Skip to content
conftrace_

fused dot-product attention

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

sliding window attention (1) cuda kernel (1) memory bandwidth (1) fused kernel (1) self attention (1) neighborhood attention (1) kernel optimization (1) transformer architecture (1)

Papers

Faster Neighborhood Attention: Reducing the O(n^2) Cost of Self Attention at the Threadblock Level NeurIPS 2024