{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T15:55:42Z","timestamp":1762876542525,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3748355.3748372","type":"proceedings-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T13:47:07Z","timestamp":1755611227000},"page":"76-83","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["eInfer: Unlocking Fine-Grained Tracing for Distributed LLM Inference with eBPF"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0303-6699","authenticated-orcid":false,"given":"Kexin","family":"Chu","sequence":"first","affiliation":[{"name":"University of Connecticut, Storrs, CT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4089-8316","authenticated-orcid":false,"given":"Jianchang","family":"Su","sequence":"additional","affiliation":[{"name":"University of Connecticut, Storrs, CT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6403-2161","authenticated-orcid":false,"given":"Yifan","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Connecticut, Storrs, CT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8528-1689","authenticated-orcid":false,"given":"Chenxingyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8011-5868","authenticated-orcid":false,"given":"Yiwei","family":"Yang","sequence":"additional","affiliation":[{"name":"UC Santa Cruz, Santa Cruz, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3193-4356","authenticated-orcid":false,"given":"Yusheng","family":"Zheng","sequence":"additional","affiliation":[{"name":"UC Santa Cruz, Santa Cruz, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2615-0525","authenticated-orcid":false,"given":"Shengkai","family":"Lin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8395-5109","authenticated-orcid":false,"given":"Shizhen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9512-4192","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Connecticut, Storrs, CT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n.d.]. https:\/\/docs.pytorch.org\/tutorials\/recipes\/recipes\/profiler_recipe.html."},{"key":"e_1_3_2_1_2_1","unstructured":"[n.d.]. https:\/\/www.tensorflow.org\/tensorboard."},{"key":"e_1_3_2_1_3_1","unstructured":"[n.d.]. https:\/\/www.sage.com\/en-us\/sage-ai\/."},{"key":"e_1_3_2_1_4_1","volume-title":"Etalon: Holistic Performance Evaluation Framework for LLM Inference Systems. arXiv preprint arXiv:2407.07000","author":"Agrawal Amey","year":"2024","unstructured":"Amey Agrawal, Anmol Agarwal, Nitin Kedia, Jayashree Mohan, Souvik Kundu, Nipun Kwatra, Ramachandran Ramjee, and Alexey Tumanov. 2024. Etalon: Holistic Performance Evaluation Framework for LLM Inference Systems. arXiv preprint arXiv:2407.07000 (2024)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS56928.2023.10154357"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00080"},{"volume-title":"BPF performance tools","author":"Gregg Brendan","key":"e_1_3_2_1_7_1","unstructured":"Brendan Gregg. 2019. BPF performance tools. Addison-Wesley Professional."},{"key":"e_1_3_2_1_8_1","volume-title":"CFP: Low-overhead Profiling-based Intra-operator Parallelism Generation by Preserving Communication-Free Structures. arXiv preprint arXiv:2504.00598","author":"Hu Weifang","year":"2025","unstructured":"Weifang Hu, Xuanhua Shi, Chang Wu, Yunkai Zhang, Xuan Peng, Jiaqi Zhai, Hai Jin, Yongluan Zhou, and Xuehai Qian. 2025. CFP: Low-overhead Profiling-based Intra-operator Parallelism Generation by Preserving Communication-Free Structures. arXiv preprint arXiv:2504.00598 (2025)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP61157.2025.00134"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid54584.2022.00128"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29200"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS56928.2023.10154433"},{"key":"e_1_3_2_1_13_1","volume-title":"Llm inference serving: Survey of recent advances and opportunities. arXiv preprint arXiv:2407.12391","author":"Li Baolin","year":"2024","unstructured":"Baolin Li, Yankai Jiang, Vijay Gadepally, and Devesh Tiwari. 2024. Llm inference serving: Survey of recent advances and opportunities. arXiv preprint arXiv:2407.12391 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"RT-LM: Uncertainty-Aware Resource Management for Real-Time Inference of Language Models. In 2023 IEEE Real-Time Systems Symposium (RTSS). IEEE, 158--171","author":"Li Yufei","year":"2023","unstructured":"Yufei Li, Zexin Li, Wei Yang, and Cong Liu. 2023. RT-LM: Uncertainty-Aware Resource Management for Real-Time Inference of Language Models. In 2023 IEEE Real-Time Systems Symposium (RTSS). IEEE, 158--171."