MCPcopy Create free account

hub / github.com/PRIME-RL/PRIME / functions

Functions2,604 in github.com/PRIME-RL/PRIME

↓ 1 callersFunctionget_deepseekcode_question_template_answer
(question: CodeGenerationProblem)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/code_generation.py:66
↓ 1 callersFunctionget_deepseekcode_question_template_answer
( question: TestOutputPredictionProblem, testcase_input: str )
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/test_output_prediction.py:93
↓ 1 callersFunctionget_deepseekcode_question_template_answer
(question: str, code, result, metadata)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/self_repair.py:84
↓ 1 callersFunctionget_default_model_parallel_config
()
training/verl/utils/megatron/tensor_parallel.py:43
↓ 1 callersFunctionget_eval_all_output_path
(model_repr:str, args)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/utils/path_utils.py:34
↓ 1 callersFunctionget_examples
()
eval/Math/Qwen25-Math/evaluation/examples.py:4
↓ 1 callersMethodget_from_buffer
(self, count, dp_size)
training/verl/utils/dataset/rl_dataset.py:180
↓ 1 callersFunctionget_huggingface_actor_config
(model_name: str, override_config_kwargs=None, trust_remote_code=False)
training/verl/utils/model.py:47
↓ 1 callersFunctionget_local_temp_path
Return a local temp path that joins cache_dir and basename of hdfs_path Args: hdfs_path: cache_dir: Returns:
training/verl/utils/fs.py:37
↓ 1 callersMethodget_lora_tokenizer
(self, lora_request: Optional[LoRARequest])
training/verl/third_party/vllm/vllm_v_0_5_4/tokenizer.py:57
↓ 1 callersMethodget_lora_tokenizer
(self, lora_request: Optional[LoRARequest])
training/verl/third_party/vllm/vllm_v_0_4_2/tokenizer.py:57
↓ 1 callersFunctionget_magicoder_question_template_answer
(question: CodeGenerationProblem)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/code_generation.py:113
↓ 1 callersFunctionget_magicoder_question_template_answer
( question: TestOutputPredictionProblem, testcase_input: str )
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/test_output_prediction.py:102
↓ 1 callersFunctionget_magicoder_question_template_answer
(question: str, code, result, metadata)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/self_repair.py:95
↓ 1 callersMethodget_megatron_global_info
(self)
training/verl/single_controller/base/megatron/worker.py:25
↓ 1 callersFunctionget_micro_data_parallel_rank
()
training/verl/workers/hybrid_engine/megatron_vllm.py:427
↓ 1 callersFunctionget_model
(actor_model: Union[PreTrainedModel, Dict], model_config: ModelConfig, device_conf
training/verl/third_party/vllm/vllm_v_0_3_1/model_loader.py:130
↓ 1 callersFunctionget_model
( actor_model: Union[PreTrainedModel, Dict], model_config: ModelConfig, load_config: LoadConfig,
training/verl/third_party/vllm/vllm_v_0_6_3/model_loader.py:33
↓ 1 callersFunctionget_model
(actor_model: Union[PreTrainedModel, Dict], model_config: ModelConfig, load_config
training/verl/third_party/vllm/vllm_v_0_5_4/model_loader.py:35
↓ 1 callersFunctionget_model
(actor_model: Union[PreTrainedModel, Dict], model_config: ModelConfig, load_config: LoadConfig,
training/verl/third_party/vllm/vllm_v_0_4_2/model_loader.py:34
↓ 1 callersFunctionget_model_loader
Get a model loader based on the load format.
training/verl/third_party/vllm/vllm_v_0_6_3/model_loader.py:65
↓ 1 callersFunctionget_model_loader
Get a model loader based on the load format.
training/verl/third_party/vllm/vllm_v_0_5_4/model_loader.py:64
↓ 1 callersFunctionget_model_loader
Get a model loader based on the load format.
