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 a8715762..8b208e1f 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
@@ -122,7 +122,7 @@ __global__ void remap_sf_to_cutlass_kernel(
     if (m >= MN || k_sf >= K_sf) return;
 
     // Compute the CUTLASS physical index from logical (m, k_sf) via the layout
-    int dst_idx = layout_sf(cute::make_coord(m, k_sf));
+    int dst_idx = cute::crd2idx(cute::make_coord(m, k_sf), layout_sf);
 
     // Read from source (row-major or col-major) and write to CUTLASS position
     dst[dst_idx] = col_major_src ? src[k_sf * MN + m] : src[m * K_sf + k_sf];