{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T06:17:39Z","timestamp":1783145859657,"version":"3.54.6"},"reference-count":26,"publisher":"IEEE","license":[{"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":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"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\/501100002766","name":"Beijing University of Posts and Telecommunications","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002766","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6,1]]},"DOI":"10.1109\/iwcmc69287.2026.11579993","type":"proceedings-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:49:45Z","timestamp":1783108185000},"page":"1647-1652","source":"Crossref","is-referenced-by-count":0,"title":["Semantics-Aware Scheduling for Low-Latency LLM Serving in Heterogeneous Computing Networks"],"prefix":"10.1109","author":[{"given":"Rui","family":"Wang","sequence":"first","affiliation":[{"name":"Southwestern University of Finance and Economics,School of Computer and Artificial Intelligence,Chengdu,611130"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyan","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing Key Laboratory of MEMS Technology and Device Reliability for Industrial Internet,Beijing,P. R. China,100876"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Southwestern University of Finance and Economics,School of Computer and Artificial Intelligence,Chengdu,611130"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mu","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing Key Laboratory of MEMS Technology and Device Reliability for Industrial Internet,Beijing,P. R. China,100876"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changqiao","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing Key Laboratory of MEMS Technology and Device Reliability for Industrial Internet,Beijing,P. R. China,100876"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3882"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2859"},{"key":"ref4","article-title":"Efficient interactive llm serving with proxy model-based sequence length prediction","author":"Qiu","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0791"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3264901"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3289611"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3356178"},{"key":"ref9","article-title":"Perllm: Personalized inference scheduling with edge-cloud collaboration for diverse llm services","author":"Yang","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2025.3562362"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2024.3424780"},{"key":"ref12","volume-title":"Time series analysis: forecasting and control","author":"Box","year":"2015"},{"key":"ref13","article-title":"Non-autoregressive neural machine translation","author":"Gu","year":"2017"},{"key":"ref14","article-title":"Inference without interference: Disaggregate llm inference for mixed downstream workloads","author":"Hu","year":"2024"},{"key":"ref15","article-title":"Don\u2019t stop me now: Embedding based scheduling for llms","author":"Shahout","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1882"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3168355"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3264607"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2023.3280170"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3319816"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3189186"},{"key":"ref22","article-title":"Stanford alpaca: An instruction-following llama model","author":"Taori","year":"2023"},{"key":"ref23","article-title":"Wildchat: 1m chatGPT interaction logs in the wild","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhao"},{"key":"ref24","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref26","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"}],"event":{"name":"2026 International Wireless Communications and Mobile Computing (IWCMC)","location":"Wuzhou, China","start":{"date-parts":[[2026,6,1]]},"end":{"date-parts":[[2026,6,6]]}},"container-title":["2026 International Wireless Communications and Mobile Computing (IWCMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11579793\/11579794\/11579993.pdf?arnumber=11579993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T05:28:01Z","timestamp":1783142881000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11579993\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,1]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iwcmc69287.2026.11579993","relation":{},"subject":[],"published":{"date-parts":[[2026,6,1]]}}}