[Th&SSKrSSKrSrSrSrg)NcT[RRRU5$)zReturn tensor ids and eager tensors for DeviceData nodes in the IR for the passed in lazy tensors. TODO: This API is currently ts backend specific. We are working on generalizing it to all backends including XLA. )torch_C_lazy_ts_backend _get_tensors_ts_device_data_nodetensorss O/var/www/auris/envauris/lib/python3.13/site-packages/torch/_lazy/computation.pyget_tensors_ts_device_data_noder s 88 $ $ E Eg NNcT[RRRU5$)z4Return the graph hash for the passed in lazy tensors)rr_lazy_get_graph_hashrs r get_graph_hashrs 88>> ) )' 22r cT[RRRX5$)zRunning the cached computation graph with the given inputs TODO: This API is currently ts backend specific. We are working on generalizing it to all backends including XLA. )rrr_run_cached_graph)hash_str graph_inputss r run_cached_graphrs 88 $ $ 6 6x NNr )torch._C._lazyrtorch._C._lazy_ts_backendr rrr r rs O3 Or