MCPcopy Create free account

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

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

Methodis_fp32
(precision)
training/verl/utils/torch_dtypes.py:55
Methodis_process_expired
(self)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/utils/multiprocess.py:88
Functionis_sequence_parallel_param
(param)
training/verl/utils/megatron/sequence_parallel.py:25
Methodis_timeout
(self)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/utils/multiprocess.py:82
Functionkl_penalty
Compute KL divergence given logprob and ref_logprob. Copied from https://github.com/huggingface/trl/blob/main/trl/trainer/ppo_trainer.py#L1104
training/verl/trainer/ppo/core_algos.py:239
Functionlast_boxed_only
Given a (q,a) sample, filter the answers so that they only contain the last \boxed{...} or \fbox{...} element
eval/utils/util.py:5
Methodlimit_sub
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:5331
Methodlist_loras
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:724
Methodlist_loras
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/worker.py:266
Methodlist_loras
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:178
Methodlist_loras
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:172
Methodlist_loras
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py:162
Methodlist_prompt_adapters
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:193
Methodlist_prompt_adapters
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:188
Functionllama_dtensor_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_6_3/dtensor_weight_loaders.py:107
Functionllama_dtensor_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_5_4/dtensor_weight_loaders.py:110
Functionllama_dtensor_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_4_2/dtensor_weight_loaders.py:120
Functionllama_megatron_core_te_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_6_3/megatron_weight_loaders.py:86
Functionllama_megatron_core_te_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_5_4/megatron_weight_loaders.py:85
Functionllama_megatron_core_te_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_4_2/megatron_weight_loaders.py:85
Functionllama_megatron_core_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_6_3/megatron_weight_loaders.py:117
Functionllama_megatron_core_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_5_4/megatron_weight_loaders.py:116
Functionllama_megatron_core_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_4_2/megatron_weight_loaders.py:116
Functionllama_megatron_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_6_3/megatron_weight_loaders.py:74
Functionllama_megatron_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_5_4/megatron_weight_loaders.py:73
Functionllama_megatron_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_4_2/megatron_weight_loaders.py:73
Functionllama_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_3_1/weight_loaders.py:68
Methodload_checkpoint
(self, checkpoint_path)
training/verl/workers/megatron_workers.py:395
Methodload_checkpoint
(self, checkpoint_path)
training/verl/workers/megatron_workers.py:568
Functionload_fsdp_grad
(module, device_id)
training/verl/utils/fsdp_utils.py:78
Methodload_model
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/model_runner.py:90
Methodload_model
( self, *, model_config: ModelConfig, device_config: DeviceConfig, lor
training/verl/third_party/vllm/vllm_v_0_6_3/model_loader.py:116
Methodload_model
( self, actor_model: Union[PreTrainedModel, Dict], model_config: ModelConfig,
training/verl/third_party/vllm/vllm_v_0_6_3/model_loader.py:156
Methodload_model
( self, actor_model: Union[PreTrainedModel, Dict], model_config: ModelConfig,
training/verl/third_party/vllm/vllm_v_0_6_3/model_loader.py:253
Methodload_model
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/model_runner.py:101
Methodload_model
(self, *, model_config: ModelConfig, device_config: DeviceConfig, lora_config: Optional[LoRAConfig],
training/verl/third_party/vllm/vllm_v_0_5_4/model_loader.py:112
Methodload_model
(self, actor_model: Union[PreTrainedModel, Dict], model_config: ModelConfig, device_config:
training/verl/third_party/vllm/vllm_v_0_5_4/model_loader.py:143
Methodload_model
(self, actor_model: Union[PreTrainedModel, Dict], model_config: ModelConfig, device_config:
training/verl/third_party/vllm/vllm_v_0_5_4/model_loader.py:230
Methodload_model
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/model_runner.py:89
Methodload_model
(self, *, model_config: ModelConfig, device_config: DeviceConfig, lora_config: Optional[LoRAConfig],
training/verl/third_party/vllm/vllm_v_0_4_2/model_loader.py:103
Methodload_model
(self, actor_model: Union[PreTrainedModel, Dict], model_config: Mo
training/verl/third_party/vllm/vllm_v_0_4_2/model_loader.py:133
Methodload_model
(self, actor_model: Union[PreTrainedModel, Dict], model_config: Mo
training/verl/third_party/vllm/vllm_v_0_4_2/model_loader.py:218
Methodload_model
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/model_runner.py:105
Methodload_pretrained_model
(self, checkpoint_path)
training/verl/workers/megatron_workers.py:399
Functionload_state_dict_to_megatron_llama
Load merged state_dict to sharded Megatron module in training.
training/verl/models/llama/megatron/checkpoint_utils/llama_loader.py:51
Methodlocal_rank_list
(self)
training/verl/single_controller/base/worker_group.py:55
Methodlocal_world_size_list
(self)
