Efficient VLA Model Inference

Vision-Language-Action (VLA) models exhibit remarkable action generation for embodied intelligence, but their heavy compute make deployment on edge platforms impractical. Aggressive, sub-4-bit weight quantization is the natural solution, yet existing post-training quantization (PTQ) methods suffer severe performance degradation in this regime. To address this, we introduce ActQuant, an action-guided mixed-precision PTQ framework that operates in two stages: (1) an inter-tensor bit allocator that assigns each weight matrix a single bit-width based on how much it contributes to predicting the agent's actions; (2) an intra-tensor scale optimizer tunes per-block quantization scales using action-aware curvature, so that dynamic range is concentrated on the weights most influential for control. To deliver the on-device benefits of our aggressive quantization, we further introduce OmniModel.cpp, an agentic conversion pipeline that ports architectures into a native C/C++ runtime with efficient low-bit kernels. We evaluate ActQuant both in simulation and on a real-world 6-DoF UR3 arm, with all models deployed through OmniModel.cpp. On the LIBERO benchmark, ActQuant is the only method that operates at or below 3 bits-per-weight, retaining 95.0% on OpenVLA-OFT and 94.8% on $π_{0.5}$. Pushed further, ActQuant reaches 2.5 bpw at 90.1% on OpenVLA-OFT, compressing the backbone from 14.3 GB to 2.7 GB (5.3$\times$). On the physical UR3 arm, $π_{0.5}$ quantized with ActQuant retains the baseline's success rate while reducing the memory footprint by 2.5$\times$.

Billion-parameter Vision-Language-Action (VLA) policies have recently shown impressive performance in robotic manipulation, yet their size and inference cost remain major obstacles for real-time closed-loop control. We introduce \textbf{VLA-AD}, a distillation framework that uses a Vision-Language Model as an offline semantic supervisor to transfer large VLA teachers into lightweight student policies. Instead of relying only on low-level action imitation, VLA-AD augments teacher-provided 7-DoF action targets with high-level semantic guidance, including task phase anchors and multi-frame operating-direction descriptions. These auxiliary signals are used only during training: at test time, the student policy runs independently, with neither the VLA teacher nor the VLM required. We evaluate VLA-AD on three LIBERO benchmark suites. Using OpenVLA-7B as the teacher, our method produces a 158M-parameter student, yielding a $44\times$ reduction in model size while matching the teacher with only a $0.27\%$ average relative gap. The resulting policy runs at 12.5 Hz on an RTX 4090, achieving a $3.28\times$ inference speedup over OpenVLA-7B. We further show that the same semantic distillation pipeline generalizes to a different $π_{0.5}$-4B teacher, where the student outperforms the teacher on two suites and remains within $0.53\%$ on \texttt{libero_goal}. Additional analysis indicates that phase-level supervision and multi-frame directional cues make the student less sensitive to noisy teacher actions, such as erroneous high-frequency gripper changes. Overall, VLA-AD demonstrates that offline semantic guidance from VLMs can substantially improve the efficiency, robustness, and deployability of VLA policy distillation.

Diffusion-based vision-language-action models (dVLAs) are promising for embodied intelligence but are fundamentally limited in real-time deployment by the high latency of full inference. We propose Realtime-VLA FLASH, a speculative inference framework that eliminates most full inference calls during replanning by introducing a lightweight draft model with parallel verification via the main model's Action Expert and a phase-aware fallback mechanism that reverts to the full inference pipeline when needed. This design enables low-latency, high-frequency replanning without sacrificing reliability. Experiments show that on LIBERO, FLASH largely preserves task performance by replacing many 58.0 ms full-inference rounds with speculative rounds as fast as 7.8 ms, lowering task-level average inference latency to 19.1 ms (3.04x speedup). We additionally demonstrate effectiveness on real-world conveyor-belt sorting, highlighting its practical impact for latency-critical embodied tasks.

