default_weight_only_qconfig

torch.quantization.qconfig.default_weight_only_qconfig

alias of QConfig(activation=<class ‘torch.nn.modules.linear.Identity’>, weight=functools.partial(<class ‘torch.ao.quantization.fake_quantize.FakeQuantize’>, observer=<class ‘torch.ao.quantization.observer.MovingAverageMinMaxObserver’>, quant_min=-128, quant_max=127, dtype=torch.qint8, qscheme=torch.per_tensor_symmetric, reduce_range=False){})