pub struct InferenceRequest {
pub request_id: RequestId,
pub sequence_length: usize,
pub max_new_tokens: usize,
pub priority: Priority,
pub arrival_time_ns: u64,
pub deadline_ns: Option<u64>,
}Expand description
An incoming inference request.
Fields§
§request_id: RequestIdUnique request identifier.
sequence_length: usizeNumber of input (prompt) tokens.
max_new_tokens: usizeMaximum number of tokens to generate.
priority: PriorityScheduling priority.
arrival_time_ns: u64Monotonic arrival timestamp in nanoseconds.
deadline_ns: Option<u64>Optional hard deadline in nanoseconds (absolute).
Trait Implementations§
Source§impl Clone for InferenceRequest
impl Clone for InferenceRequest
Source§fn clone(&self) -> InferenceRequest
fn clone(&self) -> InferenceRequest
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 InferenceRequest
impl RefUnwindSafe for InferenceRequest
impl Send for InferenceRequest
impl Sync for InferenceRequest
impl Unpin for InferenceRequest
impl UnsafeUnpin for InferenceRequest
impl UnwindSafe for InferenceRequest
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