{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T22:57:12Z","timestamp":1768517832939,"version":"3.49.0"},"reference-count":38,"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\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U24A20235,62032003"],"award-info":[{"award-number":["U24A20235,62032003"]}],"id":[{"id":"10.13039\/501100001809","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\/icpads67057.2025.11323033","type":"proceedings-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:36:54Z","timestamp":1768423014000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Dispenser: Hierarchical KV Cache Management for Efficient LLM Generative Inference"],"prefix":"10.1109","author":[{"given":"Beiquan","family":"Cao","sequence":"first","affiliation":[{"name":"School of EECS, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaigui","family":"Bian","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guojie","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joongheon","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea University,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"YaRN: Efficient context window extension of large language models","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Peng","year":"2024"},{"key":"ref2","article-title":"LongRoPE: Extending LLM context window beyond 2 million tokens","volume-title":"Proc. International Conference on Machine Learning (ICML)","author":"Ding","year":"2024"},{"key":"ref3","first-page":"34661","article-title":"H2O: Heavy-hitter oracle for efficient generative inference of large language models","volume":"36","author":"Zhang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","article-title":"Model tells you what to discard: Adaptive KV cache compression for LLMs","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Ge","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref6","article-title":"How Long Can Context Length of Open-Source LLMs truly Promise?","volume-title":"NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following","author":"Li","year":"2023"},{"key":"ref7","volume-title":"Introducing the next generation of Claude","year":"2025"},{"key":"ref8","volume-title":"Introducing GPT-4o: our fastest and most affordable flagship model","year":"2025"},{"key":"ref9","article-title":"Efficient streaming language models with attention sinks","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Xiao","year":"2024"},{"key":"ref10","first-page":"114","article-title":"Keyformer: KV cache reduction through key tokens selection for efficient generative inference","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Adnan","year":"2024"},{"key":"ref11","article-title":"On the efficacy of eviction policy for keyvalue constrained generative language model inference","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.acl-long.428","article-title":"NACL: A general and effective KV cache eviction framework for LLMs at inference time","volume-title":"Proc. of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Chen","year":"2024"},{"key":"ref13","article-title":"QUEST: Query-Aware Sparsity for Efficient Long-Context LLM Inference","volume-title":"Proc. International Conference on Machine Learning (ICML)","author":"Tang","year":"2024"},{"key":"ref14","article-title":"ArKVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Chen","year":"2024"},{"key":"ref15","article-title":"InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Lee","year":"2024"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2025.acl-long.1568","article-title":"Squeezed Attention: Accelerating Long Context Length LLM Inference","volume-title":"Proc. of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025 (Long Papers)","author":"Hooper"},{"key":"ref17","volume-title":"ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression","author":"Liu","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44503-X_27"},{"key":"ref19","first-page":"17402","article-title":"Outlier suppression: Pushing the limit of low-bit transformer language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","first-page":"30318","article-title":"GPT3.int8(): 8-bit Matrix Multiplication for Transformers at Scale","volume":"35","author":"Dettmers","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D18-1259","article-title":"HotpotQA: A dataset for diverse, explainable multi-hop question answering","volume-title":"Proc. of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Yang","year":"2018"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.coling-main.580","article-title":"Constructing a multi-hop QA dataset for comprehensive evaluation of reasoning steps","volume-title":"Proc. of the 28th International Conference on Computational Linguistics (COLING)","author":"Ho","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00475"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00023"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2021.naacl-main.365","article-title":"A dataset of information-seeking questions and answers anchored in research papers","volume-title":"Proc. of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)","author":"Dasigi","year":"2021"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.acl-long.172","article-title":"LongBench: A bilingual, multitask benchmark for long context understanding","volume-title":"Proc. of the 2024 Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Bai","year":"2024"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2021.naacl-main.112","article-title":"Efficient attentions for long document summarization","volume-title":"Proc. of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)","author":"Huang","year":"2021"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1102","article-title":"Multi-News: A large-scale multi-document summarization dataset and abstractive hierarchical model","volume-title":"Proc. of the 57th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Fabbri","year":"2019"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2021.naacl-main.472","article-title":"QMSum: A new benchmark for query-based multi-domain meeting summarization","volume-title":"Proc. of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)","author":"Zhong","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/1072228.1072378"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P17-1147","article-title":"TriviaQA: A large scale distantly supervised challenge dataset for reading comprehension","volume-title":"Proc. of the 55th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Joshi","year":"2017"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D19-5409","article-title":"SAMSum Corpus: A human-annotated dialogue dataset for abstractive summarization","volume-title":"Proc. of the 3rd Workshop on Neural Generation and Translation (W-NMT) at ACL","author":"Gliwa","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.11.139"},{"key":"ref34","first-page":"3753","article-title":"Counting-stars: A multievidence, position-aware, and scalable benchmark for evaluating longcontext large language models","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics","author":"Song","year":"2025"},{"key":"ref35","article-title":"InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory","volume-title":"Proc. of the 38th Conference on Neural Information Processing Systems (NeurIPS)","author":"Xiao","year":"2024"},{"key":"ref36","article-title":"SparQ Attention: Bandwidth-Efficient LLM Inference","volume-title":"Proc. of MEFoMo 2024 (OpenReview)","author":"Ribar"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3725338"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"}],"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\/11323033.pdf?arnumber=11323033","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:09:21Z","timestamp":1768460961000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11323033\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icpads67057.2025.11323033","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]}}}