MCPcopy Create free account

hub / github.com/BeastyZ/ConvSearch-R1 / functions

Functions1,207 in github.com/BeastyZ/ConvSearch-R1

⨍ Functions 1,207◇ Types & classes 166↳ Endpoints 40
↓ 1 callersMethod__init__
(self)
verl/tests/ray/test_colocated_workers.py:27
↓ 1 callersMethod__init__
(self, numel: int, numel_padded: int, dtype: torch.dtype, source: Optional[torch.Tensor] = None)
verl/verl/utils/memory_buffer.py:30
↓ 1 callersMethod__init__
(self, resource_pool: RayResourcePool, ray_cls_with_init: RayClassWithInitAr
verl/verl/single_controller/ray/megatron.py:44
↓ 1 callersMethod__init__
(self, config: Qwen2Config, megatron_config: ModelParallelConfig)
verl/verl/models/qwen2/megatron/layers/parallel_decoder.py:37
↓ 1 callersMethod__init__
(self, input_size, num_heads, num_key_value_heads,
verl/verl/models/qwen2/megatron/layers/parallel_linear.py:23
↓ 1 callersMethod__init__
(self, config: LlamaConfig, megatron_config: ModelParallelConfig)
verl/verl/models/llama/megatron/layers/parallel_decoder.py:37
↓ 1 callersMethod__init__
(self, input_size, num_heads, num_key_value_heads,
verl/verl/models/llama/megatron/layers/parallel_linear.py:23
↓ 1 callersMethod_batch_search
(self, query_list: List[str], query_ids: List[str], num: int, return_score: bool)
src/retrieval/server.py:162
↓ 1 callersMethod_bind_worker_method
Bind the worker method to the WorkerGroup
verl/verl/single_controller/base/worker_group.py:138
↓ 1 callersFunction_bind_workers_method_to_parent
Binds the methods of each worker to the WorkerDict. Note that we only bind public methods that are decorated by register
verl/verl/single_controller/ray/base.py:400
↓ 1 callersMethod_block_until_all_workers_alive
(self)
verl/verl/single_controller/base/worker_group.py:115
↓ 1 callersFunction_broadcast_tp_shard_tensor_gate_up
broadcast tensor in tp shards across mp_group
verl/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader.py:227
↓ 1 callersFunction_broadcast_tp_shard_tensor_gate_up
broadcast tensor in tp shards across mp_group
verl/verl/models/qwen2/megatron/checkpoint_utils/qwen2_saver.py:206
↓ 1 callersFunction_broadcast_tp_shard_tensor_gate_up
broadcast tensor in tp shards across mp_group
verl/verl/models/llama/megatron/checkpoint_utils/llama_saver.py:209
↓ 1 callersFunction_broadcast_tp_shard_tensor_gate_up
broadcast tensor in tp shards across mp_group
verl/verl/models/llama/megatron/checkpoint_utils/llama_loader.py:231
↓ 1 callersFunction_broadcast_tp_shard_tensor_qkv
broadcast tensor in tp shards across mp_group
verl/verl/models/llama/megatron/checkpoint_utils/llama_saver.py:262
↓ 1 callersFunction_broadcast_tp_shard_tensor_qkv
broadcast tensor in tp shards across mp_group
verl/verl/models/llama/megatron/checkpoint_utils/llama_loader.py:285
↓ 1 callersFunction_broadcast_tp_shard_tensor_vocab
broadcast tensor in tp shards across mp_group
verl/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader.py:134
↓ 1 callersFunction_broadcast_tp_shard_tensor_vocab
broadcast tensor in tp shards across mp_group
verl/verl/models/llama/megatron/checkpoint_utils/llama_loader.py:138
↓ 1 callersMethod_build_critic_model_optimizer
(self, model_path, megatron_config
verl/verl/workers/megatron_workers.py:526
↓ 1 callersMethod_build_critic_model_optimizer
(self, config)
verl/verl/workers/fsdp_workers.py:670
↓ 1 callersMethod_build_dataloader
(self)
verl/verl/trainer/fsdp_sft_trainer.py:121
↓ 1 callersMethod_build_model
(self, config)
verl/verl/workers/fsdp_workers.py:945
↓ 1 callersMethod_build_model_optimizer
(self)
verl/verl/trainer/fsdp_sft_trainer.py:181
↓ 1 callersMethod_build_param_buffer
Build the parameter buffer in each pp rank
verl/verl/workers/sharding_manager/megatron_vllm.py:84
↓ 1 callersMethod_build_reward_ref_model_optimizer
(self, config)
verl/recipe/prime/prime_fsdp_workers.py:84
↓ 1 callersMethod_build_rm_model
(self, model_path, megatron_config: ModelParallelConfig, override_model_config)
verl/verl/workers/megatron_workers.py:703
↓ 1 callersMethod_build_rollout
(self)
verl/verl/workers/megatron_workers.py:238
↓ 1 callersMethod_build_rollout
(self)
verl/verl/workers/fsdp_workers.py:308
↓ 1 callersFunction_check_and_sort_partitions
(partitions)
verl/verl/utils/seqlen_balancing.py:170
↓ 1 callersFunction_check_dispatch_mode
(dispatch_mode)
verl/verl/single_controller/base/decorator.py:366
↓ 1 callersFunction_check_execute_mode
(execute_mode)
verl/verl/single_controller/base/decorator.py:375
↓ 1 callersMethod_check_resource_available
Check if the resource pool can be satisfied in this ray cluster.
