English
Related papers

Related papers: OSCAR: Offline Spectral Covariance-Aware Rotation …

200 papers

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

Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference. A…

Computation and Language · Computer Science 2026-05-26 Xintong Yang , Hao Gu , Binxing Xu , Lujun Li , Bei Liu , Jiacheng Liu , Qiyuan Zhu , Sirui Han , Yike Guo

Large language models (LLMs) represent a groundbreaking advancement in the domain of natural language processing due to their impressive reasoning abilities. Recently, there has been considerable interest in increasing the context lengths…

Machine Learning · Computer Science 2024-11-11 Utkarsh Saxena , Gobinda Saha , Sakshi Choudhary , Kaushik Roy

Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving. Current systems suffer from three compounding inefficiencies: (1) the absence of unified KV cache…

Hardware Architecture · Computer Science 2026-05-01 Sanjeev Rao Ganjihal

Transformers have driven remarkable breakthroughs in natural language processing and computer vision, yet their standard attention mechanism still imposes O(N^2) complexity, hindering scalability to longer sequences. We introduce…

Machine Learning · Computer Science 2026-01-06 Yoshihiro Yamada

Chunk-wise autoregressive video diffusion models rely on a KV cache of previously generated chunks to avoid redundant computation, but this cache quickly becomes a memory bottleneck as videos grow longer. Methods that quantize the KV cache…

Machine Learning · Computer Science 2026-05-27 Tuna Tuncer , Felix Becker , Thomas Pfeil

Standard sequence mixing layers used in language models struggle to balance efficiency and performance. Self-attention performs well on long context tasks but has expensive quadratic compute and linear memory costs, while linear attention…

Machine Learning · Computer Science 2026-05-18 Nick Alonso , Tomas Figliolia , Beren Millidge

Cache fusion accelerates generation process of LLMs equipped with RAG through KV caching and selective token recomputation, thereby reducing computational costs and improving efficiency. However, existing methods primarily rely on local…

Databases · Computer Science 2026-04-13 Jianxin Yan , Zeheng Qian , Wangze Ni , Zhitao Shen , Zhiping Wang , Haoyang Li , Jia Zhu , Lei Chen , Kui Ren

Evaluating softmax attention over a fixed long context requires reading every cached key-value pair for each new query token. For a given context (a book, a manual, a legal corpus) the attention output is a deterministic function of the…

Machine Learning · Computer Science 2026-05-12 João Monteiro , Michal Klein , Pierre Ablin , Marco Cuturi

Rotary Position Embedding (RoPE) enables each attention head to capture multi-frequency information along the sequence dimension and is widely applied in foundation models. However, the nonlinearity introduced by RoPE complicates…

Machine Learning · Computer Science 2025-03-04 Yuhao Zhou , Sirui Song , Boyang Liu , Zhiheng Xi , Senjie Jin , Xiaoran Fan , Zhihao Zhang , Wei Li , Xuanjing Huang

The key-value (KV) cache in transformer models is a critical component for efficient decoding or inference, yet its memory demands scale poorly with sequence length, posing a major challenge for scalable deployment of large language models.…

Computation and Language · Computer Science 2025-06-06 Vinay Joshi , Pratik Prabhanjan Brahma , Zicheng Liu , Emad Barsoum

Given the quadratic complexity of attention, KV cache eviction is vital to accelerate model inference. Current KV cache eviction methods typically rely on instantaneous heuristic metrics, implicitly assuming that score magnitudes are…

Machine Learning · Computer Science 2026-02-10 Ziyao Tang , Pengkun Jiao , Xinhang Chen , Wei Liu , Shiyong Li , Jingjing Chen

Context lengths of Large Language Models (LLMs) have exploded in recent years, with 128k-token context becoming a standard and million-token context becoming a reality. Efficiently supporting long-context inference remains challenging as…

Computation and Language · Computer Science 2024-10-08 Isaac Rehg

In large-scale recommender systems, ultra-long user behavior sequences encode rich signals of evolving interests. Extending sequence length generally improves accuracy, but directly modeling such sequences in production is infeasible due to…

Information Retrieval · Computer Science 2025-08-26 Kaiyuan Li , Yongxiang Tang , Yanhua Cheng , Yong Bai , Yanxiang Zeng , Chao Wang , Xialong Liu , Peng Jiang

Post-training quantization (PTQ) has emerged as a widely adopted technique for compressing and accelerating Large Language Models (LLMs). The major challenge in LLM quantization is that uneven and heavy-tailed data distributions can expand…

Machine Learning · Computer Science 2025-01-27 Xing Hu , Yuan Cheng , Dawei Yang , Zukang Xu , Zhihang Yuan , Jiangyong Yu , Chen Xu , Zhe Jiang , Sifan Zhou

The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally important information. Although recent dynamic retrieval…

Computation and Language · Computer Science 2026-04-21 Zhiyuan Shi , Qibo Qiu , Feng Xue , Zhonglin Jiang , Li Yu , Jian Jiang , Xiaofei He , Wenxiao Wang

Supporting long-context LLMs is challenging due to the substantial memory demands of the key-value (KV) cache. Existing offloading systems store the full cache in host memory and selectively fetch critical entries during decoding, but this…

Computation and Language · Computer Science 2026-05-19 Jian Lin , Jiazhi Mi , Zicong Hong , Haodong Wang , Qianli Liu , Haodyue Zhang , Peng Li , Song Guo

Deploying large language models (LLMs) on edge devices requires extremely low-bit quantization. Ultra-low precision formats such as NVFP4 offer a promising solution for reducing memory footprint and accelerating computation. However,…

Machine Learning · Computer Science 2026-03-25 Hanglin Li , Shuchang Tian , Chen Lin , Zhiyong Zhao , Kun Zhan

Recent advances in Post-Training Quantization (PTQ) techniques have significantly increased demand for serving quantized large language models (LLMs), enabling higher throughput and substantially reduced memory usage with minimal accuracy…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-16 Kyungmin Bin , Seungbeom Choi , Jimyoung Son , Jieun Choi , Daseul Bae , Daehyeon Baek , Kihyo Moon , Minsung Jang , Hyojung Lee

Although LLM inference has emerged as a critical workload for many downstream applications, efficiently inferring LLMs is challenging due to the substantial memory footprint and bandwidth requirements. In parallel, compute capabilities have…