English
Related papers

Related papers: FastDecode: High-Throughput GPU-Efficient LLM Serv…

200 papers

The attention layer, a core component of Transformer-based LLMs, brings out inefficiencies in current GPU systems due to its low operational intensity and the substantial memory requirements of KV caches. We propose a High-bandwidth…

Hardware Architecture · Computer Science 2025-12-19 Myunghyun Rhee , Joonseop Sim , Taeyoung Ahn , Seungyong Lee , Daegun Yoon , Euiseok Kim , Kyoung Park , Youngpyo Joo , Hoshik Kim

In recent times, the emergence of Large Language Models (LLMs) has resulted in increasingly larger model size, posing challenges for inference on low-resource devices. Prior approaches have explored offloading to facilitate low-memory…

Performance · Computer Science 2024-03-05 Xuanlei Zhao , Bin Jia , Haotian Zhou , Ziming Liu , Shenggan Cheng , Yang You

Several works have developed eviction policies to remove key-value (KV) pairs from the KV cache for more efficient inference. The focus has been on compressing the KV cache after the input prompt has been processed for faster token…

Computation and Language · Computer Science 2025-07-04 Michael R. Metel , Boxing Chen , Mehdi Rezagholizadeh

As modern LLMs support thousands to millions of tokens, KV caches grow to hundreds of gigabytes, stressing memory capacity and bandwidth. Existing solutions, such as KV cache pruning and offloading, alleviate these but underutilize hardware…

Performance · Computer Science 2026-04-21 Mao Lin , Xi Wang , Guilherme Cox , Dong Li , Hyeran Jeon

Recently the generative Large Language Model (LLM) has achieved remarkable success in numerous applications. Notably its inference generates output tokens one-by-one, leading to many redundant computations. The widely-used KV-Cache…

Machine Learning · Computer Science 2024-12-10 Weizhuo Li , Zhigang Wang , Yu Gu , Ge Yu

The growth of long-context Large Language Models (LLMs) significantly increases memory and bandwidth pressure during autoregressive decoding due to the expanding Key-Value (KV) cache. While accuracy-preserving KV-cache quantization (e.g.,…

Hardware Architecture · Computer Science 2026-01-06 Dayou Du , Shijie Cao , Jianyi Cheng , Luo Mai , Ting Cao , Mao Yang

Multimodal Large Language Models (MLLMs) have advanced unified reasoning over text, images, and videos, but their inference is hindered by the rapid growth of key-value (KV) caches. Each visual input expands into thousands of tokens,…

Artificial Intelligence · Computer Science 2026-04-08 Bowen Zeng , Feiyang Ren , Jun Zhang , Xiaoling Gu , Ke Chen , Lidan Shou , Huan Li

Transformer-based long context generative models power emerging AI applications like hour-long video understanding and project-level coding agent. Deploying long context transformers (e.g., 100K to 10M tokens) is prohibitively expensive…

Machine Learning · Computer Science 2024-05-16 Yao Fu

Modern large language models (LLMs) drive interactive AI systems but are bottlenecked by the memory-heavy growth of key-value (KV) caches, which limits real-time throughput under concurrent loads. Existing KV-cache compression methods rely…

Machine Learning · Computer Science 2026-01-07 Joseph Kampeas , Emir Haleva

This paper introduces Helix, a distributed system for high-throughput, low-latency large language model (LLM) serving in heterogeneous GPU clusters. The key idea behind Helix is to formulate inference computation of LLMs over heterogeneous…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-07 Yixuan Mei , Yonghao Zhuang , Xupeng Miao , Juncheng Yang , Zhihao Jia , Rashmi Vinayak

Two widely adopted techniques for LLM inference serving systems today are hybrid batching and disaggregated serving. A hybrid batch combines prefill and decode tokens of different requests in the same batch to improve resource utilization…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-21 Amna Masood , Pratishtha Gaur , Nuwan Jayasena

High-throughput inference serving is essential for applications built on large language models (LLMs). Existing serving frameworks reduce request-level and batch-level bubbles through batching and scheduling, but often overlook bubbles…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-25 Fengyao Bai , Hongbin Zhang , Zhitao Chen , Jiangsu Du , Zhiguang Chen , Yutong Lu

Large Language Models (LLMs) are rapidly becoming critical infrastructure for enterprise applications, driving unprecedented demand for GPU-based inference services. A key operational challenge arises from the two-phase nature of LLM…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-04 Ruihan Lin , Zezhen Ding , Zean Han , Jiheng Zhang

Multimodal large language models (MLLMs) extend LLMs with visual understanding through a three-stage pipeline: multimodal preprocessing, vision encoding, and LLM inference. While these stages enhance capability, they introduce significant…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-22 Lingxiao Zhao , Haoran Zhou , Yuezhi Che , Dazhao Cheng

While large language models (LLMs) excel at handling long-context sequences, they require substantial prefill computation and key-value (KV) cache, which can heavily burden computational efficiency and memory usage in both prefill and…

Machine Learning · Computer Science 2026-04-21 Dongwon Jo , Jiwon Song , Yulhwa Kim , Jae-Joon Kim

With the widespread deployment of long-context large language models (LLMs), there has been a growing demand for efficient support of high-throughput inference. However, as the key-value (KV) cache expands with the sequence length, the…

Machine Learning · Computer Science 2025-04-29 Hanshi Sun , Li-Wen Chang , Wenlei Bao , Size Zheng , Ningxin Zheng , Xin Liu , Harry Dong , Yuejie Chi , Beidi Chen

Training Large Language Models(LLMs) is one of the most compute-intensive tasks in high-performance computing. Predicting end-to-end training time for multi-billion parameter models distributed across hundreds of GPUs remains challenging…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-30 Biyao Zhang , Mingkai Zheng , Debargha Ganguly , Xuecen Zhang , Vikash Singh , Vipin Chaudhary , Zhao Zhang

Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs) for inference. While it enhances decoding efficiency in Large Language Models (LLMs), its direct adoption in LVLMs introduces substantial…

Computer Vision and Pattern Recognition · Computer Science 2026-05-04 Xihao Chen , Yangyang Guo , Roger Zimmermann

Vision-Language Models (VLMs) have demonstrated impressive performance across a versatile set of tasks. A key challenge in accelerating VLMs is storing and accessing the large Key-Value (KV) cache that encodes long visual contexts, such as…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Dezhan Tu , Danylo Vashchilenko , Yuzhe Lu , Panpan Xu

Transformer-based large language models (LLMs) have demonstrated remarkable potential across a wide range of practical applications. However, long-context inference remains a significant challenge due to the substantial memory requirements…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-09 Bo Jiang , Taolue Yang , Youyuan Liu , Xubin He , Sheng Di , Sian Jin