{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:03:52Z","timestamp":1763190232572,"version":"3.45.0"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032104656","type":"print"},{"value":"9783032104663","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-10466-3_14","type":"book-chapter","created":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:00:42Z","timestamp":1763190042000},"page":"166-177","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ManuMatic: Strategy Injection for\u00a0Robust Automatic Hybrid Parallelism in\u00a0Distributed DNN Training"],"prefix":"10.1007","author":[{"given":"Ruiwen","family":"Wang","sequence":"first","affiliation":[]},{"given":"Chong","family":"Li","sequence":"additional","affiliation":[]},{"given":"Hongxing","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Raja","family":"Appuswamy","sequence":"additional","affiliation":[]},{"given":"Yujie","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,16]]},"reference":[{"key":"14_CR1","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, pp. 1877\u20131901 (2020)"},{"key":"14_CR2","unstructured":"Yang, A., et al.: Qwen2 Technical Report. arXiv preprint arXiv:2407.10671 (2024)"},{"key":"14_CR3","unstructured":"Jiang, A.Q., et al.: Mixtral of experts. arXiv preprint arXiv:2401.04088 (2024)"},{"key":"14_CR4","unstructured":"Krizhevsky, A., et al.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"14_CR5","unstructured":"Dean, J., et al.: Large scale distributed deep networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1. NIPS 2012, Lake Tahoe, Nevada (2012)"},{"key":"14_CR6","unstructured":"Krizhevsky, A.: One weird trick for parallelizing convolutional neural networks. arXiv preprint arXiv:1404.5997 (2014)"},{"key":"14_CR7","unstructured":"Shoeybi, M., et al.: Megatron-LM: training multi-billion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053 (2019)"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Efficient and systematic partitioning of large and deep neural networks for parallelization. In: European Conference on Parallel Processing, pp. 201\u2013216. Springer (2021)","DOI":"10.1007\/978-3-030-85665-6_13"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Wang, M., et al.: Supporting very large models using automatic dataflow graph partitioning. In: Proceedings of the Fourteenth EuroSys Conference 2019, EuroSys 2019. Association for Computing Machinery (2019)","DOI":"10.1145\/3302424.3303953"},{"key":"14_CR10","unstructured":"Jia, Z., et al.: Exploring hidden dimensions in accelerating convolutional neural networks. In: Dy, J. et al. (eds.) International Conference on Machine Learning, vol. 80, pp. 2274\u20132283. Proceedings of Machine Learning Research. PMLR, October 2018"},{"key":"14_CR11","unstructured":"Korthikanti, V., et al.: Reducing activation recomputation in large transformer models. arXiv preprint arXiv:2205.05198 (2022)"},{"key":"14_CR12","unstructured":"Shazeer, N., et al.: Outrageously large neural networks: the SparselyGated mixture-of-experts layer. In: International Conference on Learning Representations (ICLR) (2017)"},{"key":"14_CR13","unstructured":"Fedus, W., et al.: Switch transformers: scaling to trillion parameter models with simple and efficient sparse training. arXiv preprint arXiv:2101.03961 (2021)"},{"key":"14_CR14","unstructured":"Rajbhandari, S., et al.: DeepSpeed-MoE: advancing mixture-of-experts inference and training. arXiv preprint arXiv:2201.05596 (2022)"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: BMPipe: bubble-memory co-optimization strategy planner for very-large DNN training. In: IEEE International Conference on Cluster Computing 2025 (2025)","DOI":"10.1109\/CLUSTER59342.2025.11186487"},{"key":"14_CR16","unstructured":"Huawei. MindSpore (2022). https:\/\/www.mindspore.cn\/"},{"key":"14_CR17","unstructured":"Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), pp. 265\u2013283. USENIX Association, November 2016"},{"key":"14_CR18","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8026\u20138037 (2019)"}],"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\/978-3-032-10466-3_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:00:53Z","timestamp":1763190053000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-10466-3_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,16]]},"ISBN":["9783032104656","9783032104663"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-10466-3_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,16]]},"assertion":[{"value":"16 November 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":"Nha Trang","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"npc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.npc-conference.com\/#\/npc2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}