English
Related papers

Related papers: Statistically-Lossless Quantization of Large Langu…

200 papers

Large Language Models (LLMs) have demonstrated exceptional code generation capabilities, yet their token-level mechanisms remain underexplored, particularly in compressed models. Through systematic analysis of programming language token…

Software Engineering · Computer Science 2026-02-10 Viacheslav Siniaev , Iaroslav Chelombitko , Aleksey Komissarov

Large language models (LLMs) have demonstrated remarkable capabilities in various kinds of tasks, while the billion or even trillion parameters bring storage and efficiency bottlenecks for inference. Quantization, particularly…

Machine Learning · Computer Science 2025-10-21 Mengtao Lv , Ruiqi Zhu , Xinyu Wang , Yun Li

Quantization stands as a pivotal technique for large language model (LLM) serving, yet it poses significant challenges particularly in achieving effective low-bit quantization. The limited numerical mapping makes the quantized model produce…

Machine Learning · Computer Science 2024-12-13 Weibo Zhao , Yubin Shi , Xinyu Lyu , Wanchen Sui , Shen Li , Yong Li

Memoryless scalar quantization (MSQ) is a common technique to quantize frame coefficients of signals (which are used as a model for generalized linear samples), making them compatible with our digital technology. The process of quantization…

Numerical Analysis · Computer Science 2020-09-15 Kateryna Melnykova , Ozgur Yilmaz

Supervised Fine-Tuning (SFT) accelerates taskspecific large language models (LLMs) development, but the resulting proliferation of finetuned models incurs substantial memory overhead. Delta compression addresses this by retaining a single…

Machine Learning · Computer Science 2026-04-21 Junlin Li , Shuangyong Song , Guodong Du , Ngai Wong , Xuebo Liu , Yongxiang Li , Min Zhang , Jing Li , Xuelong Li

Large Language Models (LLMs) have revolutionized natural language processing tasks. However, their practical application is constrained by substantial memory and computational demands. Post-training quantization (PTQ) is considered an…

Machine Learning · Computer Science 2025-07-29 Chao Zeng , Songwei Liu , Yusheng Xie , Hong Liu , Xiaojian Wang , Miao Wei , Shu Yang , Fangmin Chen , Xing Mei

Large language models have achieved significant advancements in complex mathematical reasoning benchmarks, such as MATH. However, their substantial computational requirements present challenges for practical deployment. Model quantization…

Computation and Language · Computer Science 2025-02-25 Zhen Li , Yupeng Su , Runming Yang , Congkai Xie , Zheng Wang , Zhongwei Xie , Ngai Wong , Hongxia Yang

Large Language Models (LLMs) face significant deployment challenges due to their substantial memory requirements and the computational demands of auto-regressive text generation process. This paper addresses these challenges by focusing on…

Machine Learning · Computer Science 2024-02-21 Yuxuan Yue , Zhihang Yuan , Haojie Duanmu , Sifan Zhou , Jianlong Wu , Liqiang Nie

Model compression has become an emerging need as the sizes of modern speech systems rapidly increase. In this paper, we study model weight quantization, which directly reduces the memory footprint to accommodate computationally…

Model quantization is known as a promising method to compress deep neural networks, especially for inferences on lightweight mobile or edge devices. However, model quantization usually requires access to the original training data to…

Machine Learning · Computer Science 2021-11-05 Kanghyun Choi , Deokki Hong , Noseong Park , Youngsok Kim , Jinho Lee

We investigate the effects of post-training quantization and quantization-aware training on the generalization of Transformer language models. We present a new method called self-distilled quantization (SDQ) that minimizes accumulative…

Computation and Language · Computer Science 2023-07-13 James O' Neill , Sourav Dutta

When does a large language model (LLM) know what it does not know? Uncertainty quantification (UQ) provides measures of uncertainty, such as an estimate of the confidence in an LLM's generated output, and is therefore increasingly…

Computation and Language · Computer Science 2025-10-17 Debarun Bhattacharjya , Balaji Ganesan , Junkyu Lee , Radu Marinescu , Katsiaryna Mirylenka , Michael Glass , Xiao Shou

Large Language Models (LLMs) have achieved remarkable progress across reasoning, generation, and decision-making tasks, yet deploying them on mobile, embedded, and edge devices remains particularly challenging. On-device LLM inference is…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Sayed Pedram Haeri Boroujeni , Niloufar Mehrabi , Patrick Woods , Gabriel Hillesheim , Abolfazl Razi

Large language models (LLMs) show great performance in various tasks, but face deployment challenges from limited memory capacity and bandwidth. Low-bit weight quantization can save memory and accelerate inference. Although floating-point…

Computation and Language · Computer Science 2023-11-06 Yijia Zhang , Sicheng Zhang , Shijie Cao , Dayou Du , Jianyu Wei , Ting Cao , Ningyi Xu

Quantization is a promising approach for reducing memory overhead and accelerating inference, especially in large pre-trained language model (PLM) scenarios. While having no access to original training data due to security and privacy…

Computation and Language · Computer Science 2023-10-23 Miaoxi Zhu , Qihuang Zhong , Li Shen , Liang Ding , Juhua Liu , Bo Du , Dacheng Tao

Uncertainty quantification approaches have been more critical in large language models (LLMs), particularly high-risk applications requiring reliable outputs. However, traditional methods for uncertainty quantification, such as…

Artificial Intelligence · Computer Science 2024-07-01 Ferhat Ozgur Catak , Murat Kuzlu

Large language model (LLM) tokenizers act as structured compressors: by mapping text to discrete token sequences, they determine token count (and thus compute and context usage) and the statistical structure seen by downstream models.…

Information Theory · Computer Science 2026-01-15 Mete Erdogan , Abhiram Gorle , Shubham Chandak , Mert Pilanci , Tsachy Weissman

Quantization is widely used to accelerate inference and streamline the deployment of large language models (LLMs), yet its effects on self-explanations (SEs) remain unexplored. SEs, generated by LLMs to justify their own outputs, require…

Computation and Language · Computer Science 2026-01-05 Qianli Wang , Nils Feldhus , Pepa Atanasova , Fedor Splitt , Simon Ostermann , Sebastian Möller , Vera Schmitt

To enable broader deployment of Large Language Models (LLMs), it is essential to identify the best-performing model under strict memory constraints. We present AMQ, Automated Mixed-Precision Weight-Only Quantization, a framework that…

Machine Learning · Computer Science 2025-09-16 Sangjun Lee , Seung-taek Woo , Jungyu Jin , Changhun Lee , Eunhyeok Park

Parameter quantization for Large Language Models (LLMs) has attracted increasing attentions recently in reducing memory costs and improving computational efficiency. Early approaches have been widely adopted. However, the existing methods…

Machine Learning · Computer Science 2024-06-04 Haoyu Wang , Bei Liu , Hang Shao , Bo Xiao , Ke Zeng , Guanglu Wan , Yanmin Qian