Skip to main content

attention_fallback

burn_tensor::module

Function attention_fallback 

Source 
pub fn attention_fallback<B: Backend>(
    query: Tensor<B, 4>,
    key: Tensor<B, 4>,
    value: Tensor<B, 4>,
    mask: Option<Tensor<B, 4, Bool>>,
    attn_bias: Option<Tensor<B, 4>>,
    options: AttentionModuleOptions,
) -> Tensor<B, 4>
Expand description

Exports attention fallback to test backend’s attention against.