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