Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/PRIME-RL/PRIME
/ functions
Functions
2,604 in github.com/PRIME-RL/PRIME
⨍
Functions
2,604
◇
Types & classes
287
↳
Endpoints
32
Method
comp_nofunc
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2886
Function
compute_ce_dpo_loss_rm
(token_level_scores, acc, eos_mask, beta)
training/verl/trainer/ppo/core_algos.py:265
Function
compute_dpo_accuracy
(token_level_scores, acc, eos_mask, n_samples)
training/verl/trainer/ppo/core_algos.py:270
Function
compute_entropy_loss
Compute Categorical entropy loss Args: logits: `(torch.Tensor)` shape: (bs, response_length, vocab_size) eos_mask: `(
training/verl/trainer/ppo/core_algos.py:194
Function
compute_gae_advantage_return
Adapted from https://github.com/huggingface/trl/blob/main/trl/trainer/ppo_trainer.py Args: token_level_rewards: `(torch.Tensor)`
training/verl/trainer/ppo/core_algos.py:69
Function
compute_grad_norm
(model: nn.Module)
training/verl/utils/torch_functional.py:151
Method
compute_log_prob
Compute the log probability of the responses given input_ids, attention_mask and position_ids Args: data (DataProto): a DataProto
training/verl/workers/actor/megatron_actor.py:129
Method
compute_log_prob
(self, data: DataProto)
training/verl/workers/actor/dp_prime.py:75
Method
compute_log_prob
Compute the log probability of the responses given input_ids, attention_mask and position_ids Args: data (DataProto): a DataProto
training/verl/workers/actor/dp_actor.py:109
Method
compute_logprobs_fn
(output, data)
training/verl/workers/actor/megatron_actor.py:149
Function
compute_policy_loss
Adapted from https://github.com/huggingface/trl/blob/main/trl/trainer/ppo_trainer.py#L1122 Args: old_log_prob: `(torch.Tensor)`
training/verl/trainer/ppo/core_algos.py:160
Method
compute_ref_log_prob
(self, data: DataProto)
training/verl/workers/megatron_workers.py:376
Method
compute_reward
(self, data: DataProto)
training/verl/workers/reward_model/megatron/reward_model.py:123
Function
compute_rewards
(token_level_scores, old_log_prob, ref_log_prob, kl_ratio)
training/verl/trainer/ppo/core_algos.py:155
Function
compute_rloo_returns
(data:verl.DataProto, eos_mask:torch.Tensor,n_samples,config)
training/verl/trainer/ppo/core_algos.py:108
Method
compute_rm_score
(self, data: DataProto)
training/verl/workers/megatron_workers.py:723
Method
compute_rm_score
(self, data: DataProto)
training/verl/workers/fsdp_workers.py:1025
Function
compute_score
The scoring function for GSM8k. Reference: Trung, Luong, et al. "Reft: Reasoning with reinforced fine-tuning." Proceedings of the 62nd Annual Mee
training/verl/utils/reward_score/gsm8k.py:44
Function
compute_score
(solution_str, ground_truth)
training/verl/utils/reward_score/math.py:17
Function
compute_score
(completions, references, tasks)
training/verl/utils/reward_score/prime.py:85
Function
compute_value_loss
Compute the value loss. Copied from https://github.com/huggingface/trl/blob/main/trl/trainer/ppo_trainer.py#L1151 Args: vpreds (`torch.Fl
training/verl/trainer/ppo/core_algos.py:213
Method
compute_values
(self, data: DataProto)
training/verl/workers/megatron_workers.py:551
Method
compute_values
Compute values
training/verl/workers/critic/base.py:33
Method
compute_values
(self, data: DataProto)
training/verl/workers/critic/megatron_critic.py:77
Method
compute_values
(self, data: DataProto)
training/verl/workers/critic/dp_critic.py:73
Method
concat
(data: List[ray.ObjectRef])
training/verl/protocol.py:474
Function
convert_config
(hf_config: PretrainedConfig, megatron_config)
training/verl/utils/megatron_utils.py:140
Method
convert_ids_to_tokens
Converts a single index or a sequence of indices in a token or a sequence of tokens, using the vocabulary and added tokens.
training/verl/workers/rollout/tokenizer.py:116
Method
convert_tokens_to_string
Converts a sequence of tokens in a single string. The most simple way to do it is `" ".join(tokens)` but we often want to remove sub-
training/verl/workers/rollout/tokenizer.py:147
Function
create_huggingface_critic
Args: model_name: override_config_kwargs: Returns:
training/verl/utils/model.py:81
Method
create_load_config
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/arg_utils.py:62
Method
create_model_config
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/arg_utils.py:33
Function
create_nccl_communicator_in_ray
(rank: int, world_size: int, group_nam
training/verl/utils/rendezvous/ray_backend.py:47
Function
create_random_mask
Create a random mask given input_ids. Support left padding and right padding. Process: - Sample valid token length - Sample left_padding l
training/verl/utils/model.py:136
Function
decorator
(func)
training/verl/single_controller/base/decorator.py:398
Function
deepseekv2_dtensor_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_6_3/dtensor_weight_loaders.py:228
Function
deepseekv2_dtensor_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_5_4/dtensor_weight_loaders.py:194
Method
default
(self, obj)
eval/Math/math/evaluate_math.py:311
Function
default_weight_loader
Default weight loader.
