Index A | B | C | D | E | F | G | H | I | J | L | M | N | O | P | R | S | T | U | V | W | X A active_steps (fkat.pytorch.schedule.base.Fixed attribute) (fkat.pytorch.schedule.Fixed attribute) Always (class in fkat.pytorch.schedule) (class in fkat.pytorch.schedule.base) ami_id (fkat.utils.aws.imds.InstanceMetadata attribute) apply_async() (fkat.utils.pool.ThreadPool method) availability_zone (fkat.utils.aws.imds.InstanceMetadata attribute) B broadcast_mlflow_run_id() (in module fkat.utils.mlflow) C check() (fkat.pytorch.callbacks.cuda.Xid method) (fkat.pytorch.schedule.Always method) (fkat.pytorch.schedule.base.Always method) (fkat.pytorch.schedule.base.CombinedSchedule method) (fkat.pytorch.schedule.base.Elapsed method) (fkat.pytorch.schedule.base.Every method) (fkat.pytorch.schedule.base.Fixed method) (fkat.pytorch.schedule.base.GlobalRank method) (fkat.pytorch.schedule.base.InvertedSchedule method) (fkat.pytorch.schedule.base.LocalRank method) (fkat.pytorch.schedule.base.Never method) (fkat.pytorch.schedule.base.Schedule method) (fkat.pytorch.schedule.CombinedSchedule method) (fkat.pytorch.schedule.Elapsed method) (fkat.pytorch.schedule.Every method) (fkat.pytorch.schedule.Fixed method) (fkat.pytorch.schedule.GlobalRank method) (fkat.pytorch.schedule.InvertedSchedule method) (fkat.pytorch.schedule.LocalRank method) (fkat.pytorch.schedule.mlflow.HasTag method) (fkat.pytorch.schedule.Never method) (fkat.pytorch.schedule.Schedule method) (in module fkat.utils.cuda.preflight.run) checkfunction_timeout_manager() (in module fkat.utils.cuda.preflight.health_check.helpers) ckpt_path (fkat.utils.config.SingletonResolver attribute) close() (fkat.utils.pool.ThreadPool method) CombinedSchedule (class in fkat.pytorch.schedule) (class in fkat.pytorch.schedule.base) create_instance_level_mlflow_run() (in module fkat.utils.cuda.preflight.health_check.logger) create_job_level_mlflow_run() (in module fkat.utils.cuda.preflight.health_check.logger) D daemon (fkat.utils.pool.NoDaemonProcess property) data (fkat.utils.config.SingletonResolver attribute) DataModule (class in fkat.data) default() (fkat.utils.pdb.ForkedPdb method) destroy_process_group_if_initialized() (in module fkat.utils.cuda.preflight.health_check.helpers) detect_xid_errors() (in module fkat.utils.cuda.xid) DictBatchSampler (class in fkat.data.samplers) DictDataLoader (class in fkat.data) DictDataset (class in fkat.data.datasets) DistDpGroup (class in fkat.pytorch.callbacks.monitoring.dp) do_continue() (fkat.utils.pdb.ForkedPdb method) do_jump() (fkat.utils.pdb.ForkedPdb method) do_next() (fkat.utils.pdb.ForkedPdb method) do_quit() (fkat.utils.pdb.ForkedPdb method) do_return() (fkat.utils.pdb.ForkedPdb method) do_step() (fkat.utils.pdb.ForkedPdb method) dp_group_info() (fkat.pytorch.callbacks.monitoring.dp.DistDpGroup method) (fkat.pytorch.callbacks.monitoring.dp.DpGroupStrategy method) (fkat.pytorch.callbacks.monitoring.dp.EnvDpGroup method) (fkat.pytorch.callbacks.monitoring.dp.MegatronDpGroup method) DpGroupStrategy (class in fkat.pytorch.callbacks.monitoring.dp) DpSyncMonitor (class in fkat.pytorch.callbacks.monitoring.dp) dump_memory_snapshot() (fkat.pytorch.callbacks.cuda.MemoryObserver method) E Elapsed (class in fkat.pytorch.schedule) (class in fkat.pytorch.schedule.base) EmptyCache (class in fkat.pytorch.callbacks.cuda) end_all_mlflow_active_runs() (in module fkat.utils.cuda.preflight.health_check.logger) EnvDpGroup (class in fkat.pytorch.callbacks.monitoring.dp) Every (class in fkat.pytorch.schedule) (class in fkat.pytorch.schedule.base) F fetch() (in module fkat.utils.aws.imds) fetch_gpu_info() (in module fkat.utils.cuda.preflight.health_check.helpers) fetch_node_info() (in module fkat.utils.cuda.preflight.run) fit() (fkat.utils.config.Trainer method) Fixed (class