Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/Gen-Verse/OpenClaw-RL
/ functions
Functions
10,561 in github.com/Gen-Verse/OpenClaw-RL
⨍
Functions
10,561
◇
Types & classes
1,405
↳
Endpoints
144
Function
get_one_epoch_dataloader
Specifically one epoch to be used in an indexing job.
Megatron-LM/megatron/legacy/data/realm_dataset_utils.py:14
Function
get_open_tabs_info
(env, config: Dict[str, str])
gui-rl/desktop_env/evaluators/getters/chrome.py:623
Method
get_openai_tools_format
Get OpenAI format tool definitions Returns: List of OpenAI format tools
slime/examples/tau-bench/openai_tool_adapter.py:139
Method
get_output
Get the forward output
Megatron-LM/megatron/core/pipeline_parallel/utils.py:238
Function
get_packed_seq_params
Get PackedSeqParams for CP. Args: tokens (torch.Tensor): [batch, seq_len] input tokens. img_seq_len (int): Image sequence length.
Megatron-LM/megatron/core/models/multimodal/context_parallel.py:62
Function
get_page_info
(env, config: Dict[str, str])
gui-rl/desktop_env/evaluators/getters/chrome.py:538
Method
get_paused_avail
Compute number of paused blocks available.
Megatron-LM/megatron/core/inference/contexts/dynamic_block_allocator.py:67
Function
get_pdf_from_url
Download a PDF from a URL.
gui-rl/desktop_env/evaluators/getters/chrome.py:871
Method
get_permuted_hidden_states_by_experts
Get the permuted hidden states by instances.
Megatron-LM/megatron/core/transformer/moe/token_dispatcher.py:935
Method
get_permuted_hidden_states_by_experts
(self, hidden_states: torch.Tensor)
Megatron-LM/megatron/core/transformer/moe/token_dispatcher.py:1081
Method
get_pg_collection
()
Megatron-LM/tests/unit_tests/transformer/test_cuda_graphs.py:489
Function
get_physical_gpu_id
()
slime/slime/ray/utils.py:32
Function
get_pipeline_model_parallel_first_rank
Return the global rank of the first stage in the current rank's pipeline.
Megatron-LM/megatron/core/parallel_state.py:1678
Function
get_pipeline_model_parallel_last_rank
Return the global rank of the last stage in the current rank's pipeline.
Megatron-LM/megatron/core/parallel_state.py:1684
Function
get_pipeline_model_parallel_next_rank
Return the global rank that follows the caller in the pipeline.
Megatron-LM/megatron/core/parallel_state.py:1691
Function
get_pipeline_model_parallel_prev_rank
Return the global rank that precedes the caller in the pipeline.
Megatron-LM/megatron/core/parallel_state.py:1699
Function
get_platform
()
gui-rl/desktop_env/server/main.py:1189
Function
get_position_embedding_group
Get the position embedding group the caller rank belongs to.
Megatron-LM/megatron/core/parallel_state.py:1461
Function
get_pp_first_rank
Return the global rank of the first rank in the pipeline parallel group.
Megatron-LM/megatron/core/pipeline_parallel/utils.py:45
Function
get_pp_next_rank
Return the global rank of the next rank in the pipeline parallel group, or None if last stage.
Megatron-LM/megatron/core/pipeline_parallel/utils.py:57
Function
get_pp_prev_rank
Return the global rank of the previous rank in the pipeline parallel group, or None if first stage.
Megatron-LM/megatron/core/pipeline_parallel/utils.py:67
Method
get_problems
()
Megatron-LM/tests/unit_tests/fusions/test_fused_linear_cross_entropy.py:288
Method
get_problems
()
Megatron-LM/tests/unit_tests/fusions/test_fused_linear_cross_entropy.py:743
Method
get_problems
()
Megatron-LM/tests/unit_tests/fusions/test_fused_linear_cross_entropy.py:1229
Function
get_profile_name
Get the username from the Chrome browser. Assume the cookies are stored in the default location, not encrypted and not large in size.
gui-rl/desktop_env/evaluators/getters/chrome.py:353
Method
get_prompt
(self, validation=False)
Megatron-LM/examples/rl/environments/math/dapo_agent.py:43
Method
get_prompt
(self, validation=False)
Megatron-LM/examples/rl/environments/math/aime_agent.py:34
Method
get_prompt
(self, validation=False)
Megatron-LM/examples/rl/environments/math/bigmath_agent.py:31
Method
get_prompt
(self, validation=False)
Megatron-LM/examples/rl/environments/math/openmath_agent.py:31
Method
get_prompt
(self, validation=False)
Megatron-LM/examples/rl/environments/math/gsm8k_agent.py:49
Method
get_prompt
(self, validation=False)
Megatron-LM/examples/rl/environments/countdown/countdown_agent.py:39
Method
get_proxy_dict
Get proxy dictionary for requests library
gui-rl/desktop_env/providers/aws/proxy_pool.py:142
Method
get_pt_dataset
(cls, data_key: str)
Megatron-LM/tools/retro/cli/cli.py:168
Method
get_pt_num_chunks
Number of pretraining chunks (e.g., 32*n_samples).
