o h, @slddlZddlZddlmZmZddlmZmZmZm Z ddl m m m mZddlmZmZddlmZddlmZddlmZmZmZddlmZdd lmZdd lm Z dd l!m"Z"gd Z#e"e$Z%eGd ddZ&GdddZ'de ee(dfde)ede(fddZ*dede+ee(ee,ffddZ-de&de ee(dfde)ede.e,effddZ/dS)N) dataclassfield)AnyCallableOptionalUnion)eventsmetrics) WorkerSpec)LocalElasticAgent)DefaultLogsSpecs LogsSpecsSignalException)ChildFailedError)RendezvousParameters)parse_rendezvous_endpoint) get_logger) LaunchConfigelastic_launch launch_agentc@seZdZUdZeed<eed<eed<dZeeed<dZ e ed<d Z e ed <dZ e ed <d Z e ed <eedZee efed<dZeed<dZeed<dZeed<dZe ed<dZee ed<eedZee e fed<dZee ed<dZe ed<ddZdS)ra Creates a rendezvous config. Args: min_nodes: Minimum amount of nodes that the user function will be launched on. Elastic agent ensures that the user function start only when the min_nodes amount enters the rendezvous. max_nodes: Maximum amount of nodes that the user function will be launched on. nproc_per_node: On each node the elastic agent will launch this amount of workers that will execute user defined function. rdzv_backend: rdzv_backend to use in the rendezvous (zeus-adapter, etcd). rdzv_endpoint: The endpoint of the rdzv sync. storage. rdzv_configs: Key, value pair that specifies rendezvous specific configuration. rdzv_timeout: Legacy argument that specifies timeout for the rendezvous. It is going to be removed in future versions, see the note below. The default timeout is 900 seconds. run_id: The unique run id of the job (if not passed a unique one will be deduced from run environment - flow workflow id in flow - or auto generated). role: User defined role of the worker (defaults to "trainer"). max_restarts: The maximum amount of restarts that elastic agent will conduct on workers before failure. monitor_interval: The interval in seconds that is used by the elastic_agent as a period of monitoring workers. start_method: The method is used by the elastic agent to start the workers (spawn, fork, forkserver). metrics_cfg: configuration to initialize metrics. local_addr: address of the local node if any. If not set, a lookup on the local machine's FQDN will be performed. local_ranks_filter: ranks for which to show logs in console. If not set, show from all. event_log_handler: name of the event logging handler as registered in `elastic/events/handlers.py `_. .. note:: `rdzv_timeout` is a legacy argument that will be removed in future. Set the timeout via `rdzv_configs['timeout']` min_nodes max_nodesnproc_per_nodeN logs_specsrun_idZ default_rolerole rdzv_endpointZetcd rdzv_backend)default_factory rdzv_configs rdzv_timeout max_restartsg?monitor_intervalZspawn start_methodlog_line_prefix_template metrics_cfg local_addrnullevent_log_handlercCsJd}|jdkr|j|jd<n d|jvr||jd<|jdur#t|_dSdS)Nir!timeout)r"r rr )selfZdefault_timeoutr.d/home/www/facesmatcher.com/frenv_anti/lib/python3.10/site-packages/torch/distributed/launcher/api.py __post_init___s     zLaunchConfig.__post_init__)__name__ __module__ __qualname____doc__int__annotations__rrr rstrrrrrdictr rr"r$r%floatr&r'r(r)r+r0r.r.r.r/r"s( )          rc@s4eZdZdZdedeeedffddZddZ dS) ra Launches an torchelastic agent on the container that invoked the entrypoint. 1. Pass the ``entrypoint`` arguments as non ``kwargs`` (e.g. no named parameters)/ ``entrypoint`` can be a function or a command. 