training/verl/third_party/vllm/vllm_v_0_4_2/model_loader.py:55
↓ 1 callersFunctionget_nccl_id_store_by_name
(name)
training/verl/utils/rendezvous/ray_backend.py:34
↓ 1 callersMethodget_next_batch
(self)
training/verl/utils/dataset/rl_dataset.py:165
↓ 1 callersMethodget_num_layers
(self, parallel_config: "ParallelConfig")
training/verl/third_party/vllm/vllm_v_0_3_1/config.py:235
↓ 1 callersFunctionget_open_port
()
training/verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:762
↓ 1 callersFunctionget_open_port
()
training/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:240
↓ 1 callersFunctionget_open_port
()
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:237
↓ 1 callersFunctionget_open_port
()
training/verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py:202
↓ 1 callersFunctionget_parser
()
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/compute_scores.py:15
↓ 1 callersFunctionget_phind_question_template_answer
(question: CodeGenerationProblem)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/code_generation.py:143
↓ 1 callersFunctionget_phind_question_template_answer
( question: TestOutputPredictionProblem, testcase_input: str )
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/test_output_prediction.py:128
↓ 1 callersFunctionget_phind_question_template_answer
(question: str, code, result, metadata)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/self_repair.py:133
↓ 1 callersFunctionget_predefined_dispatch_fn
(dispatch_mode)
training/verl/single_controller/base/decorator.py:300
↓ 1 callersFunctionget_predefined_execute_fn
Note that here we only asks execute_all and execute_rank_zero to be implemented Leave the choice of how these two functions handle argument '
training/verl/single_controller/base/decorator.py:350
↓ 1 callersFunctionget_qwen_question_template_answer
(question: CodeGenerationProblem)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/code_generation.py:83
↓ 1 callersFunctionget_qwen_question_template_answer
(question: TestOutputPredictionProblem, testcase_input: str)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/test_output_prediction.py:135
↓ 1 callersFunctionget_qwen_question_template_answer
(question: str, code, result, metadata)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/self_repair.py:143
↓ 1 callersFunctionget_random_string
(length: int)
training/verl/single_controller/ray/base.py:29
↓ 1 callersFunctionget_tensor_model_parallel_rank
Return my rank for the tensor model parallel group.
training/verl/third_party/vllm/vllm_v_0_3_1/parallel_state.py:119
↓ 1 callersFunctionget_tensor_model_parallel_rank
Return my rank for the tensor model parallel group.
training/verl/third_party/vllm/vllm_v_0_4_2/parallel_state.py:284
↓ 1 callersMethodget_total_num_kv_heads
Returns the total number of KV heads.
training/verl/third_party/vllm/vllm_v_0_3_1/config.py:194
↓ 1 callersFunctionget_version
(pkg)
training/verl/third_party/vllm/__init__.py:18
↓ 1 callersMethodget_vocab_size
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/config.py:184
↓ 1 callersFunctionget_weight_loader
(arch: str)
training/verl/models/weight_loader_registry.py:16
↓ 1 callersFunctionget_wizard_question_template_answer
(question: CodeGenerationProblem)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/code_generation.py:126
↓ 1 callersFunctionget_wizard_question_template_answer
( question: TestOutputPredictionProblem, testcase_input: str )
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/test_output_prediction.py:119
↓ 1 callersFunctiongrade_answer
The answer will be considered correct if: (a) it normalizes to the same string as the ground truth answer OR (b) sympy can simplify t
training/verl/utils/reward_score/evaluation_utils/math_util/__init__.py:240
↓ 1 callersFunctiongroup_pred
(preds, strip=True, use_symbol=False)
eval/Math/Qwen25-Math/evaluation/rm_maj_eval.py:17
↓ 1 callersFunctionhandle_base
(x)
eval/utils/grader.py:128
↓ 1 callersFunctionhandle_base
(x)
training/verl/utils/reward_score/evaluation_utils/math_util/grader.py:127
↓ 1 callersFunctionhandle_base
(x)
data_preprocessing/math_util/grader.py:128
↓ 1 callersFunctionhandle_exp
(func)
eval/Math/Qwen25-Math/evaluation/latex2sympy/latex2sympy2.py:1055
↓ 1 callersFunctionhandle_integral
(func)
eval/Math/Qwen25-Math/evaluation/latex2sympy/latex2sympy2.py:980
↓ 1 callersFunctionhandle_limit
(func)
eval/Math/Qwen25-Math/evaluation/latex2sympy/latex2sympy2.py:1035
↓ 1 callersFunctionhandle_pi
(string, pi)
eval/utils/grader.py:137
↓ 1 callersFunctionhandle_pi
(string, pi)
training/verl/utils/reward_score/evaluation_utils/math_util/grader.py:136
↓ 1 callersFunctionhandle_pi
(string, pi)
data_preprocessing/math_util/grader.py:137
↓ 1 callersMethodinit_cache_engine
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/llm.py:133
↓ 1 callersMethodinit_cache_engine
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:215
↓ 1 callersMethodinit_device
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/worker.py:140
↓ 1 callersMethodinit_device
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/worker.py:134
↓ 1 callersMethodinit_device
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/worker.py:105
↓ 1 callersMethodinit_megatron
(self, default_megatron_kwargs: Optional[Dict] = None)
training/verl/single_controller/ray/megatron.py:58
↓ 1 callersFunctioninit_worker_distributed_environment
Initialize the distributed environment.
training/verl/third_party/vllm/vllm_v_0_6_3/worker.py:294
↓ 1 callersFunctioninit_worker_distributed_environment
Initialize the distributed environment.
training/verl/third_party/vllm/vllm_v_0_5_4/worker.py:286
↓ 1 callersFunctioninit_worker_distributed_environment
Initialize the distributed environment.
