{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:10:37Z","timestamp":1781885437939,"version":"3.54.5"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"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":[[2025,10,26]]},"DOI":"10.1109\/iccad66269.2025.11240713","type":"proceedings-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T18:39:34Z","timestamp":1763663974000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["H\n                    <sup>2<\/sup>\n                    EAL: Hybrid-Bonding Architecture with Hybrid Sparse Attention for Efficient Long-Context LLM Inference"],"prefix":"10.1109","author":[{"given":"Zizhuo","family":"Fu","sequence":"first","affiliation":[{"name":"Institute for Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaotian","family":"Guo","sequence":"additional","affiliation":[{"name":"Peking University,School of Integrated Circuits,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxuan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuzhang","family":"Zhong","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yadong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nano Core Chip Electronic Technology,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peiyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Nano Core Chip Electronic Technology,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runsheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University,School of Integrated Circuits,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le","family":"Ye","sequence":"additional","affiliation":[{"name":"Peking University,School of Integrated Circuits,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Li","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3771090"},{"key":"ref2","article-title":"Agent ai: Surveying the horizons of multimodal interaction","author":"Durante","year":"2024"},{"key":"ref3","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","author":"Huang","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3545176"},{"key":"ref5","article-title":"A survey on multi-turn interaction capabilities of large language models","author":"Zhang","year":"2025"},{"key":"ref6","article-title":"Towards reasoning era: A survey of long chain-of-thought for reasoning large language models","author":"Chen","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00105"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875680"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00037"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731694"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM13553.2020.9372039"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731565"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731008"},{"key":"ref16","article-title":"H2o: Heavy-hitter oracle for efficient generative inference of large language models","author":"Zhang","year":"2023"},{"key":"ref17","article-title":"Quest: Query-aware sparsity for efficient long-context llm inference","author":"Tang","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1126"},{"key":"ref19","article-title":"Duoattention: Efficient long-context llm inference with retrieval and streaming heads","author":"Xiao","year":"2024"},{"key":"ref20","article-title":"Not all heads matter: A head-level kv cache compression method with integrated retrieval and reasoning","author":"Fu","year":"2024"},{"key":"ref21","article-title":"Keep the cost down: A review on methods to optimize llm\u2019 s kv-cache consumption","author":"Luohe","year":"2024"},{"key":"ref22","article-title":"Efficient streaming language models with attention sinks","author":"Xiao","year":"2023"},{"key":"ref23","article-title":"Model tells you what to discard: Adaptive kv cache compression for llms","author":"Ge","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3595"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3213542"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3500362"},{"key":"ref27","article-title":"Lserve: Efficient long-sequence llm serving with unified sparse attention","author":"Yang","year":"2025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"ref29","article-title":"Fast transformer decoding: One write-head is all you need","author":"Shazeer","year":"2019"},{"key":"ref30","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref31","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref32","article-title":"Deepseek-v2: A strong, economical, and efficient mixture-of-experts language model","author":"Shao","year":"2024"},{"key":"ref33","article-title":"Mpcache: Mpc-friendly kv cache eviction for efficient private large language model inference","author":"Zeng","year":"2025"},{"key":"ref34","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","author":"Dao","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.4153\/CJM-1956-045-5"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365766"},{"key":"ref37","article-title":"Qserve: W4a8kv4 quantization and system co-design for efficient llm serving","author":"Lin","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.172"},{"key":"ref39","article-title":"Llmtest needle in a haystack - pressure testing llms","year":"2023"}],"event":{"name":"2025 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)","location":"Munich, Germany","start":{"date-parts":[[2025,10,26]]},"end":{"date-parts":[[2025,10,30]]}},"container-title":["2025 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11240608\/11240621\/11240713.pdf?arnumber=11240713","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:43:19Z","timestamp":1763703799000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11240713\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/iccad66269.2025.11240713","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]}}}