LICENSE
README.md
pyproject.toml
rlinf/__init__.py
rlinf/config.py
rlinf.egg-info/PKG-INFO
rlinf.egg-info/SOURCES.txt
rlinf.egg-info/dependency_links.txt
rlinf.egg-info/requires.txt
rlinf.egg-info/top_level.txt
rlinf/agents/__init__.py
rlinf/agents/multiturn_demo/__init__.py
rlinf/agents/multiturn_demo/fake_tool_worker.py
rlinf/agents/multiturn_demo/mcp_agent_loop.py
rlinf/agents/multiturn_demo/mcp_filesystem_worker.py
rlinf/agents/multiturn_demo/tool_agent_loop.py
rlinf/agents/searchr1/__init__.py
rlinf/agents/searchr1/search_tool_worker.py
rlinf/agents/searchr1/searchr1_agent_loop.py
rlinf/algorithms/__init__.py
rlinf/algorithms/advantages.py
rlinf/algorithms/losses.py
rlinf/algorithms/registry.py
rlinf/algorithms/utils.py
rlinf/algorithms/rewards/__init__.py
rlinf/algorithms/rewards/code/__init__.py
rlinf/algorithms/rewards/code/code_verifier/__init__.py
rlinf/algorithms/rewards/code/code_verifier/verify.py
rlinf/algorithms/rewards/math/__init__.py
rlinf/algorithms/rewards/math/math_verifier/__init__.py
rlinf/algorithms/rewards/math/math_verifier/parser.py
rlinf/algorithms/rewards/math/math_verifier/verify.py
rlinf/algorithms/rewards/searchr1/__init__.py
rlinf/algorithms/rewards/vqa/__init__.py
rlinf/algorithms/rewards/vqa/format_rewards.py
rlinf/algorithms/rewards/vqa/qa_rewards.py
rlinf/data/__init__.py
rlinf/data/embodied_io_struct.py
rlinf/data/io_struct.py
rlinf/data/replay_buffer.py
rlinf/data/tokenizers.py
rlinf/data/utils.py
rlinf/data/datasets/__init__.py
rlinf/data/datasets/item.py
rlinf/data/datasets/math.py
rlinf/data/datasets/vlm.py
rlinf/data/datasets/world_model.py
rlinf/data/tool_call/__init__.py
rlinf/data/tool_call/tool_io_struct.py
rlinf/envs/__init__.py
rlinf/envs/action_utils.py
rlinf/envs/utils.py
rlinf/envs/behavior/__init__.py
rlinf/envs/behavior/behavior_env.py
rlinf/envs/calvin/__init__.py
rlinf/envs/calvin/calvin_gym_env.py
rlinf/envs/calvin/utils.py
rlinf/envs/calvin/venv.py
rlinf/envs/frankasim/__init__.py
rlinf/envs/frankasim/frankasim_env.py
rlinf/envs/habitat/__init__.py
rlinf/envs/habitat/habitat_env.py
rlinf/envs/habitat/venv.py
rlinf/envs/habitat/extensions/__init__.py
rlinf/envs/habitat/extensions/maps.py
rlinf/envs/habitat/extensions/utils.py
rlinf/envs/habitat/extensions/config/vlnce_r2r.yaml
rlinf/envs/isaaclab/__init__.py
rlinf/envs/isaaclab/isaaclab_env.py
rlinf/envs/isaaclab/utils.py
rlinf/envs/isaaclab/venv.py
rlinf/envs/isaaclab/tasks/__init__.py
rlinf/envs/isaaclab/tasks/stack_cube.py
rlinf/envs/libero/__init__.py
rlinf/envs/libero/libero_env.py
rlinf/envs/libero/utils.py
rlinf/envs/libero/venv.py
rlinf/envs/maniskill/__init__.py
rlinf/envs/maniskill/maniskill_env.py
rlinf/envs/maniskill/maniskill_offload_env.py
rlinf/envs/maniskill/utils.py
rlinf/envs/maniskill/tasks/__init__.py
rlinf/envs/maniskill/tasks/put_carrot_on_plate.py
rlinf/envs/maniskill/tasks/put_on_in_scene_multi.py
rlinf/envs/maniskill/tasks/variants/__init__.py
rlinf/envs/maniskill/tasks/variants/put_on_plate_25_carrot.py
rlinf/envs/maniskill/tasks/variants/put_on_plate_25_ee_pose.py
rlinf/envs/maniskill/tasks/variants/put_on_plate_25_image.py
