neural_compressor.onnxrt.quantization

Package Contents

Classes

CalibrationDataReader	Get data for calibration.
RTNConfig	Config class for round-to-nearest weight-only quantization.
GPTQConfig	Config class for gptq weight-only quantization.
AWQConfig	Config class for awq weight-only quantization.
SmoohQuantConfig	Smooth quant quantization config.

Functions

smooth_quant_entry(→ onnx.ModelProto)	Apply smooth quant.
rtn_quantize_entry(→ onnx.ModelProto)	The main entry to apply rtn quantization.
gptq_quantize_entry(→ onnx.ModelProto)	The main entry to apply gptq quantization.
awq_quantize_entry(→ onnx.ModelProto)	The main entry to apply awq quantization.
get_default_rtn_config(→ RTNConfig)	Generate the default rtn config.
get_default_gptq_config(→ GPTQConfig)	Generate the default gptq config.
get_default_awq_config(→ AWQConfig)	Generate the default awq config.
get_default_sq_config(→ SmoohQuantConfig)	Generate the default smooth quant config.
autotune
get_all_config_set(...)