{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T14:30:08Z","timestamp":1787495408603,"version":"build-2736575974"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819248049","type":"print"},{"value":"9789819248056","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-4805-6_10","type":"book-chapter","created":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T13:47:45Z","timestamp":1787492865000},"page":"142-156","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TierServe: Revenue-Maximizing LLM Inference Scheduling Across Multiple Subscription Tiers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9739-2866","authenticated-orcid":false,"given":"Chang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0378-2311","authenticated-orcid":false,"given":"Jiacheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4372-7851","authenticated-orcid":false,"given":"Xiaofeng","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0034-2302","authenticated-orcid":false,"given":"Minyi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"10_CR1","unstructured":"Agrawal, A., et al.: Vidur: a large-scale simulation framework for LLM inference. In: Proceedings of Machine Learning and Systems (MLSys), vol. 6, pp. 351\u2013366 (2024)"},{"key":"10_CR2","unstructured":"Agrawal, A., et al.: Taming throughput-latency tradeoff in LLM inference with Sarathi-Serve. In: 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24), pp. 117\u2013134. USENIX Association (2024)"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Bari, A.: Optimal Scheduling Algorithms for LLM Inference: Theory and Practice (2025)","DOI":"10.1145\/3771574"},{"key":"10_CR4","unstructured":"Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., et\u00a0al.: The Llama 3 herd of models (2024). https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Fu, Y., et al.: Efficient LLM scheduling by learning to rank. In: Advances in Neural Information Processing Systems (NeurIPS) (2024)","DOI":"10.52202\/079017-1882"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Goel, K., Mohan, J., Kwatra, N., Anupindi, R.S., Ramjee, R.: Niyama: breaking the silos of LLM inference serving (2025)","DOI":"10.1145\/3779212.3790206"},{"key":"10_CR7","unstructured":"Hong, K., et al.: SOLA: optimizing SLO attainment for large language model serving with state-aware scheduling. In: Eighth Conference on Machine Learning and Systems (MLSys) (2025)"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Hou, X., Li, C., Liu, J., Zhang, L., Hu, Y., Guo, M.: Ant-man: towards agile power management in the microservice era. International Conference for High Performance Computing, Networking, Storage and Analysis (SC), pp. 1\u201314 (2020)","DOI":"10.1109\/SC41405.2020.00082"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Hou, X., et al.: Alphar: learning-powered resource management for irregular, dynamic microservice graph. In: IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 797\u2013806 (2021)","DOI":"10.1109\/IPDPS49936.2021.00089"},{"key":"10_CR10","unstructured":"Huang, J., Xiong, Y., Yu, X., Huang, W., Li, E., Zeng, L., Chen, X.: SLO-aware scheduling for large language model inferences (2025)"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Kwon, W., et al.: Efficient memory management for large language model serving with PagedAttention. In: Proceedings of the 29th ACM Symposium on Operating Systems Principles (SOSP \u201923), pp. 611\u2013626. ACM (2023)","DOI":"10.1145\/3600006.3613165"},{"issue":"10","key":"10_CR12","first-page":"1","volume":"58","author":"J Liu","year":"2026","unstructured":"Liu, J., et al.: A survey on inference optimization techniques for mixture of experts models. ACM Comput. Surv. 58(10), 1\u201337 (2026)","journal-title":"ACM Comput. Surv."},{"key":"10_CR13","unstructured":"Microsoft Azure: AzureLLMInferenceTrace2023. Azure Public Dataset (2023). https:\/\/github.com\/Azure\/AzurePublicDataset"},{"key":"10_CR14","unstructured":"ShareGPT Contributors: ShareGPT_Vicuna_unfiltered. Hugging Face Datasets (2023). https:\/\/huggingface.co\/datasets\/anon8231489123\/ShareGPT_Vicuna_unfiltered"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Stojkovic, J., Zhang, C., Goiri, \u00cd., Torrellas, J., Choukse, E.: Dynamollm: designing LLM inference clusters for performance and energy efficiency. In: 2025 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp. 1348\u20131362. IEEE (2025)","DOI":"10.1109\/HPCA61900.2025.00102"},{"key":"10_CR16","unstructured":"Sun, B., et al.: Llumnix: dynamic scheduling for large language model serving. In: 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24), pp. 173\u2013192. USENIX Association (2024)"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Tang, P., et al.: Moe-apex: an efficient MOE inference system with adaptive precision expert offloading. In: Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) (2026)","DOI":"10.1145\/3779212.3790187"},{"key":"10_CR18","unstructured":"Wu, B., Zhong, Y., Zhang, Z., Huang, G., Liu, X., Jin, X.: Fast distributed inference serving for large language models (2023)"},{"key":"10_CR19","unstructured":"Yu, G.I., Jeong, J.S., Kim, G.W., Kim, S., Chun, B.G.: Orca: a distributed serving system for transformer-based generative models. In: 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22), pp. 521\u2013538. USENIX Association (2022)"},{"key":"10_CR20","unstructured":"Zhang, W., et al.: Jitserve: Slo-aware LLM serving with imprecise request information. arXiv:2504.20068 arXiv preprint (2025)"},{"key":"10_CR21","unstructured":"Zhong, Y., et al.: DistServe: disaggregating prefill and decoding for goodput-optimized large language model serving. In: 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24), pp. 193\u2013210. USENIX Association (2024)"}],"container-title":["Lecture Notes in Computer Science","Advanced Parallel Processing Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-4805-6_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T13:47:47Z","timestamp":1787492867000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-4805-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"ISBN":["9789819248049","9789819248056"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-4805-6_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,24]]},"assertion":[{"value":"24 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APPT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Advanced Parallel Processing Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brussels","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"appt2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.appt-conference.com\/2026","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}