Mojo function

warp_specialize_gemm_with_multicasting

warp_specialize_gemm_with_multicasting[c_type: DType, c_shape: DimList, a_type: DType, a_shape: DimList, b_type: DType, b_shape: DimList, //, *, transpose_b: Bool, wgmma_shape: IndexList[3], config: MatmulConfig[a_type, b_type, c_type, transpose_b, wgmma_shape], grid_shape: OptionalReg[IndexList[2]] = OptionalReg[IndexList[2]]({:i1 0, 1}), use_tma_store: Bool = False, elementwise_lambda_fn: OptionalReg[fn[DType, Int, Int](IndexList[2], SIMD[$0, $1]) capturing -> None] = OptionalReg[fn[DType, Int, Int](IndexList[2], SIMD[$0, $1]) capturing -> None]({:i1 0, 1}), elementwise_compute_lambda_fn: OptionalReg[fn[DType, Int, Int](IndexList[2], SIMD[$0, $1]) capturing -> SIMD[$0, $1]] = OptionalReg[fn[DType, Int, Int](IndexList[2], SIMD[$0, $1]) capturing -> SIMD[$0, $1]]({:i1 0, 1}), schedule: MatmulSchedule = MatmulSchedule(__init__[__mlir_type.!pop.int_literal](-1))](c_device: NDBuffer[c_type, 2, origin, c_shape], a_device: NDBuffer[a_type, 2, origin, a_shape], b_device: NDBuffer[b_type, 2, origin, b_shape], M: Int, N: Int, K: Int, ctx: DeviceContext)