MCPcopy Create free account

hub / github.com/Gen-Verse/OpenClaw-RL / functions

Functions10,561 in github.com/Gen-Verse/OpenClaw-RL

Method_change_wallpaper_setup
(self, path: str)
gui-rl/desktop_env/controllers/setup.py:274
Method_check_and_clean
(self)
gui-rl/desktop_env/providers/aws/manager.py:223
Method_check_and_clean
(self)
gui-rl/desktop_env/providers/volcengine/manager.py:320
Method_check_and_clean
(self)
gui-rl/desktop_env/providers/aliyun/manager.py:303
Method_chrome_close_tabs_setup
(self, urls_to_close: List[str])
gui-rl/desktop_env/controllers/setup.py:648
Method_chrome_open_tabs_setup
(self, urls_to_open: List[str])
gui-rl/desktop_env/controllers/setup.py:599
Method_clone_if_needed
Clone if we detect incontiguous storage for CPU tensors Makes sure we perform a `clone` only if we detect incontiguous storage,
Megatron-LM/megatron/core/dist_checkpointing/strategies/filesystem_async.py:136
Method_close_window_setup
(self, window_name: str, strict: bool = False, by_class: bool = False)
gui-rl/desktop_env/controllers/setup.py:508
Method_collect_main_grad_data_for_unscaling
Note: this should be equivalent to the float-16 optimizer's method, but written differently, so the two should be combined.
Megatron-LM/megatron/core/optimizer/distrib_optimizer.py:2284
Method_command_setup
(self, command: List[str], **kwargs)
gui-rl/desktop_env/controllers/setup.py:470
Method_compare
(srcs, tgts, names, parallelism)
Megatron-LM/megatron/core/transformer/attention.py:1143
Function_compare_floats
Internal function that implements the default compare_func. Check the validate_result() method of the RerunStateMachine class for details.
Megatron-LM/megatron/core/rerun_state_machine.py:1326
Function_compute_prefix_cache_metrics
(args, all_samples: list[Sample])
slime/slime/ray/rollout.py:1305
Function_compute_spec_metrics
(args, all_samples: list[Sample])
slime/slime/ray/rollout.py:1295
Method_conv_out_length
(input_length, kernel_size, stride)
Megatron-LM/tests/unit_tests/models/test_mimo_audio_submodules.py:241
Function_convert_image_to_rgb
(image)
Megatron-LM/megatron/legacy/data/multimodal_dataset.py:16
Method_copy_main_params_to_model_params
Copy main params to model params. Since this step is followed by an all-gather through the DDP's grad buffer, this method is
Megatron-LM/megatron/core/optimizer/distrib_optimizer.py:2413
Method_copy_model_grads_to_main_grads
Copy model grads to main grads. Since this step follows a reduce-scatter through the DDP's grad buffer, this method is respo
Megatron-LM/megatron/core/optimizer/distrib_optimizer.py:2370
Method_copy_model_params_to_main_params
Copy model params to main params. During finetuning, this method is used to reload the main params from the model params. Th
Megatron-LM/megatron/core/optimizer/distrib_optimizer.py:2525
Function_cpp_extention_load_helper
(name, sources, extra_cuda_flags)
Megatron-LM/megatron/legacy/fused_kernels/__init__.py:37
Method_create_1d_sharded_tensor_based_on_split
(split, content_split=None, key='a')
Megatron-LM/tests/unit_tests/dist_checkpointing/test_serialization.py:698
Method_create_1d_sharded_tensors_based_on_split
(split, content_split=None, key='a')
Megatron-LM/tests/unit_tests/dist_checkpointing/test_serialization.py:773
Function_create_axui_node
(node, nodes: set = None, depth: int = 0, bbox: tuple = None)
gui-rl/desktop_env/server/main.py:744
Function_create_pywinauto_node
(node, nodes, depth: int = 0, flag: Optional[str] = None)
gui-rl/desktop_env/server/main.py:580
Function_cross_entropy_forward_step
Simple forward step with cross-entropy loss.
