sgk-ddlZddlZddlmZmZmZmZmZmZddl m Z ddl Z ddl m ZddlmZddlmZddlmZddlmZdd lmZdd lmZmZdd lmZdd lmZm Z m!Z!m"Z"d dgZ#e de$ d"dee%efdedeejLde'de(deeddfdZ)ede ddddddee%efdee%ejTdfdeedeedeejLddf dZ+ d"dee%efdedeejLde'de(deeddfdZ, d#ddddd eeee%e%fdee%ejTdfdeedeejLdee%eff d!Z-y)$N)AnycastDictOptionalSetUnion) deprecated)_EmptyStateDictLoadPlanner)_dcp_method_logger)Stateful)_storage_setup)DefaultLoadPlanner)LoadPlan LoadPlanner) StorageReader)_all_gather_keys _api_bc_check _DistWrapper_profileload_state_dictloadzb`load_state_dict` is deprecated and will be removed in future versions. Please use `load` instead.)category state_dictstorage_reader process_groupcoordinator_rankno_distplannerreturnc |jt5t||||||cdddS#1swYyxYw)z3This method is deprecated. Please switch to 'load'.N)resetr_load_state_dict)rrrrrrs a/var/www/html/venv/lib/python3.12/site-packages/torch/distributed/checkpoint/state_dict_loader.pyrrsD               s5>T)log_exceptions) checkpoint_idrrrr&c tjxrtj }|rtjdt 5t tt||d}|rt|j}n=t||}|t|jk7rtjdi}|D]1}||vr||} t| tr| jn| ||<3t!||||||D]8}||vr||} t| tr| j#||||||<: dddy#1swYyxYw)a Load a distributed ``state_dict`` in SPMD style. Each rank will try to read the least amount of data necessary to fullfill the requested `state_dict`. When loading :class:`ShardedTensor` or :class:`DTensor` instances, each rank only reads data for their local shards. For each ``Stateful`` object (having both a ``state_dict`` and a ``load_state_dict``), load will first call ``state_dict`` before attempting deserialization, followed by ``load_state_dict`` once the deserialization is complete. .. warning:: All tensors in ``state_dict`` must be allocated on their destination device *prior to* calling this function. All non-tensor data is loaded using `torch.load()` and modified in place on state_dict. .. warning:: Users must call `load_state_dict` on the root module to ensure load pos-processing and non-tensor data properly propagates. .. note: If no process group is initialized, this function will assume the intent is to load a checkpoint into the local process. This can be useful in the case of local inference, and when using regular Tensors (as opposed to DTensor or ShardedTensor) .. note: Rank 0 is assumed to be the coordinator rank. Args: state_dict (Dict[str, Any]): The state_dict to save. checkpoint_id (Union[str, os.PathLike, None]): The ID of this checkpoint instance. The meaning of the checkpoint_id depends on the storage. It can be a path to a folder or to a file. It can also be a key if the storage is a key-value store. (Default: ``None``) storage_reader (Optional[StorageReader]): Instance of StorageWriter used to perform reads. If this is not specified, DCP will automatically infer the reader based on the checkpoint_id. If checkpoint_id is also None, an exception will be raised. (Default: ``None``) planner (Optional[LoadPlanner]): Instance of LoadPlanner. If this is not specificed, the default planner will be used. (Default: ``None``) process_group (Optional[ProcessGroup]): ProcessGroup to be used for cross-rank synchronization. (Default: ``None``) Returns: None. Examples >>> # xdoctest: +SKIP >>> my_model = MyModule() >>> optimizer = Adagrad(my_model.parameters()) >>> model_state_dict = my_model.state_dict() >>> fs_storage_reader = torch.distributed.checkpoint.FileSystemReader("/checkpoint/1") >>> torch.distributed.checkpoint.load_state_dict( >>> state_dict=model_state_dict, >>> storage_reader=fs_storage_reader, >>> ) >>> # module.load_state_dict() function might have customized steps >>> # to flush the state_dict, must call it to >>> # ensure correct behavior. >>> my_model.load_state_dict(model_state_dict) .. note:: load_state_dict uses collectives to coordinate reads across ranks. For NCCL-based process groups, internal tensor representations of objects must be moved to the GPU device before communication