Vh* ddlZddlZddlmZmZddlmZmZmZm Z ddl m cm cm cmZddlmZmZddlmZddlmZddlmZmZmZddlmZdd lmZdd lm Z dd l!m"Z"gd Z#e"e$Z%eGd dZ&GddZ'de ee(dfde)ede(fdZ*dede+ee(ee,ffdZ-de&de ee(dfde)ede.e,effdZ/y)N) dataclassfield)AnyCallableOptionalUnion)eventsmetrics) WorkerSpec)LocalElasticAgent)DefaultLogsSpecs LogsSpecsSignalException)ChildFailedError)RendezvousParameters)parse_rendezvous_endpoint) get_logger) LaunchConfigelastic_launch launch_agentc.eZdZUdZeed<eed<eed<dZeeed<dZ e ed<d Z e ed <dZ e ed <d Z e ed <eeZee efed<dZeed<dZeed<dZeed<dZe ed<dZee ed<eeZee e fed<dZee ed<dZy)raP 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. .. 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_addrcd}|jdk7r|j|jd<nd|jvr||jd<|jt|_yy)Nir%timeout)r&r$rr )selfdefault_timeouts N/home/dcms/DCMS/lib/python3.12/site-packages/torch/distributed/launcher/api.py __post_init__zLaunchConfig.__post_init__[sd    "+/+<+L$sCx.>L#L#!e!L#.2hsm2"'"=Kc3h= $J $ 1r5rc2eZdZdZdedeeedffdZdZ y)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)r1rArBs r3__init__zelastic_launch.__init__s  %r5cVt|j|jt|SrD)rrErFlist)r1argss r3__call__zelastic_launch.__call__sDLL$*:*:DJGGr5) r6r7r8r9rrrr<rGrKr?r5r3rrgs04&&(C-.&Hr5rrBrJreturnct|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-Nr?).0args r3 z'_get_entrypoint_name..s>A# >s r) isinstancerr6r<sys executablenext)rBrJs r3_get_entrypoint_namerWsL*h'""" J $  '>>C C r5rdzv_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)rXr] master_addr master_ports r3_get_addr_and_portrbs(*''H~~H  Y   9PRSKb+H:5S T    %%r5rAc`|jsDttjj}t j d|||_t||}t jd||j|j|j|j|j|j|j|j|j |j"j$|j&d t)d |j|j|j|j|j|j*d|j}t-|\}}t/|j0|j|t3|t5j6||j|j |||j* }t9||j"|j:|j<} d} t?j@t?jB|j&| jE} tGjH| jK| jMrtO|| jP| jR| r|jTjWSS#tN$rtX$r'd } tGjH| j[t\$r%tGjH| j[wxYw#| r|jTjWwwxYw) Nz3config has no run_id, generated a random run_id: %saStarting elastic_operator with launch configs: entrypoint : %(entrypoint)s min_nodes : %(min_nodes)s max_nodes : %(max_nodes)s nproc_per_node : %(nproc_per_node)s run_id : %(run_id)s rdzv_backend : %(rdzv_backend)s rdzv_endpoint : %(rdzv_endpoint)s rdzv_configs : %(rdzv_configs)s max_restarts : %(max_restarts)s monitor_interval : %(monitor_interval)s log_dir : %(log_dir)s metrics_cfg : %(metrics_cfg)s ) rBrrrrr"r r$r(r)log_dirr-)r\r]rrrr.) rlocal_world_sizerBrJ rdzv_handlerr(r)r`rar.)specrr+r,T)namefailuresFr?)/rr<uuiduuid4r:loggerwarningrWinforrrr"r r$r(r)r root_log_dirr-rr.rbr rtuple rdzv_registryget_rendezvous_handlerr r+r,r initialize_metrics MetricsConfigrunr recordget_event_succeeded is_failedrri return_valuesrfshutdownrget_event_failed Exception) rArBrJrentrypoint_namerXr`rargagent shutdown_rdzvresults r3rrs ==TZZ\%%&LfU *:trs (11EE5AX NEP> = H  A1A1 A1H$H$HNhT)*26s),&)& 8C=(3- '(&&k) k)hT)*k) s)k) #s(^ k)r5