Struct Shape 

pub struct Shape(/* private fields */);

The dimensions of a tensor, outermost first.

A rank-0 shape (no dimensions) is a scalar and has exactly one element — not zero. That is the convention every tensor library converges on, and getting it wrong makes reductions (which produce scalars) special-cased everywhere.

Shape owns its dimensions in a Vec. Inference shapes are small (rank 4 at most, in practice) and created once per tensor, not per element, so the allocation is not on any hot path — and a fixed-size inline array would impose an arbitrary maximum rank for no measurable gain.

Implementations

impl Shape

pub fn new(dims: impl Into<Vec<usize>>) -> Shape

pub fn scalar() -> Shape

The scalar shape: rank 0, one element.

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

pub fn rank(&self) -> usize

Number of dimensions. Zero for a scalar.

pub fn elem_count(&self) -> usize

Total number of elements: the product of all dimensions.

An empty product is 1, so a scalar correctly reports one element. A shape containing a zero dimension correctly reports zero.

pub fn strides(&self) -> Vec<usize>

Row-major (C-order) strides, in elements, for this shape.

Row-major means the last dimension is contiguous — walking it steps one element at a time. This is the layout GGUF and SafeTensors both store weights in, so choosing it as the default avoids transposing every tensor at load time.

pub fn reshape(&self, dims: impl Into<Vec<usize>>) -> Result<Shape, Error>

Reinterprets this shape as dims, which must describe the same number of elements.

This is the shape-level half of a reshape; it says nothing about whether the underlying storage is contiguous enough to allow the reinterpretation without copying. That check belongs to the tensor.

pub fn broadcast(&self, other: &Shape) -> Result<Shape, Error>

The shape resulting from broadcasting self against other, or an error if the two are not broadcast-compatible.

Follows the standard NumPy rule: align shapes from the right; two dimensions are compatible when they are equal or one of them is 1; the result takes the larger of each pair. Missing leading dimensions on the shorter shape are treated as 1.

Trait Implementations

impl Clone for Shape

fn clone(&self) -> Shape

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Shape

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

Formats the value using the given formatter.

impl Default for Shape

fn default() -> Shape

Returns the “default value” for a type.

impl Display for Shape

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

Formats the value using the given formatter.

impl Eq for Shape

impl From<&[usize]> for Shape

fn from(dims: &[usize]) -> Shape

Converts to this type from the input type.

impl From<Vec<usize>> for Shape

fn from(dims: Vec<usize>) -> Shape

Converts to this type from the input type.

impl<const N: usize> From<[usize; N]> for Shape

fn from(dims: [usize; N]) -> Shape

Converts to this type from the input type.

impl Hash for Shape

fn hash<__H>(&self, state: &mut __H)

where __H: Hasher,

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl PartialEq for Shape

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

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for Shape