{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:00:31Z","timestamp":1780639231710,"version":"3.54.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"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"}]},{"DOI":"10.13039\/501100005145","name":"Basic Research Program of Jiangsu Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005145","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,20]]},"DOI":"10.23919\/date69613.2026.11539301","type":"proceedings-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:53:10Z","timestamp":1780602790000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systems"],"prefix":"10.23919","author":[{"given":"Qi","family":"Wu","sequence":"first","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Fang","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayuan","family":"Chen","sequence":"additional","affiliation":[{"name":"China Mobile Research Institute,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Lin","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichuan","family":"Bai","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Du","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Du","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"International Conference on Learning Representations (ICLR)","author":"Shazeer"},{"key":"ref4","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref5","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref6","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00110"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3554028"},{"key":"ref9","article-title":"GeForce RTX 5080","year":"2025"},{"key":"ref10","article-title":"Qwen3 technical report","author":"Yang","year":"2025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00051"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716261"},{"key":"ref13","article-title":"Fast inference of mixture-of-experts language models with offloading","author":"Eliseev","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/DATE64628.2025.10992741"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707267"},{"key":"ref16","article-title":"Fiddler: CPU-GPU orchestration for fast inference of mixture-of-experts models","volume-title":"International Conference on Learning Representation (ICLR)","author":"Kamahori"},{"key":"ref17","first-page":"1","article-title":"Monde: Mixture of near-data experts for large-scale sparse models","volume-title":"Proceedings of the 61st ACM\/IEEE Design Automation Conference (DAC)","author":"Kim"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00105"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3676733"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/FLLM63129.2024.10852473"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC58780.2024.10473817"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00082"},{"key":"ref23","first-page":"5209","article-title":"Medusa: Simple llm inference acceleration framework with multiple decoding heads","volume-title":"International Conference on Machine Learning (ICML)","author":"Cai"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00070"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358284"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/DAC63849.2025.11132528"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00129"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875680"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD66269.2025.11240889"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.23919\/DATE64628.2025.10993222"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546723"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546797"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00053"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM57271.2023.00015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2022.3160455"},{"key":"ref37","article-title":"Mixtral of experts","author":"Jiang","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3132402.3132406"},{"key":"ref39","article-title":"intel-core-i7-14700","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2023.3333759"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"ref42","article-title":"Phi-3 safety post-training: Aligning language models with a \u2018break-fix\u2019 cycle","author":"Haider","year":"2024"}],"event":{"name":"2026 Design, Automation & Test in Europe Conference (DATE)","location":"Verona, Italy","start":{"date-parts":[[2026,4,20]]},"end":{"date-parts":[[2026,4,22]]}},"container-title":["2026 Design, Automation & Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11539023\/11539024\/11539301.pdf?arnumber=11539301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:07:17Z","timestamp":1780636037000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11539301\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":42,"URL":"https:\/\/doi.org\/10.23919\/date69613.2026.11539301","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]}}}