Struct KvCacheState 

pub struct KvCacheState {
    pub past_len: usize,
    pub layers_k: Vec<Vec<f32>>,
    pub layers_v: Vec<Vec<f32>>,
}

Layer-wise past K/V tensors in row-major [past_len * kv_dim] layout per layer.

Fields

past_len: usize

layers_k: Vec<Vec<f32>>

layers_v: Vec<Vec<f32>>

Implementations

impl LayerKvCache

pub fn from_layer_outputs( num_layers: usize, batch: usize, past_seq: usize, kv_dim: usize, outputs: &[Vec<f32>], ) -> Result<LayerKvCache, String>

pub fn pad_layers_to_upper( &self, upper: u64, kv_dim: usize, ) -> (Vec<Vec<f32>>, Vec<Vec<f32>>)

Pad each layer’s K/V to upper rows along the sequence axis (kv_dim inner).

pub fn advance_from_decode_outputs( &mut self, outputs: Vec<Vec<f32>>, _batch: usize, kv_dim: usize, ) -> Result<(), String>

Update cache from decode outputs: [logits, k0, v0, k1, v1, …] (bucket-padded).

Trait Implementations

impl Clone for LayerKvCache

fn clone(&self) -> LayerKvCache

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LayerKvCache

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

Formats the value using the given formatter.