rlinf/envs/maniskill/tasks/variants/put_on_plate_25_instruct.py
rlinf/envs/maniskill/tasks/variants/put_on_plate_25_multi_carrot.py
rlinf/envs/maniskill/tasks/variants/put_on_plate_25_multi_plate.py
rlinf/envs/maniskill/tasks/variants/put_on_plate_25_plate.py
rlinf/envs/maniskill/tasks/variants/put_on_plate_25_position.py
rlinf/envs/maniskill/tasks/variants/put_on_plate_25_position_change.py
rlinf/envs/maniskill/tasks/variants/put_on_plate_25_single.py
rlinf/envs/maniskill/tasks/variants/put_on_plate_25_vision_image.py
rlinf/envs/maniskill/tasks/variants/put_on_plate_25_vision_texture.py
rlinf/envs/maniskill/tasks/variants/put_on_plate_25_vision_whole.py
rlinf/envs/maniskill/tasks/variants/utils.py
rlinf/envs/metaworld/__init__.py
rlinf/envs/metaworld/metaworld_env.py
rlinf/envs/metaworld/utils.py
rlinf/envs/metaworld/venv.py
rlinf/envs/realworld/__init__.py
rlinf/envs/realworld/realworld_env.py
rlinf/envs/realworld/venv.py
rlinf/envs/realworld/common/camera/__init__.py
rlinf/envs/realworld/common/camera/camera.py
rlinf/envs/realworld/common/keyboard/__init__.py
rlinf/envs/realworld/common/keyboard/keyboard_listener.py
rlinf/envs/realworld/common/ros/__init__.py
rlinf/envs/realworld/common/ros/ros_controller.py
rlinf/envs/realworld/common/spacemouse/__init__.py
rlinf/envs/realworld/common/spacemouse/spacemouse_expert.py
rlinf/envs/realworld/common/video_player/__init__.py
rlinf/envs/realworld/common/video_player/video_player.py
rlinf/envs/realworld/common/wrappers/__init__.py
rlinf/envs/realworld/common/wrappers/euler_obs.py
rlinf/envs/realworld/common/wrappers/gripper_close.py
rlinf/envs/realworld/common/wrappers/relative_frame.py
rlinf/envs/realworld/common/wrappers/reward_done_wrapper.py
rlinf/envs/realworld/common/wrappers/spacemouse_intervention.py
rlinf/envs/realworld/franka/__init__.py
rlinf/envs/realworld/franka/franka_controller.py
rlinf/envs/realworld/franka/franka_env.py
rlinf/envs/realworld/franka/franka_robot_state.py
rlinf/envs/realworld/franka/utils.py
rlinf/envs/realworld/franka/tasks/__init__.py
rlinf/envs/realworld/franka/tasks/bottle.py
rlinf/envs/realworld/franka/tasks/franka_bin_relocation.py
rlinf/envs/realworld/franka/tasks/peg_insertion_env.py
rlinf/envs/robocasa/__init__.py
rlinf/envs/robocasa/robocasa_env.py
rlinf/envs/robocasa/utils.py
rlinf/envs/robocasa/venv.py
rlinf/envs/robotwin/__init__.py
rlinf/envs/robotwin/robotwin_env.py
rlinf/envs/venv/__init__.py
rlinf/envs/venv/venv.py
rlinf/envs/world_model/__init__.py
rlinf/envs/world_model/base_world_env.py
rlinf/envs/world_model/world_model_opensora_env.py
rlinf/envs/wrappers/__init__.py
rlinf/envs/wrappers/record_video.py
rlinf/hybrid_engines/__init__.py
rlinf/hybrid_engines/fsdp/__init__.py
rlinf/hybrid_engines/fsdp/fsdp_model_manager.py
rlinf/hybrid_engines/fsdp/utils.py
rlinf/hybrid_engines/fsdp/strategy/__init__.py
rlinf/hybrid_engines/fsdp/strategy/base.py
rlinf/hybrid_engines/fsdp/strategy/checkpoint.py
rlinf/hybrid_engines/fsdp/strategy/fsdp.py
rlinf/hybrid_engines/fsdp/strategy/fsdp2.py
rlinf/hybrid_engines/megatron/__init__.py
rlinf/hybrid_engines/megatron/megatron_model_manager.py
