From 6e5b5ca580e60a3b7a6c5613ae7d8676f2c8cbc6 Mon Sep 17 00:00:00 2001
From: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Date: Tue, 22 Jul 2025 02:33:51 -0400
Subject: [PATCH] [Refactor] Fix Compile Warning #1444-D (#21208)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
---
 csrc/moe/topk_softmax_kernels.cu | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/csrc/moe/topk_softmax_kernels.cu b/csrc/moe/topk_softmax_kernels.cu
index 064b76c9c..ea4ff67ef 100644
--- a/csrc/moe/topk_softmax_kernels.cu
+++ b/csrc/moe/topk_softmax_kernels.cu
@@ -20,6 +20,7 @@
 #include <ATen/cuda/CUDAContext.h>
 #include <c10/cuda/CUDAGuard.h>
 #include "../cuda_compat.h"
+#include <cuda/std/functional>
 
 #ifndef USE_ROCM
     #include <cub/util_type.cuh>
@@ -62,7 +63,7 @@ __launch_bounds__(TPB) __global__
 
     const int thread_row_offset = blockIdx.x * num_cols;
 
-    cub::Sum sum;
+    cuda::std::plus<float> sum;
     float threadData(-FLT_MAX);
 
     // Don't touch finished rows.