Enum KvCacheMemoryFraction 

pub enum KvCacheMemoryFraction {
    OfTotal(f64),
    OfFree(f64),
}

Backend-tagged memory fraction. The variant encodes the XOR between TRT-LLM’s free-fraction and vLLM/SGLang’s total-fraction semantics; the Python estimate_kv_cache validates it against engine.backend and returns an error (mapped to KvCacheEstimateError::IncompatibleMemoryFraction) if mismatched.

Variants

OfTotal(f64)

Fraction of TOTAL GPU memory. Compatible with vLLM (gpu_memory_utilization) and SGLang (mem_fraction_static).

OfFree(f64)

Fraction of FREE (post-non-KV) GPU memory. Compatible with TRT-LLM (free_gpu_memory_fraction).

Trait Implementations

impl Clone for KvCacheMemoryFraction

fn clone(&self) -> KvCacheMemoryFraction

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for KvCacheMemoryFraction

impl Debug for KvCacheMemoryFraction

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for KvCacheMemoryFraction

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for KvCacheMemoryFraction

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for KvCacheMemoryFraction

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 KvCacheMemoryFraction