Mojo function

rms_norm_fused_residual_add_gpu

rms_norm_fused_residual_add_gpu[dtype: DType, rank: Int, //, input_fn: fn[Int, Int](IndexList[$1]) capturing -> SIMD[dtype, $0], residual_input_fn: fn[Int, Int](IndexList[$1]) capturing -> SIMD[dtype, $0], output_residual_fn: fn[Int, Int](IndexList[rank], SIMD[dtype, $0]) capturing -> None, output_fn: fn[Int, Int](IndexList[rank], SIMD[dtype, $0]) capturing -> None, multiply_before_cast: Bool](shape: IndexList[rank, element_type=element_type], gamma1: LayoutTensor[dtype, layout, origin, address_space=address_space, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], epsilon1: Scalar[dtype], weight_offset1: Scalar[dtype], gamma2: LayoutTensor[dtype, layout, origin, address_space=address_space, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], epsilon2: Scalar[dtype], weight_offset2: Scalar[dtype], ctx: DeviceContext)