Struct KvSlotRequest 

pub struct KvSlotRequest {
    pub cache_id: String,
    pub target_len: usize,
    pub admission_target_len: Option<usize>,
}

One model-owned KV slot reservation request.

cache_id is the executor/model cache key attached to a sequence. target_len is the sequence length that must be writable before the next forward runs. admission_target_len, when present, is a larger known-context bound used only for admission fit checks. Paged models must not allocate future blocks for it; it mirrors vLLM’s chunked-prefill full-context fit gate.

Fields

cache_id: String

target_len: usize

admission_target_len: Option<usize>

Trait Implementations

impl Clone for KvSlotRequest

fn clone(&self) -> KvSlotRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for KvSlotRequest

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for KvSlotRequest

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for KvSlotRequest

impl PartialEq for KvSlotRequest

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for KvSlotRequest

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 KvSlotRequest