yamle.quantization.static package

class yamle.quantization.static.StaticQuantizer(activation_bits, weight_bits)

Bases: BaseQuantizer

This is the static quantizer class.

It performs static post-training quantization on the model. It does it with respect to a specific number of bits for the activation and weight. The quantization is simulated and the model is not actually quantized.

prepare(trainer, method)

This method is used to prepare the model for quantization.

Return type:

None

get_qconfig()

This method is used to get the quantization configuration.

We use the number of activation and weight bits to create the quantization configuration.

Return type:

Any