mlx.core.dequantize

dequantize(w: array, /, scales: array, biases: array | None = None, group_size: int | None = None, bits: int | None = None, mode: str = 'affine', global_scale: array | None = None, dtype: Dtype | None = None, *, stream: None | Stream | Device = None) → array

Dequantize the matrix w using quantization parameters.

參數:

• w (array) -- Matrix to be dequantized

• scales (array) -- The scales to use per group_size elements of w.

• biases (array, optional) -- The biases to use per group_size elements of w. Default: None.

• group_size (int, optional) -- The size of the group in w that shares a scale and bias. See supported values and defaults in the table of quantization modes. Default: None.

• bits (int, optional) -- The number of bits occupied by each element of w in the quantized array. See supported values and defaults in the table of quantization modes. Default: None.

• global_scale (array, optional) -- The per-input float32 scale used for "nvfp4" quantization if provided. Default: None.

• dtype (Dtype, optional) -- The data type of the dequantized output. If None the return type is inferred from the scales and biases when possible and otherwise defaults to bfloat16. Default: None.

• mode (str, optional) -- The quantization mode. Default: "affine".

回傳:

The dequantized version of w

回傳型別:

array

備註

The currently supported quantization modes are "affine", "mxfp4, "mxfp8", and "nvfp4".

For affine quantization, given the notation in quantize(), we compute \(w_i\) from \(\hat{w_i}\) and corresponding \(s\) and \(\beta\) as follows

\[w_i = s \hat{w_i} + \beta\]