MCPcopy Create free account

hub / github.com/Xuekai-Zhu/FlowRL / functions

Functions4,141 in github.com/Xuekai-Zhu/FlowRL

⨍ Functions 4,141◇ Types & classes 610↳ Endpoints 120
↓ 2 callersMethod__exit__
(self, exc_type, exc_value, traceback)
verl_Test/verl/workers/sharding_manager/base.py:25
↓ 2 callersMethod__exit__
(self, exc_type, exc_value, traceback)
verl_FlowRL/verl/workers/sharding_manager/base.py:25
↓ 2 callersMethod__init__
(self)
verl_Test/verl/utils/activation_offload.py:92
↓ 2 callersMethod__init__
(self, config)
verl_Test/verl/workers/megatron_workers.py:541
↓ 2 callersMethod__init__
(self, config)
verl_Test/verl/workers/fsdp_workers.py:796
↓ 2 callersMethod__init__
( self, input_size, num_heads, num_key_value_heads, head_dim,
verl_Test/verl/models/llama/megatron/layers/parallel_linear.py:21
↓ 2 callersMethod__init__
( self, retrieval_method: str = "bm25", retrieval_topk: int = 10, index_path:
verl_Test/examples/sglang_multiturn/search_r1_like/local_dense_retriever/retrieval_server.py:270
↓ 2 callersMethod__init__
(self)
verl_FlowRL/verl/utils/activation_offload.py:92
↓ 2 callersMethod__init__
(self, config)
verl_FlowRL/verl/workers/megatron_workers.py:541
↓ 2 callersMethod__init__
( self, input_size, num_heads, num_key_value_heads, head_dim,
verl_FlowRL/verl/models/llama/megatron/layers/parallel_linear.py:21
↓ 2 callersMethod__init__
( self, retrieval_method: str = "bm25", retrieval_topk: int = 10, index_path:
verl_FlowRL/examples/sglang_multiturn/search_r1_like/local_dense_retriever/retrieval_server.py:270
↓ 2 callersFunction_broadcast_tp_shard_tensor_qkv
broadcast tensor in tp shards across mp_group
verl_Test/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader_depracated.py:265
↓ 2 callersFunction_broadcast_tp_shard_tensor_qkv
broadcast tensor in tp shards across mp_group
verl_Test/verl/models/qwen2/megatron/checkpoint_utils/qwen2_saver.py:247
↓ 2 callersFunction_broadcast_tp_shard_tensor_qkv
broadcast tensor in tp shards across mp_group
verl_Test/verl/models/mcore/saver.py:259
↓ 2 callersFunction_broadcast_tp_shard_tensor_qkv
broadcast tensor in tp shards across mp_group
verl_Test/verl/models/mcore/loader.py:270
↓ 2 callersFunction_broadcast_tp_shard_tensor_qkv
broadcast tensor in tp shards across mp_group
verl_FlowRL/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader_depracated.py:265
↓ 2 callersFunction_broadcast_tp_shard_tensor_qkv
broadcast tensor in tp shards across mp_group
verl_FlowRL/verl/models/qwen2/megatron/checkpoint_utils/qwen2_saver.py:247
↓ 2 callersFunction_broadcast_tp_shard_tensor_qkv
broadcast tensor in tp shards across mp_group
verl_FlowRL/verl/models/mcore/saver.py:259
↓ 2 callersFunction_broadcast_tp_shard_tensor_qkv
broadcast tensor in tp shards across mp_group
verl_FlowRL/verl/models/mcore/loader.py:270
↓ 2 callersMethod_build_model_optimizer
(self, model_path, optim_config, override_model_config, override_transformer_config)
verl_Test/verl/workers/megatron_workers.py:142
↓ 2 callersMethod_build_model_optimizer
( self, model_path, fsdp_config, optim_config, override_model_config,
verl_Test/verl/workers/fsdp_workers.py:171
↓ 2 callersMethod_build_model_optimizer
(self, model_path, optim_config, override_model_config, override_transformer_config)
verl_FlowRL/verl/workers/megatron_workers.py:142
↓ 2 callersMethod_build_model_optimizer
( self, model_path, fsdp_config, optim_config, override_model_config,
verl_FlowRL/verl/workers/fsdp_workers.py:191
↓ 2 callersFunction_call_if_main
(frame, f, args)
verl_Test/rllm/rewards/code_utils/pyext2.py:467
↓ 2 callersFunction_call_if_main
(frame, f, args)
verl_FlowRL/rllm/rewards/code_utils/pyext2.py:467
↓ 2 callersMethod_compute_loss_and_backward
Compute loss with optional sequence parallelism and remove padding features
verl_Test/verl/trainer/fsdp_sft_trainer.py:303
↓ 2 callersMethod_create_dataloader
Creates the train and validation dataloaders.