End-to-end Vision-Language-Action (VLA) models for autonomous driving unify perception, reasoning, and control in a single neural network, achieving strong driving performance but requiring 20-60GB of GPU memory-far exceeding the 12-16GB available on commodity GPUs. We present a framework, which enables memory-efficient VLA inference on VRAM-constrained GPUs through system-level optimization alone, without model modification. Our work proceeds in three stages: (1) Sequential Demand Layering reduces VRAM usage from model-level to layer-level granularity; (2) Pipelined Demand Layering hides parameter transfer time within layer execution time via transfer--compute overlap; and (3) a GPU-Resident Layer Decision Policy, informed by per-module residency benefit analysis, eliminates the residual transfer overhead that pipelining cannot hide. We further propose a performance prediction model that determines the optimal configuration-both the number and placement of resident layers-from a single profiling run with less than 1.3% prediction error across all configurations. Applied to NVIDIA's Alpamayo-R1-10B (21.52GB) on an RTX 5070Ti (16GB), our work achieves up to 3.55x speedup over Accelerate offloading while maintaining full BF16 precision.

Current Vision-Language-Action (VLA) models typically treat the deepest representation of a vision-language backbone as universally optimal for action prediction. However, robotic manipulation is composed of many frequent closed-loop spatial adjustments, for which excessive abstraction may waste computation and weaken low-level geometric cues essential for precise control. Existing early-exit strategies attempt to reduce computation by stopping at predefined layers or applying heuristic rules such as action consistency, but they do not directly answer when a representation is actually sufficient for action. In this paper, we present LoopVLA, a recurrent VLA architecture that jointly learns representation refinement, action prediction, and sufficiency estimation. LoopVLA iteratively applies a shared Transformer block to refine multimodal tokens, and at each iteration produces both a candidate action and a sufficiency score that estimates whether further refinement is necessary. By sharing parameters across iterations, LoopVLA decouples refinement from absolute layer indices and grounds sufficiency estimation in the evolving representation itself. Since sufficiency has no direct supervision, we introduce a self-supervised distribution alignment objective, where intermediate confidence scores are trained to match the relative action quality across refinement steps, thereby linking sufficiency learning to policy optimization signals. Experiments on LIBERO, LIBERO-Plus, and VLA-Arena show that LoopVLA pushes the efficiency-performance frontier of VLA policies, reducing parameters by 45% and improving inference throughput by up to 1.7 times while matching or outperforming strong baselines in task success.

Vision-Language-Action (VLA) models offer a promising path to generalist robot control, but their inference latency causes observation staleness when generated actions are executed asynchronously. Several methods have been proposed concurrently to mitigate this problem: inference-time inpainting (IT-RTC), training-time delay simulation (TT-RTC), future-state-aware conditioning (VLASH), and lightweight residual correction (A2C2). Each takes a fundamentally different approach, but they have so far been evaluated independently with different codebases, base policies, and protocols. We present a systematic comparison of these four methods under controlled conditions. We develop two unified codebases that integrate all methods with harmonized library and dataset versions, and we benchmark them on the Kinetix suite with MLPMixer policies and on the LIBERO manipulation benchmark with SmolVLA, sweeping inference delays up to $d=20$ control steps. A2C2's per-step residual correction is the most effective method on Kinetix, holding above 90% solve rate up to $d=8$, and also leads on LIBERO from $d=4$ onwards. IT-RTC is competitive at low delays but degrades sharply under long chunks ($H=30$) and high delays. TT-RTC is the most robust training-based method: stable across d_\max choices, generalizes beyond its training delay distribution, and adds zero inference overhead. VLASH exhibits a clear low-delay vs. high-delay trade-off governed by the fine-tuning delay range [0,d_\max]. Code is available at https://github.com/TheAyos/async-vla-inference

Dual-system Vision-Language-Action (VLA) models achieve state-of-the-art robotic manipulation but are bottlenecked by the VLM backbone, which must execute at every control step while producing temporally redundant features. We propose Latent Bridge, a lightweight model that predicts VLM output deltas between timesteps, enabling the action head to operate on predicted outputs while the expensive VLM backbone is called only periodically. We instantiate Latent Bridge on two architecturally distinct VLAs: GR00T-N1.6 (feature-space bridge) and π0.5 (KV-cache bridge), demonstrating that the approach generalizes across VLA designs. Our task-agnostic DAgger training pipeline transfers across benchmarks without modification. Across four LIBERO suites, 24 RoboCasa kitchen tasks, and the ALOHA sim transfer-cube task, Latent Bridge achieves 95-100% performance retention while reducing VLM calls by 50-75%, yielding 1.65-1.73x net per-episode speedup.

Vision-Language-Action (VLA) models generalize semantically well but often lack fine-grained modeling of world dynamics. We present Motubrain, a unified World Action Model that jointly models video and action under a UniDiffuser formulation with a three-stream Mixture-of-Transformers architecture. A single model supports policy learning, world modeling, video generation, inverse dynamics, and joint video-action prediction, while scaling to heterogeneous multimodal data such as video-only, task-agnostic, and cross-embodiment robot data. Building on Motus, Motubrain further introduces unified multiview modeling, an independent text stream for stronger language-action coupling, a shared cross-embodiment action representation, and an efficient post-training and deployment recipe for long-horizon real-world control. Our inference stack combines step reduction, compilation, FP8 quantization, DiT caching, V2A-style action-only inference, and real-time chunked closed-loop execution, achieving over 50x speedup over a naive baseline and up to 11 Hz inference. Experimentally, Motubrain achieves 95.8% and 96.1% average success on RoboTwin 2.0 under clean and randomized settings, respectively, attains the strongest reported EWMScore in our WorldArena comparison, and adapts to new humanoid embodiments with only 50--100 trajectories. These results show that unified world action models can scale in generality, predictive accuracy, and real-world deployability.

Flow-based vision-language-action (VLA) policies offer strong expressivity for action generation, but suffer from a fundamental inefficiency: multi-step inference is required to recover action structure from uninformative Gaussian noise, leading to a poor efficiency-quality trade-off under real-time constraints. We address this issue by rethinking the role of the starting point in generative action modeling. Instead of shortening the sampling trajectory, we propose CF-VLA, a coarse-to-fine two-stage formulation that restructures action generation into a coarse initialization step that constructs an action-aware starting point, followed by a single-step local refinement that corrects residual errors. Concretely, the coarse stage learns a conditional posterior over endpoint velocity to transform Gaussian noise into a structured initialization, while the fine stage performs a fixed-time refinement from this initialization. To stabilize training, we introduce a stepwise strategy that first learns a controlled coarse predictor and then performs joint optimization. Experiments on CALVIN and LIBERO show that our method establishes a strong efficiency-performance frontier under low-NFE (Number of Function Evaluations) regimes: it consistently outperforms existing NFE=2 methods, matches or surpasses the NFE=10 $π_{0.5}$ baseline on several metrics, reduces action sampling latency by 75.4%, and achieves the best average real-robot success rate of 83.0%, outperforming MIP by 19.5 points and $π_{0.5}$ by 4.0 points. These results suggest that structured, coarse-to-fine generation enables both strong performance and efficient inference. Our code is available at https://github.com/EmbodiedAI-RoboTron/CF-VLA.

Vision-Language-Action (VLA) models are promising for generalist robot control, but on-robot deployment is bottlenecked by real-time inference under tight cost and energy budgets. Most prior evaluations rely on desktop-grade GPUs, obscuring the trade-offs and opportunities offered by heterogeneous edge accelerators (GPUs/XPUs/NPUs). We present a systematic analysis for low-cost VLA deployment via model-hardware co-characterization. First, we build a cross-accelerator leaderboard and evaluate model-hardware pairs under CET (Cost, Energy, Time), showing that right-sized edge devices can be more cost-/energy-efficient than flagship GPUs while meeting control-rate constraints. Second, using in-depth profiling, we uncover a consistent two-phase inference pattern: a compute-bound VLM backbone followed by a memory-bound Action Expert, which induces phase-dependent underutilization and hardware inefficiency. Finally, guided by these insights, we propose DP-Cache and V-AEFusion to reduce diffusion redundancy and enable asynchronous pipeline parallelism, achieving up to 2.9x speedup on GPUs and 6x on edge NPUs with only marginal success degradation. The example leaderboard website is available at: https://vla-leaderboard-01.vercel.app/.

Chain-of-Thought (CoT) reasoning has become a powerful driver of trajectory prediction in VLA-based autonomous driving, yet its autoregressive nature imposes a latency cost that is prohibitive for real-time deployment. Latent CoT methods attempt to close this gap by compressing reasoning into continuous hidden states, but consistently fall short of their explicit counterparts. We suggest that this is due to purely linguistic latent representations compressing a symbolic abstraction of the world, rather than the causal dynamics that actually govern driving. Thus, we present OneVL (One-step latent reasoning and planning with Vision-Language explanations), a unified VLA and World Model framework that routes reasoning through compact latent tokens supervised by dual auxiliary decoders. Alongside a language decoder that reconstructs text CoT, we introduce a visual world model decoder that predicts future-frame tokens, forcing the latent space to internalize the causal dynamics of road geometry, agent motion, and environmental change. A three-stage training pipeline progressively aligns these latents with trajectory, language, and visual objectives, ensuring stable joint optimization. In inference, the auxiliary decoders are discarded, and all latent tokens are prefilled in a single parallel pass, matching the speed of answer-only prediction. Across four benchmarks, OneVL becomes the first latent CoT method to surpass explicit CoT, delivering superior accuracy at answer-only latency. These results show that with world model supervision, latent CoT produces more generalizable representations than verbose token-by-token reasoning. Code has been open-sourced to the community. Project Page: https://xiaomi-embodied-intelligence.github.io/OneVL

Vision-language-action (VLA) models achieve favorable task performance, yet runtime errors in closed-loop execution evolve with alternating updates of actions and observations. Existing VLA quantization methods mainly trade off inference speed and model performance while rarely investigating how quantization alters runtime errors. By comparing error distributions between full-precision and quantized models, we identify distinct evolutionary patterns for the two types of errors: quantization enlarges the variance of translation error distributions and increases their dispersion, whereas the distribution center of rotation errors gradually shifts across execution steps, demonstrating cumulative drift. Motivated by this observation, we rethink the optimal quantization strategy for VLA models and propose \textit{DyQ-VLA}, a runtime-error-aware quantization framework, which dynamically selects activation precision according to execution steps and tracks as well as compensates rotation errors via accumulated quantization residuals. Corresponding operators and runtime adaptation strategies are devised within the framework to enable dynamic-precision execution. Experiments show that \textit{DyQ-VLA} achieves a 1.88 to 1.93 inference speedups while maintaining comparable or higher average task success rates. Moreover, it reduces mean execution steps by 17.7% to 19.8%. Our code is here: https://anonymous.4open.science/r/DyQ-VLA-7F51/.

Manipulating dynamic objects remains an open challenge for Vision-Language-Action (VLA) models. Although recent VLAs generalize well in static manipulation, dynamic scenes introduce a latency-induced perception-execution mismatch: object states continue to evolve during inference, making actions predicted from past observations stale at execution time. We present DynamicVLA, a latency-aware VLA model for dynamic object manipulation. It combines a compact 0.4B architecture and convolutional vision encoder for efficient multimodal inference with a continuous inference schedule that overlaps reasoning and execution for non-blocking control. Latent-aware Action Streaming then discards latency-invalid action prefixes and executes only the temporally valid suffix of each predicted chunk, preserving action-time alignment under dynamic object motion. To fill the missing foundation of dynamic manipulation data, we introduce the Dynamic Object Manipulation (DOM) benchmark, built with an automated collection pipeline that gathers 200K synthetic episodes across 2.8K scenes and 206 objects, and enables fast collection of 2K real-world episodes without teleoperation. Extensive evaluations in simulation and on real robots show that DynamicVLA improves dynamic manipulation success under changing object motion, perception-heavy instructions, and unseen motion patterns.

Recent large-scale Vision Language Action (VLA) models have shown superior performance in robotic manipulation tasks guided by natural language. However, current VLA models suffer from two drawbacks: (i) generation of massive tokens leading to high inference latency and increased training cost, and (ii) insufficient utilization of generated actions resulting in potential performance loss. To address these issues, we develop a training framework to finetune VLA models for generating significantly fewer action tokens with high parallelism, effectively reducing inference latency and training cost. Furthermore, we introduce an inference optimization technique with a novel voting-based ensemble strategy to combine current and previous action predictions, improving the utilization of generated actions and overall performance. Our results demonstrate that we achieve superior performance compared with state-of-the-art VLA models, achieving significantly higher success rates and 39$\times$ faster inference than OpenVLA with 46 Hz throughput on edge platforms, demonstrating practical deployability. The code is available at https://github.com/LukeLIN-web/VOTE.