MCPcopy Create free account

hub / github.com/Jiayi-Pan/TinyZero / functions

Functions1,293 in github.com/Jiayi-Pan/TinyZero

⨍ Functions 1,293◇ Types & classes 173↳ Endpoints 30
↓ 1 callersMethod_build_rollout
(self)
verl/workers/fsdp_workers.py:250
↓ 1 callersFunction_check_and_sort_partitions
(partitions)
verl/utils/seqlen_balancing.py:170
↓ 1 callersMethod_check_beam_search_early_stopping
( self, early_stopping: Union[bool, str], sampling_params: SamplingParams, bes
verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:348
↓ 1 callersFunction_check_dispatch_mode
(dispatch_mode)
verl/single_controller/base/decorator.py:366
↓ 1 callersFunction_check_execute_mode
(execute_mode)
verl/single_controller/base/decorator.py:375
↓ 1 callersMethod_check_stop
Stop the finished sequences.
verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:681
↓ 1 callersFunction_compute_mlflow_params_from_objects
(params)
verl/utils/tracking.py:72
↓ 1 callersMethod_configure_before_init
(self, register_center_name: str, rank: int)
verl/single_controller/base/worker.py:102
↓ 1 callersMethod_configure_with_meta
This function should only be called inside by WorkerGroup
verl/single_controller/base/worker.py:147
↓ 1 callersFunction_copy
(from_path: str, to_path: str, timeout: int = None)
verl/utils/hdfs_io.py:113
↓ 1 callersMethod_create_dataloader
(self)
verl/trainer/ppo/ray_trainer.py:342
↓ 1 callersMethod_download
(self)
verl/utils/dataset/rm_dataset.py:70
↓ 1 callersMethod_download
(self)
verl/utils/dataset/sft_dataset.py:69
↓ 1 callersMethod_download
(self)
verl/utils/dataset/rl_dataset.py:91
↓ 1 callersFunction_exists
hdfs capable to check whether a file_path is exists
verl/utils/hdfs_io.py:43
↓ 1 callersFunction_expand_mask
Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.
verl/utils/torch_functional.py:469
↓ 1 callersFunction_expand_mask
Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.
verl/models/llama/megatron/modeling_llama_megatron.py:58
↓ 1 callersMethod_expand_to_token_level
(self, data: DataProto, scores: torch.Tensor)
verl/workers/fsdp_workers.py:911
↓ 1 callersFunction_flatten_dict
(raw: Dict[str, Any], *, sep: str)
verl/utils/tracking.py:99
↓ 1 callersMethod_forward_head
(self, hidden_states)
verl/models/llama/megatron/modeling_llama_megatron.py:301
↓ 1 callersMethod_forward_head
(self, hidden_states)
verl/models/llama/megatron/modeling_llama_megatron.py:554
↓ 1 callersMethod_forward_micro_batch
(self, micro_batch)
verl/workers/fsdp_workers.py:857
↓ 1 callersMethod_generate_minibatch
(self, prompts: DataProto)
verl/workers/rollout/hf_rollout.py:51
↓ 1 callersMethod_get_executor_cls
(cls, engine_config: EngineConfig)
verl/third_party/vllm/vllm_v_0_6_3/llm_engine_sp.py:355
↓ 1 callersMethod_get_executor_cls
(cls, engine_config: EngineConfig)
verl/third_party/vllm/vllm_v_0_5_4/llm_engine_sp.py:281
↓ 1 callersMethod_get_free_port
(self)
verl/single_controller/base/worker.py:58
↓ 1 callersFunction_get_model_architecture
(config: PretrainedConfig)
verl/third_party/vllm/vllm_v_0_3_1/model_loader.py:46
↓ 1 callersFunction_get_model_weight_loader
(arch: str)
verl/third_party/vllm/vllm_v_0_3_1/model_loader.py:123
↓ 1 callersFunction_get_model_weight_loader
(arch: str)
verl/third_party/vllm/vllm_v_0_6_3/dtensor_weight_loaders.py:371
↓ 1 callersFunction_get_model_weight_loader
(arch: str)
verl/third_party/vllm/vllm_v_0_6_3/megatron_weight_loaders.py:299
↓ 1 callersFunction_get_model_weight_loader
(arch: str)
verl/third_party/vllm/vllm_v_0_5_4/dtensor_weight_loaders.py:331
↓ 1 callersFunction_get_model_weight_loader
(arch: str)
verl/third_party/vllm/vllm_v_0_5_4/megatron_weight_loaders.py:298
↓ 1 callersFunction_get_model_weight_loader
(arch: str)
verl/third_party/vllm/vllm_v_0_4_2/dtensor_weight_loaders.py:260
↓ 1 callersFunction_get_model_weight_loader
(arch: str)
verl/third_party/vllm/vllm_v_0_4_2/megatron_weight_loaders.py:298
↓ 1 callersMethod_get_node_ip
(self)
verl/single_controller/base/worker.py:39
↓ 1 callersFunction_get_parallel_model_architecture_from_config
(config: PretrainedConfig, value=False)
verl/utils/model.py:243
↓ 1 callersMethod_get_weights_iterator
(self, actor_model: Union[PreTrainedModel, Dict])
verl/third_party/vllm/vllm_v_0_6_3/model_loader.py:202
↓ 1 callersMethod_get_weights_iterator
(self, actor_model: Union[PreTrainedModel, Dict])
verl/third_party/vllm/vllm_v_0_5_4/model_loader.py:181
↓ 1 callersMethod_get_weights_iterator
(self, actor_model: Union[PreTrainedModel, Dict])
verl/third_party/vllm/vllm_v_0_4_2/model_loader.py:170
↓ 1 callersMethod_init_cache_engine
(self)
verl/third_party/vllm/vllm_v_0_6_3/worker.py:235
↓ 1 callersMethod_init_cache_engine
(self)
verl/third_party/vllm/vllm_v_0_5_4/worker.py:229
↓ 1 callersMethod_init_cache_engine
(self)
verl/third_party/vllm/vllm_v_0_4_2/worker.py:199
↓ 1 callersMethod_init_cache_sp
Profiles the memory usage and initializes the KV cache.
verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:176
↓ 1 callersFunction_init_distributed_environment
Initialize the distributed environment.
verl/third_party/vllm/vllm_v_0_3_1/worker.py:270
↓ 1 callersMethod_init_executor
(self, model, distributed_init_method)
verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:74
↓ 1 callersMethod_init_executor
(self, model, distributed_init_method)
verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:66
↓ 1 callersMethod_init_executor
(self, model, distributed_init_method)
verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py:63
↓ 1 callersMethod_init_head
(self)
verl/models/llama/megatron/modeling_llama_megatron.py:289
↓ 1 callersMethod_init_head
(self)
verl/models/llama/megatron/modeling_llama_megatron.py:542
↓ 1 callersMethod_init_rope
(self)
verl/models/llama/megatron/layers/parallel_attention.py:204
↓ 1 callersMethod_init_tokenizer
(self, tokenizer, **tokenizer_init_kwargs)
verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:138
↓ 1 callersMethod_init_tokenizer
(self, tokenizer, **tokenizer_init_kwargs)
verl/third_party/vllm/vllm_v_0_6_3/llm_engine_sp.py:337
↓ 1 callersMethod_init_tokenizer
(self, tokenizer, **tokenizer_init_kwargs)
verl/third_party/vllm/vllm_v_0_5_4/llm_engine_sp.py:263
↓ 1 callersMethod_init_tokenizer
(self, tokenizer, **tokenizer_init_kwargs)
verl/third_party/vllm/vllm_v_0_4_2/llm_engine_sp.py:229
↓ 1 callersMethod_init_with_detached_workers
(self, worker_names)
verl/single_controller/ray/base.py:209
↓ 1 callersMethod_init_with_resource_pool
(self, resource_pool, ray_cls_with_init, bin_pack, detached)
verl/single_controller/ray/base.py:214
↓ 1 callersMethod_init_workers_sp
(self, model, distributed_init_method: str)
verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:149
↓ 1 callersMethod_init_workers_sp
(self, model, distributed_init_method: str)
verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:80
↓ 1 callersMethod_init_workers_sp
(self, model, distributed_init_method: str)
verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:72
↓ 1 callersMethod_init_workers_sp
(self, model, distributed_init_method: str)
verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py:69
↓ 1 callersMethod_is_worker_alive
(self, worker)
verl/single_controller/base/worker_group.py:110
↓ 1 callersMethod_load_params_to_cuda
(self, pp_rank, to_empty=False)
verl/workers/sharding_manager/megatron_vllm.py:92
↓ 1 callersFunction_make_causal_mask
Make causal mask used for bi-directional self-attention.
verl/utils/torch_functional.py:456
↓ 1 callersFunction_make_causal_mask
Make causal mask used for bi-directional self-attention.
