ActQuant is a mixed‑precision post‑training quantization framework that reduces Vision‑Language‑Action model weights to sub‑4‑bit precision. It first allocates a single bit‑width to each weight matrix based on its contribution to action prediction, then optimizes per‑block scales using action‑aware curvature to focus dynamic range on control‑critical weights. Coupled with the OmniModel.cpp conversion pipeline, ActQuant enables deployment on edge devices, achieving up to 2.5 bits‑per‑weight while preserving over 90 % of baseline performance on both simulation and a real 6‑DoF UR3 robotic arm.
arXiv:2605. 24011v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models exhibit remarkable action generation for embodied intelligence, but their heavy compute make deployment on edge platforms impractical.
SACQ is a weight‑only vector‑codebook quantization framework designed for Vision‑Language‑Action models, addressing the challenges of ultra‑low‑bit precision. It incorporates structure‑aware codebook fitting, action‑aware mixed‑bit allocation, and a two‑stage post‑quantization refinement to maintain policy performance. Experiments on GR00T N1.7 and SimplER show that SACQ achieves high success rates (up to 93.85%) while reducing memory usage by 4.83× and improving inference speed.
arXiv:2610.33074v1 Announce Type: cross Abstract: Vision-language-action (VLA) models enable robots to perform tasks specified through natural-language instructions, but their large weight footprint...
arXiv:2605. 28803v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models unify perception, reasoning, and control in a single policy, but their multi-billion-parameter backbones and diffusion-based action heads make on-device deployment prohibitively expensive.
arXiv:2602. 13710v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models enable instruction-following embodied control, but their large compute and memory footprints hinder deployment on resource-constrained robots and edge platforms.
arXiv:2609.24433v1 Announce Type: cross Abstract: Low-bit vision-language-action inference must reduce observation-to-action latency while preserving robot behavior. We present FoldQuantVLA, a post-t...
arXiv:2605. 28803v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models unify perception, reasoning, and control within a single policy, yet their multi-billion-parameter backbones and diffusion-based action heads make on-device deployment prohibitively expensive.
arXiv:2608. 08081v1 Announce Type: cross Abstract: Large mixture-of-experts (MoE) language models with 26--120 billion parameters exceed the memory capacity of consumer devices through three simultaneous pressures: resident weight matrices, key-value (KV) cache state that grows linearly with context, and dozens of expert sublayers that must be paged on demand.
arXiv:2606. 08094v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies are typically shipped as Python/PyTorch stacks that assume a workstation-class GPU, a mismatch for the hardware on which robots actually run.
arXiv:2607. 14618v1 Announce Type: new Abstract: CPUs are the most universal target for on-device LLM inference, but existing low-bit quantization methods offer either coarse operating points or fine-grained mixed precision that is difficult to execute efficiently on CPUs.
Dynamic Expert Quantization (DynaExq) is a runtime-aware mixed-precision serving system designed for single‑GPU Mixture‑of‑Experts (MoE) inference under a hard high‑bandwidth memory (HBM) envelope. It treats the problem as an online, budget‑constrained precision allocation task, keeping the most frequently used experts at higher precision while relegating the rest to low‑precision fallbacks. By estimating expert hotness from router traces and asynchronously promoting or demoting experts, DynaExq maintains a fully materialized expert set during the forward pass, improving accuracy and throughput compared to static post‑training quantization and offloading/prefetch baselines. whyItMatters":"DynaExq enables efficient deployment of large MoE models on memory‑limited GPUs by dynamically allocating precision based on runtime expert usage, thereby reducing memory footprint and latency while boosting accuracy and throughput."
arXiv:2609.39223v2 Announce Type: new Abstract: Large language model (LLM) inference is increasingly moving toward lower precision to realize the throughput of hardware accelerators, but aggressive p...