merge artefact correction

Author: Aleksandr Malyshev

csrc/layernorm_kernels.cu

@@ -51,8 +51,6 @@ __global__ void rms_norm_kernel(
 template <typename scalar_t, int width>
 __global__ std::enable_if_t<(width > 0) && _typeConvert<scalar_t>::exists>
 fused_add_rms_norm_kernel(
-    scalar_t* __restrict__ output,       // [..., hidden_size]
-    const scalar_t* __restrict__ input,  // [..., hidden_size]
     scalar_t* __restrict__ output,       // [..., hidden_size]
     const scalar_t* __restrict__ input,  // [..., hidden_size]
     const int64_t input_stride,