{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T05:12:04Z","timestamp":1788844324710,"version":"build-2803163510"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/icws72778.2026.00179","type":"proceedings-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:09:24Z","timestamp":1788808164000},"page":"1461-1470","source":"Crossref","is-referenced-by-count":0,"title":["QoS-Aware Prefix Orchestration for Geo-Distributed LLM-as-a-Service"],"prefix":"10.1109","author":[{"given":"Zhangyang","family":"Ge","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Introducing ChatGPT","year":"2022"},{"key":"ref2","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"DeepSeek-V3 technical report","volume-title":"arXiv preprint","author":"Liu","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3642970.3655843"},{"key":"ref5","article-title":"SkyPilot: An intercloud broker for sky computing","volume-title":"Proc. 20th USENIX Symp. Networked Systems Design and Implementation (NSDI)","author":"Yang","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2000"},{"key":"ref8","article-title":"GORGO: Maximizing KV-Cache reuse while minimizing network latency in cross-region LLM load balancing","volume-title":"arXiv preprint","author":"Toniolo","year":"2026"},{"key":"ref9","article-title":"SkyWalker: A localityaware cross-region load balancer for LLM inference","volume-title":"arXiv preprint","author":"Xia","year":"2025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/spe.70054"},{"key":"ref11","article-title":"Mooncake: Trading more storage for less computation - a KV-cache-centric architecture for serving LLM chatbot","volume-title":"Proc. 23rd USENIX Conf. File and Storage Technologies (FAST)","author":"Qin","year":"2025"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707215"},{"key":"ref13","article-title":"Parallax: Efficient LLM inference service over decentralized environment","volume-title":"arXiv preprint","author":"Tong","year":"2025"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1145\/3731569.3764834","article-title":"PrefillOnly: An inference engine for prefillonly workloads in large language model applications","volume-title":"arXiv preprint","author":"Du","year":"2025"},{"key":"ref15","article-title":"TokenLake: A unified segment-level prefix cache pool for fine-grained elastic longcontext LLM serving","volume-title":"arXiv preprint","author":"Wu","year":"2025"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1145\/3771576","article-title":"SageServe: Optimizing LLM serving on cloud data centers with forecast aware auto-scaling","volume-title":"arXiv preprint","author":"Jaiswal","year":"2025"},{"key":"ref17","article-title":"WANSpec: Leveraging global compute capacity for LLM inference","volume-title":"arXiv preprint","author":"Martin","year":"2026"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"ref19","first-page":"57","article-title":"FastServe: Iteration-level preemptive scheduling for large language model inference","volume-title":"Proc. 23rd USENIX Symp. Networked Systems Design and Implementation (NSDI)","author":"Wu","year":"2026"},{"key":"ref20","article-title":"Preble: Efficient distributed prompt scheduling for LLM serving","volume-title":"arXiv preprint","author":"Srivatsa","year":"2024"},{"key":"ref21","first-page":"117","article-title":"Taming throughputlatency tradeoff in LLM inference with Sarathi-Serve","volume-title":"Proc. 18th USENIX Symp. Operating Systems Design and Implementation (OSDI)","author":"Agrawal","year":"2024"},{"key":"ref22","first-page":"193","article-title":"DistServe: Disaggregating prefill and decoding for goodput-optimized large language model serving","volume-title":"Proc. 18th USENIX Symp. Operating Systems Design and Implementation (OSDI)","author":"Zhong","year":"2024"}],"event":{"name":"2026 IEEE International Conference on Web Services (ICWS)","location":"Sydney, Australia","start":{"date-parts":[[2026,7,13]]},"end":{"date-parts":[[2026,7,18]]}},"container-title":["2026 IEEE International Conference on Web Services (ICWS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11670018\/11670022\/11670114.pdf?arnumber=11670114","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T04:53:09Z","timestamp":1788843189000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11670114\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icws72778.2026.00179","relation":{},"subject":[],"published":{"date-parts":[[2026,7]]}}}