i5 ddlZddlZddlZddlmZddlmZmZddlm Z ddl Z ddl m cm cmcmZddlmZddlmZmZddlmZddlmZdd lmZmZmZdd lmZdd l m!Z!dd l"m#Z#dd l$m%Z%ddl&m'Z'gdZ(e%e)Z*eGddZ+GddZ,dee-zdzde.e de-fdZ/de!de0e-dze1dzffdZ2de+dee-zdzde.e de3e1e ffdZ4y)N)Callable) dataclassfield)Any)get_default_numa_options)eventsmetrics) WorkerSpec)LocalElasticAgent)DefaultLogsSpecs LogsSpecsSignalException)ChildFailedError)RendezvousParameters)parse_rendezvous_endpoint) get_logger) NumaOptions) LaunchConfigelastic_launch launch_agentceZdZUdZeed<eed<eed<dZedzed<dZe ed<d Z e ed <dZ e ed <d Z e ed <e eZee efed<dZeed<dZeed<dZeed<dZe ed<dZe dzed<e eZee e fed<dZe dzed<dZe ed<dZedzed<dZe ed<dZee dzed <dZee dzed!<d"Z e!ed#<d$Z"y)%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 `_. duplicate_stdout_filters: If non-empty, duplicates stdout to a file containing only lines that match _any_ of the filter strings. duplicate_stderr_filters: If non-empty, duplicates stderr to a file containing only lines that match _any_ of the filter strings. virtual_local_rank: Enable virtual local rank mode for workers (defaults to False). When enabled, LOCAL_RANK is set to 0 for all workers and CUDA_VISIBLE_DEVICES is adjusted so each worker accesses its assigned GPU at device index 0. .. 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_id default_rolerole rdzv_endpointetcd rdzv_backend)default_factory rdzv_configs rdzv_timeout max_restartsg?monitor_intervalspawn start_methodlog_line_prefix_template metrics_cfg local_addrnullevent_log_handler numa_optionszSIGTERM,SIGINT,SIGHUP,SIGQUITsignals_to_handleduplicate_stdout_filtersduplicate_stderr_filtersFvirtual_local_rankcd}|jdk7r|j|jd<nd|jvr||jd<|jt|_|j{t j jr\t j j|jk(r0t|_tjd|jyyyy)Nir%timeoutzUsing default numa options = %r) r&r$rr r1torchcuda is_available device_countrrloggerinfo)selfdefault_timeouts X/var/www/html/engine/venv/lib/python3.12/site-packages/torch/distributed/launcher/api.py __post_init__zLaunchConfig.__post_init__qs    "+/+<+L$sCx.>L#L#!e!L#+/cDj/"'"=Kc3h=!Jd !#s#'+L+$+<s<15d3i$.515d3i$.5$$NrBrc2eZdZdZdedeezdzfdZdZy)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 entrypointNc ||_||_yN)_config _entrypoint)r>rPrQs r@__init__zelastic_launch.__init__s  %rBcVt|j|jt|SrS)rrTrUrL)r>argss r@__call__zelastic_launch.__call__sDLL$*:*:DJGGrB) rCrDrErFrrrIrVrYrNrBr@rrs-4&&sNT)&HrBrrQrXreturnct|tr |jSt|tr(|tj k(rt d|DdS|Sy)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. c32K|]}|ddk7s |yw)r-NrN).0args r@ z'_get_entrypoint_name..s>A# >s r) isinstancerrCrIsys executablenext)rQrXs r@_get_entrypoint_nameresL*h'""" J $  '>>C C rBrdzv_parametersc|jdk7ry|j}|j}|s tdt |d\}}|dk(rtd|d||fS)Nstatic)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)rfrk master_addr master_ports r@_get_addr_and_portrps(*''H~~H  Y   9PRSKb+H:5S T    %%rBrPc|jsDttjj}t j d|||_t||}t jdid|d|jd|jd|jd|jd|jd |jd |jd |jd |j d |j"j$d|j&d|j(d|j*d|j,d|j.d|j0t3d|j|j|j|j|j|j4d|j}t7|\}}|j,t8j:d<t=|j>|j|tA|tCjD||j|j |||j4|j(|j*|j.|j0|jF}tI||j"|jJ|jL} d} tOjPtOjR|j&| jU} tWjX| j[|j(| j]rt_|| j`| jb| r|jdjgSS#t^$rth$r2d} tWjX| jk|j(tl$r0tWjX| jk|j(wxYw#| r|jdjgwwxYw)Nz3config has no run_id, generated a random run_id: %saRStarting 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 numa_options : %(numa_options)s signals_to_handle : %(signals_to_handle)s duplicate_stdout_filters : %(duplicate_stdout_filters)s duplicate_stderr_filters : %(duplicate_stderr_filters)s rQrrrrr"r r$r(r)log_dirr-r0r1r2r3r4)rjrkrrrr.TORCHELASTIC_SIGNALS_TO_HANDLE)rlocal_world_sizerQrX rdzv_handlerr(r)rnror.r0r1r3r4r5)specrr+r,T)namefailuresFrN)7rrIuuiduuid4rGr<warningrer=rrrr"r r$r(r)r root_log_dirr-r0r1r2r3r4rr.rposenvironr rtuple rdzv_registryget_rendezvous_handlerr5r r+r,r initialize_metrics MetricsConfigrunrrecordget_event_succeeded is_failedrrx return_valuesrushutdownrget_event_failed Exception) rPrQrXrentrypoint_namerfrnrorvagent shutdown_rdzvresults r@rrs ==TZZ\%%&LfU *:trs $( EE:5AX NEP>* = H  [N[N [N|$H$HNX^d%:$s)PS(&)& 3:sTz !"&&}) })3%}) s)}) #s(^ })rB