File	function		statements	missing	excluded		coverage
hyper_parallel / __init__.py	(no function)		12	0	0		100%
hyper_parallel / collectives / __init__.py	(no function)		0	0	0		100%
hyper_parallel / collectives / cc.py	init_process_group		1	0	0		100%
hyper_parallel / collectives / cc.py	destroy_process_group		1	0	0		100%
hyper_parallel / collectives / cc.py	get_process_group_ranks		1	0	0		100%
hyper_parallel / collectives / cc.py	get_backend		1	0	0		100%
hyper_parallel / collectives / cc.py	split_group		1	0	0		100%
hyper_parallel / collectives / cc.py	(no function)		9	0	0		100%
hyper_parallel / core / __init__.py	(no function)		0	0	0		100%
hyper_parallel / core / activation_checkpoint / __init__.py	(no function)		2	0	0		100%
hyper_parallel / core / activation_checkpoint / activation_checkpoint.py	checkpoint		4	0	0		100%
hyper_parallel / core / activation_checkpoint / activation_checkpoint.py	(no function)		13	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	SwapTensor.__init__		8	2	0		75%
hyper_parallel / core / activation_checkpoint / swap.py	SwapTensor.get_val		5	5	0		0%
hyper_parallel / core / activation_checkpoint / swap.py	SwapTensor.async_load		11	11	0		0%
hyper_parallel / core / activation_checkpoint / swap.py	SwapTensor.wait_load		8	8	0		0%
hyper_parallel / core / activation_checkpoint / swap.py	SwapTensor.async_offload		9	3	0		67%
hyper_parallel / core / activation_checkpoint / swap.py	SwapTensor.wait_offload		9	4	0		56%
hyper_parallel / core / activation_checkpoint / swap.py	SwapTensor.state		1	1	0		0%
hyper_parallel / core / activation_checkpoint / swap.py	SwapTensor.__repr__		3	3	0		0%
hyper_parallel / core / activation_checkpoint / swap.py	Storage.__init__		2	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	Storage.launch_load		4	4	0		0%
hyper_parallel / core / activation_checkpoint / swap.py	Storage.launch_load._async_load		3	3	0		0%
hyper_parallel / core / activation_checkpoint / swap.py	Storage.wait_load		4	4	0		0%
hyper_parallel / core / activation_checkpoint / swap.py	Storage.wait_load._wait_load		3	3	0		0%
hyper_parallel / core / activation_checkpoint / swap.py	Storage.wait_offload		4	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	Storage.wait_offload._wait_offload		3	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	Storage.launch_offload		4	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	Storage.launch_offload._async_offload		3	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	SwapGroup.__init__		4	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	SwapGroup.add		1	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	SwapGroup.launch_offload		9	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	SwapGroup.wait_offload		7	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	SwapGroup.launch_load		9	9	0		0%
hyper_parallel / core / activation_checkpoint / swap.py	SwapGroup.wait_load		7	7	0		0%
hyper_parallel / core / activation_checkpoint / swap.py	SwapManager.__new__		10	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	SwapManager.add_storage		3	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	SwapManager.launch_offload		6	1	0		83%
hyper_parallel / core / activation_checkpoint / swap.py	SwapManager.wait_offload		4	1	0		75%
hyper_parallel / core / activation_checkpoint / swap.py	SwapManager.launch_load		6	6	0		0%
hyper_parallel / core / activation_checkpoint / swap.py	SwapManager.wait_load		4	4	0		0%
hyper_parallel / core / activation_checkpoint / swap.py	SwapManager.get_current_group_name		1	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	SwapManager.set_current_group_name		1	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	SwapManager.set_forward_prefetch_layer		14	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	SwapManager.set_forward_prefetch_layer._ensure_group_name		6	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	SwapManager.set_forward_prefetch_layer._forward_pre_hook		3	1	0		67%
hyper_parallel / core / activation_checkpoint / swap.py	SwapManager.set_forward_prefetch_layer._forward_hook		8	1	0		88%
hyper_parallel / core / activation_checkpoint / swap.py	SwapManager.set_forward_prefetch_layer._backward_pre_hook		7	7	0		0%
hyper_parallel / core / activation_checkpoint / swap.py	SwapManager.set_forward_prefetch_layer._backward_hook		1	1	0		0%
hyper_parallel / core / activation_checkpoint / swap.py	SwapManager.set_forward_prefetch_layer._register_hooks_once		5	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	SwapManager._get_copy_stream		3	0	0		100%
hyper_parallel / core / activation_checkpoint / swap.py	(no function)		49	0	0		100%
hyper_parallel / core / checkpoint / __init__.py	(no function)		11	0	0		100%
hyper_parallel / core / checkpoint / api.py	_gather_from_all_ranks		5	0	0		100%
hyper_parallel / core / checkpoint / api.py	save		32	4	0		88%
hyper_parallel / core / checkpoint / api.py	load		34	7	0		79%
hyper_parallel / core / checkpoint / api.py	(no function)		12	0	0		100%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemWriter.__init__		5	0	0		100%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemWriter.initialize_writer		3	3	0		0%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemWriter.configure_writer		3	0	0		100%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemWriter.optimize_local_plan		1	0	0		100%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemWriter.optimize_global_plan		1	0	0		100%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemWriter._write_bytes_item		13	3	0		77%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemWriter._collect_tensors		9	1	0		89%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemWriter._write_tensors		12	1	0		92%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemWriter.execute_write		7	0	0		100%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemWriter.finalize_checkpoint		12	0	0		100%
hyper_parallel / core / checkpoint / filesystem_storage.py	_copy_tensor_to_target		4	1	0		75%
hyper_parallel / core / checkpoint / filesystem_storage.py	_load_bytes_file		4	0	0		100%
hyper_parallel / core / checkpoint / filesystem_storage.py	_get_tensor_size		3	1	0		67%
hyper_parallel / core / checkpoint / filesystem_storage.py	_load_tensor_file		17	2	0		88%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemReader.__init__		4	0	0		100%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemReader.initialize_reader		2	2	0		0%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemReader.load_metadata		9	1	0		89%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemReader.configure_reader		3	0	0		100%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemReader.optimize_local_plan		1	0	0		100%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemReader.optimize_global_plan		1	0	0		100%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemReader._get_storage_path		12	7	0		42%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemReader._group_items_by_file		5	0	0		100%
hyper_parallel / core / checkpoint / filesystem_storage.py	FileSystemReader.execute_read		7	1	0		86%
hyper_parallel / core / checkpoint / filesystem_storage.py	(no function)		34	0	0		100%
hyper_parallel / core / checkpoint / layout.py	get_current_layout		11	1	0		91%
hyper_parallel / core / checkpoint / layout.py	save_layout		2	0	0		100%
hyper_parallel / core / checkpoint / layout.py	load_layout		3	0	0		100%
hyper_parallel / core / checkpoint / layout.py	combine_layout		9	5	0		44%
hyper_parallel / core / checkpoint / layout.py	get_global_layout		10	0	0		100%
hyper_parallel / core / checkpoint / layout.py	(no function)		11	0	0		100%
hyper_parallel / core / checkpoint / loader.py	load_checkpoint		5	1	0		80%
hyper_parallel / core / checkpoint / loader.py	(no function)		6	0	0		100%
hyper_parallel / core / checkpoint / metadata.py	(no function)		29	0	0		100%
hyper_parallel / core / checkpoint / planner.py	WriteItem.tensor_storage_size		21	2	0		90%
hyper_parallel / core / checkpoint / planner.py	SavePlanner.configure_planner		0	0	0		100%
hyper_parallel / core / checkpoint / planner.py	SavePlanner.build_local_plan		0	0	0		100%
hyper_parallel / core / checkpoint / planner.py	SavePlanner.build_global_plan		0	0	0		100%
hyper_parallel / core / checkpoint / planner.py	SavePlanner.finalize_plan		0	0	0		100%
hyper_parallel / core / checkpoint / planner.py	SavePlanner.get_tensor		0	0	0		100%
hyper_parallel / core / checkpoint / planner.py	LoadPlanner.configure_planner		0	0	0		100%
hyper_parallel / core / checkpoint / planner.py	LoadPlanner.build_local_plan		0	0	0		100%
hyper_parallel / core / checkpoint / planner.py	LoadPlanner.build_global_plan		0	0	0		100%
hyper_parallel / core / checkpoint / planner.py	LoadPlanner.finalize_plan		0	0	0		100%
hyper_parallel / core / checkpoint / planner.py	LoadPlanner.acquire_tensor		0	0	0		100%
hyper_parallel / core / checkpoint / planner.py	LoadPlanner.apply_tensor		0	0	0		100%
hyper_parallel / core / checkpoint / planner.py	LoadPlanner.apply_bytes		0	0	0		100%
hyper_parallel / core / checkpoint / planner.py	(no function)		62	0	0		100%
hyper_parallel / core / checkpoint / reshard.py	check_layout		14	2	0		86%
hyper_parallel / core / checkpoint / reshard.py	check_layout.check_type_is_sequence		2	1	0		50%
hyper_parallel / core / checkpoint / reshard.py	rank_id_to_dev_id_list		6	0	0		100%
hyper_parallel / core / checkpoint / reshard.py	infer_intersection		13	1	0		92%
hyper_parallel / core / checkpoint / reshard.py	infer_intersection.is_valid_axis_list		5	2	0		60%
hyper_parallel / core / checkpoint / reshard.py	infer_slice_area_by_rank		25	0	0		100%
hyper_parallel / core / checkpoint / reshard.py	infer_slice_area_by_rank._get_dev_num_along_dim		1	0	0		100%
hyper_parallel / core / checkpoint / reshard.py	ReshardHandler.__init__		31	1	0		97%
hyper_parallel / core / checkpoint / reshard.py	ReshardHandler._infer_inner_deredundancy_rank_list_by_from_layout		21	0	0		100%
hyper_parallel / core / checkpoint / reshard.py	ReshardHandler.infer_all_tensor_offset		11	0	0		100%
hyper_parallel / core / checkpoint / reshard.py	ReshardHandler.get_real_tensor		17	1	0		94%
hyper_parallel / core / checkpoint / reshard.py	(no function)		13	0	0		100%
hyper_parallel / core / checkpoint / saver.py	save_checkpoint		5	1	0		80%
hyper_parallel / core / checkpoint / saver.py	(no function)		6	0	0		100%
hyper_parallel / core / checkpoint / standard_planner.py	StandardSavePlanner.__init__		6	0	0		100%
hyper_parallel / core / checkpoint / standard_planner.py	StandardSavePlanner.configure_planner		5	0	0		100%
hyper_parallel / core / checkpoint / standard_planner.py	StandardSavePlanner.build_local_plan		31	2	0		94%
hyper_parallel / core / checkpoint / standard_planner.py	StandardSavePlanner.build_local_plan.compute_global_offsets		14	5	0		64%
hyper_parallel / core / checkpoint / standard_planner.py	StandardSavePlanner.build_global_plan		34	2	0		94%
hyper_parallel / core / checkpoint / standard_planner.py	StandardSavePlanner._update_tensor_cache		16	0	0		100%
hyper_parallel / core / checkpoint / standard_planner.py	StandardSavePlanner.finalize_plan		2	0	0		100%
hyper_parallel / core / checkpoint / standard_planner.py	StandardSavePlanner.get_tensor		1	0	0		100%
hyper_parallel / core / checkpoint / standard_planner.py	create_read_items_for_chunk_list		16	1	0		94%
hyper_parallel / core / checkpoint / standard_planner.py	StandardLoadPlanner.__init__		5	0	0		100%
hyper_parallel / core / checkpoint / standard_planner.py	StandardLoadPlanner.configure_planner		4	0	0		100%
hyper_parallel / core / checkpoint / standard_planner.py	StandardLoadPlanner.build_local_plan		26	7	0		73%
hyper_parallel / core / checkpoint / standard_planner.py	StandardLoadPlanner.build_global_plan		1	0	0		100%
hyper_parallel / core / checkpoint / standard_planner.py	StandardLoadPlanner.finalize_plan		1	0	0		100%
hyper_parallel / core / checkpoint / standard_planner.py	StandardLoadPlanner.acquire_tensor		8	2	0		75%
hyper_parallel / core / checkpoint / standard_planner.py	StandardLoadPlanner.apply_tensor		8	3	0		62%
hyper_parallel / core / checkpoint / standard_planner.py	StandardLoadPlanner.apply_bytes		5	1	0		80%
hyper_parallel / core / checkpoint / standard_planner.py	(no function)		29	0	0		100%
hyper_parallel / core / checkpoint / storage.py	StorageWriter.initialize_writer		0	0	0		100%
hyper_parallel / core / checkpoint / storage.py	StorageWriter.configure_writer		0	0	0		100%
hyper_parallel / core / checkpoint / storage.py	StorageWriter.optimize_local_plan		0	0	0		100%
hyper_parallel / core / checkpoint / storage.py	StorageWriter.optimize_global_plan		0	0	0		100%
hyper_parallel / core / checkpoint / storage.py	StorageWriter.execute_write		0	0	0		100%
hyper_parallel / core / checkpoint / storage.py	StorageWriter.finalize_checkpoint		0	0	0		100%
hyper_parallel / core / checkpoint / storage.py	StorageReader.initialize_reader		0	0	0		100%
hyper_parallel / core / checkpoint / storage.py	StorageReader.load_metadata		0	0	0		100%
hyper_parallel / core / checkpoint / storage.py	StorageReader.configure_reader		0	0	0		100%
hyper_parallel / core / checkpoint / storage.py	StorageReader.optimize_local_plan		0	0	0		100%
hyper_parallel / core / checkpoint / storage.py	StorageReader.optimize_global_plan		0	0	0		100%
hyper_parallel / core / checkpoint / storage.py	StorageReader.execute_read		0	0	0		100%
hyper_parallel / core / checkpoint / storage.py	(no function)		42	0	0		100%
hyper_parallel / core / checkpoint / util.py	check_path		6	3	0		50%
hyper_parallel / core / checkpoint / util.py	has_valid_filename		2	0	0		100%
hyper_parallel / core / checkpoint / util.py	narrow_tensor_by_index		4	1	0		75%
hyper_parallel / core / checkpoint / util.py	chunk_to_area		1	0	0		100%
hyper_parallel / core / checkpoint / util.py	create_chunk_list_for_tensor		24	6	0		75%
hyper_parallel / core / checkpoint / util.py	remove_redundant_plans		28	2	0		93%
hyper_parallel / core / checkpoint / util.py	(no function)		17	0	0		100%
hyper_parallel / core / device_mesh.py	_get_sub_rank_list		13	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh.__init__		33	1	0		97%
hyper_parallel / core / device_mesh.py	DeviceMesh._compute_coordinate_on_dim		1	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh._compute_coordinates_from_mesh		7	1	0		86%
hyper_parallel / core / device_mesh.py	DeviceMesh.size		3	3	0		0%
hyper_parallel / core / device_mesh.py	DeviceMesh.get_coordinate		1	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh._convert_mesh_to_tensor		8	1	0		88%
hyper_parallel / core / device_mesh.py	DeviceMesh._init_one_process_group		16	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh._init_process_groups		13	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh.mesh		1	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh.device_type		1	1	0		0%
hyper_parallel / core / device_mesh.py	DeviceMesh.rank		1	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh.mesh_shape		1	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh.mesh_dim_names		1	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh.rank_list		1	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh.ndim		1	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh.root_mesh		1	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh.root_mesh		1	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh.sub_mesh		1	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh.get_flatten_mapping		1	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh.add_flatten_mapping		1	1	0		0%
hyper_parallel / core / device_mesh.py	DeviceMesh.__getitem__		9	1	0		89%
hyper_parallel / core / device_mesh.py	DeviceMesh._normalize_sub_mesh_dim_names		7	2	0		71%
hyper_parallel / core / device_mesh.py	DeviceMesh._try_get_from_flatten_mapping		3	1	0		67%
hyper_parallel / core / device_mesh.py	DeviceMesh._validate_getitem_dimensions		10	3	0		70%
hyper_parallel / core / device_mesh.py	DeviceMesh._get_or_create_original_sub_mesh		8	1	0		88%
hyper_parallel / core / device_mesh.py	DeviceMesh._create_and_cache_sub_mesh		14	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh.get_group		9	3	0		67%
hyper_parallel / core / device_mesh.py	DeviceMesh.from_group		28	4	0		86%
hyper_parallel / core / device_mesh.py	DeviceMesh.get_local_rank		20	7	0		65%
hyper_parallel / core / device_mesh.py	DeviceMesh.flatten		1	1	0		0%
hyper_parallel / core / device_mesh.py	DeviceMesh._get_root_mesh		3	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh._create_flatten_mesh		22	22	0		0%
hyper_parallel / core / device_mesh.py	DeviceMesh.axis_id		5	2	0		60%
hyper_parallel / core / device_mesh.py	DeviceMesh.axis_index		3	1	0		67%
hyper_parallel / core / device_mesh.py	DeviceMesh.get_device_num_along_axis		3	1	0		67%
hyper_parallel / core / device_mesh.py	DeviceMesh.get_rank_list_along_axis		30	3	0		90%
hyper_parallel / core / device_mesh.py	DeviceMesh.get_global_shape		27	6	0		78%
hyper_parallel / core / device_mesh.py	DeviceMesh.get_comm_group_by_axis		13	3	0		77%
hyper_parallel / core / device_mesh.py	DeviceMesh.get_devices_for_axis		31	31	0		0%
hyper_parallel / core / device_mesh.py	DeviceMesh.to_hash		3	0	0		100%
hyper_parallel / core / device_mesh.py	DeviceMesh.__repr__		1	1	0		0%
hyper_parallel / core / device_mesh.py	DeviceMesh.__str__		1	1	0		0%
hyper_parallel / core / device_mesh.py	_create_device_mesh		7	0	0		100%
