Struct TimingTelemetry 

pub struct TimingTelemetry {
    pub load_seconds: f64,
    pub generation_seconds: f64,
    pub time_to_first_token_seconds: Option<f64>,
    pub total_seconds: f64,
    pub token_rate: f64,
    pub decode_token_rate: Option<f64>,
}

Timings reported for one generation request.

Fields

load_seconds: f64

Model load duration in seconds.

generation_seconds: f64

Generation duration in seconds.

time_to_first_token_seconds: Option<f64>

Time to the first emitted token in seconds.

total_seconds: f64

Complete operation duration in seconds.

token_rate: f64

Overall generated-token rate.

decode_token_rate: Option<f64>

Post-first-token decode rate.

Implementations

impl TimingTelemetry

pub fn new( load: Duration, generation: Duration, time_to_first_token: Option<Duration>, generated_tokens: usize, total: Duration, ) -> Self

Builds stable timing metrics from monotonic durations.

Trait Implementations

impl Clone for TimingTelemetry

fn clone(&self) -> TimingTelemetry

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TimingTelemetry

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for TimingTelemetry

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for TimingTelemetry

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for TimingTelemetry

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for TimingTelemetry