neural_compressor.onnxrt.quantization
Package Contents
Classes
|
Get data for calibration. |
|
Config class for round-to-nearest weight-only quantization. |
|
Config class for gptq weight-only quantization. |
|
Config class for awq weight-only quantization. |
|
Smooth quant quantization config. |
Functions
|
Apply smooth quant. |
|
The main entry to apply rtn quantization. |
|
The main entry to apply gptq quantization. |
|
The main entry to apply awq quantization. |
|
Generate the default rtn config. |
|
Generate the default gptq config. |
|
Generate the default awq config. |
|
Generate the default smooth quant config. |
|