hyper_parallel / core / device_mesh.py	init_device_mesh		9	3	0		67%
hyper_parallel / core / device_mesh.py	(no function)		68	0	0		100%
hyper_parallel / core / dtensor.py	SkipDTensorDispatch.__enter__		2	0	0		100%
hyper_parallel / core / dtensor.py	SkipDTensorDispatch.__exit__		2	0	0		100%
hyper_parallel / core / dtensor.py	_build_layout		4	0	0		100%
hyper_parallel / core / dtensor.py	DTensor.__init_data__		4	0	0		100%
hyper_parallel / core / dtensor.py	DTensor.device_mesh		1	0	0		100%
hyper_parallel / core / dtensor.py	DTensor.placements		1	0	0		100%
hyper_parallel / core / dtensor.py	DTensor.layout		3	1	0		67%
hyper_parallel / core / dtensor.py	DTensor.from_local		1	0	0		100%
hyper_parallel / core / dtensor.py	DTensor.to_local		1	0	0		100%
hyper_parallel / core / dtensor.py	DTensor.shape		1	0	0		100%
hyper_parallel / core / dtensor.py	DTensor.size		4	4	0		0%
hyper_parallel / core / dtensor.py	DTensor.local_shape		1	0	0		100%
hyper_parallel / core / dtensor.py	DTensor.redistribute		4	0	0		100%
hyper_parallel / core / dtensor.py	DTensor.reduce_partial		7	1	0		86%
hyper_parallel / core / dtensor.py	DTensor.full_tensor		10	1	0		90%
hyper_parallel / core / dtensor.py	distribute_tensor		3	0	0		100%
hyper_parallel / core / dtensor.py	_dtensor_init_helper		6	0	0		100%
hyper_parallel / core / dtensor.py	ones		2	0	0		100%
hyper_parallel / core / dtensor.py	empty		2	0	0		100%
hyper_parallel / core / dtensor.py	full		2	0	0		100%
hyper_parallel / core / dtensor.py	zeros		2	0	0		100%
hyper_parallel / core / dtensor.py	(no function)		41	0	0		100%
hyper_parallel / core / fully_shard / __init__.py	(no function)		2	0	0		100%
hyper_parallel / core / fully_shard / api.py	_UnshardHandle.__init__		1	1	0		0%
hyper_parallel / core / fully_shard / api.py	_UnshardHandle.wait		3	3	0		0%
hyper_parallel / core / fully_shard / api.py	HSDPModule.hsdp_init		7	2	0		71%
hyper_parallel / core / fully_shard / api.py	HSDPModule.set_requires_gradient_sync		7	1	0		86%
hyper_parallel / core / fully_shard / api.py	HSDPModule.zero_grads		7	7	0		0%
hyper_parallel / core / fully_shard / api.py	HSDPModule.set_modules_to_forward_prefetch		8	1	0		88%
hyper_parallel / core / fully_shard / api.py	HSDPModule.set_modules_to_backward_prefetch		8	2	0		75%
hyper_parallel / core / fully_shard / api.py	HSDPModule.reshard		5	2	0		60%
hyper_parallel / core / fully_shard / api.py	HSDPModule.unshard		10	4	0		60%
hyper_parallel / core / fully_shard / api.py	HSDPModule.load_state_dict		42	42	0		0%
hyper_parallel / core / fully_shard / api.py	HSDPModule.set_is_last_backward		1	0	0		100%
hyper_parallel / core / fully_shard / api.py	HSDPModule.set_requires_all_reduce		9	1	0		89%
hyper_parallel / core / fully_shard / api.py	HSDPModule.set_reshard_after_forward		9	1	0		89%
hyper_parallel / core / fully_shard / api.py	HSDPModule.set_reshard_after_backward		9	1	0		89%
hyper_parallel / core / fully_shard / api.py	HSDPModule.set_reduce_op_type		2	0	0		100%
hyper_parallel / core / fully_shard / api.py	_extend_module_with_hsdp_interface		6	0	0		100%
hyper_parallel / core / fully_shard / api.py	_check_module_valid		7	7	0		0%
hyper_parallel / core / fully_shard / api.py	_check_hsdp_input_valid		23	23	0		0%
hyper_parallel / core / fully_shard / api.py	fully_shard		10	1	0		90%
hyper_parallel / core / fully_shard / api.py	_gather_full_state_dict		15	0	0		100%
hyper_parallel / core / fully_shard / api.py	_offload_sharded_state_dict		8	2	0		75%
hyper_parallel / core / fully_shard / api.py	get_model_state_dict		13	1	0		92%
hyper_parallel / core / fully_shard / api.py	hsdp_sync_stream		3	3	0		0%
hyper_parallel / core / fully_shard / api.py	(no function)		36	0	0		100%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	HSDPAsyncGradHook._pre_process		5	5	0		0%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	HSDPAsyncGradHook._post_process		5	5	0		0%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_final_async_grad_hook		2	2	0		0%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_final_async_grad_hook.async_hook_handler		7	7	0		0%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_final_async_grad_hook.async_hook_handler.post_process		5	5	0		0%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_unsharded_hook		6	6	0		0%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_unsharded_hook.grad_all_reduce_hook		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_unsharded_hook.grad_acc_all_reduce_hook		4	4	0		0%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_fully_sharded_hook		8	8	0		0%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_fully_sharded_hook.grad_reduce_scatter_hook		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_fully_sharded_hook.grad_acc_reduce_scatter_hook		4	4	0		0%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_fully_sharded_hook.grad_reduce_scatter_acc_post_hook		2	2	0		0%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_partial_sharded_hook		9	9	0		0%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_partial_sharded_hook.grad_reduce_scatter_hook		2	2	0		0%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_partial_sharded_hook.grad_acc_reduce_scatter_hook		5	5	0		0%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_partial_sharded_hook.grad_reduce_scatter_acc_hook		5	5	0		0%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	HSDPAsyncGradHook.get_hook		7	7	0		0%
hyper_parallel / core / fully_shard / hsdp_async_grad_hook.py	(no function)		10	0	0		100%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	HSDPGradBuffer.__init__		21	21	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	HSDPGradBuffer.add_param		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	HSDPGradBuffer.init		4	4	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	HSDPGradBuffer.set_requires_grad_sync		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	HSDPGradBuffer._set_handle		7	7	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	HSDPGradBuffer._init_grad_buffer_index		7	7	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	HSDPGradBuffer._init_acc_grad_buffer		8	8	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	HSDPGradBuffer._copy_grad_to_unsharded_buffer		10	10	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	HSDPGradBuffer._add_grad_to_acc_buffer		3	3	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	HSDPGradBuffer._set_grad_data		15	15	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	HSDPGradBuffer._handle_single_node_grad		4	4	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	HSDPGradBuffer._reduce_no_shard_grad		9	9	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	HSDPGradBuffer._reduce_fully_shard_grad		19	19	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	HSDPGradBuffer._reduce_partial_shard_grad		22	22	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	HSDPGradBuffer._reduce_grads		7	7	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	HSDPGradBuffer.zero_grads		3	3	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	HSDPGradBuffer.set_grad_ready		4	4	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_buffer.py	(no function)		19	0	0		100%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook.__init__		7	7	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._cast_hook		7	7	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._get_final_grad_hook		5	5	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._get_final_grad_hook.scale_with_cast_hook		5	5	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._get_final_grad_hook.scale_hook		5	5	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_single_node_hook		5	5	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_single_node_hook.grad_dummy_hook		2	2	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_single_node_hook.grad_hook		2	2	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_unsharded_hook		6	6	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_unsharded_hook.grad_all_reduce_hook		2	2	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_unsharded_hook.grad_acc_all_reduce_hook		5	5	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_fully_sharded_hook		9	9	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_fully_sharded_hook.grad_reduce_scatter_hook		2	2	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_fully_sharded_hook.grad_acc_reduce_scatter_hook		5	5	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_fully_sharded_hook.grad_reduce_scatter_acc_hook		3	3	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_partial_sharded_hook		9	9	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_partial_sharded_hook.grad_reduce_scatter_hook		3	3	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_partial_sharded_hook.grad_acc_reduce_scatter_hook		6	6	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_partial_sharded_hook.grad_reduce_scatter_acc_hook		6	6	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook.get_hook		7	7	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	HSDPGradHook.set_requires_grad_sync		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_grad_hook.py	(no function)		11	0	0		100%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.__init__		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2._init_sharded_param		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2._init_sharded_post_forward_param_metadata		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.init_dtype_attrs		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2._init_extensions		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.init_all_gather_outputs		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.init_unsharded_param		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.to_sharded		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.to_sharded_post_forward		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.to_unsharded		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.to_sharded_dtensor		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.to_sharded_post_forward_dtensor		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.to_accumulated_grad_if_needed		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.accumulate_unsharded_grad_if_needed		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.alloc_all_gather_outputs		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.free_unsharded_param		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.all_gather_inputs		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.unsharded_param		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.unsharded_grad_data		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.unsharded_accumulated_grad_data		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2._sharded_local_tensor		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2._get_unsharded_param_data		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.unshard		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.wait_for_unshard		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.shard		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.reduce_scatter_grad		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	HSDPParamV2.all_reduce_grad		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param.py	(no function)		33	0	0		100%
hyper_parallel / core / fully_shard / hsdp_param_buffer.py	HSDPParamBuffer.__init__		13	13	0		0%
hyper_parallel / core / fully_shard / hsdp_param_buffer.py	HSDPParamBuffer.init		8	8	0		0%
hyper_parallel / core / fully_shard / hsdp_param_buffer.py	HSDPParamBuffer._init_param_buffer		8	8	0		0%
hyper_parallel / core / fully_shard / hsdp_param_buffer.py	HSDPParamBuffer.add_param		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_param_buffer.py	HSDPParamBuffer.to_sharded		4	4	0		0%
hyper_parallel / core / fully_shard / hsdp_param_buffer.py	HSDPParamBuffer._update_data_view		2	2	0		0%
hyper_parallel / core / fully_shard / hsdp_param_buffer.py	HSDPParamBuffer.prefetch_unsharded		6	6	0		0%
hyper_parallel / core / fully_shard / hsdp_param_buffer.py	HSDPParamBuffer.to_unsharded		19	19	0		0%
hyper_parallel / core / fully_shard / hsdp_param_buffer.py	HSDPParamBuffer.wait_for_unsharded		13	13	0		0%
hyper_parallel / core / fully_shard / hsdp_param_buffer.py	(no function)		10	0	0		100%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerContext.__init__		3	0	0		100%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2.__init__		17	0	0		100%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2._init_platform		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2._new_cell_state		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2._new_grad_hook		3	3	0		0%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2._register_hooks		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2._register_grad_hook		6	6	0		0%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2._register_forward_backward_hooks		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2.set_reshard_after_forward		4	1	0		75%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2.set_reshard_after_backward		4	1	0		75%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2.set_requires_all_reduce		4	1	0		75%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2.set_requires_grad_sync		4	1	0		75%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2.zero_grads		2	2	0		0%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2._hsdp_forward_pre_hook		11	2	0		82%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2._hsdp_forward_hook		8	1	0		88%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2._hsdp_backward_pre_hook		5	5	0		0%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2._hsdp_backward_hook		2	2	0		0%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2._get_grad_buffer_hook		2	2	0		0%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2._get_grad_buffer_hook.hook		3	3	0		0%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2.set_forward_prefetch_cells		1	0	0		100%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2.set_backward_prefetch_cells		1	0	0		100%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2.set_requires_allreuce		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	HSDPSchedulerV2.reshard		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_scheduler.py	(no function)		29	0	0		100%
hyper_parallel / core / fully_shard / hsdp_state.py	HSDPState.__init__		16	0	0		100%
hyper_parallel / core / fully_shard / hsdp_state.py	HSDPState._init_hsdp_params		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_state.py	HSDPState._move_states_to_device		1	1	0		0%
hyper_parallel / core / fully_shard / hsdp_state.py	HSDPState._init_param_buffers		14	12	0		14%
hyper_parallel / core / fully_shard / hsdp_state.py	HSDPState._init_grad_buffers		20	18	0		10%
hyper_parallel / core / fully_shard / hsdp_state.py	HSDPState._init_grad_buffers.get_bucket_key		12	12	0		0%
hyper_parallel / core / fully_shard / hsdp_state.py	HSDPState.shard		8	3	0		62%
hyper_parallel / core / fully_shard / hsdp_state.py	HSDPState.unshard		8	2	0		75%
hyper_parallel / core / fully_shard / hsdp_state.py	HSDPState.prefetch		7	7	0		0%
hyper_parallel / core / fully_shard / hsdp_state.py	HSDPState.wait_for_unsharded		9	9	0		0%
hyper_parallel / core / fully_shard / hsdp_state.py	HSDPState.zero_grads		7	7	0		0%
hyper_parallel / core / fully_shard / hsdp_state.py	HSDPState.set_grad_ready		6	6	0		0%
hyper_parallel / core / fully_shard / hsdp_state.py	HSDPState.set_requires_grad_sync		4	4	0		0%
hyper_parallel / core / fully_shard / hsdp_state.py	(no function)		18	0	0		100%
hyper_parallel / core / fully_shard / hsdp_utils.py	GroupInfo.__init__		3	3	0		0%
hyper_parallel / core / fully_shard / hsdp_utils.py	HSDPConfigV2.__init__		10	0	0		100%
hyper_parallel / core / fully_shard / hsdp_utils.py	ExtensionsData.clear		2	2	0		0%
hyper_parallel / core / fully_shard / hsdp_utils.py	_named_parameters_with_duplicates		9	4	0		56%
hyper_parallel / core / fully_shard / hsdp_utils.py	_get_param_module_infos		13	3	0		77%
hyper_parallel / core / fully_shard / hsdp_utils.py	(no function)		34	0	0		100%
hyper_parallel / core / hsdp / __init__.py	(no function)		2	0	0		100%
hyper_parallel / core / hsdp / api.py	HSDPCell.hsdp_init		7	0	0		100%
hyper_parallel / core / hsdp / api.py	HSDPCell.set_requires_grad_sync		7	2	0		71%
hyper_parallel / core / hsdp / api.py	HSDPCell.zero_grads		5	1	0		80%
hyper_parallel / core / hsdp / api.py	HSDPCell.set_forward_prefetch_cells		8	3	0		62%
hyper_parallel / core / hsdp / api.py	HSDPCell.set_backward_prefetch_cells		8	3	0		62%
hyper_parallel / core / hsdp / api.py	_extend_cell_with_hsdp_interface		6	0	0		100%
hyper_parallel / core / hsdp / api.py	_check_cell_valid		7	2	0		71%
hyper_parallel / core / hsdp / api.py	_check_hsdp_input_valid		26	11	0		58%
hyper_parallel / core / hsdp / api.py	hsdp		6	0	0		100%
hyper_parallel / core / hsdp / api.py	hsdp_sync_stream		3	1	0		67%
