Struct KvCacheConfig 

pub struct KvCacheConfig {
    pub cache_type: KvCacheType,
    pub block_size: usize,
    pub max_blocks: usize,
    pub enable_compression: bool,
    pub compression_ratio: f32,
    pub enable_multi_level: bool,
    pub swap_threshold: f32,
    pub enable_prefix_caching: bool,
    pub prefix_cache_size: usize,
}

KV Cache configuration

Fields

cache_type: KvCacheType

Cache implementation type

block_size: usize

Block size for paged attention

max_blocks: usize

Maximum number of blocks

enable_compression: bool

Enable cache compression

compression_ratio: f32

Compression ratio target

enable_multi_level: bool

Enable multi-level caching (GPU + CPU)

swap_threshold: f32

Swap threshold (when to move to CPU)

enable_prefix_caching: bool

Enable prefix caching

prefix_cache_size: usize

Prefix cache size

Trait Implementations

impl Clone for KvCacheConfig

fn clone(&self) -> KvCacheConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for KvCacheConfig

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

Formats the value using the given formatter.

impl Default for KvCacheConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for KvCacheConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for KvCacheConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.