From 8c1e77fb585c4f42783a3d88c1efc7c9e15fd89f Mon Sep 17 00:00:00 2001
From: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Date: Thu, 28 Nov 2024 08:31:28 -0800
Subject: [PATCH] [Kernel] Update vllm-flash-attn version to reduce CPU
 overheads (#10742)

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
---
 CMakeLists.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/CMakeLists.txt b/CMakeLists.txt
index 45a3b484e0360..f43bf8143458b 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -522,7 +522,7 @@ else()
   FetchContent_Declare(
           vllm-flash-attn
           GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git
-          GIT_TAG d886f88165702b3c7e7744502772cd98b06be9e1
+          GIT_TAG fdf6d72b48aea41f4ae6a89139a453dae554abc8
           GIT_PROGRESS TRUE
           # Don't share the vllm-flash-attn build between build types
           BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn