MCPcopy Create free account

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

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

Methodoffload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/worker.py:283
Methodoffload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/llm.py:238
Methodoffload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/llm_engine_sp.py:327
Methodoffload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:206
Methodoffload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/worker.py:275
Methodoffload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/llm.py:305
Methodoffload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/llm_engine_sp.py:282
Methodoffload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py:171
Methodoffload_model_weights
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/worker.py:246
Functiononly_until_first_boxed_from_tokens
(string, tokens)
eval/utils/util.py:43
Functionpad_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
Methodpad_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
Methodpad_token_id
(self)
training/verl/third_party/vllm/vllm_v_0_3_1/tokenizer.py:67
Methodpad_token_id
(self)
training/verl/third_party/vllm/vllm_v_0_6_3/tokenizer.py:35
Methodpad_token_id
(self)
training/verl/third_party/vllm/vllm_v_0_5_4/tokenizer.py:72
Methodpad_token_id
(self)
training/verl/third_party/vllm/vllm_v_0_4_2/tokenizer.py:72
Functionparallel_put
(data_list, max_workers=None)
training/verl/utils/ray_utils.py:23
Functionparallel_weight_loader
Parallel Linear weight loader.
training/verl/third_party/vllm/vllm_v_0_3_1/weight_loaders.py:22
Functionparallel_weight_loader
Parallel Linear weight loader.
training/verl/third_party/vllm/vllm_v_0_6_3/megatron_weight_loaders.py:26
Functionparallel_weight_loader
Parallel Linear weight loader.
training/verl/third_party/vllm/vllm_v_0_5_4/megatron_weight_loaders.py:27
Functionparallel_weight_loader
Parallel Linear weight loader.
training/verl/third_party/vllm/vllm_v_0_4_2/megatron_weight_loaders.py:27
Functionpercentage_to_fraction
(text)
eval/Math/Qwen25-Math/evaluation/math_utils.py:63
Methodpin_lora
(self, lora_id: int)
training/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:196
Methodpin_lora
(self, lora_id: int)
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:191
Methodpin_prompt_adapter
(self, prompt_adapter_id: int)
training/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:200
Methodpin_prompt_adapter
(self, prompt_adapter_id: int)
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:195
Functionpost_process_logits
(input_ids, logits, temperature, top_k, top_p)
training/verl/utils/torch_functional.py:360
Methodpostfix
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2267
Methodpostfix
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2348
Methodpostfix_nofunc
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2351
Methodpostfix_op
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2425
Methodpostfix_op
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:2478
Functionpostprocess_completions
(completion_list)
eval/utils/python_interpreter.py:182
Methodpostprocess_data
(self, data: DataProto)
training/verl/workers/hybrid_engine/fsdp_vllm.py:93
Methodpostprocess_data
(self, data: DataProto)
training/verl/workers/hybrid_engine/megatron_vllm.py:394
Methodpp_group
(self)
training/verl/workers/hybrid_engine/megatron_vllm.py:203
Methodpp_models
(self)
training/verl/workers/hybrid_engine/megatron_vllm.py:207
Methodpp_rank
(self)
training/verl/workers/hybrid_engine/megatron_vllm.py:199
Methodpp_size
(self)
training/verl/single_controller/base/megatron/worker_group.py:46
Methodpp_size
(self)
training/verl/workers/hybrid_engine/megatron_vllm.py:195
Functionprepare_decoder_attention_mask
(attention_mask, input_shape, inputs_embeds)
training/verl/utils/torch_functional.py:435
Methodpreprocess_data
(self, data: DataProto)
training/verl/workers/hybrid_engine/fsdp_vllm.py:84
Methodpreprocess_data
(self, data: DataProto)
training/verl/workers/hybrid_engine/megatron_vllm.py:378
Functionprocess
(iter)
training/verl/utils/debug/trajectory_tracker.py:94
Functionprocess_completion
(completion, task, reference)
training/verl/utils/reward_score/prime.py:14
Functionput_data
(index, data)
training/verl/utils/ray_utils.py:25
Functionpytest_generate_tests
(metafunc)
eval/Math/Qwen25-Math/evaluation/latex2sympy/tests/all_good_test.py:40
Functionpytest_generate_tests
(metafunc)
eval/Math/Qwen25-Math/evaluation/latex2sympy/tests/all_bad_test.py:5
Functionqwen2_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
Functionqwen2_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
Functionqwen2_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
Functionqwen2vl_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
Methodread
(self, *args, **kwargs)
eval/utils/execution_leetcode.py:626
Functionread_jsonl_file
(file_path)
eval/Math/math/evaluate_math.py:26
Methodreadable
Returns True if the IO object can be read.
eval/utils/execution.py:134
Methodreadable
Returns True if the IO object can be read.
eval/utils/execution_leetcode.py:635
Methodreadable
Returns True if the IO object can be read.
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/utils_execute.py:165
Methodreadline
(self, *args, **kwargs)
eval/utils/execution.py:128
Methodreadline
(self, *args, **kwargs)
eval/utils/execution_leetcode.py:629
Methodreadline
(self, *args, **kwargs)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/utils_execute.py:159
Methodreadlines
(self, *args, **kwargs)
eval/utils/execution.py:131
Methodreadlines
(self, *args, **kwargs)
eval/utils/execution_leetcode.py:632
Methodreadlines
(self, *args, **kwargs)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/utils_execute.py:162
Functionregister
(dispatch_mode=Dispatch.ALL_TO_ALL, execute_mode=Execute.ALL, blocking=True, materialize_futures=True)
training/verl/single_controller/base/decorator.py:394
Methodrelation
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:856
Methodrelation
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1548
Methodrelation
(self, i=None)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1801
Methodrelation_list
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:859
Methodrelation_list_content
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:1643
Methodrelation_sempred
(self, localctx, predIndex)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:6464
Functionremove_boxed
(s)
eval/Math/aime/evaluate_aime.py:57
Functionremove_boxed
(s)
eval/Math/amc/evaluate_amc.py:63
Functionremove_boxed
(s)
eval/Math/math/evaluate_math.py:55
Functionremove_boxed
(s)
training/verl/utils/reward_score/evaluation_utils/math_util/__init__.py:295
Functionremove_boxed
(s)
data_preprocessing/math_util/__init__.py:301
Methodremove_lora
(self, lora_id: int)
training/verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py:720
Methodremove_lora
(self, lora_id: int)
training/verl/third_party/vllm/vllm_v_0_3_1/worker.py:263
Methodremove_lora
(self, lora_id: int)
training/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:174
Methodremove_lora
(self, lora_id: int)
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:168
Methodremove_lora
(self, lora_id: int)
training/verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py:158
Functionremove_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
Methodremove_prompt_adapter
(self, prompt_adapter_id: int)
training/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py:204
Methodremove_prompt_adapter
(self, prompt_adapter_id: int)
training/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py:200
Methodreorder
Note that this operation is in-place
training/verl/protocol.py:444
Functionrough_compare_ans
(generation, answer)
eval/Math/Qwen25-Math/evaluation/math_utils.py:245
Functionrun
(idx)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/old_results_check.py:26
Methodrun_batch
(self, prompts: list[str])
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/runner/vllm_runner.py:41
Functionrun_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
Functionsample
()
data_preprocessing/stage4_judge.py:312
Methodsave_checkpoint
(self, checkpoint_path)
training/verl/workers/megatron_workers.py:403
Methodsave_checkpoint
(self, checkpoint_path)
training/verl/workers/megatron_workers.py:572
Methodsave_checkpoint
(self, local_path, hdfs_path=None)
training/verl/workers/fsdp_workers.py:421
Methodsave_checkpoint
(self, local_path, hdfs_path=None)
training/verl/workers/fsdp_workers.py:629
Methodsave_checkpoint
(self, local_path, hdfs_path=None)
training/verl/workers/fsdp_workers.py:1059
Functionsave_to_hdfs
(data: io.BytesIO, name, hdfs_dir, verbose)
training/verl/utils/debug/trajectory_tracker.py:33
Methodsempred
(self, localctx, ruleIndex, predIndex)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:6449
Methodseries_to_item
(ls)
training/verl/utils/dataset/sft_dataset.py:75
Methodset_additional_resource
(self, additional_resource)
training/verl/single_controller/ray/base.py:136
Methodset_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
Functionset_real
(value)
eval/Math/Qwen25-Math/evaluation/latex2sympy/latex2sympy2.py:32
← previousnext →2,301–2,400 of 2,604, ranked by callers