hyper_parallel / core / hsdp / api.py	(no function)		18	0	0		100%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	HSDPAsyncGradHook._pre_process		5	2	0		60%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	HSDPAsyncGradHook._post_process		5	2	0		60%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_final_async_grad_hook		2	0	0		100%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_final_async_grad_hook.async_hook_handler		7	0	0		100%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_final_async_grad_hook.async_hook_handler.post_process		5	1	0		80%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_unsharded_hook		6	0	0		100%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_unsharded_hook.grad_all_reduce_hook		1	0	0		100%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_unsharded_hook.grad_acc_all_reduce_hook		4	0	0		100%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_fully_sharded_hook		8	3	0		62%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_fully_sharded_hook.grad_reduce_scatter_hook		1	0	0		100%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_fully_sharded_hook.grad_acc_reduce_scatter_hook		4	4	0		0%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_fully_sharded_hook.grad_reduce_scatter_acc_post_hook		2	2	0		0%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_partial_sharded_hook		9	1	0		89%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_partial_sharded_hook.grad_reduce_scatter_hook		2	0	0		100%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_partial_sharded_hook.grad_acc_reduce_scatter_hook		5	5	0		0%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	HSDPAsyncGradHook._get_async_param_partial_sharded_hook.grad_reduce_scatter_acc_hook		5	0	0		100%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	HSDPAsyncGradHook.get_hook		7	1	0		86%
hyper_parallel / core / hsdp / hsdp_async_grad_hook.py	(no function)		10	0	0		100%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	HSDPGradBuffer.__init__		21	1	0		95%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	HSDPGradBuffer.add_param		1	0	0		100%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	HSDPGradBuffer.init		4	0	0		100%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	HSDPGradBuffer.set_requires_grad_sync		1	1	0		0%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	HSDPGradBuffer._set_handle		7	4	0		43%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	HSDPGradBuffer._init_grad_buffer_index		7	0	0		100%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	HSDPGradBuffer._init_acc_grad_buffer		8	6	0		25%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	HSDPGradBuffer._copy_grad_to_unsharded_buffer		10	2	0		80%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	HSDPGradBuffer._add_grad_to_acc_buffer		3	3	0		0%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	HSDPGradBuffer._set_grad_data		15	3	0		80%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	HSDPGradBuffer._handle_single_node_grad		4	4	0		0%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	HSDPGradBuffer._reduce_no_shard_grad		9	9	0		0%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	HSDPGradBuffer._reduce_fully_shard_grad		19	14	0		26%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	HSDPGradBuffer._reduce_partial_shard_grad		22	22	0		0%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	HSDPGradBuffer._reduce_grads		7	4	0		43%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	HSDPGradBuffer.zero_grads		3	3	0		0%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	HSDPGradBuffer.set_grad_ready		4	0	0		100%
hyper_parallel / core / hsdp / hsdp_grad_buffer.py	(no function)		19	0	0		100%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook.__init__		7	0	0		100%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._cast_hook		7	7	0		0%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._get_final_grad_hook		5	1	0		80%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._get_final_grad_hook.scale_with_cast_hook		5	2	0		60%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._get_final_grad_hook.scale_hook		5	5	0		0%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_single_node_hook		5	5	0		0%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_single_node_hook.grad_dummy_hook		2	2	0		0%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_single_node_hook.grad_hook		2	2	0		0%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_unsharded_hook		6	0	0		100%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_unsharded_hook.grad_all_reduce_hook		2	0	0		100%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_unsharded_hook.grad_acc_all_reduce_hook		5	0	0		100%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_fully_sharded_hook		9	0	0		100%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_fully_sharded_hook.grad_reduce_scatter_hook		2	0	0		100%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_fully_sharded_hook.grad_acc_reduce_scatter_hook		5	5	0		0%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_fully_sharded_hook.grad_reduce_scatter_acc_hook		3	3	0		0%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_partial_sharded_hook		9	0	0		100%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_partial_sharded_hook.grad_reduce_scatter_hook		3	0	0		100%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_partial_sharded_hook.grad_acc_reduce_scatter_hook		6	6	0		0%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook._get_hsdp_param_partial_sharded_hook.grad_reduce_scatter_acc_hook		6	0	0		100%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook.get_hook		7	1	0		86%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	HSDPGradHook.set_requires_grad_sync		1	0	0		100%
hyper_parallel / core / hsdp / hsdp_grad_hook.py	(no function)		11	0	0		100%
hyper_parallel / core / hsdp / hsdp_param.py	HSDPParam.__init__		26	0	0		100%
hyper_parallel / core / hsdp / hsdp_param.py	HSDPParam._init_rank_info		65	6	0		91%
hyper_parallel / core / hsdp / hsdp_param.py	HSDPParam._hsdp_rank_to_global_rank		18	1	0		94%
hyper_parallel / core / hsdp / hsdp_param.py	HSDPParam._get_op_rank_list		7	0	0		100%
hyper_parallel / core / hsdp / hsdp_param.py	HSDPParam._get_dp_rank_list		9	0	0		100%
hyper_parallel / core / hsdp / hsdp_param.py	HSDPParam._init_sharded_param		1	1	0		0%
hyper_parallel / core / hsdp / hsdp_param.py	HSDPParam._init_unsharded_param		1	1	0		0%
hyper_parallel / core / hsdp / hsdp_param.py	HSDPParam._get_unsharded_param_data		2	0	0		100%
hyper_parallel / core / hsdp / hsdp_param.py	HSDPParam._init_param_shard_size		22	2	0		91%
hyper_parallel / core / hsdp / hsdp_param.py	HSDPParam._init_param_shard_size._gcd		8	2	0		75%
hyper_parallel / core / hsdp / hsdp_param.py	HSDPParam._create_sharded_dp_group		7	0	0		100%
hyper_parallel / core / hsdp / hsdp_param.py	HSDPParam._create_unsharded_dp_group		7	0	0		100%
hyper_parallel / core / hsdp / hsdp_param.py	HSDPParam._init_param		28	2	0		93%
hyper_parallel / core / hsdp / hsdp_param.py	HSDPParam.to_sharded		1	0	0		100%
hyper_parallel / core / hsdp / hsdp_param.py	HSDPParam.prefetch_unsharded		5	1	0		80%
hyper_parallel / core / hsdp / hsdp_param.py	HSDPParam.to_unsharded		10	0	0		100%
hyper_parallel / core / hsdp / hsdp_param.py	HSDPParam.zero_acc_grad		2	0	0		100%
hyper_parallel / core / hsdp / hsdp_param.py	(no function)		20	0	0		100%
hyper_parallel / core / hsdp / hsdp_param_buffer.py	HSDPParamBuffer.__init__		13	0	0		100%
hyper_parallel / core / hsdp / hsdp_param_buffer.py	HSDPParamBuffer.init		8	0	0		100%
hyper_parallel / core / hsdp / hsdp_param_buffer.py	HSDPParamBuffer._init_param_buffer		8	0	0		100%
hyper_parallel / core / hsdp / hsdp_param_buffer.py	HSDPParamBuffer.add_param		1	0	0		100%
hyper_parallel / core / hsdp / hsdp_param_buffer.py	HSDPParamBuffer.to_sharded		4	0	0		100%
hyper_parallel / core / hsdp / hsdp_param_buffer.py	HSDPParamBuffer._update_data_view		2	0	0		100%
hyper_parallel / core / hsdp / hsdp_param_buffer.py	HSDPParamBuffer.prefetch_unsharded		6	6	0		0%
hyper_parallel / core / hsdp / hsdp_param_buffer.py	HSDPParamBuffer.to_unsharded		15	4	0		73%
hyper_parallel / core / hsdp / hsdp_param_buffer.py	(no function)		9	0	0		100%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler.__init__		13	0	0		100%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler._init_platform		1	1	0		0%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler._new_cell_state		1	1	0		0%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler._new_grad_hook		3	3	0		0%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler._register_hooks		4	0	0		100%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler._register_grad_hook		6	0	0		100%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler._register_forward_backward_hooks		1	1	0		0%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler.set_requires_grad_sync		3	0	0		100%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler.zero_grads		2	0	0		100%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler._hsdp_forward_pre_hook		8	1	0		88%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler._hsdp_forward_hook		4	1	0		75%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler._hsdp_backward_pre_hook		4	1	0		75%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler._hsdp_backward_hook		2	0	0		100%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler._hsdp_acc_backward_hook		3	0	0		100%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler._get_grad_buffer_hook		2	0	0		100%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler._get_grad_buffer_hook.hook		3	0	0		100%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler.set_forward_prefetch_cells		1	0	0		100%
hyper_parallel / core / hsdp / hsdp_scheduler.py	HSDPScheduler.set_backward_prefetch_cells		1	0	0		100%
hyper_parallel / core / hsdp / hsdp_scheduler.py	(no function)		27	0	0		100%
hyper_parallel / core / hsdp / hsdp_state.py	HSDPState.__init__		11	0	0		100%
hyper_parallel / core / hsdp / hsdp_state.py	HSDPState._init_hsdp_params		1	1	0		0%
hyper_parallel / core / hsdp / hsdp_state.py	HSDPState._init_param_buffers		14	0	0		100%
hyper_parallel / core / hsdp / hsdp_state.py	HSDPState._init_grad_buffers		20	1	0		95%
hyper_parallel / core / hsdp / hsdp_state.py	HSDPState._init_grad_buffers.get_bucket_key		12	10	0		17%
hyper_parallel / core / hsdp / hsdp_state.py	HSDPState.shard		8	1	0		88%
hyper_parallel / core / hsdp / hsdp_state.py	HSDPState.unshard		8	0	0		100%
hyper_parallel / core / hsdp / hsdp_state.py	HSDPState.prefetch		7	3	0		57%
hyper_parallel / core / hsdp / hsdp_state.py	HSDPState.zero_grads		7	3	0		57%
hyper_parallel / core / hsdp / hsdp_state.py	HSDPState.set_grad_ready		6	2	0		67%
hyper_parallel / core / hsdp / hsdp_state.py	HSDPState.set_requires_grad_sync		4	2	0		50%
hyper_parallel / core / hsdp / hsdp_state.py	(no function)		13	0	0		100%
hyper_parallel / core / hsdp / hsdp_utils.py	GroupInfo.__init__		3	0	0		100%
hyper_parallel / core / hsdp / hsdp_utils.py	HSDPConfig.__init__		11	0	0		100%
hyper_parallel / core / hsdp / hsdp_utils.py	(no function)		9	0	0		100%
hyper_parallel / core / layout.py	_infer_slice_area_by_rank		24	0	0		100%
hyper_parallel / core / layout.py	_infer_slice_area_by_rank._get_dev_num_alone_dim		1	0	0		100%
hyper_parallel / core / layout.py	_infer_slice_area_by_rank._rank_id_to_dev_id_list		6	0	0		100%
hyper_parallel / core / layout.py	_get_slice_tensor_by_layout		5	0	0		100%
hyper_parallel / core / layout.py	_get_slice_tensor_by_layout.get_slice_data		4	0	0		100%
hyper_parallel / core / layout.py	_infer_slice_shape_by_layout		10	0	0		100%
hyper_parallel / core / layout.py	Layout.__init__		11	0	0		100%
hyper_parallel / core / layout.py	Layout.from_device_mesh		11	0	0		100%
hyper_parallel / core / layout.py	Layout.__call__		7	1	0		86%
hyper_parallel / core / layout.py	Layout._process_placement_layout		2	0	0		100%
hyper_parallel / core / layout.py	Layout._process_alias_layout		31	6	0		81%
hyper_parallel / core / layout.py	Layout.to_dict		6	2	0		67%
hyper_parallel / core / layout.py	Layout.placement_to_tensor_map		10	0	0		100%
hyper_parallel / core / layout.py	Layout._handle_zero_dim_placement		6	0	0		100%
hyper_parallel / core / layout.py	Layout._build_dim_map_from_placements		15	1	0		93%
hyper_parallel / core / layout.py	Layout._extract_reduce_op		4	0	0		100%
hyper_parallel / core / layout.py	Layout._convert_dim_map_to_tensor_map		2	0	0		100%
hyper_parallel / core / layout.py	Layout._build_readable_tensor_map		9	2	0		78%
hyper_parallel / core / layout.py	Layout.tensor_map_to_placement		15	1	0		93%
hyper_parallel / core / layout.py	Layout.__setstate__		2	0	0		100%
hyper_parallel / core / layout.py	Layout.mesh		1	0	0		100%
hyper_parallel / core / layout.py	Layout.update_mesh		1	0	0		100%
hyper_parallel / core / layout.py	Layout.rank_list		1	0	0		100%
hyper_parallel / core / layout.py	Layout.rank_list		1	1	0		0%
hyper_parallel / core / layout.py	Layout.mesh_shape		1	0	0		100%
hyper_parallel / core / layout.py	Layout.alias_name		1	0	0		100%
hyper_parallel / core / layout.py	Layout.alias_tensor_map		1	0	0		100%
hyper_parallel / core / layout.py	Layout.set_alias_tensor_map		1	0	0		100%
hyper_parallel / core / layout.py	Layout.placements		1	0	0		100%
hyper_parallel / core / layout.py	Layout.set_placements		1	0	0		100%
hyper_parallel / core / layout.py	Layout.tensor_map		1	0	0		100%
hyper_parallel / core / layout.py	Layout.set_tensor_map		1	0	0		100%
hyper_parallel / core / layout.py	Layout.partial		1	0	0		100%
hyper_parallel / core / layout.py	Layout.set_partial_by_dev_axis		7	2	0		71%
hyper_parallel / core / layout.py	Layout.get_partial_by_dev_id		1	0	0		100%
hyper_parallel / core / layout.py	Layout.is_dev_axis_apply_shard		4	0	0		100%
hyper_parallel / core / layout.py	Layout.is_dev_axis_apply_shard.flatten		6	1	0		83%
hyper_parallel / core / layout.py	Layout.get_dev_axis_apply_shard_axis		4	0	0		100%
hyper_parallel / core / layout.py	Layout.reset_partial		3	0	0		100%
hyper_parallel / core / layout.py	Layout.is_partial		1	0	0		100%
hyper_parallel / core / layout.py	Layout.get_global_shape		1	0	0		100%
hyper_parallel / core / layout.py	Layout.get_devices_for_axis		1	1	0		0%
hyper_parallel / core / layout.py	Layout.get_comm_group_by_axis		1	0	0		100%
hyper_parallel / core / layout.py	Layout.repeat_num		16	5	0		69%
hyper_parallel / core / layout.py	Layout._to_compact_string		4	0	0		100%
hyper_parallel / core / layout.py	Layout.compact_str		1	0	0		100%
hyper_parallel / core / layout.py	Layout.update_compact_str		1	0	0		100%
hyper_parallel / core / layout.py	Layout.to_string		16	3	0		81%
hyper_parallel / core / layout.py	Layout.__str__		1	0	0		100%
hyper_parallel / core / layout.py	Layout.__repr__		1	1	0		0%
hyper_parallel / core / layout.py	Layout.__eq__		7	3	0		57%
hyper_parallel / core / layout.py	(no function)		66	0	0		100%
hyper_parallel / core / parameter_init.py	init_parameters		3	0	0		100%
hyper_parallel / core / parameter_init.py	(no function)		1	0	0		100%
hyper_parallel / core / pipeline_parallel / __init__.py	(no function)		4	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	MetaStep.__init__		3	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	MetaStep.micro_index		1	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	MetaStep.stage_index		1	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	MetaStep.type		1	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	MetaStep.__eq__		3	3	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	MetaStep.__ne__		3	3	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	MetaStep.__hash__		1	1	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	MetaStep.__str__		1	1	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	MetaStep.__repr__		1	1	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	MetaStep.from_str		1	1	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	PipelineScheduleRuntime.__init__		15	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	PipelineScheduleRuntime.convert_stages_dict		4	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	PipelineScheduleRuntime.split_microbatches		4	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	PipelineScheduleRuntime._check_stages		8	3	0		62%
hyper_parallel / core / pipeline_parallel / scheduler.py	PipelineScheduleRuntime._init_stages		2	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	PipelineScheduleRuntime.run		4	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	PipelineScheduleRuntime.sync_shared_parameters_grad		2	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	PipelineScheduleRuntime.update_losses		2	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	PipelineScheduleRuntime._wait_p2p		3	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	PipelineScheduleRuntime.run_microbatches		48	12	0		75%
hyper_parallel / core / pipeline_parallel / scheduler.py	add_send_recv		19	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	add_send_recv._need_com		13	1	0		92%
hyper_parallel / core / pipeline_parallel / scheduler.py	add_send_recv.stage_to_rank		7	5	0		29%
hyper_parallel / core / pipeline_parallel / scheduler.py	add_send_recv.process_rank_communication		11	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	ScheduleGPipe.__init__		2	2	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	ScheduleGPipe.construct_exec_order		15	15	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	Schedule1F1B.__init__		2	2	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	Schedule1F1B.construct_exec_order		42	42	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	ScheduleInterleaved1F1B.__init__		14	2	0		86%
