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
Method
read
Read bytes into a numpy array. Let `size` be the `count` * `DType.size(dtype)`. If the requested span of bytes [`offset`, `offset` +
Megatron-LM/megatron/core/datasets/indexed_dataset.py:484
Method
read
(self, dtype: Type[numpy.number], count: int, offset: int)
Megatron-LM/megatron/core/datasets/indexed_dataset.py:549
Method
read_data_into_queue
()
slime/slime_plugins/rollout_buffer/generator/base_generator.py:195
Method
read_frame
(self, video_path, bound=None, fps=2)
Megatron-LM/examples/multimodal/evaluation/evaluation_datasets.py:1276
Function
read_golden_values_from_json
( golden_values_path: Union[str, pathlib.Path] )
Megatron-LM/tests/functional_tests/python_test_utils/common.py:161
Method
read_metadata
(self)
slime/tools/convert_fsdp_to_hf.py:27
Method
read_metadata
(self)
slime/tools/convert_torch_dist_to_hf.py:36
Function
read_tb_logs_as_list
Reads a TensorBoard Events file from the input path, and returns the summary specified as input as a list. Args: path: str, path to t
Megatron-LM/tests/functional_tests/python_test_utils/common.py:94
Method
read_video_ours
(self, video_path, bound=None)
Megatron-LM/examples/multimodal/evaluation/evaluation_datasets.py:1285
Function
rebuild_tokenizer
(args)
Megatron-LM/megatron/training/global_vars.py:164
Method
receive_lm
Receive LM model parameters over queue and save them in self.models
Megatron-LM/tools/checkpoint/saver_base.py:353
Method
receive_model
(self)
Megatron-LM/tools/checkpoint/saver_core.py:53
Method
receive_model
(self)
Megatron-LM/tools/checkpoint/saver_llava.py:359
Method
record_model_turn
( self, turn_idx: int, *, assistant_text: str, tool_calls: Optional[Li
terminal-rl/agent/prm_agent.py:109
Method
record_policy_turn
(self, *, action_text: str, response: str, screenshot_bytes: bytes)
gui-rl/agents/qwen3vl_agent.py:315
Method
record_tool_result
(self, tool_call_request: Any, raw_result: Any)
terminal-rl/rollout_agent.py:25
Method
record_tool_result
( self, turn_idx: int, tool_call_request, raw_result: Any )
terminal-rl/agent/prm_agent.py:125
Method
record_tool_result
(self, tool_call_request: Any, raw_result: Any)
terminal-rl/agent/camel_agent.py:550
Method
recover_rollout_engines
Restart any dead rollout engines and update num_new_engines for update_weights detection.
slime/slime/ray/rollout.py:200
Method
recv_anysource
(self, *a, **kw)
slime/slime/utils/reloadable_process_group.py:238
Function
reduce_scatter_last_dim_to_tensor_parallel_region
Wrapper for autograd function: forward: RS, backward AG: AG <last dim>
Megatron-LM/megatron/core/tensor_parallel/mappings.py:529
Method
reduce_scatter_tensor_coalesced
(self, *a, **kw)
slime/slime/utils/reloadable_process_group.py:223
Method
register_subclass
Register subclass for unwrapping.
Megatron-LM/megatron/rl/__init__.py:47
Method
register_submesh
Register a submesh with identifier: (*submesh, is_expert_parallel) in the mesh library.
Megatron-LM/megatron/core/distributed/fsdp/src/megatron_fsdp/utils.py:499
Method
release_memory_occupation
(self)
slime/slime/backends/sglang_utils/sglang_engine.py:358
Method
release_modifier_keys
()
gui-rl/agents/qwen35_agent.py:549
Method
release_module_parameters
(module, bwd, *unused)
Megatron-LM/megatron/core/distributed/fsdp/src/megatron_fsdp/megatron_fsdp.py:501
Method
release_params_fp8_transpose_cache
(params)
Megatron-LM/megatron/core/distributed/fsdp/src/megatron_fsdp/megatron_fsdp.py:508
Method
release_state
Release reference, this helps avoid memory leak.
Megatron-LM/megatron/core/models/common/model_chunk_schedule_plan.py:424
Method
reload_model_params
Refreshes any internal state from the current model parameters. Call whenever the parameters are changed outside of the optimizer. For
Megatron-LM/megatron/core/optimizer/optimizer.py:251
Method
reload_model_params
(self, state_dict=None)
Megatron-LM/megatron/core/optimizer/optimizer.py:492
Method
reload_model_params
(self, state_dict=None)
Megatron-LM/megatron/core/optimizer/optimizer.py:1173
Method
remaining_prompt_length
Get the length of the remaining prompt tokens.
