pub struct RuntimeModelPrediction {
pub response: PredictResponse,
pub endpoint_total_ns: Option<u64>,
pub phases: EndpointPhases,
pub group_size: Option<u64>,
}Expand description
The model’s predict reply plus the endpoint-local op duration the peer stamped.
Fields§
§response: PredictResponse§endpoint_total_ns: Option<u64>Endpoint-local op duration (ns) from JoinResponse.endpoint_total_ns.
phases: EndpointPhasesThe peer’s split of that duration, plus its queue wait and slot depth; all-zero from a peer that sends none.
group_size: Option<u64>Lanes fused into the model forward this predict rode in (1 = a lone
predict). None when the transport does not group predicts; recorded
as the group.size telemetry metric when present.
Auto Trait Implementations§
impl Freeze for RuntimeModelPrediction
impl RefUnwindSafe for RuntimeModelPrediction
impl Send for RuntimeModelPrediction
impl Sync for RuntimeModelPrediction
impl Unpin for RuntimeModelPrediction
impl UnsafeUnpin for RuntimeModelPrediction
impl UnwindSafe for RuntimeModelPrediction
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
impl<ST, DT> CastableFrom<ST, Initialized, Initialized> for DT
impl<ST, DT> CastableFrom<ST, Uninit, Uninit> for DT
Source§impl<T> Instrument for T
impl<T> Instrument for T
Source§fn instrument(self, span: Span) -> Instrumented<Self> ⓘ
fn instrument(self, span: Span) -> Instrumented<Self> ⓘ
Source§fn in_current_span(self) -> Instrumented<Self> ⓘ
fn in_current_span(self) -> Instrumented<Self> ⓘ
Source§impl<T> IntoRequest<T> for T
impl<T> IntoRequest<T> for T
Source§fn into_request(self) -> Request<T>
fn into_request(self) -> Request<T>
Wrap the input message
T in a tonic::Request