mindspore_gs.ptq
Post training quantization algorithms.
import mindspore_gs.ptq as ptq
PTQ Config
Config for post trainning quantization. |
PTQMode Enum
Mode for ptq quantizer. |
NetworkHelper
NetworkHelper for decoupling algorithm with network framework. |
|
Derived from 'NetworkHelper', a utility class for the MindFormers framework Llama2 network. |
RoundToNearest Algorithm
Native implementation for post training quantization based on min/max statistic values. |