training/verl/single_controller/base/worker_group.py:49
Functionlog_probs_from_logits_response
Compute the response log_probs from full logits. Note that logits = model(input_ids) Args: input_ids: [batch_size, seqlen] lo
training/verl/utils/torch_functional.py:284
Functionlog_probs_from_logits_response_rmpad
Compute the log_probs from logits with rmpad logits and pad input. Note that logits_rmpad = model(input_ids_rmpad). For each sentences, there is a
training/verl/utils/torch_functional.py:300
Functionlogitsprocessor_init
Args: scale: A scaling factor to apply to the logits.
training/verl/third_party/vllm/vllm_v_0_6_3/model_loader.py:307
Functionlogitsprocessor_init
Args: scale: A scaling factor to apply to the logits.
training/verl/third_party/vllm/vllm_v_0_5_4/model_loader.py:279
Functionlogprobs_of_labels_v2
A memory efficient implementation of logprobs_from_logits
training/verl/utils/torch_functional.py:76
Methodloss_func
(output, data, meta_info)
training/verl/workers/critic/megatron_critic.py:135
Methodloss_func
(output, data, meta_info)
training/verl/workers/actor/megatron_actor.py:249
Methodloss_func
(output)
training/verl/workers/reward_model/megatron/reward_model.py:219
Functionlr_lambda
(current_step)
training/verl/utils/torch_functional.py:413
Functionmain_task
(config)
training/verl/trainer/main_ppo.py:135
Methodmake_minibatch_iterator
(self, data: DataProto)
training/verl/workers/critic/megatron_critic.py:106
Functionmark_parameter_as_sequence_parallel
(parameter)
training/verl/utils/megatron/sequence_parallel.py:21
Functionmasked_sum
Compute mean of tensor with a masked values.
training/verl/utils/torch_functional.py:102
Functionmasked_whiten
Whiten values with masked values.
training/verl/utils/torch_functional.py:130
Methodmaster_address
(self)
training/verl/single_controller/ray/base.py:352
Methodmaster_port
(self)
training/verl/single_controller/ray/base.py:356
Functionmath_equal_process
(param)
eval/Math/Qwen25-Math/evaluation/grader.py:262
Methodmathit
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:4387
Methodmathit_text
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:4480
Methodmatrix
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:3019
Methodmatrix
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:3148
Methodmatrix_row
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1293
Methodmatrix_row
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1414
Functionmaybe_remote
Schedule main function as ray remote task if VERL_DRIVER_NUM_GPUS or VERL_DRIVER_RESOURCES specified in config. - VERL_DRIVER_NUM_GPUS: number
training/verl/single_controller/ray/decorator.py:25
Methodmegatron_actor_model_provider
(pre_process, post_process)
training/verl/workers/megatron_workers.py:154
Methodmegatron_critic_model_provider
(pre_process, post_process)
training/verl/workers/megatron_workers.py:476
Methodmegatron_rm_model_provider
(pre_process, post_process)
training/verl/workers/megatron_workers.py:638
Methodmemory_buffers
(self)
training/verl/utils/memory_buffer.py:213
Functionmerge_megatron_ckpt_llama
Merge sharded parameters of a Megatron module into a merged checkpoint. Args: wrapped_modelss (list of megatron.model.DistributedDataPara
training/verl/models/llama/megatron/checkpoint_utils/llama_saver.py:76
Functionmerge_resource_pool
(rp1: RayResourcePool, rp2: RayResourcePool)
training/verl/single_controller/ray/base.py:114
Functionmistral_megatron_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_6_3/megatron_weight_loaders.py:254
Functionmistral_megatron_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_5_4/megatron_weight_loaders.py:253
Functionmistral_megatron_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_4_2/megatron_weight_loaders.py:253
Functionmistral_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_3_1/weight_loaders.py:83
Methodmp
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1988
Methodmp
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2071
Methodmp
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:5316
Methodmp_nofunc
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2166
Methodmp_nofunc
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:6077
Methodmp_nofunc
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:6171
Methodmp_nofunc_sempred
(self, localctx, predIndex)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:6476
Methodmp_sempred
(self, localctx, predIndex)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:6472
Methodnorm_group
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2995
Methodnorm_group
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:3127
Functionnormalize_answer
(answer: Optional[str])
training/verl/utils/reward_score/evaluation_utils/math_util/math_normalize.py:10
Functionnormalize_answer
(answer: Optional[str])
data_preprocessing/math_util/math_normalize.py:10
Functionnullable_str
(val: str)
training/verl/third_party/vllm/vllm_v_0_5_4/arg_utils.py:43
Functionnullable_str
(val: str)
training/verl/third_party/vllm/vllm_v_0_4_2/arg_utils.py:33
Methodoffload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:730
Methodoffload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/worker.py:250
Methodoffload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/llm.py:199
Methodoffload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/llm_engine_sp.py:407
Methodoffload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:209
← previousnext →2,201–2,300 of 2,604, ranked by callers