{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:16:24Z","timestamp":1777058184177,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819628292","type":"print"},{"value":"9789819628308","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-2830-8_2","type":"book-chapter","created":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T19:21:47Z","timestamp":1743362507000},"page":"16-27","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["AsymFB: Accelerating LLM Training Through Asymmetric Model Parallelism"],"prefix":"10.1007","author":[{"given":"Jiawei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"En","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leping","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangming","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ninghui","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,29]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Chen, C., et al.: Centauri: enabling efficient scheduling for communication-computation overlap in large model training via communication partitioning. In: Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, vol. 3, pp. 178\u2013191 (2024)","DOI":"10.1145\/3620666.3651379"},{"key":"2_CR2","unstructured":"Chen, T., Xu, B., Zhang, C., Guestrin, C.: Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174 (2016)"},{"issue":"7","key":"2_CR3","first-page":"1802","volume":"32","author":"Y Cheng","year":"2020","unstructured":"Cheng, Y., et al.: Accelerating end-to-end deep learning workflow with codesign of data preprocessing and scheduling. IEEE Trans. Parallel Distrib. Syst. 32(7), 1802\u20131814 (2020)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"240","key":"2_CR4","first-page":"1","volume":"24","author":"A Chowdhery","year":"2023","unstructured":"Chowdhery, A., et al.: PaLM: scaling language modeling with pathways. J. Mach. Learn. Res. 24(240), 1\u2013113 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Fan, S., et\u00a0al.: DAPPLE: a pipelined data parallel approach for training large models. In: Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 431\u2013445 (2021)","DOI":"10.1145\/3437801.3441593"},{"key":"2_CR6","unstructured":"He, C., Li, S., Soltanolkotabi, M., Avestimehr, S.: PipeTransformer: automated elastic pipelining for distributed training of transformers. arXiv preprint arXiv:2102.03161 (2021)"},{"key":"2_CR7","unstructured":"Huang, Y., et\u00a0al.: GPipe: efficient training of giant neural networks using pipeline parallelism. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"2_CR8","unstructured":"Jia, Z., Lin, S., Qi, C.R., Aiken, A.: Exploring hidden dimensions in accelerating convolutional neural networks. In: International Conference on Machine Learning, pp. 2274\u20132283. PMLR (2018)"},{"key":"2_CR9","first-page":"1","volume":"1","author":"Z Jia","year":"2019","unstructured":"Jia, Z., Zaharia, M., Aiken, A.: Beyond data and model parallelism for deep neural networks. Proc. Mach. Learn. Syst. 1, 1\u201313 (2019)","journal-title":"Proc. Mach. Learn. Syst."},{"key":"2_CR10","first-page":"341","volume":"5","author":"VA Korthikanti","year":"2023","unstructured":"Korthikanti, V.A., et al.: Reducing activation recomputation in large transformer models. Proc. Mach. Learn. Syst. 5, 341\u2013353 (2023)","journal-title":"Proc. Mach. Learn. Syst."},{"issue":"5","key":"2_CR11","doi-asserted-by":"publisher","first-page":"1432","DOI":"10.1109\/TPDS.2023.3247883","volume":"34","author":"F Li","year":"2023","unstructured":"Li, F., et al.: Fold3D: rethinking and parallelizing computational and communicational tasks in the training of large DNN models. IEEE Trans. Parallel Distrib. Syst. 34(5), 1432\u20131449 (2023)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"2_CR12","unstructured":"Li, Z., et al.: TeraPipe: token-level pipeline parallelism for training large-scale language models. In: International Conference on Machine Learning, pp. 6543\u20136552. PMLR (2021)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Narayanan, D., et al.: PipeDream: generalized pipeline parallelism for DNN training. In: Proceedings of the 27th ACM Symposium on Operating Systems Principles, pp. 1\u201315 (2019)","DOI":"10.1145\/3341301.3359646"},{"key":"2_CR14","unstructured":"Paszke, A., et\u00a0al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"2_CR15","unstructured":"Qi, P., Wan, X., Huang, G., Lin, M.: Zero bubble pipeline parallelism. arXiv preprint arXiv:2401.10241 (2023)"},{"issue":"8","key":"2_CR16","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S., Rasley, J., Ruwase, O., He, Y.: ZeRO: memory optimizations toward training trillion parameter models. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201316. IEEE (2020)","DOI":"10.1109\/SC41405.2020.00024"},{"key":"2_CR18","unstructured":"Shoeybi, M., Patwary, M., Puri, R., LeGresley, P., Casper, J., Catanzaro, B.: Megatron-LM: training multi-billion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053 (2019)"},{"key":"2_CR19","unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, L., Xu, H., Wang, Y., Li, Y., Han, Y.: PrimePar: efficient spatial-temporal tensor partitioning for large transformer model training. In: Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, vol. 3, pp. 801\u2013817 (2024)","DOI":"10.1145\/3620666.3651357"},{"key":"2_CR21","unstructured":"Xu, Y., et\u00a0al.: GSPMD: general and scalable parallelization for ML computation graphs. arXiv preprint arXiv:2105.04663 (2021)"},{"key":"2_CR22","unstructured":"Yuan, J., et\u00a0al.: OneFlow: redesign the distributed deep learning framework from scratch. arXiv preprint arXiv:2110.15032 (2021)"},{"key":"2_CR23","unstructured":"Zhang, S., et\u00a0al.: OPT: open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)"},{"key":"2_CR24","unstructured":"Zheng, L., et\u00a0al.: Alpa: automating inter-and $$\\{$$intra-operator$$\\}$$ parallelism for distributed deep learning. In: 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22), pp. 559\u2013578 (2022)"}],"container-title":["Lecture Notes in Computer Science","Network and Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2830-8_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T08:41:47Z","timestamp":1757148107000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2830-8_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819628292","9789819628308"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2830-8_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"29 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Network and Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Haikou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"npc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}