From 820ba182a07511b3f05182fef9902ce49690e3ec Mon Sep 17 00:00:00 2001
From: Yi DING <yi.ding@amd.com>
Date: Wed, 25 Jun 2025 07:35:54 +0800
Subject: [PATCH] Fix unmatched K size of
 WarpGemmMfmaBf16Bf16F32M16N16K32TransposedCDistribution on gfx950 (#2393)

[ROCm/composable_kernel commit: c5d9181e1bd8c64110941e244b3d3e1e6c5f6385]
---
 include/ck_tile/ops/gemm/warp/warp_gemm.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/ck_tile/ops/gemm/warp/warp_gemm.hpp b/include/ck_tile/ops/gemm/warp/warp_gemm.hpp
index be5d5690ff..f243aceda8 100644
--- a/include/ck_tile/ops/gemm/warp/warp_gemm.hpp
+++ b/include/ck_tile/ops/gemm/warp/warp_gemm.hpp
@@ -172,7 +172,7 @@ using WarpGemmMfmaBf16Bf16F32M32N32K16TransposedCDistribution =
 #if defined(__gfx950__)
 using WarpGemmMfmaBf16Bf16F32M16N16K32TransposedCDistribution =
     WarpGemmImpl<WarpGemmAtrributeMfmaTransposedCDistribution<
-        WarpGemmAttributeMfmaImplBf16Bf16F32M16N16K16<WGAttrCtlEnum::Default_>>>;
+        WarpGemmAttributeMfmaImplBf16Bf16F32M16N16K32<WGAttrCtlEnum::Default_>>>;
 #else
 using WarpGemmMfmaBf16Bf16F32M16N16K32TransposedCDistribution =
     WarpGemmImpl<WarpGemmAtrributeMfmaIterateKAndTransposedCDistribution<