Starrick Liu
421db17d53
This release introduces significant performance optimizations, memory efficiency improvements, and enhanced system robustness: 🚀 Performance Optimizations: - Add three new fused CUDA kernels (rope_index, rot_pos_emb, get_window_index) for accelerated multimodal preprocessing - Implement FSDP2 support for distributed training with improved memory efficiency - Add Torch.compile integration for additional performance gains - Optimize memory usage: reduce peak allocation from 48GB to 24GB on 8-GPU setup 🔧 System Robustness: - Fix missing token position inputs in prediction pipeline - Add type-robust negation operations in RoPE CUDA kernels (half/bfloat16 support) - Fix dataset root parameter initialization in LeRobot data loader - Enhanced error handling and input validation across fusion operators 📚 Documentation & Usability: - Add comprehensive memory usage benchmarks and hardware recommendations - Update citation format with proper arXiv reference - Improve training configuration documentation with quick start guide - Add detailed API documentation for new fusion operators 🛠️ Technical Details: - Version bump to 1.0.1 - New CUDA kernels: rope_index.cu, rot_pos.cu, window_index.cu - FSDP2 state dict loading with distribute_tensor support - Enhanced multimodal RoPE with 3D position encoding - Window attention optimization for Vision Transformers Breaking Changes: None - all changes are backward compatible
5.4 KiB
Wall-X
Building General-Purpose Robots Based on Embodied Foundation Model
We are building the embodied foundation model to capture and compress the world's most valuable data: the continuous, high-fidelity stream of physical interaction.
By creating a direct feedback loop between the model's decisions and the body's lived experience, we enable the emergence of a truly generalizable intelligence—one that understands not just how the world works, but how to act effectively within it.
Repository
This repository provides the training and inference code that supports our WALL series open-source embodied foundation models. It includes end-to-end pipelines for data preparation (LeRobot), model configuration, flow-matching and FAST action branches, and evaluation utilities for real and simulated robots.
News
- We introduce WALL-OSS: Igniting VLMs toward the Embodied Space, an end-to-end embodied foundation model that leverages large-scale multimodal pretraining to achieve (1) embodiment-aware vision–language understanding, (2) strong language–action association, and (3) robust manipulation capability.
Models
- WALL-OSS-FLOW: https://huggingface.co/x-square-robot/wall-oss-flow
- WALL-OSS-FAST: https://huggingface.co/x-square-robot/wall-oss-fast
Environment Setup
Create and activate conda environment:
conda create --name wallx python=3.10
conda activate wallx
Install requirements:
pip install -r requirements.txt
MAX_JOBS=4 pip install flash-attn==2.7.4.post1 --no-build-isolation
Install lerobot:
git clone https://github.com/huggingface/lerobot.git
cd lerobot
pip install -e .
Install wall_x:
git submodule update --init --recursive
MAX_JOBS=4 pip install --no-build-isolation --verbose .
Training
Finetune on LeRobot Datasets
Before training, please refer to workspace/README.md for detailed configuration instructions including:
Training script path configuration
- GPU setup
- Model and data paths
- Robot DOF configuration
- Training hyperparameters
Download the Flow/FAST pretrained model and run:
bash ./workspace/lerobot_example/run.sh
Inference
Basic Action Inference
For model inference, please refer to:
python ./scripts/fake_inference.py
This script demonstrates how to:
- Load the Wall-OSS model using
Qwen2_5_VLMoEForAction.from_pretrained() - Prepare input data including proprioceptive information, attention masks, and dataset specifications
- Run inference in validation mode with proper data types (bfloat16)
- Validate model outputs and check for numerical stability
Open-Loop Evaluation
To generate an open-loop comparison plot, please follow:
python ./scripts/draw_openloop_plot.py
VQA Inference and Chain-of-Thought Testing
To run VQA inference and test the model's Chain-of-Thought (COT) reasoning capabilities, please follow:
python ./scripts/vqa_inference.py
This script can be used to test the model's COT reasoning abilities for embodied tasks. Below is an example of COT testing:
Input Image:
Input Text:
To move the red block in the plate with same color, what should you do next? Think step by step.
Model Output (COT Reasoning):
To move the red block in the plate with the same color, you should first locate the red block. It is currently positioned on the table, not in the plate. Then, you should carefully grasp the red block using your fingers. Next, you should use your hand to lift the red block from the table and place it into the plate that is also red in color. Ensure that the red block is securely placed in the plate without slipping or falling.
📚 Cite Us
If you find WALL-OSS models useful, please cite:
@article{zhai2025igniting,
title = {Igniting VLMs Toward the Embodied Space},
author = {Zhai, Andy and Liu, Brae and Fang, Bruno and Cai, Chalse and Ma, Ellie and Yin, Ethan and Wang, Hao and Zhou, Hugo and Wang, James and Shi, Lights and Liang, Lucy and Wang, Make and Wang, Qian and Gan, Roy and Yu, Ryan and Li, Shalfun and Liu, Starrick and Chen, Sylas and Chen, Vincent and Xu, Zach},
journal = {arXiv preprint arXiv:2509.11766},
year = {2025}
}