Mojo function

naive_block_scaled_nvfp4_matmul

naive_block_scaled_nvfp4_matmul[c_type: DType, a_type: DType, b_type: DType, a_scales_type: DType, b_scales_type: DType, //, *, SF_VECTOR_SIZE: Int, accum_type: DType = DType.float32, transpose_b: Bool = True, elementwise_lambda_fn: OptionalReg[fn[dtype: DType, width: Int, *, alignment: Int = 1](IndexList[2], SIMD[dtype, width]) capturing -> None] = None, BLOCK_DIM: Int = 16](c: LayoutTensor[c_type, layout, origin, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], a: LayoutTensor[a_type, layout, origin, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], b: LayoutTensor[b_type, layout, origin, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], a_scales: LayoutTensor[a_scales_type, layout, origin, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], b_scales: LayoutTensor[b_scales_type, layout, origin, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], ctx: DeviceContext)