{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T20:34:53Z","timestamp":1783715693615,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62402025"],"award-info":[{"award-number":["62402025"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,7]]},"DOI":"10.1145\/3735358.3735372","type":"proceedings-article","created":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T23:08:27Z","timestamp":1752793707000},"page":"157-163","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Mnemosyne: Lightweight and Fast Error Recovery for LLM Training in a Just-In-Time Manner"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5975-5718","authenticated-orcid":false,"given":"Jinyi","family":"Xia","sequence":"first","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5274-5512","authenticated-orcid":false,"given":"Menghao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8999-6468","authenticated-orcid":false,"given":"Jiaxun","family":"Huang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5443-2066","authenticated-orcid":false,"given":"Yuezheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1487-2419","authenticated-orcid":false,"given":"Xiaohe","family":"Hu","sequence":"additional","affiliation":[{"name":"Infrawaves, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8865-3055","authenticated-orcid":false,"given":"Xudong","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3473-9703","authenticated-orcid":false,"given":"Chunming","family":"Hu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,6]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00089"},{"key":"e_1_3_3_1_3_2","unstructured":"Anonymous authors. 2025. Mnemosyne. https:\/\/anonymous.4open.science\/r\/Mnemosyne"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441620"},{"key":"e_1_3_3_1_5_2","unstructured":"Aakanksha Chowdhery Sharan Narang Jacob Devlin Maarten Bosma Gaurav Mishra Adam Roberts Paul Barham Hyung\u00a0Won Chung Charles Sutton Sebastian Gehrmann et\u00a0al. 2023. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research 24 240 (2023) 1\u2013113."},{"key":"e_1_3_3_1_6_2","unstructured":"CRIU. 2024. Checkpoint\/Restore in Userspace. https:\/\/criu.org\/Main_Page"},{"key":"e_1_3_3_1_7_2","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers)","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171\u20134186."},{"key":"e_1_3_3_1_8_2","first-page":"929","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Eisenman Assaf","year":"2022","unstructured":"Assaf Eisenman, Kiran\u00a0Kumar Matam, Steven Ingram, Dheevatsa Mudigere, Raghuraman Krishnamoorthi, Krishnakumar Nair, Misha Smelyanskiy, and Murali Annavaram. 2022. Check-N-Run: A checkpointing system for training deep learning recommendation models. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). 929\u2013943."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472904"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695960"},{"key":"e_1_3_3_1_11_2","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et\u00a0al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.12948 (2025)."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3650085"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.5555\/3691825.3691864"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613152"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507778"},{"key":"e_1_3_3_1_16_2","first-page":"745","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Jiang Ziheng","year":"2024","unstructured":"Ziheng Jiang, Haibin Lin, Yinmin Zhong, Qi Huang, Yangrui Chen, Zhi Zhang, Yanghua Peng, Xiang Li, Cong Xie, Shibiao Nong, et\u00a0al. 2024. MegaScale: Scaling large language model training to more than 10,000 GPUs. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 745\u2013760."},{"key":"e_1_3_3_1_17_2","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom\u00a0B Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2001.08361 (2020)."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3672198.3673799"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672249"},{"key":"e_1_3_3_1_20_2","unstructured":"Kiwan Maeng Shivam Bharuka Isabel Gao Mark Jeffrey Vikram Saraph Bor-Yiing Su Caroline Trippel Jiyan Yang Mike Rabbat Brandon Lucia et\u00a0al. 2021. Understanding and improving failure tolerant training for deep learning recommendation with partial recovery. Proceedings of Machine Learning and Systems 3 (2021) 637\u2013651."