verl/verl/trainer/ppo/ray_trainer.py:104
↓ 1 callersFunction_compute_mlflow_params_from_objects
(params)
verl/verl/utils/tracking.py:136
↓ 1 callersMethod_configure_before_init
(self, register_center_name: str, rank: int)
verl/verl/single_controller/base/worker.py:101
↓ 1 callersMethod_configure_with_meta
This function should only be called inside by WorkerGroup
verl/verl/single_controller/base/worker.py:178
↓ 1 callersFunction_copy
(from_path: str, to_path: str, timeout: int = None)
verl/verl/utils/hdfs_io.py:113
↓ 1 callersMethod_create_dataloader
(self)
verl/verl/trainer/ppo/ray_trainer.py:404
↓ 1 callersMethod_download
(self)
verl/verl/utils/dataset/rm_dataset.py:70
↓ 1 callersMethod_download
(self)
verl/verl/utils/dataset/sft_dataset.py:69
↓ 1 callersFunction_exists
hdfs capable to check whether a file_path is exists
verl/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/verl/utils/torch_functional.py:502
↓ 1 callersFunction_expand_mask
Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.
verl/verl/models/qwen2/megatron/modeling_qwen2_megatron.py:59
↓ 1 callersFunction_expand_mask
Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.
verl/verl/models/llama/megatron/modeling_llama_megatron.py:60
↓ 1 callersMethod_expand_to_token_level
(self, data: DataProto, scores: torch.Tensor)
verl/verl/workers/fsdp_workers.py:1067
↓ 1 callersFunction_fix_a_slash_b
(string)
verl/verl/utils/reward_score/prime_math/math_normalize.py:89
↓ 1 callersFunction_fix_fracs
(string)
verl/verl/utils/reward_score/prime_math/math_normalize.py:57
↓ 1 callersFunction_fix_sqrt
(string)
verl/verl/utils/reward_score/prime_math/math_normalize.py:114
↓ 1 callersFunction_flatten_dict
(raw: Dict[str, Any], *, sep: str)
verl/verl/utils/tracking.py:163
↓ 1 callersMethod_forward_head
(self, hidden_states)
verl/verl/models/qwen2/megatron/modeling_qwen2_megatron.py:305
↓ 1 callersMethod_forward_head
(self, hidden_states)
verl/verl/models/qwen2/megatron/modeling_qwen2_megatron.py:611
↓ 1 callersMethod_forward_head
(self, hidden_states)
verl/verl/models/llama/megatron/modeling_llama_megatron.py:306
↓ 1 callersMethod_forward_head
(self, hidden_states)
verl/verl/models/llama/megatron/modeling_llama_megatron.py:561
↓ 1 callersMethod_forward_micro_batch
(self, micro_batch)
verl/verl/workers/fsdp_workers.py:1013
↓ 1 callersMethod_generate_minibatch
(self, prompts: DataProto)
verl/verl/workers/rollout/hf_rollout.py:51
↓ 1 callersMethod_get_free_port
(self)
verl/verl/single_controller/base/worker.py:56
↓ 1 callersMethod_get_gold_rank
(self, candidate_ids: List[List[str]], query_ids_batch: List[str])
src/retrieval/server.py:175
↓ 1 callersMethod_get_gold_rank
(self, candidate_ids: List[List[str]], query_ids_batch: List[str])
src/retrieval/server.py:246
↓ 1 callersMethod_get_node_ip
(self)
verl/verl/single_controller/base/worker.py:39
↓ 1 callersFunction_get_parallel_model_architecture_from_config
(config: PretrainedConfig, value=False)
verl/verl/utils/model.py:269
↓ 1 callersMethod_init_head
(self, config: Qwen2Config)
verl/verl/models/qwen2/megatron/modeling_qwen2_megatron.py:293
↓ 1 callersMethod_init_head
(self, config)
verl/verl/models/qwen2/megatron/modeling_qwen2_megatron.py:550
↓ 1 callersMethod_init_head
(self, config)
verl/verl/models/llama/megatron/modeling_llama_megatron.py:294
↓ 1 callersMethod_init_head
(self, config)
verl/verl/models/llama/megatron/modeling_llama_megatron.py:549
↓ 1 callersMethod_init_rope
(self)
verl/verl/models/qwen2/megatron/layers/parallel_attention.py:208
↓ 1 callersMethod_init_rope
(self)
verl/verl/models/llama/megatron/layers/parallel_attention.py:204
↓ 1 callersMethod_init_with_detached_workers
(self, worker_names)
verl/verl/single_controller/ray/base.py:229
↓ 1 callersMethod_init_with_resource_pool
(self, resource_pool, ray_cls_with_init, bin_pack, detached)
verl/verl/single_controller/ray/base.py:234
↓ 1 callersFunction_inject_implicit_mixed_number
Automatically make a mixed number evalable e.g. 7 3/4 => 7+3/4
verl/verl/utils/reward_score/prime_math/__init__.py:126
↓ 1 callersFunction_inner_call_method
(_method)
verl/verl/utils/reward_score/prime_code/testing_util.py:633
↓ 1 callersFunction_is_float
(num: str)
verl/verl/utils/reward_score/prime_math/__init__.py:92
↓ 1 callersFunction_is_int
(x: float)
verl/verl/utils/reward_score/prime_math/__init__.py:100
↓ 1 callersMethod_is_worker_alive
(self, worker)
verl/verl/single_controller/base/worker_group.py:112
↓ 1 callersFunction_last_boxed_only_string
(string)
verl/verl/utils/reward_score/prime_math/__init__.py:333
↓ 1 callersMethod_load_checkpoint
(self)
verl/recipe/prime/prime_ray_trainer.py:270
↓ 1 callersMethod_load_params_to_cuda
(self, pp_rank, to_empty=False)
verl/verl/workers/sharding_manager/megatron_vllm.py:107
↓ 1 callersFunction_make_causal_mask
Make causal mask used for bi-directional self-attention.