verl_Test/recipe/spin/spin_trainer.py:524
↓ 2 callersMethod_create_dataloader
Creates the train and validation dataloaders.
verl_FlowRL/recipe/spin/spin_trainer.py:524
↓ 2 callersMethod_download
(self, use_origin_parquet=False)
verl_Test/verl/utils/dataset/rl_dataset.py:121
↓ 2 callersMethod_download
(self, use_origin_parquet=False)
verl_FlowRL/verl/utils/dataset/rl_dataset.py:121
↓ 2 callersFunction_fetch_tp_shard_tensor_qkv
fetch tensor in tp shards across mp_group
verl_Test/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader.py:152
↓ 2 callersFunction_fetch_tp_shard_tensor_qkv
fetch tensor in tp shards across mp_group
verl_FlowRL/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader.py:152
↓ 2 callersMethod_forward_micro_batch
(self, micro_batch, prompt_length)
verl_Test/recipe/prime/prime_dp_rm.py:50
↓ 2 callersMethod_forward_micro_batch
(self, micro_batch)
verl_Test/verl/workers/critic/dp_critic.py:60
↓ 2 callersMethod_forward_micro_batch
Returns: entropy: # (bs, response_len) log_probs: # (bs, response_len)
verl_Test/verl/workers/actor/dp_actor.py:75
↓ 2 callersMethod_forward_micro_batch
(self, micro_batch, prompt_length)
verl_FlowRL/recipe/prime/prime_dp_rm.py:50
↓ 2 callersMethod_forward_micro_batch
(self, micro_batch)
verl_FlowRL/verl/workers/critic/dp_critic.py:60
↓ 2 callersMethod_forward_micro_batch
Returns: entropy: # (bs, response_len) log_probs: # (bs, response_len)
verl_FlowRL/verl/workers/actor/dp_actor.py:75
↓ 2 callersMethod_get_tp_pp_rank_from_sharded_dir
(self, sharded_dir: str)
verl_Test/scripts/model_merger.py:342
↓ 2 callersMethod_get_tp_pp_rank_from_sharded_dir
(self, sharded_dir: str)
verl_FlowRL/scripts/model_merger.py:342
↓ 2 callersFunction_is_frac
(expr: str)
verl_Test/rllm/rewards/math_utils/utils.py:218
↓ 2 callersFunction_is_frac
(expr: str)
verl_Test/recipe/entropy_math/__init__.py:743
↓ 2 callersFunction_is_frac
(expr: str)
verl_Test/verl/utils/reward_score/prime_math/__init__.py:86
↓ 2 callersFunction_is_frac
(expr: str)
verl_FlowRL/rllm/rewards/math_utils/utils.py:218
↓ 2 callersFunction_is_frac
(expr: str)
verl_FlowRL/verl/utils/reward_score/prime_math/__init__.py:86
↓ 2 callersFunction_load_hf_model
Helper function containing the loading hf model logic
verl_Test/verl/utils/model.py:277
↓ 2 callersFunction_load_hf_model
Helper function containing the loading hf model logic
verl_FlowRL/verl/utils/model.py:277
↓ 2 callersFunction_materialize_futures
(*args, **kwargs)
verl_Test/verl/single_controller/base/decorator.py:490
↓ 2 callersFunction_materialize_futures
(*args, **kwargs)
verl_FlowRL/verl/single_controller/base/decorator.py:490
↓ 2 callersFunction_normalize
Normalize answer expressions.
