to_marlinqqq_quantized_intx#
- torchao.dtypes.to_marlinqqq_quantized_intx(input_float: Tensor, block_size: Tuple[int, ...], quant_min: Optional[int] = None, quant_max: Optional[int] = None, zero_point_domain: ZeroPointDomain = ZeroPointDomain.INT, _layout: Optional[Layout] = None)[source]#
Converts a floating point tensor to a Marlin QQQ quantized tensor.
