Skip to content

[5868890][ONNX][Autocast] Fix: failure when checking input shape with unknown dimension #859

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
gcunhase merged 4 commits into from
Feb 9, 2026
Merged

[5868890][ONNX][Autocast] Fix: failure when checking input shape with unknown dimension #859

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
1fc5843
Fix: issue with input shape comparison with unknown dimensions
gcunhase Feb 5, 2026
115fc48
Add check for input rank
gcunhase Feb 5, 2026
629e4bb
Add UNK input shape for model shape only
gcunhase Feb 5, 2026
8c26e5b
Update: consider input shape > 0 as static
gcunhase Feb 5, 2026
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
11 changes: 10 additions & 1 deletion modelopt/onnx/autocast/referencerunner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,7 +89,16 @@ def _validate_inputs(self, data_loader):
if sorted(self.input_names) != sorted(data_loader[0].keys()):
raise ValueError("Input names from ONNX model do not match provided input names.")
for inp_name, inp_shape in data_loader[0].items():
if self.input_shapes[inp_name] != list(inp_shape.shape):
# Get model and data shapes as numpy arrays
inp_shape_model = np.array(self.input_shapes[inp_name])
inp_shape_data = np.array(inp_shape.shape)
# Compare input rank
raise_value_error = len(inp_shape_model) != len(inp_shape_data)
if not raise_value_error:
# Compare input shape, skipping check for unknown dimensions
mask = inp_shape_model > 0
raise_value_error = np.any(inp_shape_model[mask] != inp_shape_data[mask])
if raise_value_error:
raise ValueError(
f"Input shape from '{inp_name}' does not match provided input shape: "
f"{self.input_shapes[inp_name]} vs {list(inp_shape.shape)}. "
Expand Down