verl_Test/rllm/rewards/math_utils/utils.py:258
↓ 2 callersFunction_normalize
Normalize answer expressions.
verl_Test/verl/utils/reward_score/prime_math/__init__.py:126
↓ 2 callersFunction_normalize
Normalize answer expressions.
verl_FlowRL/rllm/rewards/math_utils/utils.py:258
↓ 2 callersFunction_normalize
Normalize answer expressions.
verl_FlowRL/verl/utils/reward_score/prime_math/__init__.py:126
↓ 2 callersMethod_offload_params_to_cpu
(self, pp_rank, to_empty=False)
verl_Test/verl/workers/sharding_manager/megatron_vllm.py:138
↓ 2 callersMethod_offload_params_to_cpu
(self, pp_rank, to_empty=False)
verl_FlowRL/verl/workers/sharding_manager/megatron_vllm.py:138
↓ 2 callersFunction_pad_tensor
(x: Tensor, dim: int, padding_size: int)
verl_Test/verl/utils/ulysses.py:104
↓ 2 callersFunction_pad_tensor
(x: Tensor, dim: int, padding_size: int)
verl_FlowRL/verl/utils/ulysses.py:104
↓ 2 callersMethod_pad_to_length
(self, input_ids, attention_mask)
verl_Test/verl/utils/dataset/rm_dataset.py:99
↓ 2 callersMethod_pad_to_length
(self, input_ids, attention_mask)
verl_FlowRL/verl/utils/dataset/rm_dataset.py:99
↓ 2 callersFunction_parse
(s)
verl_Test/recipe/entropy_math/grader.py:325
↓ 2 callersFunction_parse
(s)
verl_Test/recipe/entropy_math/__init__.py:554
↓ 2 callersFunction_parse
(s)
verl_Test/verl/utils/reward_score/prime_math/grader.py:283
↓ 2 callersFunction_parse
(s)
verl_FlowRL/verl/utils/reward_score/prime_math/grader.py:283
↓ 2 callersMethod_postprocess
(self, batch: DataProto, batch_conversations: List[List[List[Dict[str, str]]]], n: int)
verl_FlowRL/examples/ppo_trainer/naive_chat_scheduler.py:91
↓ 2 callersMethod_read_files_and_tokenize
(self)
verl_Test/verl/utils/dataset/rl_dataset.py:128
↓ 2 callersMethod_read_files_and_tokenize
(self)
verl_FlowRL/verl/utils/dataset/rl_dataset.py:128
↓ 2 callersFunction_record_directory_structure
(folder_path)
verl_Test/verl/utils/fs.py:160
↓ 2 callersFunction_record_directory_structure
(folder_path)
verl_FlowRL/verl/utils/fs.py:160
↓ 2 callersMethod_req_level_generate_sequences
(self, prompts: DataProto, **kwargs)
verl_Test/verl/workers/rollout/sglang_rollout/sglang_rollout.py:810
↓ 2 callersMethod_req_level_generate_sequences
(self, prompts: DataProto, **kwargs)
verl_FlowRL/verl/workers/rollout/sglang_rollout/sglang_rollout.py:810
↓ 2 callersMethod_save_checkpoint
(self)
verl_Test/recipe/prime/prime_ray_trainer.py:223
↓ 2 callersMethod_save_checkpoint
(self)
verl_FlowRL/recipe/prime/prime_ray_trainer.py:223
↓ 2 callersMethod_set_cos_sin_cache
(self, seq_len, device, dtype)
verl_Test/verl/models/qwen2/megatron/layers/parallel_attention.py:55
↓ 2 callersMethod_set_cos_sin_cache
(self, seq_len, device, dtype)
verl_FlowRL/verl/models/qwen2/megatron/layers/parallel_attention.py:55
↓ 2 callersFunction_strip_properly_formatted_commas
(expr: str)
verl_Test/rllm/rewards/math_utils/utils.py:247
↓ 2 callersFunction_strip_properly_formatted_commas
(expr: str)
verl_Test/recipe/entropy_math/__init__.py:772
↓ 2 callersFunction_strip_properly_formatted_commas
(expr: str)
verl_Test/verl/utils/reward_score/prime_math/__init__.py:115
↓ 2 callersFunction_strip_properly_formatted_commas
