{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T22:08:16Z","timestamp":1775081296132,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/globecom59602.2025.11431780","type":"proceedings-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T20:04:01Z","timestamp":1773950641000},"page":"2547-2552","source":"Crossref","is-referenced-by-count":0,"title":["ChAMP: Optimizing Collaborative Inference with Chunking Adaptive Mixed Parallelism"],"prefix":"10.1109","author":[{"given":"Yulin","family":"Chen","sequence":"first","affiliation":[{"name":"The International Joint Institute of Tianjin University, Tianjin University,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Qiu","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhicheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunfeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Gao","sequence":"additional","affiliation":[{"name":"Tianjin University,College of New Media and Communication,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3672758.3672824"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref3","article-title":"GPT-4o system card","author":"Hurst","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.121.2100324"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3123535"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM52923.2024.10901157"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599453"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3543295"},{"key":"ref9","article-title":"Tinyagent: Quantization-aware model compression and adaptation for on-device LLM agent deployment","author":"Kong","year":"2024","journal-title":"ICML 2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3284217"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3132413"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3432855"},{"key":"ref13","first-page":"667","article-title":"OPER: Optimality-guided embedding table parallelization for large-scale recommendation model","author":"Wang","year":"2024","journal-title":"USENIX ATC 2024"},{"key":"ref14","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.134"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3098451"},{"key":"ref17","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Advances in Neural Infor. Proc. Sys","volume":"30","author":"Lowe"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"issue":"8","key":"ref19","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI"},{"key":"ref20","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"}],"event":{"name":"GLOBECOM 2025 - 2025 IEEE Global Communications Conference","location":"Taipei, Taiwan","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,12]]}},"container-title":["GLOBECOM 2025 - 2025 IEEE Global Communications Conference"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11431620\/11431622\/11431780.pdf?arnumber=11431780","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:07:06Z","timestamp":1775074026000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11431780\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/globecom59602.2025.11431780","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}