{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:57:33Z","timestamp":1763704653905,"version":"3.45.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,26]]},"DOI":"10.1109\/iccad66269.2025.11240984","type":"proceedings-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T18:39:34Z","timestamp":1763663974000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["HD-MoE: Hybrid and Dynamic Parallelism for Mixture-of-Expert LLMs with 3D Near-Memory Processing"],"prefix":"10.1109","author":[{"given":"Haochen","family":"Huang","sequence":"first","affiliation":[{"name":"Peking University,Institute for Artificial Intelligence,Beijing,China"}]},{"given":"Shuzhang","family":"Zhong","sequence":"additional","affiliation":[{"name":"Peking University,Institute for Artificial Intelligence,Beijing,China"}]},{"given":"Zhe","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group,DAMO Academy,Beijing,China"}]},{"given":"Shuangchen","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group,DAMO Academy,Beijing,China"}]},{"given":"Dimin","family":"Niu","sequence":"additional","affiliation":[{"name":"Alibaba Group,DAMO Academy,Beijing,China"}]},{"given":"Hongzhong","family":"Zheng","sequence":"additional","affiliation":[{"name":"Alibaba Group,DAMO Academy,Beijing,China"}]},{"given":"Runsheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University,School of Integrated Circuits,Beijing,China"}]},{"given":"Meng","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University,Institute for Artificial Intelligence,Beijing,China"}]}],"member":"263","reference":[{"article-title":"Deepseek-v3 technical report","year":"2024","author":"Liu","key":"ref1"},{"article-title":"Mixtral of experts","year":"2024","author":"Jiang","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3547658"},{"article-title":"Megatron-lm: Training multi-billion parameter language models using model parallelism","year":"2019","author":"Shoeybi","key":"ref5"},{"article-title":"Gshard: Scaling giant models with conditional computation and automatic sharding","year":"2020","author":"Lepikhin","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3676741"},{"article-title":"Task scheduling for efficient inference of large language models on single moderate gpu systems","year":"2024","author":"Lin","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/date64628.2025.10992741"},{"article-title":"Hobbit: A mixed precision expert offloading system for fast moe inference","year":"2024","author":"Tang","key":"ref10"},{"article-title":"Qwen2. 5 technical report","year":"2024","author":"Yang","key":"ref11"},{"article-title":"Deepseek-v2: A strong, economical, and efficient mixture-of-experts language model","year":"2024","author":"Liu","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/DAC63849.2025.11133274"},{"article-title":"Eps-moe: Expert pipeline scheduler for cost-efficient moe inference","year":"2025","author":"Qian","key":"ref14"},{"article-title":"Moetuner: Optimized mixture of expert serving with balanced expert placement and token routing","year":"2025","author":"Go","key":"ref15"},{"article-title":"Shortcut-connected expert parallelism for accelerating mixture-of-experts","year":"2024","author":"Cai","key":"ref16"},{"issue":"120","key":"ref17","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508418"},{"article-title":"Netmoe: Accelerating moe training through dynamic sample placement","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Liu","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HCS59251.2023.10254711"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iedm13553.2020.9372039"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731694"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00037"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731008"},{"article-title":"Qwen2 technical report","year":"2024","author":"Yang","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1122971.1122975"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS48437.2020.00018"},{"key":"ref28","first-page":"46595","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","volume":"36","author":"Zheng","year":"2023","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)","start":{"date-parts":[[2025,10,26]]},"location":"Munich, Germany","end":{"date-parts":[[2025,10,30]]}},"container-title":["2025 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11240608\/11240621\/11240984.pdf?arnumber=11240984","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:47:17Z","timestamp":1763704037000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11240984\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iccad66269.2025.11240984","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]}}}