{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T21:57:04Z","timestamp":1757627824797,"version":"3.44.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T00:00:00Z","timestamp":1751414400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T00:00:00Z","timestamp":1751414400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172241,62402247"],"award-info":[{"award-number":["62172241,62402247"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["CUC24GT17"],"award-info":[{"award-number":["CUC24GT17"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,2]]},"DOI":"10.1109\/iwqos65803.2025.11143346","type":"proceedings-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T17:29:52Z","timestamp":1757438992000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Libra: Novel LLM Token Streaming via Region-Based Task Scheduling and Token Bundling"],"prefix":"10.1109","author":[{"given":"Chengjin","family":"Zhou","sequence":"first","affiliation":[{"name":"College of Computer Science, DISSec, Nankai University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science, DISSec, Nankai University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinjing","family":"Yuan","sequence":"additional","affiliation":[{"name":"College of Computer Science, DISSec, Nankai University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianxin","family":"Shi","sequence":"additional","affiliation":[{"name":"College of Computer Science, DISSec, Nankai University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Communication University of China,State Key Laboratory of Media Convergence and Communication,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingjun","family":"Pu","sequence":"additional","affiliation":[{"name":"College of Computer Science, DISSec, Nankai University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"GPT-4o."},{"key":"ref2","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref3","author":"Zhang","year":"2022","journal-title":"Opt: Open pre-trained transformer language models"},{"key":"ref4","author":"Zheng","year":"2023","journal-title":"Lmsys-chat-1m: A large-scale real-world llm conversation dataset"},{"key":"ref5","author":"Wan","year":"2023","journal-title":"Efficient large language models: A survey"},{"key":"ref6","author":"Liu","year":"2024","journal-title":"Andes: Defining and enhancing quality-of-experience in llm-based text streaming services"},{"key":"ref7","author":"Wang","year":"2024","journal-title":"Towards efficient and reliable llm serving: A real-world workload study"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref9","article-title":"Orca: A distributed serving system for transformer-based generative models","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Yu","year":"2022"},{"key":"ref10","article-title":"Efficiently scaling transformer inference","volume-title":"Proceedings of Machine Learning and Systems (MLSys)","author":"Pope","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640383"},{"key":"ref12","author":"Qin","year":"2024","journal-title":"Mooncake: A kvcache-centric disaggregated architecture for llm serving"},{"key":"ref13","author":"Hu","year":"2024","journal-title":"Inference without interference: Disaggregate 1 lm inference for mixed downstream workloads"},{"key":"ref14","article-title":"Llumnix: Dynamic scheduling for large language model serving","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Sun","year":"2024"},{"key":"ref15","author":"Shen","year":"2024","journal-title":"Fastswitch: Optimizing context switching efficiency in fairness-aware large language model serving"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696086"},{"key":"ref17","article-title":"LMSYS-chat-1m: A large-scale real-world LLM conversation dataset","volume-title":"The Twelfth International Conference on Learning Representations (ICLR)","author":"Zheng","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.17487\/rfc7141"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2008.93"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS54832.2022.9812871"},{"key":"ref21","author":"Chen","year":"2023","journal-title":"Typefly: Flying drones with large language model"},{"key":"ref22","article-title":"{TANGO}: Secure collaborative route control across the public internet","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI)","author":"Birge-Lee","year":"2024"},{"key":"ref23","article-title":"Fairness in serving large language models","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Sheng","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.2200\/s00271ed1v01y201006cnt007"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2656877.2656890"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672228"},{"key":"ref27","author":"Taori","year":"2023","journal-title":"Stanford alpaca: An instruction-following llama model"},{"key":"ref28","volume-title":"ShareGPT Dataset."},{"key":"ref29","volume-title":"OpenAI ChatGPT."},{"key":"ref30","volume-title":"OpenAI Tokenizer."}],"event":{"name":"2025 IEEE\/ACM International Symposium on Quality of Service (IWQoS)","location":"Gold Coast, Australia","start":{"date-parts":[[2025,7,2]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE\/ACM 33rd International Symposium on Quality of Service (IWQoS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11143240\/11143247\/11143346.pdf?arnumber=11143346","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T05:04:49Z","timestamp":1757480689000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11143346\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,2]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iwqos65803.2025.11143346","relation":{},"subject":[],"published":{"date-parts":[[2025,7,2]]}}}