Embodied.cpp: A Portable C++ 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). Existing inference runtimes are built for request-response serving and cannot meet embodied deployment requirements such as multi-rate execution within closed-loop control, latency-first batch-1 inference on heterogeneous hardware, and extensible embodied interfaces beyond fixed token I/O. Based on an architectural analysis of representative VLA models and WAMs, Embodied.cpp extracts a shared execution path organized into five layers: input adapter, sequence builder, backbone execution, head plugin, and deployment adapter. It provides modular multi-rate execution, latency-first fused inference, and extensible operator and I/O support through a single backend abstraction. Evaluated on two VLA models (HY-VLA and pi0.5) and a preliminary WAM benchmark using LingBot-VA Transformer blocks, the runtime achieved task success rates of 100.0% and 91.0%, and reduced block memory from 312.2 MiB to 88.1 MiB, maintaining high accuracy while improving deployment efficiency across devices, robots, and simulators.

Paper Overview

Field: 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

Summary

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

The authors present Embodied.cpp, 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 adapter 2. Sequence builder 3. Backbone execution 4. Head plugin 5. Deployment adapter

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 via 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 100.0% and 91.0% task success rates, successfully completing 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 across a variety of embodied model architectures.

Original Abstract (excerpt)

> 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... We present Embodied.cpp, a portable C++ inference runtime for embodied models...

--- *Auto-collected on 2026-07-06*

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

Summary

Paper Overview

Summary

Evaluation Results

Original Abstract (excerpt)

Tags