Struct Tensor 

pub struct Tensor { /* private fields */ }

An owned, device-aware tensor (docs/EAGER.md §3).

Owns the DeviceBuffer that holds its elements and the EP that must free it. On Phase-1 CPU the buffer is a host allocation, so Tensor::as_bytes and the typed accessors read it directly.

Implementations

impl Tensor

pub fn from_raw_in( allocator: Arc<dyn ExecutionProvider>, dtype: DataType, shape: Vec<usize>, bytes: &[u8], ) -> Result<Self>

Allocate a tensor from raw little-endian element bytes using allocator.

bytes must hold exactly storage_bytes(numel) bytes for dtype and shape.

pub fn zeros_in( allocator: Arc<dyn ExecutionProvider>, dtype: DataType, shape: Vec<usize>, ) -> Result<Self>

Allocate a zero-initialized tensor of shape/dtype using allocator.

Used by dispatch to materialise output tensors before kernel execution (docs/EAGER.md §10.1 step 6).

pub fn from_raw( dtype: DataType, shape: Vec<usize>, bytes: &[u8], ) -> Result<Self>

Build a tensor from raw little-endian bytes on the shared CPU device.

pub fn zeros(dtype: DataType, shape: Vec<usize>) -> Result<Self>

Build a zero-initialized tensor on the shared CPU device.

pub fn from_f32(shape: &[usize], data: &[f32]) -> Result<Self>

Build an f32 tensor from a dense row-major slice on the CPU device.

pub fn from_i64(shape: &[usize], data: &[i64]) -> Result<Self>

Build an i64 tensor from a dense row-major slice on the CPU device.

pub fn dtype(&self) -> DataType

The element type.

pub fn shape(&self) -> &[usize]

The logical shape (static dims).

pub fn layout(&self) -> &TensorLayout

The physical layout (row-major contiguous for tensors this crate produces).

pub fn device(&self) -> DeviceId

The device this tensor lives on.

pub fn numel(&self) -> usize

Number of elements.

pub fn as_bytes(&self) -> &[u8]

Borrow the raw little-endian element bytes (host tensors only).

pub fn to_vec_f32(&self) -> Vec<f32>

Copy out the elements as f32. Panics if the dtype is not Float32.

pub fn to_vec_i64(&self) -> Vec<i64>

Copy out the elements as i64. Panics if the dtype is not Int64.

Trait Implementations

impl Clone for Tensor

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Tensor

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

Formats the value using the given formatter.

impl Drop for Tensor

fn drop(&mut self)

Executes the destructor for this type.

fn pin_drop(self: Pin<&mut Self>)

🔬This is a nightly-only experimental API. (pin_ergonomics)

Execute the destructor for this type, but different to Drop::drop, it requires self to be pinned.