fix quantization for onnxruntime v1.16.0 (#1405)
* fix quantization for onnxruntime v1.16.0
* Update optimum/onnxruntime/quantization.py
Co-authored-by: fxmarty <9808326+fxmarty@users.noreply.github.com>
* Update optimum/onnxruntime/quantization.py
Co-authored-by: fxmarty <9808326+fxmarty@users.noreply.github.com>
* Update optimum/onnxruntime/quantization.py
Co-authored-by: fxmarty <9808326+fxmarty@users.noreply.github.com>
* skip test for ort v1.16.0
---------
Co-authored-by: fxmarty <9808326+fxmarty@users.noreply.github.com>
