Enum TensorDtype 

pub enum TensorDtype {
    F64,
    F32,
    F16,
    BF16,
    I64,
    I32,
    I16,
    I8,
    U64,
    U32,
    U16,
    U8,
    Bool,
}

Element dtypes supported by the loaders.

Variants

F64

IEEE 64-bit float.

F32

IEEE 32-bit float.

F16

IEEE 16-bit half float.

BF16

bfloat16.

I64

Signed 64-bit integer.

I32

Signed 32-bit integer.

I16

Signed 16-bit integer.

I8

Signed 8-bit integer.

U64

Unsigned 64-bit integer.

U32

Unsigned 32-bit integer.

U16

Unsigned 16-bit integer.

U8

Unsigned 8-bit integer (raw packed data, e.g. quantized weights).

Bool

Boolean (stored as one byte).

Implementations

impl TensorDtype

pub fn size(&self) -> usize

Byte size of one element.

Trait Implementations

impl Clone for TensorDtype

fn clone(&self) -> TensorDtype

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Copy for TensorDtype

impl Debug for TensorDtype

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Display for TensorDtype

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Eq for TensorDtype

impl PartialEq for TensorDtype

fn eq(&self, other: &TensorDtype) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl StructuralPartialEq for TensorDtype