{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T13:48:10Z","timestamp":1772632090134,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,2,15]],"date-time":"2026-02-15T00:00:00Z","timestamp":1771113600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,15]],"date-time":"2026-02-15T00:00:00Z","timestamp":1771113600000},"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":[[2026,2,15]]},"DOI":"10.1109\/isscc49663.2026.11409211","type":"proceedings-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:50:24Z","timestamp":1772571024000},"page":"532-534","source":"Crossref","is-referenced-by-count":0,"title":["31.1 A 14.08-to-135.69Token\/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding"],"prefix":"10.1109","author":[{"given":"Pingcheng","family":"Dong","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghao","family":"Tan","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuejiao","family":"Liu","sequence":"additional","affiliation":[{"name":"AI Chip Center for Emerging Smart System,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Luo","sequence":"additional","affiliation":[{"name":"AI Chip Center for Emerging Smart System,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"AI Chip Center for Emerging Smart System,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Pang","sequence":"additional","affiliation":[{"name":"AI Chip Center for Emerging Smart System,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songchen","family":"Ma","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xijie","family":"Huang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shih-Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhichao","family":"Lu","sequence":"additional","affiliation":[{"name":"Hefei Reliance Memory,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luhong","family":"Liang","sequence":"additional","affiliation":[{"name":"AI Chip Center for Emerging Smart System,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-Ying","family":"Tsui","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengbin","family":"Tu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kwang-Ting","family":"Cheng","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The Llama 3 Herd of Models","author":"Dubey","year":"2024","journal-title":"arXiv"},{"key":"ref2","article-title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","author":"Touvron","year":"2023","journal-title":"arXiv"},{"key":"ref3","first-page":"368","article-title":"C-Transformer: A 2.6-18.1 \u03bcJ\/token Homogeneous DNN-Transformer\/Spiking-Transformer Processor with Big-Little Network and Implicit Weight Generation for Large Language Models","author":"Kim","year":"2024","journal-title":"ISSCC"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/isscc49661.2025.10904774"},{"key":"ref5","first-page":"421","article-title":"Slim-Llama: A 4.69 mW Large-Language-Model Processor with Binary\/Ternary Weights for Billion-Parameter Llama Model","author":"Kim","year":"2025","journal-title":"ISSCC"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/vlsitechnologyandcir65189.2025.11074939"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.23919\/VLSITechnologyandCir65189.2025.11075101","article-title":"CELLA: A 28nm Compute-Memory Co-Optimized Real-Time Digital CIMBased Edge LLM Accelerator with 1.78 ms -Response in Prefill and 31.32 Token\/s in Decoding","volume-title":"IEEE Symp. VLSI Circuits","author":"Wu","year":"2025"},{"key":"ref8","first-page":"19274","article-title":"Fast Inference from Transformers via Speculative Decoding","author":"Leviathan","year":"2023","journal-title":"ICML"},{"key":"ref9","first-page":"28935","article-title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","author":"Li","year":"2024","journal-title":"ICML"},{"key":"ref10","article-title":"GPTQ: Accurate Post-Training Quantization for Generative Pretrained Transformers","author":"Frantar","year":"2023","journal-title":"ICLR"},{"key":"ref11","first-page":"100213","article-title":"QuaRot: Outlier-Free 4-bit Inference in Rotated LLMs","author":"Ashkboos","year":"2024","journal-title":"NeurIPS"},{"key":"ref12","article-title":"SpinQuant: LLM Quantization with Learned Rotations","author":"Liu","year":"2025","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.444"},{"key":"ref14","article-title":"PEARL: Parallel Speculative Decoding with Adaptive Draft Length","author":"Liu","year":"2025","journal-title":"ICLR"},{"key":"ref15","volume-title":"A Library of Hadamard Matrices","author":"Sloane","year":"2024"},{"key":"ref16","article-title":"GPTVQ: The Blessing of Dimensionality for LLM Quantization","author":"Mart","year":"2024","journal-title":"arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.467"},{"key":"ref18","first-page":"731","article-title":"MVQ: Towards Efficient DNN Compression and Acceleration with Masked Vector Quantization","author":"Li","year":"2025","journal-title":"ACM ASPLOS"},{"key":"ref19","first-page":"7736","article-title":"MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models","author":"Gong","year":"2024","journal-title":"NeurIPS"},{"key":"ref20","first-page":"408","article-title":"A 28 nm 0.22 \u03bcJ\/Token Memory-Compute-Intensity-Aware CNNTransformer Accelerator with Hybrid-Attention-Based Layer-Fusion and Cascaded Pruning for Semantic-Segmentation","author":"Dong","year":"2025","journal-title":"ISSCC"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037702"}],"event":{"name":"2026 IEEE International Solid-State Circuits Conference (ISSCC)","location":"San Francisco, CA, USA","start":{"date-parts":[[2026,2,15]]},"end":{"date-parts":[[2026,2,19]]}},"container-title":["2026 IEEE International Solid-State Circuits Conference (ISSCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11408863\/11408946\/11409211.pdf?arnumber=11409211","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T06:50:41Z","timestamp":1772607041000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11409211\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,15]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/isscc49663.2026.11409211","relation":{},"subject":[],"published":{"date-parts":[[2026,2,15]]}}}