in fkat.pytorch.schedule) (class in fkat.pytorch.schedule.base) fkat module fkat.data module fkat.data.datasets module fkat.data.samplers module fkat.data.samplers.strategies module fkat.predict module fkat.pytorch.actions module fkat.pytorch.actions.aws.batch module fkat.pytorch.actions.aws.ec2 module fkat.pytorch.callbacks.cuda module fkat.pytorch.callbacks.debugging module fkat.pytorch.callbacks.gc module fkat.pytorch.callbacks.logging module fkat.pytorch.callbacks.monitoring.dp module fkat.pytorch.callbacks.profiling module fkat.pytorch.schedule module fkat.pytorch.schedule.base module fkat.pytorch.schedule.mlflow module fkat.test module fkat.train module fkat.utils.aws.imds module fkat.utils.boto3 module fkat.utils.config module fkat.utils.cuda.preflight.health_check.ddb_client module fkat.utils.cuda.preflight.health_check.gpu_connection_test module fkat.utils.cuda.preflight.health_check.gpu_stress_test module fkat.utils.cuda.preflight.health_check.helpers module fkat.utils.cuda.preflight.health_check.logger module fkat.utils.cuda.preflight.health_check.timer module fkat.utils.cuda.preflight.run module fkat.utils.cuda.xid module fkat.utils.logging module fkat.utils.mlflow module fkat.utils.pandas module fkat.utils.pdb module fkat.utils.pool module fkat.utils.profiler module fkat.utils.pyarrow module fkat.utils.rng module fkat.utils.shm module fkat.validate module Flops (class in fkat.pytorch.callbacks.profiling) ForkedPdb (class in fkat.utils.pdb) Frequency (class in fkat.data.samplers.strategies) FutureResult (class in fkat.utils.pool) G generate_ddb_item() (fkat.utils.cuda.preflight.health_check.ddb_client.HealthStatusDDBClient method) generate_gpu_uuid_hash() (in module fkat.utils.cuda.preflight.health_check.helpers) generate_random_string() (in module fkat.utils.cuda.preflight.health_check.helpers) generate_test_folder_name() (in module fkat.utils.cuda.preflight.health_check.helpers) get() (fkat.utils.pool.FutureResult method) get_item() (fkat.utils.cuda.preflight.health_check.ddb_client.HealthStatusDDBClient method) get_parent_mlflow_id() (in module fkat.utils.cuda.preflight.health_check.logger) get_rng_states() (in module fkat.utils.rng) GlobalRank (class in fkat.pytorch.schedule) (class in fkat.pytorch.schedule.base) gpu_hash_id (fkat.utils.cuda.preflight.health_check.helpers.UniqueID attribute) gpu_per_node (fkat.utils.cuda.preflight.health_check.helpers.UniqueID attribute) H HasTag (class in fkat.pytorch.schedule.mlflow) HealthStatusDDBClient (class in fkat.utils.cuda.preflight.health_check.ddb_client) Heartbeat (class in fkat.pytorch.callbacks.logging) hostname (fkat.utils.aws.imds.InstanceMetadata attribute) I initialize() (in module fkat) initialize_mlflow() (in module fkat.utils.cuda.preflight.health_check.logger) instance_id (fkat.utils.aws.imds.InstanceMetadata attribute) instance_metadata() (in module fkat.utils.aws.imds) instance_type (fkat.utils.aws.imds.InstanceMetadata attribute) InstanceMetadata (class in fkat.utils.aws.imds) InstanceStats (class in fkat.utils.cuda.preflight.health_check.helpers) interaction() (fkat.utils.pdb.ForkedPdb method) Introspection (class in fkat.pytorch.callbacks.debugging) InvertedSchedule (class in fkat.pytorch.schedule) (class in fkat.pytorch.schedule.base) isolate_bad_node() (in module fkat.utils.cuda.preflight.run) iter_rows() (in module fkat.utils.pandas) (in module fkat.utils.pyarrow) IterableJsonDataset (class in fkat.data.datasets) IterableMapDataset (class in fkat.data.datasets) IterableParquetDataset (class in fkat.data.datasets) J join() (fkat.utils.pool.ThreadPool method) JsonDataset (class in fkat.data.datasets) L LightningAction (class in fkat.pytorch.actions) load() (in module fkat.utils.shm) load_batch() (fkat.data.ShardedDataLoader method) (fkat.data.ShmDataLoader