MCPcopy Create free account

hub / github.com/InternLM/InternBootcamp / functions

Functions18,522 in github.com/InternLM/InternBootcamp

⨍ Functions 18,522◇ Types & classes 3,617↳ Endpoints 206
↓ 4,958 callersMethodappend
(self, value: Union[Numeric, "Metric"])
verl/verl/utils/metric/utils.py:103
↓ 2,883 callersMethodget
(x)
internbootcamp/bootcamps/bootcamps_v1/algorithm/cserejaandsubsequences/Cserejaandsubsequences_tools.py:116
↓ 1,400 callersMethodverify_score
Verifies model output for currents, potentials, and equations, calculating a comprehensive score. 新的分数计算逻辑： 0.5 * (正确的KCL方程数/
internbootcamp/bootcamps/bootcamps_v1/natural_science/circuit/circuit_tools.py:327
↓ 807 callersMethodgetenv
(self, key)
verl/tests/single_controller/test_ray_local_envs_on_cpu.py:31
↓ 634 callersMethodsplit
(self, stone, k)
internbootcamp/bootcamps/bootcamps_v1/algorithm/einterestinggame/Einterestinggame_tools.py:106
↓ 622 callersMethodget
获取环境实例
internbootcamp/bootcamps/mole_bootcamp/mole_server.py:236
↓ 606 callersMethodget
Return a tensor with the input `shape` as a view into the 1-D data starting at `start_index`.
verl/verl/utils/memory_buffer.py:45
↓ 532 callersMethodpop
Pop a subset of the DataProto via `batch_keys` and `meta_info_keys` Args: batch_keys (list, optional): a list of strings indicati
verl/verl/protocol.py:732
↓ 507 callersMethodadd
(x)
internbootcamp/bootcamps/bootcamps_v1/algorithm/ekalilaanddimnaintheloggingindustry/Ekalilaanddimnaintheloggingindustry_tools.py:121
↓ 393 callersMethodget
Get a rollout replica class by name.
verl/verl/workers/rollout/replica.py:267
↓ 331 callersMethodto
Move model parameters, optimizer states, or both to the specified device. Args: device: Target device identifier.
verl/verl/workers/engine/base.py:169
↓ 230 callersMethodextend
(self, values: Union["Metric", list[Numeric]])
verl/verl/utils/metric/utils.py:115
↓ 186 callersMethodget
(self, lbl: str)
internbootcamp/bootcamps/bot_bootcamp/bot_server.py:400
↓ 157 callersMethodvalues
(cls)
verl/verl/utils/py_functional.py:253
↓ 156 callersMethodget
(self)
verl/tests/single_controller/test_nested_worker.py:31
↓ 149 callersMethodsplit
split the dataset into num_splits sub-datasets Args: num_splits: specified number of splits Returns:
verl/verl/utils/dataset/rl_dataset.py:398
↓ 139 callersMethodcount
(d_val)
internbootcamp/bootcamps/bootcamps_v1/algorithm/canniversary/Canniversary_tools.py:107
↓ 137 callersFunctionget_device_name
Get the device type string based on available accelerators. Detects the available accelerator and returns the corresponding PyTorch device ty
verl/verl/utils/device.py:67
↓ 132 callersFunctionget_torch_device
Get the PyTorch device module for the current accelerator. Returns the torch device namespace (e.g., torch.cuda, torch.npu) based on the dete
verl/verl/utils/device.py:85
↓ 131 callersMethodexists
(self, lbl: str)
internbootcamp/bootcamps/escape_bootcamp/escape_server.py:786
↓ 129 callersMethodload
(self)
internbootcamp/bootcamps/bot_bootcamp/bot_server.py:534
↓ 121 callersFunctionget_device_id
Get the index of the current accelerator device. Returns: int: The current device index (e.g., 0 for 'cuda:0').
verl/verl/utils/device.py:103
↓ 109 callersMethodsub
(self, data: DataProto)
verl/tests/single_controller/test_colocated_workers.py:47
↓ 104 callersMethodupdate
Update method for fixed KL controller (no-op). Args: current_kl (float): Current KL divergence value (unused). n_step
verl/verl/trainer/ppo/core_algos.py:182
↓ 96 callersFunctionmarked_timer
Context manager for timing with platform markers. This utility function measures the execution time of code within its context, accumulates t
verl/verl/utils/profiler/performance.py:172
↓ 86 callersFunctionprint_rank_0
If distributed is initialized, print only on rank 0.
verl/verl/utils/logger/aggregate_logger.py:89
↓ 80 callersMethodremove
(self, lbl: str)
internbootcamp/bootcamps/bot_bootcamp/bot_server.py:421
↓ 79 callersMethodfrom_pretrained
(cls, save_directory: str | os.PathLike, **kwargs)
verl/tests/special_e2e/envs/digit_completion/tokenizer.py:151
↓ 79 callersFunctionlog_gpu_memory_usage
Log GPU memory usage information. Args: head (str): A descriptive header for the memory usage log message. logger (logging.Logger
verl/verl/utils/profiler/performance.py:63
↓ 79 callersFunctionomega_conf_to_dataclass
Convert an OmegaConf DictConfig to a dataclass. Args: config: The OmegaConf DictConfig or dict to convert. dataclass_type: T
verl/verl/utils/config.py:23
↓ 77 callersMethodfrom_dict
Create a DataProto from a dict of tensors. This assumes that 1. All the tensor in tensors have the same dim0 2. Only dim0 is the batch
verl/verl/protocol.py:507
↓ 77 callersMethodupdate
(self, batch: DataProto)
verl/verl/experimental/dataset/sampler.py:39
↓ 72 callersMethodget
Return a tensor with the input `shape` as a view into the 1-D data starting at `start_index`.
verl/verl/utils/megatron/memory.py:31
↓ 72 callersMethodsearch
(self, query: str, num: int = None, return_score: bool = False)
verl/examples/sglang_multiturn/search_r1_like/local_dense_retriever/retrieval_server.py:139
↓ 69 callersMethodgcd
(a, b)
internbootcamp/bootcamps/bootcamps_v1/algorithm/cnekodoesmaths/Cnekodoesmaths_tools.py:105
↓ 67 callersMethodcreate
Create a tool instance. Args: instance_id: The instance id of the tool. Returns: The instance id of the tool
verl/verl/tools/base_tool.py:46
↓ 67 callersFunctionsafe_copy
( src_tensor: torch.Tensor, dst_tensor: torch.Tensor, skip_dtype_assert: bool = False, )
verl/scripts/converter_hf_to_mcore.py:209
↓ 66 callersFunctiondfs
(cur, current_sum)
internbootcamp/bootcamps/bootcamps_v1/algorithm/cxortree/Cxortree_tools.py:46
↓ 61 callersMethodchunk
Split the batch among dim=0 into chunks. The meta_info is passed to each DataProto after split. Args: chunks (int): the number of
verl/verl/protocol.py:875
↓ 56 callersMethoddecode
Converts a sequence of ids in a string, using the tokenizer and vocabulary with options to remove special tokens and clean up tokeniz
verl/verl/workers/rollout/tokenizer.py:89
↓ 53 callersMethodselect
Select a subset of the DataProto via batch_keys and meta_info_keys Args: batch_keys (list, optional): a list of strings indicatin
verl/verl/protocol.py:611
↓ 53 callersMethodupdate
(self, index, value)
internbootcamp/bootcamps/bootcamps_v1/graphical_puzzles/ftokitsukazeandstrangerectangle/Ftokitsukazeandstrangerectangle_tools.py:69
↓ 51 callersMethodinit
(self)
verl/tests/single_controller/test_rvdz.py:26
↓ 50 callersMethodsleep
Sleep each rollout server.
verl/verl/workers/rollout/replica.py:227
↓ 49 callersMethodto
move the batch to device Args: device (torch.device, str): torch device Returns: DataProto: the current Data
verl/verl/protocol.py:597
↓ 49 callersMethodwrite
(self, data)
internbootcamp/utils/tool_server/cli.py:124
↓ 47 callersMethod_uniform
(self, low: float, high: float)
internbootcamp/bootcamps/bbeh_bootcamps/bbeh_geometric_shapes/instruction_generator.py:25
↓ 47 callersMethodlog
(self, data, step, backend=None)
verl/verl/utils/tracking.py:162
↓ 47 callersFunctionlog_with_rank
_summary_ Log a message with rank information using a logger. This function logs the message only if `log_only_rank_0` is False or if the rank
verl/verl/utils/logger/aggregate_logger.py:128
↓ 46 callersMethodconcat
Concat a list of DataProto. The batch is concatenated among dim=0. The meta_info is merged, with special handling for metrics from different w
verl/verl/protocol.py:928
↓ 46 callersMethodshutdown
(self)
verl/tests/utils/test_special_linear_cross_entropy_tp.py:196
↓ 43 callersFunctionhf_tokenizer
Create a huggingface pretrained tokenizer which correctness handles eos and pad tokens. Args: name (str): The name of the tokenizer.
