{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:00:43Z","timestamp":1780639243559,"version":"3.54.1"},"reference-count":34,"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\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","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\/date69613.2026.11539577","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":["Dolphium: Co-Optimizing Quantization Dataflow and Paradigms on Poly-Hierarchical NPUs"],"prefix":"10.23919","author":[{"given":"Xiuping","family":"Cui","sequence":"first","affiliation":[{"name":"Peking University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengrui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun Eric","family":"Liang","sequence":"additional","affiliation":[{"name":"Peking University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358302"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00071"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2654822.2541967"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716243"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2017.2765695"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00083"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589048"},{"key":"ref9","author":"Lin","year":"2025","journal-title":"Qserve: W4a8kv4 quantization and system co-design for efficient llm serving"},{"key":"ref10","article-title":"Atom: Low-bit quantization for efficient and accurate llm serving","author":"Zhao","year":"2024","journal-title":"MLSys"},{"key":"ref11","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"ICML","author":"Xiao"},{"key":"ref12","article-title":"Awq: Activation-aware weight quantization for llm compression and acceleration","author":"Lin","year":"2024","journal-title":"MLSys"},{"key":"ref13","author":"Frantar","year":"2022","journal-title":"GPTQ: Accurate post-training compression for generative pretrained transformers"},{"key":"ref14","author":"Shao","year":"2023","journal-title":"Omniquant: Omnidirectionally calibrated quantization for large language models"},{"key":"ref15","author":"Zhang","year":"2024","journal-title":"Qqq: Quality quattuor-bit quantization for large language models"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/DATE64628.2025.10993079"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/DATE64628.2025.10992912"},{"key":"ref18","article-title":"Evasion: Efficient kv cache compression via product quantization","volume-title":"DATE","author":"Wang"},{"key":"ref19","year":"2025","journal-title":"Cann-ops-adv operator library"},{"key":"ref20","article-title":"Ladder: Enabling efficient Low-Precision deep learning computing through hardware-aware tensor transformation","volume-title":"OSDI","author":"Wang"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1145\/3352460.3358252","article-title":"Understanding reuse, performance, and hardware cost of dnn dataflow: A data-centric approach","volume-title":"MICRO","author":"Kwon"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623792"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527440"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3655922"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651330"},{"key":"ref29","author":"Touvron","year":"2023","journal-title":"Llama 2: Open foundation and fine-tuned chat models"},{"key":"ref30","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref31","author":"Jiang","year":"2024","journal-title":"Mixtral of experts"},{"key":"ref32","author":"Merity","year":"2016","journal-title":"Pointer sentinel mixture models"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref34","author":"Clark","year":"2018","journal-title":"Think you have solved question answering? try arc, the ai2 reasoning challenge"}],"event":{"name":"2026 Design, Automation &amp; 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 &amp;amp; Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11539023\/11539024\/11539577.pdf?arnumber=11539577","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:08:30Z","timestamp":1780636110000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11539577\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":34,"URL":"https:\/\/doi.org\/10.23919\/date69613.2026.11539577","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]}}}