English
Related papers

Related papers: Prefixing Attention Sinks can Mitigate Activation …

200 papers

The quadratic complexity of the attention module makes it gradually become the bulk of compute in Transformer-based LLMs during generation. Moreover, the excessive key-value cache that arises when dealing with long inputs also brings severe…

Computation and Language · Computer Science 2023-10-17 Siyu Ren , Qi Jia , Kenny Q. Zhu

Quantization of large language models (LLMs) faces significant challenges, particularly due to the presence of outlier activations that impede efficient low-bit representation. Traditional approaches predominantly address Normal Outliers,…

Computation and Language · Computer Science 2024-11-04 Haokun Lin , Haobo Xu , Yichen Wu , Jingzhi Cui , Yingtao Zhang , Linzhan Mou , Linqi Song , Zhenan Sun , Ying Wei

Modern large language models (LLMs) have established state-of-the-art performance through architectural improvements, but still require significant computational cost for inference. In an effort to reduce the inference cost, post-training…

Computation and Language · Computer Science 2024-05-24 Jaewoo Yang , Hayun Kim , Younghoon Kim

As the field of Large Language Models (LLMs) continues to evolve, the context length in inference is steadily growing. Key-Value Cache (KVCache), the intermediate representations of tokens within LLM inference, has now become the primary…

Computation and Language · Computer Science 2025-04-01 Hailin Zhang , Xiaodong Ji , Yilin Chen , Fangcheng Fu , Xupeng Miao , Xiaonan Nie , Weipeng Chen , Bin Cui

Self-attention is an essential component of large language models (LLM) but a significant source of inference latency for long sequences. In multi-tenant LLM serving scenarios, the compute and memory operation cost of self-attention can be…

Machine Learning · Computer Science 2024-08-02 Lu Ye , Ze Tao , Yong Huang , Yang Li

Post-training quantization~(PTQ) of transformer language models faces significant challenges due to the existence of detrimental outliers in activations. We observe that these outliers are concentrated in specific channels and are…

Computation and Language · Computer Science 2023-10-24 Xiuying Wei , Yunchen Zhang , Yuhang Li , Xiangguo Zhang , Ruihao Gong , Jinyang Guo , Xianglong Liu

Large language models (LLMs) have become pivotal in artificial intelligence, demonstrating strong capabilities in reasoning, understanding, and generating data. However, their deployment on edge devices is hindered by their substantial…

Machine Learning · Computer Science 2025-05-14 Lucas Maisonnave , Cyril Moineau , Olivier Bichler , Fabrice Rastello

During inference for transformer-based large language models (LLM), prefilling is the computation of the key-value (KV) cache for input tokens in the prompt prior to autoregressive generation. For longer input prompt lengths, prefilling…

Machine Learning · Computer Science 2024-04-16 Siyan Zhao , Daniel Israel , Guy Van den Broeck , Aditya Grover

Post-training quantization (PTQ) is a widely used approach for reducing the memory and compute costs of large language models (LLMs). Recent studies have shown that applying invertible transformations to activations can significantly…

Machine Learning · Computer Science 2026-04-27 Ofir Gordon , Lior Dikstein , Arnon Netzer , Idan Achituve , Hai Victor Habi

Low-precision fine-tuning of language models has gained prominence as a cost-effective and energy-efficient approach to deploying large-scale models in various applications. However, this approach is susceptible to the existence of outlier…

Computation and Language · Computer Science 2024-01-17 Alireza Ghaffari , Justin Yu , Mahsa Ghazvini Nejad , Masoud Asgharian , Boxing Chen , Vahid Partovi Nia

Despite the significant success of large language models (LLMs), their extensive memory requirements pose challenges for deploying them in long-context token generation. The substantial memory footprint of LLM decoders arises from the…

Machine Learning · Computer Science 2024-02-12 Amir Zandieh , Insu Han , Vahab Mirrokni , Amin Karbasi

Fine-tuning provides an effective means to specialize pre-trained models for various downstream tasks. However, fine-tuning often incurs high memory overhead, especially for large transformer-based models, such as LLMs. While existing…

Computation and Language · Computer Science 2025-02-03 Antoine Simoulin , Namyong Park , Xiaoyi Liu , Grey Yang

We consider the problem of accurate quantization for language models, where both the weights and activations are uniformly quantized to 4 bits per parameter, the lowest bitwidth format natively supported by GPU hardware. In this context,…

Machine Learning · Computer Science 2024-08-28 Aniruddha Nrusimha , Mayank Mishra , Naigang Wang , Dan Alistarh , Rameswar Panda , Yoon Kim

Multimodal large language models (MLLMs) are plagued by exorbitant inference costs attributable to the profusion of visual tokens within the vision encoder. The redundant visual tokens engenders a substantial computational load and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Jiedong Zhuang , Lu Lu , Ming Dai , Rui Hu , Jian Chen , Qiang Liu , Haoji Hu

The emergence of LLMs has ignited a fresh surge of breakthroughs in NLP applications, particularly in domains such as question-answering systems and text generation. As the need for longer context grows, a significant bottleneck in model…

Computation and Language · Computer Science 2024-04-15 Shichen Dong , Wen Cheng , Jiayu Qin , Wei Wang

Accurately quantifying a large language model's (LLM) predictive uncertainty is crucial for judging the reliability of its answers. While most existing research focuses on short, directly answerable questions with closed-form outputs (e.g.,…

Computation and Language · Computer Science 2025-08-08 Yinghao Li , Rushi Qiang , Lama Moukheiber , Chao Zhang

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

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

Post-training quantization (PTQ) techniques applied to weights, activations, and the KV cache greatly reduce memory usage, latency, and power consumption of Large Language Models (LLMs), but may lead to large quantization errors when…

Post-training quantization of Large Language Models (LLMs) is challenging. In this work, we introduce Low-rank Quantization Error Reduction (LQER), which combines quantization and low-rank approximation to recover the model capability. LQER…

Machine Learning · Computer Science 2024-05-31 Cheng Zhang , Jianyi Cheng , George A. Constantinides , Yiren Zhao