# vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models

arXiv: https://arxiv.org/abs/2606.08094 · HTML: https://mlsanity.com/paper/2606.08094/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Efficient VLA inference and adaptation, one of 13 directions in Vision-language-action models.
- Builds on 34 of its 53 references that are in the map.
- First posted on arXiv 6 Jun 2026.

## Placed in

- Vision-language-action models / [Efficient VLA inference and adaptation](https://mlsanity.com/vla/efficient-vla-inference-and-adaptation/)

## Builds on (most cited first, 30 of 34)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://mlsanity.com/paper/2506.01844/) (2025)
- [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024)
- [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025)
- [Real-Time Execution of Action Chunking Flow Policies](https://mlsanity.com/paper/2506.07339/) (2025)
- [LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization](https://mlsanity.com/paper/2510.03827/) (2025)
- [VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model](https://mlsanity.com/paper/2509.09372/) (2025)
- [VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model](https://mlsanity.com/paper/2602.10098/) (2026)
- [Defeating the Training-Inference Mismatch via FP16](https://mlsanity.com/paper/2510.26788/) (2025)
- [Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling](https://mlsanity.com/paper/2408.17355/) (2024)
- [Leave No Observation Behind: Real-time Correction for VLA Action Chunks](https://mlsanity.com/paper/2509.23224/) (2025)
- [BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation](https://mlsanity.com/paper/2506.07530/) (2025)
- [SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning](https://mlsanity.com/paper/2509.05614/) (2025)
- [Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment](https://mlsanity.com/paper/2511.04555/) (2025)
- [A Survey on Efficient Vision-Language-Action Models](https://mlsanity.com/paper/2510.24795/) (2025)
- [Bitnet.cpp: Efficient Edge Inference for Ternary LLMs](https://mlsanity.com/paper/2502.11880/) (2025)
- [FASTER: Rethinking Real-Time Flow VLAs](https://mlsanity.com/paper/2603.19199/) (2026)
- [How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf](https://mlsanity.com/paper/2602.18397/) (2026)
- [NanoVLA: Routing Decoupled Vision-Language Understanding for Nano-sized Generalist Robotic Policies](https://mlsanity.com/paper/2510.25122/) (2025)
- [Lite VLA: Efficient Vision-Language-Action Control on CPU-Bound Edge Robots](https://mlsanity.com/paper/2511.05642/) (2025)
- [ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models](https://mlsanity.com/paper/2605.24011/) (2026)
- [Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment](https://mlsanity.com/paper/2604.24447/) (2026)
- [ActionFlow: A Pipelined Action Acceleration for Vision Language Models on Edge](https://mlsanity.com/paper/2512.20276/) (2025)

## Built on by (most cited first, 4 of 4)

- [Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference](https://mlsanity.com/paper/2607.12659/) (2026)
- [Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots](https://mlsanity.com/paper/2607.02501/) (2026)
- [When Faster VLA Deployment Changes Closed-Loop Behavior: Task Success-Latency Analysis of SmolVLA Across PyTorch and ONNX Variants](https://mlsanity.com/paper/2609.14146/) (2026)
- [vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation](https://mlsanity.com/paper/2609.24274/) (2026)

## Abstract (arXiv)

Deploying vision--language--action (VLA) models on robots requires adapting model-specific inference pipelines to heterogeneous processors and limited onboard memory. We present vla.cpp, a unified C++ inference runtime for eleven VLA models, with no PyTorch dependency for model execution. The runtime shares model loading, tensor execution, and serving while retaining architecture-specific attention, conditioning, and action heads. Iterative policies reuse observation-dependent computation across solver steps, while regression policies predict actions directly. We evaluate task success on LIBERO-Object and profile supported configurations on NVIDIA, Apple, and Intel hardware. BitVLA completes 200/200 LIBERO-Object episodes on an 8,GB Jetson Orin Nano. A ternary tensor-core kernel accelerates its client inference by 4.0--4.6× over the CUDA-core baseline on RTX 3060 and AGX Orin. A SmolVLA case study links positional-index precision to gripper commands and task success, showing why fixed-input numerical checks should accompany rollout evaluation. Deployments on UR10e and ALOHA demonstrate physical robot integration; delay and execution-horizon studies characterize synchronous chunked control. The results demonstrate a common deployment path across VLA architectures and hardware, with numerical validation and control settings guiding deployment alongside inference efficiency.