Skip to content

Skip fp16-config tests on accelerators without fp16 support #8398

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

Merged
delock merged 1 commit into from
Sep 3, 2026
+6 −0
Merged

Skip fp16-config tests on accelerators without fp16 support #8398

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
2 changes: 2 additions & 0 deletions tests/unit/runtime/test_multiple_models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@
import deepspeed
import deepspeed.comm as dist
import torch
from deepspeed import get_accelerator

@chatgpt-codex-connector chatgpt-codex-connector Bot Sep 3, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Add the required Signed-off-by trailer

This is a non-merge commit, but its message has no Signed-off-by trailer. Add the author name and email from the Git configuration using git commit --signoff so the commit satisfies the repository's mandatory DCO/CI requirement.

AGENTS.md reference: AGENTS.md:L8-L8

Useful? React with 👍 / 👎.

from unit.common import DistributedTest
from unit.simple_model import SimpleModel, random_dataloader

Expand Down Expand Up @@ -76,6 +77,7 @@ class TestMultipleModels(DistributedTest):
@pytest.mark.parametrize('fp32_grad_accum', [False, True])
@pytest.mark.parametrize('contiguous_gradients', [False, True])
@pytest.mark.parametrize('overlap_comm', [False, True])
@pytest.mark.skipif(not get_accelerator().is_fp16_supported(), reason="fp16 is not supported on this accelerator")
def test_zero_optimizer(self, num_models, shared_loss, zero_stage, fp32_grad_accum, contiguous_gradients,
overlap_comm):
config_dict = {
Expand Down
3 changes: 3 additions & 0 deletions tests/unit/v1/moe/test_moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@
class TestSimpleMoE(DistributedTest):
world_size = 2

@pytest.mark.skipif(not get_accelerator().is_fp16_supported(), reason="fp16 is not supported on this accelerator")
def test(self, zero_stage):
if not required_torch_version(min_version=1.8):
pytest.skip("DeepSpeed MoE tests need torch 1.8 or higher to run correctly")
Expand Down Expand Up @@ -66,6 +67,7 @@ def test(self, zero_stage):
class TestMoE(DistributedTest):
world_size = 4

@pytest.mark.skipif(not get_accelerator().is_fp16_supported(), reason="fp16 is not supported on this accelerator")
def test(self, ep_size, zero_stage, use_residual):
if not required_torch_version(min_version=1.8):
pytest.skip("DeepSpeed MoE tests need torch 1.8 or higher to run correctly")
Expand Down Expand Up @@ -164,6 +166,7 @@ def strict_narrow(dim, start, length):
class TestPRMoE(DistributedTest):
world_size = 4

@pytest.mark.skipif(not get_accelerator().is_fp16_supported(), reason="fp16 is not supported on this accelerator")
def test(self, ep_size, use_residual):
if not required_torch_version(min_version=1.8):
pytest.skip("DeepSpeed MoE tests need torch 1.8 or higher to run correctly")
Expand Down
1 change: 1 addition & 0 deletions tests/unit/v1/moe/test_moe_tp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,6 +57,7 @@ def get_model_parallel_group(self):
class TestMOETensorParallel(DistributedTest):
world_size = 4

@pytest.mark.skipif(not get_accelerator().is_fp16_supported(), reason="fp16 is not supported on this accelerator")
def test(self, ep_size, tp_size, enable_expert_tp, use_residual):
# TODO: replace this with a true parallel mlp in the future
# and run convergence tests
Expand Down
Loading