{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T07:22:02Z","timestamp":1772695322808,"version":"3.50.1"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"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":[],"published-print":{"date-parts":[[2026,1,31]]},"DOI":"10.1109\/hpca68181.2026.11408577","type":"proceedings-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T20:47:22Z","timestamp":1772657242000},"page":"1-17","source":"Crossref","is-referenced-by-count":0,"title":["LiLo: Harnessing the on-Chip Accelerators in Intel CPUs for Compressed LLM Inference Acceleration"],"prefix":"10.1109","author":[{"given":"Hyungyo","family":"Kim","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qirong","family":"Xia","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinghan","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nachuan","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Younjoo","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jung Ho","family":"Ahn","sequence":"additional","affiliation":[{"name":"Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wajdi K","family":"Feghali","sequence":"additional","affiliation":[{"name":"Intel Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ren","family":"Wang","sequence":"additional","affiliation":[{"name":"Intel Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nam Sung","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Source coding algorithms for fast data compression, author=Pasco, Richard Clark","year":"1976"},{"key":"ref2","volume-title":"HuggingFace model list for text generation","year":"2025"},{"key":"ref3","volume-title":"Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual: Volume 1","year":"2025"},{"key":"ref4","volume-title":"Intel\u00ae Architecture Instruction Set Extensions and Future Features","year":"2025"},{"key":"ref5","volume-title":"Intel\u00ae Extension for PyTorch","year":"2025"},{"key":"ref6","volume-title":"Intel\u00ae In-Memory Analytics Accelerator (Intel\u00ae IAA)","year":"2025"},{"key":"ref7","volume-title":"Intel\u00ae Query Processing Library (Intel\u00ae QPL)","year":"2025"},{"key":"ref8","volume-title":"Intel\u00ae Xeon\u00ae 6980P Processor","year":"2025"},{"key":"ref9","volume-title":"July 2025 Server Memory Prices","year":"2025"},{"key":"ref10","volume-title":"LLMSimulator","year":"2025"},{"key":"ref11","volume-title":"LZ4 Bindings for Python","year":"2025"},{"key":"ref12","volume-title":"NVIDIA H100 Price Guide 2025: Detailed Costs, Comparisons & Expert Insights","year":"2025"},{"key":"ref13","volume-title":"OpenMP","year":"2025"},{"key":"ref14","volume-title":"Our next-generation model: Gemini 1.5","year":"2025"},{"key":"ref15","volume-title":"The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation","year":"2025"},{"key":"ref16","volume-title":"turbostat - Report processor frequency and idle statistics at Linux.org","year":"2025"},{"key":"ref17","volume-title":"zlib - Compression compatible with gzip","year":"2025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00012"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/sc41404.2022.00051"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/PL00000552"},{"key":"ref21","volume-title":"Unlocking Enterprise AI: Why are CPUs the Backbone!","author":"Blogs","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HCS52781.2021.9567066"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.498"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/jssc.2016.2616357"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"ref26","volume-title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","author":"Deepseek-Ai","year":"2025"},{"key":"ref27","volume-title":"Deepseek-v3 technical report","author":"Liu","year":"2025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.17487\/rfc1951"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1319"},{"key":"ref30","article-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Moetuner: Optimized mixture of expert serving with balanced expert placement and token routing","author":"Go","year":"2025","journal-title":"arXiv preprint"},{"key":"ref32","volume-title":"The Llama 3 Herd of Models","author":"Grattafiori","year":"2024"},{"key":"ref33","volume-title":"Accelerate: Training and inference at scale made simple, efficient and adaptable","author":"Gugger","year":"2022"},{"key":"ref34","volume-title":"Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression","author":"Hong","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1952.273898"},{"key":"ref36","volume-title":"Mixtral of experts","author":"Jiang","year":"2024"},{"key":"ref37","article-title":"Scaling Laws for Neural Language Models","author":"Kaplan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731092"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3431815"},{"key":"ref40","volume-title":"Teknium\u201d, \u201cOpenOrca: An Open Dataset of GPT Augmented FLAN Reasoning Traces","author":"Lian","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.26"},{"key":"ref42","volume-title":"lz4","year":"2025"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.935"},{"key":"ref44","volume-title":"GPT-4 Technical Report","author":"Achiam","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3725843.3756043"},{"key":"ref46","volume-title":"AI Inferencing on Intel CPU-Powered Lenovo Servers: Strategic CPU Selection and Implementation","author":"Press","year":"2025"},{"key":"ref47","volume-title":"Server Memory for Data Centers Market Growth Analysis, Dynamics, Key Players and Innovations, Outlook and Forecast2025\u20132032","author":"Research","year":"2025"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1967.5493"},{"key":"ref49","first-page":"31094","article-title":"FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Sheng","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695964"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/MC.1984.1659158"},{"key":"ref52","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"International Conference on Machine Learning","author":"Xiao","year":"2023"},{"key":"ref53","article-title":"Beyond perplexity: Multi-dimensional safety evaluation of 11 m compression","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00105"},{"key":"ref55","article-title":"Catastrophic Failure of LLM Unlearning via Quantization","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1977.1055714"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1978.1055934"}],"event":{"name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","location":"Sydney, Australia","start":{"date-parts":[[2026,1,31]]},"end":{"date-parts":[[2026,2,4]]}},"container-title":["2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11408404\/11408433\/11408577.pdf?arnumber=11408577","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T06:51:00Z","timestamp":1772693460000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408577\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/hpca68181.2026.11408577","relation":{},"subject":[],"published":{"date-parts":[[2026,1,31]]}}}