diff --git a/src/nvfp4_megamoe_kernel/cutlass_nvfp4_gemm/cutlass_nvfp4_gemm.cu b/src/nvfp4_megamoe_kernel/cutlass_nvfp4_gemm/cutlass_nvfp4_gemm.cu
index da9196b2..b880cfb4 100644
--- a/src/nvfp4_megamoe_kernel/cutlass_nvfp4_gemm/cutlass_nvfp4_gemm.cu
+++ b/src/nvfp4_megamoe_kernel/cutlass_nvfp4_gemm/cutlass_nvfp4_gemm.cu
@@ -125,7 +125,7 @@ __global__ void remap_sf_to_cutlass_kernel(
     bool col_major_src = false                        // true if source is (K_sf, MN) row-major
 ) {
     int dst_idx = blockIdx.x * blockDim.x + threadIdx.x;
-    int total = cute::size(layout_sf);
+    int total = cute::cosize(layout_sf);
     if (dst_idx >= total) return;
 
     auto coord = cute::idx2crd(dst_idx, layout_sf.shape(), layout_sf.stride());