verl/verl/utils/tokenizer.py:37
↓ 42 callersMethodget
(self, lbl: str)
internbootcamp/bootcamps/escape_bootcamp/escape_server.py:780
↓ 41 callersFunctioncopy_to_local
Copy files/directories from HDFS to local cache with validation. Args: src (str): Source path - HDFS path (hdfs://...), local filesystem
verl/verl/utils/fs.py:195
↓ 41 callersMethodupdate
(x, v)
internbootcamp/bootcamps/bootcamps_v1/algorithm/cserejaandsubsequences/Cserejaandsubsequences_tools.py:123
↓ 39 callersMethodunion
(self, other: "ProfilerConfig")
verl/verl/utils/profiler/config.py:129
↓ 38 callersMethodrepeat
Repeat the batch data a specified number of times. Args: repeat_times (int): Number of times to repeat the data.
verl/verl/protocol.py:982
↓ 37 callersFunctionfunc
(self, *args, **kwargs)
verl/verl/single_controller/ray/base.py:908
↓ 36 callersMethodclose
(self)
verl/verl/experimental/vla/envs/isaac_env/isaac_env.py:294
↓ 35 callersMethod_log
统一的日志记录方法
internbootcamp/utils/tool_server/master_server.py:76
↓ 35 callersMethodsplit
Split the batch among dim=0 into chunks. The meta_info is passed to each DataProto after split. Args: split_size (int): the size
verl/verl/protocol.py:916
↓ 34 callersMethod_log
统一的日志记录方法
internbootcamp/utils/tool_server/worker_server.py:72
↓ 34 callersMethodstart
(self, **kwargs)
verl/verl/utils/profiler/profile.py:144
↓ 32 callersMethodstep
(self)
verl/verl/utils/profiler/torch_profile.py:119
↓ 30 callersFunctionunwrap_model
(model, module_instances=ALL_MODULE_WRAPPER_CLASSNAMES)
verl/verl/utils/megatron_utils.py:313
↓ 29 callersFunctionfsdp_version
(model)
verl/verl/utils/fsdp_utils.py:399
↓ 29 callersMethodget
Get the value associated with the given key. If the key does not exist, return the default value. Args: key (str): The attribute
verl/verl/base_config.py:40
↓ 29 callersMethodsave
将修改后的游戏状态保存回 Redis，保留剩余 TTL
internbootcamp/bootcamps/holdem_bootcamp/holdem_server.py:963
↓ 28 callersFunctiongather_seq_scatter_heads
A func to sync embedding input with alltoall in sequence parallel gather sequence dimension and scatter head dim: e.g. seq_dim: 1, head_d
verl/verl/utils/ulysses.py:62
↓ 28 callersMethodget_resource_pool
Get the resource pool of the worker_cls
verl/verl/single_controller/ray/base.py:197
↓ 28 callersMethodreverse
(self)
internbootcamp/bootcamps/flangeplane_bootcamp/utils/cadlib/curves.py:296
↓ 27 callersMethodapply_chat_template
Apply chat template to messages with optional tools, images, and videos. Args: messages (list[dict]): Input messages.
verl/verl/experimental/agent_loop/agent_loop.py:249
↓ 27 callersMethoddump
(self, outputs: DataProto)
verl/verl/utils/rollout_skip.py:105
↓ 26 callersMethodinit_process_group
Init process group for checkpoint engine. Args: **kwargs: Keyword arguments from `build_topology`.
