3ff6c6860e
SmolVLA's ``vlm_with_expert.forward`` doesn't actually support incremental KV cache growth — its only ``fill_kv_cache=True`` mode *overwrites* the cache with the latest call's key/value states, and its only ``fill_kv_cache=False`` mode concatenates ``cache + new`` into a local ``key_states`` for one matmul without ever updating the cache itself. The original ``select_message`` decode loop tried to use ``fill_kv_cache=True`` per step, which clobbered the cache to 1 token after the first decode and threw ``Expected size for first two dimensions of batch2 tensor to be: [15, 139] but got: [15, 1]`` — the attention mask still expected 139 keys but the cached + new key_states only had 1. Match the pattern ``denoise_step`` already uses successfully: maintain a cumulative ``(embs, pad, att)`` buffer that starts as the prefix and grows by one bool/embedding row per step. Each step forwards the *full* sequence with ``use_cache=False, fill_kv_cache=False, past_key_values=None`` so the matmul shapes always line up. Generated-token rows are tagged ``pad=1, att=1`` which makes them fully causal among themselves while still able to attend back to the entire prefix (per ``make_att_2d_masks`` semantics: a token can attend to any earlier token whose cumulative ``att`` count is ≤ its own). Image encoding is still done once via the initial ``embed_prefix`` call — the expensive part doesn't repeat. The remaining cost is O(n²) text-only transformer forwards, which is fine for the dry-run REPL's 50–100 token responses. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
LeRobot aims to provide models, datasets, and tools for real-world robotics in PyTorch. The goal is to lower the barrier to entry so that everyone can contribute to and benefit from shared datasets and pretrained models.
🤗 A hardware-agnostic, Python-native interface that standardizes control across diverse platforms, from low-cost arms (SO-100) to humanoids.
🤗 A standardized, scalable LeRobotDataset format (Parquet + MP4 or images) hosted on the Hugging Face Hub, enabling efficient storage, streaming and visualization of massive robotic datasets.
🤗 State-of-the-art policies that have been shown to transfer to the real-world ready for training and deployment.
🤗 Comprehensive support for the open-source ecosystem to democratize physical AI.
Quick Start
LeRobot can be installed directly from PyPI.
pip install lerobot
lerobot-info
Important
For detailed installation guide, please see the Installation Documentation.
Robots & Control
LeRobot provides a unified Robot class interface that decouples control logic from hardware specifics. It supports a wide range of robots and teleoperation devices.
from lerobot.robots.myrobot import MyRobot
# Connect to a robot
robot = MyRobot(config=...)
robot.connect()
# Read observation and send action
obs = robot.get_observation()
action = model.select_action(obs)
robot.send_action(action)
Supported Hardware: SO100, LeKiwi, Koch, HopeJR, OMX, EarthRover, Reachy2, Gamepads, Keyboards, Phones, OpenARM, Unitree G1.
While these devices are natively integrated into the LeRobot codebase, the library is designed to be extensible. You can easily implement the Robot interface to utilize LeRobot's data collection, training, and visualization tools for your own custom robot.
For detailed hardware setup guides, see the Hardware Documentation.
LeRobot Dataset
To solve the data fragmentation problem in robotics, we utilize the LeRobotDataset format.
- Structure: Synchronized MP4 videos (or images) for vision and Parquet files for state/action data.
- HF Hub Integration: Explore thousands of robotics datasets on the Hugging Face Hub.
- Tools: Seamlessly delete episodes, split by indices/fractions, add/remove features, and merge multiple datasets.
from lerobot.datasets.lerobot_dataset import LeRobotDataset
# Load a dataset from the Hub
dataset = LeRobotDataset("lerobot/aloha_mobile_cabinet")
# Access data (automatically handles video decoding)
episode_index=0
print(f"{dataset[episode_index]['action'].shape=}\n")
Learn more about it in the LeRobotDataset Documentation
SoTA Models
LeRobot implements state-of-the-art policies in pure PyTorch, covering Imitation Learning, Reinforcement Learning, and Vision-Language-Action (VLA) models, with more coming soon. It also provides you with the tools to instrument and inspect your training process.
Training a policy is as simple as running a script configuration:
lerobot-train \
--policy=act \
--dataset.repo_id=lerobot/aloha_mobile_cabinet
| Category | Models |
|---|---|
| Imitation Learning | ACT, Diffusion, VQ-BeT, Multitask DiT Policy |
| Reinforcement Learning | HIL-SERL, TDMPC & QC-FQL (coming soon) |
| VLAs Models | Pi0Fast, Pi0.5, GR00T N1.5, SmolVLA, XVLA |
Similarly to the hardware, you can easily implement your own policy & leverage LeRobot's data collection, training, and visualization tools, and share your model to the HF Hub
For detailed policy setup guides, see the Policy Documentation.
Inference & Evaluation
Evaluate your policies in simulation or on real hardware using the unified evaluation script. LeRobot supports standard benchmarks like LIBERO, MetaWorld and more to come.
# Evaluate a policy on the LIBERO benchmark
lerobot-eval \
--policy.path=lerobot/pi0_libero_finetuned \
--env.type=libero \
--env.task=libero_object \
--eval.n_episodes=10
Learn how to implement your own simulation environment or benchmark and distribute it from the HF Hub by following the EnvHub Documentation
Resources
- Documentation: The complete guide to tutorials & API.
- Chinese Tutorials: LeRobot+SO-ARM101中文教程-同济子豪兄 Detailed doc for assembling, teleoperate, dataset, train, deploy. Verified by Seed Studio and 5 global hackathon players.
- Discord: Join the
LeRobotserver to discuss with the community. - X: Follow us on X to stay up-to-date with the latest developments.
- Robot Learning Tutorial: A free, hands-on course to learn robot learning using LeRobot.
Citation
If you use LeRobot in your project, please cite the GitHub repository to acknowledge the ongoing development and contributors:
@misc{cadene2024lerobot,
author = {Cadene, Remi and Alibert, Simon and Soare, Alexander and Gallouedec, Quentin and Zouitine, Adil and Palma, Steven and Kooijmans, Pepijn and Aractingi, Michel and Shukor, Mustafa and Aubakirova, Dana and Russi, Martino and Capuano, Francesco and Pascal, Caroline and Choghari, Jade and Moss, Jess and Wolf, Thomas},
title = {LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch},
howpublished = "\url{https://github.com/huggingface/lerobot}",
year = {2024}
}
If you are referencing our research or the academic paper, please also cite our ICLR publication:
ICLR 2026 Paper
@inproceedings{cadenelerobot,
title={LeRobot: An Open-Source Library for End-to-End Robot Learning},
author={Cadene, Remi and Alibert, Simon and Capuano, Francesco and Aractingi, Michel and Zouitine, Adil and Kooijmans, Pepijn and Choghari, Jade and Russi, Martino and Pascal, Caroline and Palma, Steven and Shukor, Mustafa and Moss, Jess and Soare, Alexander and Aubakirova, Dana and Lhoest, Quentin and Gallou\'edec, Quentin and Wolf, Thomas},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://arxiv.org/abs/2602.22818}
}
Contribute
We welcome contributions from everyone in the community! To get started, please read our CONTRIBUTING.md guide. Whether you're adding a new feature, improving documentation, or fixing a bug, your help and feedback are invaluable. We're incredibly excited about the future of open-source robotics and can't wait to work with you on what's next—thank you for your support!
