pub struct QuantizePerTokenDescriptor {
pub n: i32,
pub d: i32,
pub q_min: i32,
pub q_max: i32,
pub input_element: ElementKind,
pub output_element: ElementKind,
}Expand description
Descriptor for a quantize_per_token forward op.
Fields§
§n: i32Number of token rows (first axis of input/output).
d: i32Feature dim (second axis of input/output).
q_min: i32Quantization range lower bound (e.g. -128 for s8 symmetric).
q_max: i32Quantization range upper bound (e.g. 127 for s8 symmetric).
input_element: ElementKindInput FP element kind. Must match TIn::KIND.
output_element: ElementKindOutput int element kind (s8 or u8). Must match TOut::KIND.
Trait Implementations§
Source§impl Clone for QuantizePerTokenDescriptor
impl Clone for QuantizePerTokenDescriptor
Source§fn clone(&self) -> QuantizePerTokenDescriptor
fn clone(&self) -> QuantizePerTokenDescriptor
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 moreimpl Copy for QuantizePerTokenDescriptor
Auto Trait Implementations§
impl Freeze for QuantizePerTokenDescriptor
impl RefUnwindSafe for QuantizePerTokenDescriptor
impl Send for QuantizePerTokenDescriptor
impl Sync for QuantizePerTokenDescriptor
impl Unpin for QuantizePerTokenDescriptor
impl UnsafeUnpin for QuantizePerTokenDescriptor
impl UnwindSafe for QuantizePerTokenDescriptor
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