{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:45:36Z","timestamp":1782798336560,"version":"3.54.5"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,18]]},"DOI":"10.1109\/infocom59046.2026.11571360","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:38:15Z","timestamp":1782761895000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Robust Prewarming Orchestration for Multi-Model Elastic Inference under Traffic Uncertainty"],"prefix":"10.1109","author":[{"given":"Mengfei","family":"Zhu","sequence":"first","affiliation":[{"name":"China Mobile Group Design Institute Co., Ltd,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Kang","sequence":"additional","affiliation":[{"name":"Kyoto University,Kyoto,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Li","sequence":"additional","affiliation":[{"name":"Renmin University of China,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref2","article-title":"Alpaserve: Statistical multiplexing with model parallelism for deep learning serving","volume-title":"Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Li"},{"key":"ref3","article-title":"Fast and live model auto scaling with O(1) host caching","volume-title":"Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Zhang"},{"key":"ref4","article-title":"Serverlessllm: Low-latency serverless inference for large language models","volume-title":"Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Fu"},{"key":"ref5","article-title":"Deepserve: Serverless large language model serving at scale","volume-title":"Proceedings of the USENIX Annual Technical Conference (ATC)","author":"Hu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737413"},{"key":"ref7","article-title":"PRED: Performance-oriented random early detection for consistently stable performance in datacenters","author":"Du","year":"2025","journal-title":"USENIX NSDI"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405850"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref10","article-title":"KVCache cache in the wild: Characterizing and optimizing KVCache cache at a large cloud provider","volume-title":"Proceedings of the USENIX Annual Technical Conference (ATC)","author":"Wang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3135906"},{"key":"ref12","article-title":"Mooncake: Trading more storage for less computation \u2013 a KVCache-centric architecture for serving LLM chatbot","volume-title":"USENIX Conference on File and Storage Technologies (FAST)","author":"Qin"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1030.0065"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1515\/9781400831050","volume-title":"Robust Optimization","author":"Ben-Tal","year":"2009"},{"key":"ref15","article-title":"Gurobi optimizer","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2023.109826"}],"event":{"name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","location":"Tokyo, Japan","start":{"date-parts":[[2026,5,18]]},"end":{"date-parts":[[2026,5,21]]}},"container-title":["IEEE INFOCOM 2026 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11571071\/11571169\/11571360.pdf?arnumber=11571360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:24:23Z","timestamp":1782797063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11571360\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/infocom59046.2026.11571360","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}