{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T17:04:41Z","timestamp":1754154281372,"version":"3.41.2"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T00:00:00Z","timestamp":1734048000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T00:00:00Z","timestamp":1734048000000},"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"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,13]]},"DOI":"10.1109\/hpcc64274.2024.00105","type":"proceedings-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T18:33:48Z","timestamp":1753295628000},"page":"761-768","source":"Crossref","is-referenced-by-count":0,"title":["Joint Layer-wise Caching and Request Routing for Serverless Inference Acceleration at the Edge"],"prefix":"10.1109","author":[{"given":"Zhaowu","family":"Huang","sequence":"first","affiliation":[{"name":"Southeast University,School of Computer Science and Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fang","family":"Dong","sequence":"additional","affiliation":[{"name":"Southeast University,School of Computer Science and Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolin","family":"Guo","sequence":"additional","affiliation":[{"name":"Southeast University,School of Computer Science and Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haodong","family":"Tian","sequence":"additional","affiliation":[{"name":"Southeast University,School of Computer Science and Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3398724"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3375108"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3172402"},{"article-title":"Tetris: Memory-efficient serverless inference through tensor sharing","volume-title":"Proc. of USENIX ATC","author":"Li","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621106"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10228916"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10229034"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-022-01047-w"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3355118"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3352834"},{"volume-title":"Cold starts in aws lambda","key":"ref11"},{"volume-title":"Cold starts in azure functions","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3348165"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3617232.3624871"},{"article-title":"Cloud programming simplified: A berkeley view on serverless computing","year":"2019","author":"Jonas","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629567"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486992"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446757"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507750"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796705"},{"article-title":"Serverless in the wild: Characterizing and optimizing the serverless workload at a large cloud provider","volume-title":"Proc. of USENIX ATC","author":"Shahrad","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3620678.3624664"},{"article-title":"Sock: Rapid task provisioning with serverless-optimized containers","volume-title":"Proc. of USENIX ATC","author":"Oakes","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545071"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00075"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10229030"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488779"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796670"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SECON55815.2022.9918601"},{"volume-title":"Google or-tools","key":"ref30"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511813603","article-title":"Probability and computing: Randomized algorithms and probabilistic analysis","author":"Mitzenmacher","year":"2005"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378512"}],"event":{"name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","start":{"date-parts":[[2024,12,13]]},"location":"Wuhan, China","end":{"date-parts":[[2024,12,15]]}},"container-title":["2024 IEEE International Conference on High Performance Computing and Communications (HPCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11083115\/11083125\/11083354.pdf?arnumber=11083354","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T04:50:57Z","timestamp":1753332657000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11083354\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,13]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/hpcc64274.2024.00105","relation":{},"subject":[],"published":{"date-parts":[[2024,12,13]]}}}