Megatron-LM/tools/retro/cli/cli.py:163
Method
get_pt_num_samples
Number of pretraining samples.
Megatron-LM/tools/retro/cli/cli.py:158
Function
get_pyt_dist_save_sharded_strategy
()
Megatron-LM/tests/unit_tests/dist_checkpointing/conftest.py:24
Method
get_query_key_value_tensors
Derives `query`, `key`, `value` tensors from `hidden_states`. If `output_gate` is True, then also derives `gate` tensor. If `
Megatron-LM/megatron/core/transformer/attention.py:1184
Method
get_query_key_value_tensors
Derives `query` tensor from `hidden_states`, and `key`/`value` tensors from `key_value_states`.
Megatron-LM/megatron/core/transformer/attention.py:1436
Function
get_qwen3_5_spec
(args, config, vp_stage)
slime/slime_plugins/models/qwen3_5.py:186
Function
get_qwen3_next_spec
(args, config, vp_stage)
slime/slime_plugins/models/qwen3_next.py:196
Method
get_restored_hidden_states_by_experts
Get the restored hidden states by instances.
Megatron-LM/megatron/core/transformer/moe/token_dispatcher.py:940
Method
get_restored_hidden_states_by_experts
(self, hidden_states: torch.Tensor)
Megatron-LM/megatron/core/transformer/moe/token_dispatcher.py:1084
Function
get_retro_decoder_layer_local_spec
Retro decoder local spec (uses Megatron-Core components). A Retro decoder layer uses custom attention and bias-dropout-add operators to perfo
Megatron-LM/megatron/core/models/retro/decoder_spec.py:92
Function
get_retro_decoder_layer_te_spec
Retro decoder TE spec (uses Transformer Engine components). A Retro decoder layer uses custom attention and bias-dropout-add operators to per
Megatron-LM/megatron/core/models/retro/decoder_spec.py:58
Function
get_retro_encoder_layer_local_spec
Retro encoder local spec (uses Megatron-Core components). A Retro encoder layer uses custom attention, bias-dropout-add, and layernorm operat
Megatron-LM/megatron/core/models/retro/encoder_spec.py:86
Function
get_retro_encoder_layer_te_spec
Retro encoder TE spec (uses Transformer Engine components). A Retro encoder layer uses custom attention, bias-dropout-add, and layernorm oper
Megatron-LM/megatron/core/models/retro/encoder_spec.py:54
Function
get_reverse_idx
(idx_map)
slime/slime/utils/seqlen_balancing.py:180
Method
get_reward
(self, response, golden: dict)
Megatron-LM/examples/rl/environments/math/dapo_agent.py:50
Method
get_reward
(self, response, golden: dict)
Megatron-LM/examples/rl/environments/math/aime_agent.py:44
Method
get_reward
(self, response, golden: dict)
Megatron-LM/examples/rl/environments/math/bigmath_agent.py:37
Method
get_reward
(self, response, golden: dict)
Megatron-LM/examples/rl/environments/math/openmath_agent.py:37
Method
get_reward
(self, response, golden: dict)
Megatron-LM/examples/rl/environments/math/gsm8k_agent.py:56
Method
get_reward
(self, response, golden: dict)
Megatron-LM/examples/rl/environments/countdown/countdown_agent.py:44
Method
get_reward_rollouts
Distribute rollouts across sub-agents according to weights.
Megatron-LM/megatron/rl/agent/weighted_multi_task.py:159
Method
get_reward_rollouts
(self, request: RolloutRequest)
Megatron-LM/megatron/rl/agent/api.py:122
Method
get_reward_rollouts
(self, request: RolloutRequest)
Megatron-LM/megatron/rl/agent/api.py:156
Function
get_rollout_data
(request: Request)
slime/slime_plugins/rollout_buffer/buffer.py:278
Method
get_rollout_engines_and_lock
(self, include_prm=False)
slime/slime/ray/rollout.py:135
Method
get_rotary_pos_emb
(transformer_module, transformer_input)
Megatron-LM/megatron/core/transformer/cuda_graphs.py:1581
Function
get_rule
Returns the rule as-is.
