Struct FlashAttentionConfig 

pub struct FlashAttentionConfig {
    pub block_size: usize,
    pub dimensions: usize,
    pub temperature: f32,
}

Configuration for Flash Attention.

Fields

block_size: usize

Block size for tiled computation (tune to L1 cache). Default 64 works well for typical f32 vectors.

dimensions: usize

Embedding dimensionality.

temperature: f32

Softmax temperature scaling.

Trait Implementations

impl Clone for FlashAttentionConfig

fn clone(&self) -> FlashAttentionConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for FlashAttentionConfig

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

Formats the value using the given formatter.

impl Default for FlashAttentionConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for FlashAttentionConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for FlashAttentionConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.