Skip to content
This repository has been archived by the owner on Oct 25, 2024. It is now read-only.

Fix WOQ IPEX condition #1203

Merged
merged 1 commit into from
Jan 29, 2024
Merged

Fix WOQ IPEX condition #1203

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 intel_extension_for_transformers/llm/quantization/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,7 +105,7 @@ def _replace_linear(
is_removed = False

if (isinstance(module, torch.nn.Linear) or isinstance(module, WeightOnlyLinear)
or (is_ipex_available and isinstance(module, ipex.nn.utils._weight_prepack._IPEXLinear))) \
or (is_ipex_available() and isinstance(module, ipex.nn.utils._weight_prepack._IPEXLinear))) \
and (name not in modules_to_not_convert):
# Check if the current key is not in the `modules_to_not_convert`
if not any(
Expand Down
Loading