04-03, 16:10–17:50 (CET), Rotterdam hall 1A
Session Chair: Rodrigo Bruno (Univ. of Lisbon)
Litmus: Fair Pricing for Serverless Computing
Qi Pei (Computer Science / Watson School, The State University of New York at Binghamton), Yipeng Wang (Intel Lab., Intel), Seunghee Shin (Computer Science / Watson School, The State University of New York at Binghamton)
Paper
Concurrency-Informed Orchestration for Serverless Functions
Qichang Liu (University of Virginia), Yue Cheng (University of Virginia), Haiying Shen (University of Virginia), Ao Wang (Alibaba Group), Bharathan Balaji (Amazon)
Paper
Dilu: Enabling GPU Resourcing-on-Demand for Serverless DL Serving via Introspective Elasticity
Cunchi Lv (ICT, CAS,UCAS), Xiao Shi (ICT, CAS,Nanjing Institute of InforSuperBahn), Zhengyu Lei (ICT, CAS,UCAS), Jinyue Huang (ICT, CAS, UCAS), Wenting Tan (ICT, CAS), Xiaohui Zheng (ICT, CAS), Xiaofang Zhao (ICT, CAS,IICT, Suzhou, CAS)
Paper
Medusa: Accelerating Serverless LLM Inference with Materialization
Shaoxun Zeng (Tsinghua University), Minhui Xie (Tsinghua University), Shiwei Gao (Tsinghua University), Youmin Chen (Tsinghua University), Youyou Lu (Tsinghua University)
Paper