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 5efce57f..62089d11 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
@@ -116,7 +116,6 @@ using LayoutSFB = typename Gemm::GemmKernel::CollectiveMainloop::LayoutSFB;
 // positions that aren't written are correct zeros.
 /////////////////////////////////////////////////////////////////////////////////////////////////
 
-template<typename LayoutSF>
 template<typename LayoutSF>
 __global__ void remap_sf_to_cutlass_kernel(
     const cutlass::float_ue4m3_t* __restrict__ src,