Hi,
I have a problem about the * or mul operation in snpe.
I conduct attention block in my neural network that require * operation, i.e. input [24,4,60,60] (channel,batch,h,w) * attention [24,4,1,1].
When I convert the pytorch onnx to the snpe platform, it seems have problem about the mul operation.
Is there any idea to solve this?
Many thanks.
Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.
Did you solve the issue?
Could you kindly provide more details about the architecture that you were using? I'm porting a LLM on-device atm :)
Thanks!