(expr: str)
verl_FlowRL/rllm/rewards/math_utils/utils.py:247
↓ 2 callersFunction_strip_properly_formatted_commas
(expr: str)
verl_FlowRL/verl/utils/reward_score/prime_math/__init__.py:115
↓ 2 callersFunction_unpad_tensor
(x: Tensor, dim: int, padding_size: int)
verl_Test/verl/utils/ulysses.py:111
↓ 2 callersFunction_unpad_tensor
(x: Tensor, dim: int, padding_size: int)
verl_FlowRL/verl/utils/ulysses.py:111
↓ 2 callersMethod_validate
(self)
verl_Test/verl/trainer/ppo/ray_trainer.py:634
↓ 2 callersMethod_validate
(self)
verl_FlowRL/verl/trainer/ppo/ray_trainer.py:634
↓ 2 callersMethod_validate_config
(self)
verl_Test/recipe/spin/spin_trainer.py:411
↓ 2 callersMethod_validate_config
(self)
verl_FlowRL/recipe/spin/spin_trainer.py:411
↓ 2 callersMethodadd
(self, x)
verl_FlowRL/tests/ray_cpu/test_fused_workers.py:28
↓ 2 callersMethodadd
(self, data: DataProto)
verl_FlowRL/tests/ray_gpu/test_colocated_workers_fused.py:34
↓ 2 callersMethodadd
(self, data: DataProto)
verl_FlowRL/tests/ray_gpu/test_colocated_workers.py:34
↓ 2 callersMethodadd
(self, a, b)
verl_FlowRL/tests/e2e/envs/digit_completion/task.py:76
↓ 2 callersFunctionall_to_all_tensor
( local_input: Tensor, scatter_dim: int, gather_dim: int, group: Optional[dist.ProcessGroup] =
verl_Test/verl/utils/ulysses.py:133
↓ 2 callersFunctionall_to_all_tensor
( local_input: Tensor, scatter_dim: int, gather_dim: int, group: Optional[dist.ProcessGroup] =
verl_FlowRL/verl/utils/ulysses.py:133
↓ 2 callersFunctionare_lists_similar
(a, b, threshold=10)
verl_FlowRL/tests/workers/rollout/utils_sglang.py:40
↓ 2 callersFunctionassign
Assign `value` to `varname` and return it. If `varname` is an attribute and the instance name it belongs to is not defined, a NameError is raised.
verl_Test/rllm/rewards/code_utils/pyext2.py:436
↓ 2 callersFunctionassign
Assign `value` to `varname` and return it. If `varname` is an attribute and the instance name it belongs to is not defined, a NameError is raised.
verl_FlowRL/rllm/rewards/code_utils/pyext2.py:436
↓ 2 callersMethodasync_forward
Asynchronous implementation of the tool functionality. Override this method for asynchronous tools. Returns:
verl_Test/rllm/tools/tool_base.py:105
↓ 2 callersMethodasync_forward
Asynchronous implementation of the tool functionality. Override this method for asynchronous tools. Returns:
verl_FlowRL/rllm/tools/tool_base.py:105
↓ 2 callersFunctionbootstrap_metric
Performs bootstrap resampling to estimate statistics of metrics. This function uses bootstrap resampling to estimate the mean and standard d
verl_Test/verl/trainer/ppo/metric_utils.py:246
↓ 2 callersFunctionbuild_memory_reference_from_module
(module: torch.nn.Module, memory_buffers: Dict[torch.dtype, MemoryBuffer], maintain_weight=True)
verl_Test/verl/utils/memory_buffer.py:99
↓ 2 callersFunctionbuild_memory_reference_from_module
(module: torch.nn.Module, memory_buffers: Dict[torch.dtype, MemoryBuffer], maintain_weight=True)
verl_FlowRL/verl/utils/memory_buffer.py:99
↓ 2 callersMethodbulk_offload_group
Bulk offload group.
verl_Test/verl/utils/activation_offload.py:294
← previousnext →601–700 of 4,141, ranked by callers