Saved in:
Bibliographic Details
Main Authors: Koike-Akino, Toshiaki, Liu, Jing, Wang, Ye
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.19296
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918405648416768
author Koike-Akino, Toshiaki
Liu, Jing
Wang, Ye
author_facet Koike-Akino, Toshiaki
Liu, Jing
Wang, Ye
contents To tackle the huge computational demand of large foundation models, activation-aware compression techniques without retraining have been introduced. However, since these methods highly rely on calibration data, domain shift issues may arise for unseen downstream tasks. We propose a test-time quantization (TTQ) framework which compresses large models on the fly at inference time to resolve this issue. With an efficient online calibration, instant activation-aware quantization can adapt every prompt regardless of the downstream tasks, yet achieving inference speedup. Several experiments demonstrate that TTQ can improve the quantization performance over state-of-the-art baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2603_19296
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TTQ: Activation-Aware Test-Time Quantization to Accelerate LLM Inference On The Fly
Koike-Akino, Toshiaki
Liu, Jing
Wang, Ye
Machine Learning
Computation and Language
Signal Processing
To tackle the huge computational demand of large foundation models, activation-aware compression techniques without retraining have been introduced. However, since these methods highly rely on calibration data, domain shift issues may arise for unseen downstream tasks. We propose a test-time quantization (TTQ) framework which compresses large models on the fly at inference time to resolve this issue. With an efficient online calibration, instant activation-aware quantization can adapt every prompt regardless of the downstream tasks, yet achieving inference speedup. Several experiments demonstrate that TTQ can improve the quantization performance over state-of-the-art baselines.
title TTQ: Activation-Aware Test-Time Quantization to Accelerate LLM Inference On The Fly
topic Machine Learning
Computation and Language
Signal Processing
url https://arxiv.org/abs/2603.19296