce exactly the same results
zero_optimizer = LowLevelZeroOptimizer(zero_optimizer,
overlap_communication=False,
initial_scale=grad_scale,
reduce_bucket_size=262144,
clip_grad_norm=1.0)
@@ -128,9 +126,8 @@ def exam_zero_1_grad_acc():
if check_flag:
# check grad
for (n, p), z1p in zip(torch_model.named_parameters(), zero_model.parameters()):
unscale_grad = z1p.grad / grad_scale
# print(n, p.shape, torch.max(torch.abs(p.grad - unscale_grad)))
assert torch.equal(p.grad, unscale_grad)
assert torch.equal(p.grad, z1p.grad)
zero_optimizer._sync_grad()

35
tests/test_zero/test_low_level/test_zero1_2.py
View File

@@ -7,7 +7,7 @@ from torch.nn.parallel import DistributedDataParallel as DDP
from torch.testing import assert_close
import colossalai
from colossalai.testing import rerun_if_address_is_in_use, spawn
from colossalai.testing import parameterize, rerun_if_address_is_in_use, spawn
from colossalai.testing.random import seed_all
from colossalai.zero import LowLevelZeroOptimizer
@@ -25,15 +25,18 @@ class MlpModel(nn.Module):
return x
def half_close(a, b, loose=False):
def loose_close(a, b, dtype: torch.dtype = torch.float32):
rtol = None
atol = None
if loose:
if dtype is torch.float16:
rtol = 5e-2
atol = 5e-4
elif dtype is torch.bfloat16:
rtol = 4e-3
atol = 4e-3
a = a.detach().half()
b = b.detach().half()
a = a.detach().to(dtype)
b = b.detach().to(dtype)
assert_close(a, b, rtol=rtol, atol=atol)
@@ -96,7 +99,8 @@ def exam_zero_1_2():
assert torch.equal(z1p.data, z2p.data)
def exam_zero_1_torch_ddp():
@parameterize('dtype', [torch.float16, torch.bfloat16])
def exam_zero_1_torch_ddp(dtype: torch.dtype):
"""
In this test, two pairs of model and optimizers are created.
1. zero: use sharded optimizer and fp16 parameters
@@ -109,15 +113,10 @@ def exam_zero_1_torch_ddp():
seed_all(1453)
# create models
zero_model = MlpModel()
torch_model = copy.deepcopy(zero_model)
torch_model = MlpModel().cuda()
zero_model = copy.deepcopy(torch_model).to(dtype)
zero_model = zero_model.cuda().half()
torch_model = DDP(torch_model.cuda(), bucket_cap_mb=0)
torch_model = torch_model.cuda()
# for (n, p), z1p in zip(torch_model.named_parameters(), zero_model.parameters()):
# half_close(p.data, z1p.data)
torch_model = DDP(torch_model.cuda(), bucket_cap_mb=0).cuda()
# create optimizer
zero_optimizer = torch.optim.SGD(zero_model.parameters(), lr=1)
@@ -137,11 +136,11 @@ def exam_zero_1_torch_ddp():
input_data = torch.rand(32, 128).cuda()
# zero-dp forward
zero_output = zero_model(input_data.half())
zero_output = zero_model(input_data.to(dtype))
# torch-ddp forward
torch_output = torch_model(input_data)
half_close(zero_output, torch_output, loose=True)
loose_close(zero_output, torch_output, dtype=dtype)
# zero-dp backward
zero_optimizer.backward(zero_output.mean().float(), sync_grad=False)
@@ -151,7 +150,7 @@ def exam_zero_1_torch_ddp():
# check grad
for (n, p), z1p in zip(torch_model.named_parameters(), zero_model.parameters()):
half_close(p.grad, z1p.grad, loose=True)
loose_close(p.grad, z1p.grad, dtype=dtype)
# zero-dp step
zero_optimizer._sync_grad()
@@ -163,7 +162,7 @@ def exam_zero_1_torch_ddp():
# check updated param
for (n, p), z1p in zip(torch_model.named_parameters(), zero_model.parameters()):
# print(n, torch.max(torch.abs(p.data - z1p.data)))
half_close(p.data, z1p.data, loose=True)
loose_close(p.data, z1p.data, dtype=dtype)
def run_dist(rank, world_size, port):