Mojo function

multistage_gemm_q

multistage_gemm_q[c_type: DType, a_type: DType, b_type: DType, //, *, group_size: Int, pack_factor: Int, config: MatmulConfig[a_type, b_type, c_type, True], elementwise_lambda_fn: OptionalReg[fn[dtype: DType, width: Int, *, alignment: Int = 1](IndexList[2], SIMD[dtype, width]) capturing -> None] = None](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], runtime_config: MatmulConfig[a_type, b_type, c_type, True], ctx: DeviceContext)