{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T14:54:03Z","timestamp":1768488843571,"version":"3.49.0"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"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","award":["2024YFC3015300"],"award-info":[{"award-number":["2024YFC3015300"]}],"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","award":["62471066"],"award-info":[{"award-number":["62471066"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,14]]},"DOI":"10.1109\/icpads67057.2025.11323227","type":"proceedings-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:36:54Z","timestamp":1768423014000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing Distributed LLM Serving through Request Scheduling and Key-Value Cache Sharing"],"prefix":"10.1109","author":[{"given":"Hongye","family":"Jiang","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mu","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Su","family":"Yao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing National Research Center for Information Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cui","family":"Ting","sequence":"additional","affiliation":[{"name":"Institute of National Security and Development Studies, Guangdong University of Finance and Economics,Guangdong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziwei","family":"Li","sequence":"additional","affiliation":[{"name":"Zhongguancun Laboratory,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changqiao","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Gear: An efficient kv cache compression recipe for near-lossless generative inference of 11m","author":"Kang","year":"2024"},{"key":"ref2","volume-title":"Hydragen: High-throughput 11m inference with shared prefixes","author":"Juravsky","year":"2024"},{"key":"ref3","volume-title":"Sglang: Efficient execution of structured language model programs","author":"Zheng","year":"2024"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1145\/3600006.3613165","volume-title":"Efficient memory management for large language model serving with pagedattention","author":"Kwon","year":"2023"},{"key":"ref5","volume-title":"Prompt cache: Modular attention reuse for low-latency inference","author":"Gim","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15575\/join.v4i2.446"},{"key":"ref7","first-page":"193","article-title":"Distserve: Disaggregating prefill and decoding for goodput-optimized large language model serving","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2024, Santa Clara, CA, USA, July 10\u201312, 2024","author":"Zhong","year":"2024"},{"key":"ref8","volume-title":"Flashforge: Ultra-efficient prefix-aware attention for llm decoding","author":"Wang","year":"2025"},{"key":"ref9","first-page":"45870","article-title":"Toolkengpt: Augmenting frozen language models with massive tools via tool embeddings","volume":"36","author":"Hao","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref10","volume-title":"Loogle: Can long-context language models understand long contexts?","author":"Li","year":"2024"},{"key":"ref11","volume-title":"Fairness in serving large language models","author":"Sheng","year":"2024"},{"key":"ref12","first-page":"553","article-title":"SMART: A high-performance adaptive radix tree for disaggregated memory","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2023, Boston, MA, USA, July 10\u201312, 2023","author":"Luo","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2020.102183"},{"key":"ref14","volume-title":"The missing guide to the h100 gpu market","year":"2024"},{"key":"ref15","volume-title":"Glm-4.5: Agentic, reasoning, and coding (arc) foundation models","author":"Zeng","year":"2025"},{"key":"ref16","article-title":"Text generation inference documentation","volume-title":"Documentation","author":"Face","year":"2023"}],"event":{"name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","location":"Hefei, China","start":{"date-parts":[[2025,12,14]]},"end":{"date-parts":[[2025,12,18]]}},"container-title":["2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11322805\/11322871\/11323227.pdf?arnumber=11323227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:29:58Z","timestamp":1768462198000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11323227\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/icpads67057.2025.11323227","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]}}}