Skip to content

bypass add and addRelu that have inputs from non-dq nodes #19315

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

Open
rezaasjd wants to merge 1 commit into
base: main
Choose a base branch
from
+4 −0
Open

bypass add and addRelu that have inputs from non-dq nodes #19315

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
4 changes: 4 additions & 0 deletions backends/cadence/aot/quantizer/fusion_pass.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -620,6 +620,8 @@ def call(self, graph_module: fx.GraphModule) -> PassResult: # noqa: C901
)
kwargs = {}
if isinstance(pattern, AddReluPatterns):
if len(dequants_inputs) != 2:
continue
# For AddReLU, we are fusing Add+ReLU.
# The quantized_add op performs requantization,
# so the relu is implicit in the output quant params.
Expand All @@ -633,6 +635,8 @@ def call(self, graph_module: fx.GraphModule) -> PassResult: # noqa: C901
quant_node,
)
elif isinstance(pattern, AddPattern):
if len(dequants_inputs) != 2:
continue
args, kwargs = get_args_and_kwargs_add(
graph_module,
inputs_inputs,
Expand Down
Loading