},{"key":"e_1_3_3_1_21_2","unstructured":"Linux manual page. 2024. ld.so. https:\/\/man7.org\/linux\/man-pages\/man8\/ld.so.8.html"},{"key":"e_1_3_3_1_22_2","unstructured":"Meta Platforms Inc.2023. Gloo: Collective Communications Library. https:\/\/github.com\/facebookincubator\/gloo"},{"key":"e_1_3_3_1_23_2","first-page":"203","volume-title":"19th USENIX Conference on File and Storage Technologies (FAST 21)","author":"Mohan Jayashree","year":"2021","unstructured":"Jayashree Mohan, Amar Phanishayee, and Vijay Chidambaram. 2021. CheckFreq: Frequent, Fine-Grained DNN Checkpointing. In 19th USENIX Conference on File and Storage Technologies (FAST 21). 203\u2013216."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid49817.2020.00-76"},{"key":"e_1_3_3_1_25_2","unstructured":"NVIDIA Corporation. 2023. NVIDIA Collective Communications Library (NCCL). https:\/\/developer.nvidia.com\/nccl"},{"key":"e_1_3_3_1_26_2","unstructured":"OpenAI. 2024. Learning to reason with LLMs. https:\/\/openai.com\/index\/learning-to-reason-with-llms\/."},{"key":"e_1_3_3_1_27_2","unstructured":"Alec Radford. 2018. Improving language understanding with unsupervised learning. OpenAI Res (2018)."},{"key":"e_1_3_3_1_28_2","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et\u00a0al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_3_1_29_2","unstructured":"Colin Raffel Noam Shazeer Adam Roberts Katherine Lee Sharan Narang Michael Matena Yanqi Zhou Wei Li and Peter\u00a0J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research 21 140 (2020) 1\u201367."},{"key":"e_1_3_3_1_30_2","series-title":"(SC \u201920)","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Rajbhandari Samyam","year":"2020","unstructured":"Samyam Rajbhandari, Jeff Rasley, Olatunji Ruwase, and Yuxiong He. 2020. ZeRO: memory optimizations toward training trillion parameter models. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (Atlanta, Georgia) (SC \u201920). IEEE Press, Article 20, 16\u00a0pages."},{"key":"e_1_3_3_1_31_2","first-page":"593","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Shah Aashaka","year":"2023","unstructured":"Aashaka Shah, Vijay Chidambaram, Meghan Cowan, Saeed Maleki, Madan Musuvathi, Todd Mytkowicz, Jacob Nelson, Olli Saarikivi, and Rachee Singh. 2023. TACCL: Guiding collective algorithm synthesis using communication sketches. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 593\u2013612."},{"key":"e_1_3_3_1_32_2","unstructured":"Dharma Shukla Muthian Sivathanu Srinidhi Viswanatha Bhargav Gulavani Rimma Nehme Amey Agrawal Chen Chen Nipun Kwatra Ramachandran Ramjee Pankaj Sharma et\u00a0al. 2022. Singularity: Planet-scale preemptive and elastic scheduling of AI workloads. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2202.07848 (2022)."},{"key":"e_1_3_3_1_33_2","first-page":"497","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Thorpe John","year":"2023","unstructured":"John Thorpe, Pengzhan Zhao, Jonathan Eyolfson, Yifan Qiao, Zhihao Jia, Minjia Zhang, Ravi Netravali, and Guoqing\u00a0Harry Xu. 2023. Bamboo: Making preemptible instances resilient for affordable training of large { DNNs}. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 497\u2013513."},{"key":"e_1_3_3_1_34_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_1_35_2","unstructured":"Guanhua Wang Shivaram Venkataraman Amar Phanishayee Nikhil Devanur Jorgen Thelin and Ion Stoica. 2020. Blink: Fast and generic collectives for distributed ml. Proceedings of Machine Learning and Systems 2 (2020) 172\u2013186."},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613145"},{"key":"e_1_3_3_1_37_2","unstructured":"Susan Zhang Stephen Roller Naman Goyal Mikel Artetxe Moya Chen Shuohui Chen Christopher Dewan Mona Diab Xian Li Xi\u00a0Victoria Lin et\u00a0al. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.01068 (2022)."},{"key":"e_1_3_3_1_38_2","unstructured":"Wayne\u00a0Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et\u00a0al. 2023. A survey of large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.18223 1 2 (2023)."}],"event":{"name":"APNET 2025: The 9th Asia-Pacific Workshop on Networking","location":"Shang Hai China","acronym":"APNET 2025"},"container-title":["Proceedings of the 9th Asia-Pacific Workshop on Networking"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3735358.3735372","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T05:09:45Z","timestamp":1753160985000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3735358.3735372"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,6]]},"references-count":37,"alternative-id":["10.1145\/3735358.3735372","10.1145\/3735358"],"URL":"https:\/\/doi.org\/10.1145\/3735358.3735372","relation":{},"subject":[],"published":{"date-parts":[[2025,8,6]]},"assertion":[{"value":"2025-08-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}