Skip to content

[not4land] TorchAOBaseTensor BC Testing - Add a new optional attribute #3105

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

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

[not4land] TorchAOBaseTensor BC Testing - Add a new optional attribute #3105

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: 4 additions & 0 deletions torchao/quantization/quantize_/workflows/float8/float8_tensor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,6 +99,7 @@ class Float8Tensor(TorchAOBaseTensor):
"act_quant_kwargs",
"kernel_preference",
"dtype",
"test_only_new_attr",
]

def __new__(
Expand All @@ -110,6 +111,7 @@ def __new__(
act_quant_kwargs: Optional[QuantizeTensorToFloat8Kwargs] = None,
kernel_preference: KernelPreference = KernelPreference.AUTO,
dtype: Optional[torch.dtype] = None,
test_only_new_attr: Optional[int] = None,
):
shape = qdata.shape
kwargs = {}
Expand All @@ -127,6 +129,7 @@ def __init__(
act_quant_kwargs: Optional[QuantizeTensorToFloat8Kwargs] = None,
kernel_preference: KernelPreference = KernelPreference.AUTO,
dtype: Optional[torch.dtype] = None,
test_only_new_attr: Optional[int] = None,
):
super().__init__()
self.qdata = qdata
Expand All @@ -135,6 +138,7 @@ def __init__(
self.mm_config = mm_config
self.act_quant_kwargs = act_quant_kwargs
self.kernel_preference = kernel_preference
self.test_only_new_attr = test_only_new_attr

def __repr__(self):
return (
Expand Down
Loading