Skip to content

Fix comparison of module_type and MulLinear #1671

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 2 commits into from
Mar 14, 2024
Merged

Fix comparison of module_type and MulLinear #1671

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
466489a
fix MulLinear Comparison
Kaihui-intel Mar 13, 2024
6af59c1
fix full name
Kaihui-intel Mar 13, 2024
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
3 changes: 1 addition & 2 deletions neural_compressor/utils/pytorch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,7 +210,6 @@ def load_weight_only(checkpoint_dir, model, layer_wise=False):
Returns:
(object): quantized model
"""
import neural_compressor # for eval(config['module_type'])
from neural_compressor.adaptor.torch_utils.model_wrapper import MulLinear

weights_file = os.path.join(os.path.abspath(os.path.expanduser(checkpoint_dir)), "best_model.pt")
Expand All @@ -221,7 +220,7 @@ def load_weight_only(checkpoint_dir, model, layer_wise=False):
for op_name, config in weight_only_config.items():
if config["dtype"] == "fp32":
continue
if eval(config["module_type"]) == MulLinear:
if config["module_type"] == MulLinear.__module__ + "." + MulLinear.__name__:
# op should be repleced by MulLinear
module = util.fetch_module(model, op_name)
new_module = MulLinear(module)
Expand Down