Megatron-LM/megatron/core/inference/inference_request.py:254
Method
remove_extra_states_check
Remove _extra_state from unexpected keys. These keys are for dist ckpt compatibility with SequentialMLP.
Megatron-LM/megatron/core/transformer/moe/experts.py:222
Method
remove_sharded_tensors
Removes checkpoint files whose keys have the given prefix. Performs the following steps: 1. checks whether there are files that start
Megatron-LM/megatron/core/dist_checkpointing/strategies/torch.py:1035
Function
replace_press_less_than
(match)
gui-rl/desktop_env/desktop_env.py:45
Method
replace_screen_env_in_command
(command)
gui-rl/desktop_env/controllers/setup.py:355
Method
req_count
Returns the total number of requests.
Megatron-LM/megatron/core/inference/batch_dimensions_utils.py:120
Method
request_id
Get request id. Returns: (int) Request id.
Megatron-LM/megatron/core/inference/inference_request.py:404
Function
request_thread
()
swe-rl/mini-swe-agent/tests/agents/test_interactive_textual.py:578
Function
reset
(request: Request)
terminal-rl/router_server.py:345
Function
reset
(request: Request)
terminal-rl/remote/pool_server.py:427
Function
reset
()
gui-rl/env_pool_server.py:368
Method
reset
( self, *, task_meta: dict[str, Any], run_ctx: RunContext, timeouts: T
terminal-rl/remote/terminal_env.py:85
Method
reset
(self, task_config: Optional[Dict[str, Any]] = None, seed=None, options=None)
gui-rl/desktop_env/desktop_env.py:242
Method
reset
(self, _logger=None)
gui-rl/agents/qwen35_agent.py:101
Method
reset
(self, _logger=None)
gui-rl/agents/qwen3vl_agent.py:85
Method
reset
Reset timer.
Megatron-LM/megatron/core/timers.py:60
Method
reset
(self)
Megatron-LM/megatron/core/timers.py:90
Method
reset
Handle the processing tasks and reset the pipeline.
Megatron-LM/megatron/core/distributed/fsdp/src/megatron_fsdp/param_and_grad_buffer.py:2930
Method
reset
Reset the pipeline state.
Megatron-LM/megatron/core/distributed/fsdp/src/megatron_fsdp/param_and_grad_buffer.py:3319
Method
reset
Reset the allocator to initial state. This resets the available block count to the entire memory pool (except for the dummy block).
Megatron-LM/megatron/core/inference/contexts/dynamic_block_allocator.py:112
Method
reset
Resets the inference state for a new batch.
Megatron-LM/megatron/core/inference/contexts/static_context.py:74
Method
reset
Resets all Mamba states and frees all allocated slots.
Megatron-LM/megatron/core/inference/contexts/attention_context/mamba_metadata.py:54
Method
reset
(self)
Megatron-LM/megatron/core/inference/contexts/attention_context/mha_metadata.py:170
Method
reset
Reset the metadata.
Megatron-LM/megatron/core/inference/contexts/attention_context/metadata_base.py:26
Method
reset
(self)
slime/examples/geo3k_vlm_multi_turn/base_env.py:6
Method
reset_drop_path
(self, drop_path_rate)
Megatron-LM/megatron/legacy/model/vision/mit_backbone.py:275
Function
reset_env_vars
Reset environment variables
Megatron-LM/tests/unit_tests/conftest.py:100
Method
reset_eval_scores
(self)
openclaw-fireworks/fireworks_server.py:871
Method
reset_eval_scores
(self)
openclaw-tinker/api_server.py:345
Function
reset_global_stats
Reset global model stats and ensure exclusive access for tests that need it. This fixture should be used by any test that depends on global model
swe-rl/mini-swe-agent/tests/conftest.py:14
Method
reset_index
Delete existing index and create a new
Megatron-LM/megatron/legacy/data/realm_index.py:166
Function
resolve_artifact_config
(cluster: str)
Megatron-LM/tests/test_utils/python_scripts/recipe_parser.py:37
Function
resolve_cluster_config
(cluster: str)
Megatron-LM/tests/test_utils/python_scripts/recipe_parser.py:23
Method
resolve_tensor
(self, read_item)
Megatron-LM/tools/checkpoint/checkpoint_inspector.py:326
Method
resolve_tensor
Override to add FP8 support. Narrowing the Float8Tensor can create incontiguous tensors and there are no `copy` kernels for such case
Megatron-LM/megatron/core/dist_checkpointing/strategies/torch.py:656
Method
restore
(self, tag: str)
slime/slime/utils/tensor_backper.py:69
Method
restore
(self, tag: str)
slime/slime/utils/tensor_backper.py:99
Method
restore_custom_attrs
(module, custom_attrs)
Megatron-LM/megatron/core/distributed/torch_fully_sharded_data_parallel.py:102
Method
restore_from_cpu
Function used for RL training. Restore optimizer state tensors from CPU back to GPU for training.
