English
Related papers

Related papers: AlignedKV: Reducing Memory Access of KV-Cache with…

200 papers

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

We introduce a method that dramatically reduces fine-tuning VRAM requirements and rectifies quantization errors in quantized Large Language Models. First, we develop an extremely memory-efficient fine-tuning (EMEF) method for quantized…

Computation and Language · Computer Science 2023-06-16 Yuji Chai , John Gkountouras , Glenn G. Ko , David Brooks , Gu-Yeon Wei

The Key-Value (KV) cache is integral to efficient autoregressive inference in large language models (LLMs), yet its unbounded growth in stateful multi-turn scenarios presents major challenges. This paper examines the interplay between KV…

Machine Learning · Computer Science 2025-11-10 Pratik Poudel

Large language models (LLMs) exhibit excellent performance in various tasks. However, the memory requirements of LLMs present a great challenge when deploying on memory-limited devices, even for quantized LLMs. This paper introduces a…

Computation and Language · Computer Science 2025-02-24 Weilan Wang , Yu Mao , Dongdong Tang , Hongchao Du , Nan Guan , Chun Jason Xue

Deploying Large Language Models (LLMs) on edge or mobile devices offers significant benefits, such as enhanced data privacy and real-time processing capabilities. However, it also faces critical challenges due to the substantial memory…

Machine Learning · Computer Science 2024-05-07 Yu Mao , Weilan Wang , Hongchao Du , Nan Guan , Chun Jason Xue

Deploying Large Language Models (LLMs) on edge devices faces severe computational and memory constraints, limiting real-time processing and on-device intelligence. Hybrid architectures combining Structured State Space Models (SSMs) with…

Machine Learning · Computer Science 2026-04-16 Jason Kong , Nilesh Prasad Pandey , Flavio Ponzina , Tajana Rosing

Key-Value (KV) cache plays a crucial role in accelerating inference in large language models (LLMs) by storing intermediate attention states and avoiding redundant computation during autoregressive generation. However, its memory footprint…

Machine Learning · Computer Science 2026-04-14 Yuzhen Mao , Qitong Wang , Martin Ester , Ke Li

Large language models (LLMs) have demonstrated strong capabilities in processing long contexts, enabling them to tackle tasks involving long textual inputs such as multi-turn conversations, legal documents, or retrieved documents in…

Computation and Language · Computer Science 2025-11-25 Yuechi Zhou , Yi Su , Jianxin Zhang , Juntao Li , Qingrong Xia , Zhefeng Wang , Xinyu Duan , Baoxing Huai

The KV cache is a dominant memory bottleneck for LLM inference. While 4-bit KV quantization preserves accuracy, 2-bit often degrades it, especially on long-context reasoning. We close this gap via an algorithm-system co-design for…

The increasing context window size in large language models (LLMs) has improved their ability to handle complex, long-text tasks. However, as the conversation rounds continue, it is required to store a large amount of KV cache in GPU…

Computation and Language · Computer Science 2025-06-30 Yaohua Tang , Zhicheng Hu , Kun Cheng , Fan Mo , Qiheng Lv , Hua Wang , Zhi Chen

Recent advancements in large language models (LLMs) have shown their remarkable capacities in many NLP tasks. However, their substantial size often presents challenges for deployment. This necessitates efficient techniques for model…

Computation and Language · Computer Science 2026-05-20 Robin Baki Davidsson , Pierre Nugues

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

The Segment Anything Model (SAM) is a popular vision foundation model; however, its high computational and memory demands make deployment on resource-constrained devices challenging. While Post-Training Quantization (PTQ) is a practical…

Computer Vision and Pattern Recognition · Computer Science 2025-05-09 Navin Ranjan , Andreas Savakis

Inference for Large Language Models (LLMs) is computationally demanding. To reduce the cost of auto-regressive decoding, Key-Value (KV) cache is used to store intermediate activations, which significantly lowers the computational overhead…

Machine Learning · Computer Science 2025-06-05 Chaoyi Jiang , Lei Gao , Hossein Entezari Zarch , Murali Annavaram

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

Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI. Despite the overall superiority of the Decoder architecture, the gradually increasing Key-Value (KV) cache during…

Computation and Language · Computer Science 2025-07-16 Luohe Shi , Zuchao Li , Lefei Zhang , Guoming Liu , Baoyuan Qi , Hai Zhao

Efficient inference with Large Language Models (LLMs) increasingly relies on Key-Value (KV) caches to store previously computed key and value vectors at each layer. These caches are essential to minimize redundant computation during…

Hardware Architecture · Computer Science 2026-04-08 Oteo Mamo , Olga Kogiou , Hyunjin Yi , Weikuan Yu

The demand for inference on extremely large scale LLMs has seen enormous growth in the recent months. It made evident the colossal shortage of dedicated hardware capable of efficient and fast processing of the involved compute and memory…

Artificial Intelligence · Computer Science 2024-04-01 Nikita Trukhanov , Ilya Soloveychik

Quantization is a technique for creating efficient Deep Neural Networks (DNNs), which involves performing computations and storing tensors at lower bit-widths than f32 floating point precision. Quantization reduces model size and inference…

Machine Learning · Computer Science 2023-10-02 Eliska Kloberdanz , Wei Le

The memory-for-computation paradigm of KV caching is essential for accelerating large language model (LLM) inference service, but limited GPU high-bandwidth memory (HBM) capacity motivates offloading the KV cache to cheaper external storage…