The paper introduces BEA, a fine‑grained estimator that predicts the time‑to‑first‑token (TTFT) for language model queries by replaying token‑batch formation based on current workload snapshots. BEA achieves about 5% error with 0.1 ms prediction time, enabling the latency‑aware router BEAR to balance accuracy, cost, and latency across heterogeneous LLM pools. BEAR outperforms seven baselines, improving utility of on‑target responses by 63% on average and by 30.5% at each arrival rate.
By Shivam Patel, Akaash R. Parthasarathy, Akash Dhasade, Ankur Mallick, Gauri Joshi
arXiv:2606. 00946v1 Announce Type: cross Abstract: Efficiently serving large language model (LLM) inference tasks is crucial both for user-perceived latency such as time-to-first-token (TTFT) and for GPU utilization.
By Gangmuk Lim, Wanyu Zhao, Brighten Godfrey, Jiaxin Shan, Le Xu, Liguang Xie
arXiv:2606. 11440v1 Announce Type: new Abstract: Existing multi-agent LLM orchestration methods, ranging from brute-force ensembles to learned routers, select models and topologies based on task and model features.
By Ahasan Kabir, Jiaqi Xue, Mengxin Zheng, Qian Lou
arXiv:2606. 13968v1 Announce Type: cross Abstract: Researchers and practitioners working with large language models face a fragmented landscape: local models are free and private but hardware limits the model size and context windows a researcher can use; institutional HPC centers offer powerful GPU resources at no marginal cost and keep data within institutional boundaries, but operate behind firewalls and are designed for batch jobs rather than interactive use; commercial cloud APIs provide frontier-model quality on demand but impose significant cost and data retention policies unsuitable for sensitive research data.
By Anas Nassar, Steve Mohr, Leonard Apanasevich, Himanshu Sharma
arXiv:2606. 10493v1 Announce Type: cross Abstract: Local deployment of large Mixture-of-Experts (MoE) models falls short of the service quality achieved in cloud-scale environments, even under low-concurrency workloads.
By Wenxin Wang, Yule Hou, Yu Ji, Peng Qu, Youhui Zhang
arXiv:2610.08268v1 Announce Type: cross
Abstract: Pervasive intelligent applications are increasingly deployed on mobile and Internet of Things (IoT) edge devices. Consequently, Large Language Models...
By Jingpo Xu, Paul Joe Maliakel, Ivona Brandic, Shashikant Ilager
arXiv:2609.08307v1 Announce Type: cross
Abstract: Large language models (LLMs) are increasingly used as backends for intelligent web services, but serving them across the edge continuum requires bala...
By Maysam Khatib, Moysis Symeonides, Demetris Trihinas, George Pallis, Marios D. Dikaiakos
arXiv:2602. 24044v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) adapters enable low-cost model specialization, but introduce complex caching and scheduling challenges in distributed serving systems where hundreds of adapters must be hosted concurrently.
By Ferran Agullo, Joan Oliveras, Chen Wang, Alberto Gutierrez-Torre, Olivier Tardieu, Alaa Youssef, Jordi Torres, Josep Ll. Berral
arXiv:2512. 10236v2 Announce Type: replace-cross Abstract: Modern ML workloads demand distributing training and inference across multiple GPUs.
By Shagnik Pal, Shaizeen Aga, Suchita Pati, Mahzabeen Islam, Lizy K. John
arXiv:2402. 09589v2 Announce Type: replace-cross Abstract: We present MLCC, a novel technique to augment today's congestion control algorithms to accelerate DNN training jobs in shared GPU clusters in a fully distributed manner.
By Anton A. Zabreyko, Sanjoli Narang, Sudarsanan Rajasekaran, Manya Ghobadi
arXiv:2608.28726v1 Announce Type: new
Abstract: The remarkable performance of multimodal large language models (MLLMs) comes at the cost of substantial computational overhead, posing significant chal...
By Xinyuan Gui, Shaowen Wang, Sheng Sun, Zijian Wang, Zishu Yu, Zheming Yang
arXiv:2607. 28633v1 Announce Type: cross Abstract: Disaggregated LLM inference creates a datacenter networking problem that no existing system solves correctly.
By Sanjeev Rao Ganjihal