Struct CacheBlock

Source

pub struct CacheBlock {
    pub keys: Vec<Vec<f32>>,
    pub values: Vec<Vec<f32>>,
    pub token_ids: Vec<u32>,
    pub last_used: u64,
    pub ref_count: usize,
}

Expand description

One cache block: KV tensors for block_size tokens in every layer.

Fields§

§keys: Vec<Vec<f32>>

key tensors: [num_layers][num_kv_heads * head_dim * block_size] f32

§values: Vec<Vec<f32>>

value tensors: [num_layers][num_kv_heads * head_dim * block_size] f32

§token_ids: Vec<u32>

The exact token IDs this block covers.

§last_used: u64

LRU generation counter — higher means more recently used.

§ref_count: usize

How many live requests are currently using this block.

Implementations§

Source §

impl CacheBlock

Source

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

Allocate a new, zeroed cache block.

Source

pub fn memory_bytes(&self) -> usize

Total memory consumed by this block’s KV tensors in bytes.

Formula: 2 (K+V) × num_layers × per_layer_elements × 4 bytes/f32.

Auto Trait Implementations§

§

impl UnwindSafe for CacheBlock

Blanket Implementations§

Source §

impl<T> Any for T
where T: 'static + ?Sized,

Source §

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more

Source §

impl<T> Borrow<T> for T
where T: ?Sized,

Source §

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more

Source §

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source §

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more

Source §

impl<T> From<T> for T

Source §

fn from(t: T) -> T

Returns the argument unchanged.

Source §

impl<T> Instrument for T

Source §

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided Span, returning an Instrumented wrapper. Read more

Source §

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more

Source §

impl<T, U> Into for T
where U: From<T>,

Source §

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source §

impl<T> IntoEither for T

Source §

fn into_either(self, into_left: bool) -> Either<Self, Self>

Converts self into a Left variant of Either<Self, Self> if into_left is true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more

Source §

fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
where F: FnOnce(&Self) -> bool,

Converts self into a Left variant of Either<Self, Self> if into_left(&self) returns true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more

Source §