pub struct ModelEndpoint {
pub id: String,
pub url: String,
pub weight: u32,
pub max_rps: f64,
pub healthy: bool,
pub latency_p99_ms: f64,
}Expand description
A single model inference endpoint.
Fields§
§id: StringUnique identifier for this endpoint (e.g. "gpt-4o-primary").
url: StringBase URL of the endpoint (e.g. "https://api.openai.com/v1").
weight: u32Relative weight used for weighted round-robin selection. Higher weight = more traffic. Must be > 0.
max_rps: f64Maximum requests per second this endpoint can sustain.
healthy: boolWhether this endpoint is currently considered healthy.
latency_p99_ms: f6499th-percentile observed latency in milliseconds.
Trait Implementations§
Source§impl Clone for ModelEndpoint
impl Clone for ModelEndpoint
Source§fn clone(&self) -> ModelEndpoint
fn clone(&self) -> ModelEndpoint
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 ModelEndpoint
impl RefUnwindSafe for ModelEndpoint
impl Send for ModelEndpoint
impl Sync for ModelEndpoint
impl Unpin for ModelEndpoint
impl UnsafeUnpin for ModelEndpoint
impl UnwindSafe for ModelEndpoint
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> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
§impl<T> FutureExt for T
impl<T> FutureExt for T
§fn with_context(self, otel_cx: Context) -> WithContext<Self>
fn with_context(self, otel_cx: Context) -> WithContext<Self>
§fn with_current_context(self) -> WithContext<Self>
fn with_current_context(self) -> WithContext<Self>
§impl<T> Instrument for T
impl<T> Instrument for T
§fn instrument(self, span: Span) -> Instrumented<Self>
fn instrument(self, span: Span) -> Instrumented<Self>
§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