rlinf/hybrid_engines/megatron/utils.py
rlinf/hybrid_engines/sglang/common/__init__.py
rlinf/hybrid_engines/sglang/common/detokenizer_manager.py
rlinf/hybrid_engines/sglang/common/io_struct.py
rlinf/hybrid_engines/sglang/common/sgl_engine.py
rlinf/hybrid_engines/sglang/common/sgl_scheduler.py
rlinf/hybrid_engines/sglang/common/tokenizer_manager.py
rlinf/hybrid_engines/vllm/vllm_0_8_5/__init__.py
rlinf/hybrid_engines/vllm/vllm_0_8_5/executor.py
rlinf/hybrid_engines/vllm/vllm_0_8_5/weight_loader.py
rlinf/hybrid_engines/vllm/vllm_0_8_5/worker.py
rlinf/models/__init__.py
rlinf/models/embodiment/__init__.py
rlinf/models/embodiment/base_policy.py
rlinf/models/embodiment/cnn_policy/__init__.py
rlinf/models/embodiment/cnn_policy/cnn_policy.py
rlinf/models/embodiment/dexbotic_pi/__init__.py
rlinf/models/embodiment/dexbotic_pi/dexbotic_pi_policy.py
rlinf/models/embodiment/flow_policy/__init__.py
rlinf/models/embodiment/flow_policy/flow_policy.py
rlinf/models/embodiment/gr00t/__init__.py
rlinf/models/embodiment/gr00t/embodiment_tags.py
rlinf/models/embodiment/gr00t/gr00t_action_model.py
rlinf/models/embodiment/gr00t/modality_config.py
rlinf/models/embodiment/gr00t/simulation_io.py
rlinf/models/embodiment/gr00t/utils.py
rlinf/models/embodiment/mlp_policy/__init__.py
rlinf/models/embodiment/mlp_policy/mlp_policy.py
rlinf/models/embodiment/modules/__init__.py
rlinf/models/embodiment/modules/batch_renorm.py
rlinf/models/embodiment/modules/entropy_tunning.py
rlinf/models/embodiment/modules/explore_noise_net.py
rlinf/models/embodiment/modules/flow_actor.py
rlinf/models/embodiment/modules/mlp.py
rlinf/models/embodiment/modules/q_head.py
rlinf/models/embodiment/modules/resnet_utils.py
rlinf/models/embodiment/modules/utils.py
rlinf/models/embodiment/modules/value_head.py
rlinf/models/embodiment/openpi/__init__.py
rlinf/models/embodiment/openpi/openpi_action_model.py
rlinf/models/embodiment/openpi/dataconfig/__init__.py
rlinf/models/embodiment/openpi/dataconfig/behavior_dataconfig.py
rlinf/models/embodiment/openpi/dataconfig/calvin_dataconfig.py
rlinf/models/embodiment/openpi/dataconfig/franka_dataconfig.py
rlinf/models/embodiment/openpi/dataconfig/gsenv_dataconfig.py
rlinf/models/embodiment/openpi/dataconfig/libero_dataconfig.py
rlinf/models/embodiment/openpi/dataconfig/maniskill_dataconfig.py
rlinf/models/embodiment/openpi/dataconfig/metaworld_dataconfig.py
rlinf/models/embodiment/openpi/dataconfig/robocasa_dataconfig.py
rlinf/models/embodiment/openpi/dataconfig/robotwin_aloha_dataconfig.py
rlinf/models/embodiment/openpi/policies/__init__.py
rlinf/models/embodiment/openpi/policies/aloha_policy.py
rlinf/models/embodiment/openpi/policies/behavior_policy.py
rlinf/models/embodiment/openpi/policies/calvin_policy.py
rlinf/models/embodiment/openpi/policies/franka_policy.py
rlinf/models/embodiment/openpi/policies/gsenv_policy.py
rlinf/models/embodiment/openpi/policies/libero_policy.py
rlinf/models/embodiment/openpi/policies/maniskill_policy.py
rlinf/models/embodiment/openpi/policies/metaworld_policy.py
rlinf/models/embodiment/openpi/policies/robocasa_policy.py