training/verl/third_party/vllm/vllm_v_0_3_1/weight_loaders.py:32
Function
default_weight_loader
Default weight loader.
training/verl/third_party/vllm/vllm_v_0_6_3/megatron_weight_loaders.py:37
Function
default_weight_loader
Default weight loader.
training/verl/third_party/vllm/vllm_v_0_5_4/megatron_weight_loaders.py:37
Function
default_weight_loader
Default weight loader.
training/verl/third_party/vllm/vllm_v_0_4_2/megatron_weight_loaders.py:37
Method
det
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:3022
Method
det
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:3151
Method
determine_num_available_blocks
Determine the number of available KV blocks. This invokes `determine_num_available_blocks` on each worker and takes the min of the re
training/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:114
Method
determine_num_available_blocks
Profiles the peak memory usage of the model to determine how many KV blocks may be allocated without OOMs. The engine will first cond
training/verl/third_party/vllm/vllm_v_0_6_3/worker.py:177
Method
determine_num_available_blocks
Determine the number of available KV blocks. This invokes `determine_num_available_blocks` on each worker and takes the min of the re
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:107
Method
determine_num_available_blocks
Profiles the peak memory usage of the model to determine how many KV blocks may be allocated without OOMs. The engine will first cond
training/verl/third_party/vllm/vllm_v_0_5_4/worker.py:171
Method
determine_num_available_blocks
Determine the number of available KV blocks. This invokes `determine_num_available_blocks` on each worker and takes the min of the re
training/verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py:97
Method
determine_num_available_blocks
Profiles the peak memory usage of the model to determine how many KV blocks may be allocated without OOMs. The engine will first cond
training/verl/third_party/vllm/vllm_v_0_4_2/worker.py:142
Function
dispatch_all_to_all
(worker_group, *args, **kwargs)
training/verl/single_controller/base/decorator.py:66
Function
dispatch_dp_compute
(worker_group, *args, **kwargs)
training/verl/single_controller/base/decorator.py:255
Function
dispatch_dp_compute_data_proto
(worker_group, *args, **kwargs)
training/verl/single_controller/base/decorator.py:272
Function
dispatch_dp_compute_data_proto_with_func
(worker_group, *args, **kwargs)
training/verl/single_controller/base/decorator.py:279
Function
dispatch_megatron_compute_data_proto
All the args and kwargs must be DataProto. The batch will be chunked by dp_size and passed to each rank
training/verl/single_controller/base/decorator.py:118
Function
dispatch_megatron_pp_as_dp_data_proto
(worker_group, *args, **kwargs)
training/verl/single_controller/base/decorator.py:237
Function
dispatch_one_to_all
(worker_group, *args, **kwargs)
training/verl/single_controller/base/decorator.py:60
Method
do_log_stats
Forced log when no requests active.
training/verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:595
Method
download_model
(self, model_config: ModelConfig)
training/verl/third_party/vllm/vllm_v_0_6_3/model_loader.py:113
Method
download_model
(self, model_config: ModelConfig)
training/verl/third_party/vllm/vllm_v_0_6_3/model_loader.py:144
Method
dp_size
(self)
training/verl/single_controller/base/megatron/worker_group.py:41
Method
elementary_transform
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1232
Method
elementary_transforms
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1314
Method
encode_async
(self, prompt: str, request_id: Optional[str] = None,
training/verl/third_party/vllm/vllm_v_0_3_1/tokenizer.py:45
Method
encode_async
(self, prompt: str, request_id: Optional[str] = None,
training/verl/third_party/vllm/vllm_v_0_5_4/tokenizer.py:50
Method
encode_async
(self, prompt: str, request_id: Optional[str] = None,
training/verl/third_party/vllm/vllm_v_0_4_2/tokenizer.py:50
Method
engine
(self)
training/verl/single_controller/ray/dp.py:85
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:820
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:865
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:910
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:964
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1032
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1097
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1140
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1184
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1247
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1332
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1432
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1502
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1581
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1679
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1822
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1912
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1958
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2006
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2196
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2276
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2360
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2434
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2487
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2540
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2600
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2668
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2733
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2807
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2913
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:3028
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:3157
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:3307
Method
enterRule
(self, listener)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:3627
← previous
next →
1,701–1,800 of 2,604, ranked by callers