Struct AdmissionSnapshot 

pub struct AdmissionSnapshot {
    pub slots: Vec<ResidentSlotSnapshot>,
    pub queued: Vec<QueuedModelSnapshot>,
    pub total_queued: u64,
    pub total_swaps: u64,
    pub secondary_slot: SecondarySlotStatus,
}

Everything the admission queue and resident set look like right now.

Fields

slots: Vec<ResidentSlotSnapshot>

Models resident in VRAM, primary first. Empty before anything has been launched.

queued: Vec<QueuedModelSnapshot>

Models with requests waiting, oldest waiter first. Empty in the steady state — a non-empty list means traffic is being batched behind a swap.

total_queued: u64

Requests that have waited in the queue since the runtime started. Compare against Self::total_swaps: a large ratio is the queue doing its job, batching many requests behind one swap.

total_swaps: u64

Model swaps performed since the runtime started.

secondary_slot: SecondarySlotStatus

Why the second slot is or is not in use.

Implementations

impl AdmissionSnapshot

pub fn waiting(&self) -> usize

Total requests waiting across every model.

pub fn inflight(&self) -> u32

Total requests currently being served across every resident slot.

Trait Implementations

impl Clone for AdmissionSnapshot

fn clone(&self) -> AdmissionSnapshot

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for AdmissionSnapshot

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for AdmissionSnapshot

fn default() -> AdmissionSnapshot

Returns the “default value” for a type.

impl PartialEq for AdmissionSnapshot

fn eq(&self, other: &AdmissionSnapshot) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for AdmissionSnapshot

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Eq for AdmissionSnapshot

impl StructuralPartialEq for AdmissionSnapshot