linear

fastforward.nn.linear.QuantizedLinear

Bases: QuantizedModule, Linear

Quantized implementation of torch.nn.Linear.

bias_quantizer: Quantizer | None instance-attribute

input_quantizer: Quantizer instance-attribute

output_quantizer: Quantizer instance-attribute

weight_quantizer: Quantizer instance-attribute

__init_quantization__()

forward(input)