Megatron-LM/tasks/finetune_utils.py:53
Method_delete_vm
(self, vm_path, region=DEFAULT_REGION)
gui-rl/desktop_env/providers/aws/manager.py:211
Method_delete_vm
(self, vm_path)
gui-rl/desktop_env/providers/volcengine/manager.py:308
Method_delete_vm
(self, vm_path)
gui-rl/desktop_env/providers/aliyun/manager.py:291
Function_disable_gc
Temporarily disables GC.
Megatron-LM/megatron/core/dist_checkpointing/strategies/async_utils.py:25
Method_does_param_require_new_bucket
Split shared embedding parameters into separate bucket if using distributed optimizer that makes use of reduce-scatters inste
Megatron-LM/megatron/core/distributed/param_and_grad_buffer.py:677
Method_download_setup
Args: files (List[Dict[str, str]]): files to download. lisf of dict like { "url": str, the url to d
gui-rl/desktop_env/controllers/setup.py:109
Function_drain_toolkit_sessions
(toolkit: Any)
terminal-rl/remote/terminal_env.py:38
Method_drop_removed_samples
Drop sample if it is marked as removed.
slime/slime/ray/rollout.py:624
Function_dummy_loss_func
(output_tensor, non_loss_data=True)
Megatron-LM/megatron/post_training/generate.py:26
Method_duplicate_kv_head
Duplicates a kv tensor along specified dimension. [hidden_dim, num_kv_heads, 1, size_per_head] -> [hidden_dim, num_kv_heads, rep, size_per
Megatron-LM/megatron/core/export/trtllm/trtllm_weights_converter/single_device_trtllm_model_weights_converter.py:155
Method_end_coalescing
(self, *a, **kw)
slime/slime/utils/reloadable_process_group.py:244
Method_ensure_list_type
(value)
Megatron-LM/examples/mimo/data/energon_avlm_task_encoder.py:109
Method_ensure_list_type
(value)
Megatron-LM/examples/mimo/data/energon_vlm_task_encoder.py:88
Function_eval_one
(idx)
openclaw-rl/oel/eval/personalization_evaluator.py:195
Function_evaluate_once
Run a single GPT-4.1 evaluation call. Returns score or -1.0 on failure.
openclaw-rl/oel/eval/personalization_evaluator.py:110
Method_evaluation
( self, prompt: str, golden: Any, request: EvaluationRequest )
Megatron-LM/megatron/rl/agent/reward_only_agent.py:161
Method_execute_with_verification_setup
Execute command with verification of results Args: command: Command to execute verification: Dict with verifi
gui-rl/desktop_env/controllers/setup.py:419
Method_extract_answer_from_text
Prefer a concise answer by pulling the last \\boxed{} chunk; fall back to the last non-empty line (capped) to avoid echoing the whole
slime/examples/geo3k_vlm_multi_turn/env_geo3k.py:110
Method_extract_balanced_json
Best-effort balanced brace extraction starting at `start` (index of an opening '{'). Keeps string-awareness to avoid terminating insi
slime/examples/geo3k_vlm_multi_turn/env_geo3k.py:125
Method_fill_in_data
(t: Union[ShardedTensor, torch.Tensor])
Megatron-LM/megatron/core/dist_checkpointing/strategies/two_stage.py:248
Function_filter_checks
( checks: List[Union[ApproximateTest, DeterministicTest]], filter_for_type_of_check )
Megatron-LM/tests/functional_tests/python_test_utils/common.py:172
Function_find_submodule
Find sub-module in model
