Struct TensorConversion 

pub struct TensorConversion { /* private fields */ }

One source tensor’s explicit artifact location and storage recipe.

Implementations

impl TensorConversion

pub fn verbatim( source_name: impl Into<String>, artifact_name: impl Into<String>, access_class: AccessClass, ) -> Self

Declares a source tensor that remains at its source precision.

pub fn q8_per_output_channel( source_name: impl Into<String>, artifact_name: impl Into<String>, access_class: AccessClass, ) -> Self

Declares a source matrix that uses the shared canonical Q8 quantization primitive.

Trait Implementations

impl Clone for TensorConversion

fn clone(&self) -> TensorConversion

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TensorConversion

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

Formats the value using the given formatter.

impl Eq for TensorConversion

impl PartialEq for TensorConversion

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

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for TensorConversion