{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:13:28Z","timestamp":1759331608778,"version":"build-2065373602"},"reference-count":12,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,8]],"date-time":"2025-06-08T00:00:00Z","timestamp":1749340800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,8]],"date-time":"2025-06-08T00:00:00Z","timestamp":1749340800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,8]]},"DOI":"10.1109\/icc52391.2025.11160773","type":"proceedings-article","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T17:34:55Z","timestamp":1758908095000},"page":"6161-6166","source":"Crossref","is-referenced-by-count":0,"title":["Distributed Inference Optimization for Large Language Model in Edge-Cloud Collaborative Networks"],"prefix":"10.1109","author":[{"given":"Zideng","family":"Feng","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Lu","sequence":"additional","affiliation":[{"name":"China Mobile Research Institute,Department of Basic Network Technology Research,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Li","sequence":"additional","affiliation":[{"name":"China Mobile Research Institute,Department of Basic Network Technology Research,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Chai","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinglei","family":"Teng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Da","family":"Guo","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"A survey of large language models","year":"2023","author":"Zhao","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3393230"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3257342"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467078"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118403"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LNET.2023.3260567"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3357874"},{"journal-title":"Megatron-lm: Training multibillion parameter language models using model parallelism","year":"2019","author":"Shoeybi","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3656628"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC57260.2024.10571127"},{"journal-title":"Keep the Cost Down: A Review on Methods to Optimize LLM\u2019s KV-Cache Consumption","year":"2024","author":"Luohe","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3376977"}],"event":{"name":"ICC 2025 - IEEE International Conference on Communications","start":{"date-parts":[[2025,6,8]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2025,6,12]]}},"container-title":["ICC 2025 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11160703\/11160705\/11160773.pdf?arnumber=11160773","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T13:20:51Z","timestamp":1759238451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11160773\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,8]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/icc52391.2025.11160773","relation":{},"subject":[],"published":{"date-parts":[[2025,6,8]]}}}