hyper_parallel / core / pipeline_parallel / scheduler.py	ScheduleInterleaved1F1B.warmup_ops		3	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	ScheduleInterleaved1F1B.forward_stage_index		3	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	ScheduleInterleaved1F1B.backward_stage_index		4	0	0		100%
hyper_parallel / core / pipeline_parallel / scheduler.py	ScheduleInterleaved1F1B.construct_stage_exec_order		39	6	0		85%
hyper_parallel / core / pipeline_parallel / scheduler.py	detect_cycle_in_graph		39	39	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	output_cycle_results		8	8	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	parse_and_validate		23	23	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	parse_and_validate.parse_elements		3	3	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	generate_operations		35	35	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	generate_operations.stage_to_rank		7	7	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	generate_operations.find_send_target		3	3	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	generate_operations.find_recv_source		8	8	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	validate_pipeline_execution		6	6	0		0%
hyper_parallel / core / pipeline_parallel / scheduler.py	(no function)		62	0	0		100%
hyper_parallel / core / pipeline_parallel / stage.py	SharedParameterInfo.__init__		7	7	0		0%
hyper_parallel / core / pipeline_parallel / stage.py	SharedParameterInfo.parameter		1	1	0		0%
hyper_parallel / core / pipeline_parallel / stage.py	SharedParameterInfo.shared_stage		1	1	0		0%
hyper_parallel / core / pipeline_parallel / stage.py	SharedParameterInfo.__repr__		1	1	0		0%
hyper_parallel / core / pipeline_parallel / stage.py	SharedParameterInfo.__str__		1	1	0		0%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage.__init__		18	0	0		100%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage.init		3	0	0		100%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage._init_pp_group		8	0	0		100%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage.clear_states		2	2	0		0%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage._check_shared_parameters		10	8	0		20%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage._sync_shared_parameters		8	6	0		25%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage._global_rank		3	0	0		100%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage._init_shared_parameter_group		6	6	0		0%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage.sync_shared_parameters_grad		9	7	0		22%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage._check_src_stage		5	3	0		40%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage._check_dst_stage		5	3	0		40%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage._update_layout		8	8	0		0%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage.get_last_stage_sens		14	9	0		36%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage._construct_forward_recv_info		10	5	0		50%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage._communicate_meta		14	0	0		100%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage.exec_fwd_recv_ops		14	0	0		100%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage._construct_backward_recv_info		7	3	0		57%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage._extract_meta_from_tensor		3	1	0		67%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage.exec_fwd_send_ops		18	1	0		94%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage.exec_bwd_recv_ops		8	1	0		88%
hyper_parallel / core / pipeline_parallel / stage.py	PipelineStage.exec_bwd_send_ops		10	1	0		90%
hyper_parallel / core / pipeline_parallel / stage.py	(no function)		35	0	0		100%
hyper_parallel / core / pipeline_parallel / utils.py	BatchDimSpec.__init__		3	3	0		0%
hyper_parallel / core / pipeline_parallel / utils.py	BatchDimSpec.__repr__		1	1	0		0%
hyper_parallel / core / pipeline_parallel / utils.py	BatchDimSpec.__str__		1	1	0		0%
hyper_parallel / core / pipeline_parallel / utils.py	BatchDimSpec.from_tuple		3	3	0		0%
hyper_parallel / core / pipeline_parallel / utils.py	BatchDimSpec.from_dict		3	3	0		0%
hyper_parallel / core / pipeline_parallel / utils.py	_RecvInfo.__init__		2	0	0		100%
hyper_parallel / core / pipeline_parallel / utils.py	_RecvInfo.global_rank		1	0	0		100%
hyper_parallel / core / pipeline_parallel / utils.py	_RecvInfo.buffer		1	0	0		100%
hyper_parallel / core / pipeline_parallel / utils.py	_RecvInfo.buffer		1	0	0		100%
hyper_parallel / core / pipeline_parallel / utils.py	(no function)		17	0	0		100%
hyper_parallel / core / placement_types.py	Placement.__repr__		1	1	0		0%
hyper_parallel / core / placement_types.py	Placement.is_shard		1	1	0		0%
hyper_parallel / core / placement_types.py	Placement.is_replicate		1	1	0		0%
hyper_parallel / core / placement_types.py	Placement.is_partial		1	1	0		0%
hyper_parallel / core / placement_types.py	Shard.__init__		2	0	0		100%
hyper_parallel / core / placement_types.py	Shard.dim		1	0	0		100%
hyper_parallel / core / placement_types.py	Shard.is_shard		3	3	0		0%
hyper_parallel / core / placement_types.py	Shard.__eq__		1	0	0		100%
hyper_parallel / core / placement_types.py	Shard.__hash__		1	1	0		0%
hyper_parallel / core / placement_types.py	Shard.__repr__		2	2	0		0%
hyper_parallel / core / placement_types.py	Shard.__str__		1	1	0		0%
hyper_parallel / core / placement_types.py	Replicate.is_replicate		1	1	0		0%
hyper_parallel / core / placement_types.py	Replicate.__eq__		1	1	0		0%
hyper_parallel / core / placement_types.py	Replicate.__hash__		1	1	0		0%
hyper_parallel / core / placement_types.py	Replicate.__str__		1	1	0		0%
hyper_parallel / core / placement_types.py	Partial.__init__		2	0	0		100%
hyper_parallel / core / placement_types.py	Partial.reduce_op		1	0	0		100%
hyper_parallel / core / placement_types.py	Partial.is_partial		3	3	0		0%
hyper_parallel / core / placement_types.py	Partial.__eq__		3	3	0		0%
hyper_parallel / core / placement_types.py	Partial.__hash__		1	1	0		0%
hyper_parallel / core / placement_types.py	Partial.__repr__		2	2	0		0%
hyper_parallel / core / placement_types.py	Partial.__str__		1	1	0		0%
hyper_parallel / core / placement_types.py	(no function)		29	0	0		100%
hyper_parallel / core / random.py	is_rng_supported_mesh		4	4	0		0%
hyper_parallel / core / random.py	_PhiloxState.__init__		1	0	0		100%
hyper_parallel / core / random.py	_PhiloxState.state		1	0	0		100%
hyper_parallel / core / random.py	_PhiloxState.offset		1	0	0		100%
hyper_parallel / core / random.py	_PhiloxState.offset		2	0	0		100%
hyper_parallel / core / random.py	_PhiloxState.seed		1	1	0		0%
hyper_parallel / core / random.py	_PhiloxState.seed		2	2	0		0%
hyper_parallel / core / random.py	_RNGStateTracker.__init__		5	1	0		80%
hyper_parallel / core / random.py	_RNGStateTracker.distribute_region_enabled		1	0	0		100%
hyper_parallel / core / random.py	_RNGStateTracker.distribute_region_enabled		1	0	0		100%
hyper_parallel / core / random.py	_RNGStateTracker._distribute_region		1	1	0		0%
hyper_parallel / core / random.py	_RNGStateTracker._manual_seed		1	0	0		100%
hyper_parallel / core / random.py	OffsetBasedRNGTracker.__init__		8	0	0		100%
hyper_parallel / core / random.py	OffsetBasedRNGTracker._get_device_state		2	0	0		100%
hyper_parallel / core / random.py	OffsetBasedRNGTracker._set_device_state		1	0	0		100%
hyper_parallel / core / random.py	OffsetBasedRNGTracker._distribute_region		15	2	0		87%
hyper_parallel / core / random.py	OffsetBasedRNGTracker._set_pre_op_offset		9	0	0		100%
hyper_parallel / core / random.py	OffsetBasedRNGTracker._set_post_op_offset		4	0	0		100%
hyper_parallel / core / random.py	OffsetBasedRNGTracker._calc_shard_linear_idx		1	0	0		100%
hyper_parallel / core / random.py	_calc_first_shard_size		7	3	0		57%
hyper_parallel / core / random.py	_calc_shard_info		25	11	0		56%
hyper_parallel / core / random.py	_calc_shard_linear_idx		6	0	0		100%
hyper_parallel / core / random.py	_resolve_device		4	0	0		100%
hyper_parallel / core / random.py	_resolve_device.get_device		1	0	0		100%
hyper_parallel / core / random.py	local_shard_size_and_offset		10	10	0		0%
hyper_parallel / core / random.py	fork_rng		19	7	0		63%
hyper_parallel / core / random.py	(no function)		52	0	0		100%
hyper_parallel / core / redistribute_infer.py	TensorMap.__init__		1	0	0		100%
hyper_parallel / core / redistribute_infer.py	TensorMap.GetDimByIdx		1	0	0		100%
hyper_parallel / core / redistribute_infer.py	TensorMap.GetIndexByValue		4	0	0		100%
hyper_parallel / core / redistribute_infer.py	TensorMap.GetIndexContainValue		8	8	0		0%
hyper_parallel / core / redistribute_infer.py	DevMat.__init__		2	0	0		100%
hyper_parallel / core / redistribute_infer.py	DevMat.GetDimByReverseIdx		3	1	0		67%
hyper_parallel / core / redistribute_infer.py	DevMat._GetCombinedSize		7	7	0		0%
hyper_parallel / core / redistribute_infer.py	DevMat._GetDevicesAlongDim		20	4	0		80%
hyper_parallel / core / redistribute_infer.py	DevMat.GetDevicesAlongDim		15	13	0		13%
hyper_parallel / core / redistribute_infer.py	RedistributionOperatorInfer.__init__		8	0	0		100%
hyper_parallel / core / redistribute_infer.py	RedistributionOperatorInfer.InsertOperator		2	0	0		100%
hyper_parallel / core / redistribute_infer.py	RedistributionOperatorInfer.InferRedistributionOperator		25	4	0		84%
hyper_parallel / core / redistribute_infer.py	RedistributionOperatorInfer._HandleSimpleSplitCase		11	1	0		91%
hyper_parallel / core / redistribute_infer.py	RedistributionOperatorInfer._HandleTupleSplitCase		12	10	0		17%
hyper_parallel / core / redistribute_infer.py	RedistributionOperatorInfer.InferSplitByAxis		16	3	0		81%
hyper_parallel / core / redistribute_infer.py	RedistributionOperatorInfer._HandleNoneDimPermuteCase		24	8	0		67%
hyper_parallel / core / redistribute_infer.py	RedistributionOperatorInfer._HandleNoneDimTuplePermuteCase		29	23	0		21%
hyper_parallel / core / redistribute_infer.py	RedistributionOperatorInfer._HandleTupleDimPermuteCase		29	27	0		7%
hyper_parallel / core / redistribute_infer.py	RedistributionOperatorInfer.InferPermuteByAxis		16	3	0		81%
hyper_parallel / core / redistribute_infer.py	RedistributionOperatorInfer._HandleTupleConcatCase		13	11	0		15%
hyper_parallel / core / redistribute_infer.py	RedistributionOperatorInfer._HandleSimpleConcatCase		12	3	0		75%
hyper_parallel / core / redistribute_infer.py	RedistributionOperatorInfer.InferConcatByAxis		11	2	0		82%
hyper_parallel / core / redistribute_infer.py	RedistributionOperatorInfer.InferOpsList		28	0	0		100%
hyper_parallel / core / redistribute_infer.py	(no function)		34	0	0		100%
hyper_parallel / core / shard / __init__.py	(no function)		0	0	0		100%
hyper_parallel / core / shard / _op_dispatch.py	enable_dtensor_dispatch		1	0	0		100%
hyper_parallel / core / shard / _op_dispatch.py	disable_dtensor_dispatch		1	0	0		100%
hyper_parallel / core / shard / _op_dispatch.py	get_dtensor_dispatch		1	0	0		100%
hyper_parallel / core / shard / _op_dispatch.py	LayoutCacheKey.__init__		1	0	0		100%
hyper_parallel / core / shard / _op_dispatch.py	LayoutCacheKey.__eq__		3	1	0		67%
hyper_parallel / core / shard / _op_dispatch.py	LayoutCacheKey.__hash__		5	0	0		100%
hyper_parallel / core / shard / _op_dispatch.py	LayoutCacheManager.__init__		2	0	0		100%
hyper_parallel / core / shard / _op_dispatch.py	LayoutCacheManager.get_instance		3	0	0		100%
hyper_parallel / core / shard / _op_dispatch.py	LayoutCacheManager.get_layout_cache		1	0	0		100%
hyper_parallel / core / shard / _op_dispatch.py	LayoutCacheManager.distributed_op		2	0	0		100%
hyper_parallel / core / shard / _op_dispatch.py	LayoutCacheManager.clear_cache		1	0	0		100%
hyper_parallel / core / shard / _op_dispatch.py	OpDispatcher.__init__		7	0	0		100%
hyper_parallel / core / shard / _op_dispatch.py	OpDispatcher._setup_paths_from_env		2	0	0		100%
hyper_parallel / core / shard / _op_dispatch.py	OpDispatcher._setup_yaml_dir		8	5	0		38%
hyper_parallel / core / shard / _op_dispatch.py	OpDispatcher._extend_sys_path		6	4	0		33%
hyper_parallel / core / shard / _op_dispatch.py	OpDispatcher._register_distributed_ops		2	0	0		100%
hyper_parallel / core / shard / _op_dispatch.py	OpDispatcher._register_single_distributed_op		19	11	0		42%
hyper_parallel / core / shard / _op_dispatch.py	OpDispatcher._process_args_and_kwargs		42	1	0		98%
hyper_parallel / core / shard / _op_dispatch.py	OpDispatcher._with_layout_infer		34	2	0		94%
hyper_parallel / core / shard / _op_dispatch.py	OpDispatcher._with_layout_infer_with_tuple_expand		52	13	0		75%
hyper_parallel / core / shard / _op_dispatch.py	OpDispatcher._with_layout_infer_reshape		33	0	0		100%
hyper_parallel / core / shard / _op_dispatch.py	OpDispatcher._process_args_and_kwargs_with_shape		54	16	0		70%
hyper_parallel / core / shard / _op_dispatch.py	OpDispatcher._with_layout_infer_with_shape		35	2	0		94%
hyper_parallel / core / shard / _op_dispatch.py	OpDispatcher._with_layout_infer_slice		37	37	0		0%
hyper_parallel / core / shard / _op_dispatch.py	OpDispatcher._merge_default		11	0	0		100%
hyper_parallel / core / shard / _op_dispatch.py	OpDispatcher.safe_load_yaml_from_dir		13	2	0		85%
hyper_parallel / core / shard / _op_dispatch.py	OpDispatcher.dispatch		19	4	0		79%
hyper_parallel / core / shard / _op_dispatch.py	(no function)		46	0	0		100%
hyper_parallel / core / shard / api.py	_has_kwargs		2	0	0		100%
hyper_parallel / core / shard / api.py	_get_param_name		2	0	0		100%
hyper_parallel / core / shard / api.py	_convert_sharding_plan		20	9	0		55%
hyper_parallel / core / shard / api.py	_convert_sharding_plan._is_placement_tuple		15	4	0		73%
hyper_parallel / core / shard / api.py	_convert_sharding_plan._to_layout		3	0	0		100%
hyper_parallel / core / shard / api.py	_convert_sharding_plan._convert_value		15	6	0		60%
hyper_parallel / core / shard / api.py	_convert_sharding_plan._convert_forward_plan		16	4	0		75%
hyper_parallel / core / shard / api.py	_parallel_in		19	1	0		95%
hyper_parallel / core / shard / api.py	_parallel_in._get_layout		4	0	0		100%
hyper_parallel / core / shard / api.py	_parallel_out		16	5	0		69%
hyper_parallel / core / shard / api.py	_forward_pre_hook		4	1	0		75%
hyper_parallel / core / shard / api.py	_forward_pre_with_kwargs_hook		3	1	0		67%
hyper_parallel / core / shard / api.py	_forward_hook		3	1	0		67%
hyper_parallel / core / shard / api.py	_forward_with_kwargs_hook		1	0	0		100%
hyper_parallel / core / shard / api.py	_register_hook		20	2	0		90%
hyper_parallel / core / shard / api.py	_register_hook._register_cell_hook		7	0	0		100%
hyper_parallel / core / shard / api.py	_register_hook._set_layouts		4	0	0		100%
hyper_parallel / core / shard / api.py	_register_local_tensor_hook		7	0	0		100%
hyper_parallel / core / shard / api.py	_register_local_tensor_hook.hook_func		2	0	0		100%
hyper_parallel / core / shard / api.py	_register_local_tensor_hook.hook_func._recursive_to_local		8	5	0		38%
hyper_parallel / core / shard / api.py	_shard_callable		6	1	0		83%
hyper_parallel / core / shard / api.py	_shard_callable._shard_wrapper		8	8	0		0%
hyper_parallel / core / shard / api.py	shard_module		42	6	0		86%
hyper_parallel / core / shard / api.py	parallelize_value_and_grad		10	0	0		100%
hyper_parallel / core / shard / api.py	parallelize_value_and_grad.CellWrapper.__init__		2	0	0		100%
hyper_parallel / core / shard / api.py	parallelize_value_and_grad.CellWrapper.construct		1	0	0		100%
hyper_parallel / core / shard / api.py	parallelize_value_and_grad.CellWrapper.forward		1	1	0		0%
hyper_parallel / core / shard / api.py	parallelize_value_and_grad.wrapper		38	14	0		63%
hyper_parallel / core / shard / api.py	(no function)		26	0	0		100%
hyper_parallel / core / shard / local_func.py	custom_shard		2	0	0		100%
hyper_parallel / core / shard / local_func.py	custom_shard.wrapped		37	8	0		78%
hyper_parallel / core / shard / local_func.py	(no function)		9	0	0		100%
hyper_parallel / core / shard / ops / __init__.py	(no function)		0	0	0		100%
hyper_parallel / core / shard / ops / parallel_activation_with_axis.py	ActivationWithAxisDistributedOp.infer_layout		12	2	0		83%
hyper_parallel / core / shard / ops / parallel_activation_with_axis.py	ActivationWithAxisDistributedOp.check_layout		14	1	0		93%
hyper_parallel / core / shard / ops / parallel_activation_with_axis.py	(no function)		4	0	0		100%
hyper_parallel / core / shard / ops / parallel_argmax_with_value_ops.py	ArgMaxWithValueDistributedOp.infer_layout		21	21	0		0%
hyper_parallel / core / shard / ops / parallel_argmax_with_value_ops.py	ArgMaxWithValueDistributedOp.infer_layout.is_shard		10	10	0		0%
hyper_parallel / core / shard / ops / parallel_argmax_with_value_ops.py	(no function)		3	0	0		100%
hyper_parallel / core / shard / ops / parallel_concat.py	ConcatDistributedOp.infer_layout		28	28	0		0%
hyper_parallel / core / shard / ops / parallel_concat.py	(no function)		4	0	0		100%
hyper_parallel / core / shard / ops / parallel_cumsum.py	CumsumDistributedOp.infer_layout		23	4	0		83%
hyper_parallel / core / shard / ops / parallel_cumsum.py	CumsumDistributedOp.infer_layout.idx_to_alias		3	0	0		100%
hyper_parallel / core / shard / ops / parallel_cumsum.py	(no function)		4	0	0		100%
hyper_parallel / core / shard / ops / parallel_elementwise.py	ElementWiseDistributedOp.infer_layout		19	4	0		79%
hyper_parallel / core / shard / ops / parallel_elementwise.py	ElementWiseDistributedOp._handle_no_input_shapes		5	5	0		0%
hyper_parallel / core / shard / ops / parallel_elementwise.py	ElementWiseDistributedOp._align_layouts_and_shapes		8	0	0		100%
