.. _op_ai_rt_Dequantize:

Dequantize
==========

- **Domain**: ``ai.rt``
- **Since version**: 1

Decodes a supported EncodedValueProto into the requested floating dtype without changing its logical shape. Rejects malformed layouts, unsupported dtypes, nonfinite reconstructions and output overflow. Supports the portable quantization and ORT MatMulNBits layouts, including model-catalogue type references.

**Inputs**

- **X** (*E*): Structured quantized value.

**Outputs**

- **Y** (*T*): Decoded tensor in the requested dtype.

**Attributes**

- **dtype** (*int*): Required output TensorProto dtype: FLOAT, DOUBLE, FLOAT16 or BFLOAT16.

**Type Constraints**

- **E**: Structured encoded value.
  Allowed types: struct.
- **T**
  Allowed types: tensor(bfloat16), tensor(double), tensor(float), tensor(float16).

Examples
--------

**test_cc_dequantize_int4**

.. code-block:: text

    Node:
      ai.rt.Dequantize(Q) -> (Y)
      Attributes:
        dtype = 11

.. code-block:: text

    Inputs:

    Outputs:
      Y: shape=(3,), dtype=float64
        [-1.,  0.,  1.]

**test_cc_dequantize_nf4**

.. code-block:: text

    Node:
      ai.rt.Dequantize(Q) -> (Y)
      Attributes:
        dtype = 11

.. code-block:: text

    Inputs:

    Outputs:
      Y: shape=(3,), dtype=float64
        [-1.,  0.,  1.]

**test_cc_dequantize_ternary**

.. code-block:: text

    Node:
      ai.rt.Dequantize(Q) -> (Y)
      Attributes:
        dtype = 11

.. code-block:: text

    Inputs:

    Outputs:
      Y: shape=(3,), dtype=float64
        [-1.,  0.,  1.]

**test_cc_dequantize_tiled_float**

.. code-block:: text

    Node:
      ai.rt.Dequantize(Q) -> (Y)
      Attributes:
        dtype = 11

.. code-block:: text

    Inputs:

    Outputs:
      Y: shape=(3,), dtype=float64
        [-1.,  0.,  1.]

**test_cc_quantize_int4**

.. code-block:: text

    Node:
      ai.rt.Dequantize(Q) -> (Y)
      Attributes:
        dtype = 11

.. code-block:: text

    Inputs:
      Q: shape=(3,), dtype=float32
        [-1.,  0.,  1.]

    Outputs:
      Y: shape=(3,), dtype=float64
        [-1.,  0.,  1.]

**test_cc_quantize_nf4**

.. code-block:: text

    Node:
      ai.rt.Dequantize(Q) -> (Y)
      Attributes:
        dtype = 11

.. code-block:: text

    Inputs:
      Q: shape=(3,), dtype=float32
        [-1.,  0.,  1.]

    Outputs:
      Y: shape=(3,), dtype=float64
        [-1.,  0.,  1.]

**test_cc_quantize_ternary**

.. code-block:: text

    Node:
      ai.rt.Dequantize(Q) -> (Y)
      Attributes:
        dtype = 11

.. code-block:: text

    Inputs:
      Q: shape=(3,), dtype=float32
        [-1.,  0.,  1.]

    Outputs:
      Y: shape=(3,), dtype=float64
        [-1.,  0.,  1.]

**test_cc_quantize_tiled_float**

.. code-block:: text

    Node:
      ai.rt.Dequantize(Q) -> (Y)
      Attributes:
        dtype = 11

.. code-block:: text

    Inputs:
      Q: shape=(3,), dtype=float32
        [-1.,  0.,  1.]

    Outputs:
      Y: shape=(3,), dtype=float64
        [-1.,  0.,  1.]