quant_linear

Quantized Linear.

Classes

`Linear`	alias of `QuantLinear`
`QuantLinear`	Quantized version of nn.Linear.

class QuantLinear

Bases: _LegacyQuantLinearConvBaseMixin, Linear

Quantized version of nn.Linear.

default_quant_desc_weight = QuantizerAttributeConfig(enable=True, num_bits=8, axis=0, fake_quant=True, unsigned=False, narrow_range=False, learn_amax=False, type='static', block_sizes=None, trt_high_precision_dtype='Float', calibrator='max')