Struct StreamingMultiheadAttention

pub struct StreamingMultiheadAttention { /* private fields */ }

Implementations

impl StreamingMultiheadAttention

pub fn new( cfg: &Config, builder: &KvCacheBuilder, vb: MaybeQuantizedVarBuilder<'_>, ) -> Result<Self>

pub fn is_quantized(&self) -> bool

pub fn forward( &mut self, xs: &Tensor, rope: Option<&Rope>, iam: &IndicesAndMask, ) -> Result<Tensor>

pub fn set_kv_cache(&mut self, kv_cache: KvCache)

Trait Implementations

impl Clone for StreamingMultiheadAttention

fn clone(&self) -> StreamingMultiheadAttention

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for StreamingMultiheadAttention

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

Formats the value using the given formatter.