Skip to content

Fix full CI test isolation for ZeRO chmod and NVMe quantization tests #8008

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
tohtana wants to merge 1 commit into
base: master
Choose a base branch
from
+17 −9
Open

Fix full CI test isolation for ZeRO chmod and NVMe quantization tests #8008

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion tests/unit/checkpoint/test_zero_optimizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -653,7 +653,9 @@ def test_save_tensor_clone(self, tmpdir, zero_stage, use_cpu_device):

class TestZeRONonDistributed(DistributedTest):
world_size = 1
init_distributed = False
# This test calls deepspeed.initialize(), so use the harness' file-store
# initialization instead of env:// TCP rendezvous ports under xdist.
init_distributed = True

@pytest.mark.parametrize('zero_stage', [1, 2, 3])
def test_chmod_exception_handling(self, monkeypatch, zero_stage):
Expand Down
22 changes: 14 additions & 8 deletions tests/unit/inference/quantization/test_intX_quantization.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,7 @@ def quantization_test_helper(pre_quant_type: torch.dtype, num_bits: int):
assert mean_diff < 0.15 and max_diff < 0.5, f'Numeric error exceed threshold, mean diff {mean_diff} (threshold 0.15), max diff {max_diff} (threshold 0.5)'


def zero3_post_init_quantization_test_helper(cpu_offload: bool, nvme_offload: bool, bits: int):
def zero3_post_init_quantization_test_helper(cpu_offload: bool, nvme_offload: bool, bits: int, nvme_path=None):
import deepspeed
from transformers.integrations.deepspeed import HfDeepSpeedConfig

Expand Down Expand Up @@ -131,7 +131,7 @@ def get_zero3_ds_config(hf_config: OPTConfig, cpu_offload: bool, nvme_offload: b
ds_config["zero_optimization"]["offload_param"] = dict(
device="nvme",
pin_memory=True,
nvme_path='~/tmp_offload_dir',
nvme_path=nvme_path or '~/tmp_offload_dir',
buffer_count=5,
buffer_size=1 * GB,
)
Expand Down Expand Up @@ -174,7 +174,7 @@ def get_zero3_ds_config(hf_config: OPTConfig, cpu_offload: bool, nvme_offload: b
assert mean_diff < 0.4, f'Numeric error exceed threshold, relative error {mean_diff} (threshold 0.4)'


def zero3_quantized_initialization_test_helper(cpu_offload: bool, nvme_offload: bool, bits: int):
def zero3_quantized_initialization_test_helper(cpu_offload: bool, nvme_offload: bool, bits: int, nvme_path=None):
import deepspeed
from transformers.integrations.deepspeed import HfDeepSpeedConfig

Expand Down Expand Up @@ -213,7 +213,7 @@ def get_zero3_ds_config(hf_config: OPTConfig, cpu_offload: bool, nvme_offload: b
ds_config["zero_optimization"]["offload_param"] = dict(
device="nvme",
pin_memory=True,
nvme_path='~/tmp_offload_dir',
nvme_path=nvme_path or '~/tmp_offload_dir',
buffer_count=5,
buffer_size=1 * GB,
)
Expand Down Expand Up @@ -393,9 +393,12 @@ def test_zero3_int4_post_init_quant_cpu_offload(self, quantization_bits):
zero3_post_init_quantization_test_helper(cpu_offload=True, nvme_offload=False, bits=quantization_bits)

@pytest.mark.skipif(device == 'cpu', reason='CPU does support FP16 GEMM')
def test_zero3_int4_post_init_quant_nvme_offload(self):
def test_zero3_int4_post_init_quant_nvme_offload(self, tmpdir):
reset_random()
zero3_post_init_quantization_test_helper(cpu_offload=False, nvme_offload=True, bits=4)
zero3_post_init_quantization_test_helper(cpu_offload=False,
nvme_offload=True,
bits=4,
nvme_path=str(tmpdir.join("nvme_offload")))

@pytest.mark.skipif(device == 'cpu', reason='CPU does support FP16 GEMM')
def test_zero3_int4_quantized_initialization(self, quantization_bits):
Expand All @@ -408,6 +411,9 @@ def test_zero3_int4_quantized_initialization_cpu_offload(self, quantization_bits
zero3_quantized_initialization_test_helper(cpu_offload=True, nvme_offload=False, bits=quantization_bits)

@pytest.mark.skipif(device == 'cpu', reason='CPU does support FP16 GEMM')
def test_zero3_int4_quantized_initialization_nvme_offload(self):
def test_zero3_int4_quantized_initialization_nvme_offload(self, tmpdir):
reset_random()
zero3_quantized_initialization_test_helper(cpu_offload=False, nvme_offload=True, bits=4)
zero3_quantized_initialization_test_helper(cpu_offload=False,
nvme_offload=True,
bits=4,
nvme_path=str(tmpdir.join("nvme_offload")))
Loading