2026-02-03 12:18 AM
Hey,
I am trying to run a model on the n6 npu.
Currently most layers are run on the npu as the should but there are some layers which are executed on the SW target, even though the documentation states that the layer should be HW supported (in this case its the HardSigmoid layer). Changing the activation to a Sigmoid layer will make it run on the HW side. I thought it could be the case since in the documentation it states that sigmoid supports X*Sigmoid(X) and the problem layer is at a skip connection but i have early occurrences of the exact same HardSigmoid Skip connection pattern which are executed on the HW. Its only 2 of these blocks that are executed on the SW. Is this a bug or intential due to some optimization being done by the compiler.
I attached an image of the model graph and Cube AI Analyze output.
Thanks in advance
2026-02-03 8:03 AM - edited 2026-02-17 6:07 AM
Hi @M_Benz,
First elements indicate that it could be a bug.
I am asking confirmation internally.
I will update you.
If this is indeed a bug, its resolution will depend on the priority.
Could you please share the model?
If you feel like it is very important for your company project, please contact your local FAE.
Have a good day,
Julian
2026-02-09 1:21 AM