method) load_batch_sync() (fkat.data.ShardedDataLoader method) (fkat.data.ShmDataLoader method) load_state_dict() (fkat.data.DataModule method) (fkat.data.ShardedDataLoader method), [1] (fkat.pytorch.callbacks.cuda.Nvtx method) local_hostname (fkat.utils.aws.imds.InstanceMetadata attribute) local_ipv4 (fkat.utils.aws.imds.InstanceMetadata attribute) local_rank (fkat.utils.cuda.preflight.health_check.helpers.UniqueID attribute) LocalRank (class in fkat.pytorch.schedule) (class in fkat.pytorch.schedule.base) log_preflight_results() (in module fkat.utils.cuda.preflight.run) LogInstanceTags (class in fkat.pytorch.actions.aws.ec2) M main() (in module fkat.predict) (in module fkat.test) (in module fkat.train) (in module fkat.validate) make_requests() (in module fkat.utils.cuda.preflight.health_check.helpers) ManualGc (class in fkat.pytorch.callbacks.gc) MapDataset (class in fkat.data.datasets) master_addr (fkat.utils.cuda.preflight.health_check.helpers.UniqueID attribute) maybe_collect() (fkat.pytorch.callbacks.gc.ManualGc method) maybe_dump_memory_snapshot() (fkat.pytorch.callbacks.cuda.MemoryObserver method) maybe_empty_cache() (fkat.pytorch.callbacks.cuda.EmptyCache method) maybe_gc() (fkat.pytorch.callbacks.gc.ManualGc method) MegatronDpGroup (class in fkat.pytorch.callbacks.monitoring.dp) MemoryObserver (class in fkat.pytorch.callbacks.cuda) Memray (class in fkat.pytorch.callbacks.profiling) mlflow_logger() (in module fkat.utils.mlflow) model (fkat.utils.config.SingletonResolver attribute) module fkat fkat.data fkat.data.datasets fkat.data.samplers fkat.data.samplers.strategies fkat.predict fkat.pytorch.actions fkat.pytorch.actions.aws.batch fkat.pytorch.actions.aws.ec2 fkat.pytorch.callbacks.cuda fkat.pytorch.callbacks.debugging fkat.pytorch.callbacks.gc fkat.pytorch.callbacks.logging fkat.pytorch.callbacks.monitoring.dp fkat.pytorch.callbacks.profiling fkat.pytorch.schedule fkat.pytorch.schedule.base fkat.pytorch.schedule.mlflow fkat.test fkat.train fkat.utils.aws.imds fkat.utils.boto3 fkat.utils.config fkat.utils.cuda.preflight.health_check.ddb_client fkat.utils.cuda.preflight.health_check.gpu_connection_test fkat.utils.cuda.preflight.health_check.gpu_stress_test fkat.utils.cuda.preflight.health_check.helpers fkat.utils.cuda.preflight.health_check.logger fkat.utils.cuda.preflight.health_check.timer fkat.utils.cuda.preflight.run fkat.utils.cuda.xid fkat.utils.logging fkat.utils.mlflow fkat.utils.pandas fkat.utils.pdb fkat.utils.pool fkat.utils.profiler fkat.utils.pyarrow fkat.utils.rng fkat.utils.shm fkat.validate monitor (fkat.pytorch.callbacks.cuda.Xid attribute) N n_batches (fkat.pytorch.schedule.base.Every attribute) (fkat.pytorch.schedule.Every attribute) n_steps (fkat.pytorch.schedule.base.Every attribute) (fkat.pytorch.schedule.Every attribute) Never (class in fkat.pytorch.schedule) (class in fkat.pytorch.schedule.base) NoDaemonContext (class in fkat.utils.pool) NoDaemonPool (class in fkat.utils.pool) NoDaemonProcess (class in fkat.utils.pool) node_rank (fkat.utils.cuda.preflight.health_check.helpers.UniqueID attribute) Nsys (class in fkat.pytorch.callbacks.cuda) num_nodes (fkat.utils.cuda.preflight.health_check.helpers.UniqueID attribute) Nvtx (class in fkat.pytorch.callbacks.cuda) O on_after_backward() (fkat.pytorch.callbacks.cuda.Nvtx method) on_before_backward() (fkat.pytorch.callbacks.cuda.Nvtx method) on_before_optimizer_step() (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.debugging.Introspection method) (fkat.pytorch.callbacks.monitoring.dp.DpSyncMonitor method) on_before_zero_grad() (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.logging.Throughput method) on_exception() (fkat.data.DataModule method) (fkat.data.ShardedDataLoader method) (fkat.data.ShmDataLoader