{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T15:24:22Z","timestamp":1787671462850,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,1,28]]},"DOI":"10.1145\/3774934.3786413","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T15:25:57Z","timestamp":1769613957000},"page":"509-521","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Laser: Unlocking Layer-Level Scheduling for Efficient Multi-SLO LLM Serving"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1076-7284","authenticated-orcid":false,"given":"Jianxiong","family":"Liao","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2307-6047","authenticated-orcid":false,"given":"Quanxing","family":"Dong","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4008-8813","authenticated-orcid":false,"given":"Yunkai","family":"Liang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0987-9344","authenticated-orcid":false,"given":"Zhi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9943-6020","authenticated-orcid":false,"given":"Xu","family":"Chen","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,1,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2023. ShareGPT. https:\/\/sharegpt.com\/"},{"key":"e_1_3_2_1_2_1","unstructured":"2025. LangChain Summarize Text. https:\/\/python.langchain.com\/docs\/tutorials\/summarization\/"},{"key":"e_1_3_2_1_3_1","unstructured":"2025. NVIDIA Dynamo Platform. https:\/\/www.nvidia.com\/en-us\/ai\/dynamo\/"},{"key":"e_1_3_2_1_4_1","unstructured":"2025. Qwen FinAgent. https:\/\/www.tongyi.com\/discover?type=FindAgent"},{"key":"e_1_3_2_1_5_1","unstructured":"2025. Ray. https:\/\/docs.ray.io\/en\/latest\/index.html"},{"key":"e_1_3_2_1_6_1","unstructured":"Amey Agrawal Nitin Kedia Ashish Panwar Jayashree Mohan Nipun Kwatra Bhargav S Gulavani Alexey Tumanov and Ramachandran Ramjee. 2024. Taming throughput-latency tradeoff in llm inference with sarathi-serve. arXiv preprint arXiv:2403.02310."},{"key":"e_1_3_2_1_7_1","unstructured":"Ebtesam Almazrouei Hamza Alobeidli Abdulaziz Alshamsi Alessandro Cappelli Ruxandra Cojocaru Merouane Debbah Etienne Goffinet Daniel Heslow Julien Launay Quentin Malartic Badreddine Noune Baptiste Pannier and Guilherme Penedo. 2023. Falcon-40B: an open large language model with state-of-the-art performance."},{"key":"e_1_3_2_1_8_1","volume-title":"Longbench: A bilingual, multitask benchmark for long context understanding. arXiv preprint arXiv:2308.14508.","author":"Bai Yushi","year":"2023","unstructured":"Yushi Bai, Xin Lv, Jiajie Zhang, Hongchang Lyu, Jiankai Tang, Zhidian Huang, Zhengxiao Du, Xiao Liu, Aohan Zeng, Lei Hou, et al. 2023. Longbench: A bilingual, multitask benchmark for long context understanding. arXiv preprint arXiv:2308.14508."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jml.2019.104047"},{"key":"e_1_3_2_1_10_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","unstructured":"Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde De Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374."},{"key":"e_1_3_2_1_11_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","unstructured":"Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde De Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374."},{"key":"e_1_3_2_1_12_1","unstructured":"Siyuan Chen Zhipeng Jia Samira Khan Arvind Krishnamurthy and Phillip B Gibbons. 2025. SLOs-Serve: Optimized Serving of Multi-SLO LLMs. arXiv preprint arXiv:2504.08784."},{"key":"e_1_3_2_1_13_1","unstructured":"Shiyang Chen Rain Jiang Dezhi Yu Jinlai Xu Mengyuan Chao Fanlong Meng Chenyu Jiang Wei Xu and Hang Liu. 2024. KVDirect: Distributed Disaggregated LLM Inference. arXiv preprint arXiv:2501.14743."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714930"},{"key":"e_1_3_2_1_15_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv e-prints arXiv\u20132407."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3730999"},{"key":"e_1_3_2_1_17_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_19_1","volume-title":"SOLA: Optimizing SLO Attainment for Large Language Model Serving with State-Aware Scheduling. In Eighth Conference on Machine Learning and Systems.","author":"Hong Ke","unstructured":"Ke Hong, Xiuhong Li, Lufang Chen, Qiuli Mao, Guohao Dai, Xuefei Ning, Shengen Yan, Yun Liang, and Yu Wang. [n. d.]. SOLA: Optimizing SLO Attainment for Large Language Model Serving with State-Aware Scheduling. In Eighth Conference on Machine Learning and Systems."},{"key":"e_1_3_2_1_20_1","volume-title":"Interference: Disaggregate LLM Inference for Mixed Downstream Workloads. arXiv preprint arXiv:2401.11181.","author":"Hu Cunchen","year":"2024","unstructured":"Cunchen Hu, Heyang Huang, Liangliang Xu, Xusheng Chen, Jiang Xu, Shuang Chen, Hao Feng, Chenxi Wang, Sa Wang, Yungang Bao, et al. 2024. Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads. arXiv preprint arXiv:2401.11181."},{"key":"e_1_3_2_1_21_1","unstructured":"Jinqi Huang Yi Xiong Xuebing Yu Wenjie Huang Entong Li Li Zeng and Xin Chen. 2025. SLO-Aware Scheduling for Large Language Model Inferences. arXiv preprint arXiv:2504.14966."