English
Related papers

Related papers: CAOTE: KV Cache Selection for LLMs via Attention O…

200 papers

Transformer-based large language models (LLMs) cache context as key-value (KV) pairs during inference. As context length grows, KV cache sizes expand, leading to substantial memory overhead and increased attention latency. This paper…

Databases · Computer Science 2025-10-01 Jang-Hyun Kim , Jinuk Kim , Sangwoo Kwon , Jae W. Lee , Sangdoo Yun , Hyun Oh Song

The acoustic-to-word model based on the Connectionist Temporal Classification (CTC) criterion is a natural end-to-end (E2E) system directly targeting word as output unit. Two issues exist in the system: first, the current output of the CTC…

Computation and Language · Computer Science 2019-09-06 Amit Das , Jinyu Li , Guoli Ye , Rui Zhao , Yifan Gong

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

Large Language Models (LLMs) are increasingly deployed in large-scale online services, enabling sophisticated applications. However, the computational overhead of generating key-value (KV) caches in the prefill stage presents a major…

Machine Learning · Computer Science 2025-02-24 Shuowei Jin , Xueshen Liu , Qingzhao Zhang , Z. Morley Mao

Retrieval-Augmented Generation (RAG) systems suffer from severe time-to-first-token (TTFT) bottlenecks due to long input sequences. Existing KV cache reuse methods face a fundamental trade-off: prefix caching requires identical prefixes…

Machine Learning · Computer Science 2026-05-22 Bin Yang , Qiuyu Leng , Jun Zeng , Zhenhua Wu

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

Long-context decoding in LLMs is IO-bound: each token re-reads an ever-growing KV cache. Prior accelerations cut bytes via compression, which lowers fidelity, or selection/eviction, which restricts what remains accessible, and both can…

Machine Learning · Computer Science 2026-04-02 Jinghan Yao , Sam Adé Jacobs , Walid Krichene , Masahiro Tanaka , Dhabaleswar K Panda

Inference on large language models (LLMs) can be expensive in terms of the compute and memory costs involved, especially when long sequence lengths are used. In particular, the self-attention mechanism used in LLM inference contributes…

Machine Learning · Computer Science 2024-11-11 Prajwal Singhania , Siddharth Singh , Shwai He , Soheil Feizi , Abhinav Bhatele

The development of large language models (LLMs) has revolutionized automated code generation. However, their high demand of computation resources has hindered a broader deployment and raised environmental concerns. A common strategy for…

Software Engineering · Computer Science 2024-11-12 Xiangyu Zhang , Yu Zhou , Guang Yang , Harald C. Gall , Taolue Chen

Large language models allocate uniform computation across all tokens, ignoring that some sequences are trivially predictable while others require deep reasoning. We introduce ConceptMoE, which dynamically merges semantically similar tokens…

Machine Learning · Computer Science 2026-01-30 Zihao Huang , Jundong Zhou , Xingwei Qu , Qiyang Min , Ge Zhang

Handling long-context sequences efficiently remains a significant challenge in large language models (LLMs). Existing methods for token selection in sequence extrapolation either employ a permanent eviction strategy or select tokens by…

Computation and Language · Computer Science 2025-02-21 Haoyu Wang , Tong Teng , Tianyu Guo , An Xiao , Duyu Tang , Hanting Chen , Yunhe Wang

The KV cache in self-attention has emerged as a major bottleneck in long-context and large-batch inference for LLMs. Existing approaches often treat sparsity prediction and compression as separate modules, relying on auxiliary index…

Machine Learning · Computer Science 2026-03-17 Xu Yang , Jiapeng Zhang , Dongyang Zhao , Guo Chen , Zhuo Tang

Whether attention key value (KV) states computed for one prompt for a small LLM can be reused to accelerate inference on a new similar prompt, giving an increase to the space to its context memory using an approach called token recycling.…

Machine Learning · Computer Science 2025-12-16 Prashant Pandey

Large Language Models (LLMs) are pivotal in advancing natural language processing but often struggle with complex reasoning tasks due to inefficient attention distributions. In this paper, we explore the effect of increased computed tokens…

Computation and Language · Computer Science 2024-06-25 Bingli Liao , Danilo Vasconcellos Vargas

The inference of large language models imposes significant computational workloads, often requiring the processing of billions of parameters. Although early-exit strategies have proven effective in reducing computational demands by halting…

Computation and Language · Computer Science 2026-01-08 Sangmin Yoo , Srikanth Malla , Chiho Choi , Wei D. Lu , Joon Hee Choi

KV-cache quantizers usually optimize storage-space reconstruction, even though attention reads keys through logits and values through attention-weighted readout. We argue that persistent cache error should be measured in model-visible…

Machine Learning · Computer Science 2026-05-21 Jorge L. Ruiz Williams

Large language models (LLMs) excel in natural language processing but demand intensive computation. To mitigate this, various quantization methods have been explored, yet they compromise LLM performance. This paper unveils a previously…

Computation and Language · Computer Science 2024-05-28 Ruikang Liu , Haoli Bai , Haokun Lin , Yuening Li , Han Gao , Zhengzhuo Xu , Lu Hou , Jun Yao , Chun Yuan

Large Language Models (LLMs) excel in natural language processing tasks but pose significant computational and memory challenges for edge deployment due to their intensive resource demands. This work addresses the efficiency of LLM…

Hardware Architecture · Computer Science 2025-07-02 Zhican Wang , Hongxiang Fan , Haroon Waris , Gang Wang , Zhenyu Li , Jianfei Jiang , Yanan Sun , Guanghui He

Autoregressive Transformers rely on Key-Value (KV) caching to accelerate inference. However, the linear growth of the KV cache with context length leads to excessive memory consumption and bandwidth constraints. This bottleneck is…

Computation and Language · Computer Science 2025-06-10 Ravi Ghadia , Avinash Kumar , Gaurav Jain , Prashant Nair , Poulami Das

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