onnxruntime/onnxruntime/python/tools/quantization/fusions
Adrian Lizarraga 4838cb6b3e
[QNN Quantization] Ensure fused nodes have names (#19650)
### Description
- Updates the `qnn_preprocess_model()` method to set a name for any new
nodes added to the graph (due to fusion).
- Updates the `qnn_preprocess_model()` method to set a name for any
unnamed nodes that previously existed in the original graph.
- Adds unit tests for fusions (previously missing)
  - Checks that fused node names exist and are unique
  - Checks that fused graph is equivalent to original graph


### Motivation and Context
Nodes are not strictly required to have names. However, a
planned/upcoming feature to support mixed-precision (integer) quantized
models needs nodes to have names.
2024-02-27 02:27:35 -08:00
..
__init__.py
fusion.py [QNN Quantization] Ensure fused nodes have names (#19650) 2024-02-27 02:27:35 -08:00
fusion_gelu.py [QNN Quantization] Ensure fused nodes have names (#19650) 2024-02-27 02:27:35 -08:00
fusion_layernorm.py [QNN Quantization] Ensure fused nodes have names (#19650) 2024-02-27 02:27:35 -08:00