torch.ao.quantization.observer.default_float_qparams_observer

torch.ao.quantization.observer.default_float_qparams_observer = functools.partial(<class 'torch.ao.quantization.observer.PerChannelMinMaxObserver'>, dtype=torch.quint8, qscheme=torch.per_channel_affine_float_qparams, ch_axis=0){}

Default observer for a floating point zero-point.

上一页

torch.ao.quantization.observer.default_dynamic_quant_observer

下一页

torch.ao.quantization.observer.default_float_qparams_observer_4bit