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
↓ 1 callers
Method
_process_sequence_group_outputs
(self, seq_group: SequenceGroup, outputs: SequenceGroupOutput)
training/verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:385
↓ 1 callers
Method
_read_files_and_tokenize
(self)
training/verl/utils/dataset/rm_dataset.py:85
↓ 1 callers
Method
_read_files_and_tokenize
(self)
training/verl/utils/dataset/sft_dataset.py:73
↓ 1 callers
Method
_read_files_and_tokenize
(self)
training/verl/utils/dataset/rl_dataset.py:100
↓ 1 callers
Function
_remove_right_units
(string)
eval/utils/math_equivalence.py:48
↓ 1 callers
Function
_remove_right_units
(string)
training/verl/utils/reward_score/evaluation_utils/math_util/math_normalize.py:71
↓ 1 callers
Function
_remove_right_units
(string)
data_preprocessing/math_util/math_normalize.py:71
↓ 1 callers
Method
_run_engine
(self, use_tqdm: bool)
training/verl/third_party/vllm/vllm_v_0_3_1/llm.py:217
↓ 1 callers
Method
_run_engine
(self, use_tqdm: bool)
training/verl/third_party/vllm/vllm_v_0_4_2/llm.py:248
↓ 1 callers
Method
_run_single
(self, prompt: list[dict[str, str]])
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/runner/deepseek_runner.py:32
↓ 1 callers
Function
_set_default_torch_dtype
Sets the default torch dtype to the given dtype.
training/verl/third_party/vllm/vllm_v_0_3_1/model_loader.py:38
↓ 1 callers
Function
_str_to_int
(x: str)
training/verl/utils/reward_score/evaluation_utils/math_util/__init__.py:82
↓ 1 callers
Function
_str_to_int
(x: str)
data_preprocessing/math_util/__init__.py:82
↓ 1 callers
Function
_strip_string
(string)
training/verl/utils/reward_score/evaluation_utils/math_util/math_normalize.py:96
↓ 1 callers
Function
_strip_string
(string)
data_preprocessing/math_util/math_normalize.py:96
↓ 1 callers
Method
_switch_chat_template
(self, data: DataProto)
training/verl/workers/fsdp_workers.py:745
↓ 1 callers
Method
_switch_chat_template
(self, data: DataProto)
training/verl/workers/fsdp_workers.py:967
↓ 1 callers
Function
_sympy_parse
Parses an expression with sympy.
training/verl/utils/reward_score/evaluation_utils/math_util/__init__.py:24
↓ 1 callers
Function
_sympy_parse
Parses an expression with sympy.
data_preprocessing/math_util/__init__.py:24
↓ 1 callers
Function
_test
()
eval/Math/Qwen25-Math/evaluation/python_executor.py:202
↓ 1 callers
Function
_test_extract_answer
()
eval/Math/Qwen25-Math/evaluation/parser.py:740
↓ 1 callers
Function
_test_generate_completions
()
eval/Math/Qwen25-Math/evaluation/model_utils.py:203
↓ 1 callers
Function
_test_math_equal
()
eval/utils/grader.py:426
↓ 1 callers
Function
_test_math_equal
()
eval/Math/Qwen25-Math/evaluation/grader.py:351
↓ 1 callers
Function
_test_math_equal
()
data_preprocessing/math_util/grader.py:426
↓ 1 callers
Function
_test_str_to_trajectory
()
eval/Math/Qwen25-Math/evaluation/trajectory.py:120
↓ 1 callers
Method
_verify_args
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/config.py:271
↓ 1 callers
Method
_verify_args
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/config.py:348
↓ 1 callers
Method
_verify_args
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/config.py:401
↓ 1 callers
Method
_verify_args
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:172
↓ 1 callers
Method
_verify_cache_dtype
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/config.py:276
↓ 1 callers
Method
_verify_load_format
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/config.py:91
↓ 1 callers
Method
_verify_load_format
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/config.py:232
↓ 1 callers
Method
_verify_load_format
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/config.py:186
↓ 1 callers
Method
accent_symbol
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:828
↓ 1 callers
Method
add_cli_args
Shared CLI arguments for vLLM engine.
training/verl/third_party/vllm/vllm_v_0_3_1/arg_utils.py:61
↓ 1 callers
Method
add_to_buffer
(self, batch, batch_size, n_samples)
training/verl/trainer/ppo/ray_trainer.py:693
↓ 1 callers
Method
analyze_solutions
(attempts: List[str], ground_truth)
data_preprocessing/stage4_judge.py:206
↓ 1 callers
Function
apply_rotary_pos_emb
(q, k, cos, sin, position_ids)
training/verl/models/llama/megatron/layers/parallel_attention.py:123
↓ 1 callers
Function
apply_rotary_pos_emb_rmpad_flash
(q, k, cos, sin, cu_seqlens, max_seqlen)
training/verl/models/llama/megatron/layers/parallel_attention.py:320
↓ 1 callers
Function
are_equal_under_sympy
(ground_truth_normalized: str, given_normalized: str)
training/verl/utils/reward_score/evaluation_utils/math_util/__init__.py:207
↓ 1 callers
Function
are_equal_under_sympy
(ground_truth_normalized: str, given_normalized: str)
data_preprocessing/math_util/__init__.py:207
↓ 1 callers
Function
broadcast_params
(module)
training/verl/models/llama/megatron/checkpoint_utils/llama_loader.py:66
↓ 1 callers
Function
build_memory_reference
Build the memory references. The memory buffers are built using the build_memory_buffer API. This API will allocate a weight buffer pointer to the
training/verl/utils/memory_buffer.py:113
↓ 1 callers
Function
build_runner
(args, model: LanguageModel)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/runner/runner_utils.py:4
↓ 1 callers
Function
call_method
(method, inputs)
training/verl/utils/reward_score/evaluation_utils/code_util/testing_util.py:642
↓ 1 callers
Function
call_with_timeout
(func, *args, timeout=1, **kwargs)
eval/Math/Qwen25-Math/evaluation/grader.py:337
↓ 1 callers
Method
chat_complete
(self, messages)
data_preprocessing/stage4_judge.py:124
↓ 1 callers
Function
chdir
(root)
eval/utils/execution.py:144
↓ 1 callers
Function
chdir
(root)
eval/utils/execution_leetcode.py:645
↓ 1 callers
Function
chdir
(root)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/utils_execute.py:175
↓ 1 callers
Method
check_consistency
Check the consistency of the DataProto. Mainly for batch and non_tensor_batch We expose this function as a public one so that user can call th
training/verl/protocol.py:154
↓ 1 callers
Function
check_correctness
Evaluates the functional correctness of a completion by running the test suite provided in the problem. :param completion_id: an optiona
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/utils_execute.py:64
↓ 1 callers
Function
check_correctness
Check correctness of code generation with a global timeout. The global timeout is to catch some extreme/rare cases not handled by the timeouts
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/compute_code_generation_metrics.py:26
↓ 1 callers
Method
check_health
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:181
↓ 1 callers
Method
check_health
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:175
↓ 1 callers
Method
check_health
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py:165
↓ 1 callers
Function
check_testcase_output
(testcase_str, expected_output)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/compute_test_output_prediction_metrics.py:39
↓ 1 callers
Function
clean_units
Clean the units in the number.
eval/Math/Qwen25-Math/evaluation/parser.py:434
↓ 1 callers
Function
code_execution_metrics
( samples, generations, )
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/compute_code_execution_metrics.py:25
↓ 1 callers
Function
collect_dp_compute
(worker_group, output)
training/verl/single_controller/base/decorator.py:265
↓ 1 callers
Function
collect_megatron_compute
Only collect the data from the tp=0 and pp=last and every dp ranks
training/verl/single_controller/base/decorator.py:103
↓ 1 callers
Function
collect_megatron_pp_as_dp
treat pp as dp. Only collect data on tp=0
training/verl/single_controller/base/decorator.py:209
↓ 1 callers
Function
combine_results
()
eval/utils/evaluation.py:93
↓ 1 callers
Function
combine_results
( scenario: Scenario, results: list[list[str]], model: LanguageModel, cot_code_execution: bool
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/runner/scenario_router.py:79
↓ 1 callers
Function
compare
(actual, expected, symbolically=False)
eval/Math/Qwen25-Math/evaluation/latex2sympy/tests/context.py:65
↓ 1 callers
Function
compare_ans
(ans_p_str, ans_l_str, is_strict=False)
eval/Math/Qwen25-Math/evaluation/math_utils.py:210
↓ 1 callers
Function
compare_numerical_ans
(ans_p, ans_l)
eval/Math/Qwen25-Math/evaluation/math_utils.py:29
↓ 1 callers
Method
compute_reward
Computing reward given input_ids. The transformers should output a tensor with shape [batch_size, sequence_length], and the value at [EOS]
training/verl/workers/reward_model/base.py:29
↓ 1 callers
Function
compute_scores
(args)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/compute_scores.py:72
↓ 1 callers
Method
compute_values
(self, data: DataProto)
training/verl/workers/fsdp_workers.py:587
↓ 1 callers
Function
concat_dict_to_str
(dict: Dict, step)
training/verl/utils/logger/aggregate_logger.py:24
↓ 1 callers
Function
construct_prompt
(example, data_name, args)
eval/Math/Qwen25-Math/evaluation/utils.py:168
↓ 1 callers
Function
convert_binom
(binom)
eval/Math/Qwen25-Math/evaluation/latex2sympy/latex2sympy2.py:788
↓ 1 callers
Function
convert_exp
(exp)
eval/Math/Qwen25-Math/evaluation/latex2sympy/latex2sympy2.py:542
↓ 1 callers
Function
convert_func
(func)
eval/Math/Qwen25-Math/evaluation/latex2sympy/latex2sympy2.py:794
↓ 1 callers
Function
convert_pi_to_number
(code_string)
eval/Math/Qwen25-Math/evaluation/parser.py:437
↓ 1 callers
Function
convert_postfix
(postfix)
eval/Math/Qwen25-Math/evaluation/latex2sympy/latex2sympy2.py:503
↓ 1 callers
Function
convert_postfix_list
(arr, i=0)
eval/Math/Qwen25-Math/evaluation/latex2sympy/latex2sympy2.py:460
↓ 1 callers
Function
convert_word_number
(text: str)
eval/Math/Qwen25-Math/evaluation/parser.py:65
↓ 1 callers
Function
count_unknown_letters_in_expr
(expr: str)
training/verl/utils/reward_score/evaluation_utils/math_util/__init__.py:184
↓ 1 callers
Function
count_unknown_letters_in_expr
(expr: str)
data_preprocessing/math_util/__init__.py:184
↓ 1 callers
Method
create_aops_forum_prompt
(self, problem: str)
data_preprocessing/stage4_judge.py:75
↓ 1 callers
Method
create_cnk12_prompt
(self, problem: str)
data_preprocessing/stage4_judge.py:55
↓ 1 callers
Method
create_engine_config
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/arg_utils.py:70
↓ 1 callers
Method
create_engine_config
( self, )
training/verl/third_party/vllm/vllm_v_0_5_4/arg_utils.py:264
↓ 1 callers
Method
create_engine_config
( self, )
training/verl/third_party/vllm/vllm_v_0_4_2/arg_utils.py:230
↓ 1 callers
Method
create_engine_configs
( self, )
training/verl/third_party/vllm/vllm_v_0_3_1/arg_utils.py:185
↓ 1 callers
Function
create_filter_prompt
(item)
data_preprocessing/stage2_format_choice.py:79
↓ 1 callers
Function
create_huggingface_actor
Args: model_name: actor_override_config_kwargs: Returns:
training/verl/utils/model.py:58
↓ 1 callers
Method
create_olympiads_prompt
(self, problem: str)
data_preprocessing/stage4_judge.py:95
↓ 1 callers
Function
create_question_prompt
(item)
data_preprocessing/stage2_format_choice.py:10
↓ 1 callers
Function
create_solution_prompt
(item)
data_preprocessing/stage2_format_choice.py:50
↓ 1 callers
Function
create_tempdir
()
eval/utils/execution.py:112
↓ 1 callers
Function
create_tempdir
()
eval/utils/execution_leetcode.py:613
↓ 1 callers
Function
create_tempdir
()
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/utils_execute.py:143
↓ 1 callers
Function
create_worker_group_register_center
(name, info)
training/verl/single_controller/base/register_center/ray.py:28
↓ 1 callers
Function
custom_compare_
(output, ground_truth)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/testing_util.py:629
↓ 1 callers
Function
custom_compare_
(output, ground_truth)
training/verl/utils/reward_score/evaluation_utils/code_util/testing_util.py:620
↓ 1 callers
Function
debug
(idx)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/old_results_check.py:19
← previous
next →
601–700 of 2,604, ranked by callers