method) (fkat.pytorch.callbacks.cuda.Nsys method) (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.cuda.Xid method) (fkat.pytorch.callbacks.profiling.Memray method) (fkat.pytorch.callbacks.profiling.PyTorch method) (fkat.pytorch.callbacks.profiling.VizTracer method) on_load_checkpoint() (fkat.data.DataModule method) (fkat.pytorch.callbacks.cuda.Nvtx method) on_predict_batch_end() (fkat.pytorch.callbacks.cuda.EmptyCache method) (fkat.pytorch.callbacks.cuda.Nsys method) (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.gc.ManualGc method) (fkat.pytorch.callbacks.logging.Throughput method) (fkat.pytorch.callbacks.profiling.Flops method) (fkat.pytorch.callbacks.profiling.Memray method) (fkat.pytorch.callbacks.profiling.PyTorch method) (fkat.pytorch.callbacks.profiling.VizTracer method) on_predict_batch_start() (fkat.pytorch.callbacks.cuda.MemoryObserver method) (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.cuda.Xid method) (fkat.pytorch.callbacks.logging.Heartbeat method) (fkat.pytorch.callbacks.profiling.Flops method) on_predict_end() (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.logging.Throughput method) on_predict_epoch_end() (fkat.pytorch.callbacks.cuda.EmptyCache method) (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.gc.ManualGc method) (fkat.pytorch.callbacks.logging.Throughput method) on_predict_epoch_start() (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.logging.Throughput method) on_predict_start() (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.profiling.Memray method) on_sanity_check_end() (fkat.pytorch.callbacks.cuda.Nvtx method) on_sanity_check_start() (fkat.pytorch.callbacks.cuda.Nvtx method) on_save_checkpoint() (fkat.data.DataModule method) (fkat.pytorch.callbacks.cuda.Nvtx method) on_test_batch_end() (fkat.pytorch.callbacks.cuda.EmptyCache method) (fkat.pytorch.callbacks.cuda.Nsys method) (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.gc.ManualGc method) (fkat.pytorch.callbacks.logging.Throughput method) (fkat.pytorch.callbacks.profiling.Flops method) (fkat.pytorch.callbacks.profiling.Memray method) (fkat.pytorch.callbacks.profiling.PyTorch method) (fkat.pytorch.callbacks.profiling.VizTracer method) on_test_batch_start() (fkat.pytorch.callbacks.cuda.MemoryObserver method) (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.cuda.Xid method) (fkat.pytorch.callbacks.logging.Heartbeat method) (fkat.pytorch.callbacks.profiling.Flops method) on_test_end() (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.logging.Throughput method) on_test_epoch_end() (fkat.pytorch.callbacks.cuda.EmptyCache method) (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.gc.ManualGc method) (fkat.pytorch.callbacks.logging.Throughput method) on_test_epoch_start() (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.logging.Throughput method) on_test_start() (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.profiling.Memray method) on_train_batch_end() (fkat.pytorch.callbacks.cuda.EmptyCache method) (fkat.pytorch.callbacks.cuda.Nsys method) (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.debugging.Introspection method) (fkat.pytorch.callbacks.gc.ManualGc method) (fkat.pytorch.callbacks.logging.Throughput method) (fkat.pytorch.callbacks.profiling.Flops method) (fkat.pytorch.callbacks.profiling.Memray method) (fkat.pytorch.callbacks.profiling.PyTorch method) (fkat.pytorch.callbacks.profiling.VizTracer method) on_train_batch_start() (fkat.pytorch.callbacks.cuda.MemoryObserver method) (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.cuda.Xid method) (fkat.pytorch.callbacks.debugging.Introspection method) (fkat.pytorch.callbacks.debugging.OptimizerSnapshot method) (fkat.pytorch.callbacks.logging.Heartbeat method) (fkat.pytorch.callbacks.monitoring.dp.DpSyncMonitor