microsoft / microsoft/onnxruntime
[Performance] QNN EP Leaving QDQ Nodes in the QNN Graph
- Dominant language
- C++
- Stars
- 21.9k
- Forks
- 4.2k
- Avg merge
- 4d 11h
- Merged PRs (30d)
- 184
Description
### Describe the issue
The QNN EP appears to be leaving QDQ nodes in the QNN graph for Mul and Sub, rather than inserting quantized ops. I have included a sample model below.
### To reproduce
See attached model.
Affects Inception_v3 among other models.
### Urgency
_No response_
### Platform
Linux
### OS Version
Ubuntu 22.04
### ONNX Runtime Installation
Built from Source
### ONNX Runtime Version or Commit ID
Latest
### ONNX Runtime API
Python
### Architecture
ARM64
### Execution Provider
QNN EP
### Execution Provider Library Version
QNN 2.20
### Model File
[qdq_min_mul_sub_example.zip](https://github.com/microsoft/onnxruntime/files/15179000/qdq_min_mul_sub_example.zip)
### Is this a quantized model?
Yes
Contributor guide
Assessment
This issue has not been assessed yet.