vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation

arXiv:2609.24274 · cs.RO, cs.AI, cs.SY, eess.SY · Submitted 2026-09-21 · Read on arXiv

cs.RO, cs.AI, cs.SY, eess.SY

Submitted: 2026-09-21

Updated: 2026-09-21

Comments: 8 pages, 7 tables, 5 figures. Project page: https://vla-simd.github.io/

Code: https://github.com/google/XNNPACK

Project page: https://vla-simd.github.io

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Transformer — 11× in this paper · explained in 2 episodes
• Quantization — 7× in this paper · explained in 12 episodes
• Core — 5× in this paper · explained in 2 episodes
• Fidelity — 5× in this paper · explained in 2 episodes
• Action Chunking — 4× in this paper · explained in 1 episode
• Benchmark — 4× in this paper · explained in 2 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• Conference on Robot Learning — 2× in this paper
• International Conference on Learning Representations — 2× in this paper
• Benchmarking — 1× in this paper · explained in 3 episodes
• CONFIDENCE INTERVALS — 1× in this paper
• Consistency — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Edge AI — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Flow Matching — 1× in this paper · explained in 8 episodes
• IEEE International Conference on Robotics and Automation — 1× in this paper
• Instruction-Modulated Perception and Action Chunking with Transformers — 1× in this paper
• SIMD Micro Kernel — 1× in this paper
• Tokenization — 1× in this paper · explained in 2 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes
• VLA Models — 1× in this paper · explained in 3 episodes
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 2 episodes

Sources

• SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM
• NanoVLA: Routing Decoupled Vision-Language Understanding for Nano-sized Generalist Robotic Policies
• BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation
• A Survey on Efficient Vision-Language-Action Models
• How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf
• Characterizing VLA Models: Identifying the Action Generation Bottleneck for Edge AI Architectures
• Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment
• Lite VLA: Efficient Vision-Language-Action Control on CPU-Bound Edge Robots
• Decoupling Vision, Language, and Action for Efficient Multi-Task Robot Policies
• ExecuTorch -- A Unified PyTorch Solution to Run AI Models On-Device
• vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving