QuantizedRowParallelLinear¶

class paddle.nn.quant.quant_layers. QuantizedRowParallelLinear ( layer, weight_bits=8, activation_bits=8, moving_rate=0.9, weight_quantize_type='abs_max', activation_quantize_type='abs_max', weight_pre_layer=None, act_pre_layer=None, weight_quant_layer=None, act_quant_layer=None ) [source]

forward ( input )

forward¶

Defines the computation performed at every call. Should be overridden by all subclasses.

Parameters

• *inputs (tuple) – unpacked tuple arguments

• **kwargs (dict) – unpacked dict arguments