neural_compressor.adaptor.onnxrt

Module Contents

Classes

ONNXRUNTIMEAdaptor	The ONNXRT adaptor layer, do onnx-rt quantization, calibration, inspect layer tensors.
ONNXRT_WeightOnlyAdaptor	The ONNXRT adaptor layer, do onnx-rt quantization, calibration, inspect layer tensors.
ONNXRT_QLinearOpsAdaptor	The ONNXRT adaptor layer, do onnx-rt quantization, calibration, inspect layer tensors.
ONNXRT_IntegerOpsAdaptor	The ONNXRT adaptor layer, do onnx-rt quantization, calibration, inspect layer tensors.
ONNXRT_QDQAdaptor	The ONNXRT adaptor layer, do onnx-rt quantization, calibration, inspect layer tensors.

class neural_compressor.adaptor.onnxrt.ONNXRUNTIMEAdaptor(framework_specific_info)

The ONNXRT adaptor layer, do onnx-rt quantization, calibration, inspect layer tensors.

Parameters:

framework_specific_info (dict) – framework specific configuration for quantization.

class neural_compressor.adaptor.onnxrt.ONNXRT_WeightOnlyAdaptor(framework_specific_info)

The ONNXRT adaptor layer, do onnx-rt quantization, calibration, inspect layer tensors.

Parameters:

framework_specific_info (dict) – framework specific configuration for quantization.

class neural_compressor.adaptor.onnxrt.ONNXRT_QLinearOpsAdaptor(framework_specific_info)

The ONNXRT adaptor layer, do onnx-rt quantization, calibration, inspect layer tensors.

Parameters:

framework_specific_info (dict) – framework specific configuration for quantization.

class neural_compressor.adaptor.onnxrt.ONNXRT_IntegerOpsAdaptor(framework_specific_info)

The ONNXRT adaptor layer, do onnx-rt quantization, calibration, inspect layer tensors.

Parameters:

framework_specific_info (dict) – framework specific configuration for quantization.

class neural_compressor.adaptor.onnxrt.ONNXRT_QDQAdaptor(framework_specific_info)

The ONNXRT adaptor layer, do onnx-rt quantization, calibration, inspect layer tensors.

Parameters:

framework_specific_info (dict) – framework specific configuration for quantization.