from optimum.onnxruntime import ORTQuantizer
from optimum.onnxruntime.configuration import AutoQuantizationConfig
 
# create ORTQuantizer and define quantization configuration
dynamic_quantizer = ORTQuantizer.from_pretrained(model)
dqconfig = AutoQuantizationConfig.avx512_vnni(is_static=False, per_channel=False)
 
# apply the quantization configuration to the model
model_quantized_path = dynamic_quantizer.quantize(
    save_dir=onnx_path,
    quantization_config=dqconfig,
)