onnxruntime/include/onnxruntime/core
Edward Chen 9f942e1a3e
Graph transformer to ensure unique DQ nodes for QDQ node units (#15145)
### Description
<!-- Describe your changes. -->

Add required graph transformer to duplicate DQ nodes to ensure that QDQ
node units have unique DQ nodes. This condition is necessary for QDQ
node unit processing.

### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

There is an existing Python utility that does this: 

c7ced7a5e9/tools/python/util/qdq_helpers/qdq_model_utils.py (L77)

This PR implements it as a graph transformer so it is integrated into
ORT and does not require a separate step to update the model. There are
also tests to ensure that its effects are not undone by basic level
graph optimizations.
2023-03-31 08:39:43 +10:00
..
common Graph transformer to ensure unique DQ nodes for QDQ node units (#15145) 2023-03-31 08:39:43 +10:00
eager support register external ep lib information (#8897) 2021-08-31 20:51:22 -07:00
framework FasterTransformer model wrapper using custom op (#15013) 2023-03-20 09:05:30 -07:00
graph Graph transformer to ensure unique DQ nodes for QDQ node units (#15145) 2023-03-31 08:39:43 +10:00
optimizer Graph transformer to ensure unique DQ nodes for QDQ node units (#15145) 2023-03-31 08:39:43 +10:00
platform Improve thread pool creation failure handling. (#13313) 2022-10-15 17:57:19 -07:00
providers [CANN] Multi-stream execution support for CANN EP. (#14058) 2023-03-29 11:57:22 -07:00
session Transpose optimizer enhancements (#15117) 2023-03-28 08:28:17 +10:00