PackedTensor

class onnx_ir.PackedTensor(value, dtype, *, shape, name=None, doc_string=None, metadata_props=None)

A tensor that stores 4bit datatypes in packed format.

Parameters:

• value (TArrayCompatible)

• dtype (_enums.DataType)

• shape (Shape | Sequence[int])

• name (str | None)

• doc_string (str | None)

• metadata_props (dict[str, str] | None)

display(*, page=False)

Pretty print the object.

Parameters:

page (bool) – Whether to page the output.

Return type:

None

property doc_string: str | None

The documentation string.

property dtype: DataType

The data type of the tensor. Immutable.

property meta: MetadataStore

The metadata store for intermediate analysis.

Write to the metadata_props if you would like the metadata to be serialized to the ONNX proto.

property metadata_props: dict[str, str]

property name: str | None

The name of the tensor.

property nbytes: int

The number of bytes in the tensor.

numpy()

Return the tensor as a numpy array.

When the data type is not supported by numpy, the dtypes from the ml_dtype package are used. The values can be reinterpreted as bit representations using the .view() method.

Return type:

ndarray

numpy_packed()

Return the tensor as a packed array.

Return type:

npt.NDArray[np.uint8]

property raw: TArrayCompatible

Backing data of the tensor. Immutable.

property shape: Shape

The shape of the tensor. Immutable.

property size: int

The number of elements in the tensor.

tobytes()

Returns the value as bytes encoded in little endian.

Override this method for more efficient serialization when the raw value is not a numpy array.

Return type:

bytes