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