# How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf

arXiv: https://arxiv.org/abs/2602.18397 · HTML: https://mlsanity.com/paper/2602.18397/

## Key facts

- Cited by 19 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 40 of its 44 references that are in the map.
- First posted on arXiv 20 Feb 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 40)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [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)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://mlsanity.com/paper/2506.01844/) (2025)
- [TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2409.12514/) (2024)
- [π*0.6: a VLA That Learns From Experience](https://mlsanity.com/paper/2511.14759/) (2025)
- [Real-Time Execution of Action Chunking Flow Policies](https://mlsanity.com/paper/2506.07339/) (2025)
- [MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2508.19236/) (2025)
- [LLM Inference Unveiled: Survey and Roofline Model Insights](https://mlsanity.com/paper/2402.16363/) (2024)
- [RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches](https://mlsanity.com/paper/2311.01977/) (2023)
- [Vidur: A Large-Scale Simulation Framework For LLM Inference](https://mlsanity.com/paper/2405.05465/) (2024)
- [DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution](https://mlsanity.com/paper/2411.02359/) (2024)
- [HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers](https://mlsanity.com/paper/2410.05273/) (2024)
- [Training-Time Action Conditioning for Efficient Real-Time Chunking](https://mlsanity.com/paper/2512.05964/) (2025)
- [VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference](https://mlsanity.com/paper/2512.01031/) (2025)
- [Hume: Introducing System-2 Thinking in Visual-Language-Action Model](https://mlsanity.com/paper/2505.21432/) (2025)
- [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)
- [Running VLAs at Real-time Speed](https://mlsanity.com/paper/2510.26742/) (2025)
- [Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment](https://mlsanity.com/paper/2511.04555/) (2025)
- [KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems](https://mlsanity.com/paper/2409.14908/) (2024)
- [ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context](https://mlsanity.com/paper/2510.04246/) (2025)
- [A Survey on Efficient Vision-Language-Action Models](https://mlsanity.com/paper/2510.24795/) (2025)

## Built on by (most cited first, 19 of 19)

- [Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs](https://mlsanity.com/paper/2605.13778/) (2026)
- [FLARE: Diffusion for Hybrid Language Model](https://mlsanity.com/paper/2606.01774/) (2026)
- [OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism](https://mlsanity.com/paper/2603.14371/) (2026)
- [Understanding Asynchronous Inference Methods for Vision-Language-Action Models](https://mlsanity.com/paper/2605.08168/) (2026)
- [vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models](https://mlsanity.com/paper/2606.08094/) (2026)
- [Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference](https://mlsanity.com/paper/2607.12659/) (2026)
- [Offload or Overload: A Platform Measurement Study of Mobile Robotic Manipulation Workloads](https://mlsanity.com/paper/2603.18284/) (2026)
- [Acting While Understanding: Asynchronous Semantic-Action Decoupling for Real-Time Vision-Language-Action Models](https://mlsanity.com/paper/2606.15285/) (2026)
- [The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks](https://mlsanity.com/paper/2606.28529/) (2026)
- [EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints](https://mlsanity.com/paper/2608.15502/) (2026)
- [LiteVLA-H: Dual-Rate Vision-Language-Action Inference for Onboard Aerial Guidance and Semantic Perception](https://mlsanity.com/paper/2605.00884/) (2026)
- [IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies](https://mlsanity.com/paper/2609.10915/) (2026)
- [Efficient Vision-Language-Action Management and Serving for Robot Factories](https://mlsanity.com/paper/2609.12075/) (2026)
- [rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference](https://mlsanity.com/paper/2609.19104/) (2026)
- [Catch Me If You Can: Real-Time Feedback Denoising for Responsive VLAs](https://mlsanity.com/paper/2609.21022/) (2026)
- [KerColle: Unlocking Fine-Grained GPU Concurrency in Vision-Language-Action Models](https://mlsanity.com/paper/2609.22335/) (2026)
- [vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation](https://mlsanity.com/paper/2609.24274/) (2026)
- [Text-Vision Synergistic Token Caching: A Training-Free Framework for Efficient Vision-Language-Action Inference](https://mlsanity.com/paper/2609.34319/) (2026)
- [JitterVLA: A Replay Benchmark for Motion Quality in VLA-Driven Human-Robot Manipulation](https://mlsanity.com/paper/2610.13628/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models have recently demonstrated impressive capabilities across various embodied AI tasks. While deploying VLA models on real-world robots imposes strict real-time inference constraints, the inference performance landscape of VLA remains poorly understood due to the large combinatorial space of model architectures and inference systems. In this paper, we ask a fundamental research question: How should we design future VLA models and systems to support real-time inference? To address this question, we first introduce VLA-Perf, an analytical performance model that can analyze inference performance for arbitrary combinations of VLA models and inference systems. Using VLA-Perf, we conduct the first systematic study of the VLA inference performance landscape. From a model-design perspective, we examine how inference performance is affected by model scaling, model architectural choices, long-context video inputs, asynchronous inference, and dual-system model pipelines. From the deployment perspective, we analyze where VLA inference should be executed -- on-device, on edge servers, or in the cloud -- and how hardware capability and network performance jointly determine end-to-end latency. By distilling 15 key takeaways from our comprehensive evaluation, we hope this work can provide practical guidance for the design of future VLA models and inference systems.