English
Related papers

Related papers: RaZeR: Pushing the Limits of NVFP4 Quantization wi…

200 papers

Catastrophic forgetting poses a fundamental challenge in continual learning, particularly when models are quantized for deployment efficiency. We systematically investigate the interplay between quantization precision (FP16, INT8, INT4) and…

Machine Learning · Computer Science 2025-12-23 Michael S. Zhang , Rishi A. Ruia , Arnav Kewalram , Saathvik Dharmapuram , Utkarsh Sharma , Kevin Zhu

Neural network quantization is widely used to reduce model inference complexity in real-world deployments. However, traditional integer quantization suffers from accuracy degradation when adapting to various dynamic ranges. Recent research…

Performance · Computer Science 2023-10-30 Zhuoyi Zhang , Yunchen Zhang , Gonglei Shi , Yu Shen , Ruihao Gong , Xiaoxu Xia , Qi Zhang , Lewei Lu , Xianglong Liu

Ternary large language models (LLMs), which utilize ternary precision weights and 8-bit activations, have demonstrated competitive performance while significantly reducing the high computational and memory requirements of full-precision…

Hardware Architecture · Computer Science 2025-06-03 Akul Malhotra , Sumeet Kumar Gupta

While building machine learning models, Feature selection (FS) stands out as an essential preprocessing step used to handle the uncertainty and vagueness in the data. Recently, the minimum Redundancy and Maximum Relevance (mRMR) approach…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-07-25 Yelleti Vivek , P. S. V. S. Sai Prasad

Six-bit quantization (FP6) can effectively reduce the size of large language models (LLMs) and preserve the model quality consistently across varied applications. However, existing systems do not provide Tensor Core support for FP6…

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

Large language models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks. However, their exponentially increasing parameters pose significant challenges for deployment on…

Machine Learning · Computer Science 2025-10-03 Zukang Xu , Xing Hu , Qiang Wu , Dawei Yang

Large language models demand massive computational power and memory resources, posing significant challenges for efficient deployment. While quantization has been widely explored to reduce model size and computation, this paper demonstrates…

Hardware Architecture · Computer Science 2025-09-29 Soroush Ahadi , Mehdi Modarressi , Masoud Daneshtalab

As large language models become increasingly prevalent, memory bandwidth constraints significantly limit inference throughput, motivating post-training quantization (PTQ). In this paper, we propose FireQ, a co-designed PTQ framework and an…

Machine Learning · Computer Science 2025-07-21 Daehyeon Baek , Jieun Choi , Jimyoung Son , Kyungmin Bin , Seungbeom Choi , Kihyo Moon , Minsung Jang , Hyojung Lee

Modern AI hardware, such as Nvidia's Blackwell architecture, is increasingly embracing low-precision floating-point (FP) formats to handle the pervasive activation outliers in Large Language Models (LLMs). Despite this industry trend, a…

Machine Learning · Computer Science 2025-10-30 Mengzhao Chen , Meng Wu , Hui Jin , Zhihang Yuan , Jing Liu , Chaoyi Zhang , Yunshui Li , Jie Huang , Jin Ma , Zeyue Xue , Zhiheng Liu , Xingyan Bin , Ping Luo

The inference of Large language models (LLMs) requires immense computation and memory resources. To curtail these costs, quantisation has merged as a promising solution, but existing LLM quantisation mainly focuses on 8-bit. In this work,…

Machine Learning · Computer Science 2024-03-15 Cheng Zhang , Jianyi Cheng , Ilia Shumailov , George A. Constantinides , Yiren Zhao

We introduce ReALLM, a novel approach for compression and memory-efficient adaptation of pre-trained language models that encompasses most of the post-training quantization and fine-tuning methods for a budget of <4 bits. Pre-trained…

Machine Learning · Computer Science 2024-05-24 Louis Leconte , Lisa Bedin , Van Minh Nguyen , Eric Moulines

Retrieval-augmented generation (RAG) has become a dominant paradigm for grounding large language models (LLMs) with external evidence in knowledge-intensive question answering. A core design choice is how to fuse retrieved samples into the…

Computation and Language · Computer Science 2026-02-16 Yixin Chen , Ying Xiong , Shangyu Wu , Xiangrui Ke , Nan Guan , Chun Jason Xue

The immense computational cost of training Large Language Models (LLMs) presents a major barrier to innovation. While FP8 training offers a promising solution with significant theoretical efficiency gains, its widespread adoption has been…

Computation and Language · Computer Science 2025-10-20 Wenjun Wang , Shuo Cai , Congkai Xie , Mingfa Feng , Yiming Zhang , Zhen Li , Kejing Yang , Ming Li , Jiannong Cao , Hongxia Yang

Large Language Models (LLMs) demonstrate exceptional performance but entail significant memory and computational costs, restricting their practical deployment. While existing INT4/INT8 quantization reduces these costs, they often degrade…

Machine Learning · Computer Science 2025-11-04 Hao Zhang , Aining Jia , Weifeng Bu , Yushu Cai , Kai Sheng , Hao Chen , Xin He

In information retrieval, proprietary large language models (LLMs) such as GPT-4 and open-source counterparts such as LLaMA and Vicuna have played a vital role in reranking. However, the gap between open-source and closed models persists,…

Information Retrieval · Computer Science 2023-12-06 Ronak Pradeep , Sahel Sharifymoghaddam , Jimmy Lin

Speculative decoding (SD) is a widely used approach for accelerating decode-heavy LLM inference workloads. While online inference workloads are highly dynamic, existing SD systems are rigid and take a coarse-grained approach to SD…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-23 Wenyan Chen , Chengzhi Lu , Yanying Lin , Dmitrii Ustiugov

A new coding scheme for image transmission over noisy channel is proposed. Similar to standard image compression, the scheme includes a linear transform followed by successive refinement scalar quantization. Unlike conventional schemes, in…

Information Theory · Computer Science 2012-10-03 Ozgun Y. Bursalioglu , Giuseppe Caire , Dariush Divsalar

Key-value (KV) caching has become the de-facto to accelerate generation speed for large language models (LLMs) inference. However, the growing cache demand with increasing sequence length has transformed LLM inference to be a memory bound…

Machine Learning · Computer Science 2024-10-02 Hao Kang , Qingru Zhang , Souvik Kundu , Geonhwa Jeong , Zaoxing Liu , Tushar Krishna , Tuo Zhao

Large Language Models (LLMs) face significant deployment challenges due to their substantial resource requirements. While low-bit quantized weights can reduce memory usage and improve inference efficiency, current hardware lacks native…

Machine Learning · Computer Science 2025-06-10 Pengxiang Zhao , Xiaoming Yuan