takes place. In this case, the device used is given by ``torch.cuda.current_device()`` and it is the user's responsibility to ensure that this is set so that each rank has an individual GPU, via ``torch.cuda.set_device()``. ftorch.distributed is unavailable or uninitialized, assuming the intent is to load in a single process.Treaderz|Detected mismatched keys in state dict after all gather! This behavior is unsupported and may cause errors may cause errors.rrrrrN)dist is_availableis_initializedwarningswarnrrrrlistkeysrsorted isinstancer rr#r) rr&rrrrr2 statetful_sdkeyelems r$rr3ser$$&@4+>+>+@AG t  %0 >.-PTU   )*D#J >Dvjoo/00 [   C*$c?D%/h%?!T     #)'   0C*$c?D$)$$\#%67*3/JsO  0?%0%0%0s C;EEct tjjdt|| |  t i}t ddx}||d<t di| fd}t di|fd} jd||  t di| fd} jd| } y) Nz,torch.distributed.checkpoint.load_state_dictr&cJj}j|jj|jj }j |}|SN) read_metadataset_up_planneris_coordinatorset_up_storage_readercreate_local_planprepare_local_plan)metadata local_plandistWrrrs r$ local_stepz$_load_state_dict..local_stepso"""!//1z8U5I5IJ,,Xu7K7KL..0 #66zB cTJj|}j|}|Sr:)create_global_planprepare_global_plan)all_local_plansrrs r$ global_stepz%_load_state_dict..global_steps5"""!44_E(<<_MrEplanctJj}j|}|jyr:) finish_plan read_datawait)final_local_plan all_reads central_planrrs r$rNz#_load_state_dict..read_datas@""""..|<",,-=wG rEread) torch_C_log_api_usage_oncerrgetattrr reduce_scatter all_gather)rrrrrr ckpt_kwargsckpt_idrDrJrN_rRrCs`` ` @@r$r#r#s HH  !OP G 5E FE$&K>?DAAN'. O$&+&'&+&' #11&*kRL&+&' +ArE)r&rrr2c vtjjdtjxrtj }|rt jdttt||d}t|tr|h}i}t||||t|xs t|S)a Load only the specified keys from the checkpoint, if no keys are specified, the entire checkpoint will be loaded. Note, this method completely loads the checkpoint into the current process and is not distributed. .. warning:: .. warning:: All non-tensor data is loaded using `torch.load()` .. note: As opposed to the usual pattern, this function does not take a state dict as input and does not load inplace. Instead, a new state dict is directly initialized and read from file. .. note: If no process group is initialized, this function will assume the intent is to load a checkpoint into the local process. This can be useful in the case of local inference, and when using regular Tensors (as opposed to DTensor or ShardedTensor) .. note: Rank 0 is assumed to be the coordinator rank. Args: keys (Optional[Union[Set[str], str]]): Loads any key specified in this set. If no keys are specified, the entire checkpoint is loaded. checkpoint_id (Union[str, os.PathLike, None]): The ID of this checkpoint instance. The meaning of the checkpoint_id depends on the storage. It can be a path to a folder or to a file. It can also be a key if the storage is a key-value store. (Default: ``None``) storage_reader (Optional[StorageReader]): Instance of StorageWriter used to perform reads. If this is not specified, DCP will automatically infer the reader based on the checkpoint_id. If checkpoint_id is also None, an exception will be raised. (Default: ``None``) process_group (Optional[ProcessGroup]): ProcessGroup to be used for cross-rank synchronization. (Default: ``None``) Returns: State dict from specified keys z7torch.distributed.checkpoint._load_state_dict_from_keysr(Tr))r2r+)rUrVrWr,r-r.r/r0rrrr4strr#r set)r2r&rrrsds r$_load_state_dict_from_keysrbsl HH  A$$&@4+>+>+@AG t ~nmDQN$vB%#* >  IrE)NrFNr:).osr/typingrrrrrrtyping_extensionsr rUtorch.distributed distributedr,,torch.distributed.checkpoint.default_plannerr #torch.distributed.checkpoint.loggerr %torch.distributed.checkpoint.statefulr _storage_utilsrdefault_plannerrrrrstoragerutilsrrrr__all__ FutureWarningr_ ProcessGroupintboolrPathLikerr#rbrTrEr$rusd 88( SB:*/*"JJ f % ! 26%)  S#X ! D--.     k "      ,4(48.2%)15 B0S#XB0bkk4/0B0]+ B0 k " B0 D--. B0 B0)B0P26%) /,S#X/,!/,D--./, /,  /, k " /, /,f,0P48.215 P 5S3' (Pbkk4/0P]+ P D--. P  #s(^ PrE