Struct Cache Economics | NVIDIA NeMo Relay

Generated from cargo doc --no-deps -p nemo-relay -p nemo-relay-adaptive -p nemo-relay-ffi.

pub struct CacheEconomics {
    pub write_short_multiplier: f64,
    pub write_long_multiplier: Option<f64>,
    pub read_multiplier: f64,
}

Provider/model-specific cache economics used by the internal planner.

These values are kept on the capability surface so the core planner can stay provider-agnostic while concrete plugins/model families supply the pricing model that makes a cache write profitable.

Fields

`write_short_multiplier: f64`

Input cost multiplier for creating a short-lived cache entry.

`write_long_multiplier: Option<f64>`

Optional input cost multiplier for creating a longer-lived cache entry.

`read_multiplier: f64`

Input cost multiplier for reading from cache.

Trait Implementations

`impl Clone for CacheEconomics`

impl Clone for CacheEconomics

`clone`

fn clone(&self) -> CacheEconomics

`clone_from`

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

`impl Debug for CacheEconomics`

impl Debug for CacheEconomics

`fmt`

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

`impl<'de> Deserialize<'de> for CacheEconomics`

impl<'de> Deserialize<'de> for CacheEconomics

`deserialize`

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
    __D: Deserializer<'de>,

`impl PartialEq for CacheEconomics`

impl PartialEq for CacheEconomics

`eq`

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

`ne`

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

`impl Serialize for CacheEconomics`

impl Serialize for CacheEconomics

`serialize`

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

`impl StructuralPartialEq for CacheEconomics`

impl StructuralPartialEq for CacheEconomics