{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:52:52Z","timestamp":1763704372689,"version":"3.45.0"},"reference-count":40,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,26]]},"DOI":"10.1109\/iccad66269.2025.11240807","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":["MoE-OPU: An FPGA Overlay Processor Leveraging Expert Parallelism for MoE-based Large Language Models"],"prefix":"10.1109","author":[{"given":"Shaoqiang","family":"Lu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangbo","family":"Wei","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhong","family":"Qian","sequence":"additional","affiliation":[{"name":"Southeast University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Wu","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology,Ningbo,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Shi","sequence":"additional","affiliation":[{"name":"Southeast University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"He","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology,Ningbo,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.3"},{"article-title":"UniAudio: Towards universal audio generation with large language models","volume-title":"International Conference on Machine Learning (ICML)","author":"Yang","key":"ref2"},{"article-title":"DeLLMa: Decision making under uncertainty with large language models","volume-title":"The Thirteenth International Conference on Learning Representations (ICLR)","author":"Liu","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0038"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00051"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1145\/3676536.3676761","article-title":"ChatOPU: An FPGA-based overlay processor for large language models with unstructured sparsity","volume-title":"IEEE\/ACM International Conference on Computer-Aided Design (ICCAD)","author":"Zhao"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00081"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00082"},{"article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"International Conference on Learning Representations (ICLR)","author":"Shazeer","key":"ref9"},{"article-title":"FIDDLER: CPU-GPU orchestration for fast inference of mixture-of-experts models","year":"2024","author":"Kamahori","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3656507"},{"article-title":"M3ViT: mixture-of-experts vision transformer for efficient multi-task learning with model-accelerator co-design","volume-title":"International Conference on Neural Information Processing Systems (NIPS)","author":"Liang","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323651"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00105"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49657.2024.10454487"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604869"},{"article-title":"Examining post-training quantization for mixture-of-experts: A benchmark","year":"2024","author":"Li","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3706628.3708867"},{"article-title":"Speculative MoE: Communication efficient parallel moe inference with speculative token and expert pre-scheduling","year":"2025","author":"Li","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3317789"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/FPL53798.2021.00014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637569"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3656177"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2020.2995741"},{"article-title":"A survey on inference optimization techniques for mixture of experts models","year":"2024","author":"Liu","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637562"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3656497"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3490422.3502364"},{"key":"ref29","article-title":"ProMOE: Fast moe-based llm serving using proactive caching","author":"Song","year":"2024","journal-title":"preprint arXiv:2410.22134"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2019.2939726"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3706628.3708864"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3373087.3375311"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3474597"},{"key":"ref34","article-title":"NVIDIA-SMI: NVIDIA System Management Interface User Guide","author":"Corporation","year":"2013","journal-title":"NVIDIA Technical Documentation"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"ref36","article-title":"DeepSeek-V2: A strong, economical, and efficient mixture-of-experts language model","volume-title":"CoRR","author":"Liu","year":"2024"},{"year":"2024","key":"ref37","article-title":"Qwen1.5-MoE: Matching 7b model performance with 1\/3 activated parameters"},{"article-title":"Muon is scalable for llm training","year":"2025","author":"Liu","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323752"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ISEDA62518.2024.10617729"}],"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\/11240807.pdf?arnumber=11240807","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:44:39Z","timestamp":1763703879000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11240807\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/iccad66269.2025.11240807","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]}}}