Megatron-LM/tests/unit_tests/transformer/moe/test_upcycling.py:46
Method_format_v6_uri
(addr)
slime/slime/backends/sglang_utils/sglang_engine.py:143
Function_forward
(self, hidden_states: torch.Tensor)
slime/slime/backends/fsdp_utils/models/qwen3_moe_hf.py:9
Method_forward
(self, tokens, position_ids, attention_mask)
Megatron-LM/tools/run_vlm_text_generation.py:174
Method_forward
(self, model_inputs)
Megatron-LM/tools/bert_embedding/huggingface.py:25
Method_forward
Runs a forward pass of the model. Args: inference_input(Dict[str, Any]): The input data. Returns: The model
Megatron-LM/megatron/core/inference/model_inference_wrappers/multimodal/vlm_inference_wrapper.py:126
Method_forward
Per-chunk bias-dropout-add. Args: x_with_bias (dict): Attention output and bias tuple. residual (Tensor): Transformer
Megatron-LM/megatron/core/models/retro/encoder_attention.py:124
Method_forward
Per-chunk bias-dropout-add. Args: x_with_bias (dict): Attention output and bias, along with other Retro relevant
Megatron-LM/megatron/core/models/retro/decoder_attention.py:240
Method_forward
(self, tokens, position_ids, attention_mask)
Megatron-LM/examples/multimodal/run_text_generation.py:482
Function_forward_step_func
(data, model)
Megatron-LM/megatron/post_training/generate.py:29
Function_forward_step_func
(data_iterator, model)
Megatron-LM/tests/unit_tests/export/trtllm/test_single_device_fp8.py:82
Function_forward_step_func
(data_iterator, model)
Megatron-LM/tests/unit_tests/export/trtllm/test_distributed_fp8.py:85
Method_fp8_quantize_params
(dense_param_quantize_kwargs, expert_param_quantize_kwargs)
Megatron-LM/megatron/core/distributed/fsdp/src/megatron_fsdp/param_and_grad_buffer.py:2613
Function_full_attention_layer_ids
(self)
slime/slime/backends/sglang_utils/qwen3_5.py:281
Method_get_actual_server_args
()
slime/slime/backends/sglang_utils/sglang_engine.py:182
Method_get_backend_name
(self)
slime/slime/utils/reloadable_process_group.py:247
Method_get_fp8_enabled
()
Megatron-LM/megatron/core/transformer/cuda_graphs.py:1823
Method_get_global_buffer
(buffer_id: int)
Megatron-LM/megatron/core/distributed/fsdp/src/megatron_fsdp/param_and_grad_buffer.py:604
Method_get_gptmodel_args
Override to add MTP block spec if needed.
slime/slime_plugins/mbridge/qwen3_next.py:43
Method_get_gptmodel_args
Override to add MTP block spec if needed.
slime/slime_plugins/mbridge/mimo.py:37
Function_get_handle
()
Megatron-LM/tests/test_utils/python_scripts/auto_reminder.py:78
Method_get_layer_offset
Get the layer offset for the current pipeline stage. Deprecated: please use `get_transformer_layer_offset` instead.
Megatron-LM/megatron/core/transformer/transformer_layer.py:451
Method_get_layer_static_inputs
Get the static inputs for a layer.
Megatron-LM/megatron/core/transformer/cuda_graphs.py:1573
Function_get_mlp_module_spec
( use_te: Optional[bool] = True, num_experts: Optional[int] = None, moe_grouped_gemm: Optional[boo
Megatron-LM/megatron/core/models/gpt/gpt_layer_specs.py:511
Method_get_model_and_main_params_data_float16
Get aligned list of model and main params.