training/verl/third_party/vllm/vllm_v_0_4_2/worker.py:257
↓ 1 callersMethodinit_workers
Init resource pool and worker group
training/verl/trainer/ppo/ray_trainer.py:355
↓ 1 callersFunctioninitialize_cluster
Initialize the distributed cluster probably with Ray. Args: parallel_config: The configurations for parallel execution. engine_us
training/verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:734
↓ 1 callersFunctioninitialize_cluster
Initialize the distributed cluster probably with Ray. Args: parallel_config: The configurations for parallel execution. Returns:
training/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:216
↓ 1 callersFunctioninitialize_cluster
Initialize the distributed cluster probably with Ray. Args: parallel_config: The configurations for parallel execution. Returns:
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:213
↓ 1 callersFunctioninitialize_cluster
Initialize the distributed cluster probably with Ray. Args: parallel_config: The configurations for parallel execution. Returns:
training/verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py:178
↓ 1 callersFunctioninitialize_global_process_group
(timeout_second=36000)
training/verl/utils/distributed.py:18
↓ 1 callersFunctioninitialize_model_parallel_for_vllm
( tensor_model_parallel_size: int, num_tensor_model_parallel_groups_per_train_tp: int = 1, pipelin
training/verl/third_party/vllm/vllm_v_0_6_3/parallel_state.py:104
↓ 1 callersFunctioninitialize_model_parallel_for_vllm
(tensor_model_parallel_size: int, num_tensor_model_parallel_groups_per_
training/verl/third_party/vllm/vllm_v_0_5_4/parallel_state.py:101
↓ 1 callersFunctioninitialize_model_parallel_for_vllm
(tensor_model_parallel_size: int, num_tensor_model_parallel_groups_per_
training/verl/third_party/vllm/vllm_v_0_4_2/parallel_state.py:98
↓ 1 callersFunctioninitialize_model_parallel_from_megatron
( tensor_model_parallel_size=None # we set None for backward compatibility to set infer_tp = train_tp
training/verl/third_party/vllm/vllm_v_0_3_1/parallel_state.py:26
↓ 1 callersMethodinsert_output
(self, output_list: list[str], code_list: list[str])
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/benchmarks/code_generation.py:78
↓ 1 callersMethodinsert_output
(self, output_list: list[str], pred_list: list[str])
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/benchmarks/test_output_prediction.py:32
↓ 1 callersFunctionis_equiv
(str1, str2, verbose=False)
training/verl/utils/reward_score/math.py:32
↓ 1 callersFunctionis_execution_success
(output)
eval/Math/Qwen25-Math/evaluation/trajectory.py:63
↓ 1 callersFunctionis_megatron_core_available
()
training/verl/utils/import_utils.py:24
↓ 1 callersFunctionis_number
(element: str)
eval/Math/Qwen25-Math/evaluation/math_utils.py:55
↓ 1 callersMethodis_success
(self)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/utils/multiprocess.py:79
↓ 1 callersFunctionlast_boxed_only_string
(string)
eval/utils/util.py:16
↓ 1 callersFunctionlast_boxed_only_string
(string)
training/verl/utils/reward_score/math.py:63
↓ 1 callersFunctionload_code_generation_dataset_not_fast
(release_version="release_v1")
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/benchmarks/code_generation.py:131
↓ 1 callersFunctionload_data
(data_name, split, data_dir="../../../data")
eval/Math/Qwen25-Math/evaluation/data_loader.py:9
↓ 1 callersMethodload_data
(self)
data_preprocessing/stage4_judge.py:286
↓ 1 callersFunctionload_hf_weights
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_6_3/hf_weight_loader.py:27
↓ 1 callersFunctionload_hf_weights
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_5_4/hf_weight_loader.py:30
↓ 1 callersFunctionload_hf_weights
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_4_2/hf_weight_loader.py:79
↓ 1 callersFunctionload_megatron_param_and_grad
(module_list: nn.ModuleList, device_id, load_grad=False, hybrid_engine=None)
training/verl/utils/megatron_utils.py:241
↓ 1 callersMethodload_model
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/worker.py:117
↓ 1 callersMethodload_params_to_cuda
(self)
training/verl/workers/reward_model/megatron/reward_model.py:270
↓ 1 callersMethodload_test_data
(self)
data_preprocessing/stage4_judge.py:268
↓ 1 callersFunctionlogprobs_from_logits_flash_attn
(logits, labels)
training/verl/utils/torch_functional.py:65
↓ 1 callersFunctionlogprobs_from_logits_naive
(logits, labels)
training/verl/utils/torch_functional.py:70
↓ 1 callersFunctionlower_keys
(example)
eval/Math/Qwen25-Math/evaluation/utils.py:41
← previousnext →901–1,000 of 2,604, ranked by callers