A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference

• URL: http://arxiv.org/abs/2607.24148v1
• Date: Mon, 27 Jul 2026 08:29:05 GMT
• Title: A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference
• Abstract summary: Vision-Language-Action (VLA) models have demonstrated strong potential for embodied AI, yet their high inference latency on GPU limits real-time deployment.<n>We propose VQVLA, an algorithm-hardware co-design framework that accelerates VLA inference by exploiting weight similarity and execution dynamics.<n>VQVLA achieves 6.5x, 2.8x, 1.9x, 3.3x, and 4.3x speedup over the A100 GPU, Dadu-Corki, LUT-DLA, CodeGEMM, and ShiftAddLLM, respectively, with negligible accuracy degradation.
• Score: 16.66163943624991
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Vision-Language-Action (VLA) models have demonstrated strong potential for embodied AI, yet their high inference latency on GPUs limits real-time deployment. Existing accelerators, such as Dadu-Corki, improve efficiency but treat VLA models as full-precision workloads, leaving substantial redundancy in both memory and computation underexploited. In this paper, we propose VQVLA, an algorithm-hardware co-design framework that accelerates VLA inference by exploiting weight similarity and execution dynamics. We first introduce MotionVQ, a motion-aware vector quantization scheme that dynamically adjusts quantization precision based on the robot's execution state, reducing memory access while preserving task success rate. We then propose a merged-centroid vectorized GEMM paradigm that operates on the codebook-index representation, eliminating redundant multiplications through spatial aggregation and temporal reuse of centroids. To realize these optimizations, we design an accelerator that efficiently supports dynamic precision selection and centroid-reuse computation. Experimental results show that VQVLA achieves 6.5x, 2.8x, 1.9x, 3.3x, and 4.3x speedup over the A100 GPU, Dadu-Corki, LUT-DLA, CodeGEMM, and ShiftAddLLM, respectively, with negligible accuracy degradation.

Related papers

• Deltoris: Enabling Real-time VLA Inference in Embodied AI via Bit-level Sparsity and Speculative Inference [40.7778980764007]
  Vision--action (VLA) models have emerged as a key component in embodied AI.<n>We present Deltoris, an algorithm-hardware co-design framework for efficient diffusion-based VLA inference.
  arXiv  Detail & Related papers  (2026-08-05T04:17:03Z)
• DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models [61.26694413585136]
  Drift-Aware Post-Training Quantization (DA-PTQ) formulates quantization as a drift-aware optimization problem over sequential decision processes.<n>DA-PTQ significantly reduces kinematic drift and achieves comparable performance to full-precision models under low-bit settings.
  arXiv  Detail & Related papers  (2026-04-13T14:51:43Z)
• AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization [84.25316984309725]
  Integration of dynamic, sparse structures with parameter-efficient adapters (e.g., LoRA) is a powerful technique for enhancing Large Language Models (LLMs)<n>Despite minimal increases in computational load, the computation latency often skyrockets, leading to decoding speeds slowing by over 2.5 times.<n>AdaFuse is a framework built on a tight co-design between the algorithm and the underlying hardware system to enable efficient dynamic adapter execution.
  arXiv  Detail & Related papers  (2026-03-12T12:46:42Z)
• Learning to Accelerate Vision-Language-Action Models through Adaptive Visual Token Caching [25.295588774254952]
  We reformulate inference acceleration as a learnable policy optimization problem.<n>We propose a novel framework that integrates a task-aware decision-making process directly into the Vision-Language-Action model.<n>Our method achieves a 1.76x wall-clock inference speedup while simultaneously improving the average success rate.
  arXiv  Detail & Related papers  (2026-01-31T12:12:51Z)
• DCO: Dynamic Cache Orchestration for LLM Accelerators through Predictive Management [2.5993532871616027]
  We propose a multi-core AI accelerator equipped with a shared system-level cache and application-aware management policies.<n>We observe substantial performance gains (up to 1.80x speedup) compared with conventional cache architectures.<n>Our findings explore the potential of the shared cache design to assist the development of future AI accelerator systems.
  arXiv  Detail & Related papers  (2025-12-08T08:56:10Z)
• Orthogonal Finetuning Made Scalable [92.34573849209238]
  Orthogonal finetuning (OFT) offers highly parameter-efficient adaptation while preventing catastrophic forgetting, but its high runtime and memory demands limit practical deployment.<n>We identify the core computational bottleneck in OFT as its weight-centric implementation, which relies on costly matrix-matrix multiplications with cubic complexity.<n>We propose OFTv2, an input-centric reformulation that instead uses matrix-vector multiplications (i.e., matrix-free computation), reducing the computational cost to quadratic.<n>These modifications allow OFTv2 to achieve up to 10x faster training and 3x lower GPU memory usage without
  arXiv  Detail & Related papers  (2025-06-24T17:59:49Z)
• SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration [70.72227437717467]
  Vision-Language-Action (VLA) models have attracted increasing attention for their strong control capabilities.<n>Their high computational cost and low execution frequency hinder their suitability for real-time tasks such as robotic manipulation and autonomous navigation.<n>We propose SP-VLA, a unified framework that accelerates VLA models by jointly scheduling models and pruning tokens.
  arXiv  Detail & Related papers  (2025-06-15T05:04:17Z)
• Accelerating 3D Gaussian Splatting with Neural Sorting and Axis-Oriented Rasterization [14.87046071090259]
  3D Gaussian Splatting (3DGS) has recently gained significant attention for high-quality and efficient view synthesis.<n>Despite its impressive algorithmic performance, real-time rendering on resource-constrained devices remains a major challenge due to tight power and area budgets.
  arXiv  Detail & Related papers  (2025-06-08T10:14:54Z)
• QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge [55.75103034526652]
  We propose QuartDepth which adopts post-training quantization to quantize MDE models with hardware accelerations for ASICs.<n>Our approach involves quantizing both weights and activations to 4-bit precision, reducing the model size and computation cost.<n>We design a flexible and programmable hardware accelerator by supporting kernel fusion and customized instruction programmability.
  arXiv  Detail & Related papers  (2025-03-20T21:03:10Z)
• Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding [24.1236728596359]
  Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation.<n>We propose PD-VLA, the first parallel decoding framework for VLA models integrated with action chunking.<n>Our framework reformulates autoregressive decoding as a nonlinear system solved by parallel fixed-point iterations.
  arXiv  Detail & Related papers  (2025-03-04T06:12:08Z)
• Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores [3.6385567224218556]
  Large language models (LLMs) have been widely applied but face challenges in efficient inference. We introduce a novel bipolar-INT data format that facilitates parallel computing and supports symmetric quantization. We implement an arbitrary precision matrix multiplication scheme that decomposes and recovers at the bit level, enabling flexible precision.
  arXiv  Detail & Related papers  (2024-09-26T14:17:58Z)
• Latency-aware Unified Dynamic Networks for Efficient Image Recognition [72.8951331472913]
  LAUDNet is a framework to bridge the theoretical and practical efficiency gap in dynamic networks. It integrates three primary dynamic paradigms-spatially adaptive computation, dynamic layer skipping, and dynamic channel skipping. It can notably reduce the latency of models like ResNet by over 50% on platforms such as V100,3090, and TX2 GPUs.
  arXiv  Detail & Related papers  (2023-08-30T10:57:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.