verl/verl/checkpoint_engine/base.py:143
↓ 26 callersMethodsave_pretrained
(self, save_directory: str | os.PathLike, **kwargs)
verl/tests/special_e2e/envs/digit_completion/tokenizer.py:144
↓ 26 callersMethodto_dtype
(precision)
verl/verl/utils/torch_dtypes.py:61
↓ 25 callersMethodacquire
Acquire tokens from the bucket, waiting if necessary. This method will block (using asyncio.sleep) until sufficient tokens are availa
verl/verl/experimental/reward_loop/reward_manager/limited.py:90
↓ 24 callersMethodcreate_task
创建新任务
internbootcamp/web_service/backend/utils/task_manager.py:19
↓ 24 callersMethodrecord
(x)
internbootcamp/bootcamps/bootcamps_v1/algorithm/dmahmoudandehabandanotherarrayconstructiontask/Dmahmoudandehabandanotherarrayconstructiontask_tools.py:118
↓ 23 callersMethodadd
(self, idx: int, val: int)
verl/verl/utils/seqlen_balancing.py:78
↓ 23 callersFunctioncopy
r"""Works like shutil.copy() for file, and shutil.copytree for dir, and supports hdfs. Copy data and mode bits ("cp src dst"). Return the file's
verl/verl/utils/hdfs_io.py:84
↓ 23 callersFunctiondfs
(x, parent_adj, tin, tout, dep, current_time, current_g)
internbootcamp/bootcamps/bootcamps_v1/algorithm/eonchangingtree/Eonchangingtree_tools.py:31
↓ 23 callersMethodnamed_parameters
(self)
verl/verl/utils/memory_buffer.py:209
↓ 22 callersFunctionagg_loss
Aggregate the loss across global batch to ensure the loss is invariant to fsdp/megatron parallelism. NOTE: The returned loss has different b
verl/verl/trainer/ppo/core_algos.py:1025
↓ 22 callersFunctiongcd
(a, b)
internbootcamp/bootcamps/bootcamps_v1/mathematical_modeling/asavethenature/Asavethenature_tools.py:25
↓ 22 callersMethodget
从 Redis 反序列化获取游戏实例
internbootcamp/bootcamps/holdem_bootcamp/holdem_server.py:955
↓ 22 callersMethodget_data_parallel_rank
(self)
verl/verl/workers/engine/base.py:163
↓ 21 callersMethod_register_dispatch_collect_info
Register the dp_rank for a given mesh name. This function is meant to be called by the worker Args: mesh_name (str):
verl/verl/single_controller/base/worker.py:86
↓ 21 callersMethodfrom_single_dict
(cls, data, meta_info=None, auto_padding=False)
verl/tests/test_protocol_on_cpu.py:580
↓ 21 callersMethodget
(self)
verl/verl/utils/rendezvous/ray_backend.py:28
↓ 21 callersFunctionunpad_input
Unified entry point for `unpad_input` across CUDA and NPU backends. Dynamically dispatches to the appropriate device-specific implementation
verl/verl/utils/attention_utils.py:84
↓ 20 callersFunctionload_megatron_model_to_gpu
(models, load_grad=True)
verl/verl/utils/megatron_utils.py:447
↓ 20 callersFunctionmakedirs
r"""Works like os.makedirs() but supports hdfs. Super-mkdir; create a leaf directory and all intermediate ones. Works like mkdir, except tha
verl/verl/utils/hdfs_io.py:50
↓ 20 callersFunctionoffload_megatron_model_to_cpu
In megatron, the model and optimizer storage are: - bf16 parameter data chunked in model parallel group - fp32 grad chunked in model para
verl/verl/utils/megatron_utils.py:411
↓ 20 callersFunctionrearrange
Unified entry point for `rearrange` across CUDA and NPU backends. Dynamically dispatches to the appropriate device-specific implementation:
verl/verl/utils/attention_utils.py:69
↓ 20 callersMethodstart_interaction
Create a tool instance. Args: instance_id: The instance id of the tool. Returns: The instance id of the tool
verl/verl/interactions/base.py:25
↓ 20 callersMethodstore
(self)
verl/verl/single_controller/base/worker_group.py:60
↓ 19 callersMethodclose
(self)
internbootcamp/bootcamps/bot_bootcamp/bot_server.py:329
↓ 19 callersMethodfrom_config
(cls, config: dict)
verl/tests/special_e2e/envs/digit_completion/tokenizer.py:137
↓ 19 callersMethodgenerate_sequences
Batch generate sequences in sync mode. Args: prompts: The input prompts. Returns: The output sequences.
verl/verl/workers/rollout/base.py:69
next →1–100 of 18,522, ranked by callers