_choose_quant_func_and_quantize_tensor#
- torchao.quantization.quantize_.common._choose_quant_func_and_quantize_tensor(tensor: Tensor, quant_kwargs: QuantizeTensorKwargs, scale: Optional[Tensor] = None) Tensor[source][source]#
Given a tensor and a kwargs container, chooses a derived dtype (float8, int8, etc) to quantize tensor to, based on the type of quant_kwargs quantizes tensor to the derived dtype chosen in (1) This is needed to support flexible quantization of activation to various derived dtypes.
