# Efficient Block-Layer Parallel Inference for Vision-Language-Action on Hybrid Architectures

arXiv: https://arxiv.org/abs/2608.14586 · HTML: https://mlsanity.com/paper/2608.14586/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLA for autonomous driving, one of 13 directions in Vision-language-action models.
- Builds on 23 of its 30 references that are in the map.
- First posted on arXiv 19 Jun 2026.

## Placed in

- Vision-language-action models / [VLA for autonomous driving](https://mlsanity.com/vla/vla-for-autonomous-driving/)

## Builds on (most cited first, 23 of 23)

- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [VAD: Vectorized Scene Representation for Efficient Autonomous Driving](https://mlsanity.com/paper/2303.12077/) (2023)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model](https://mlsanity.com/paper/2310.01412/) (2023)
- [TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2409.12514/) (2024)
- [LMDrive: Closed-Loop End-to-End Driving with Large Language Models](https://mlsanity.com/paper/2312.07488/) (2023)
- [AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.13757/) (2025)
- [Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline](https://mlsanity.com/paper/2206.08129/) (2022)
- [Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes](https://mlsanity.com/paper/2305.10430/) (2023)
- [ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation](https://mlsanity.com/paper/2503.19755/) (2025)
- [CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving](https://mlsanity.com/paper/2408.10845/) (2024)
- [MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation](https://mlsanity.com/paper/2503.20384/) (2025)
- [EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism](https://mlsanity.com/paper/2312.04916/) (2023)
- [MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning](https://mlsanity.com/paper/2512.13636/) (2025)
- [TempBEV: Improving Learned BEV Encoders with Combined Image and BEV Space Temporal Aggregation](https://mlsanity.com/paper/2404.11803/) (2024)
- [RAEE: A Robust Retrieval-Augmented Early Exit Framework for Efficient Inference](https://mlsanity.com/paper/2405.15198/) (2024)
- [HiDP: Hierarchical DNN Partitioning for Distributed Inference on Heterogeneous Edge Platforms](https://mlsanity.com/paper/2411.16086/) (2024)
- [GM-Skip: Metric-Guided Transformer Block Skipping for Efficient Vision-Language Models](https://mlsanity.com/paper/2508.18227/) (2025)

## Abstract (arXiv)

Vision-Language-Action (VLA) models are becoming a promising paradigm for autonomous driving, but their deployment on existing vehicle platforms remains difficult because they introduce both high inference latency and strong GPU-side resource pressure. In a full autonomous driving stack, this problem is even more pronounced: legacy vehicle platforms were provisioned for modular pipelines, yet after several planning-related functions are absorbed into a unified VLA model, part of the original CPU budget becomes underutilized, while the visual encoder and the main reasoning path still concentrate most computation and memory demand on the GPU. As a result, directly deploying VLA together with the rest of the onboard system can be hard under realistic GPU memory constraints. To address this issue, we present a hybrid CPU--GPU inference framework with flexible resource scheduling for autonomous driving. Our design partitions the VLA backbone at the block-layer granularity, executes the visual encoder and LLM prefix on the GPU, and offloads the LLM suffix to the CPU through a cross-frame asynchronous pipeline, thereby exposing a schedulable boundary for redistributing compute and memory pressure across heterogeneous processors. We evaluate the proposed framework on two representative driving VLA models, Orion and MindDrive. On Bench2Drive, our method reduces average latency from 521ms to 408.0ms for Orion and from 443ms to 306.2ms for MindDrive, corresponding to 21.7% and 30.9% reduction, respectively. For Orion, the estimated peak GPU memory is further reduced from 45GB to 29GB. In real-vehicle deployment under coexistence with Autoware.Universe, native Orion cannot run because the onboard GPU memory budget is insufficient, whereas the hybrid version runs successfully together with the full vehicle stack.