pub struct QuantizedVector {
pub data: Vec<i8>,
pub scale: f32,
pub zero_point: i8,
}Expand description
Scalar quantization parameters for a single vector.
Fields§
§data: Vec<i8>Quantized int8 values.
scale: f32Scale factor: original[i] ≈ (data[i] - zero_point) * scale
zero_point: i8Quantization zero point, always in the i8 range [-128, 127].
Trait Implementations§
Source§impl Clone for QuantizedVector
impl Clone for QuantizedVector
Source§fn clone(&self) -> QuantizedVector
fn clone(&self) -> QuantizedVector
Returns a duplicate of the value. Read more
1.0.0 (const: unstable) · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
Performs copy-assignment from
source. Read moreAuto Trait Implementations§
impl Freeze for QuantizedVector
impl RefUnwindSafe for QuantizedVector
impl Send for QuantizedVector
impl Sync for QuantizedVector
impl Unpin for QuantizedVector
impl UnsafeUnpin for QuantizedVector
impl UnwindSafe for QuantizedVector
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more