{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T22:53:03Z","timestamp":1768517583113,"version":"3.49.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0201504"],"award-info":[{"award-number":["2021ZD0201504"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,14]]},"DOI":"10.1109\/icpads67057.2025.11323105","type":"proceedings-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:36:54Z","timestamp":1768423014000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["LISLLM: Long Context Inference of Large Language Models with Short KV Cache"],"prefix":"10.1109","author":[{"given":"Tielong","family":"Liu","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,CDL,Beijing,China"}]},{"given":"Gang","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,CDL,Beijing,China"}]},{"given":"Zeyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,CDL,Beijing,China"}]},{"given":"Zitao","family":"Mo","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,CDL,Beijing,China"}]},{"given":"Xingting","family":"Yao","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,CDL,Beijing,China"}]},{"given":"Jian","family":"Cheng","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,CDL,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Efficient Streaming Language Models with Attention Sinks","volume-title":"International Conference on Learning Representations (ICLR)","author":"Xiao","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.222"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-023-00370-1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2023.14217"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2594291.2594321"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416591"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.155"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615220"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3637364"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10639-023-11834-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00632"},{"key":"ref15","article-title":"OPTQ: Accurate quantization for generative pre-trained transformers","volume-title":"International Conference on Learning Representations (ICLR)","author":"Frantar","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3714983.3714987"},{"key":"ref17","first-page":"10323","article-title":"Sparsegpt: Massive language models can be accurately pruned in one-shot","volume-title":"International conference on machine learning (ICML)","author":"Frantar","year":"2023"},{"key":"ref18","first-page":"21702","article-title":"Llm-pruner: On the structural pruning of large language models","author":"Ma","year":"2023","journal-title":"Neural Information Processing Systems (NeurPIS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637562"},{"key":"ref20","article-title":"EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Scissorhands: Exploiting the persistence of importance hypothesis for 11 m kv cache compression at test time","volume-title":"Neural Information Processing Systems (NeurIPS)","author":"Liu","year":"2024"},{"key":"ref22","article-title":"Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ge","year":"2024"},{"key":"ref23","article-title":"MiniLLM: Knowledge distillation of large language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Gu","year":"2024"},{"key":"ref24","first-page":"10421","article-title":"Specializing smaller language models towards multi-step reasoning","volume-title":"International conference on machine learning (ICML)","author":"Fu","year":"2023"},{"key":"ref25","article-title":"H2o: Heavyhitter oracle for efficient generative inference of large language models","author":"Zhang","year":"2024","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref26","article-title":"Compressive Transformers for Long-Range Sequence Modelling","author":"Rae","year":"2019","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","author":"Gao","year":"2021","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Calculation of prompt diphoton production cross sections at Tevatron and LHC energies","author":"Bal\u00e1zs","year":"2007","journal-title":"arXiv preprint"},{"key":"ref29","year":"2023","journal-title":"Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs"},{"key":"ref30","article-title":"The Falcon Series of Open Language Models","author":"Almazrouei","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Qwen Technical Report","author":"Bai","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","location":"Hefei, China","start":{"date-parts":[[2025,12,14]]},"end":{"date-parts":[[2025,12,18]]}},"container-title":["2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11322805\/11322871\/11323105.pdf?arnumber=11323105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:09:27Z","timestamp":1768460967000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11323105\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icpads67057.2025.11323105","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]}}}