Skip to navigation

Struct LlmOptimization Summary

View as Markdown

Generated from cargo doc --no-deps -p nemo-relay-builtins -p nemo-relay-diagnostics -p nemo-relay-logging -p nemo-relay-plugin-host -p nemo-relay-codecs -p nemo-relay -p nemo-relay-runtime -p nemo-relay-model-pricing -p nemo-relay-resource-metrics -p nemo-relay-observability -p nemo-relay-adaptive -p nemo-relay-pii-redaction -p nemo-relay-ffi -p nemo-relay-types -p nemo-relay-plugin -p nemo-relay-worker-proto -p nemo-relay-worker.

pub struct LlmOptimizationSummary {Show 14 fields
    pub schema_version: String,
    pub calculation_version: String,
    pub status: i32,
    pub limitations: Vec<String>,
    pub baseline_model: Option<LlmOptimizationModel>,
    pub effective_model: Option<LlmOptimizationModel>,
    pub effective_usage: Option<Usage>,
    pub baseline_usage: Option<Usage>,
    pub tokens_saved: Option<LlmOptimizationTokens>,
    pub baseline_cost: Option<CostEstimate>,
    pub actual_cost: Option<CostEstimate>,
    pub estimated_cost_saved: Option<f64>,
    pub currency: Option<String>,
    pub contributions: Vec<LlmOptimizationContribution>,
}

Host-computed optimization accounting at completed LLM scope closure.

Fields

schema_version: String

Versions of the optimization report/calculation, not the worker protocol.

calculation_version: String

Arithmetic implementation version.

status: i32

Whether all accounting inputs were available.

limitations: Vec<String>

Machine-readable reasons for partial accounting.

baseline_model: Option<LlmOptimizationModel>

Counterfactual model used for baseline pricing.

effective_model: Option<LlmOptimizationModel>

Model that actually served the terminal response.

effective_usage: Option<Usage>

Usage observed on the effective response.

baseline_usage: Option<Usage>

Counterfactual usage derived from observed usage plus explicit savings.

tokens_saved: Option<LlmOptimizationTokens>

Explicit aggregate token reductions, retained independently from pricing.

baseline_cost: Option<CostEstimate>

Estimated cost for baseline model/usage.

actual_cost: Option<CostEstimate>

Provider-reported or Relay-estimated actual cost.

estimated_cost_saved: Option<f64>

Baseline cost minus actual cost when both share a currency.

currency: Option<String>

Currency for estimated_cost_saved.

contributions: Vec<LlmOptimizationContribution>

Ordered, bounded source evidence used by the calculation.

Implementations

impl LlmOptimizationSummary

impl LlmOptimizationSummary

status

pub fn status(&self) -> LlmOptimizationSummaryStatus

Returns the enum value of status, or the default if the field is set to an invalid enum value.

set_status

pub fn set_status(&mut self, value: LlmOptimizationSummaryStatus)

Sets status to the provided enum value.

estimated_cost_saved

pub fn estimated_cost_saved(&self) -> f64

Returns the value of estimated_cost_saved, or the default value if estimated_cost_saved is unset.

currency

pub fn currency(&self) -> &str

Returns the value of currency, or the default value if currency is unset.

Trait Implementations

impl Clone for LlmOptimizationSummary

impl Clone for LlmOptimizationSummary

clone

fn clone(&self) -> LlmOptimizationSummary

clone_from

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

impl Debug for LlmOptimizationSummary

impl Debug for LlmOptimizationSummary

fmt

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

impl Default for LlmOptimizationSummary

impl Default for LlmOptimizationSummary

default

fn default() -> Self

impl Message for LlmOptimizationSummary

impl Message for LlmOptimizationSummary

encoded_len

fn encoded_len(&self) -> usize

clear

fn clear(&mut self)

encode

fn encode(&self, buf: &mut impl BufMut) -> Result<(), EncodeError>where
    Self: Sized,

encode_to_vec

fn encode_to_vec(&self) -> Vec<u8> where
    Self: Sized,

encode_length_delimited

fn encode_length_delimited(
    &self,
    buf: &mut impl BufMut,
) -> Result<(), EncodeError>where
    Self: Sized,

encode_length_delimited_to_vec

fn encode_length_delimited_to_vec(&self) -> Vec<u8> where
    Self: Sized,

decode

fn decode(buf: impl Buf) -> Result<Self, DecodeError>where
    Self: Default,

decode_length_delimited

fn decode_length_delimited(buf: impl Buf) -> Result<Self, DecodeError>where
    Self: Default,

merge

fn merge(&mut self, buf: impl Buf) -> Result<(), DecodeError>where
    Self: Sized,

merge_length_delimited

fn merge_length_delimited(&mut self, buf: impl Buf) -> Result<(), DecodeError>where
    Self: Sized,

impl Name for LlmOptimizationSummary

impl Name for LlmOptimizationSummary

NAME

const NAME: &'static str = "LlmOptimizationSummary"

PACKAGE

const PACKAGE: &'static str = "nvidia.nemo.relay.worker.v1"

full_name

fn full_name() -> String

type_url

fn type_url() -> String

impl PartialEq for LlmOptimizationSummary

impl PartialEq for LlmOptimizationSummary

eq

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

ne

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

impl WireValue<LlmOptimizationSummary> for LlmOptimizationSummary

impl WireValue<LlmOptimizationSummary> for LlmOptimizationSummary

to_wire

fn to_wire(self) -> Result<LlmOptimizationSummary>

from_wire

fn from_wire(value: LlmOptimizationSummary) -> Result<Self>

impl StructuralPartialEq for LlmOptimizationSummary

impl StructuralPartialEq for LlmOptimizationSummary