Quantized model export_onnx_qop - AssertionError: Output quant required #611
Unanswered
shoskensMagics
asked this question in
Q&A
Replies: 1 comment
-
Thanks for you feedback, it is really appreciated! QOps have more strict requirements compared to QCDQ format. We have a notebook tutorial that could be helpful for this issue. Please let me know if you have further questions. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I've been playing with the
brevitas_examples.imagenet_classification.ptq
flow for a little bit. Very impressed on how easy it is to quantize, validate and then export to an interchangeable format like ONNX.I would like my quantized model to be used further down the line (through TVM on custom hardware, if it matters much).
For this purpose, I expect the ONNX to have QOps, instead of the QCDQ composed nodes.
Instead of calling
export_onnx_qcdq
, I thought a simple call toexport_onnx_qop
would do the job.This does not seem to be the case. I'm getting an
AssertionError
originating from the place specified below.Is there something I can do here? I expect my layers to be fully quantizable?
Can I play around with some settings in
ptq_common.quantize_model
?Beta Was this translation helpful? Give feedback.
All reactions