{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:45:07Z","timestamp":1785912307011,"version":"3.56.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62571055,62431015"],"award-info":[{"award-number":["62571055,62431015"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/2575-8411.2026.00051","type":"proceedings-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T19:08:59Z","timestamp":1785870539000},"page":"469-479","source":"Crossref","is-referenced-by-count":0,"title":["ShadowLLM: Resource-Efficient Hot Standby for Heterogeneous Edge LLM Serving"],"prefix":"10.1109","author":[{"given":"Zhenguo","family":"Chen","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pujun","family":"Ding","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanwei","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Big Data and Statistics, Anhui University","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"China Telecom Wanwei Information Technology Co., Ltd.","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Lv","sequence":"additional","affiliation":[{"name":"China Telecom Wanwei Information Technology Co., Ltd.","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yakun","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuquan","family":"Qiao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv"},{"key":"ref2","article-title":"Qwen3 technical report","author":"Team","year":"2025","journal-title":"arXiv"},{"key":"ref3","article-title":"Gemma: Open models based on gemini research and technology","author":"Team","year":"2024","journal-title":"arXiv"},{"key":"ref4","article-title":"Llama2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.678"},{"key":"ref6","first-page":"32431","article-title":"MobileLLM: Optimizing sub-billion parameter language models for on-device use cases","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Liu","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695964"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3513457"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS60910.2024.00036"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3362068"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref12","volume-title":"MLC-LLM","year":"2025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2000"},{"key":"ref14","first-page":"606","article-title":"Efficiently scaling transformer inference","volume-title":"Proceedings of Machine Learning and Systems","author":"Pope","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640411"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2022.109262"},{"key":"ref17","first-page":"135","article-title":"ServerlessLLM:Low-Latency serverless inference for large language models","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Fu","year":"2024"},{"key":"ref18","first-page":"11905","article-title":"Muxserve: Flexible spatial-temporal multiplexing for multiple LLM serving","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Duan","year":"2024"},{"key":"ref19","first-page":"193","article-title":"DistServe: Disaggregating prefill and decoding for goodput-optimized large language model serving","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Zhong","year":"2024"},{"key":"ref20","volume-title":"llama.cpp","year":"2025"},{"key":"ref21","volume-title":"libzmq","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.172"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586176"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2021.3116597"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3276937"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2025.3536311"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3397315"},{"key":"ref28","first-page":"521","article-title":"Orca: A distributed serving system for Transformer-Based generative models","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yu","year":"2022"},{"key":"ref29","first-page":"31094","article-title":"FlexGen: High-throughput generative inference of large language models with a single GPU","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Sheng","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/sc41404.2022.00051"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS63083.2025.00062"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"ref34","article-title":"Fast transformer decoding: One write-head is all you need","author":"Shazeer","year":"2019","journal-title":"arXiv"}],"event":{"name":"2026 IEEE 46th International Conference on Distributed Computing Systems (ICDCS)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2026,6,22]]},"end":{"date-parts":[[2026,6,25]]}},"container-title":["2026 IEEE 46th International Conference on Distributed Computing Systems (ICDCS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11618978\/11618981\/11619107.pdf?arnumber=11619107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:52:13Z","timestamp":1785909133000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11619107\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/2575-8411.2026.00051","relation":{},"subject":[],"published":{"date-parts":[[2026,6]]}}}