gui-rl/desktop_env/evaluators/getters/misc.py:87
Function
get_rule_based_math_reward
(item)
slime/slime_plugins/rollout_buffer/generator/base_generator.py:22
Function
get_rule_relativeTime
According to the rule definded in funciton "apply_rules_to_timeFormat", convert the relative time to absolute time. config: 'relative
gui-rl/desktop_env/evaluators/getters/misc.py:93
Method
get_samples
(self, num_samples: int)
gui-rl/gui_data_source.py:93
Method
get_samples
(self, num_samples: int)
gui-rl/gui_data_source.py:233
Method
get_samples
(self, num_samples)
slime/slime/rollout/data_source.py:84
Method
get_samples
Return num_samples samples
slime/slime/rollout/data_source.py:166
Function
get_samples_mapping
Get a list that maps a sample index to a starting sentence index, end sentence index, and length
Megatron-LM/megatron/legacy/data/dataset_utils.py:641
Function
get_score
(x)
Megatron-LM/examples/academic_paper_scripts/detxoify_lm/perspective_api.py:80
Function
get_score
(line)
Megatron-LM/examples/academic_paper_scripts/detxoify_lm/annotations/perspective_api_annotate.py:88
Function
get_scores
(lines)
Megatron-LM/examples/academic_paper_scripts/detxoify_lm/annotations/perspective_api_annotate.py:118
Function
get_screen_size
()
gui-rl/desktop_env/server/main.py:968
Method
get_sd
(val=3)
Megatron-LM/tests/unit_tests/dist_checkpointing/test_checkpointable.py:31
Function
get_sequence_packing_log_info
Get logging information for sequence packing mode.
Megatron-LM/megatron/rl/rl_utils.py:2369
Function
get_sequence_packing_tensorboard_metrics
Get tensorboard metrics for sequence packing mode.
Megatron-LM/megatron/rl/rl_utils.py:2376
Method
get_shard_fp32_from_fp8
Traverse the param groups and collect the fp8 params, their corresponding main params and the starting offsets of the main pa
Megatron-LM/megatron/core/optimizer/distrib_optimizer.py:2349
Method
get_sharded_state_dict
(base=0)
Megatron-LM/tests/unit_tests/dist_checkpointing/test_serialization.py:372
Function
get_shortcuts_on_desktop
(env, config: Dict[str, str])
gui-rl/desktop_env/evaluators/getters/chrome.py:1062
Method
get_special_tokens
Get special tokens.
Megatron-LM/megatron/training/tokenizer/multimodal_tokenizer.py:313
Method
get_special_tokens
Get special tokens.
Megatron-LM/megatron/training/tokenizer/sft_tokenizer.py:159
Method
get_state_dict
()
Megatron-LM/tests/unit_tests/dist_checkpointing/test_mapping.py:150
Method
get_state_dict
(fill_val=1)
Megatron-LM/tests/unit_tests/dist_checkpointing/test_fp8.py:84
Function
get_static_inference_engine
Get the relevant backend for running inference. This function will automatically choose the TRTLLMBackend when possible, and default to Mcore
Megatron-LM/megatron/rl/inference/megatron.py:47
Method
get_stats
Get proxy pool statistics
gui-rl/desktop_env/providers/aws/proxy_pool.py:165
Function
get_swin
(drop_path_rate=0.3, output_avg=False)
Megatron-LM/megatron/legacy/model/vision/swin_backbone.py:605
Method
get_system_commands
(self, screen: Screen)
swe-rl/mini-swe-agent/src/minisweagent/agents/interactive_textual.py:400
Method
get_tag
(self)
slime/setup.py:19
Method
get_template_vars
(self)
swe-rl/mini-swe-agent/src/minisweagent/__init__.py:50
Method
get_template_vars
(self)
swe-rl/mini-swe-agent/src/minisweagent/__init__.py:60
Method
get_template_vars
(self)
swe-rl/mini-swe-agent/src/minisweagent/environments/local.py:37
Method
get_template_vars
(self)
swe-rl/mini-swe-agent/src/minisweagent/environments/singularity.py:60
Method
get_template_vars
(self)
swe-rl/mini-swe-agent/src/minisweagent/environments/docker.py:52
Method
get_template_vars
(self)
swe-rl/mini-swe-agent/src/minisweagent/environments/extra/swerex_docker.py:46
Method
get_template_vars
(self)
swe-rl/mini-swe-agent/src/minisweagent/models/test_models.py:41
Method
get_template_vars
(self)
swe-rl/mini-swe-agent/src/minisweagent/models/extra/roulette.py:30
Method
get_template_vars
(self)
swe-rl/mini-swe-agent/tests/run/test_swebench.py:392
Method
get_ten
(dtype: str = 'fp8')
Megatron-LM/tests/unit_tests/dist_checkpointing/test_fp8.py:50
Function
get_tensor_and_context_parallel_rank
Return caller's rank in the joint tensor-model-parallel and context-parallel group.
Megatron-LM/megatron/core/parallel_state.py:1763
Function
get_tensor_and_context_parallel_world_size
Return world size for the tensor and context-parallel group.
Megatron-LM/megatron/core/parallel_state.py:1755
Function
get_tensor_and_data_parallel_group
Get the tensor- and data-parallel group the caller rank belongs to.
Megatron-LM/megatron/core/parallel_state.py:1494
Function
get_terminal_output
()
gui-rl/desktop_env/server/main.py:348
← previous
next →
7,801–7,900 of 10,561, ranked by callers