https://github.com/NVIDIA/Model-Optimizer/tree/main/examples/onnx_ptq#prepare-calibration-data > For Int4 quantization, it is recommended to set --calibration_data_size=64. Why int4 quant use special data size setting ?
https://github.com/NVIDIA/Model-Optimizer/tree/main/examples/onnx_ptq#prepare-calibration-data
Why int4 quant use special data size setting ?