ActionFlow: A Pipelined Action Acceleration for Vision Language Models on Edge
ActionFlow: A Pipelined Action Acceleration for Vision Language Models on Edge
This paper presents ActionFlow, a system-level inference framework designed to accelerate Vision-Language-Action (VLA) models on resource-constrained edge platforms. The authors introduce a Cross-Request Pipelining strategy that batches memory-bound Decode phases with compute-bound Prefill phases to maximize hardware utilization. Additionally, they propose a Cross-Request State Packed Forward operator and a Unified KV Ring Buffer to fuse fragmented memory operations into efficient dense computations. Experimental results show that ActionFlow achieves a 2.55x improvement in frames per second (FPS) on the OpenVLA-7B model without requiring retraining, enabling real-time dynamic manipulation on edge hardware. The work is available at https://github.com/Frankd35/Action-Flow.
ActionFlow introduces a system-level inference framework for Vision-Language-Action models on edge devices, achieving a 2.55x FPS improvement on OpenVLA-7B without retraining by utilizing cross-request pipelining and memory-efficient operators.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
FPS improvement
2.55
View original evidence
computations. Experimental results demonstrate that ActionFlow achieves a 2.55x improvement in FPS on the OpenVLA-7B model without retraining, enabling real-time dynamic manipulation on edge hardware. Our work is available at https://github.com/Frankd35/Action-Flow.
Open source S5control frequency range
20–30
View original evidence
arXiv:2512.20276v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a unified paradigm for robotic perception and control, enabling emergent generalization and long-horizon task execution. However, their deployment in dynamic, real-world environments is severely hindered by high inference latency. While smooth robotic interaction requires control frequencies of 20-30 Hz, curr
Open source S2VLA model operating frequency
3–5
View original evidence
ent VLA models typically operate at only 3-5 Hz on edge devices due to the memory-bound nature of autoregressive decoding. Existing optimizations often require extensive retraining or compromise model accuracy. To bridge this gap, we introduce ActionFlow, a system-level inference framework tailored for resource-constrained edge platforms. At the core of ActionFlow is a Cross-Request Pipelining strategy, a novel sched
Open source S3FPS improvement factor
2.55
View original evidence
computations. Experimental results demonstrate that ActionFlow achieves a 2.55x improvement in FPS on the OpenVLA-7B model without retraining, enabling real-time dynamic manipulation on edge hardware. Our work is available at https://github.com/Frankd35/Action-Flow.
Open source S5
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
computations. Experimental results demonstrate that ActionFlow achieves a 2.55x improvement in FPS on the OpenVLA-7B model without retraining, enabling real-time dynamic manipulation on edge hardware. Our work is available at https://github.com/Frankd35/Action-Flow.
Open source S5
arXiv:2512.20276v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a unified paradigm for robotic perception and control, enabling emergent generalization and long-horizon task execution. However, their deployment in dynamic, real-world environments is severely hindered by high inference latency. While smooth robotic interaction requires control frequencies of 20-30 Hz, curr
Open source S2
ent VLA models typically operate at only 3-5 Hz on edge devices due to the memory-bound nature of autoregressive decoding. Existing optimizations often require extensive retraining or compromise model accuracy. To bridge this gap, we introduce ActionFlow, a system-level inference framework tailored for resource-constrained edge platforms. At the core of ActionFlow is a Cross-Request Pipelining strategy, a novel sched
Open source S3
Source：arXiv Robotics — research abstracts · arxiv.org