Cover Image

Not All Prefills Are Equal: PPD Disaggregation for Multi-turn LLM Serving

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Zongze, Liu, Jingyu, Xu, Zhen, Zhang, Yineng, Rabbani, Tahseen, Zhang, Ce
Format:	Preprint
Published:	2026
Subjects:	Networking and Internet Architecture
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Sketch Disaggregation Across Time and Space
by: Langlet, Jonatan, et al.
Published: (2025)

Disaggregated Architectures and the Redesign of Data Center Ecosystems: Scheduling, Pooling, and Infrastructure Trade-offs
by: Guo, Chao, et al.
Published: (2025)

Towards Disaggregating the SDN Control Plane
by: Comer, Douglas, et al.
Published: (2019)

KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving
by: Liu, Zedong, et al.
Published: (2026)

Multi-stage Flow Scheduling for LLM Serving
by: Sun, Yijun, et al.
Published: (2026)

Avoiding Cross-Datacenter Collective Congestion via Disaggregated Buffering
by: Scazzariello, Mariano, et al.
Published: (2026)

Surviving the Storm: The Impacts of Open RAN Disaggregation on Latency and Resilience
by: Chatzimiltis, Sotiris, et al.
Published: (2025)

Integration of Computer Networks and Artificial Neural Networks for an AI-based Network Operator
by: Wu, Binbin, et al.
Published: (2024)

Joint Resource Allocation and Trajectory Design for Resilient Multi-UAV Communication Networks
by: Ge, Linghui, et al.
Published: (2024)

A Multi-Tenant System for 5/6G Testbed as-a-Service
by: Bolla, Raffaele, et al.
Published: (2024)

Recursive Offloading for LLM Serving in Multi-tier Networks
by: Wu, Zhiyuan, et al.
Published: (2025)

Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey
by: Liu, Yinqiu, et al.
Published: (2025)

Generating Packet-Level Header Traces Using GNN-powered GAN
by: Xu, Zhen
Published: (2024)

Serving Long-Context LLMs at the Mobile Edge: Test-Time Reinforcement Learning-based Model Caching and Inference Offloading
by: Xu, Minrui, et al.
Published: (2025)

Next-Generation Wi-Fi Networks with Generative AI: Design and Insights
by: Wang, Jingyu, et al.
Published: (2024)

LLM-Slice: Dedicated Wireless Network Slicing for Large Language Models
by: Liu, Boyi, et al.
Published: (2024)

Analyzing Communication Predictability in LLM Training
by: Li, Wenxue, et al.
Published: (2025)

LLM-supported 3D Modeling Tool for Radio Radiance Field Reconstruction
by: Xu, Chengling, et al.
Published: (2026)

Rethinking Network Topologies for Cost-Effective Mixture-of-Experts LLM Serving
by: Choi, Junsun, et al.
Published: (2026)

Serv-Drishti: An Interactive Serverless Function Request Simulation Engine and Visualiser
by: Agarwal, Siddharth, et al.
Published: (2025)

WiLLM: an Open Framework for LLM Services over Wireless Systems
by: Liu, Boyi, et al.
Published: (2025)

LLM-Sketch: Enhancing Network Sketches with LLM
by: Li, Yuanpeng, et al.
Published: (2025)

EDM: An Ultra-Low Latency Ethernet Fabric for Memory Disaggregation
by: Su, Weigao, et al.
Published: (2024)

Edge-Served Congestion Control for Wireless Multipath Transmission with a Transformer Agent
by: Wang, Liang
Published: (2025)

Quark: Implementing Convolutional Neural Networks Entirely on Programmable Data Plane
by: Zhang, Mai, et al.
Published: (2025)

Camel: Energy-Aware LLM Inference on Resource-Constrained Devices
by: Xu, Hao, et al.
Published: (2025)

An All-Optical Metro Network Architecture and QoS-Aware Wavelength Allocation Study for Converged Fixed, Mobile, and Edge Computing Multi-Granular Traffic
by: Georgantas, David, et al.
Published: (2025)

A Highly Scalable LLM Clusters with Optical Interconnect
by: Han, Xinchi, et al.
Published: (2024)

Fast Heterogeneous Serving: Scalable Mixed-Scale LLM Allocation for SLO-Constrained Inference
by: Cheng, Jiaming, et al.
Published: (2026)

Toward Generative 6G Simulation: An Experimental Multi-Agent LLM and ns-3 Integration
by: Rezazadeh, Farhad, et al.
Published: (2025)

Optimizing Resource Allocation for Multi-modal Semantic Communication in Mobile AIGC Networks: A Diffusion-based Game Approach
by: Liu, Jian, et al.
Published: (2024)

Deadline and Priority Constrained Immersive Video Streaming Transmission Scheduling
by: Feng, Tongtong, et al.
Published: (2024)

To Reconfigure or Not to Reconfigure: Optimizing All-to-All Collectives in Circuit-Switched Photonic Interconnects
by: Zhou, Anchengcheng, et al.
Published: (2026)

An LLM-Agent-Based Framework for Age of Information Optimization in Heterogeneous Random Access Networks
by: Liu, Fang, et al.
Published: (2026)

GenOnet: Generative Open xG Network Simulation with Multi-Agent LLM and ns-3
by: Rezazadeh, Farhad, et al.
Published: (2024)

LLM-Empowered Agentic AI for QoE-Aware Network Slicing Management in Industrial IoT
by: Wang, Xudong, et al.
Published: (2025)

Compact LLM Deployment and World Model Assisted Offloading in Mobile Edge Computing
by: Zhang, Ruichen, et al.
Published: (2026)

Multi-hop Multi-RIS Wireless Communication Systems: Multi-reflection Path Scheduling and Beamforming
by: Ma, Xiaoyan, et al.
Published: (2024)

LLM Agent Communication Protocol (LACP) Requires Urgent Standardization: A Telecom-Inspired Protocol is Necessary
by: Li, Xin, et al.
Published: (2025)

Traffic-cognitive Slicing for Resource-efficient Offloading with Dual-distillation DRL in Multi-edge Systems
by: Xiaoyang, Ting, et al.
Published: (2024)