{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T06:11:13Z","timestamp":1760422273641,"version":"build-2065373602"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,23]]},"DOI":"10.1109\/icmlt65785.2025.11193187","type":"proceedings-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T17:39:05Z","timestamp":1760377145000},"page":"383-387","source":"Crossref","is-referenced-by-count":0,"title":["S4T-GPTQ: A Space-for-Time Strategy For Optimizing GPTQ 4-bit Quantization"],"prefix":"10.1109","author":[{"given":"Yaozheng","family":"Zhang","sequence":"first","affiliation":[{"name":"Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengxiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Peng","sequence":"additional","affiliation":[{"name":"Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunpeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiehan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haojie","family":"Zhou","sequence":"additional","affiliation":[{"name":"JiangNan University,School of Aritificial Intelligence and Computer Science,Wuxi,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shouhua","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Oulu,Faculty of Information Technology and Computer Science,Oulu,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huanqing","family":"Cui","sequence":"additional","affiliation":[{"name":"Shandong University of Science and Technology,School of Computer Science and Engineering,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2023","author":"Touvron","article-title":"Llama: Open and efficient foundation language models","key":"ref1"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1016\/j.mlwa.2024.100541"},{"year":"2023","author":"Team","article-title":"Gemini: a family of highly capable multimodal models","key":"ref3"},{"year":"2024","author":"Zhou","article-title":"A survey on efficient inference for large language models","key":"ref4"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/CCECE59415.2024.10667177"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/DTPI61353.2024.10778878"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CCECE59415.2024.10667092"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1145\/3600006.3613165"},{"year":"2022","author":"Frantar","article-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","key":"ref9"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1162\/tacl_a_00704"},{"year":"2023","author":"Wu","article-title":"Zeroquant (4+ 2): Redefining llms quantization with a new fp6-centric strategy for diverse generative tasks","key":"ref11"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1609\/aaai.v38i17.29815"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/CIS-RAM61939.2024.10672819"},{"author":"Petrenko","journal-title":"unpublished.","article-title":"Language model optimization using pruning, distillation and quantization techniques for NLP tasks","key":"ref14"},{"key":"ref15","first-page":"148","article-title":"FlashDecoding++: Faster Large Language Model Inference with Asynchronization, Flat GEMM Optimization, and Heuristics","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Hong"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1145\/3620666.3651380"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/MASCOTS64422.2024.10786517"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.3390\/electronics10040438"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.23919\/DATE.2018.8342033"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/CVPR52733.2024.00540"},{"year":"2024","author":"Nair","article-title":"CDQuant: Greedy Coordinate Descent for Accurate LLM Quantization","key":"ref21"},{"year":"2024","author":"Shao","article-title":"GWQ: Gradient-Aware Weight Quantization for Large Language Models","key":"ref22"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/TPDS.2012.319"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1145\/3641289"},{"key":"ref25","article-title":"Efficient training and inference: Techniques for large language models using llama","author":"Cunningham","year":"2024","journal-title":"Authorea Preprints"},{"volume-title":"2024, gitLab repository.","article-title":"vllm-v0.3.3-dtk24.04","key":"ref26"},{"article-title":"The dataset used is ShareGPT_V3_unfiltered_cleaned_split","key":"ref27"}],"event":{"name":"2025 10th International Conference on Machine Learning Technologies (ICMLT)","start":{"date-parts":[[2025,5,23]]},"location":"Helsinki, Finland","end":{"date-parts":[[2025,5,25]]}},"container-title":["2025 10th International Conference on Machine Learning Technologies (ICMLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11192828\/11192850\/11193187.pdf?arnumber=11193187","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T05:34:14Z","timestamp":1760420054000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11193187\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,23]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icmlt65785.2025.11193187","relation":{},"subject":[],"published":{"date-parts":[[2025,5,23]]}}}