rlinf/models/embodiment/openvla/__init__.py
rlinf/models/embodiment/openvla/openvla_action_model.py
rlinf/models/embodiment/openvla_oft/__init__.py
rlinf/models/embodiment/openvla_oft/openvla_utils.py
rlinf/models/embodiment/openvla_oft/official/__init__.py
rlinf/models/embodiment/openvla_oft/official/openvla_oft_action_model.py
rlinf/models/embodiment/openvla_oft/rlinf/__init__.py
rlinf/models/embodiment/openvla_oft/rlinf/openvla_oft_action_model.py
rlinf/models/embodiment/prismatic/__init__.py
rlinf/models/embodiment/prismatic/processing_prismatic.py
rlinf/runners/__init__.py
rlinf/runners/agent_eval_runner.py
rlinf/runners/agent_runner.py
rlinf/runners/async_embodied_runner.py
rlinf/runners/coding_online_rl_runner.py
rlinf/runners/embodied_eval_runner.py
rlinf/runners/embodied_runner.py
rlinf/runners/reasoning_eval_runner.py
rlinf/runners/reasoning_runner.py
rlinf/runners/sft_runner.py
rlinf/scheduler/__init__.py
rlinf/scheduler/channel/__init__.py
rlinf/scheduler/channel/channel.py
rlinf/scheduler/channel/channel_worker.py
rlinf/scheduler/cluster/__init__.py
rlinf/scheduler/cluster/cluster.py
rlinf/scheduler/cluster/config.py
rlinf/scheduler/cluster/node.py
rlinf/scheduler/cluster/utils.py
rlinf/scheduler/collective/__init__.py
rlinf/scheduler/collective/async_work.py
rlinf/scheduler/collective/collective.py
rlinf/scheduler/collective/collective_group.py
rlinf/scheduler/collective/multi_channel_pg.py
rlinf/scheduler/dynamic_scheduler/__init__.py
rlinf/scheduler/dynamic_scheduler/manager.py
rlinf/scheduler/dynamic_scheduler/scheduler_worker.py
rlinf/scheduler/dynamic_scheduler/utils.py
rlinf/scheduler/hardware/__init__.py
rlinf/scheduler/hardware/hardware.py
rlinf/scheduler/hardware/accelerators/__init__.py
rlinf/scheduler/hardware/accelerators/accelerator.py
rlinf/scheduler/hardware/accelerators/amd_gpu.py
rlinf/scheduler/hardware/accelerators/ascend_npu.py
rlinf/scheduler/hardware/accelerators/intel_gpu.py
rlinf/scheduler/hardware/accelerators/musa_gpu.py
rlinf/scheduler/hardware/accelerators/nvidia_gpu.py
rlinf/scheduler/hardware/robots/__init__.py
rlinf/scheduler/hardware/robots/franka.py
rlinf/scheduler/manager/__init__.py
rlinf/scheduler/manager/coll_manager.py
rlinf/scheduler/manager/lock_manager.py
rlinf/scheduler/manager/manager.py
rlinf/scheduler/manager/node_manager.py
rlinf/scheduler/manager/worker_manager.py
rlinf/scheduler/placement/__init__.py
rlinf/scheduler/placement/flexible.py
rlinf/scheduler/placement/node.py
rlinf/scheduler/placement/packed.py
rlinf/scheduler/placement/placement.py
rlinf/scheduler/worker/__init__.py
rlinf/scheduler/worker/lock.py
rlinf/scheduler/worker/worker.py
rlinf/scheduler/worker/worker_group.py
rlinf/utils/__init__.py
rlinf/utils/cuda_graph.py
rlinf/utils/data_iter_utils.py
rlinf/utils/data_process.py
rlinf/utils/distributed.py
rlinf/utils/drq.py
rlinf/utils/flops.py
rlinf/utils/initialize.py
rlinf/utils/logging.py
rlinf/utils/metric_logger.py
rlinf/utils/metric_utils.py
rlinf/utils/nested_dict_process.py
rlinf/utils/omega_resolver.py
rlinf/utils/patcher.py
rlinf/utils/placement.py
rlinf/utils/profiler.py
