float_qparams_weight_only_qconfig

torch.quantization.qconfig.float_qparams_weight_only_qconfig

alias of QConfig(activation=<class ‘torch.ao.quantization.observer.PlaceholderObserver’>, weight=functools.partial(<class ‘torch.ao.quantization.observer.PerChannelMinMaxObserver’>, dtype=torch.quint8, qscheme=torch.per_channel_affine_float_qparams, ch_axis=0){})