{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T05:11:56Z","timestamp":1788844316312,"version":"build-2803163510"},"reference-count":11,"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\/icws72778.2026.00156","type":"proceedings-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:13:55Z","timestamp":1788808435000},"page":"1228-1230","source":"Crossref","is-referenced-by-count":0,"title":["HiCoSched: Production-Trace-Driven Backtesting for LLM Online-Offline Co-Serving"],"prefix":"10.1109","author":[{"given":"Chang","family":"Xu","sequence":"first","affiliation":[{"name":"Peking University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"ChuXuan","family":"Zeng","sequence":"additional","affiliation":[{"name":"China Unicom Intelligent Manufacturing, Technology & Industry (Guangdong) Co., Ltd.","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Peking University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun","family":"Fan","sequence":"additional","affiliation":[{"name":"Peking University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingting","family":"Long","sequence":"additional","affiliation":[{"name":"Peking University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Batch API","year":"2025"},{"key":"ref2","volume-title":"Message Batches","year":"2025"},{"key":"ref3","volume-title":"ConServe: fine-grained GPU harvesting for LLM online and offline co-serving","author":"Qiao","year":"2024"},{"key":"ref4","volume-title":"Hybrid offline-online scheduling method for large language model inference optimization","author":"Pang","year":"2025"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-53282-5","article-title":"Vidur: a large-scale simulation framework for LLM inference","volume-title":"Proc. Machine Learning and Systems (MLSys)","author":"Agrawal","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref7","article-title":"Llumnix: dynamic scheduling for large language model serving","volume-title":"Proc. 18th USENIX Symp. Operating Systems Design and Implementation (OSDI)","author":"Sun","year":"2024"},{"key":"ref8","article-title":"SOLA: optimizing SLO attainment for LLM serving with state-aware scheduling","volume-title":"Proc. Machine Learning and Systems (MLSys)","author":"Hong","year":"2025"},{"key":"ref9","volume-title":"Sarathi: efficient LLM inference by piggybacking decodes with chunked prefills","author":"Agrawal","year":"2023"},{"key":"ref10","volume-title":"BurstGPT: a real-world workload dataset to optimize LLM serving systems","author":"Wang","year":"2025"},{"key":"ref11","volume-title":"ServeGen: workload characterization and generation of large language model serving in production","author":"Xiang","year":"2026"}],"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\/11670053.pdf?arnumber=11670053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T04:52:35Z","timestamp":1788843155000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11670053\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":11,"URL":"https:\/\/doi.org\/10.1109\/icws72778.2026.00156","relation":{},"subject":[],"published":{"date-parts":[[2026,7]]}}}