method) (fkat.pytorch.callbacks.profiling.Flops method) on_train_end() (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.debugging.Introspection method) (fkat.pytorch.callbacks.logging.Throughput method) on_train_epoch_end() (fkat.pytorch.callbacks.cuda.EmptyCache method) (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.gc.ManualGc method) (fkat.pytorch.callbacks.logging.Throughput method) on_train_epoch_start() (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.logging.Throughput method) on_train_start() (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.debugging.Introspection method) (fkat.pytorch.callbacks.profiling.Memray method) on_validation_batch_end() (fkat.pytorch.callbacks.cuda.EmptyCache method) (fkat.pytorch.callbacks.cuda.Nsys method) (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.gc.ManualGc method) (fkat.pytorch.callbacks.logging.Throughput method) (fkat.pytorch.callbacks.profiling.Flops method) (fkat.pytorch.callbacks.profiling.Memray method) (fkat.pytorch.callbacks.profiling.PyTorch method) (fkat.pytorch.callbacks.profiling.VizTracer method) on_validation_batch_start() (fkat.pytorch.callbacks.cuda.MemoryObserver method) (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.cuda.Xid method) (fkat.pytorch.callbacks.logging.Heartbeat method) (fkat.pytorch.callbacks.profiling.Flops method) on_validation_end() (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.logging.Throughput method) (fkat.pytorch.callbacks.logging.ValidationMetrics method) on_validation_epoch_end() (fkat.pytorch.callbacks.cuda.EmptyCache method) (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.gc.ManualGc method) (fkat.pytorch.callbacks.logging.Throughput method) on_validation_epoch_start() (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.logging.Throughput method) on_validation_start() (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.profiling.Memray method) OptimizerSnapshot (class in fkat.pytorch.callbacks.debugging) P ParquetDataset (class in fkat.data.datasets) patch_args() (in module fkat) perform() (fkat.pytorch.actions.aws.batch.TerminateJob method) (fkat.pytorch.actions.aws.ec2.LogInstanceTags method) (fkat.pytorch.actions.aws.ec2.RebootInstances method) (fkat.pytorch.actions.aws.ec2.TerminateInstances method) (fkat.pytorch.actions.LightningAction method) PersistStates (class in fkat.data) post_mortem() (fkat.utils.pdb.ForkedPdb method) (in module fkat.utils.pdb) precmd() (fkat.utils.pdb.ForkedPdb method) predict() (fkat.utils.config.Trainer method) predict_dataloader() (fkat.data.DataModule method) prefetch() (fkat.data.ShmDataLoader method) prefetch_shards() (fkat.data.ShardedDataLoader method) preflight_health_check() (in module fkat.utils.cuda.preflight.run) prepare_data() (fkat.data.DataModule method) print_rank_info() (fkat.utils.pdb.ForkedPdb method) Process (fkat.utils.pool.NoDaemonContext attribute) profile_until_exit() (in module fkat.utils.profiler) public_hostname (fkat.utils.aws.imds.InstanceMetadata attribute) put_item() (fkat.utils.cuda.preflight.health_check.ddb_client.HealthStatusDDBClient method) PyTorch (class in fkat.pytorch.callbacks.profiling) R rank (fkat.utils.cuda.preflight.health_check.helpers.UniqueID attribute) rank0_logger() (in module fkat.utils.logging) ranks (fkat.pytorch.schedule.base.GlobalRank attribute) (fkat.pytorch.schedule.base.LocalRank attribute) (fkat.pytorch.schedule.GlobalRank attribute) (fkat.pytorch.schedule.LocalRank attribute) ready() (fkat.utils.pool.FutureResult method) RebootInstances (class in fkat.pytorch.actions.aws.ec2) region (fkat.utils.aws.imds.InstanceMetadata attribute) register_singleton_resolver() (in module fkat.utils.config) RestoreStates (class in fkat.data) return_predictions (fkat.utils.config.SingletonResolver