{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T21:56:27Z","timestamp":1781301387229,"version":"3.54.1"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62502251"],"award-info":[{"award-number":["62502251"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014890","name":"Qilu University of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014890","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2023QF104"],"award-info":[{"award-number":["ZR2023QF104"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2023QF152"],"award-info":[{"award-number":["ZR2023QF152"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008118","name":"Shandong Academy of Sciences","doi-asserted-by":"publisher","award":["2024QZJH02"],"award-info":[{"award-number":["2024QZJH02"]}],"id":[{"id":"10.13039\/501100008118","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113599","type":"journal-article","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:09:15Z","timestamp":1774310955000},"page":"113599","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["Structure prediction and opportunity-cost scheduler for LLM inference"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3812-9609","authenticated-orcid":false,"given":"Weiyan","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8271-9090","authenticated-orcid":false,"given":"Guomao","family":"Xin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3008-6285","authenticated-orcid":false,"given":"Bruce","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2944-4647","authenticated-orcid":false,"given":"Youyang","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3026-7537","authenticated-orcid":false,"given":"Longxiang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113599_bib0001","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113599_bib0002","unstructured":"J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F. L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, S. Anadkat, et al., GPT-4 technical report, arXiv preprint arXiv: 2303.08774(2023)."},{"key":"10.1016\/j.patcog.2026.113599_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112765","article-title":"Visual reasoning consistency and robustness analysis of multimodal LLMs","volume":"172","author":"Jegham","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113599_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111992","article-title":"SceneLLM: implicit language reasoning in LLM for dynamic scene graph generation","volume":"170","author":"Zhang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113599_bib0005","series-title":"2024\u202fUSENIX Annual Technical Conference (USENIX ATC 24)","first-page":"111","article-title":"Cost-efficient large language model serving for multi-turn conversations with CachedAttention","author":"Gao","year":"2024"},{"issue":"2","key":"10.1016\/j.patcog.2026.113599_bib0006","doi-asserted-by":"crossref","first-page":"430","DOI":"10.26599\/BDMA.2024.9020068","article-title":"Federated transfer learning for on-device LLMs efficient fine tuning optimization","volume":"8","author":"Li","year":"2025","journal-title":"Big Data Min. Anal."},{"issue":"2","key":"10.1016\/j.patcog.2026.113599_bib0007","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0279743","article-title":"Early detection of depression using a conversational AI bot: a non-clinical trial","volume":"18","author":"Kaywan","year":"2023","journal-title":"PLoS ONE"},{"key":"10.1016\/j.patcog.2026.113599_bib0008","series-title":"First Conference on Language Modeling","article-title":"Length-controlled alpacaeval: a simple debiasing of automatic evaluators","author":"Dubois","year":"2024"},{"key":"10.1016\/j.patcog.2026.113599_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112462","article-title":"Parameter-efficient action planning with large language models for vision-and-language navigation","volume":"172","author":"Mohammadi","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113599_bib0010","series-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","first-page":"481","article-title":"Heterogeneity-aware cluster scheduling policies for deep learning workloads","author":"Narayanan","year":"2020"},{"key":"10.1016\/j.patcog.2026.113599_bib0011","series-title":"International Conference on Algorithms and Architectures for Parallel Processing","first-page":"317","article-title":"Federated learning and parallel prompt scheduling strategies for large language models","author":"Lv","year":"2024"},{"key":"10.1016\/j.patcog.2026.113599_bib0012","series-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","first-page":"521","article-title":"Orca: a distributed serving system for transformer-Based generative models","author":"Yu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113599_bib0013","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.patcog.2026.113599_bib0014","series-title":"The 5th International Workshop on Cloud Intelligence \/ AIOps at ASPLOS 2024","first-page":"1","article-title":"Efficient interactive LLM serving with proxy model-based sequence length prediction","volume":"5","author":"Qiu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113599_bib0015","first-page":"65517","article-title":"Response length perception and sequence scheduling: an LLM-empowered LLM inference pipeline","volume":"36","author":"Zheng","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113599_bib0016","series-title":"Proceedings of the 29th Symposium on Operating Systems Principles","first-page":"611","article-title":"Efficient memory management for large language model serving with pagedattention","author":"Kwon","year":"2023"},{"key":"10.1016\/j.patcog.2026.113599_bib0017","series-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","first-page":"117","article-title":"Taming throughput-latency tradeoff in LLM inference with Sarathi-Serve","author":"Agrawal","year":"2024"},{"key":"10.1016\/j.patcog.2026.113599_bib0018","series-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","first-page":"193","article-title":"DistServe: disaggregating prefill and decoding for goodput-optimized large language model serving","author":"Zhong","year":"2024"},{"key":"10.1016\/j.patcog.2026.113599_bib0019","unstructured":"B. Wu, Y. Zhong, Z. Zhang, S. Liu, F. Liu, Y. Sun, G. Huang, X. Liu, X. Jin, Fast distributed inference serving for large language models, arXiv preprint arXiv: 2305.05920(2023)."},{"key":"10.1016\/j.patcog.2026.113599_bib0020","unstructured":"J. Liu, J.-W. Chung, Z. Wu, F. Lai, M. Lee, M. Chowdhury, Andes: defining and enhancing quality-of-experience in LLM-based text streaming services, arXiv preprint arXiv: 2404.16283(2024)."