pub struct BatchConfig {
pub max_batch_size: usize,
pub max_wait_ms: u64,
pub group_by_prefix_len: usize,
}Expand description
Configuration for SmartBatcher.
Fields§
§max_batch_size: usizeMaximum number of requests in a single batch.
Defaults to 8. Must be ≥ 1.
max_wait_ms: u64Maximum time (milliseconds) to wait for a batch to fill before flushing with whatever is available.
Defaults to 50 ms.
group_by_prefix_len: usizeLength (in bytes) of the prompt prefix used for similarity grouping.
When > 0, requests are bucketed by their first group_by_prefix_len
bytes. This improves prefix-cache hit rate on compatible servers.
Set to 0 to disable grouping (FIFO ordering).
Defaults to 0.
Trait Implementations§
Source§impl Clone for BatchConfig
impl Clone for BatchConfig
Source§fn clone(&self) -> BatchConfig
fn clone(&self) -> BatchConfig
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 moreSource§impl Debug for BatchConfig
impl Debug for BatchConfig
Auto Trait Implementations§
impl Freeze for BatchConfig
impl RefUnwindSafe for BatchConfig
impl Send for BatchConfig
impl Sync for BatchConfig
impl Unpin for BatchConfig
impl UnsafeUnpin for BatchConfig
impl UnwindSafe for BatchConfig
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