{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:50:27Z","timestamp":1765547427047,"version":"3.41.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"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":[[2025,3,31]]},"DOI":"10.23919\/date64628.2025.10992741","type":"proceedings-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T17:36:35Z","timestamp":1747848995000},"page":"1-7","source":"Crossref","is-referenced-by-count":3,"title":["DAOP: Data-Aware Offloading and Predictive Pre-Calculation for Efficient MoE Inference"],"prefix":"10.23919","author":[{"given":"Yujie","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computing, National University of Singapore"}]},{"given":"Shivam","family":"Aggarwal","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore"}]},{"given":"Tulika","family":"Mitra","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"journal-title":"Mixtral of experts","year":"2024","author":"Jiang","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/FPL64840.2024.00048"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.334"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546782"},{"key":"ref6","first-page":"224","article-title":"SiDA: Sparsity-inspired data-aware serving for efficient and scalable large mixture-of-experts models","volume-title":"Proc. of MLSys","volume":"6","author":"Du","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00078"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3676741"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.nlp.2023.100048"},{"journal-title":"LLaMA: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref10"},{"journal-title":"Fast inference of mixture-of-experts language models with offloading","year":"2023","author":"Eliseev","key":"ref11"},{"journal-title":"MoE-Infinity: Activation-aware expert offloading for efficient moe serving","year":"2024","author":"Xue","key":"ref12"},{"journal-title":"EdgeMoE: Fast on-device inference of moe-based large language models","year":"2023","author":"Yi","key":"ref13"},{"journal-title":"Fiddler: CPU-GPU orchestration for fast inference of mixture-of-experts models","year":"2024","author":"Kamahori","key":"ref14"},{"journal-title":"A review of sparse expert models in deep learning","year":"2022","author":"Fedus","key":"ref15"},{"journal-title":"A survey on mixture of experts","year":"2024","author":"Cai","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"},{"journal-title":"Think you have solved question answering? try arc, the ai2 reasoning challenge","year":"2018","author":"Clark","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"journal-title":"Training verifiers to solve math word problems","year":"2021","author":"Cobbe","key":"ref21"},{"journal-title":"Measuring massive multitask language understanding","year":"2020","author":"Hendrycks","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1147"},{"key":"ref24","first-page":"74","article-title":"Rouge: A package for automatic evaluation of sum-maries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"volume-title":"A framework for few-shot language model evaluation","year":"2023","author":"Gao","key":"ref26"},{"volume-title":"ShareGPT","year":"2024","author":"Team","key":"ref27"},{"article-title":"DeepSpeed-MII","volume-title":"Microsoft","year":"2024","key":"ref28"},{"article-title":"GeForce RTX 4090","volume-title":"NVIDIA","year":"2024","key":"ref29"},{"article-title":"MI300X","volume-title":"AMD","year":"2024","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3256796"}],"event":{"name":"2025 Design, Automation & Test in Europe Conference (DATE)","start":{"date-parts":[[2025,3,31]]},"location":"Lyon, France","end":{"date-parts":[[2025,4,2]]}},"container-title":["2025 Design, Automation & Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10992638\/10992588\/10992741.pdf?arnumber=10992741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T05:49:09Z","timestamp":1747892949000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10992741\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":31,"URL":"https:\/\/doi.org\/10.23919\/date64628.2025.10992741","relation":{},"subject":[],"published":{"date-parts":[[2025,3,31]]}}}