FluxVLA/FluxVLA

An all-in-one VLA engineering platform for embodied AI — from data to real-robot deployment.

What it solves

FluxVLA Engine is a full-stack engineering platform designed to simplify the deployment of embodied intelligence applications. It lowers the engineering barriers for Vision-Language-Action (VLA) research and development by providing a standardized foundation for the entire loop from data processing to real-device deployment.

How it works

The platform is built on principles of unified configuration, standardized interfaces, and module decoupling. It supports a wide range of VLA models (such as GR00T, PI0, Cosmos3, and SmolVLA) and provides integrated workflows for training, simulation evaluation, and real-robot inference. It includes support for various hardware targets, including NVIDIA Jetson Orin and Franka robots, and offers acceleration options like Triton and GR00T-RTC.

Who it’s for

It is intended for researchers and developers in the field of embodied intelligence and robotics who need a standardized, end-to-end framework for developing and deploying VLA models.

Highlights

  • Broad Model Support: Compatible with numerous VLA architectures including DiT4DiT, FastWAM, and PI0.5.
  • Real-Robot Deployment: Supports single-arm and dual-arm Franka robots, as well as Oli humanoid whole-body loco-manipulation.
  • Edge Acceleration: Optimized for NVIDIA Jetson Orin with inference acceleration reaching 7.4 Hz for GR00T-N1.5.
  • Simulation Integration: Integrated with benchmarks like LIBERO and RoboCasa for performance evaluation.

Related

  • Project
    dexmal/dexbotic

    A VLA (Vision-Language-Action) development toolbox for embodied intelligence that provides a unified framework for pretraining, fine-tuning, and evaluating robotic policies.

  • Project
    X-Square-Robot/wall-x

    An open-source framework for embodied foundation models that enables robots to perform complex physical manipulations by bridging vision-language understanding with action prediction.

  • Project
    starVLA/starVLA

    An open-source research platform for developing Vision-Language-Action (VLA) models with a modular, plug-and-play codebase for generalist robotics.

  • Project
    2toinf/X-VLA

    X-VLA is a soft-prompted Transformer-based Vision-Language-Action model designed for scalable cross-embodiment robotic control across diverse hardware platforms.

  • Dispatch
    Qwen-VLA: Unifying Vision-Language-Action Modeling for Embodied Intelligence

    Qwen-VLA is a general-purpose Vision-Language-Action model that unifies robotic manipulation, vision-language navigation, and cross-embodiment control into a single generalist policy model.