English
Related papers

Related papers: MILLION: Mastering Long-Context LLM Inference Via …

200 papers

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

Quantization is an effective approach to reduce the memory footprint and inference cost of large language models (LLMs), yet maintaining performance in the ultra-low-bit regime remains challenging. Existing post-training methods often…

Machine Learning · Computer Science 2026-05-27 Phong Nam Huu Nguyen , Khoi M. Le , Cong-Duy T Nguyen , Anh Tuan Luu , Thong Thanh Nguyen , Tho Quan

Long-context Multimodal Large Language Models (MLLMs) demand substantial computational resources for inference as the growth of their multimodal Key-Value (KV) cache, in response to increasing input lengths, challenges memory and time…

Computation and Language · Computer Science 2024-06-27 Zhongwei Wan , Ziang Wu , Che Liu , Jinfa Huang , Zhihong Zhu , Peng Jin , Longyue Wang , Li Yuan

This paper presents a comprehensive analysis of quantization techniques for optimizing Large Language Models (LLMs), specifically focusing on Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT). Through empirical…

Machine Learning · Computer Science 2024-11-12 Jahid Hasan

Today's large language models (LLMs) typically train on short text segments (e.g., <4K tokens) due to the quadratic complexity of their Transformer architectures. As a result, their performance suffers drastically on inputs longer than…

Computation and Language · Computer Science 2024-06-26 Chi Han , Qifan Wang , Hao Peng , Wenhan Xiong , Yu Chen , Heng Ji , Sinong Wang

Transformer-based large language models (LLMs) have achieved remarkable success as model sizes continue to grow, yet their deployment remains challenging due to significant computational and memory demands. Quantization has emerged as a…

Machine Learning · Computer Science 2024-11-26 Yu Zhang , Mingzi Wang , Lancheng Zou , Wulong Liu , Hui-Ling Zhen , Mingxuan Yuan , Bei Yu

As the demand for long-context large language models (LLMs) increases, models with context windows of up to 128K or 1M tokens are becoming increasingly prevalent. However, long-context LLM inference is challenging since the inference speed…

Computation and Language · Computer Science 2024-08-28 Jiaming Tang , Yilong Zhao , Kan Zhu , Guangxuan Xiao , Baris Kasikci , Song Han

Large language models (LLMs) are one of the most important killer computer applications. The recent algorithmic advancement proposes a fine-grained group-wise quantization for LLMs, which treats a small set (e.g., 64) of values in a tensor…

Hardware Architecture · Computer Science 2025-02-27 Weiming Hu , Haoyan Zhang , Cong Guo , Yu Feng , Renyang Guan , Zhendong Hua , Zihan Liu , Yue Guan , Minyi Guo , Jingwen Leng

Large language models can be quantized to reduce inference time latency, model size, and energy consumption, thereby delivering a better user experience at lower cost. A challenge exists to deliver quantized models with minimal loss of…

Machine Learning · Computer Science 2025-07-24 Steven K. Esser , Jeffrey L. McKinstry , Deepika Bablani , Rathinakumar Appuswamy , Dharmendra S. Modha

Quantization is wildly taken as a model compression technique, which obtains efficient models by converting floating-point weights and activations in the neural network into lower-bit integers. Quantization has been proven to work well on…

Computer Vision and Pattern Recognition · Computer Science 2022-09-15 Lingran Zhao , Zhen Dong , Kurt Keutzer

Large language models (LLMs) have revolutionized natural language processing tasks. However, their practical deployment is hindered by their immense memory and computation requirements. Although recent post-training quantization (PTQ)…

Machine Learning · Computer Science 2024-03-19 Wenqi Shao , Mengzhao Chen , Zhaoyang Zhang , Peng Xu , Lirui Zhao , Zhiqian Li , Kaipeng Zhang , Peng Gao , Yu Qiao , Ping Luo

The KV cache in large language models is a dominant factor in memory usage, limiting their broader applicability. Quantizing the cache to lower bit widths is an effective way to reduce computational costs; however, previous methods struggle…

Machine Learning · Computer Science 2025-02-04 Songhao Wu , Ang Lv , Xiao Feng , Yufei Zhang , Xun Zhang , Guojun Yin , Wei Lin , Rui Yan

While 4-bit quantization has emerged as a memory-optimal choice for non-reasoning models and zero-shot tasks across scales, we show that this universal prescription fails for reasoning models, where the KV cache rather than model size can…

Machine Learning · Computer Science 2025-10-14 Junhyuck Kim , Ethan Ewer , Taehong Moon , Jongho Park , Dimitris Papailiopoulos

Quantization can accelerate large language model (LLM) inference. Going beyond INT8 quantization, the research community is actively exploring even lower precision, such as INT4. Nonetheless, state-of-the-art INT4 quantization techniques…

Computation and Language · Computer Science 2025-05-02 Yujun Lin , Haotian Tang , Shang Yang , Zhekai Zhang , Guangxuan Xiao , Chuang Gan , Song Han

KV cache compression methods have mainly relied on scalar quantization techniques to reduce the memory requirements during decoding. In this work, we apply residual vector quantization, which has been widely used for high fidelity audio…

Machine Learning · Computer Science 2024-10-22 Ankur Kumar

Excessive memory requirements of key and value features (KV-cache) present significant challenges in the autoregressive inference of large language models (LLMs), restricting both the speed and length of text generation. Approaches such as…

Computation and Language · Computer Science 2024-06-18 Vinay Joshi , Prashant Laddha , Shambhavi Sinha , Om Ji Omer , Sreenivas Subramoney

Large language models (LLMs) have achieved near-human performance across diverse reasoning tasks, yet their deployment on resource-constrained Internet-of-Things (IoT) devices remains impractical due to massive parameter footprints and…

Machine Learning · Computer Science 2025-11-07 Mingyu Sung , Vikas Palakonda , Suhwan Im , Sunghwan Moon , Il-Min Kim , Sangseok Yun , Jae-Mo Kang

In recent years, compression of large language models (LLMs) has emerged as an important problem to enable language model deployment on resource-constrained devices, reduce computational costs, and mitigate the environmental footprint of…

Machine Learning · Computer Science 2024-10-04 Sean I. Young

Quantization has emerged as a promising technique for improving the memory and computational efficiency of large language models (LLMs). Though the trade-off between performance and efficiency is well-known, there is still much to be…

Machine Learning · Computer Science 2024-03-12 Zhuocheng Gong , Jiahao Liu , Jingang Wang , Xunliang Cai , Dongyan Zhao , Rui Yan

How can we quantize large language models while preserving accuracy? Quantization is essential for deploying large language models (LLMs) efficiently. Binary-coding quantization (BCQ) and uniform quantization (UQ) are promising quantization…

Computation and Language · Computer Science 2025-06-17 Seungcheol Park , Jeongin Bae , Beomseok Kwon , Minjun Kim , Byeongwook Kim , Se Jung Kwon , U Kang , Dongsoo Lee