English
Related papers

Related papers: ICaRus: Identical Cache Reuse for Efficient Multi …

200 papers

KV cache quantization can improve Large Language Models (LLMs) inference throughput and latency in long contexts and large batch-size scenarios while preserving LLMs effectiveness. However, current methods have three unsolved issues:…

Machine Learning · Computer Science 2025-11-21 Xing Li , Zeyu Xing , Yiming Li , Linping Qu , Hui-Ling Zhen , Wulong Liu , Yiwu Yao , Sinno Jialin Pan , Mingxuan Yuan

Multiple Low-Rank Adapters (Multi-LoRAs) are gaining popularity for task-specific Large Language Model (LLM) applications. For multi-LoRA serving, caching hot KV caches and LoRA adapters in high bandwidth memory of accelerations can improve…

Hardware Architecture · Computer Science 2025-05-08 Hang Zhang , Jiuchen Shi , Yixiao Wang , Quan Chen , Yizhou Shan , Minyi Guo

This paper presents VLCache, a cache reuse framework that exploits both Key-Value (KV) cache and encoder cache from prior multimodal inputs to eliminate costly recomputation when the same multimodal inputs recur. Unlike previous heuristic…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Shengling Qin , Hao Yu , Chenxin Wu , Zheng Li , Yizhong Cao , Zhengyang Zhuge , Yuxin Zhou , Wentao Yao , Yi Zhang , Zhengheng Wang , Shuai Bai , Jianwei Zhang , Junyang Lin

Transformers have emerged as the underpinning architecture for Large Language Models (LLMs). In generative language models, the inference process involves two primary phases: prompt processing and token generation. Token generation, which…

Machine Learning · Computer Science 2024-04-09 Muhammad Adnan , Akhil Arunkumar , Gaurav Jain , Prashant J. Nair , Ilya Soloveychik , Purushotham Kamath

When transformer-based language models are deployed for text generation, most of the inference time is spent in the decoding stage, where output tokens are generated sequentially. Reducing the hardware cost of each decoding step is…

Machine Learning · Computer Science 2026-05-22 Sayed Mohammadreza Tayaranian Hosseini , Amir Ardakani , Warren J. Gross

Large Language Models (LLMs) are increasingly deployed in multi-turn conversational applications, where the management of the Key-Value (KV) Cache presents a significant bottleneck. The linear growth of the KV Cache with dialogue history…

Computation and Language · Computer Science 2025-10-09 Xiang Liu , Hong Chen , Xuming Hu , Xiaowen Chu

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…

Computation and Language · Computer Science 2026-03-06 Jia-Nan Li , Jian Guan , Wei Wu , Chongxuan Li

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

Visual Autoregressive (VAR) modeling has garnered significant attention for its innovative next-scale prediction approach, which yields substantial improvements in efficiency, scalability, and zero-shot generalization. Nevertheless, the…

Machine Learning · Computer Science 2025-05-27 Kunjun Li , Zigeng Chen , Cheng-Yen Yang , Jenq-Neng Hwang

To mitigate the performance gap between CPU and the main memory, multi-level cache architectures are widely used in modern processors. Therefore, modeling the behaviors of the downstream caches becomes a critical part of the processor…

Hardware Architecture · Computer Science 2020-10-13 Ming Ling , Jiancong Ge , Guangmin Wang

Complex visual reasoning and question answering (VQA) is a challenging task that requires compositional multi-step processing and higher-level reasoning capabilities beyond the immediate recognition and localization of objects and events.…

Machine Learning · Computer Science 2024-11-22 Shantanu Jaiswal , Debaditya Roy , Basura Fernando , Cheston Tan

Large Language Models (LLMs) exhibit enhanced capabilities by Chain-of-Thought reasoning. However, the extended reasoning sequences introduce significant GPU memory overhead due to increased key-value (KV) cache. Existing KV cache…

Machine Learning · Computer Science 2025-10-16 Haoyue Zhang , Hualei Zhang , Xiaosong Ma , Jie Zhang , Song Guo

Large Language Model or LLM inference has two phases, the prompt (or prefill) phase to output the first token and the extension (or decoding) phase to the generate subsequent tokens. In this work, we propose an efficient parallelization…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-05-15 Minsik Cho , Mohammad Rastegari , Devang Naik

Vision-Language Models (VLMs) have emerged as a critical and fast-growing extension of Large Language Models (LLMs) that enable multimodal reasoning through both text and image inputs. Although VLMs enrich the capabilities of language…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Yingbing Huang , Tharun Adithya Srikrishnan , Steven K. Reinhardt , Deming Chen

Large Language Models (LLMs) are rapidly being integrated into real-world applications, yet their autoregressive architectures introduce significant inference time variability, especially when deployed across heterogeneous edge-cloud…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-30 Panlong Wu , Yifei Zhong , Danyang Chen , Ting Wang , Fangxin Wang

Key-value (KV) caching is essential for large language model inference, yet its memory overhead poses a critical bottleneck for long-context generation. Existing eviction policies predominantly rely on empirical heuristics, lacking a…

Machine Learning · Computer Science 2026-04-30 Jiaming Yang , Chenwei Tang , Liangli Zhen , Jiancheng Lv

Large Language Model (LLM) inference, where a trained model generates text one word at a time in response to user prompts, is a computationally intensive process requiring efficient scheduling to optimize latency and resource utilization. A…

Machine Learning · Computer Science 2026-01-16 Patrick Jaillet , Jiashuo Jiang , Konstantina Mellou , Marco Molinaro , Chara Podimata , Zijie Zhou

Multi-modal Large Language Models (MLLMs) serving systems commonly employ KV-cache compression to reduce memory footprint. However, existing compression methods introduce significant processing overhead and queuing delays, particularly in…

Multimedia · Computer Science 2025-03-12 Jianian Zhu , Hang Wu , Haojie Wang , Yinghui Li , Biao Hou , Ruixuan Li , Jidong Zhai

KV cache accelerates LLM inference by avoiding redundant computation, at the expense of memory. To support larger KV caches, prior work extends GPU memory with CPU memory via CPU-offloading. This involves swapping KV cache between GPU and…

Operating Systems · Computer Science 2025-10-31 Ruihao Li , Shagnik Pal , Vineeth Narayan Pullu , Prasoon Sinha , Jeeho Ryoo , Lizy K. John , Neeraja J. Yadwadkar

The advent of pre-trained large language models (LLMs) has revolutionized various natural language processing tasks. These models predominantly employ an auto-regressive decoding mechanism that utilizes Key-Value (KV) caches to eliminate…

Computation and Language · Computer Science 2024-06-12 Hao Yu , Zelan Yang , Shen Li , Yong Li , Jianxin Wu