rlinf/utils/pytree.py
rlinf/utils/runner_utils.py
rlinf/utils/timers.py
rlinf/utils/torch_functionals.py
rlinf/utils/train_utils.py
rlinf/utils/utils.py
rlinf/utils/ckpt_convertor/__init__.py
rlinf/utils/ckpt_convertor/convert_openpi_jax_to_python.py
rlinf/utils/ckpt_convertor/fsdp_convertor/__init__.py
rlinf/utils/ckpt_convertor/fsdp_convertor/convert_dcp_to_pt.py
rlinf/utils/ckpt_convertor/fsdp_convertor/convert_pt_to_hf.py
rlinf/utils/ckpt_convertor/fsdp_convertor/utils.py
rlinf/utils/ckpt_convertor/fsdp_convertor/config/fsdp_model_convertor.yaml
rlinf/utils/ckpt_convertor/megatron_convertor/__init__.py
rlinf/utils/ckpt_convertor/megatron_convertor/config.py
rlinf/utils/ckpt_convertor/megatron_convertor/convert_hf_to_mg.py
rlinf/utils/ckpt_convertor/megatron_convertor/convert_hf_to_middle_file.py
rlinf/utils/ckpt_convertor/megatron_convertor/convert_mg_to_middle_file.py
rlinf/utils/ckpt_convertor/megatron_convertor/convert_middle_file_to_hf.py
rlinf/utils/ckpt_convertor/megatron_convertor/convert_middle_file_to_mg.py
rlinf/utils/ckpt_convertor/megatron_convertor/default_args.yaml
rlinf/utils/ckpt_convertor/megatron_convertor/utils/__init__.py
rlinf/utils/ckpt_convertor/megatron_convertor/utils/fp8_utils.py
rlinf/utils/ckpt_convertor/megatron_convertor/utils/mg_loader.py
rlinf/utils/ckpt_convertor/megatron_convertor/utils/mg_moe_groupgemm.py
rlinf/utils/ckpt_convertor/megatron_convertor/utils/mp_utils.py
rlinf/utils/ckpt_convertor/megatron_convertor/utils/safetensors_loader.py
rlinf/utils/ckpt_convertor/megatron_convertor/utils/tensor_operations.py
rlinf/utils/convertor/__init__.py
rlinf/utils/convertor/utils.py
rlinf/utils/resharding/__init__.py
rlinf/utils/resharding/mcore_weight_reshard.py
rlinf/utils/resharding/reshard_config.py
rlinf/utils/resharding/utils.py
rlinf/workers/__init__.py
rlinf/workers/actor/__init__.py
rlinf/workers/actor/async_fsdp_sac_policy_worker.py
rlinf/workers/actor/fsdp_actor_worker.py
rlinf/workers/actor/fsdp_sac_policy_worker.py
rlinf/workers/actor/megatron_actor_worker.py
rlinf/workers/agent/__init__.py
rlinf/workers/agent/agent_loop.py
rlinf/workers/agent/tool_worker.py
rlinf/workers/env/__init__.py
rlinf/workers/env/async_env_worker.py
rlinf/workers/env/env_worker.py
rlinf/workers/inference/__init__.py
rlinf/workers/inference/fsdp_inference_worker.py
rlinf/workers/inference/megatron_inference_worker.py
rlinf/workers/inference/utils.py
rlinf/workers/reward/__init__.py
rlinf/workers/reward/reward_worker.py
rlinf/workers/rollout/__init__.py
rlinf/workers/rollout/utils.py
rlinf/workers/rollout/hf/__init__.py
rlinf/workers/rollout/hf/async_huggingface_worker.py
rlinf/workers/rollout/hf/huggingface_worker.py
rlinf/workers/rollout/hf/utils.py
rlinf/workers/rollout/server/__init__.py
rlinf/workers/rollout/server/online_router_worker.py
rlinf/workers/rollout/server/server_rollout_worker.py
rlinf/workers/rollout/sglang/__init__.py
rlinf/workers/rollout/sglang/sglang_worker.py
rlinf/workers/rollout/vllm/__init__.py
rlinf/workers/rollout/vllm/vllm_worker.py
rlinf/workers/sft/__init__.py
rlinf/workers/sft/fsdp_sft_worker.py