Megatron-LM/megatron/core/optimizer/distrib_optimizer.py:2302
Function_get_model_config_for_expert_location
(cls, config)
slime/slime/backends/sglang_utils/qwen3_5.py:242
Function_get_one
(idx)
openclaw-rl/oel/eval/gsm8k_personal_agent.py:285
Method_get_parallel_config
(self)
slime/slime/ray/train_actor.py:128
Method_get_param_groups
(self)
Megatron-LM/megatron/core/optimizer/optimizer.py:290
Method_get_param_state_sharded_tensors
(model_param, item_slice)
Megatron-LM/megatron/core/optimizer/distrib_optimizer.py:1698
Function_get_position_embedding_weight
Return the position-embedding weight tensor from the given model module. Args: model_module: The model module that owns the p
Megatron-LM/megatron/core/distributed/finalize_model_grads.py:151
Function_get_shared_word_embedding_weight
Return the shared word-embedding weight if it is duplicated across stages. Args: model_module: The model module from which to extract the
Megatron-LM/megatron/core/distributed/finalize_model_grads.py:132
Method_get_state
(self)
Megatron-LM/megatron/core/optimizer/optimizer.py:279
Method_get_submodules_under_cudagraphs
Get the submodules that are covered by cudagraphs.
Megatron-LM/megatron/core/transformer/transformer_layer.py:800
Method_get_te_cuda_graph_replay_args
Helper function to get tensor arguments for TE CUDA graph.
Megatron-LM/megatron/core/transformer/transformer_layer.py:951
Method_get_token_mask
Abstract method implementation 100% of the time, replace the token id with mask token id. Args: numpy_random_state (Rand
Megatron-LM/megatron/core/datasets/t5_dataset.py:327
Method_get_token_mask
Abstract method implementation 80% of the time, replace the token id with mask token id. 10% of the time, replace token id with a ran
Megatron-LM/megatron/core/datasets/bert_dataset.py:173
Method_get_transformer_layer_spec
Gets the transformer layer specification. Creates and returns a specification for the transformer layers based on the curren
slime/slime_plugins/mbridge/glm4.py:64
Method_get_weight_tensors
Get the weight tensors of the module.
Megatron-LM/megatron/core/extensions/transformer_engine.py:1421
Method_googledrive_setup
Clean google drive space (eliminate the impact of previous experiments to reset the environment) @args: config(Dict[str, Any]): c
gui-rl/desktop_env/controllers/setup.py:690
Method_grad_acc
Accumulate the gradient in the main_grad buffer. Utilizes the patched main_grad property of the parameter to allocate
Megatron-LM/megatron/core/distributed/fsdp/src/megatron_fsdp/megatron_fsdp.py:513
Function_grade_eval_output
(instance: dict, git_patch: str, apply_output: str, eval_output: str)
swe-rl/generate_with_swe_trajectory.py:405
Function_handle_one
(task)
slime/slime/backends/megatron_utils/update_weight/hf_weight_iterator_bridge.py:45
Method_handle_request
(self, body, session_id, turn_type, session_done)
openclaw-tinker/api_server.py:527
Method_handle_request
(self, body, session_id, turn_type, session_done)
openclaw-tinker/api_server.py:685
Method_handle_request
(self, body, session_id, turn_type, session_done)
openclaw-tinker/api_server.py:888
Function_handler
(signum, frame)
Megatron-LM/megatron/core/inference/unified_memory.py:55
Method_handler
Thread function for the controller. It is a tcp-server that listens on a port. Uses HTTP protocol. If connected to it using curl, it
Megatron-LM/megatron/core/utils.py:1674
Method_has_rollout_log_probs
(batch)
slime/slime/backends/fsdp_utils/actor.py:648
Method_health_monitor_loop
(self)
slime/slime/utils/health_monitor.py:106
Function_hf_dataset_forword_loop_func
(model)
Megatron-LM/examples/post_training/modelopt/prune.py:206
Function_hf_dataset_forword_loop_func
(model)
Megatron-LM/examples/post_training/modelopt/quantize.py:196
Function_hybrid_gdn_config
(self)
slime/slime/backends/sglang_utils/qwen3_5.py:314
Function_indices_to_multihot_kernel
Triton kernel for converting indices to multihot representation. Input: indices: [num_of_tokens, topk] probs_in_indices: [nu
Megatron-LM/megatron/core/fusions/fused_indices_converter.py:32
← previousnext →6,301–6,400 of 10,561, ranked by callers