Struct CacheRoutingHint 

pub struct CacheRoutingHint {
    pub prefix_id: u64,
    pub relevant_ranks: Vec<usize>,
    pub reusable_tokens: usize,
}

Describes which ranks need cache data for a given request.

Used by the inference scheduler to decide which ranks to notify when a new request arrives that can reuse cached prefixes.

Fields

prefix_id: u64

The prefix ID to look up.

relevant_ranks: Vec<usize>

Ranks that hold the relevant cache shards.

reusable_tokens: usize

Number of tokens that can be skipped (reused from cache).

Implementations

impl CacheRoutingHint

pub fn new( prefix_id: u64, relevant_ranks: Vec<usize>, reusable_tokens: usize, ) -> Self

Create a routing hint.

pub fn has_targets(&self) -> bool

Whether this hint has any ranks to notify.

Trait Implementations

impl Clone for CacheRoutingHint

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CacheRoutingHint

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for CacheRoutingHint

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for CacheRoutingHint

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

where __S: Serializer,

Serialize this value into the given Serde serializer.