English
Related papers

Related papers: COMET: Towards Partical W4A4KV4 LLMs Serving

200 papers

Model compression methods are used to reduce the computation and energy requirements for Large Language Models (LLMs). Quantization Aware Training (QAT), an effective model compression method, is proposed to reduce performance degradation…

Machine Learning · Computer Science 2024-10-16 He Li , Jianhang Hong , Yuanzhuo Wu , Snehal Adbol , Zonglin Li

We introduce QuaRot, a new Quantization scheme based on Rotations, which is able to quantize LLMs end-to-end, including all weights, activations, and KV cache in 4 bits. QuaRot rotates LLMs in a way that removes outliers from the hidden…

Large language models (LLMs) have transformed numerous AI applications. On-device LLM is becoming increasingly important: running LLMs locally on edge devices can reduce the cloud computing cost and protect users' privacy. However, the…

Computation and Language · Computer Science 2026-04-28 Ji Lin , Jiaming Tang , Haotian Tang , Shang Yang , Wei-Ming Chen , Wei-Chen Wang , Guangxuan Xiao , Xingyu Dang , Chuang Gan , Song Han

Weight-only quantization is widely used to mitigate the memory-bound nature of LLM inference. Codebook-based methods extend this trend by achieving strong accuracy in the extremely low-bit regime (e.g., 2-bit). However, current kernels rely…

Machine Learning · Computer Science 2025-12-23 Gunho Park , Jeongin Bae , Byeongwook Kim , Baeseong park , Jiwon Ryu , Hoseung Kim , Se Jung Kwon , Dongsoo Lee

Quantizing large language models (LLMs) to 1-bit precision significantly reduces computational costs, but existing quantization techniques suffer from noticeable performance degradation when using weight and activation precisions below 4…

Machine Learning · Computer Science 2025-07-01 Siqing Song , Chuang Wang , Ruiqi Wang , Yi Yang , Xu-Yao Zhang

As large language models (LLMs) scale, model compression is crucial for edge deployment and accessibility. Weight-only quantization reduces model size but suffers from performance degradation at lower bit widths. Moreover, standard…

Computation and Language · Computer Science 2025-06-03 Baohao Liao , Christian Herold , Seyyed Hadi Hashemi , Stefan Vasilev , Shahram Khadivi , Christof Monz

Post-training quantization (PTQ) is essential for deploying large diffusion transformers on resource-constrained hardware, but aggressive 4-bit quantization significantly degrades generative performance. Low-rank approximation methods have…

Machine Learning · Computer Science 2026-04-21 Yann Bouquet , Alireza Khodamoradi , Sophie Yáng Shen , Kristof Denolf , Mathieu Salzmann

Quantization is essential for efficient large language model (LLM) inference, yet the dequantization step-converting low-bit weights back to high-precision for matrix multiplication has become a critical bottleneck on modern AI…

Machine Learning · Statistics 2026-05-15 Lingchao Zheng , Yuwei Fan , Jun Li , Chengqiu Hu , Qichen Liao , Junyi Fan , Rui Shi , Fangzheng Miao

Large language models (LLMs) have shown promising performance across various tasks. However, their autoregressive decoding process poses significant challenges for efficient deployment on existing AI hardware. Quantization alleviates memory…

Machine Learning · Computer Science 2025-12-01 Guanxi Lu , Hao Mark Chen , Zhiqiang Que , Wayne Luk , Hongxiang Fan

Recently, significant progress has been made in developing reasoning-capable Large Language Models (LLMs) through long Chain-of-Thought (CoT) techniques. However, this long-CoT reasoning process imposes substantial memory overhead due to…

Computation and Language · Computer Science 2025-05-27 Tengxuan Liu , Shiyao Li , Jiayi Yang , Tianchen Zhao , Feng Zhou , Xiaohui Song , Guohao Dai , Shengen Yan , Huazhong Yang , Yu Wang

Large language models (LLMs) show impressive performance in solving complex language tasks. However, its large number of parameters presents significant challenges for the deployment. So, compressing LLMs to low bits can enable to deploy on…

Deploying Large Language Models (LLMs) on edge devices is increasingly important, as it eliminates reliance on network connections, reduces expensive API calls, and enhances user privacy. However, on-device deployment is challenging due to…

Machine Learning · Computer Science 2025-05-26 Yijiang Liu , Hengyu Fang , Liulu He , Rongyu Zhang , Yichuan Bai , Yuan Du , Li Du

We propose a simple approach for memory-efficient adaptation of pretrained language models. Our approach uses an iterative algorithm to decompose each pretrained matrix into a high-precision low-rank component and a memory-efficient…

Computation and Language · Computer Science 2024-08-28 Han Guo , Philip Greengard , Eric P. Xing , Yoon Kim

Large language models (LLMs) deliver impressive results for a variety of tasks, but state-of-the-art systems require fast GPUs with large amounts of memory. To reduce both the memory and latency of these systems, practitioners quantize…

Computer Vision and Pattern Recognition · Computer Science 2026-01-22 Gautom Das , Vincent La , Ethan Lau , Abhinav Shrivastava , Matthew Gwilliam

We propose Rotate, Clip, and Partition (RCP), a quantization-aware training (QAT) approach that first realizes extreme compression of LLMs with W2A4KV4(2-bit weight, 4-bit activation, and 4-bit KV cache) configuration. RCP integrates recent…

Machine Learning · Computer Science 2025-09-03 Euntae Choi , Sumin Song , Woosang Lim , Sungjoo Yoo

Large language models (LLMs) face the challenges in fine-tuning and deployment due to their high memory demands and computational costs. While parameter-efficient fine-tuning (PEFT) methods aim to reduce the memory usage of the optimizer…

Machine Learning · Computer Science 2023-10-31 Jeonghoon Kim , Jung Hyun Lee , Sungdong Kim , Joonsuk Park , Kang Min Yoo , Se Jung Kwon , Dongsoo Lee

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 (LLMs) have achieved outstanding performance across a wide range of natural language processing tasks, but their enormous parameter counts impose ubstantial memory and computational overheads. This challenge is…

Machine Learning · Computer Science 2026-04-07 Seoungsub Lee , In Seo Kim , Seon Wook Kim

The key-value (KV) cache in large language models presents a significant memory bottleneck during inference, growing linearly with sequence length and often exceeding the memory footprint of model weights themselves. We implement and…

Machine Learning · Computer Science 2026-01-09 Maanas Taneja , Purab Shingvi

Generative Large Language Models (LLMs) have demonstrated remarkable results for a wide range of tasks. However, deploying these models for inference has been a significant challenge due to their unprecedented resource requirements. This…

Computation and Language · Computer Science 2024-06-06 Sehoon Kim , Coleman Hooper , Amir Gholami , Zhen Dong , Xiuyu Li , Sheng Shen , Michael W. Mahoney , Kurt Keutzer
‹ Prev 1 3 4 5 6 7 10 Next ›