hyper_parallel / core / shard / ops / parallel_elementwise.py	ElementWiseDistributedOp._compute_output_shape		4	0	0		100%
hyper_parallel / core / shard / ops / parallel_elementwise.py	ElementWiseDistributedOp._merge_all_layouts		8	3	0		62%
hyper_parallel / core / shard / ops / parallel_elementwise.py	ElementWiseDistributedOp._extract_input_shapes		7	2	0		71%
hyper_parallel / core / shard / ops / parallel_elementwise.py	ElementWiseDistributedOp._merge_partial_status		15	2	0		87%
hyper_parallel / core / shard / ops / parallel_elementwise.py	ElementWiseDistributedOp._check_shard_partial_conflict		17	6	0		65%
hyper_parallel / core / shard / ops / parallel_elementwise.py	ElementWiseDistributedOp._check_all_inputs_broadcasts_and_partial		16	2	0		88%
hyper_parallel / core / shard / ops / parallel_elementwise.py	ElementWiseDistributedOp._merge_tensor_maps_without_shape		23	23	0		0%
hyper_parallel / core / shard / ops / parallel_elementwise.py	ElementWiseDistributedOp._broadcast_shapes		14	2	0		86%
hyper_parallel / core / shard / ops / parallel_elementwise.py	ElementWiseDistributedOp._align_tensor_maps_for_broadcast		7	0	0		100%
hyper_parallel / core / shard / ops / parallel_elementwise.py	ElementWiseDistributedOp._normalize_tensor_map_element		7	3	0		57%
hyper_parallel / core / shard / ops / parallel_elementwise.py	ElementWiseDistributedOp._denormalize_tensor_map_element		5	2	0		60%
hyper_parallel / core / shard / ops / parallel_elementwise.py	ElementWiseDistributedOp._merge_tensor_maps_for_broadcast		30	6	0		80%
hyper_parallel / core / shard / ops / parallel_elementwise.py	ElementWiseDistributedOp._create_output_layout		16	2	0		88%
hyper_parallel / core / shard / ops / parallel_elementwise.py	ElementWiseWithPartialDistributedOp.__init__		2	0	0		100%
hyper_parallel / core / shard / ops / parallel_elementwise.py	AddDistributedOp.get_expand_impl		15	1	0		93%
hyper_parallel / core / shard / ops / parallel_elementwise.py	AddDistributedOp.get_expand_impl.expand_impl1		2	0	0		100%
hyper_parallel / core / shard / ops / parallel_elementwise.py	AddDistributedOp.get_expand_impl.expand_impl2		2	0	0		100%
hyper_parallel / core / shard / ops / parallel_elementwise.py	(no function)		23	0	0		100%
hyper_parallel / core / shard / ops / parallel_embedding.py	EmbeddingDistributedOp.infer_layout		19	1	0		95%
hyper_parallel / core / shard / ops / parallel_embedding.py	EmbeddingDistributedOp.infer_layout.idx_to_alias		3	0	0		100%
hyper_parallel / core / shard / ops / parallel_embedding.py	(no function)		4	0	0		100%
hyper_parallel / core / shard / ops / parallel_expand.py	ExpandDistributedOp.infer_layout		38	5	1		87%
hyper_parallel / core / shard / ops / parallel_expand.py	ExpandDistributedOp.infer_layout.idx_to_alias		3	0	0		100%
hyper_parallel / core / shard / ops / parallel_expand.py	ExpandAsDistributedOp.infer_layout		38	7	0		82%
hyper_parallel / core / shard / ops / parallel_expand.py	ExpandAsDistributedOp.infer_layout.idx_to_alias		3	0	0		100%
hyper_parallel / core / shard / ops / parallel_expand.py	(no function)		6	0	0		100%
hyper_parallel / core / shard / ops / parallel_expand_dims.py	ExpandDimsDistributedOp.infer_layout		22	6	0		73%
hyper_parallel / core / shard / ops / parallel_expand_dims.py	(no function)		4	0	0		100%
hyper_parallel / core / shard / ops / parallel_flash_attention_score.py	ParallelFlashAttention.__init__		22	1	0		95%
hyper_parallel / core / shard / ops / parallel_flash_attention_score.py	ParallelFlashAttention.construct		9	1	0		89%
hyper_parallel / core / shard / ops / parallel_flash_attention_score.py	ParallelFlashAttention._setup_layout_tensor_maps		7	0	0		100%
hyper_parallel / core / shard / ops / parallel_flash_attention_score.py	ParallelFlashAttention._get_device_mesh_from_layouts		7	4	0		43%
hyper_parallel / core / shard / ops / parallel_flash_attention_score.py	ParallelFlashAttention._build_custom_shard_func		4	0	0		100%
hyper_parallel / core / shard / ops / parallel_flash_attention_score.py	ParallelFlashAttention.shard		9	9	0		0%
hyper_parallel / core / shard / ops / parallel_flash_attention_score.py	ParallelFlashAttention._insert_none_for_non_tensor_arg		9	2	0		78%
hyper_parallel / core / shard / ops / parallel_flash_attention_score.py	ParallelFlashAttention._infer_dim_by_layout		9	0	0		100%
hyper_parallel / core / shard / ops / parallel_flash_attention_score.py	ParallelFlashAttention._infer_split_dim_by_in_strategy		6	0	0		100%
hyper_parallel / core / shard / ops / parallel_flash_attention_score.py	ParallelFlashAttention._get_split_num		10	4	0		60%
hyper_parallel / core / shard / ops / parallel_flash_attention_score.py	(no function)		19	0	0		100%
hyper_parallel / core / shard / ops / parallel_gather.py	IndexSelectDistributedOp.infer_layout		21	21	0		0%
hyper_parallel / core / shard / ops / parallel_gather.py	GatherDistributedOp.infer_layout		21	21	0		0%
hyper_parallel / core / shard / ops / parallel_gather.py	GatherNdDistributedOp.infer_layout		12	1	0		92%
hyper_parallel / core / shard / ops / parallel_gather.py	GatherNdDistributedOp._parse_input_layouts		9	4	0		56%
hyper_parallel / core / shard / ops / parallel_gather.py	GatherNdDistributedOp._validate_tensor_maps		15	4	0		73%
hyper_parallel / core / shard / ops / parallel_gather.py	GatherNdDistributedOp._get_input_shapes		14	3	0		79%
hyper_parallel / core / shard / ops / parallel_gather.py	GatherNdDistributedOp._normalize_shape		9	4	0		56%
hyper_parallel / core / shard / ops / parallel_gather.py	GatherNdDistributedOp._get_k_and_trailing_rank		11	4	0		64%
hyper_parallel / core / shard / ops / parallel_gather.py	GatherNdDistributedOp._is_none_axis		5	3	0		40%
hyper_parallel / core / shard / ops / parallel_gather.py	(no function)		14	0	0		100%
hyper_parallel / core / shard / ops / parallel_isin.py	IsinDistributedOp.infer_layout		17	2	0		88%
hyper_parallel / core / shard / ops / parallel_isin.py	IsinDistributedOp.infer_layout.idx_to_alias		3	0	0		100%
hyper_parallel / core / shard / ops / parallel_isin.py	(no function)		4	0	0		100%
hyper_parallel / core / shard / ops / parallel_masked_scatter.py	MaskedScatterDistributedOp.infer_layout		9	1	0		89%
hyper_parallel / core / shard / ops / parallel_masked_scatter.py	(no function)		3	0	0		100%
hyper_parallel / core / shard / ops / parallel_matmul.py	MatMulExtDistributedOp.infer_layout		26	6	0		77%
hyper_parallel / core / shard / ops / parallel_matmul.py	MatMulDistributedOp.infer_layout		33	10	0		70%
hyper_parallel / core / shard / ops / parallel_matmul.py	BaseBatchMatMulDistributedOp._merge_batch_entry		9	4	0		56%
hyper_parallel / core / shard / ops / parallel_matmul.py	BaseBatchMatMulDistributedOp._is_none_entry		3	1	0		67%
hyper_parallel / core / shard / ops / parallel_matmul.py	BaseBatchMatMulDistributedOp._merge_batches		9	0	0		100%
hyper_parallel / core / shard / ops / parallel_matmul.py	BaseBatchMatMulDistributedOp._build_output_layout		9	2	0		78%
hyper_parallel / core / shard / ops / parallel_matmul.py	BatchMatMulExtDistributedOp.infer_layout		15	3	0		80%
hyper_parallel / core / shard / ops / parallel_matmul.py	BatchMatMulDistributedOp.infer_layout		24	8	0		67%
hyper_parallel / core / shard / ops / parallel_matmul.py	LinearDistributedOp.infer_layout		31	8	0		74%
hyper_parallel / core / shard / ops / parallel_matmul.py	LinearDistributedOp.get_expand_impl		14	2	0		86%
hyper_parallel / core / shard / ops / parallel_matmul.py	LinearDistributedOp.get_expand_impl.expand_impl		2	0	0		100%
hyper_parallel / core / shard / ops / parallel_matmul.py	(no function)		18	0	0		100%
hyper_parallel / core / shard / ops / parallel_multinomial.py	MultinomialDistributedOp.infer_layout		15	1	0		93%
hyper_parallel / core / shard / ops / parallel_multinomial.py	(no function)		4	0	0		100%
hyper_parallel / core / shard / ops / parallel_new_ones.py	NewOnesDistributedOp.infer_layout		12	2	0		83%
hyper_parallel / core / shard / ops / parallel_new_ones.py	(no function)		4	0	0		100%
hyper_parallel / core / shard / ops / parallel_norm.py	NormDistributedOp.infer_layout		33	33	0		0%
hyper_parallel / core / shard / ops / parallel_norm.py	LayerNormDistributedOp.infer_layout		28	5	0		82%
hyper_parallel / core / shard / ops / parallel_norm.py	LayerNormDistributedOp.infer_layout.idx_to_alias		3	0	0		100%
hyper_parallel / core / shard / ops / parallel_norm.py	(no function)		6	0	0		100%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp.__init__		3	0	0		100%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._tensor_map_to_placements		19	4	0		79%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._is_dynamic_shape		7	3	0		57%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._get_dynamic_shape_info		11	1	0		91%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._is_attn_mask_compressed		1	0	0		100%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._compute_sparse_params		23	2	0		91%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._compute_sparse_params_dynamic		27	27	0		0%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._adjust_actual_seq_len_for_tnd_cp		4	0	0		100%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._adjust_actual_seq_len		23	3	0		87%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._validate_atten_mask		14	3	0		79%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._validate_pse_configuration		7	5	0		29%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp.infer_layout		28	11	0		61%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._infer_softmax_layout_conservatively		11	11	0		0%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._infer_softmax_layout_by_input_layout		7	0	0		100%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._build_softmax_tensor_map		26	1	0		96%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._create_default_softmax_layout		3	3	0		0%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._validate_sharding_consistency		10	2	0		80%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._check_batch_consistency		9	1	0		89%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._check_hidden_consistency		9	1	0		89%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._check_dim_consistency		9	1	0		89%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._check_seq_sharding_compatibility		17	4	0		76%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._truncate_result		3	1	0		67%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._adjust_head_num		5	1	0		80%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._compute_adjusted_sparse_params		7	1	0		86%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._adjust_tnd_layout_params		15	3	0		80%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp.get_expand_impl		11	1	0		91%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp.get_expand_impl.expanded_impl		34	1	0		97%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._get_seq_dim_idx		5	1	0		80%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._normalize_dim_map		3	1	0		67%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._get_split_info		15	1	0		93%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._calculate_tnd_split_params		11	2	0		82%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._get_dim_split_num		17	10	0		41%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._get_split_id		27	16	0		41%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._validate_tnd_cp_requirements		12	2	0		83%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	FlashAttentionScoreDistributedOp._create_replicated_scalar_layout		6	0	0		100%
hyper_parallel / core / shard / ops / parallel_npu_flash_attention_score.py	(no function)		53	0	0		100%
hyper_parallel / core / shard / ops / parallel_one_hot_ext.py	OneHotExtDistributedOp.infer_layout		20	20	0		0%
hyper_parallel / core / shard / ops / parallel_one_hot_ext.py	OneHotExtDistributedOp.get_expand_impl		13	13	0		0%
hyper_parallel / core / shard / ops / parallel_one_hot_ext.py	OneHotExtDistributedOp.get_expand_impl.expanded_one_hot		22	22	0		0%
hyper_parallel / core / shard / ops / parallel_one_hot_ext.py	OneHotExtDistributedOp._get_num_classes		5	5	0		0%
hyper_parallel / core / shard / ops / parallel_one_hot_ext.py	OneHotExtDistributedOp._validate_num_classes		4	4	0		0%
hyper_parallel / core / shard / ops / parallel_one_hot_ext.py	OneHotExtDistributedOp._validate_indices_dtype		3	3	0		0%
hyper_parallel / core / shard / ops / parallel_one_hot_ext.py	OneHotExtDistributedOp._get_sharded_axes		12	12	0		0%
hyper_parallel / core / shard / ops / parallel_one_hot_ext.py	OneHotExtDistributedOp._get_axis		5	5	0		0%
hyper_parallel / core / shard / ops / parallel_one_hot_ext.py	OneHotExtDistributedOp._validate_axis		5	5	0		0%
hyper_parallel / core / shard / ops / parallel_one_hot_ext.py	OneHotExtDistributedOp._validate_multi_dim_restriction		9	9	0		0%
hyper_parallel / core / shard / ops / parallel_one_hot_ext.py	OneHotExtDistributedOp._validate_inputs_layouts		6	6	0		0%
hyper_parallel / core / shard / ops / parallel_one_hot_ext.py	OneHotExtDistributedOp._infer_output_tensor_map		9	9	0		0%
hyper_parallel / core / shard / ops / parallel_one_hot_ext.py	OneHotExtDistributedOp._create_layout_from_tensor_map		5	5	0		0%
hyper_parallel / core / shard / ops / parallel_one_hot_ext.py	OneHotExtDistributedOp._tensor_map_to_alias_tensor_map		12	12	0		0%
hyper_parallel / core / shard / ops / parallel_one_hot_ext.py	OneHotExtDistributedOp._tensor_map_to_placements		19	19	0		0%
hyper_parallel / core / shard / ops / parallel_one_hot_ext.py	(no function)		20	0	0		100%
hyper_parallel / core / shard / ops / parallel_ops.py	DistributedOp.__init__		3	0	0		100%
hyper_parallel / core / shard / ops / parallel_ops.py	DistributedOp._check_partial_inputs		3	1	0		67%
hyper_parallel / core / shard / ops / parallel_ops.py	DistributedOp.infer_layout		5	5	0		0%
hyper_parallel / core / shard / ops / parallel_ops.py	DistributedOp.get_expand_impl		1	0	0		100%
hyper_parallel / core / shard / ops / parallel_ops.py	(no function)		6	0	0		100%
hyper_parallel / core / shard / ops / parallel_ops_register.py	register_distributed_op		1	0	0		100%
hyper_parallel / core / shard / ops / parallel_ops_register.py	get_distributed_op		1	0	0		100%
hyper_parallel / core / shard / ops / parallel_ops_register.py	(no function)		3	0	0		100%
hyper_parallel / core / shard / ops / parallel_pad.py	PadDistributedOp.infer_layout		29	7	0		76%
hyper_parallel / core / shard / ops / parallel_pad.py	(no function)		3	0	0		100%
hyper_parallel / core / shard / ops / parallel_reduce.py	ReduceExtDistributedOpBase.__init__		4	1	0		75%
hyper_parallel / core / shard / ops / parallel_reduce.py	ReduceExtDistributedOpBase.infer_layout		16	3	0		81%
hyper_parallel / core / shard / ops / parallel_reduce.py	ReduceExtDistributedOpBase._infer_output_layout		8	0	0		100%
hyper_parallel / core / shard / ops / parallel_reduce.py	ReduceExtDistributedOpBase._handle_all_axis_reduce		7	2	0		71%
hyper_parallel / core / shard / ops / parallel_reduce.py	ReduceExtDistributedOpBase.replace_axis_with_none		15	2	0		87%
hyper_parallel / core / shard / ops / parallel_reduce.py	ReduceExtDistributedOpBase._flatten_aliases		6	1	0		83%
hyper_parallel / core / shard / ops / parallel_reduce.py	ReduceExtDistributedOpBase._replace_keepdim		10	2	0		80%
hyper_parallel / core / shard / ops / parallel_reduce.py	ReduceExtDistributedOpBase._replace_dropdim		13	4	0		69%
hyper_parallel / core / shard / ops / parallel_reduce.py	ReduceExtDistributedOpBase._compact_tensor_map		2	0	0		100%
hyper_parallel / core / shard / ops / parallel_reduce.py	ReduceExtDistributedOpBase._compact_tensor_map._compress		8	6	0		25%
hyper_parallel / core / shard / ops / parallel_reduce.py	ReduceExtDistributedOpBase._apply_partial		7	0	0		100%
hyper_parallel / core / shard / ops / parallel_reduce.py	SumExtDistributedOp.__init__		1	0	0		100%
hyper_parallel / core / shard / ops / parallel_reduce.py	MeanExtDistributedOp.__init__		1	0	0		100%
hyper_parallel / core / shard / ops / parallel_reduce.py	ReduceMaxDistributedOp.__init__		1	0	0		100%
hyper_parallel / core / shard / ops / parallel_reduce.py	ProdExtDistributedOp.__init__		1	0	0		100%
hyper_parallel / core / shard / ops / parallel_reduce.py	AllExtDistributedOp.__init__		1	0	0		100%
hyper_parallel / core / shard / ops / parallel_reduce.py	MaxDistributedOp.__init__		1	0	0		100%
hyper_parallel / core / shard / ops / parallel_reduce.py	MaxDistributedOp.infer_layout		21	3	0		86%
hyper_parallel / core / shard / ops / parallel_reduce.py	(no function)		32	0	0		100%
hyper_parallel / core / shard / ops / parallel_repeat_interleave.py	RepeatInterleaveDistributedOp.infer_layout		26	4	0		85%
hyper_parallel / core / shard / ops / parallel_repeat_interleave.py	RepeatInterleaveDistributedOp.infer_layout.idx_to_alias		3	1	0		67%
hyper_parallel / core / shard / ops / parallel_repeat_interleave.py	(no function)		4	0	0		100%
hyper_parallel / core / shard / ops / parallel_reshape.py	_filter_none_split_tensor_map		14	9	0		36%
hyper_parallel / core / shard / ops / parallel_reshape.py	ReshapeDistributedOp._get_dynamic_shape_info		7	0	0		100%
hyper_parallel / core / shard / ops / parallel_reshape.py	ReshapeDistributedOp._handle_dynamic_shape		22	9	0		59%
hyper_parallel / core / shard / ops / parallel_reshape.py	ReshapeDistributedOp._merge_unshared_axis		13	0	0		100%
