Diff Coverage

Total: 59 lines
Missing: 3 lines
Coverage: 94%

Source File	Diff Coverage (%)	Missing Lines
hyper_parallel/core/dtensor/redistribute_infer.py	100%
hyper_parallel/core/dtensor/tensor_redistribution.py	80.0%	320-321,325
hyper_parallel/core/shard/_op_dispatch.py	100%
hyper_parallel/core/shard/custom_shard.py	100%

hyper_parallel/core/dtensor/tensor_redistribution.py

        # 1. ReduceScatter is executed before AllReduce
        # 2. If multiple split, the dev axis split outer will be execute first.
        #    e.g. ("cp", "tp"), will execute reduce_scatter along "cp" before "tp"
        # 3. Lower dev_id execute before higher dev_id
        def _reduce_pair_sort_key(reduce_pair):
            return (reduce_pair[0] != "ReduceScatter",
                    dev_map_order.get(reduce_pair[2], 0),
                    to_layout.mesh.axis_id(reduce_pair[2]))

        sorted_pending_reduce_op_list = sorted(pending_reduce_op_list, key=_reduce_pair_sort_key)

        output_alias_tensor_map = list(from_layout.alias_tensor_map)
        for reduce_op_pair in sorted_pending_reduce_op_list:
            comm_op = reduce_op_pair[0]