2. The return value is a map of each worker's output mapped by their respective global rank. Usage :: def worker_fn(foo): # ... def main(): # entrypoint is a function. outputs = elastic_launch(LaunchConfig, worker_fn)(foo) # return rank 0's output return outputs[0] # entrypoint is a command and ``script.py`` is the python module. outputs = elastic_launch(LaunchConfig, "script.py")(args) outputs = elastic_launch(LaunchConfig, "python")("script.py") config entrypointNcCs||_||_dSN)_config _entrypoint)r-r:r;r.r.r/__init__s zelastic_launch.__init__cGst|j|jt|Sr<)rr=r>list)r-argsr.r.r/__call__szelastic_launch.__call__) r1r2r3r4rrrr7r?rBr.r.r.r/rks  rr;rAreturncCs@t|tr|jSt|tr|tjkrtdd|DdS|SdS)aRetrieve entrypoint name with the rule: 1. If entrypoint is a function, use ``entrypoint.__qualname__``. 2. If entrypoint is a string, check its value: 2.1 if entrypoint equals to ``sys.executable`` (like "python"), use the first element from ``args`` which does not start with hifen letter (for example, "-u" will be skipped). 2.2 otherwise, use ``entrypoint`` value. 3. Otherwise, return empty string. css |] }|ddkr|VqdS)r-Nr.).0argr.r.r/ sz'_get_entrypoint_name..r) isinstancerr1r7sys executablenext)r;rAr.r.r/_get_entrypoint_names   rLrdzv_parameterscCsX|jdkrdS|j}|}|stdt|dd\}}|dkr(td|d||fS)NZstatic)NNzKEndpoint is missing in endpoint. Try to add --master-addr and --master-portr!) default_portzport is missing in endpoint: z. Try to specify --master-port)backendendpointstrip ValueErrorr)rMrP master_addr master_portr.r.r/_get_addr_and_ports  rUr:c Cs|jsttj}td|||_t||}td||j |j |j |j|j |j |j|j|j|jj|j|jd td |j |j |j|j |j |jd|j}t|\}}t|j|j |t|t||j|j|||j|jd }t||j|j|jd} d} zYz.t !t "|j| #} t$%| &|j| 'rt(|| j)d| j*WW| r|j+,SSt(yt-yd } t$%| .|jt/yt$%| .|jw| r|j+,ww) Nz3config has no run_id, generated a random run_id: %sa/Starting elastic_operator with launch configs: entrypoint : %(entrypoint)s min_nodes : %(min_nodes)s max_nodes : %(max_nodes)s nproc_per_node : %(nproc_per_node)s run_id : %(run_id)s rdzv_backend : %(rdzv_backend)s rdzv_endpoint : %(rdzv_endpoint)s rdzv_configs : %(rdzv_configs)s max_restarts : %(max_restarts)s monitor_interval : %(monitor_interval)s log_dir : %(log_dir)s metrics_cfg : %(metrics_cfg)s event_log_handler : %(event_log_handler)s ) r;rrrrrrr r$r%Zlog_dirr(r+)rOrPrrrr)) rZlocal_world_sizer;rA rdzv_handlerr$r%rSrTr)r+)specrr&r'T)namefailuresFr.)0rr7uuiduuid4r5loggerwarningrLinforrrrrr r$r%rZ root_log_dirr(r+rr)rUr rtuple rdzv_registryZget_rendezvous_handlerr r&r'r Zinitialize_metricsZ MetricsConfigrunrrecordZget_event_succeededZ is_failedrrYZ return_valuesrVshutdownrZget_event_failed Exception) r:r;rArZentrypoint_namerMrSrTrWZagentZ shutdown_rdzvresultr.r.r/rs         r)0rIrZ dataclassesrrtypingrrrrZ-torch.distributed.elastic.rendezvous.registry distributedZelasticZ rendezvousregistryr`Ztorch.distributed.elasticrr Z*torch.distributed.elastic.agent.server.apir Z:torch.distributed.elastic.agent.server.local_elastic_agentr Z)torch.distributed.elastic.multiprocessingr r rZ0torch.distributed.elastic.multiprocessing.errorsrZ$torch.distributed.elastic.rendezvousrZ*torch.distributed.elastic.rendezvous.utilsrZ'torch.distributed.elastic.utils.loggingr__all__r1r\rrr7r@rLr_r5rUr8rr.r.r.r/sN      H'