Multimedia · Computer Science
FastCache: Optimizing Multimodal LLM Serving through Lightweight KV-Cache Compression Framework
Jianian Zhu, Hang Wu, Haojie Wang, Yinghui Li +3
2025-03-12
Distributed, Parallel, and Cluster Computing · Computer Science
KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving
Zedong Liu, Xinyang Ma, Dejun Luo, Hairui Zhao +8
2026-05-14
Distributed, Parallel, and Cluster Computing · Computer Science
LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism
Bingyang Wu, Shengyu Liu, Yinmin Zhong, Peng Sun +2
2024-10-30
Distributed, Parallel, and Cluster Computing · Computer Science
A System for Microserving of LLMs
Hongyi Jin, Ruihang Lai, Charlie F. Ruan, Yingcheng Wang +4
2024-12-18
Distributed, Parallel, and Cluster Computing · Computer Science
BanaServe: Unified KV Cache and Dynamic Module Migration for Balancing Disaggregated LLM Serving in AI Infrastructure
Yiyuan He, Minxian Xu, Jingfeng Wu, Jianmin Hu +6
2026-03-11
Machine Learning · Computer Science
BestServe: Serving Strategies with Optimal Goodput in Collocation and Disaggregation Architectures
Xiannan Hu, Tianyou Zeng, Xiaoming Yuan, Liwei Song +2
2025-06-09
Computation and Language · Computer Science
semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage
Ke Hong, Lufang Chen, Zhong Wang, Xiuhong Li +8
2025-04-29
Computation and Language · Computer Science
LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
Shang Yang, Junxian Guo, Haotian Tang, Qinghao Hu +6
2025-04-22
Distributed, Parallel, and Cluster Computing · Computer Science
DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving
Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu +4
2024-06-07
Distributed, Parallel, and Cluster Computing · Computer Science
eLLM: Elastic Memory Management Framework for Efficient LLM Serving
Jiale Xu, Rui Zhang, Yi Xiong, Cong Guo +10
2026-05-08
Performance · Computer Science
Revisiting Disaggregated Large Language Model Serving for Performance and Energy Implications
Jiaxi Li, Yue Zhu, Eun Kyung Lee, Klara Nahrstedt
2026-01-15
Distributed, Parallel, and Cluster Computing · Computer Science
MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving
Jiangfei Duan, Runyu Lu, Haojie Duanmu, Xiuhong Li +4
2024-06-14
Computation and Language · Computer Science
From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs
Alireza Rezazadeh, Zichao Li, Wei Wei, Yujia Bao
2025-03-21
Distributed, Parallel, and Cluster Computing · Computer Science
Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache
Bin Lin, Chen Zhang, Tao Peng, Hanyu Zhao +11
2024-07-08
Distributed, Parallel, and Cluster Computing · Computer Science
AlignedServe: Orchestrating Prefix-aware Batching to Build a High-throughput and Computing-efficient LLM Serving System
Fengyao Bai, Hongbin Zhang, Zhitao Chen, Jiangsu Du +2
2026-05-25
Machine Learning · Computer Science
MPIC: Position-Independent Multimodal Context Caching System for Efficient MLLM Serving
Shiju Zhao, Junhao Hu, Rongxiao Huang, Jiaqi Zheng +1
2025-09-23
Distributed, Parallel, and Cluster Computing · Computer Science
DeepServe: Serverless Large Language Model Serving at Scale
Junhao Hu, Jiang Xu, Zhixia Liu, Yulong He +17
2025-06-10
Distributed, Parallel, and Cluster Computing · Computer Science
LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure
Jaehong Cho, Hyunmin Choi, Guseul Heo, Jongse Park
2026-03-24
Machine Learning · Computer Science
PrefillShare: A Shared Prefill Module for KV Reuse in Multi-LLM Disaggregated Serving
Sunghyeon Woo, Hoseung Kim, Sunghwan Shim, Minjung Jo +7
2026-02-13
Computation and Language · Computer Science
ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models
Jianxin Yan, Wangze Ni, Lei Chen, Xuemin Lin +3
2025-07-16
Machine Learning · Computer Science
Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving
Shihong Gao, Xin Zhang, Yanyan Shen, Lei Chen
2025-04-11
Hardware Architecture · Computer Science
Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System
Yunhua Fang, Rui Xie, Asad Ul Haq, Linsen Ma +5
2025-09-16
Distributed, Parallel, and Cluster Computing · Computer Science
SparseServe: Unlocking Parallelism for Dynamic Sparse Attention in Long-Context LLM Serving
Qihui Zhou, Peiqi Yin, Pengfei Zuo, James Cheng
2025-09-30
Distributed, Parallel, and Cluster Computing · Computer Science
KVCache Cache in the Wild: Characterizing and Optimizing KVCache Cache at a Large Cloud Provider
Jiahao Wang, Jinbo Han, Xingda Wei, Sijie Shen +5
2026-02-17