From ba44e7b7a474cb26ec88c9292e8e755ea5652f40 Mon Sep 17 00:00:00 2001
From: lalala-sh <Jiaxing.Wen@amd.com>
Date: Fri, 21 Nov 2025 09:27:05 +0800
Subject: [PATCH] fix static assert (#3178)

Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>

[ROCm/composable_kernel commit: f58bd56e6bd8d1981253e64345ac3caa336bda7b]
---
 .../gpu/device/impl/device_moe_mx_gemm_bpreshuffle.hpp          | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/ck/tensor_operation/gpu/device/impl/device_moe_mx_gemm_bpreshuffle.hpp b/include/ck/tensor_operation/gpu/device/impl/device_moe_mx_gemm_bpreshuffle.hpp
index 6b2228f439..e64970145b 100644
--- a/include/ck/tensor_operation/gpu/device/impl/device_moe_mx_gemm_bpreshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_moe_mx_gemm_bpreshuffle.hpp
@@ -122,7 +122,7 @@ struct DeviceMoeGemmMXBPreShuffle : public DeviceMoEGemmMXBPreShuffle<ALayout,
         MPerXDL,
         NPerXDL,
         MXdlPerWave,
-        math::max(2, NXdlPerWave_),
+        math::max(CShuffleNXdlPerWavePerShuffle, NXdlPerWave_),
         ABlockTransferThreadClusterLengths_AK0_M_AK1,
         ABlockTransferThreadClusterArrangeOrder,
         ABlockTransferSrcAccessOrder,