mirror of
https://github.com/deepseek-ai/smallpond
synced 2025-06-26 18:27:45 +00:00
132 lines
4.2 KiB
ReStructuredText
132 lines
4.2 KiB
ReStructuredText
smallpond.execution.task.ArrowStreamTask
|
|
========================================
|
|
|
|
.. currentmodule:: smallpond.execution.task
|
|
|
|
.. autoclass:: ArrowStreamTask
|
|
|
|
|
|
.. automethod:: __init__
|
|
|
|
|
|
.. rubric:: Methods
|
|
|
|
.. autosummary::
|
|
|
|
~ArrowStreamTask.__init__
|
|
~ArrowStreamTask.add_elapsed_time
|
|
~ArrowStreamTask.adjust_row_group_size
|
|
~ArrowStreamTask.clean_complex_attrs
|
|
~ArrowStreamTask.clean_output
|
|
~ArrowStreamTask.cleanup
|
|
~ArrowStreamTask.compute_avg_row_size
|
|
~ArrowStreamTask.create_input_views
|
|
~ArrowStreamTask.dump
|
|
~ArrowStreamTask.dump_output
|
|
~ArrowStreamTask.exec
|
|
~ArrowStreamTask.exec_query
|
|
~ArrowStreamTask.finalize
|
|
~ArrowStreamTask.get_partition_info
|
|
~ArrowStreamTask.initialize
|
|
~ArrowStreamTask.inject_fault
|
|
~ArrowStreamTask.merge_metrics
|
|
~ArrowStreamTask.oom
|
|
~ArrowStreamTask.parquet_kv_metadata_bytes
|
|
~ArrowStreamTask.parquet_kv_metadata_str
|
|
~ArrowStreamTask.prepare_connection
|
|
~ArrowStreamTask.process
|
|
~ArrowStreamTask.random_float
|
|
~ArrowStreamTask.random_uint32
|
|
~ArrowStreamTask.restore_input_state
|
|
~ArrowStreamTask.run
|
|
~ArrowStreamTask.run_on_ray
|
|
~ArrowStreamTask.set_memory_limit
|
|
|
|
|
|
|
|
|
|
|
|
.. rubric:: Attributes
|
|
|
|
.. autosummary::
|
|
|
|
~ArrowStreamTask.process_func
|
|
~ArrowStreamTask.background_io_thread
|
|
~ArrowStreamTask.streaming_batch_size
|
|
~ArrowStreamTask.streaming_batch_count
|
|
~ArrowStreamTask.parquet_row_group_size
|
|
~ArrowStreamTask.parquet_row_group_bytes
|
|
~ArrowStreamTask.parquet_dictionary_encoding
|
|
~ArrowStreamTask.parquet_compression
|
|
~ArrowStreamTask.parquet_compression_level
|
|
~ArrowStreamTask.secs_checkpoint_interval
|
|
~ArrowStreamTask.allow_speculative_exec
|
|
~ArrowStreamTask.any_input_empty
|
|
~ArrowStreamTask.compression_level_str
|
|
~ArrowStreamTask.compression_options
|
|
~ArrowStreamTask.compression_type_str
|
|
~ArrowStreamTask.cpu_limit
|
|
~ArrowStreamTask.cpu_overcommit_ratio
|
|
~ArrowStreamTask.ctx
|
|
~ArrowStreamTask.dataset
|
|
~ArrowStreamTask.default_output_name
|
|
~ArrowStreamTask.elapsed_time
|
|
~ArrowStreamTask.enable_temp_directory
|
|
~ArrowStreamTask.exception
|
|
~ArrowStreamTask.exec_cq
|
|
~ArrowStreamTask.exec_id
|
|
~ArrowStreamTask.exec_on_scheduler
|
|
~ArrowStreamTask.fail_count
|
|
~ArrowStreamTask.final_output_abspath
|
|
~ArrowStreamTask.finish_time
|
|
~ArrowStreamTask.gpu_limit
|
|
~ArrowStreamTask.id
|
|
~ArrowStreamTask.input_datasets
|
|
~ArrowStreamTask.input_deps
|
|
~ArrowStreamTask.input_udfs
|
|
~ArrowStreamTask.input_view_index
|
|
~ArrowStreamTask.key
|
|
~ArrowStreamTask.local_gpu
|
|
~ArrowStreamTask.local_gpu_ranks
|
|
~ArrowStreamTask.local_rank
|
|
~ArrowStreamTask.location
|
|
~ArrowStreamTask.max_batch_size
|
|
~ArrowStreamTask.memory_limit
|
|
~ArrowStreamTask.memory_overcommit_ratio
|
|
~ArrowStreamTask.node_id
|
|
~ArrowStreamTask.numa_node
|
|
~ArrowStreamTask.numpy_random_gen
|
|
~ArrowStreamTask.output
|
|
~ArrowStreamTask.output_deps
|
|
~ArrowStreamTask.output_dirname
|
|
~ArrowStreamTask.output_filename
|
|
~ArrowStreamTask.output_name
|
|
~ArrowStreamTask.output_root
|
|
~ArrowStreamTask.partition_dims
|
|
~ArrowStreamTask.partition_infos
|
|
~ArrowStreamTask.partition_infos_as_dict
|
|
~ArrowStreamTask.perf_metrics
|
|
~ArrowStreamTask.perf_profile
|
|
~ArrowStreamTask.python_random_gen
|
|
~ArrowStreamTask.query_udfs
|
|
~ArrowStreamTask.rand_seed_float
|
|
~ArrowStreamTask.rand_seed_uint32
|
|
~ArrowStreamTask.random_seed_bytes
|
|
~ArrowStreamTask.ray_dataset_path
|
|
~ArrowStreamTask.ray_marker_path
|
|
~ArrowStreamTask.retry_count
|
|
~ArrowStreamTask.runtime_id
|
|
~ArrowStreamTask.runtime_output_abspath
|
|
~ArrowStreamTask.runtime_state
|
|
~ArrowStreamTask.sched_epoch
|
|
~ArrowStreamTask.self_contained_output
|
|
~ArrowStreamTask.skip_when_any_input_empty
|
|
~ArrowStreamTask.staging_root
|
|
~ArrowStreamTask.start_time
|
|
~ArrowStreamTask.status
|
|
~ArrowStreamTask.temp_abspath
|
|
~ArrowStreamTask.temp_output
|
|
~ArrowStreamTask.udfs
|
|
~ArrowStreamTask.uniform_failure_prob
|
|
|
|
|