{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T23:48:37Z","timestamp":1768520917907,"version":"3.49.0"},"reference-count":13,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572341,62202328"],"award-info":[{"award-number":["62572341,62202328"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB4501000"],"award-info":[{"award-number":["2022YFB4501000"]}],"id":[{"id":"10.13039\/501100012166","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\/icpads67057.2025.11323175","type":"proceedings-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:36:54Z","timestamp":1768423014000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["MoEoM: Joint Compute and Memory-Aware Balancing for Fast MoE Inference"],"prefix":"10.1109","author":[{"given":"Ziqi","family":"Gong","sequence":"first","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Advanced Networking,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yitao","family":"Hu","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Advanced Networking,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Advanced Networking,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxin","family":"Li","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Advanced Networking,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keqiu","family":"Li","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Advanced Networking,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref3","author":"Douchet","year":"2025","journal-title":"HarMoEny: Efficient multi-GPU inference of MoE models"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1214\/aop\/1176990746"},{"key":"ref5","article-title":"FasterMoE: Modeling and optimizing training of large-scale MoE models","volume-title":"Proc. 27th ACM SIGPLAN Symp. Principles and Practice of Parallel Programming (PPoPP)","author":"Wang","year":"2022"},{"key":"ref6","author":"Jiang","year":"2024","journal-title":"Mixtral of experts"},{"key":"ref7","volume-title":"Exploiting inter-layer expert affinity for accelerating mixture-of-experts model inference (ExFlow)","author":"Yao","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref9","volume-title":"Memory Systems: Cache, DRAM, Disk","author":"Jacob","year":"2007"},{"key":"ref10","article-title":"ShareGPT52K Dataset","volume-title":"Hugging Face","year":"2025"},{"key":"ref11","article-title":"vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs","volume-title":"GitHub repository","year":"2025"},{"key":"ref12","volume-title":"Gini coefficient","year":"2025"},{"key":"ref13","article-title":"The Pile: An 800 GB Dataset of Diverse Text for Language Modeling","volume-title":"arXiv preprint","author":"Gao","year":"2020"}],"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\/11323175.pdf?arnumber=11323175","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:58:28Z","timestamp":1768463908000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11323175\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/icpads67057.2025.11323175","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]}}}