From 41ca7eb49192cbee65986527319c6eb929d6aa7c Mon Sep 17 00:00:00 2001
From: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Date: Thu, 24 Apr 2025 23:12:21 -0400
Subject: [PATCH] [Attention] FA3 decode perf improvement - single mma warp
 group support for head dim 128 (#16864)

Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
---
 cmake/external_projects/vllm_flash_attn.cmake | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/cmake/external_projects/vllm_flash_attn.cmake b/cmake/external_projects/vllm_flash_attn.cmake
index 110ef266c665..c60a54745519 100644
--- a/cmake/external_projects/vllm_flash_attn.cmake
+++ b/cmake/external_projects/vllm_flash_attn.cmake
@@ -38,7 +38,7 @@ else()
   FetchContent_Declare(
           vllm-flash-attn
           GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git
-          GIT_TAG 0a721daebe4fa7149f06ecf3d3eabeb6dcd0f1fa
+          GIT_TAG e93779c59ba4905e56e5c39dc2c1904ada71fa21
           GIT_PROGRESS TRUE
           # Don't share the vllm-flash-attn build between build types
           BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn