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
offload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/worker.py:283
Method
offload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/llm.py:238
Method
offload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/llm_engine_sp.py:327
Method
offload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:206
Method
offload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/worker.py:275
Method
offload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/llm.py:305
Method
offload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/llm_engine_sp.py:282
Method
offload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py:171
Method
offload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/worker.py:246
Function
only_until_first_boxed_from_tokens
(string, tokens)
eval/utils/util.py:43
Function
pad_packed_inputs
pad the tokens such that the total length is a multiple of size. This function is useful when applying sequence parallel and context parallel
training/verl/utils/model.py:299
Method
pad_token_id
`Optional[int]`: Id of the padding token in the vocabulary. Returns `None` if the token has not been set.
training/verl/workers/rollout/tokenizer.py:36
Method
pad_token_id
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/tokenizer.py:67
Method
pad_token_id
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/tokenizer.py:35
Method
pad_token_id
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/tokenizer.py:72
Method
pad_token_id
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/tokenizer.py:72
Function
parallel_put
(data_list, max_workers=None)
training/verl/utils/ray_utils.py:23
Function
parallel_weight_loader
Parallel Linear weight loader.
training/verl/third_party/vllm/vllm_v_0_3_1/weight_loaders.py:22
Function
parallel_weight_loader
Parallel Linear weight loader.
training/verl/third_party/vllm/vllm_v_0_6_3/megatron_weight_loaders.py:26
Function
parallel_weight_loader
Parallel Linear weight loader.
training/verl/third_party/vllm/vllm_v_0_5_4/megatron_weight_loaders.py:27
Function
parallel_weight_loader
Parallel Linear weight loader.
training/verl/third_party/vllm/vllm_v_0_4_2/megatron_weight_loaders.py:27
Function
percentage_to_fraction
(text)
eval/Math/Qwen25-Math/evaluation/math_utils.py:63
Method
pin_lora
(self, lora_id: int)
training/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:196
Method
pin_lora
(self, lora_id: int)
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:191
Method
pin_prompt_adapter
(self, prompt_adapter_id: int)
training/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:200
Method
pin_prompt_adapter
(self, prompt_adapter_id: int)
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:195
Function
post_process_logits
(input_ids, logits, temperature, top_k, top_p)
training/verl/utils/torch_functional.py:360
Method
postfix
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2267
Method
postfix
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2348
Method
postfix_nofunc
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2351
Method
postfix_op
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2425
Method
postfix_op
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2478
Function
postprocess_completions
(completion_list)
eval/utils/python_interpreter.py:182
Method
postprocess_data
(self, data: DataProto)
training/verl/workers/hybrid_engine/fsdp_vllm.py:93
Method
postprocess_data
(self, data: DataProto)
training/verl/workers/hybrid_engine/megatron_vllm.py:394
Method
pp_group
(self)
training/verl/workers/hybrid_engine/megatron_vllm.py:203
Method
pp_models
(self)
training/verl/workers/hybrid_engine/megatron_vllm.py:207
Method
pp_rank
(self)
training/verl/workers/hybrid_engine/megatron_vllm.py:199
Method
pp_size
(self)
training/verl/single_controller/base/megatron/worker_group.py:46
Method
pp_size
(self)
training/verl/workers/hybrid_engine/megatron_vllm.py:195
Function
prepare_decoder_attention_mask
(attention_mask, input_shape, inputs_embeds)
training/verl/utils/torch_functional.py:435
Method
preprocess_data
(self, data: DataProto)
training/verl/workers/hybrid_engine/fsdp_vllm.py:84
Method
preprocess_data
(self, data: DataProto)
training/verl/workers/hybrid_engine/megatron_vllm.py:378
Function
process
(iter)
training/verl/utils/debug/trajectory_tracker.py:94
Function
process_completion
(completion, task, reference)
training/verl/utils/reward_score/prime.py:14
Function
put_data
(index, data)
training/verl/utils/ray_utils.py:25
Function
pytest_generate_tests
(metafunc)
eval/Math/Qwen25-Math/evaluation/latex2sympy/tests/all_good_test.py:40
Function
pytest_generate_tests
(metafunc)
eval/Math/Qwen25-Math/evaluation/latex2sympy/tests/all_bad_test.py:5
Function
qwen2_dtensor_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_6_3/dtensor_weight_loaders.py:151
Function
qwen2_dtensor_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_5_4/dtensor_weight_loaders.py:154
Function
qwen2_dtensor_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_4_2/dtensor_weight_loaders.py:164
Function
qwen2vl_dtensor_weight_loader
(actor_weights: Dict, vllm_model: nn.Module)
training/verl/third_party/vllm/vllm_v_0_6_3/dtensor_weight_loaders.py:188
Method
read
(self, *args, **kwargs)
eval/utils/execution_leetcode.py:626
Function
read_jsonl_file
(file_path)
eval/Math/math/evaluate_math.py:26
Method
readable
Returns True if the IO object can be read.
eval/utils/execution.py:134
Method
readable
Returns True if the IO object can be read.
eval/utils/execution_leetcode.py:635
Method
readable
Returns True if the IO object can be read.
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/utils_execute.py:165
Method
readline
(self, *args, **kwargs)
eval/utils/execution.py:128
Method
readline
(self, *args, **kwargs)
eval/utils/execution_leetcode.py:629
Method
readline
(self, *args, **kwargs)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/utils_execute.py:159
Method
readlines
(self, *args, **kwargs)
eval/utils/execution.py:131
Method
readlines
(self, *args, **kwargs)
eval/utils/execution_leetcode.py:632
Method
readlines
(self, *args, **kwargs)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/utils_execute.py:162
Function
register
(dispatch_mode=Dispatch.ALL_TO_ALL, execute_mode=Execute.ALL, blocking=True, materialize_futures=True)
training/verl/single_controller/base/decorator.py:394
Method
relation
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:856
Method
relation
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1548
Method
relation
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1801
Method
relation_list
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:859
Method
relation_list_content
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1643
Method
relation_sempred
(self, localctx, predIndex)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:6464
Function
remove_boxed
(s)
eval/Math/aime/evaluate_aime.py:57
Function
remove_boxed
(s)
eval/Math/amc/evaluate_amc.py:63
Function
remove_boxed
(s)
eval/Math/math/evaluate_math.py:55
Function
remove_boxed
(s)
training/verl/utils/reward_score/evaluation_utils/math_util/__init__.py:295
Function
remove_boxed
(s)
data_preprocessing/math_util/__init__.py:301
Method
remove_lora
(self, lora_id: int)
training/verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:720
Method
remove_lora
(self, lora_id: int)
training/verl/third_party/vllm/vllm_v_0_3_1/worker.py:263
Method
remove_lora
(self, lora_id: int)
training/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:174
Method
remove_lora
(self, lora_id: int)
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:168
Method
remove_lora
(self, lora_id: int)
training/verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py:158
Function
remove_pad_token
Remove the pad token. Args: input_ids shape: [bs, seq_length] attention_mask shape: [bs, seq_length] Returns: no_pa
training/verl/utils/torch_functional.py:269
Method
remove_prompt_adapter
(self, prompt_adapter_id: int)
training/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:204
Method
remove_prompt_adapter
(self, prompt_adapter_id: int)
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:200
Method
reorder
Note that this operation is in-place
training/verl/protocol.py:444
Function
rough_compare_ans
(generation, answer)
eval/Math/Qwen25-Math/evaluation/math_utils.py:245
Function
run
(idx)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/old_results_check.py:26
Method
run_batch
(self, prompts: list[str])
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/runner/vllm_runner.py:41
Function
run_func_in_process
Runs the provided function in a separate process with the supplied args and kwargs. The args, kwargs, and return values must all be pickl
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/utils/multiprocess.py:33
Function
sample
()
data_preprocessing/stage4_judge.py:312
Method
save_checkpoint
(self, checkpoint_path)
training/verl/workers/megatron_workers.py:403
Method
save_checkpoint
(self, checkpoint_path)
training/verl/workers/megatron_workers.py:572
Method
save_checkpoint
(self, local_path, hdfs_path=None)
training/verl/workers/fsdp_workers.py:421
Method
save_checkpoint
(self, local_path, hdfs_path=None)
training/verl/workers/fsdp_workers.py:629
Method
save_checkpoint
(self, local_path, hdfs_path=None)
training/verl/workers/fsdp_workers.py:1059
Function
save_to_hdfs
(data: io.BytesIO, name, hdfs_dir, verbose)
training/verl/utils/debug/trajectory_tracker.py:33
Method
sempred
(self, localctx, ruleIndex, predIndex)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:6449
Method
series_to_item
(ls)
training/verl/utils/dataset/sft_dataset.py:75
Method
set_additional_resource
(self, additional_resource)
training/verl/single_controller/ray/base.py:136
Method
set_input_tensor
Set input tensor to be used instead of forward()'s input. When doing pipeline parallelism the input from the previous stage comes fro
training/verl/models/llama/megatron/modeling_llama_megatron.py:536
Function
set_real
(value)
eval/Math/Qwen25-Math/evaluation/latex2sympy/latex2sympy2.py:32
← previous
next →
2,301–2,400 of 2,604, ranked by callers