pub struct InferenceMetrics {
pub total_requests: AtomicU64,
pub total_tokens_generated: AtomicU64,
pub total_prompt_tokens: AtomicU64,
pub total_errors: AtomicU64,
}Expand description
Metrics specific to LLM inference.
Fields§
§total_requests: AtomicU64Total requests processed.
total_tokens_generated: AtomicU64Total tokens generated.
total_prompt_tokens: AtomicU64Total prompt tokens processed.
total_errors: AtomicU64Total errors.
Implementations§
Source§impl InferenceMetrics
impl InferenceMetrics
Sourcepub fn record_request(&self, prompt_tokens: u32, completion_tokens: u32)
pub fn record_request(&self, prompt_tokens: u32, completion_tokens: u32)
Records a completed request.
Sourcepub fn record_error(&self)
pub fn record_error(&self)
Records an error.
Sourcepub fn tokens_generated(&self) -> u64
pub fn tokens_generated(&self) -> u64
Returns the total tokens generated.
Trait Implementations§
Source§impl Default for InferenceMetrics
impl Default for InferenceMetrics
Source§fn default() -> InferenceMetrics
fn default() -> InferenceMetrics
Returns the “default value” for a type. Read more
Auto Trait Implementations§
impl !Freeze for InferenceMetrics
impl RefUnwindSafe for InferenceMetrics
impl Send for InferenceMetrics
impl Sync for InferenceMetrics
impl Unpin for InferenceMetrics
impl UnwindSafe for InferenceMetrics
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
Source§impl<T> FutureExt for T
impl<T> FutureExt for T
Source§fn with_context(self, otel_cx: Context) -> WithContext<Self>
fn with_context(self, otel_cx: Context) -> WithContext<Self>
Source§fn with_current_context(self) -> WithContext<Self>
fn with_current_context(self) -> WithContext<Self>
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>
Wrap the input message
T in a tonic::Request