Struct KVCacheConfig 

pub struct KVCacheConfig {
    pub num_layers: usize,
    pub num_heads: usize,
    pub head_dim: usize,
    pub max_seq_len: usize,
    pub max_batch_size: usize,
    pub enabled: bool,
}

Configuration for KV-cache

Fields

num_layers: usize

Number of layers in the model

num_heads: usize

Number of attention heads per layer

head_dim: usize

Dimension per attention head (d_k)

max_seq_len: usize

Maximum sequence length to cache

max_batch_size: usize

Maximum batch size

enabled: bool

Whether to enable cache

Implementations

impl KVCacheConfig

pub fn new(num_layers: usize, num_heads: usize, head_dim: usize) -> Self

Create a new KV-cache configuration

pub fn with_max_seq_len(self, max_seq_len: usize) -> Self

Set maximum sequence length

pub fn with_max_batch_size(self, max_batch_size: usize) -> Self

Set maximum batch size

pub fn with_enabled(self, enabled: bool) -> Self

Enable or disable cache

pub fn validate(&self) -> Result<()>

Validate configuration

pub fn memory_usage(&self) -> usize

Calculate memory usage in bytes

pub fn memory_usage_mb(&self) -> f64

Human-readable memory usage

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<'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.