mirror of
https://github.com/deepseek-ai/smallpond
synced 2025-06-26 18:27:45 +00:00
103 lines
3.2 KiB
ReStructuredText
103 lines
3.2 KiB
ReStructuredText
smallpond.execution.task.MergeDataSetsTask
|
|
==========================================
|
|
|
|
.. currentmodule:: smallpond.execution.task
|
|
|
|
.. autoclass:: MergeDataSetsTask
|
|
|
|
|
|
.. automethod:: __init__
|
|
|
|
|
|
.. rubric:: Methods
|
|
|
|
.. autosummary::
|
|
|
|
~MergeDataSetsTask.__init__
|
|
~MergeDataSetsTask.add_elapsed_time
|
|
~MergeDataSetsTask.adjust_row_group_size
|
|
~MergeDataSetsTask.clean_complex_attrs
|
|
~MergeDataSetsTask.clean_output
|
|
~MergeDataSetsTask.cleanup
|
|
~MergeDataSetsTask.compute_avg_row_size
|
|
~MergeDataSetsTask.dump
|
|
~MergeDataSetsTask.exec
|
|
~MergeDataSetsTask.finalize
|
|
~MergeDataSetsTask.get_partition_info
|
|
~MergeDataSetsTask.initialize
|
|
~MergeDataSetsTask.inject_fault
|
|
~MergeDataSetsTask.merge_metrics
|
|
~MergeDataSetsTask.oom
|
|
~MergeDataSetsTask.parquet_kv_metadata_bytes
|
|
~MergeDataSetsTask.parquet_kv_metadata_str
|
|
~MergeDataSetsTask.random_float
|
|
~MergeDataSetsTask.random_uint32
|
|
~MergeDataSetsTask.run
|
|
~MergeDataSetsTask.run_on_ray
|
|
~MergeDataSetsTask.set_memory_limit
|
|
|
|
|
|
|
|
|
|
|
|
.. rubric:: Attributes
|
|
|
|
.. autosummary::
|
|
|
|
~MergeDataSetsTask.ctx
|
|
~MergeDataSetsTask.id
|
|
~MergeDataSetsTask.node_id
|
|
~MergeDataSetsTask.sched_epoch
|
|
~MergeDataSetsTask.output_name
|
|
~MergeDataSetsTask.output_root
|
|
~MergeDataSetsTask.dataset
|
|
~MergeDataSetsTask.input_deps
|
|
~MergeDataSetsTask.output_deps
|
|
~MergeDataSetsTask.perf_metrics
|
|
~MergeDataSetsTask.perf_profile
|
|
~MergeDataSetsTask.runtime_state
|
|
~MergeDataSetsTask.input_datasets
|
|
~MergeDataSetsTask.allow_speculative_exec
|
|
~MergeDataSetsTask.any_input_empty
|
|
~MergeDataSetsTask.cpu_limit
|
|
~MergeDataSetsTask.default_output_name
|
|
~MergeDataSetsTask.elapsed_time
|
|
~MergeDataSetsTask.exception
|
|
~MergeDataSetsTask.exec_cq
|
|
~MergeDataSetsTask.exec_id
|
|
~MergeDataSetsTask.exec_on_scheduler
|
|
~MergeDataSetsTask.fail_count
|
|
~MergeDataSetsTask.final_output_abspath
|
|
~MergeDataSetsTask.finish_time
|
|
~MergeDataSetsTask.gpu_limit
|
|
~MergeDataSetsTask.key
|
|
~MergeDataSetsTask.local_gpu
|
|
~MergeDataSetsTask.local_gpu_ranks
|
|
~MergeDataSetsTask.local_rank
|
|
~MergeDataSetsTask.location
|
|
~MergeDataSetsTask.memory_limit
|
|
~MergeDataSetsTask.numa_node
|
|
~MergeDataSetsTask.numpy_random_gen
|
|
~MergeDataSetsTask.output
|
|
~MergeDataSetsTask.output_dirname
|
|
~MergeDataSetsTask.output_filename
|
|
~MergeDataSetsTask.partition_dims
|
|
~MergeDataSetsTask.partition_infos
|
|
~MergeDataSetsTask.partition_infos_as_dict
|
|
~MergeDataSetsTask.python_random_gen
|
|
~MergeDataSetsTask.random_seed_bytes
|
|
~MergeDataSetsTask.ray_dataset_path
|
|
~MergeDataSetsTask.ray_marker_path
|
|
~MergeDataSetsTask.retry_count
|
|
~MergeDataSetsTask.runtime_id
|
|
~MergeDataSetsTask.runtime_output_abspath
|
|
~MergeDataSetsTask.self_contained_output
|
|
~MergeDataSetsTask.skip_when_any_input_empty
|
|
~MergeDataSetsTask.staging_root
|
|
~MergeDataSetsTask.start_time
|
|
~MergeDataSetsTask.status
|
|
~MergeDataSetsTask.temp_abspath
|
|
~MergeDataSetsTask.temp_output
|
|
~MergeDataSetsTask.uniform_failure_prob
|
|
|
|
|