{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T16:55:27Z","timestamp":1787936127417,"version":"build-2784847793"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T00:00:00Z","timestamp":1718755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T00:00:00Z","timestamp":1718755200000},"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":[[2024,6,19]]},"DOI":"10.1109\/iwqos61813.2024.10682957","type":"proceedings-article","created":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T13:41:00Z","timestamp":1727358060000},"page":"1-10","source":"Crossref","is-referenced-by-count":14,"title":["SCALM: Towards Semantic Caching for Automated Chat Services with Large Language Models"],"prefix":"10.1109","author":[{"given":"Jiaxing","family":"Li","sequence":"first","affiliation":[{"name":"Simon Fraser University,School of Computing Science,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi","family":"Xu","sequence":"additional","affiliation":[{"name":"Simon Fraser University,School of Computing Science,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Mississippi,Department of Computer and Information Science,Mississippi,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isaac M","family":"von Riedemann","sequence":"additional","affiliation":[{"name":"Simon Fraser University,School of Computing Science,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Jiangxing Intelligence Inc.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangchuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Simon Fraser University,School of Computing Science,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"ChatGPT Users","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1000"},{"key":"ref3","article-title":"On optimal caching and model multiplexing for large model inference","author":"Zhu","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.nlposs-1.24"},{"key":"ref5","article-title":"Lmsys-chat-1m: A large-scale real-world llm conversation dataset","author":"Zheng","year":"2023"},{"key":"ref6","article-title":"Moss: Training conversational language models from synthetic data","author":"Sun","year":"2023"},{"key":"ref7","author":"Wessels","year":"2001","journal-title":"Web Caching"},{"key":"ref8","article-title":"2q: A low overhead high performance buffer management replacement algorithm","volume-title":"Proc. of the 20th International Conference on Very Large Data Bases (VLDB)","author":"Johnson"},{"key":"ref9","article-title":"The multi-queue replacement algorithm for second level buffer caches","volume-title":"Proc. of the 10th Usenix Annual Technical Conference (ATC)","author":"Zhou"},{"key":"ref10","article-title":"Arc: a self-tuning, low overhead replacement cache","volume-title":"Proc. of the 2nd USENIX conference on File and storage technologies (FAST)","author":"Megiddo"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/511334.511340"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2001.970573"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241563"},{"key":"ref14","article-title":"Learning relaxed belady for content distribution network caching","volume-title":"Proc. of the 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI)","author":"Song"},{"key":"ref15","article-title":"An imitation learning approach for cache replacement","volume-title":"Proc. of the 37th International Conference on Machine Learning (ICML)","author":"Liu"},{"key":"ref16","article-title":"Halp: Heuristic aided learned preference eviction policy for youtube content delivery network","volume-title":"Proc. of the 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI)","author":"Song"},{"key":"ref17","article-title":"Sparks of gpts in edge intelligence for metaverse: Caching and inference for mobile aigc services","author":"Xu","year":"2023"},{"key":"ref18","article-title":"H2o: Heavy-hitter oracle for efficient generative inference of large language models","author":"Zhang","year":"2023"},{"key":"ref19","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. of the 40th International Conference on Machine Learning (ICML)","author":"Xiao"},{"key":"ref20","article-title":"Lut-gemm: Quantized matrix multiplication based on luts for efficient inference in large-scale generative language models","volume-title":"Proc. of the 12th International Conference on Learning Representations (ICLR)","author":"Park"},{"key":"ref21","article-title":"Llm-pruner: On the structural pruning of large language models","volume-title":"Proc. of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Ma"},{"key":"ref22","article-title":"Frugalgpt: How to use large language models while reducing cost and improving performance","author":"Chen","year":"2023"},{"key":"ref23","article-title":"Big little transformer decoder","author":"Kim","year":"2023"},{"key":"ref24","article-title":"ShareGPT","year":"2024"},{"key":"ref25","article-title":"Openassistant conversations - democratizing large language model alignment","volume-title":"Proc. of the 37th Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"K\u00f6pf"},{"key":"ref26","article-title":"OpenAI\u2019s embedding models","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3068335"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2007.03.016"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/widm.53"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1147\/sj.52.0078"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref32","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref34","article-title":"Video generation models as world simulators","year":"2023"},{"key":"ref35","article-title":"Text-to-video: The task, challenges and the current state","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10279564"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672268"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2018.2837040"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3047307"}],"event":{"name":"2024 IEEE\/ACM 32nd International Symposium on Quality of Service (IWQoS)","location":"Guangzhou, China","start":{"date-parts":[[2024,6,19]]},"end":{"date-parts":[[2024,6,21]]}},"container-title":["2024 IEEE\/ACM 32nd International Symposium on Quality of Service (IWQoS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10682818\/10682608\/10682957.pdf?arnumber=10682957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T00:41:28Z","timestamp":1727397688000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10682957\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,19]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/iwqos61813.2024.10682957","relation":{},"subject":[],"published":{"date-parts":[[2024,6,19]]}}}