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
getRuleIndex
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:6225
Method
getRuleIndex
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:6302
Method
getRuleIndex
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:6365
Method
getRuleIndex
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:6416
Method
get_added_vocab
Returns the added tokens in the vocabulary as a dictionary of token to index. Results might be different from the fast call because f
training/verl/workers/rollout/tokenizer.py:135
Method
get_cuda_visible_devices
(self)
training/verl/single_controller/base/worker.py:165
Method
get_data
()
training/verl/protocol.py:382
Function
get_default_kwargs_for_column_parallel_linear
()
training/verl/utils/megatron/tensor_parallel.py:58
Function
get_default_kwargs_for_parallel_embedding
()
training/verl/utils/megatron/tensor_parallel.py:77
Function
get_default_kwargs_for_row_parallel_linear
()
training/verl/utils/megatron/tensor_parallel.py:72
Function
get_device_mesh
()
training/verl/third_party/vllm/vllm_v_0_6_3/parallel_state.py:281
Function
get_device_mesh
()
training/verl/third_party/vllm/vllm_v_0_5_4/parallel_state.py:272
Function
get_device_mesh
()
training/verl/third_party/vllm/vllm_v_0_4_2/parallel_state.py:263
Method
get_evaluation_sample
(self)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/benchmarks/code_generation.py:106
Method
get_evaluation_sample
(self)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/benchmarks/test_output_prediction.py:55
Method
get_head_size
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/config.py:190
Method
get_hidden_size
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/config.py:187
Function
get_kl_controller
(config)
training/verl/trainer/ppo/core_algos.py:55
Method
get_log_path
Return the path to the log file.
training/verl/utils/logger/aggregate_logger.py:111
Method
get_master_addr_port
(self)
training/verl/single_controller/base/worker.py:162
Method
get_max_input_len
Get the maximum input length for the LoRA request.
training/verl/third_party/vllm/vllm_v_0_5_4/tokenizer.py:39
Method
get_max_input_len
Get the maximum input length for the LoRA request.
training/verl/third_party/vllm/vllm_v_0_4_2/tokenizer.py:39
Method
get_megatron_global_info
(self)
training/verl/single_controller/base/megatron/worker_group.py:50
Method
get_megatron_rank_info
(self, rank: int)
training/verl/single_controller/base/megatron/worker_group.py:31
Method
get_memory_buffers
(self)
training/verl/utils/memory_buffer.py:153
Function
get_micro_data_parallel_rank
()
training/verl/third_party/vllm/vllm_v_0_3_1/parallel_state.py:146
Function
get_micro_data_parallel_world_size
()
training/verl/third_party/vllm/vllm_v_0_3_1/parallel_state.py:142
Function
get_mixtral_question_template_answer
( question: TestOutputPredictionProblem, testcase_input: str )
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/test_output_prediction.py:112
Function
get_mixtral_question_template_answer
(question: str, code, result, metadata)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/self_repair.py:106
Method
get_model_config
Gets the model configuration.
training/verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:336
Method
get_model_size_on_rank_zero
(self)
training/verl/single_controller/ray/dp.py:88
Method
get_model_size_on_rank_zero
(self)
training/verl/single_controller/base/dp.py:40
Method
get_node_ip_by_sdk
()
training/verl/single_controller/base/worker.py:41
Method
get_num_kv_heads
Returns the number of KV heads per GPU.
training/verl/third_party/vllm/vllm_v_0_3_1/config.py:226
Method
get_rank_zero_info
(self)
training/verl/single_controller/base/register_center/ray.py:24
Function
get_tensor_model_parallel_rank
Return my rank for the tensor model parallel group.
training/verl/third_party/vllm/vllm_v_0_6_3/parallel_state.py:302
Function
get_tensor_model_parallel_rank
Return my rank for the tensor model parallel group.
training/verl/third_party/vllm/vllm_v_0_5_4/parallel_state.py:293
Function
get_tensor_model_parallel_src_rank
Calculate the global rank corresponding to the first local rank in the tensor model parallel group.
training/verl/third_party/vllm/vllm_v_0_3_1/parallel_state.py:124
Function
get_tensor_model_parallel_src_rank
Calculate the global rank corresponding to the first local rank in the tensor model parallel group.
training/verl/third_party/vllm/vllm_v_0_6_3/parallel_state.py:307
Function
get_tensor_model_parallel_src_rank
Calculate the global rank corresponding to the first local rank in the tensor model parallel group.
training/verl/third_party/vllm/vllm_v_0_5_4/parallel_state.py:298
Function
get_tensor_model_parallel_src_rank
Calculate the global rank corresponding to the first local rank in the tensor model parallel group.
training/verl/third_party/vllm/vllm_v_0_4_2/parallel_state.py:289
Function
get_tensor_parallel_partition_dim
(param)
training/verl/utils/megatron/tensor_parallel.py:90
Function
get_tensor_parallel_partition_stride
(param)
training/verl/utils/megatron/tensor_parallel.py:95
Method
get_tokenizer
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/llm.py:139
Method
get_tokenizer
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/llm.py:151
Method
get_tokenizer
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/llm.py:157
Method
get_tokenizer
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/llm.py:143
Method
get_tokenizer_for_seq
(sequence: Sequence)
training/verl/third_party/vllm/vllm_v_0_6_3/llm_engine_sp.py:200
Function
get_unpad_data
(attention_mask)
training/verl/utils/torch_functional.py:484
Method
get_weight_buffer_meta
(self)
training/verl/utils/memory_buffer.py:156
Function
gpt2_dtensor_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_6_3/dtensor_weight_loaders.py:308
Function
gpt2_dtensor_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_5_4/dtensor_weight_loaders.py:270
Function
gpt2_dtensor_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_4_2/dtensor_weight_loaders.py:201
Function
gpt2_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_3_1/weight_loaders.py:40
Function
gpt2_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_6_3/megatron_weight_loaders.py:46
Function
gpt2_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_5_4/megatron_weight_loaders.py:45
Function
gpt2_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_4_2/megatron_weight_loaders.py:45
Function
gptbigcode_dtensor_load_weights
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_6_3/dtensor_weight_loaders.py:61
Function
gptbigcode_dtensor_load_weights
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_5_4/dtensor_weight_loaders.py:64
Function
gptbigcode_dtensor_load_weights
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_4_2/dtensor_weight_loaders.py:74
Method
group
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1020
Method
group
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2992
Method
group
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:3124
Method
init_cache_engine
(self, cache_config: CacheConfig)
training/verl/third_party/vllm/vllm_v_0_3_1/worker.py:168
Method
init_cache_engine
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/llm.py:145
Method
init_cache_engine
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/llm_engine_sp.py:344
Method
init_cache_engine
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:156
Method
init_cache_engine
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/llm.py:151
Method
init_cache_engine
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/llm_engine_sp.py:270
Method
init_cache_engine
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:150
Method
init_cache_engine
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/llm.py:137
Method
init_cache_engine
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/llm_engine_sp.py:236
Method
init_cache_engine
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py:140
Function
init_fn
(x: torch.nn.Module)
training/verl/utils/fsdp_utils.py:21
Method
init_megatron
(self, default_megatron_kwargs: Dict = None)
training/verl/single_controller/base/megatron/worker_group.py:28
Method
init_model
(self)
training/verl/workers/megatron_workers.py:261
Method
init_model
(self)
training/verl/workers/megatron_workers.py:514
Method
init_model
(self)
training/verl/workers/megatron_workers.py:672
Method
init_model
(self)
training/verl/workers/fsdp_workers.py:251
Method
init_model
(self)
training/verl/workers/fsdp_workers.py:568
Method
init_model
(self)
training/verl/workers/fsdp_workers.py:715
Method
init_model
(self)
training/verl/workers/fsdp_workers.py:955
Method
init_workers
Init resource pool and worker group
training/verl/trainer/ppo/ray_trainer.py:849
Method
initialize_cache
Initialize the KV cache in all workers.
training/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:134
Method
initialize_cache
Initialize the KV cache in all workers.
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:127
Method
initialize_cache
Initialize the KV cache in all workers.
training/verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py:117
Function
initialize_parallel_state
( distributed_init_method: str = "env://", backend: str = "nccl", tensor_model_parallel_size: int
training/verl/third_party/vllm/vllm_v_0_6_3/parallel_state.py:38
Function
initialize_parallel_state
( distributed_init_method: str = "env://", backend: str = "nccl", tensor_model_parallel_size: int
training/verl/third_party/vllm/vllm_v_0_5_4/parallel_state.py:37
Function
initialize_parallel_state
( distributed_init_method: str = "env://", backend: str = "nccl", tensor_model_parallel_size: int
training/verl/third_party/vllm/vllm_v_0_4_2/parallel_state.py:35
Method
initialize_weight_buffer
Initialize the weight buffer. The weight buffer is obtained according to the actor. We will construct a large buffer for each dtype i
training/verl/utils/memory_buffer.py:181
Function
initializer
Set maximum amount of memory each worker process can allocate.
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/utils/multiprocess.py:92
Method
inject
(self, var_dict: Dict[str, Any])
eval/Math/Qwen25-Math/evaluation/python_executor.py:51
Function
inner
(*args, **kwargs)
training/verl/single_controller/base/decorator.py:401
Method
insert_output_evaluation
( self, output_list: list[str], code_list: list[str], graded_list: list[bool],
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/benchmarks/code_generation.py:92
Method
insert_output_evaluation
( self, output_list: list[str], code_list: list[str], graded_list: list[bool] )
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/benchmarks/test_output_prediction.py:47
Method
is_bf16
(precision)
training/verl/utils/torch_dtypes.py:59
Function
is_equiv
(str1, str2, verbose=False)
eval/utils/math_equivalence.py:140
Method
is_exception
(self)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/utils/multiprocess.py:85
Method
is_fast
(self)
training/verl/workers/rollout/tokenizer.py:161
Method
is_fp16
(precision)
training/verl/utils/torch_dtypes.py:51
← previous
next →
2,101–2,200 of 2,604, ranked by callers