From 3b62d4807fcba158e9ebaf2926ab11aee53be820 Mon Sep 17 00:00:00 2001
From: rocking <ChunYu.Lai@amd.com>
Date: Wed, 10 Jul 2024 06:57:00 +0000
Subject: [PATCH] Add necessary compile flag

---
 setup.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/setup.py b/setup.py
index 511d19520..391eb9254 100644
--- a/setup.py
+++ b/setup.py
@@ -317,6 +317,7 @@ def validate_and_update_archs(archs):
         "nvcc":
             [
                 "-O3","-std=c++17",
+                "-mllvm", "-enable-post-misched=0",
                 "-DCK_TILE_FMHA_FWD_FAST_EXP2=1",
                 "-fgpu-flush-denormals-to-zero",
                 "-DCK_ENABLE_BF16",