# When Faster VLA Deployment Changes Closed-Loop Behavior: Task Success-Latency Analysis of SmolVLA Across PyTorch and ONNX Variants

arXiv: https://arxiv.org/abs/2609.14146 · HTML: https://mlsanity.com/paper/2609.14146/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 12 Sep 2026.

## Builds on (most cited first, 9 of 9)

- [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)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://mlsanity.com/paper/2506.01844/) (2025)
- [QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models](https://mlsanity.com/paper/2602.20309/) (2026)
- [NanoVLA: Routing Decoupled Vision-Language Understanding for Nano-sized Generalist Robotic Policies](https://mlsanity.com/paper/2510.25122/) (2025)
- [LiteVLA-Edge: Quantized On-Device Multimodal Control for Embedded Robotics](https://mlsanity.com/paper/2603.03380/) (2026)
- [vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models](https://mlsanity.com/paper/2606.08094/) (2026)
- [EaqVLA: Encoding-aligned Quantization for Vision-Language-Action Models](https://mlsanity.com/paper/2505.21567/) (2025)

## Abstract (arXiv)

Vision-language-action (VLA) deployment can reduce inference latency while changing closed-loop task behavior. We evaluate HuggingFaceVLA/smolvla_libero on an RTX 2060 (6 GB) in LIBERO Spatial and Object (MuJoCo 3.3.2, LeRobot 0.6.1, seed 42), comparing PyTorch+AMP with ONNX Runtime CUDA Execution Provider (CUDA EP). The main evaluation uses 100 episodes/suite; a paired rollout uses 300 episodes/suite. PyTorch+AMP reaches 70.0%/88.0% Spatial/Object success at 1181 ms p99. Requested-FP16 and requested-INT8 ONNX reduce tether-inspect p99 to 601 ms and 532 ms, while Spatial success falls to 41.0% and 40.0% and Object remains at 89.0%. A graph audit shows those artifacts are byte-identical FP32 graphs, so the requested-INT8 row is not operator-level INT8 quantization. A static language-width ablation (16/24/32 tokens) yields Spatial success of 41.0%, 75.0%, and 71.0%; widths 24 and 32 recover much of the Spatial drop while Object success and uniform-bench latency stay approximately stable. Width-24 ONNX Spatial success is comparable to the PyTorch+AMP baseline at roughly half the latency (Wilson intervals overlap; two-proportion chi-squared p=0.53). Context width is an important contributor in this stack; it does not account for every PyTorch-vs-ONNX difference. Deployment evaluation should jointly report latency, artifact inspection, interface constraints, and closed-loop success. Code: https://github.com/rafiqul713/smolvla-libero-onnx.