Skip to content

Fix custom op example #15483

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
cccclai wants to merge 4 commits into
base: main
Choose a base branch
from
+4 −6
Open

Fix custom op example #15483

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
20c3d0b
Fix custom op example
cccclai Oct 30, 2025
9bfe282
Update custom_ops_1.py
cccclai Oct 30, 2025
ea5ec21
Update custom_ops_1.py
cccclai Oct 31, 2025
50b850f
Fix indentation and clean up code in custom_ops_1.py
cccclai Nov 14, 2025
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
10 changes: 4 additions & 6 deletions examples/qualcomm/custom_op/custom_ops_1.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,16 +69,13 @@ def annotate_custom(gm: torch.fx.GraphModule) -> None:
This function is specific for custom op.
The source_fn of the rewritten nn module turns out to be "my_ops.mul3.default"
"""
from executorch.backends.qualcomm.quantizer.annotators import (
_is_annotated,
QUANT_ANNOTATION_KEY,
)

from executorch.backends.qualcomm.quantizer.annotators import _is_annotated
from executorch.backends.qualcomm.quantizer.qconfig import (
get_ptq_per_channel_quant_config,
)
from torch.fx import Node
from torchao.quantization.pt2e.quantizer import QuantizationAnnotation
from torchao.quantization.pt2e.quantizer.quantizer import Q_ANNOTATION_KEY

quantization_config = get_ptq_per_channel_quant_config()
for node in gm.graph.nodes:
Expand All @@ -95,7 +92,7 @@ def annotate_custom(gm: torch.fx.GraphModule) -> None:
input_spec = quantization_config.input_activation
input_qspec_map[input_act] = input_spec

node.meta[QUANT_ANNOTATION_KEY] = QuantizationAnnotation(
node.meta[Q_ANNOTATION_KEY] = QuantizationAnnotation(
input_qspec_map=input_qspec_map,
output_qspec=quantization_config.output_activation,
_annotated=True,
Expand Down Expand Up @@ -235,6 +232,7 @@ def main(args):
f"--output_folder_path {output_data_folder}",
]
)

subprocess.run(
runner_cmd,
# stdout=subprocess.PIPE,
Expand Down
Loading