scale
parsed as float
in ONNX scaled_dot_product_attention
implementation
#125158
Labels
module: onnx
Related to torch.onnx
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Hi,
I have been getting errors looking like the one below when trying to export a model to ONNX within which I manually provide a
scale
argument to the scaled dot product attention calls:Looking at
symbolic_opset14.py
, I see that_maybe_get_const
parsesscale
as afloat
which triggers the error as the type is not correct, cf.here
Is this intentional? If I remove this line, then I manage to export successfully my model.
Thanks
The text was updated successfully, but these errors were encountered: