Saved in:
Bibliographic Details
Main Authors: Zhang, Jinghe, Xu, Daliang, Wang, Chenghua, Xie, Weikai, Qi, Tao, Ma, Yun, Xu, Mengwei, Huang, Gang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.20295
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910237213065216
author Zhang, Jinghe
Xu, Daliang
Wang, Chenghua
Xie, Weikai
Qi, Tao
Ma, Yun
Xu, Mengwei
Huang, Gang
author_facet Zhang, Jinghe
Xu, Daliang
Wang, Chenghua
Xie, Weikai
Qi, Tao
Ma, Yun
Xu, Mengwei
Huang, Gang
contents Large language models (LLMs) are increasingly deployed on mobile devices, where Neural Processing Units (NPUs) necessitate fully static quantization for optimal inference efficiency. However, existing post-training quantization (PTQ) methods predominantly rely on dynamic activation quantization, rendering them incompatible with NPU hardware constraints. To bridge the gap between high-fidelity PTQ and NPU-constrained inference, we propose Quant.npu, a integer-only fully static quantization framework. It incorporates learnable quantization parameters and rotation matrices, enabling low-bit activation-weight quantization without runtime quantization parameters re-computation. Crucially, we identify that initialization and selective optimization of quantization parameters is pivotal for optimization stability, as improper initialization and naive joint optimization induce gradient instability that disrupts the optimization of rotation matrices. To address this, we propose a rotation-and-bit-width-aware initialization tailored to diverse activation profiles and a distribution-aware selective optimization (two-stage quantization pipeline) tailored to rotated and unrotated tensors. Furthermore, we introduce a sensitivity-guided adaptive mixed-precision scheme to balance accuracy with inference efficiency. Extensive experiments on real-world mobile NPUs demonstrate that Quant.npu achieves comparable accuracy to state-of-the-art methods, while reducing inference latency by up to 15.1%.
format Preprint
id arxiv_https___arxiv_org_abs_2605_20295
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Quant.npu: Enabling Efficient Mobile NPU Inference for on-device LLMs via Fully Static Quantization
Zhang, Jinghe
Xu, Daliang
Wang, Chenghua
Xie, Weikai
Qi, Tao
Ma, Yun
Xu, Mengwei
Huang, Gang
Machine Learning
Artificial Intelligence
Large language models (LLMs) are increasingly deployed on mobile devices, where Neural Processing Units (NPUs) necessitate fully static quantization for optimal inference efficiency. However, existing post-training quantization (PTQ) methods predominantly rely on dynamic activation quantization, rendering them incompatible with NPU hardware constraints. To bridge the gap between high-fidelity PTQ and NPU-constrained inference, we propose Quant.npu, a integer-only fully static quantization framework. It incorporates learnable quantization parameters and rotation matrices, enabling low-bit activation-weight quantization without runtime quantization parameters re-computation. Crucially, we identify that initialization and selective optimization of quantization parameters is pivotal for optimization stability, as improper initialization and naive joint optimization induce gradient instability that disrupts the optimization of rotation matrices. To address this, we propose a rotation-and-bit-width-aware initialization tailored to diverse activation profiles and a distribution-aware selective optimization (two-stage quantization pipeline) tailored to rotated and unrotated tensors. Furthermore, we introduce a sensitivity-guided adaptive mixed-precision scheme to balance accuracy with inference efficiency. Extensive experiments on real-world mobile NPUs demonstrate that Quant.npu achieves comparable accuracy to state-of-the-art methods, while reducing inference latency by up to 15.1%.
title Quant.npu: Enabling Efficient Mobile NPU Inference for on-device LLMs via Fully Static Quantization
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2605.20295