Megatron-LM/megatron/core/optimizer/optimizer.py:364
Method
restore_tensor_device
Restores all tensors to their original devices, if a move is required. Using non_blocking=True allows for asynchronous copying.
Megatron-LM/megatron/core/dist_checkpointing/tensor_aware_state_dict.py:264
Method
resume
Resume/start energy monitor.
Megatron-LM/megatron/core/energy_monitor.py:54
Method
resume
(self)
Megatron-LM/megatron/rl/inference/megatron.py:259
Method
resume
(self)
Megatron-LM/megatron/rl/server/inference/inference_interface_server.py:96
Method
resume_memory_occupation
Available tags for multi-stage resume: weights, kv_cache
slime/slime/backends/sglang_utils/sglang_engine.py:362
Function
retrieve_endpoint
Endpoint that accepts queries and performs retrieval. Input format: { "queries": ["What is Python?", "Tell me about neural network
slime/examples/search-r1/local_dense_retriever/retrieval_server.py:329
Method
retrieve_from_text
Get token information from text input
slime/slime/router/router.py:203
Function
return_none
(input_tensor)
Megatron-LM/tests/unit_tests/pipeline_parallel/test_schedules.py:487
Method
returns
Return a single information on function return. Takes the first return information.
Megatron-LM/tools/retro/config_utils.py:190
Method
revert_to_snapshot
(self, path_to_vm: str, snapshot_name: str)
gui-rl/desktop_env/providers/azure/provider.py:110
Method
revert_to_snapshot
(self, path_to_vm: str, snapshot_name: str)
gui-rl/desktop_env/providers/aws/provider.py:103
Method
revert_to_snapshot
(self, path_to_vm: str, snapshot_name: str)
gui-rl/desktop_env/providers/docker/provider.py:153
Method
revert_to_snapshot
(self, path_to_vm: str, snapshot_name: str)
gui-rl/desktop_env/providers/virtualbox/provider.py:109
Method
revert_to_snapshot
(self, path_to_vm: str, snapshot_name: str)
gui-rl/desktop_env/providers/volcengine/provider.py:103
Method
revert_to_snapshot
(self, path_to_vm: str, snapshot_name: str)
gui-rl/desktop_env/providers/vmware/provider.py:93
Method
revert_to_snapshot
(self, path_to_vm: str, snapshot_name: str)
gui-rl/desktop_env/providers/aliyun/provider.py:168
Function
reward_func
(args, sample_or_samples, **kwargs)
openclaw-rl/openclaw_api_server.py:160
Function
reward_func
(args, sample_or_samples, **kwargs)
openclaw-rl/oel/openclaw_oel_api_server.py:234
Function
reward_func
(args, sample_or_samples, **kwargs)
openclaw-opd/openclaw_opd_api_server.py:225
Function
reward_func
(args, sample: Sample | list[Sample], **kwargs)
gui-rl/generate_with_gui.py:734
Function
reward_func
Reward is pre-set in generate(); this is a no-op pass-through.
gui-rl/generate_with_agentnet.py:280
Function
reward_func
Tool call reward function using math_dapo as primary reward model
toolcall-rl/generate_with_retool.py:856
Function
reward_func
(args, sample, **kwargs)
swe-rl/generate_with_swe.py:29
Function
reward_func
(args, sample, **kwargs)
slime/examples/on_policy_distillation/on_policy_distillation.py:8
Function
reward_func
Reward function using math_dapo scoring.
slime/examples/strands_sglang/generate_with_strands.py:100
Function
rl_inference_interface_shutdown
()
Megatron-LM/megatron/rl/rl_utils.py:2342
Function
rng_context_wrapper
Wrapper to add rng context to submodule callables
Megatron-LM/megatron/core/models/gpt/fine_grained_callables.py:564
Method
rollout
(self, request: RolloutRequest)
Megatron-LM/megatron/rl/server/agent/fastapi_env_server.py:141
Method
rollout
(self, request: RolloutRequest)
Megatron-LM/megatron/rl/agent/weighted_multi_task.py:154
← previous
next →
8,501–8,600 of 10,561, ranked by callers