{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T14:30:51Z","timestamp":1787495451251,"version":"build-2736575974"},"publisher-location":"Singapore","reference-count":15,"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_44","type":"book-chapter","created":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T13:45:44Z","timestamp":1787492744000},"page":"613-618","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Characterizing and\u00a0Mitigating I\/O Bottlenecks in\u00a0LLM Inference on\u00a0Disaggregated HPC Systems"],"prefix":"10.1007","author":[{"given":"Qin","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fanzi","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenli","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hai","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longbao","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenlong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"44_CR1","unstructured":"Gao, P.X., et al.: Network requirements for resource disaggregation. In: Proceedings of USENIX OSDI, pp. 249\u2013264 (2016)"},{"key":"44_CR2","doi-asserted-by":"crossref","unstructured":"Kwon, W., et al.: Efficient memory management for large language model serving with PagedAttention. In: Proceedings of ACM SOSP, pp. 611\u2013626 (2023)","DOI":"10.1145\/3600006.3613165"},{"key":"44_CR3","unstructured":"NVIDIA.: TensorRT-LLM (2023). https:\/\/github.com\/NVIDIA\/TensorRT-LLM"},{"key":"44_CR4","doi-asserted-by":"crossref","unstructured":"Aminabadi, R.Y.: DeepSpeed inference: enabling efficient inference of transformer models at unprecedented scale. In: Proceedings of IEEE SC, pp. 1\u201315 (2022)","DOI":"10.1109\/SC41404.2022.00051"},{"key":"44_CR5","doi-asserted-by":"crossref","unstructured":"Carns, P., et al.: Understanding and improving computational science storage access through continuous characterization. ACM Trans. Storage 7(3) (2011)","DOI":"10.1145\/2027066.2027068"},{"key":"44_CR6","doi-asserted-by":"crossref","unstructured":"Thakur, R., Gropp, W., Lusk, E.: Data sieving and collective I\/O in ROMIO. In: Proceedings of IEEE Symposium Frontiers Massively Parallel Computer, pp.\u00a0182\u2013189 (1999)","DOI":"10.1109\/FMPC.1999.750599"},{"issue":"1","key":"44_CR7","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1006\/jpdc.1997.1346","volume":"44","author":"A Alexandrov","year":"1997","unstructured":"Alexandrov, A., et al.: LogGP: incorporating long messages into the LogP model. J. Parallel Distrib. Comput. 44(1), 71\u201379 (1997)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"6","key":"44_CR8","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1109\/TPDS.2004.9","volume":"15","author":"E Varki","year":"2004","unstructured":"Varki, E., Merchant, A., Xu, J., Qiu, X.: Issues and challenges in the performance analysis of real disk arrays. IEEE Trans. Parallel Distrib. Syst. 15(6), 559\u2013574 (2004)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"44_CR9","unstructured":"Shan, Y., Huang, Y., Chen, Y., Zhang, Y.: LegoOS: a disseminated, distributed OS for hardware resource disaggregation. In: Proceedings of USENIX OSDI, pp.\u00a069\u201387 (2018)"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Kalia, A., Kaminsky, M., Andersen, D.G.: Using RDMA efficiently for key-value services. In: Proceedings of ACM SIGCOMM, pp. 295\u2013306 (2014)","DOI":"10.1145\/2619239.2626299"},{"key":"44_CR11","doi-asserted-by":"crossref","unstructured":"Liu, N.: On the role of burst buffers in leadership-class storage systems. In: Proceedings of IEEE MSST (2012)","DOI":"10.1109\/MSST.2012.6232369"},{"key":"44_CR12","unstructured":"Schmuck, F., Haskin, R.: GPFS: a shared-disk file system for large computing clusters. In: Proceedings of USENIX FAST (2002)"},{"key":"44_CR13","doi-asserted-by":"crossref","unstructured":"Zhou, Y., et al.: Mixture-of-experts with expert choice routing. In: Proceedings of NeurIPS (2022)","DOI":"10.52202\/068431-0515"},{"key":"44_CR14","unstructured":"Roller, S., Sukhbaatar, S., Szlam, A., Weston, J.: Hash layers for large sparse models. In: Proceedings of NeurIPS (2021)"},{"key":"44_CR15","unstructured":"Kumar, A.V., Sivathanu, M.: Quiver: an informed storage cache for deep learning. In: Proceedings of USENIX FAST, pp. 283\u2013296 (2020)"}],"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_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T13:45:45Z","timestamp":1787492745000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-4805-6_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"ISBN":["9789819248049","9789819248056"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-4805-6_44","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":"The technical solution and experimental design were independently completed by the authors. AI tools were used solely for language polishing and formatting optimization.","order":1,"name":"Ethics","label":"AI Use Statement","group":{"name":"EthicsHeading","label":"Ethics"}},{"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"}}]}}