-
Notifications
You must be signed in to change notification settings - Fork 181
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.
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
Temporary fix for QAT quantizer when linear layer bias is True #1087
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/1087
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit b6982c0 with merge base 6ea36c5 (): This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Hi @elfisworking, thanks for fixing this. Changes look great! Would you mind adding a test in |
@@ -617,7 +617,7 @@ def _replace_linear_int4( | |||
copy_weights: bool = False, | |||
): | |||
for name, child in module.named_children(): | |||
if isinstance(child, nn.Linear) and (skip_layer_func is None or not skip_layer_func(child.weight)): | |||
if isinstance(child, nn.Linear) and child.bias is None and (skip_layer_func is None or not skip_layer_func(child.weight)): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
can you also add a TODO: support linear bias (here and L982)
Signed-off-by: yumin <[email protected]>
test has been added |
Thanks @elfisworking, merging this. |
Link issue: Int8DynActInt4WeightQATQuantizer doesn't support qwen series #1080