Skip to content

Use nn_module_stack instead #3268

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 1 commit into from
Nov 3, 2025
Merged

Use nn_module_stack instead #3268

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions torchao/quantization/pt2e/qat_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -887,8 +887,8 @@ def _fold_conv_bn_qat(m: GraphModule) -> GraphModule:
node.target == torch.ops.aten.add_.Tensor
and node.args[0].op == "get_attr"
and node.args[1] == 1
and torch.nn.modules.batchnorm.BatchNorm2d
in [val[1] for val in node.meta["source_fn_stack"]]
and "torch.nn.modules.batchnorm.BatchNorm2d"
in [val[1] for _, val in node.meta["nn_module_stack"].items()]
):
m.graph.erase_node(node)

Expand Down
Loading