},{"key":"10.1016\/j.patcog.2026.113599_bib0021","series-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","first-page":"965","article-title":"Fairness in serving large language models","author":"Sheng","year":"2024"},{"issue":"12","key":"10.1016\/j.patcog.2026.113599_bib0022","doi-asserted-by":"crossref","first-page":"29230","DOI":"10.1109\/JIOT.2025.3565782","article-title":"Graph learning-based multi-user multi-task offloading in wireless computing power networks","volume":"12","author":"Dai","year":"2025","journal-title":"IEEE Internet Things J."},{"issue":"2","key":"10.1016\/j.patcog.2026.113599_bib0023","doi-asserted-by":"crossref","DOI":"10.1145\/3732941","article-title":"ShuffleInfer: disaggregate LLM inference for mixed downstream workloads","volume":"22","author":"Hu","year":"2025","journal-title":"ACM Trans. Archit. Code Optim."},{"key":"10.1016\/j.patcog.2026.113599_bib0024","series-title":"Proceedings of the 41st International Conference on Machine Learning","article-title":"D\u00e9j\u00e0Vu: KV-cache streaming for fast, fault-tolerant generative LLM serving","author":"Strati","year":"2024"},{"issue":"1","key":"10.1016\/j.patcog.2026.113599_bib0025","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1186\/s42774-021-00077-8","article-title":"Predicting running time of aerodynamic jobs in HPC system by combining supervised and unsupervised learning method","volume":"3","author":"Wang","year":"2021","journal-title":"Adv. Aerodyn."},{"issue":"1","key":"10.1016\/j.patcog.2026.113599_bib0026","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1186\/s40537-022-00623-1","article-title":"Runtime prediction of big data jobs: performance comparison of machine learning algorithms and analytical models","volume":"9","author":"Ahmed","year":"2022","journal-title":"J. Big Data"},{"issue":"4","key":"10.1016\/j.patcog.2026.113599_bib0027","doi-asserted-by":"crossref","first-page":"2298","DOI":"10.1109\/TNSE.2019.2933639","article-title":"Privacy on the edge: customizable privacy-preserving context sharing in hierarchical edge computing","volume":"7","author":"Gu","year":"2019","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"10.1016\/j.patcog.2026.113599_bib0028","series-title":"Proceedings of the 26th ACM Symposium on Parallelism in Algorithms and Architectures","first-page":"2","article-title":"On dynamic bin packing for resource allocation in the cloud","author":"Li","year":"2014"},{"issue":"3","key":"10.1016\/j.patcog.2026.113599_bib0029","first-page":"1","article-title":"Large language models: a comprehensive survey of its applications, challenges, limitations, and future prospects","volume":"1","author":"Hadi","year":"2023","journal-title":"Authorea Preprints"},{"key":"10.1016\/j.patcog.2026.113599_bib0030","series-title":"2024\u202fIEEE\/ACM 32nd International Symposium on Quality of Service (IWQoS)","first-page":"1","article-title":"SyncIntellects: orchestrating LLM inference with progressive prediction and QoS-friendly control","author":"Lin","year":"2024"},{"key":"10.1016\/j.patcog.2026.113599_bib0031","series-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","article-title":"S3: increasing GPU utilization during generative inference for higher throughput","author":"Jin","year":"2023"},{"key":"10.1016\/j.patcog.2026.113599_bib0032","series-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","first-page":"173","article-title":"Llumnix: dynamic scheduling for large language model serving","author":"Sun","year":"2024"},{"key":"10.1016\/j.patcog.2026.113599_bib0033","series-title":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","first-page":"369","article-title":"ExeGPT: constraint-aware resource scheduling for LLM inference","author":"Oh","year":"2024"},{"key":"10.1016\/j.patcog.2026.113599_bib0034","series-title":"2024\u202fACM\/IEEE 51st Annual International Symposium on Computer Architecture (ISCA)","first-page":"118","article-title":"Splitwise: efficient generative LLM inference using phase splitting","author":"Patel","year":"2024"},{"key":"10.1016\/j.patcog.2026.113599_bib0035","series-title":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"641","article-title":"C-pack: packed resources for general chinese embeddings","author":"Xiao","year":"2024"},{"key":"10.1016\/j.patcog.2026.113599_bib0036","series-title":"Findings of the Association for Computational Linguistics: ACL 2024","first-page":"2318","article-title":"M3-embedding: multi-linguality, multi-functionality, multi-granularity text embeddings through self-knowledge distillation","author":"Chen","year":"2024"},{"key":"10.1016\/j.patcog.2026.113599_bib0037","series-title":"The Twelfth International Conference on Learning Representations","article-title":"OpenChat: advancing open-source language models with mixed-quality data","author":"Wang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113599_bib0038","unstructured":"L. Zheng, W.-L. Chiang, Y. Sheng, T. Li, S. Zhuang, Z. Wu, Y. Zhuang, Z. Li, Z. Lin, E.P. Xing, et al., LMSYS-Chat-1M: a large-scale real-world LLM conversation dataset, arXiv preprint arXiv: 2309.11998(2023)."},{"key":"10.1016\/j.patcog.2026.113599_bib0039","doi-asserted-by":"crossref","first-page":"59006","DOI":"10.52202\/079017-1882","article-title":"Efficient llm scheduling by learning to rank","volume":"37","author":"Fu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113599_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112330","article-title":"Reliable classification through rank-based conformal prediction sets","volume":"172","author":"Luo","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113599_bib0041","unstructured":"A. Dubey, A. Jauhri, A. Pandey, A. Kadian, A. Al-Dahle, A. Letman, A. Mathur, A. Schelten, A. Yang, A. Fan, et al., The Llama 3 herd of models, arXiv e-prints (2024) arXiv\u20132407."},{"key":"10.1016\/j.patcog.2026.113599_bib0042","unstructured":"Q. Team, Qwen3 Technical Report, 2025, arXiv preprint arXiv: 2505.09388."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326005650?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326005650?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T21:09:48Z","timestamp":1781298588000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326005650"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":42,"alternative-id":["S0031320326005650"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113599","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Structure prediction and opportunity-cost scheduler for LLM inference","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113599","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"113599"}}