verl/models/llama/megatron/modeling_llama_megatron.py:45
↓ 1 callersFunction_materialize_futures
(*args, **kwargs)
verl/single_controller/base/decorator.py:379
↓ 1 callersFunction_megatron_calc_layer_map
Calculate the mapping of global layer_idx to local layer_idx Returns: layer_map (Dict: int -> tuple(int, int, int)): mapping f
verl/models/llama/megatron/checkpoint_utils/llama_saver.py:45
↓ 1 callersFunction_megatron_calc_layer_map
Calculate the mapping of global layer_idx to local layer_idx Returns: layer_map (Dict: int -> tuple(int, int, int)): mapping f
verl/models/llama/megatron/checkpoint_utils/llama_loader.py:21
↓ 1 callersFunction_mkdir
hdfs mkdir
verl/utils/hdfs_io.py:75
↓ 1 callersMethod_normalize_config_bsz
(self)
verl/trainer/fsdp_sft_trainer.py:81
↓ 1 callersMethod_optimizer_step
(self)
verl/workers/critic/dp_critic.py:103
↓ 1 callersMethod_optimizer_step
(self)
verl/workers/actor/dp_actor.py:143
↓ 1 callersMethod_post_process_outputs
(self, outputs: List[RequestOutput])
verl/third_party/vllm/vllm_v_0_3_1/llm.py:250
↓ 1 callersMethod_post_process_outputs
(self, request_outputs: List[RequestOutput])
verl/third_party/vllm/vllm_v_0_6_3/llm.py:174
↓ 1 callersMethod_post_process_outputs
(self, request_outputs: List[RequestOutput])
verl/third_party/vllm/vllm_v_0_5_4/llm.py:214
↓ 1 callersMethod_post_process_outputs
(self, request_outputs: List[RequestOutput])
verl/third_party/vllm/vllm_v_0_4_2/llm.py:281
↓ 1 callersMethod_post_process_params
For each param, if it is a tp-splited param, we all-gather from micro_dp group.
verl/workers/sharding_manager/megatron_vllm.py:318
↓ 1 callersMethod_pre_process_inputs
(self, prompt_token_ids: torch.Tensor)
verl/third_party/vllm/vllm_v_0_3_1/llm.py:242
↓ 1 callersMethod_pre_process_inputs
(self, prompt_token_ids: torch.Tensor)
verl/third_party/vllm/vllm_v_0_4_2/llm.py:273
↓ 1 callersMethod_prepare_decoder_attention_mask
(self, attention_mask, input_shape, inputs_embeds)
verl/models/llama/megatron/modeling_llama_megatron.py:97
↓ 1 callersMethod_prepare_sample
( self, seq_group_metadata_list: List[SequenceGroupMetadata], prompt_lens: List[int],
verl/third_party/vllm/vllm_v_0_3_1/model_runner.py:109
↓ 1 callersMethod_process_model_outputs
(self, output: SamplerOutput, scheduler_outputs: SchedulerOutputs)
verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:545
↓ 1 callersFunction_process_parameter_names
(name)
verl/third_party/vllm/vllm_v_0_6_3/dtensor_weight_loaders.py:326
↓ 1 callersFunction_process_parameter_names
(name)
verl/third_party/vllm/vllm_v_0_5_4/dtensor_weight_loaders.py:287
↓ 1 callersFunction_process_parameter_names
(name)
verl/third_party/vllm/vllm_v_0_4_2/dtensor_weight_loaders.py:218
↓ 1 callersMethod_process_sequence_group_outputs
(self, seq_group: SequenceGroup, outputs: SequenceGroupOutput)
verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:385
↓ 1 callersMethod_read_files_and_tokenize
(self)
verl/utils/dataset/rm_dataset.py:85
↓ 1 callersMethod_read_files_and_tokenize
(self)
verl/utils/dataset/sft_dataset.py:73
↓ 1 callersMethod_read_files_and_tokenize
(self)
verl/utils/dataset/rl_dataset.py:96
↓ 1 callersMethod_run_engine
(self, use_tqdm: bool)
verl/third_party/vllm/vllm_v_0_3_1/llm.py:217
↓ 1 callersMethod_run_engine
(self, use_tqdm: bool)
verl/third_party/vllm/vllm_v_0_4_2/llm.py:248
↓ 1 callersMethod_save_checkpoint
(self)
verl/trainer/ppo/ray_trainer.py:516
↓ 1 callersFunction_select_rm_score_fn
(data_source)
verl/trainer/main_ppo.py:24
↓ 1 callersFunction_select_rm_score_fn
(data_source)
examples/split_placement/main_ppo_split.py:24
↓ 1 callersFunction_set_default_torch_dtype
Sets the default torch dtype to the given dtype.
verl/third_party/vllm/vllm_v_0_3_1/model_loader.py:38
↓ 1 callersMethod_switch_chat_template
(self, data: DataProto)
verl/workers/fsdp_workers.py:926
↓ 1 callersFunction_transform_params_to_json_serializable
(x, convert_list_to_dict: bool)
verl/utils/tracking.py:79
↓ 1 callersMethod_verify_args
(self)
verl/third_party/vllm/vllm_v_0_3_1/config.py:271
↓ 1 callersMethod_verify_args
(self)
verl/third_party/vllm/vllm_v_0_3_1/config.py:348
↓ 1 callersMethod_verify_args
(self)
verl/third_party/vllm/vllm_v_0_3_1/config.py:401
↓ 1 callersMethod_verify_args
(self)
verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:172
← previousnext →301–400 of 1,293, ranked by callers