From c5239d83123297e28d4cf7bb51bbf307bb4eaf4e Mon Sep 17 00:00:00 2001 From: Ali Hassani <68103095+alihassanijr@users.noreply.github.com> Date: Wed, 10 Jul 2024 11:09:13 -0400 Subject: [PATCH] Add Faster Neighborhood Attention to pubs (#1471) --- PUBLICATIONS.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/PUBLICATIONS.md b/PUBLICATIONS.md index 32b76e5f..65d1f08e 100644 --- a/PUBLICATIONS.md +++ b/PUBLICATIONS.md @@ -1,5 +1,9 @@ # Publications Using Cutlass +## 2024 + +- ["Faster Neighborhood Attention: Reducing the O(n^2) Cost of Self Attention at the Threadblock Level"](https://arxiv.org/abs/2403.04690). Ali Hassani, Wen-Mei Hwu, Humphrey Shi. _arXiv_, March 2024. + ## 2023 - ["A Case Study in CUDA Kernel Fusion: Implementing FlashAttention-2 on NVIDIA Hopper Architecture using the CUTLASS Library"](https://arxiv.org/abs/2312.11918). Ganesh Bikshandi, Jay Shah. _arXiv_, December 2023.