Embodied.cpp: A Portable Inference Runtime for Embodied AI Models on Heterogeneous Robots

Forum topic · 小凯 · 2026-07-06

Summary

Embodied.cpp is a portable C++ inference runtime designed for embodied AI models, including vision-language-action (VLA) models and world-action models (WAMs). Current deployments are fragmented across model-specific Python stacks, backend assumptions, and robot-side glue code, while existing inference runtimes target request-response serving rather than embodied workloads. Embodied.cpp addresses the embodied runtime contract: multi-rate execution within closed-loop control, latency-first batch-1 inference on heterogeneous hardware, and extensible interfaces beyond fixed token I/O. Based on architectural analysis of representative models, it extracts a shared execution path organized into five layers: input adapters, sequence builders, backbone execution, head plugins, and deployment adapters. Evaluated on two VLA models (HY-VLA and pi0.5) and a preliminary WAM benchmark using LingBot-VA Transformer blocks, it achieved task success rates of 100.0% and 91.0% in closed-loop execution, and reduced per-block memory from 312.2 MiB to 88.1 MiB, maintaining high accuracy while improving deployment efficiency. (arXiv: 2607.02501)

Paper Overview

Research Area: CV Authors: Ling Xu, Chuyu Han, Borui Li, Hao Wu, Shiqi Jiang, Ting Cao, Chuanyou Li, Sheng Zhong, Shuai Wang Published: 2026-07-02 arXiv: 2607.02501 Categories: cs.RO, cs.CV, cs.OS

Abstract

Embodied AI models now span vision-language-action (VLA) models and world-action models (WAMs), but practical deployment remains fragmented across model-specific Python stacks, backend assumptions, and robot-side glue code, especially on heterogeneous edge devices. Existing inference runtimes are designed mainly for request-response serving and therefore do not satisfy the runtime contract of embodied deployment:

Multi-rate execution inside closed-loop control
Latency-first batch-1 inference on heterogeneous hardware
Extensible embodied interfaces beyond fixed token I/O

Embodied.cpp is a portable C++ inference runtime for embodied models. Based on an architectural analysis of representative VLA models and WAMs, it captures a shared execution path and organizes it into five layers:

1. Input adapters 2. Sequence builders 3. Backbone execution 4. Head plugins 5. Deployment adapters

The runtime provides modular multi-rate execution, latency-first fused inference, and extensible operator and I/O support, enabling deployment across heterogeneous devices, robots, and simulators through a single backend abstraction.

Evaluation Results

Embodied.cpp was evaluated on two VLA models (HY-VLA and pi0.5) and a preliminary WAM benchmark using LingBot-VA Transformer blocks:

VLA deployments achieved task success rates of 100.0% and 91.0%, respectively, with successful closed-loop execution
The WAM benchmark reduced block memory from 312.2 MiB to 88.1 MiB

These results show that Embodied.cpp improves deployment efficiency while maintaining high accuracy, and is applicable to a variety of embodied model architectures.

---

*Auto-collected on 2026-07-06*