default_qat_qconfig_v2¶
-
torch.quantization.qconfig.default_qat_qconfig_v2¶ Fused version of default_qat_config, has performance benefits.
alias of
torch.ao.quantization.qconfig.QConfig(activation=functools.partial(<class 'torch.ao.quantization.fake_quantize.FusedMovingAvgObsFakeQuantize'>, observer=<class 'torch.ao.quantization.observer.MovingAverageMinMaxObserver'>, quant_min=0, quant_max=255, dtype=torch.quint8){}, weight=functools.partial(<class 'torch.ao.quantization.fake_quantize.FusedMovingAvgObsFakeQuantize'>, observer=<class 'torch.ao.quantization.observer.MovingAverageMinMaxObserver'>, quant_min=-128, quant_max=127, dtype=torch.qint8, qscheme=torch.per_tensor_symmetric){})
