{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:28:31Z","timestamp":1777984111349,"version":"3.51.4"},"reference-count":14,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["IEEE Comput. Arch. Lett."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/lca.2026.3659512","type":"journal-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T21:02:09Z","timestamp":1769806929000},"page":"45-48","source":"Crossref","is-referenced-by-count":0,"title":["De-Quantization Penalties for Interactive LLM Inference on Prosumer GPUs"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7211-4646","authenticated-orcid":false,"given":"Junaid Ahmad","family":"Khan","sequence":"first","affiliation":[{"name":"Department of Electrical and Information Engineering, Seoul National University of Science and Technology, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3719664"},{"key":"ref2","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022"},{"key":"ref3","first-page":"606","article-title":"Efficiently scaling transformer inference","volume-title":"Proc. Mach. Learn. Syst.","volume":"5","author":"Pope"},{"key":"ref4","first-page":"87","article-title":"AWQ: Activation-aware weight quantization for on-device LLM compression and acceleration","volume-title":"Proc. Mach. Learn. Syst.","volume":"6","author":"Lin"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref6","first-page":"30318","article-title":"GPT3.int8(): 8-bit matrix multiplication for transformers at scale","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dettmers"},{"key":"ref7","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao"},{"key":"ref8","first-page":"196","article-title":"Atom: Low-bit quantization for efficient and accurate LLM serving","volume-title":"Proc. Mach. Learn. Syst.","volume":"6","author":"Zhao"},{"key":"ref9","article-title":"A100 tensor core GPU architecture","author":"Nvidia","year":"2020"},{"key":"ref10","article-title":"LUT-LLM: Efficient large language model inference with memory-based computations on FPGAs","author":"He","year":"2025"},{"key":"ref11","article-title":"Hardware acceleration of LLMs: A comprehensive survey and comparison","author":"Koilia","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3710848.3710871"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651329"},{"key":"ref14","article-title":"Advances to low-bit quantization enable LLMs on edge devices","author":"Research","year":"2024"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10208\/11321093\/11368735.pdf?arnumber=11368735","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:47:07Z","timestamp":1771879627000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11368735\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":14,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/lca.2026.3659512","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.177203475.54045626\/v1","asserted-by":"object"}]},"ISSN":["1556-6056","1556-6064","2473-2575"],"issn-type":[{"value":"1556-6056","type":"print"},{"value":"1556-6064","type":"electronic"},{"value":"2473-2575","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}