attribute) RoundRobin (class in fkat.data.samplers.strategies) run_gpu_connection_test() (in module fkat.utils.cuda.preflight.health_check.gpu_connection_test) run_gpu_stress_test() (in module fkat.utils.cuda.preflight.health_check.gpu_stress_test) run_main() (in module fkat) S SamplerStrategy (class in fkat.data.samplers.strategies) save() (in module fkat.utils.config) (in module fkat.utils.shm) Schedule (class in fkat.pytorch.schedule) (class in fkat.pytorch.schedule.base) search_join_mlflow_run() (in module fkat.utils.cuda.preflight.health_check.logger) session() (in module fkat.utils.boto3) set_device() (fkat.data.ShardedDataLoader method) (fkat.data.ShmDataLoader method) set_rng_states() (in module fkat.utils.rng) setup() (fkat.data.DataModule method) (fkat.pytorch.callbacks.cuda.MemoryObserver method) (fkat.pytorch.callbacks.cuda.Nsys method) (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.cuda.Xid method) (fkat.pytorch.callbacks.debugging.Introspection method) (fkat.pytorch.callbacks.gc.ManualGc method) (fkat.pytorch.callbacks.logging.Heartbeat method) (fkat.pytorch.callbacks.logging.Throughput method) (fkat.pytorch.callbacks.logging.ValidationMetrics method) (fkat.pytorch.callbacks.monitoring.dp.DpSyncMonitor method) (fkat.pytorch.callbacks.profiling.Flops method) (fkat.pytorch.callbacks.profiling.Memray method) (fkat.pytorch.callbacks.profiling.PyTorch method) (fkat.pytorch.callbacks.profiling.VizTracer method) (in module fkat) ShardedDataLoader (class in fkat.data), [1] ShmDataLoader (class in fkat.data), [1] SingletonResolver (class in fkat.utils.config) SizedDataset (class in fkat.data.datasets) SizedSampler (class in fkat.data.samplers) stage (fkat.pytorch.schedule.base.Every attribute) (fkat.pytorch.schedule.Every attribute) state_dict() (fkat.data.DataModule method) (fkat.data.ShardedDataLoader method), [1] (fkat.pytorch.callbacks.cuda.Nvtx method) strip_aws_batch_id() (in module fkat.utils.cuda.preflight.health_check.helpers) successful() (fkat.utils.pool.FutureResult method) T teardown() (fkat.data.DataModule method) (fkat.data.ShardedDataLoader method) (fkat.data.ShmDataLoader method) (fkat.pytorch.callbacks.cuda.Nsys method) (fkat.pytorch.callbacks.cuda.Nvtx method) (fkat.pytorch.callbacks.cuda.Xid method) (fkat.pytorch.callbacks.profiling.Memray method) (fkat.pytorch.callbacks.profiling.PyTorch method) (fkat.pytorch.callbacks.profiling.VizTracer method) TerminateInstances (class in fkat.pytorch.actions.aws.ec2) TerminateJob (class in fkat.pytorch.actions.aws.batch) test() (fkat.utils.config.Trainer method) test_dataloader() (fkat.data.DataModule method) ThreadPool (class in fkat.utils.pool) Throughput (class in fkat.pytorch.callbacks.logging) Timer (class in fkat.utils.cuda.preflight.health_check.timer) to_primitive_container() (in module fkat.utils.config) to_str() (in module fkat.utils.config) token() (in module fkat.utils.aws.imds) train_dataloader() (fkat.data.DataModule method) Trainer (class in fkat.utils.config) trainer (fkat.utils.config.SingletonResolver attribute) tuners (fkat.utils.config.SingletonResolver attribute) U UniqueID (class in fkat.utils.cuda.preflight.health_check.helpers) upload_mlflow() (fkat.utils.cuda.preflight.health_check.helpers.InstanceStats method) V val_dataloader() (fkat.data.DataModule method) validate() (fkat.utils.config.Trainer method) ValidationMetrics (class in fkat.pytorch.callbacks.logging) VizTracer (class in fkat.pytorch.callbacks.profiling) W wait() (fkat.utils.pool.FutureResult method) warmup_steps (fkat.pytorch.schedule.base.Fixed attribute) (fkat.pytorch.schedule.Fixed attribute) Weighted (class in fkat.data.samplers.strategies) world_size (fkat.utils.cuda.preflight.health_check.helpers.UniqueID attribute) X Xid (class in fkat.pytorch.callbacks.cuda)