Skip to content

fix bug in sq torch backend #1342

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
chensuyue merged 1 commit into from
Oct 24, 2023
Merged

fix bug in sq torch backend #1342

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 neural_compressor/adaptor/torch_utils/model_wrapper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ def get_torch_version():


class QDQLinear(torch.nn.Module):
def __init__(self, module, scale=1, zero_point=0, dtype=torch.quint8):
def __init__(self, module, scale=1.0, zero_point=0, dtype=torch.quint8):
super().__init__()
if PT_VERSION < Version("1.13.0").release:
import torch.nn.quantized as nnq
Expand Down
1 change: 1 addition & 0 deletions neural_compressor/adaptor/torch_utils/smooth_quant.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -386,6 +386,7 @@ def _dump_min_max(self, calib_iter=100):
:param calibration_method: only support min_max currently
:param calib_iter: Sample size for calibration
:return:"""
logger.info("Calibrating...")
if self.q_func:
self.q_func(self.model)
else:
Expand Down