hyper_parallel / core / shard / ops / parallel_reshape.py	ReshapeDistributedOp._cal_output_layout_and_dst_shape		19	8	0		58%
hyper_parallel / core / shard / ops / parallel_reshape.py	ReshapeDistributedOp.infer_layout		54	15	0		72%
hyper_parallel / core / shard / ops / parallel_reshape.py	(no function)		12	0	0		100%
hyper_parallel / core / shard / ops / parallel_scaled_dot_product_attention.py	ScaledDotProductAttentionDistributedOp.__init__		2	0	0		100%
hyper_parallel / core / shard / ops / parallel_scaled_dot_product_attention.py	ScaledDotProductAttentionDistributedOp._tensor_map_to_placements		19	19	0		0%
hyper_parallel / core / shard / ops / parallel_scaled_dot_product_attention.py	ScaledDotProductAttentionDistributedOp._normalize_dim_map		3	1	0		67%
hyper_parallel / core / shard / ops / parallel_scaled_dot_product_attention.py	ScaledDotProductAttentionDistributedOp._get_dims		4	1	0		75%
hyper_parallel / core / shard / ops / parallel_scaled_dot_product_attention.py	ScaledDotProductAttentionDistributedOp._get_dim_split_num		17	10	0		41%
hyper_parallel / core / shard / ops / parallel_scaled_dot_product_attention.py	ScaledDotProductAttentionDistributedOp._get_split_info		8	1	0		88%
hyper_parallel / core / shard / ops / parallel_scaled_dot_product_attention.py	ScaledDotProductAttentionDistributedOp._get_split_id		26	16	0		38%
hyper_parallel / core / shard / ops / parallel_scaled_dot_product_attention.py	ScaledDotProductAttentionDistributedOp._validate_sharding_consistency		16	5	0		69%
hyper_parallel / core / shard / ops / parallel_scaled_dot_product_attention.py	ScaledDotProductAttentionDistributedOp._build_causal_mask_for_chunk		5	0	0		100%
hyper_parallel / core / shard / ops / parallel_scaled_dot_product_attention.py	ScaledDotProductAttentionDistributedOp._adjust_attn_mask_for_sp		12	2	0		83%
hyper_parallel / core / shard / ops / parallel_scaled_dot_product_attention.py	ScaledDotProductAttentionDistributedOp.infer_layout		8	3	0		62%
hyper_parallel / core / shard / ops / parallel_scaled_dot_product_attention.py	ScaledDotProductAttentionDistributedOp.get_expand_impl		12	1	0		92%
hyper_parallel / core / shard / ops / parallel_scaled_dot_product_attention.py	ScaledDotProductAttentionDistributedOp.get_expand_impl.expanded_impl		18	0	0		100%
hyper_parallel / core / shard / ops / parallel_scaled_dot_product_attention.py	(no function)		22	0	0		100%
hyper_parallel / core / shard / ops / parallel_scatter_update.py	ScatterUpdateDistributedOp.infer_layout		13	4	0		69%
hyper_parallel / core / shard / ops / parallel_scatter_update.py	ScatterUpdateDistributedOp._validate_strategy		23	7	0		70%
hyper_parallel / core / shard / ops / parallel_scatter_update.py	(no function)		5	0	0		100%
hyper_parallel / core / shard / ops / parallel_slice.py	SliceDistributedOp._is_shard_dim		14	14	0		0%
hyper_parallel / core / shard / ops / parallel_slice.py	SliceDistributedOp._check_layout		8	8	0		0%
hyper_parallel / core / shard / ops / parallel_slice.py	SliceDistributedOp.infer_layout		7	7	0		0%
hyper_parallel / core / shard / ops / parallel_slice.py	(no function)		5	0	0		100%
hyper_parallel / core / shard / ops / parallel_slice_ext.py	SliceExtDistributedOp.infer_layout		6	6	0		0%
hyper_parallel / core / shard / ops / parallel_slice_ext.py	(no function)		3	0	0		100%
hyper_parallel / core / shard / ops / parallel_sort.py	SortDistributedOp.infer_layout		22	4	0		82%
hyper_parallel / core / shard / ops / parallel_sort.py	(no function)		3	0	0		100%
hyper_parallel / core / shard / ops / parallel_split.py	SplitWithSizeDistributedOp.infer_layout		9	9	0		0%
hyper_parallel / core / shard / ops / parallel_split.py	SplitWithSizeViewDistributedOp.infer_layout		9	9	0		0%
hyper_parallel / core / shard / ops / parallel_split.py	SplitDistributedOp.infer_layout		27	7	0		74%
hyper_parallel / core / shard / ops / parallel_split.py	SplitTensorDistributedOp.infer_layout		12	12	0		0%
hyper_parallel / core / shard / ops / parallel_split.py	SplitTensorViewDistributedOp.infer_layout		12	2	0		83%
hyper_parallel / core / shard / ops / parallel_split.py	(no function)		12	0	0		100%
hyper_parallel / core / shard / ops / parallel_squeeze.py	SqueezeDistributedOp.infer_layout		9	3	0		67%
hyper_parallel / core / shard / ops / parallel_squeeze.py	SqueezeDistributedOp._extract_args		13	5	0		62%
hyper_parallel / core / shard / ops / parallel_squeeze.py	SqueezeDistributedOp._compute_squeeze_layout		5	1	0		80%
hyper_parallel / core / shard / ops / parallel_squeeze.py	SqueezeDistributedOp._handle_scalar_case		5	5	0		0%
hyper_parallel / core / shard / ops / parallel_squeeze.py	SqueezeDistributedOp._validate_input_shape		4	1	0		75%
hyper_parallel / core / shard / ops / parallel_squeeze.py	SqueezeDistributedOp._get_dims_to_squeeze		5	0	0		100%
hyper_parallel / core / shard / ops / parallel_squeeze.py	SqueezeDistributedOp._get_all_squeezable_dims		5	0	0		100%
hyper_parallel / core / shard / ops / parallel_squeeze.py	SqueezeDistributedOp._get_specified_dims_to_squeeze		7	0	0		100%
hyper_parallel / core / shard / ops / parallel_squeeze.py	SqueezeDistributedOp._validate_axis_range		3	1	0		67%
hyper_parallel / core / shard / ops / parallel_squeeze.py	SqueezeDistributedOp._validate_axis_for_squeeze		4	1	0		75%
hyper_parallel / core / shard / ops / parallel_squeeze.py	SqueezeDistributedOp._create_output_layout		11	0	0		100%
hyper_parallel / core / shard / ops / parallel_squeeze.py	SqueezeDistributedOp._copy_partial_operations		5	3	0		40%
hyper_parallel / core / shard / ops / parallel_squeeze.py	(no function)		15	0	0		100%
hyper_parallel / core / shard / ops / parallel_topk.py	TopKDistributedOp.infer_layout		15	2	0		87%
hyper_parallel / core / shard / ops / parallel_topk.py	(no function)		3	0	0		100%
hyper_parallel / core / shard / ops / parallel_transpose.py	TransposeDistributedOp.infer_layout		34	8	0		76%
hyper_parallel / core / shard / ops / parallel_transpose.py	(no function)		4	0	0		100%
hyper_parallel / core / shard / ops / parallel_tuple_elementwise.py	TupleElementWiseDistributedOp.infer_layout		3	1	0		67%
hyper_parallel / core / shard / ops / parallel_tuple_elementwise.py	(no function)		3	0	0		100%
hyper_parallel / core / shard / ops / parallel_unbind.py	UnbindDistributedOp.infer_layout		19	1	0		95%
hyper_parallel / core / shard / ops / parallel_unbind.py	(no function)		4	0	0		100%
hyper_parallel / core / shard / sharding_plan.py	(no function)		8	0	0		100%
hyper_parallel / core / tensor_redistribution.py	_construct_layout_tuple_for_transform_operator_list		5	0	0		100%
hyper_parallel / core / tensor_redistribution.py	TensorRedistribution.__init__		5	0	0		100%
hyper_parallel / core / tensor_redistribution.py	TensorRedistribution._construct_reshape		1	1	0		0%
hyper_parallel / core / tensor_redistribution.py	TensorRedistribution._construct_all_concat		5	5	0		0%
hyper_parallel / core / tensor_redistribution.py	TensorRedistribution._construct_strided_slice		2	0	0		100%
hyper_parallel / core / tensor_redistribution.py	TensorRedistribution._construct_all_concat_new		5	0	0		100%
hyper_parallel / core / tensor_redistribution.py	TensorRedistribution._construct_all_split		5	0	0		100%
hyper_parallel / core / tensor_redistribution.py	TensorRedistribution._construct_all_to_all		47	2	0		96%
hyper_parallel / core / tensor_redistribution.py	TensorRedistribution._apply_eazy_redistribute		6	1	0		83%
hyper_parallel / core / tensor_redistribution.py	TensorRedistribution._redistribution_without_shape		6	0	0		100%
hyper_parallel / core / tensor_redistribution.py	TensorRedistribution.redistribution		36	6	0		83%
hyper_parallel / core / tensor_redistribution.py	TensorRedistribution._infer_transform_operator_list		3	0	0		100%
hyper_parallel / core / tensor_redistribution.py	TensorRedistribution._allreduce_along_dev_dim		16	0	0		100%
hyper_parallel / core / tensor_redistribution.py	TensorRedistribution._reduce_scatter_along_dev_dim_with_axis		4	4	0		0%
hyper_parallel / core / tensor_redistribution.py	TensorRedistribution.reduce_partial		42	13	0		69%
hyper_parallel / core / tensor_redistribution.py	(no function)		21	0	0		100%
hyper_parallel / core / utils.py	compute_local_shape_and_global_offset		12	0	0		100%
hyper_parallel / core / utils.py	(no function)		2	0	0		100%
hyper_parallel / platform / __init__.py	(no function)		1	0	0		100%
hyper_parallel / platform / mindspore / __init__.py	(no function)		0	0	0		100%
hyper_parallel / platform / mindspore / custom_pass / __init__.py	(no function)		7	0	0		100%
hyper_parallel / platform / mindspore / custom_pass / build_plugin.py	find_cmake		4	4	0		0%
hyper_parallel / platform / mindspore / custom_pass / build_plugin.py	build_plugin		38	38	0		0%
hyper_parallel / platform / mindspore / custom_pass / build_plugin.py	(no function)		14	14	0		0%
hyper_parallel / platform / mindspore / dtensor.py	DTensorBase.__new__		17	2	0		88%
hyper_parallel / platform / mindspore / dtensor.py	DTensorBase.asnumpy		1	0	0		100%
hyper_parallel / platform / mindspore / dtensor.py	DTensorBase.__str__		1	0	0		100%
hyper_parallel / platform / mindspore / dtensor.py	DTensorBase.__copy__		14	4	0		71%
hyper_parallel / platform / mindspore / dtensor.py	DTensorBase.__fallback__		6	0	0		100%
hyper_parallel / platform / mindspore / dtensor.py	DTensorBase._need_contiguous		1	1	0		0%
hyper_parallel / platform / mindspore / dtensor.py	DTensorBase.device		1	0	0		100%
hyper_parallel / platform / mindspore / dtensor.py	DTensorBase.set_data		14	7	0		50%
hyper_parallel / platform / mindspore / dtensor.py	DTensorBase.has_init		3	1	0		67%
hyper_parallel / platform / mindspore / dtensor.py	DTensorBase.init		3	1	0		67%
hyper_parallel / platform / mindspore / dtensor.py	DTensorBase.init		1	0	0		100%
hyper_parallel / platform / mindspore / dtensor.py	DTensorBase.local_param_info		3	3	0		0%
hyper_parallel / platform / mindspore / dtensor.py	DTensorBase.local_param_info		1	0	0		100%
hyper_parallel / platform / mindspore / dtensor.py	(no function)		23	0	0		100%
hyper_parallel / platform / mindspore / hsdp / __init__.py	(no function)		0	0	0		100%
hyper_parallel / platform / mindspore / hsdp / async_grad_hook.py	MindSporeHSDPAsyncGradHook._get_final_grad_hook		3	3	0		0%
hyper_parallel / platform / mindspore / hsdp / async_grad_hook.py	MindSporeHSDPAsyncGradHook._get_final_grad_hook.set_grad_hook		3	3	0		0%
hyper_parallel / platform / mindspore / hsdp / async_grad_hook.py	(no function)		3	0	0		100%
hyper_parallel / platform / mindspore / hsdp / grad_hook.py	MindSporeHSDPGradHook.__init__		3	1	0		67%
hyper_parallel / platform / mindspore / hsdp / grad_hook.py	MindSporeHSDPGradHook._cast_hook		7	5	0		29%
hyper_parallel / platform / mindspore / hsdp / grad_hook.py	MindSporeHSDPGradHook._get_final_grad_hook		5	1	0		80%
hyper_parallel / platform / mindspore / hsdp / grad_hook.py	MindSporeHSDPGradHook._get_final_grad_hook.set_grad_hook		3	0	0		100%
hyper_parallel / platform / mindspore / hsdp / grad_hook.py	MindSporeHSDPGradHook.set_requires_grad_sync		3	1	0		67%
hyper_parallel / platform / mindspore / hsdp / grad_hook.py	(no function)		10	0	0		100%
hyper_parallel / platform / mindspore / hsdp / param.py	MindSporeHSDPParam._init_sharded_param		19	0	0		100%
hyper_parallel / platform / mindspore / hsdp / param.py	MindSporeHSDPParam._init_unsharded_param		1	0	0		100%
hyper_parallel / platform / mindspore / hsdp / param.py	(no function)		9	0	0		100%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._init_platform		3	1	0		67%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._new_cell_state		1	0	0		100%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._new_grad_hook		3	0	0		100%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._register_forward_backward_hooks		8	0	0		100%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._register_hooks		3	1	0		67%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler.get_pass_library_pass		8	5	0		38%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._register_custom_passes		8	8	0		0%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._get_param_forward_hook		8	8	0		0%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._get_param_forward_hook.stateless_param_forward_hook		2	2	0		0%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._get_param_forward_hook.stateful_param_forward_hook		2	2	0		0%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._get_param_backward_hook		6	6	0		0%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._get_param_backward_hook.backward_hook		1	1	0		0%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._get_param_backward_hook.backward_acc_grad_hook		1	1	0		0%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._get_parameter_forward_hook		8	8	0		0%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._get_parameter_forward_hook.ForwardHookNet.__init__		2	2	0		0%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._get_parameter_forward_hook.ForwardHookNet.construct		1	1	0		0%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._get_parameter_forward_hook.ForwardHookNet.bprop		1	1	0		0%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._get_parameter_forward_hook.parameter_forward_hook		1	1	0		0%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._register_graph_hook		7	7	0		0%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._get_grad_buffer_hook		3	0	0		100%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	MindSporeHSDPScheduler._get_grad_buffer_hook.set_grad_hook		3	0	0		100%
hyper_parallel / platform / mindspore / hsdp / scheduler.py	(no function)		29	0	0		100%
hyper_parallel / platform / mindspore / hsdp / state.py	MindSporeHSDPState._init_hsdp_params		11	1	0		91%
hyper_parallel / platform / mindspore / hsdp / state.py	MindSporeHSDPState.shard		1	0	0		100%
hyper_parallel / platform / mindspore / hsdp / state.py	MindSporeHSDPState.unshard		1	0	0		100%
hyper_parallel / platform / mindspore / hsdp / state.py	MindSporeHSDPState.prefetch		1	0	0		100%
hyper_parallel / platform / mindspore / hsdp / state.py	MindSporeHSDPState.zero_grads		1	0	0		100%
hyper_parallel / platform / mindspore / hsdp / state.py	MindSporeHSDPState.set_grad_ready		1	0	0		100%
hyper_parallel / platform / mindspore / hsdp / state.py	MindSporeHSDPState.set_requires_grad_sync		1	0	0		100%
hyper_parallel / platform / mindspore / hsdp / state.py	(no function)		19	0	0		100%
hyper_parallel / platform / mindspore / parameter_init.py	init_parameters		31	3	0		90%
hyper_parallel / platform / mindspore / parameter_init.py	(no function)		1	0	0		100%
hyper_parallel / platform / mindspore / pipeline_parallel / __init__.py	(no function)		0	0	0		100%
hyper_parallel / platform / mindspore / pipeline_parallel / _utils.py	_MicroBatch.__init__		4	4	0		0%
hyper_parallel / platform / mindspore / pipeline_parallel / _utils.py	_MicroBatch.construct		20	20	0		0%
hyper_parallel / platform / mindspore / pipeline_parallel / _utils.py	_MicroBatch.split_inputs_with_custom_shard		5	5	0		0%
hyper_parallel / platform / mindspore / pipeline_parallel / _utils.py	_MicroBatch.split_inputs		12	12	0		0%
hyper_parallel / platform / mindspore / pipeline_parallel / _utils.py	send_object_list		10	10	0		0%
hyper_parallel / platform / mindspore / pipeline_parallel / _utils.py	recv_object_list		14	14	0		0%
hyper_parallel / platform / mindspore / pipeline_parallel / _utils.py	(no function)		15	15	0		0%
hyper_parallel / platform / mindspore / pipeline_parallel / stage.py	PipelineStageBase.__init__		12	12	0		0%
hyper_parallel / platform / mindspore / pipeline_parallel / stage.py	PipelineStageBase.clear_cache		3	3	0		0%
hyper_parallel / platform / mindspore / pipeline_parallel / stage.py	PipelineStageBase._check_pp_group		5	5	0		0%
hyper_parallel / platform / mindspore / pipeline_parallel / stage.py	PipelineStageBase._clear_recv_buffer		4	4	0		0%
hyper_parallel / platform / mindspore / pipeline_parallel / stage.py	PipelineStageBase.is_first_stage		1	1	0		0%
hyper_parallel / platform / mindspore / pipeline_parallel / stage.py	PipelineStageBase.is_last_stage		1	1	0		0%
hyper_parallel / platform / mindspore / pipeline_parallel / stage.py	PipelineStageBase.forward_one_chunk		13	13	0		0%
hyper_parallel / platform / mindspore / pipeline_parallel / stage.py	PipelineStageBase.backward_one_chunk		21	21	0		0%
hyper_parallel / platform / mindspore / pipeline_parallel / stage.py	PipelineStageBase._construct_backward_func		6	6	0		0%
