pub struct StrategyDirect {
pub max_queue_delay_microseconds: u64,
pub minimum_slot_utilization: f32,
}Expand description
@@ .. cpp:var:: message StrategyDirect @@ @@ The sequence batcher uses a specific, unique batch @@ slot for each sequence. All inference requests in a @@ sequence are directed to the same batch slot in the same @@ model instance over the lifetime of the sequence. This @@ is the default strategy. @@
Fields§
§max_queue_delay_microseconds: u64@@ .. cpp:var:: uint64 max_queue_delay_microseconds @@ @@ The maximum time, in microseconds, a candidate request @@ will be delayed in the sequence batch scheduling queue to @@ wait for additional requests for batching. Default is 0. @@
minimum_slot_utilization: f32@@ .. cpp:var:: float minimum_slot_utilization @@ @@ The minimum slot utilization that must be satisfied to @@ execute the batch before ‘max_queue_delay_microseconds’ expires. @@ For example, a value of 0.5 indicates that the batch should be @@ executed as soon as 50% or more of the slots are ready even if @@ the ‘max_queue_delay_microseconds’ timeout has not expired. @@ The default is 0.0, indicating that a batch will be executed @@ before ‘max_queue_delay_microseconds’ timeout expires if at least @@ one batch slot is ready. ‘max_queue_delay_microseconds’ will be @@ ignored unless minimum_slot_utilization is set to a non-zero @@ value. @@
Trait Implementations§
Source§impl Clone for StrategyDirect
impl Clone for StrategyDirect
Source§fn clone(&self) -> StrategyDirect
fn clone(&self) -> StrategyDirect
1.0.0 · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
source. Read moreSource§impl Debug for StrategyDirect
impl Debug for StrategyDirect
Source§impl Default for StrategyDirect
impl Default for StrategyDirect
Source§impl Message for StrategyDirect
impl Message for StrategyDirect
Source§fn encoded_len(&self) -> usize
fn encoded_len(&self) -> usize
Source§fn encode<B>(&self, buf: &mut B) -> Result<(), EncodeError>
fn encode<B>(&self, buf: &mut B) -> Result<(), EncodeError>
Source§fn encode_to_vec(&self) -> Vec<u8> ⓘwhere
Self: Sized,
fn encode_to_vec(&self) -> Vec<u8> ⓘwhere
Self: Sized,
Source§fn encode_length_delimited<B>(&self, buf: &mut B) -> Result<(), EncodeError>
fn encode_length_delimited<B>(&self, buf: &mut B) -> Result<(), EncodeError>
Source§fn encode_length_delimited_to_vec(&self) -> Vec<u8> ⓘwhere
Self: Sized,
fn encode_length_delimited_to_vec(&self) -> Vec<u8> ⓘwhere
Self: Sized,
Source§fn decode<B>(buf: B) -> Result<Self, DecodeError>
fn decode<B>(buf: B) -> Result<Self, DecodeError>
Source§fn decode_length_delimited<B>(buf: B) -> Result<Self, DecodeError>
fn decode_length_delimited<B>(buf: B) -> Result<Self, DecodeError>
Source§fn merge<B>(&mut self, buf: B) -> Result<(), DecodeError>
fn merge<B>(&mut self, buf: B) -> Result<(), DecodeError>
self. Read moreSource§fn merge_length_delimited<B>(&mut self, buf: B) -> Result<(), DecodeError>
fn merge_length_delimited<B>(&mut self, buf: B) -> Result<(), DecodeError>
self.Source§impl PartialEq for StrategyDirect
impl PartialEq for StrategyDirect
impl StructuralPartialEq for StrategyDirect
Auto Trait Implementations§
impl Freeze for StrategyDirect
impl RefUnwindSafe for StrategyDirect
impl Send for StrategyDirect
impl Sync for StrategyDirect
impl Unpin for StrategyDirect
impl UnwindSafe for StrategyDirect
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
Source§impl<T> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
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>
T in a tonic::Request