{"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":1787495451513,"version":"build-2736575974"},"publisher-location":"Singapore","reference-count":27,"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_9","type":"book-chapter","created":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T13:46:04Z","timestamp":1787492764000},"page":"129-141","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TokenSimV2: Accurate and\u00a0Fast LLM Inference on\u00a0GPUs via\u00a0Dynamic Graph Modeling"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3377-8926","authenticated-orcid":false,"given":"Zhuohang","family":"Bian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6638-509X","authenticated-orcid":false,"given":"Feiyang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8049-1190","authenticated-orcid":false,"given":"Zhuoran","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0485-1771","authenticated-orcid":false,"given":"Yibo","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9249-9284","authenticated-orcid":false,"given":"Junchi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1112-5863","authenticated-orcid":false,"given":"Xuxiao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1557-2613","authenticated-orcid":false,"given":"Youwei","family":"Zhuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"9_CR1","unstructured":"Agrawal, A., et al.: Vidur: a large-scale simulation framework for LLM inference. In: Proceedings of Machine Learning and Systems, vol. 6, pp. 351\u2013366 (2024)"},{"key":"9_CR2","unstructured":"Bambhaniya, A., et al.: Demystifying platform requirements for diverse LLM inference use cases. arXiv:2406.01698 arXiv preprint (2024)"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Cho, J., Kim, M., Choi, H., Heo, G., Park, J.: Llmservingsim: a HW\/SW co-simulation infrastructure for LLM inference serving at scale. In: 2024 IEEE International Symposium on Workload Characterization (IISWC), pp. 15\u201329 (2024)","DOI":"10.1109\/IISWC63097.2024.00012"},{"key":"9_CR4","doi-asserted-by":"publisher","first-page":"16344","DOI":"10.52202\/068431-1189","volume":"35","author":"T Dao","year":"2022","unstructured":"Dao, T., Fu, D., Ermon, S., Rudra, A., R\u00e9, C.: Flashattention: fast and memory-efficient exact attention with io-awareness. Adv. Neural. Inf. Process. Syst. 35, 16344\u201316359 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR5","unstructured":"Gao, B., et al.: Cost-efficient large language model serving for multi-turn conversations with cachedattention (2024). https:\/\/arxiv.org\/abs\/2403.19708"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Gao, S., Chen, Y., Shu, J.: Fast state restoration in LLM serving with HCACHE. In: Proceedings of the Twentieth European Conference on Computer Systems, pp. 128\u2013143 (2025)","DOI":"10.1145\/3689031.3696072"},{"key":"9_CR7","unstructured":"Gim, I., Chen, G., Lee, S.s., Sarda, N., Khandelwal, A., Zhong, L.: Prompt cache: modular attention reuse for low-latency inference. In: Gibbons, P., Pekhimenko, G., Sa, C.D. (eds.) Proceedings of Machine Learning and Systems. vol.\u00a06, pp. 325\u2013338 (2024). https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2024\/file\/a66caa1703fe34705a4368c3014c1966-Paper-Conference.pdf"},{"key":"9_CR8","unstructured":"Hu, C., et al.: Memserve: context caching for disaggregated LLM serving with elastic memory pool. arXiv preprint arXiv:2406.17565 (2024)"},{"key":"9_CR9","unstructured":"Hu, J., et al.: Epic: efficient position-independent caching for serving large language models. arXiv preprint arXiv:2410.15332 (2024)"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Kwon, W., et al.: Efficient memory management for large language model serving with pagedattention. In: Proceedings of the 29th Symposium on Operating Systems Principles, pp. 611\u2013626 (2023)","DOI":"10.1145\/3600006.3613165"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Kwon, Y., et\u00a0al.: System architecture and software stack for gddr6-aim. In: 2022 IEEE Hot Chips 34 Symposium (HCS), pp. 1\u201325 (2022)","DOI":"10.1109\/HCS55958.2022.9895629"},{"key":"9_CR12","unstructured":"Lee, W., Lee, J., Seo, J., Sim, J.: InfiniGen: Efficient generative inference of large language models with dynamic KV cache management. In: 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24), pp. 155\u2013172 (2024)"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Cachegen: KV cache compression and streaming for fast large language model serving. In: Proceedings of the ACM SIGCOMM 2024 Conference, pp. 38\u201356 (2024)","DOI":"10.1145\/3651890.3672274"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Patel, P., et al.: Splitwise: efficient generative LLM inference using phase splitting. arXiv:2311.18677 arXiv preprint (2024)","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"9_CR15","unstructured":"Qin, R., et\u00a0al.: Mooncake: a kvcache-centric disaggregated architecture for LLM serving. ACM Trans. Storage (2024)"},{"key":"9_CR16","unstructured":"ShareGPT Team: Sharegpt (2023). https:\/\/www.sharegpt.com\/"},{"key":"9_CR17","unstructured":"SimPy Contributors: Simpy: Discrete event simulation for python (2026). https:\/\/simpy.readthedocs.io\/. Accessed 11 Apr 2026"},{"key":"9_CR18","unstructured":"Touvron, H., et al.: Llama: Open and efficient foundation language models. arXiv:2302.13971 arXiv preprint (2023)"},{"key":"9_CR19","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models. arXiv:2307.09288 arXiv preprint (2023)"},{"key":"9_CR20","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Yao, J., et al.: Cacheblend: fast large language model serving for rag with cached knowledge fusion. In: Proceedings of the Twentieth European Conference on Computer Systems, pp. 94\u2013109 (2025)","DOI":"10.1145\/3689031.3696098"},{"key":"9_CR22","unstructured":"Ye, Z., et\u00a0al.: Flashinfer: efficient and customizable attention engine for LLM inference serving. Proc. Mach. Learn. Syst. 7 (2025)"},{"key":"9_CR23","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 (2022)"},{"key":"9_CR24","unstructured":"Zhang, H., Ning, A., Prabhakar, R., Wentzlaff, D.: A hardware evaluation framework for large language model inference. arXiv:2312.03134 arXiv preprint (2023)"},{"key":"9_CR25","unstructured":"Zhang, Y., et al.: To see is not to master: teaching LLMs to use private libraries for code generation. arXiv preprint arXiv:2603.15159 (2026)"},{"key":"9_CR26","doi-asserted-by":"publisher","first-page":"62557","DOI":"10.52202\/079017-2000","volume":"37","author":"L Zheng","year":"2024","unstructured":"Zheng, L., et al.: Sglang: efficient execution of structured language model programs. Adv. Neural. Inf. Process. Syst. 37, 62557\u201362583 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR27","unstructured":"Zhong, Y., et al.: Distserve: disaggregating prefill and decoding for goodput-optimized large language model serving. arXiv preprint arXiv:2401.09670 (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_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T13:46:08Z","timestamp":1787492768000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-4805-6_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"ISBN":["9789819248049","9789819248056"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-4805-6_9","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 authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"Artificial intelligence tools, if used, were used only for language organization and figure\/table polishing, and did not participate in the generation of the core ideas or technical content.","order":2,"name":"Ethics","label":"Artificial Intelligence Tools","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"}}]}}