Struct KvCacheEstimate 

pub struct KvCacheEstimate {
    pub total_gpu_capacity_bytes: u64,
    pub total_kv_size_bytes: u64,
    pub kv_size_per_token_bytes: u64,
    pub total_kv_size_tokens: u64,
    pub source: EstimateSource,
    pub memory_breakdown: Option<MemoryBreakdown>,
    pub tolerance_adjusted: Option<KvCacheEstimateAdjusted>,
}

KV-cache memory estimate.

Fields

total_gpu_capacity_bytes: u64

total_kv_size_bytes: u64

kv_size_per_token_bytes: u64

total_kv_size_tokens: u64

source: EstimateSource

memory_breakdown: Option<MemoryBreakdown>

Some on the native path; None on the naive fallback.

tolerance_adjusted: Option<KvCacheEstimateAdjusted>

Some iff tolerance_fraction set; None for the raw estimate.

Trait Implementations

impl Clone for KvCacheEstimate

fn clone(&self) -> KvCacheEstimate

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for KvCacheEstimate

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for KvCacheEstimate

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for KvCacheEstimate

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for KvCacheEstimate

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 KvCacheEstimate