hyper_parallel / platform / mindspore / pipeline_parallel / stage.py	(no function)		13	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.device_count		6	2	0		67%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.get_rng_state		2	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.set_rng_state		2	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.device_type		4	1	0		75%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.device		3	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.get_device_handle		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.manual_seed		1	1	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.ones		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.zeros		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.full		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.empty		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.get_rank		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.get_global_rank		1	1	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.get_world_size		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.get_op_name		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.differentiable_all_gather_concat		5	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.chunk		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.differentiable_all_to_all		2	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.tensor_type_cast		4	4	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.differentiable_all_reduce		2	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.differentiable_reduce_scatter		6	6	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.init_parameters		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.update_param_data		3	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.get_cell_construct		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.get_cells_and_names		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.search_parameter_by_name		17	14	0		18%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.update_parameter_by_name		6	1	0		83%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.set_layout_into_parameter		17	4	0		76%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.get_param_local_shape		3	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.get_param_local_data		3	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.get_param_type_size		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.new_zero_parameter		4	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.new_tensor		4	1	0		75%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.full_like		1	1	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.isend		1	1	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.irecv		1	1	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.send_object_list		2	2	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.recv_object_list		2	2	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.set_tensor_requires_grad		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform._create_group		5	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.all_gather_into_tensor		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.all_reduce		4	1	0		75%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.broadcast		4	1	0		75%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.reduce_scatter_tensor		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.parameters_dict		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.get_tensor_transform		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.construct_strided_slice		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.micro_batch		2	2	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.save_checkpoint		2	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.load_checkpoint		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.new_stream		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.get_stream_context		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.all_gather_object		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.init_process_group		3	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.destroy_process_group		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.get_process_group_ranks		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.get_backend		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.split_group		11	1	0		91%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.no_grad		1	1	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.empty_like		1	1	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.get_current_stream		1	1	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.new_event		1	1	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.tree_map		7	7	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.register_forward_pre_hook		1	1	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.register_full_backward_hook		1	1	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.register_full_backward_pre_hook		1	1	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.checkpoint		1	1	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.ckpt_wrapper		1	1	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.noop_context_fn		1	1	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.create_selective_checkpoint_contexts		1	1	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.async_save_on_cpu		1	1	0		0%
hyper_parallel / platform / mindspore / platform.py	MindSporePlatform.tensor_to_numpy		1	0	0		100%
hyper_parallel / platform / mindspore / platform.py	(no function)		168	0	0		100%
hyper_parallel / platform / mindspore / platform_graph.py	MindSporeGraphPlatform.all_gather_into_tensor		2	2	0		0%
hyper_parallel / platform / mindspore / platform_graph.py	MindSporeGraphPlatform.all_reduce		2	2	0		0%
hyper_parallel / platform / mindspore / platform_graph.py	MindSporeGraphPlatform.reduce_scatter_tensor		2	2	0		0%
hyper_parallel / platform / mindspore / platform_graph.py	MindSporeGraphPlatform.ckpt_wrapper		1	1	0		0%
hyper_parallel / platform / mindspore / platform_graph.py	MindSporeGraphPlatform.noop_context_fn		1	1	0		0%
hyper_parallel / platform / mindspore / platform_graph.py	MindSporeGraphPlatform.create_selective_checkpoint_contexts		1	1	0		0%
hyper_parallel / platform / mindspore / platform_graph.py	MindSporeGraphPlatform.async_save_on_cpu		1	1	0		0%
hyper_parallel / platform / mindspore / platform_graph.py	(no function)		17	0	0		100%
hyper_parallel / platform / platform.py	get_mindspore_platform		3	0	0		100%
hyper_parallel / platform / platform.py	get_torch_platform		3	0	0		100%
hyper_parallel / platform / platform.py	get_platform		13	4	0		69%
hyper_parallel / platform / platform.py	Platform.get_rank		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.get_global_rank		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.get_world_size		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.get_op_name		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.differentiable_all_gather_concat		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.chunk		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.differentiable_all_to_all		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.tensor_type_cast		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.differentiable_all_reduce		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.differentiable_reduce_scatter		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.init_parameters		4	4	0		0%
hyper_parallel / platform / platform.py	Platform.get_cell_construct		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.get_cells_and_names		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.search_parameter_by_name		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.update_parameter_by_name		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.set_layout_into_parameter		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.get_param_local_shape		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.get_param_local_data		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.update_param_data		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.get_param_type_size		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.new_zero_parameter		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.new_tensor		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.full_like		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.set_tensor_requires_grad		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.all_gather_into_tensor		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.all_reduce		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.broadcast		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.isend		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.irecv		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.send_object_list		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.recv_object_list		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.reduce_scatter_tensor		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.parameters_dict		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.save_checkpoint		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.load_checkpoint		1	1	0		0%
hyper_parallel / platform / platform.py	Platform._create_group		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.new_stream		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.get_stream_context		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.get_tensor_transform		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.construct_strided_slice		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.micro_batch		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.create_group		8	0	0		100%
hyper_parallel / platform / platform.py	Platform._process_current_handle		6	1	0		83%
hyper_parallel / platform / platform.py	Platform.set_grad_reduce_handle		7	0	0		100%
hyper_parallel / platform / platform.py	Platform.wait_grad_handle		11	1	0		91%
hyper_parallel / platform / platform.py	Platform.all_gather_object		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.init_process_group		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.destroy_process_group		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.get_process_group_ranks		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.get_backend		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.split_group		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.no_grad		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.empty_like		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.get_current_stream		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.new_event		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.tree_map		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.register_forward_pre_hook		1	0	0		100%
hyper_parallel / platform / platform.py	Platform.register_full_backward_hook		1	0	0		100%
hyper_parallel / platform / platform.py	Platform.register_full_backward_pre_hook		1	0	0		100%
hyper_parallel / platform / platform.py	Platform.checkpoint		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.ckpt_wrapper		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.noop_context_fn		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.create_selective_checkpoint_contexts		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.async_save_on_cpu		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.tensor_to_numpy		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.cast_fp_tensor		1	1	0		0%
hyper_parallel / platform / platform.py	Platform.apply_to_tensors		1	1	0		0%
hyper_parallel / platform / platform.py	(no function)		142	0	0		100%
hyper_parallel / platform / torch / __init__.py	(no function)		0	0	0		100%
hyper_parallel / platform / torch / activation_checkpoint / __init__.py	(no function)		1	0	0		100%
hyper_parallel / platform / torch / activation_checkpoint / activation_swap.py	base_check_fn		5	0	0		100%
hyper_parallel / platform / torch / activation_checkpoint / activation_swap.py	AsyncSaveOnCpu.__init__		9	0	0		100%
hyper_parallel / platform / torch / activation_checkpoint / activation_swap.py	AsyncSaveOnCpu.__init__.pack_to_cpu		13	0	0		100%
hyper_parallel / platform / torch / activation_checkpoint / activation_swap.py	AsyncSaveOnCpu.__init__.unpack_from_cpu		8	8	0		0%
hyper_parallel / platform / torch / activation_checkpoint / activation_swap.py	ActivationWrapper.__init__		4	0	0		100%
hyper_parallel / platform / torch / activation_checkpoint / activation_swap.py	ActivationWrapper.forward		1	1	0		0%
hyper_parallel / platform / torch / activation_checkpoint / activation_swap.py	ActivationWrapper.__getattr__		4	2	0		50%
hyper_parallel / platform / torch / activation_checkpoint / activation_swap.py	ActivationWrapper.__getitem__		1	1	0		0%
hyper_parallel / platform / torch / activation_checkpoint / activation_swap.py	ActivationWrapper.named_parameters		2	2	0		0%
hyper_parallel / platform / torch / activation_checkpoint / activation_swap.py	ActivationWrapper._post_state_dict_hook		2	2	0		0%
hyper_parallel / platform / torch / activation_checkpoint / activation_swap.py	ActivationWrapper._pre_load_state_dict_hook		1	1	0		0%
hyper_parallel / platform / torch / activation_checkpoint / activation_swap.py	SwapWrapper.__init__		2	0	0		100%
hyper_parallel / platform / torch / activation_checkpoint / activation_swap.py	SwapWrapper.forward		2	0	0		100%
hyper_parallel / platform / torch / activation_checkpoint / activation_swap.py	swap_wrapper		1	0	0		100%
hyper_parallel / platform / torch / activation_checkpoint / activation_swap.py	(no function)		31	0	0		100%
hyper_parallel / platform / torch / activation_checkpoint / sac.py	_is_compiling		4	1	0		75%
hyper_parallel / platform / torch / activation_checkpoint / sac.py	_VersionWrapper.__init__		2	0	0		100%
hyper_parallel / platform / torch / activation_checkpoint / sac.py	_VersionWrapper.get_val		4	4	0		0%
hyper_parallel / platform / torch / activation_checkpoint / sac.py	_maybe_detach		4	0	0		100%
hyper_parallel / platform / torch / activation_checkpoint / sac.py	SelectiveCheckpointContext.__init__		1	0	0		100%
hyper_parallel / platform / torch / activation_checkpoint / sac.py	_policy_from_bool		1	1	0		0%
hyper_parallel / platform / torch / activation_checkpoint / sac.py	_CachingTorchDispatchMode.__init__		3	0	0		100%
hyper_parallel / platform / torch / activation_checkpoint / sac.py	_CachingTorchDispatchMode.__torch_dispatch__		22	3	0		86%
hyper_parallel / platform / torch / activation_checkpoint / sac.py	_CachedTorchDispatchMode.__init__		3	0	0		100%
hyper_parallel / platform / torch / activation_checkpoint / sac.py	_CachedTorchDispatchMode.__torch_dispatch__		23	23	0		0%
hyper_parallel / platform / torch / activation_checkpoint / sac.py	create_selective_checkpoint_contexts		11	6	0		45%
hyper_parallel / platform / torch / activation_checkpoint / sac.py	create_selective_checkpoint_contexts.policy_fn		3	3	0		0%
hyper_parallel / platform / torch / activation_checkpoint / sac.py	(no function)		24	0	0		100%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.__new__		11	5	0		55%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.__torch_function__		4	0	0		100%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.to		6	6	0		0%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.grad		1	0	0		100%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.grad		1	0	0		100%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.requires_grad		1	0	0		100%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.requires_grad		2	0	0		100%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.requires_grad_		3	0	0		100%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.grad_fn		1	0	0		100%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.grad_zero_		3	3	0		0%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.detach		2	0	0		100%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.detach_		3	3	0		0%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.is_leaf		1	0	0		100%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.retains_grad		1	1	0		0%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.retains_grad		1	1	0		0%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.backward		1	0	0		100%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.device		1	0	0		100%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.dtype		1	0	0		100%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.shape		1	1	0		0%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.type		4	4	0		0%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.size		1	1	0		0%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.ndim		1	1	0		0%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.data_ptr		1	1	0		0%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.numel		1	1	0		0%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.zero_		7	7	0		0%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.copy_		8	8	0		0%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.fill_		7	7	0		0%
hyper_parallel / platform / torch / dtensor.py	DTensorBase.__repr__		1	1	0		0%
hyper_parallel / platform / torch / dtensor.py	(no function)		45	0	0		100%
hyper_parallel / platform / torch / fully_shard / __init__.py	(no function)		0	0	0		100%
hyper_parallel / platform / torch / fully_shard / async_grad_hook.py	TorchHSDPAsyncGradHook._get_final_async_grad_hook		3	3	0		0%
hyper_parallel / platform / torch / fully_shard / async_grad_hook.py	TorchHSDPAsyncGradHook._get_final_async_grad_hook.set_grad_hook		4	4	0		0%
hyper_parallel / platform / torch / fully_shard / async_grad_hook.py	(no function)		3	3	0		0%
hyper_parallel / platform / torch / fully_shard / grad_hook.py	TorchHSDPGradHook._get_final_grad_hook		3	3	0		0%
hyper_parallel / platform / torch / fully_shard / grad_hook.py	TorchHSDPGradHook._get_final_grad_hook.set_grad_hook		4	4	0		0%
hyper_parallel / platform / torch / fully_shard / grad_hook.py	(no function)		3	3	0		0%
hyper_parallel / platform / torch / fully_shard / hook_function.py	PostBackwardFunction.forward		2	0	0		100%
hyper_parallel / platform / torch / fully_shard / hook_function.py	PostBackwardFunction.backward		2	2	0		0%
