{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T13:03:42Z","timestamp":1773320622487,"version":"3.50.1"},"reference-count":32,"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\/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":[[2026,1,19]]},"DOI":"10.1109\/asp-dac66049.2026.11420528","type":"proceedings-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:51:15Z","timestamp":1773172275000},"page":"1456-1462","source":"Crossref","is-referenced-by-count":0,"title":["ROMA: A Read-Only-Memory-based Accelerator for QLoRA-based On-Device LLM"],"prefix":"10.1109","author":[{"given":"Wenqiang","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yijia","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zikai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanting","family":"Huo","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Liang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shijie","family":"Cao","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ningyi","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv preprint arXiv:2303.18223"},{"key":"ref2","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv:2205.01068"},{"key":"ref3","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2302.13971"},{"key":"ref4","article-title":"Large language model inference acceleration: A comprehensive hardware perspective","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2410.04466"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref6","article-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022","journal-title":"arXiv preprint arXiv:2210.17323"},{"key":"ref7","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint arXiv:2106.09685"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref10","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2307.09288"},{"key":"ref11","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv preprint arXiv:2407.21783"},{"key":"ref12","article-title":"Mistral 7b","author":"jiang","year":"2023","journal-title":"arXiv preprint arXiv:2310.06825"},{"key":"ref13","article-title":"Gemma: Open models based on gemini research and technology","author":"Team","year":"2024","journal-title":"arXiv preprint arXiv:2403.08295"},{"key":"ref14","article-title":"Twitter Financial News Sentiment"},{"key":"ref15","article-title":"Gpt-4 technical report","volume-title":"arXiv preprint arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref16","article-title":"Apple intelligence foundation language models","author":"Gunter","year":"2024","journal-title":"arXiv preprint arXiv:2407.21075"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1049\/piee.1963.0023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1975.224307"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5015-0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1463891.1463976"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/nano10081555"},{"key":"ref22","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint arXiv:2407.21783"},{"key":"ref23","article-title":"Llama 3.2"},{"key":"ref24","article-title":"FusionCompiler"},{"key":"ref25","article-title":"PTPX"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00064"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2024.3350661"},{"key":"ref29","article-title":"i5-1135g7"},{"key":"ref30","article-title":"RTX 4090"},{"key":"ref31","article-title":"Llamacpp"},{"key":"ref32","article-title":"TensorRT-LLM"}],"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\/11420528.pdf?arnumber=11420528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T19:35:57Z","timestamp":1773257757000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11420528\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,19]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/asp-dac66049.2026.11420528","relation":{},"subject":[],"published":{"date-parts":[[2026,1,19]]}}}