},{"key":"e_1_3_2_1_15_1","volume-title":"Alan Zhu, Lijie Yang, Xiaoxiang Shi, et al.","author":"Miao Xupeng","year":"2023","unstructured":"Xupeng Miao, Gabriele Oliaro, Zhihao Zhang, Xinhao Cheng, Zeyu Wang, Zhengxin Zhang, Rae Ying Yee Wong, Alan Zhu, Lijie Yang, Xiaoxiang Shi, et al. 2023. Specinfer: Accelerating generative large language model serving with tree-based speculative inference and verification. arXiv preprint arXiv:2305.09781 (2023)."},{"key":"e_1_3_2_1_16_1","unstructured":"NVDIA. [n. d.]. https:\/\/github.com\/NVIDIA\/FasterTransformer."},{"key":"e_1_3_2_1_17_1","unstructured":"NVIDIA. 2023. CUPTI. https:\/\/developer.nvidia.com\/cupti."},{"key":"e_1_3_2_1_18_1","unstructured":"Mateusz Piotrowski. [n. d.]. Benchmarking Performance Overhead of DTrace on FreeBSD and eBPF on Linux. ([n. d.])."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/NFV-SDN61811.2024.10807468"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604823"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning. 44687--44711","author":"Shen Maohao","year":"2024","unstructured":"Maohao Shen, Subhro Das, Kristjan Greenewald, Prasanna Sattigeri, Gregory Wornell, and Soumya Ghosh. 2024. Thermometer: towards universal calibration for large language models. In Proceedings of the 41st International Conference on Machine Learning. 44687--44711."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3613213"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00104"},{"volume-title":"Mastering Distributed Tracing: Analyzing performance in microservices and complex systems","author":"Shkuro Yuri","key":"e_1_3_2_1_24_1","unstructured":"Yuri Shkuro. 2019. Mastering Distributed Tracing: Analyzing performance in microservices and complex systems. Packt Publishing Ltd."},{"key":"e_1_3_2_1_25_1","volume-title":"Mike Burrows, Pat Stephenson, Manoj Plakal, Donald Beaver, Saul Jaspan, and Chandan Shanbhag.","author":"Sigelman Benjamin H","year":"2010","unstructured":"Benjamin H Sigelman, Luiz Andr\u00e9 Barroso, Mike Burrows, Pat Stephenson, Manoj Plakal, Donald Beaver, Saul Jaspan, and Chandan Shanbhag. 2010. Dapper, a large-scale distributed systems tracing infrastructure. (2010)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716025"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00102"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICS64339.2024.00022"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CloudIntelligence52565.2021.00014"},{"key":"e_1_3_2_1_30_1","volume-title":"Fast distributed inference serving for large language models. arXiv preprint arXiv:2305.05920","author":"Wu Bingyang","year":"2023","unstructured":"Bingyang Wu, Yinmin Zhong, Zili Zhang, Shengyu Liu, Fangyue Liu, Yuanhang Sun, Gang Huang, Xuanzhe Liu, and Xin Jin. 2023. Fast distributed inference serving for large language models. arXiv preprint arXiv:2305.05920 (2023)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696094"},{"key":"e_1_3_2_1_32_1","volume-title":"ZeroTracer: Inband eBPF-based Trace Generator with Zero Instrumentation for Microservice Systems","author":"Yang Wanqi","year":"2025","unstructured":"Wanqi Yang, Pengfei Chen, Kai Liu, and Huxing Zhang. 2025. ZeroTracer: Inband eBPF-based Trace Generator with Zero Instrumentation for Microservice Systems. IEEE Transactions on Parallel and Distributed Systems (2025)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3723851.3726984"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00151"},{"key":"e_1_3_2_1_35_1","volume-title":"bpftime: userspace eBPF Runtime for Uprobe, Syscall and Kernel-User Interactions. arXiv preprint arXiv:2311.07923","author":"Zheng Yusheng","year":"2023","unstructured":"Yusheng Zheng, Tong Yu, Yiwei Yang, Yanpeng Hu, Xiaozheng Lai, and Andrew Quinn. 2023. bpftime: userspace eBPF Runtime for Uprobe, Syscall and Kernel-User Interactions. arXiv preprint arXiv:2311.07923 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Zhou Yang","year":"2023","unstructured":"Yang Zhou, Zezhou Wang, Sowmya Dharanipragada, and Minlan Yu. 2023. Electrode: Accelerating Distributed Protocols with {eBPF}. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 1391--1407."}],"event":{"name":"SIGCOMM '25: ACM SIGCOMM 2025 Conference","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"],"location":"Coimbra Portugal","acronym":"SIGCOMM '25"},"container-title":["Proceedings of the 3rd Workshop on eBPF and Kernel Extensions"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3748355.3748372","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T14:11:19Z","timestamp":1760019079000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3748355.3748372"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":36,"alternative-id":["10.1145\/3748355.3748372","10.1145\/3748355"],"URL":"https:\/\/doi.org\/10.1145\/3748355.3748372","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]},"assertion":[{"value":"2025-09-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}