},{"key":"e_1_3_2_1_22_1","unstructured":"Binyuan Hui Jian Yang Zeyu Cui Jiaxi Yang Dayiheng Liu Lei Zhang Tianyu Liu Jiajun Zhang Bowen Yu Keming Lu et al. 2024. Qwen2. 5-coder technical report. arXiv preprint arXiv:2409.12186."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_24_1","unstructured":"Zikun Li Zhuofu Chen Remi Delacourt Gabriele Oliaro Zeyu Wang Qinghan Chen Shuhuai Lin April Yang Zhihao Zhang Zhuoming Chen et al. 2025. AdaServe: SLO-Customized LLM Serving with Fine-Grained Speculative Decoding. arXiv preprint arXiv:2501.12162."},{"key":"e_1_3_2_1_25_1","unstructured":"Yunkai Liang Zhangyu Chen Pengfei Zuo Zhi Zhou Xu Chen and Zhou Yu. 2025. Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation. arXiv preprint arXiv:2503.20552."},{"key":"e_1_3_2_1_26_1","volume-title":"Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism. arXiv preprint arXiv:2509.08309.","author":"Mo Zizhao","year":"2025","unstructured":"Zizhao Mo, Jianxiong Liao, Huanle Xu, Zhi Zhou, and Chengzhong Xu. 2025. Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism. arXiv preprint arXiv:2509.08309."},{"key":"e_1_3_2_1_27_1","unstructured":"Bowen Pang Kai Li and Feifan Wang. 2025. Optimizing LLM Inference Throughput via Memory-aware and SLA-constrained Dynamic Batching. arXiv preprint arXiv:2503.05248."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"e_1_3_2_1_29_1","unstructured":"Archit Patke Dhemath Reddy Saurabh Jha Chandra Narayanaswami Zbigniew Kalbarczyk and Ravishankar Iyer. 2025. Hierarchical Autoscaling for Large Language Model Serving with Chiron. arXiv preprint arXiv:2501.08090."},{"key":"e_1_3_2_1_30_1","volume-title":"Mooncake: A kvcache-centric disaggregated architecture for llm serving. arXiv preprint arXiv:2407.00079.","author":"Qin Ruoyu","year":"2024","unstructured":"Ruoyu Qin, Zheming Li, Weiran He, Mingxing Zhang, Yongwei Wu, Weimin Zheng, and Xinran Xu. 2024. Mooncake: A kvcache-centric disaggregated architecture for llm serving. arXiv preprint arXiv:2407.00079."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_1_32_1","unstructured":"Gursimran Singh Xinglu Wang Ivan Hu Timothy Yu Linzi Xing Wei Jiang Zhefeng Wang Xiaolong Bai Yi Li Ying Xiong et al. 2024. Efficiently serving large multimedia models using EPD Disaggregation. arXiv preprint arXiv:2501.05460."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00102"},{"key":"e_1_3_2_1_34_1","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Sun Biao","year":"2024","unstructured":"Biao Sun, Ziming Huang, Hanyu Zhao, Wencong Xiao, Xinyi Zhang, Yong Li, and Wei Lin. 2024. Llumnix: Dynamic scheduling for large language model serving. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). 173\u2013191."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_1_36_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971."},{"key":"e_1_3_2_1_37_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, 30 (2017)."},{"key":"e_1_3_2_1_38_1","volume-title":"Openchat: Advancing open-source language models with mixed-quality data. arXiv preprint arXiv:2309.11235.","author":"Wang Guan","year":"2023","unstructured":"Guan Wang, Sijie Cheng, Xianyuan Zhan, Xiangang Li, Sen Song, and Yang Liu. 2023. Openchat: Advancing open-source language models with mixed-quality data. arXiv preprint arXiv:2309.11235."},{"key":"e_1_3_2_1_39_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35 (2022), 24824\u201324837."},{"key":"e_1_3_2_1_40_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388."},{"key":"e_1_3_2_1_41_1","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yu Gyeong-In","year":"2022","unstructured":"Gyeong-In Yu, Joo Seong Jeong, Geon-Woo Kim, Soojeong Kim, and Byung-Gon Chun. 2022. Orca: A distributed serving system for $Transformer-Based$ generative models. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). 521\u2013538."},{"key":"e_1_3_2_1_42_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068."},{"key":"e_1_3_2_1_43_1","unstructured":"Yinmin Zhong Shengyu Liu Junda Chen Jianbo Hu Yibo Zhu Xuanzhe Liu Xin Jin and Hao Zhang. 2024. DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving. arXiv preprint arXiv:2401.09670."}],"event":{"name":"PPoPP '26: 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","location":"Sydney NSW Australia","acronym":"PPoPP '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGPLAN ACM Special Interest Group on Programming Languages"]},"container-title":["Proceedings of the 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774934.3786413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T15:29:04Z","timestamp":1769614144000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774934.3786413"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,28]]},"references-count":43,"alternative-id":["10.1145\/3774934.3786413","10.1145\/3774934"],"URL":"https:\/\/doi.org\/10.1145\/3774934.3786413","relation":{},"subject":[],"published":{"date-parts":[[2026,1,28]]},"assertion":[{"value":"2026-01-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}