arXiv:2607. 26566v1 Announce Type: cross Abstract: Text-to-image (T2I) workflows are increasingly deployed on serverless platforms because users often compose customized workflows and invoke them intermittently.
By Xiaoxiao Jiang, Suyi Li, Sheng Yao, Tianyu Feng, Lingyun Yang, Dapeng Nie, Haoran Yang, Wei Wang
arXiv:2606. 13501v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) have become the dominant architecture for image and video generation, creating growing demand for efficient DiT serving.
By Xinwei Qiang, Yifan Hu, Shixuan Sun, Jing Yang, Han Zhao, Chen Chen, Yu Feng, Jingwen Leng, Minyi Guo
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
Scepsy is a serving system designed to efficiently schedule arbitrary multi‑LLM agentic workflows on GPU clusters. It leverages the observation that each LLM’s share of execution time remains relatively stable across requests, profiling LLMs under various parallelism levels to build an Aggregate LLM Pipeline that predicts throughput and latency. Using this predictor, Scepsy searches for optimal GPU allocations—balancing fractional GPU shares, tensor parallelism, and replica counts—and then heuristically places them on the cluster to reduce fragmentation and honor network topology, achieving up to 2.5× higher throughput and 1.0–3.3× lower latency compared to baseline approaches.
By Otto White, Marcel Wagenl\"ander, Britannio Jarrett, Xijin Zhao, Yanda Tao, Pedro Silvestre, Guo Li, Huanzhou Zhu, Llu\'is Vilanova, Peter Pietzuch
PipeLive introduces a method for live, in‑place reconfiguration of pipeline parallelism in large language model serving. By redesigning the KV cache layout and extending PageAttention, it enables dynamic resizing of the cache without interrupting inference. The system also uses an incremental KV patching mechanism to keep KV states consistent during reconfiguration, achieving significant reductions in reconfiguration time and improvements in latency metrics.
By Xu Bai, Muhammed Tawfiqul Islam, Chen Wang, Adel N. Toosi
arXiv:2607. 19539v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures increase model capacity without proportionally increasing computation cost and have become a key building block for scaling large language models (LLMs) to trillion-parameter regimes.
By Minyu Cui, Anna Wingkvist, Morgan Ericsson