verl/verl/utils/torch_functional.py:489
↓ 1 callersFunction_make_causal_mask
Make causal mask used for bi-directional self-attention.
verl/verl/models/qwen2/megatron/modeling_qwen2_megatron.py:46
↓ 1 callersFunction_make_causal_mask
Make causal mask used for bi-directional self-attention.
verl/verl/models/llama/megatron/modeling_llama_megatron.py:47
↓ 1 callersFunction_map_each_response
(l)
verl/verl/workers/rollout/sglang_rollout/sglang_rollout.py:60
↓ 1 callersFunction_materialize_futures
(*args, **kwargs)
verl/verl/single_controller/base/decorator.py:379
↓ 1 callersMethod_maybe_log_val_generations
Log a table of validation samples to the configured logger (wandb or swanlab)
verl/verl/trainer/ppo/ray_trainer.py:478
↓ 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/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader.py:21
↓ 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/verl/models/qwen2/megatron/checkpoint_utils/qwen2_saver.py:39
↓ 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/verl/models/llama/megatron/checkpoint_utils/llama_saver.py:42
↓ 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/verl/models/llama/megatron/checkpoint_utils/llama_loader.py:23
↓ 1 callersFunction_mkdir
hdfs mkdir
verl/verl/utils/hdfs_io.py:75
↓ 1 callersMethod_normalize_config_bsz
(self)
verl/verl/trainer/fsdp_sft_trainer.py:110
↓ 1 callersMethod_optimizer_step
(self)
verl/recipe/prime/prime_dp_rm.py:183
↓ 1 callersMethod_optimizer_step
(self)
verl/verl/workers/critic/dp_critic.py:115
↓ 1 callersMethod_optimizer_step
(self)
verl/verl/workers/actor/dp_actor.py:161
↓ 1 callersFunction_parse_latex
Attempts to parse latex to an expression sympy can read.
verl/verl/utils/reward_score/prime_math/__init__.py:74
↓ 1 callersFunction_post_process_outputs
(tokenizer, output)
verl/verl/workers/rollout/sglang_rollout/sglang_rollout.py:58
↓ 1 callersMethod_post_process_params
For each param, if it is a tp-splited param, we all-gather from micro_dp group.
verl/verl/workers/sharding_manager/megatron_vllm.py:334
↓ 1 callersFunction_pre_process_inputs
(pad_token_id, prompt_token_ids: torch.Tensor)
verl/tests/rollout/test_sglang_spmd.py:205
↓ 1 callersFunction_pre_process_inputs
(pad_token_id, prompt_token_ids: torch.Tensor)
verl/verl/workers/rollout/sglang_rollout/sglang_rollout.py:49
↓ 1 callersFunction_pre_process_inputs
(pad_token_id, prompt_token_ids: torch.Tensor)
verl/verl/workers/rollout/vllm_rollout/fire_vllm_rollout.py:50
↓ 1 callersFunction_pre_process_inputs
(pad_token_id, prompt_token_ids: torch.Tensor)
verl/verl/workers/rollout/vllm_rollout/vllm_rollout_spmd.py:50
↓ 1 callersMethod_prepare_decoder_attention_mask
(self, attention_mask, input_shape, inputs_embeds)
verl/verl/models/qwen2/megatron/modeling_qwen2_megatron.py:99
↓ 1 callersMethod_prepare_decoder_attention_mask
(self, attention_mask, input_shape, inputs_embeds)
verl/verl/models/llama/megatron/modeling_llama_megatron.py:100
← previousnext →301–400 of 1,207, ranked by callers