Skip to content

Fix fp8-all-gather buck errors #912

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
merged 1 commit into from
Sep 25, 2024
Merged

Fix fp8-all-gather buck errors #912

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: 1 addition & 1 deletion test/float8/test_fsdp2/test_fsdp2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@
from torchao.float8.config import CastConfig, Float8LinearConfig, ScalingType
from torchao.float8.float8_linear_utils import convert_to_float8_training
from torchao.float8.fsdp_utils import WeightWithDynamicFloat8CastTensor
from fsdp2_common import check_parity_bf16_mp, check_parity_no_mp
from torchao.testing.float8.fsdp2_utils import check_parity_bf16_mp, check_parity_no_mp
from torch.distributed._composable.fsdp import fully_shard, MixedPrecisionPolicy
from torch.distributed._tensor import DTensor
from torch.testing._internal.common_cuda import TEST_CUDA
Expand Down
Empty file added torchao/testing/__init__.py
View file
Open in desktop
Empty file.
Empty file added torchao/testing/float8/__init__.py
View file
Open in desktop
Empty file.
6 changes: 3 additions & 3 deletions test/float8/test_fsdp2/fsdp2_common.py → torchao/testing/float8/fsdp2_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,9 +49,9 @@ def check_parity_no_mp(
precompute_float8_dynamic_scale_for_fsdp(model)

if compile_transformer_block:
test_cls.assertEqual(losses[0], losses[1], atol=1e-4, rtol=1e-4)
test_cls.assertEqual(losses[0], losses[1], atol=1e-4, rtol=1e-4, msg = f"iter: {iter_idx}, loss-ref: {losses[0]}, loss-fp8: {losses[1]}")
else:
test_cls.assertEqual(losses[0], losses[1])
test_cls.assertEqual(losses[0], losses[1], msg = f"iter: {iter_idx}, loss-ref: {losses[0]}, loss-fp8: {losses[1]}")


def check_parity_bf16_mp(
Expand Down Expand Up @@ -86,4 +86,4 @@ def check_parity_bf16_mp(
ref_model.parameters(), ref_model_bf16.parameters()
):
param_bf16.detach().copy_(param_fp32)
test_cls.assertEqual(losses[0], losses[1])
test_cls.assertEqual(losses[0], losses[1], msg = f"iter: {iter_idx}, loss-ref: {losses[0]}, loss-fp8: {losses[1]}")
Loading