hyper_parallel / platform / torch / fully_shard / hook_function.py	PostBackwardFunction.apply		26	9	0		65%
hyper_parallel / platform / torch / fully_shard / hook_function.py	(no function)		8	0	0		100%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.__init__		18	1	0		94%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2._init_sharded_param		65	23	0		65%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2._init_sharded_post_forward_param_metadata		8	8	0		0%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.init_dtype_attrs		8	0	0		100%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2._init_extensions		8	2	0		75%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.init_all_gather_outputs		3	0	0		100%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.init_unsharded_param		7	1	0		86%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.to_sharded		3	0	0		100%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.to_sharded_post_forward		14	14	0		0%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.to_unsharded		6	2	0		67%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2._setattr_on_modules		7	4	0		43%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.to_sharded_dtensor		1	1	0		0%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.to_sharded_post_forward_dtensor		4	4	0		0%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.to_accumulated_grad_if_needed		4	4	0		0%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.accumulate_unsharded_grad_if_needed		3	0	0		100%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.alloc_all_gather_outputs		5	0	0		100%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.free_unsharded_param		4	0	0		100%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.all_gather_inputs		13	5	0		62%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.unsharded_param		1	0	0		100%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.unsharded_grad_data		6	2	0		67%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.unsharded_accumulated_grad_data		2	0	0		100%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2._sharded_local_tensor		1	0	0		100%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.shard_world_size		3	1	0		67%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.replicate_world_size		3	1	0		67%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2._assert_in_states		2	1	0		50%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.reset_sharded_param		30	30	0		0%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2._get_unsharded_param_data		14	6	0		57%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.unshard		4	1	0		75%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.wait_for_unshard		6	0	0		100%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.shard		2	0	0		100%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.reduce_scatter_grad		16	2	0		88%
hyper_parallel / platform / torch / fully_shard / param.py	TorchHSDPParamV2.all_reduce_grad		11	5	0		55%
hyper_parallel / platform / torch / fully_shard / param.py	set_requires_grad_if_needed		2	1	0		50%
hyper_parallel / platform / torch / fully_shard / param.py	(no function)		56	0	0		100%
hyper_parallel / platform / torch / fully_shard / scheduler.py	TorchHSDPSchedulerV2._register_hooks		1	0	0		100%
hyper_parallel / platform / torch / fully_shard / scheduler.py	TorchHSDPSchedulerV2._init_platform		4	1	0		75%
hyper_parallel / platform / torch / fully_shard / scheduler.py	TorchHSDPSchedulerV2._new_cell_state		6	1	0		83%
hyper_parallel / platform / torch / fully_shard / scheduler.py	TorchHSDPSchedulerV2._new_grad_hook		1	0	0		100%
hyper_parallel / platform / torch / fully_shard / scheduler.py	TorchHSDPSchedulerV2._register_post_backward_hook		9	0	0		100%
hyper_parallel / platform / torch / fully_shard / scheduler.py	TorchHSDPSchedulerV2._forward_pre_hook		2	0	0		100%
hyper_parallel / platform / torch / fully_shard / scheduler.py	TorchHSDPSchedulerV2._register_backward_pre_hook		5	0	0		100%
hyper_parallel / platform / torch / fully_shard / scheduler.py	TorchHSDPSchedulerV2._forward_hook		5	1	0		80%
hyper_parallel / platform / torch / fully_shard / scheduler.py	TorchHSDPSchedulerV2._backward_pre_hook		5	5	0		0%
hyper_parallel / platform / torch / fully_shard / scheduler.py	TorchHSDPSchedulerV2._backward_hook		3	3	0		0%
hyper_parallel / platform / torch / fully_shard / scheduler.py	TorchHSDPSchedulerV2._register_forward_backward_hooks		2	0	0		100%
hyper_parallel / platform / torch / fully_shard / scheduler.py	(no function)		20	0	0		100%
hyper_parallel / platform / torch / fully_shard / state.py	_to_dtype_if_needed		3	0	0		100%
hyper_parallel / platform / torch / fully_shard / state.py	TorchHSDPStateV2.__init__		11	0	0		100%
hyper_parallel / platform / torch / fully_shard / state.py	TorchHSDPStateV2._move_states_to_device		10	1	0		90%
hyper_parallel / platform / torch / fully_shard / state.py	TorchHSDPStateV2._init_hsdp_params		11	0	0		100%
hyper_parallel / platform / torch / fully_shard / state.py	TorchHSDPStateV2._init_mp_dtypes		11	2	0		82%
hyper_parallel / platform / torch / fully_shard / state.py	TorchHSDPStateV2._validate_cpu_offload_params		5	1	0		80%
hyper_parallel / platform / torch / fully_shard / state.py	TorchHSDPStateV2.lazy_init		1	1	0		0%
hyper_parallel / platform / torch / fully_shard / state.py	TorchHSDPStateV2.reshard		1	1	0		0%
hyper_parallel / platform / torch / fully_shard / state.py	TorchHSDPStateV2._apply_reduced_grad		18	18	0		0%
hyper_parallel / platform / torch / fully_shard / state.py	TorchHSDPStateV2.post_backward		31	31	0		0%
hyper_parallel / platform / torch / fully_shard / state.py	TorchHSDPStateV2.set_requires_grad_sync		1	0	0		100%
hyper_parallel / platform / torch / fully_shard / state.py	TorchHSDPStateV2.set_reduce_op_type		5	1	0		80%
hyper_parallel / platform / torch / fully_shard / state.py	(no function)		20	0	0		100%
hyper_parallel / platform / torch / fully_shard / utils.py	DataParallelMeshInfo.__post_init__		2	1	0		50%
hyper_parallel / platform / torch / fully_shard / utils.py	FSDPMeshInfo.__post_init__		6	1	0		83%
hyper_parallel / platform / torch / fully_shard / utils.py	DDPMeshInfo.__post_init__		6	1	0		83%
hyper_parallel / platform / torch / fully_shard / utils.py	HSDPMeshInfo.__post_init__		1	0	0		100%
hyper_parallel / platform / torch / fully_shard / utils.py	(no function)		31	0	0		100%
hyper_parallel / platform / torch / function_override.py	DTensorBackwardHookFunction.apply		25	9	0		64%
hyper_parallel / platform / torch / function_override.py	ExtendBackwardHook.setup_output_hook		5	3	0		40%
hyper_parallel / platform / torch / function_override.py	override_functions		2	0	0		100%
hyper_parallel / platform / torch / function_override.py	(no function)		12	0	0		100%
hyper_parallel / platform / torch / group_utils.py	_validate_intra_step		7	2	0		71%
hyper_parallel / platform / torch / group_utils.py	_compute_group_starts		1	0	0		100%
hyper_parallel / platform / torch / group_utils.py	_build_groups_for_blocks		8	0	0		100%
hyper_parallel / platform / torch / group_utils.py	generate_groups_from_template		33	8	0		76%
hyper_parallel / platform / torch / group_utils.py	create_sub_groups		30	8	0		73%
hyper_parallel / platform / torch / group_utils.py	(no function)		7	0	0		100%
hyper_parallel / platform / torch / hsdp / __init__.py	(no function)		0	0	0		100%
hyper_parallel / platform / torch / hsdp / async_grad_hook.py	TorchHSDPAsyncGradHook._get_final_async_grad_hook		3	0	0		100%
hyper_parallel / platform / torch / hsdp / async_grad_hook.py	TorchHSDPAsyncGradHook._get_final_async_grad_hook.set_grad_hook		4	4	0		0%
hyper_parallel / platform / torch / hsdp / async_grad_hook.py	(no function)		3	0	0		100%
hyper_parallel / platform / torch / hsdp / grad_hook.py	TorchHSDPGradHook._get_final_grad_hook		3	0	0		100%
hyper_parallel / platform / torch / hsdp / grad_hook.py	TorchHSDPGradHook._get_final_grad_hook.set_grad_hook		4	4	0		0%
hyper_parallel / platform / torch / hsdp / grad_hook.py	(no function)		3	0	0		100%
hyper_parallel / platform / torch / hsdp / hook_function.py	PostBackwardFunction.forward		2	0	0		100%
hyper_parallel / platform / torch / hsdp / hook_function.py	PostBackwardFunction.backward		2	2	0		0%
hyper_parallel / platform / torch / hsdp / hook_function.py	PostBackwardFunction.apply		25	5	0		80%
hyper_parallel / platform / torch / hsdp / hook_function.py	(no function)		8	0	0		100%
hyper_parallel / platform / torch / hsdp / param.py	TorchHSDPParam._init_sharded_param		5	0	0		100%
hyper_parallel / platform / torch / hsdp / param.py	TorchHSDPParam._init_unsharded_param		3	0	0		100%
hyper_parallel / platform / torch / hsdp / param.py	TorchHSDPParam._get_unsharded_param_data		6	0	0		100%
hyper_parallel / platform / torch / hsdp / param.py	(no function)		8	0	0		100%
hyper_parallel / platform / torch / hsdp / scheduler.py	TorchHSDPScheduler._init_platform		1	0	0		100%
hyper_parallel / platform / torch / hsdp / scheduler.py	TorchHSDPScheduler._new_cell_state		1	0	0		100%
hyper_parallel / platform / torch / hsdp / scheduler.py	TorchHSDPScheduler._new_grad_hook		3	0	0		100%
hyper_parallel / platform / torch / hsdp / scheduler.py	TorchHSDPScheduler._register_backward_hook		9	0	0		100%
hyper_parallel / platform / torch / hsdp / scheduler.py	TorchHSDPScheduler._forward_pre_hook		2	0	0		100%
hyper_parallel / platform / torch / hsdp / scheduler.py	TorchHSDPScheduler._register_backward_pre_hook		5	0	0		100%
hyper_parallel / platform / torch / hsdp / scheduler.py	TorchHSDPScheduler._forward_hook		6	1	0		83%
hyper_parallel / platform / torch / hsdp / scheduler.py	TorchHSDPScheduler._backward_pre_hook		5	5	0		0%
hyper_parallel / platform / torch / hsdp / scheduler.py	TorchHSDPScheduler._backward_hook		5	5	0		0%
hyper_parallel / platform / torch / hsdp / scheduler.py	TorchHSDPScheduler._register_forward_backward_hooks		2	0	0		100%
hyper_parallel / platform / torch / hsdp / scheduler.py	(no function)		21	0	0		100%
hyper_parallel / platform / torch / hsdp / state.py	TorchHSDPState._init_hsdp_params		9	1	0		89%
hyper_parallel / platform / torch / hsdp / state.py	(no function)		5	0	0		100%
hyper_parallel / platform / torch / pipeline_parallel / __init__.py	(no function)		0	0	0		100%
hyper_parallel / platform / torch / pipeline_parallel / _utils.py	_MicroBatch.__init__		4	0	0		100%
hyper_parallel / platform / torch / pipeline_parallel / _utils.py	_MicroBatch.forward		24	9	0		62%
hyper_parallel / platform / torch / pipeline_parallel / _utils.py	_MicroBatch.split_inputs_with_custom_shard		3	3	0		0%
hyper_parallel / platform / torch / pipeline_parallel / _utils.py	_MicroBatch.split_inputs		11	2	0		82%
hyper_parallel / platform / torch / pipeline_parallel / _utils.py	(no function)		7	0	0		100%
hyper_parallel / platform / torch / pipeline_parallel / stage.py	PipelineStageBase.__init__		10	0	0		100%
hyper_parallel / platform / torch / pipeline_parallel / stage.py	PipelineStageBase.clear_cache		3	3	0		0%
hyper_parallel / platform / torch / pipeline_parallel / stage.py	PipelineStageBase._clear_recv_buffer		4	0	0		100%
hyper_parallel / platform / torch / pipeline_parallel / stage.py	PipelineStageBase._check_pp_group		5	3	0		40%
hyper_parallel / platform / torch / pipeline_parallel / stage.py	PipelineStageBase.is_first_stage		1	0	0		100%
hyper_parallel / platform / torch / pipeline_parallel / stage.py	PipelineStageBase.is_last_stage		1	0	0		100%
hyper_parallel / platform / torch / pipeline_parallel / stage.py	PipelineStageBase.forward_one_chunk		13	1	0		92%
hyper_parallel / platform / torch / pipeline_parallel / stage.py	PipelineStageBase.backward_one_chunk		24	3	0		88%
hyper_parallel / platform / torch / pipeline_parallel / stage.py	(no function)		14	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.device_count		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.device_type		4	1	0		75%
hyper_parallel / platform / torch / platform.py	TorchPlatform.device		4	1	0		75%
hyper_parallel / platform / torch / platform.py	TorchPlatform.get_rng_state		5	1	0		80%
hyper_parallel / platform / torch / platform.py	TorchPlatform.set_rng_state		5	1	0		80%
hyper_parallel / platform / torch / platform.py	TorchPlatform.manual_seed		1	1	0		0%
hyper_parallel / platform / torch / platform.py	TorchPlatform.ones		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.zeros		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.full		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.empty		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.get_rank		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.get_global_rank		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.get_world_size		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.get_param_local_shape		3	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.get_param_local_data		3	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.update_param_data		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.get_op_name		14	12	0		14%
hyper_parallel / platform / torch / platform.py	TorchPlatform.differentiable_all_gather_concat		2	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.chunk		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.differentiable_all_to_all		3	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.tensor_type_cast		4	1	0		75%
hyper_parallel / platform / torch / platform.py	TorchPlatform.differentiable_all_reduce		2	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.get_cell_construct		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.get_cells_and_names		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.search_parameter_by_name		17	14	0		18%
hyper_parallel / platform / torch / platform.py	TorchPlatform.update_parameter_by_name		5	1	0		80%
hyper_parallel / platform / torch / platform.py	TorchPlatform.set_layout_into_parameter		8	1	0		88%
hyper_parallel / platform / torch / platform.py	TorchPlatform.differentiable_reduce_scatter		7	7	0		0%
hyper_parallel / platform / torch / platform.py	TorchPlatform.get_device_handle		3	1	0		67%
hyper_parallel / platform / torch / platform.py	TorchPlatform.get_param_type_size		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.parameters_dict		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.save_checkpoint		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.load_checkpoint		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.new_zero_parameter		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.new_tensor		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.full_like		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.set_tensor_requires_grad		2	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform._create_group		2	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.all_gather_into_tensor		5	5	0		0%
hyper_parallel / platform / torch / platform.py	TorchPlatform.all_reduce		4	4	0		0%
hyper_parallel / platform / torch / platform.py	TorchPlatform.broadcast		3	1	0		67%
hyper_parallel / platform / torch / platform.py	TorchPlatform.isend		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.irecv		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.send_object_list		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.recv_object_list		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.reduce_scatter_tensor		5	5	0		0%
hyper_parallel / platform / torch / platform.py	TorchPlatform.get_tensor_transform		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.construct_strided_slice		1	1	0		0%
hyper_parallel / platform / torch / platform.py	TorchPlatform.micro_batch		2	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.new_stream		2	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.get_stream_context		2	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.all_gather_object		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.init_process_group		6	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.destroy_process_group		2	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.get_process_group_ranks		2	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.get_backend		2	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.split_group		8	1	0		88%
hyper_parallel / platform / torch / platform.py	TorchPlatform.no_grad		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.empty_like		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.get_current_stream		2	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.new_event		2	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.tree_map		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.checkpoint		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.ckpt_wrapper		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.noop_context_fn		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.create_selective_checkpoint_contexts		2	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.async_save_on_cpu		2	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.tensor_to_numpy		1	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.cast_fp_tensor		3	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.apply_to_tensors		2	0	0		100%
hyper_parallel / platform / torch / platform.py	TorchPlatform.apply_to_tensors.apply		22	12	0		45%
hyper_parallel / platform / torch / platform.py	(no function)		167	1	0		99%
Total			12129	3695	1		70%

No items found using the specified filter.