Skip to content

Dependency package upgrade #407

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

Merged
merged 14 commits into from
Jul 14, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
8 changes: 4 additions & 4 deletions pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -28,11 +28,11 @@ dependencies = [
"multidict==6.0.4",
"urllib3<2",
"sentencepiece==0.2.0",
"onnx==1.16.0",
"onnxruntime==1.16.3",
"onnx==1.18.0",
"onnxruntime==1.22",
"numpy==1.26.4",
"protobuf==3.20.2",
"onnxscript==0.1.0.dev20240327",
"protobuf==6.31.0",
"onnxscript==0.2.5",
"pillow===10.4.0",
"sympy",
"tensorboard",
Expand Down
11 changes: 6 additions & 5 deletions tests/peft/test_peft_onnx_transforms.py
Original file line number Diff line number Diff line change
Expand Up @@ -46,18 +46,19 @@ def test_adapter_weights_to_inputs_transform():

out_onnx, transformed = AdapterWeightsToInputsTransform.apply(test_onnx, adapter_name=adapter_name)
assert transformed

assert (
onnx.printer.to_text(out_onnx)
== textwrap.dedent("""
<
ir_version: 8,
opset_import: ["" : 17]
>
test_adapter_weights (float[n,32] input, float[32,32] layer1.weight, float[32,32] layer2.weight) => (float[n,32] output, float[32,32] layer1.weight_RetainedState, float[32,32] layer2.weight_RetainedState) {
layer1output = MatMul (input, layer1.weight)
output = MatMul (layer1output, layer2.weight)
layer1.weight_RetainedState = Identity (layer1.weight)
layer2.weight_RetainedState = Identity (layer2.weight)
test_adapter_weights (float[n,32] input, float[32,32] "layer1.weight", float[32,32] "layer2.weight") => (float[n,32] output, float[32,32] "layer1.weight_RetainedState", float[32,32] "layer2.weight_RetainedState") {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why these changes are done?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The code already exists. Changes were made because with the upgrade of onnx and other components the format needs to be changed else it will throw an error.

layer1output = MatMul (input, "layer1.weight")
output = MatMul (layer1output, "layer2.weight")
["layer1.weight_identity"] "layer1.weight_RetainedState" = Identity ("layer1.weight")
["layer2.weight_identity"] "layer2.weight_RetainedState" = Identity ("layer2.weight")
}
""").strip()
)
Loading