Skip to content

Fix groupwise quantization when group size divides channel size #2264

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

Closed
wants to merge 1 commit into from
Closed

Fix groupwise quantization when group size divides channel size #2264

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 examples/models/llama2/quantize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,7 @@ def dynamically_quantize_per_channel(

if group_size is None or group_size == 0:
items = x_shape_1
elif not enable_non_multiple_groups:
elif ((x_shape_1 % group_size) == 0) or not enable_non_multiple_groups:
assert group_size > 0, "group size must be positive"
assert (
x_shape_1 % group_size
Expand Down