{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T13:03:48Z","timestamp":1773320628683,"version":"3.50.1"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,19]]},"DOI":"10.1109\/asp-dac66049.2026.11420472","type":"proceedings-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:51:15Z","timestamp":1773172275000},"page":"999-1005","source":"Crossref","is-referenced-by-count":0,"title":["MoBiLE: Efficient Mixture-of-Experts Inference on Consumer GPU with Mixture of Big Little Experts"],"prefix":"10.1109","author":[{"given":"Yushu","family":"Zhao","sequence":"first","affiliation":[{"name":"Tsinghua University,BNRist"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yubin","family":"Qin","sequence":"additional","affiliation":[{"name":"Tsinghua University,BNRist"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,BNRist"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolong","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University,BNRist"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiming","family":"Han","sequence":"additional","affiliation":[{"name":"Tsinghua University,BNRist"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaojun","family":"Wei","sequence":"additional","affiliation":[{"name":"Tsinghua University,BNRist"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Hu","sequence":"additional","affiliation":[{"name":"Tsinghua University,BNRist"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shouyi","family":"Yin","sequence":"additional","affiliation":[{"name":"Tsinghua University,BNRist"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey on mixture of experts","volume":"abs\/2407.06204","author":"Cai","year":"2024","journal-title":"CoRR"},{"key":"ref2","article-title":"Evaluating large language models trained on code","volume":"abs\/2107.03374","author":"Chen","year":"2021"},{"key":"ref3","article-title":"Training verifiers to solve math word problems","volume":"abs\/2110.14168","author":"Cobbe","year":"2021","journal-title":"CoRR"},{"key":"ref4","article-title":"No language left behind: Scaling human-centered machine translation","volume":"abs\/2207.04672","author":"Costa-juss\u00e0","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"ref6","article-title":"Sida: Sparsity-inspired data-aware serving for efficient and scalable large mixture-of-experts models","author":"Du","year":"2024"},{"key":"ref7","first-page":"120:1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00078"},{"key":"ref9","article-title":"Speculative decoding with big little decoder","author":"Kim","year":"2023"},{"key":"ref10","article-title":"Scaling laws for fine-grained mixture of experts","author":"Ludziejewski","year":"2024"},{"key":"ref11","article-title":"Olmoe: Open mixture-of-experts language models","volume":"abs\/2409.02060","author":"Muennighoff","year":"2024","journal-title":"CoRR"},{"key":"ref12","article-title":"HOBBIT: A mixed precision expert offloading system for fast moe inference","volume":"abs\/2411.01433","author":"Tang","year":"2024","journal-title":"CoRR"},{"key":"ref13","article-title":"Qwen1.5-moe: Matching 7b model performance with 1\/3 activated parameters","author":"Team"},{"key":"ref14","article-title":"Edgemoe: Fast on-device inference of moe-based large language models","volume":"abs\/2308.14352","author":"Yi","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3676741"}],"event":{"name":"2026 31st Asia and South Pacific Design Automation Conference (ASP-DAC)","location":"Lantau, Hong Kong","start":{"date-parts":[[2026,1,19]]},"end":{"date-parts":[[2026,1,22]]}},"container-title":["2026 31st Asia and South Pacific Design Automation Conference (ASP-DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11420221\/11420229\/11420472.pdf?arnumber=11420472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T19:36:00Z","timestamp":1773257760000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11420472\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,19]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/asp-dac66049.2026.11420472","relation":{},"subject":[],"published":{"date-parts":[[2026,1,19]]}}}