torchao.dtypes¶

`to_nf4`
`to_affine_quantized_intx`
`to_affine_quantized_intx_static`
`to_affine_quantized_floatx`
`to_affine_quantized_floatx_static`
`to_affine_quantized_fpx`
`NF4Tensor`	NF4Tensor class for converting a weight to the QLoRA NF4 format
`AffineQuantizedTensor`	Affine quantized tensor subclass. Affine quantization means we quantize the floating point tensor with an affine transformation:

Docs