{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T07:54:32Z","timestamp":1775634872488,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819584017","type":"print"},{"value":"9789819584024","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-981-95-8402-4_7","type":"book-chapter","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T07:18:22Z","timestamp":1775632702000},"page":"124-143","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EAHP: An Efficient Automatic Hybrid Parallelism Approach with\u00a0Genetic Algorithm"],"prefix":"10.1007","author":[{"given":"Yichen","family":"Gu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiquan","family":"Lai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weijie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinghui","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,9]]},"reference":[{"key":"7_CR1","doi-asserted-by":"publisher","unstructured":"Almazrouei, E., et al.: The Falcon series of open language models. arXiv e-prints arXiv:2311.16867 (2023). https:\/\/doi.org\/10.48550\/arXiv.2311.16867","DOI":"10.48550\/arXiv.2311.16867"},{"key":"7_CR2","doi-asserted-by":"publisher","unstructured":"Black, S., Leo, G., Wang, P., Leahy, C., Biderman, S.: GPT-neo: large scale autoregressive language modeling with mesh-tensorflow (2021). https:\/\/doi.org\/10.5281\/zenodo.5297715","DOI":"10.5281\/zenodo.5297715"},{"key":"7_CR3","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 1877\u20131901. Curran Associates, Inc. (2020)"},{"key":"7_CR4","doi-asserted-by":"publisher","unstructured":"Fan, S., et al.: 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. PPoPP \u201921, pp. 431\u2013445. Association for Computing Machinery, New York (2021). https:\/\/doi.org\/10.1145\/3437801.3441593","DOI":"10.1145\/3437801.3441593"},{"issue":"1","key":"7_CR5","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1109\/TPDS.2022.3219819","volume":"34","author":"J Fang","year":"2023","unstructured":"Fang, J., et al.: Parallel training of pre-trained models via chunk-based dynamic memory management. IEEE Trans. Parallel Distrib. Syst. 34(1), 304\u2013315 (2023). https:\/\/doi.org\/10.1109\/TPDS.2022.3219819","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"7_CR6","unstructured":"Jia, Z., Lin, S., Qi, C.R., Aiken, A.: Exploring hidden dimensions in parallelizing convolutional neural networks. In: Dy, J.G., Krause, A. (eds.) ICML. Proceedings of Machine Learning Research, vol.\u00a080, pp. 2279\u20132288. PMLR (2018)"},{"key":"7_CR7","unstructured":"Jia, Z., Zaharia, M., Aiken, A.: Beyond data and model parallelism for deep neural networks. In: Talwalkar, A., Smith, V., Zaharia, M. (eds.) Proceedings of Machine Learning and Systems, vol.\u00a01, pp. 1\u201313 (2019)"},{"key":"7_CR8","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of naacL-HLT, Minneapolis, Minnesota, vol.\u00a01, p.\u00a02 (2019)"},{"issue":"5","key":"7_CR9","doi-asserted-by":"publisher","first-page":"1466","DOI":"10.1109\/TPDS.2023.3247001","volume":"34","author":"Z Lai","year":"2023","unstructured":"Lai, Z., et al.: Merak: an efficient distributed dnn training framework with automated 3d parallelism for giant foundation models. IEEE Trans. Parallel Distrib. Syst. 34(5), 1466\u20131478 (2023). https:\/\/doi.org\/10.1109\/TPDS.2023.3247001","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Li, D., Wang, H., Xing, E., Zhang, H.: Amp: automatically finding model parallel strategies with heterogeneity awareness. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, vol.\u00a035, pp. 6630\u20136639. Curran Associates, Inc. (2022)","DOI":"10.52202\/068431-0480"},{"key":"7_CR11","doi-asserted-by":"publisher","unstructured":"Li, S., et al.: Pytorch distributed: experiences on accelerating data parallel training. Proc. VLDB Endow. 13(12), 3005\u20133018 (2020). https:\/\/doi.org\/10.14778\/3415478.3415530","DOI":"10.14778\/3415478.3415530"},{"key":"7_CR12","doi-asserted-by":"publisher","unstructured":"Li, S., et al.: Automated tensor model parallelism with overlapped communication for efficient foundation model training. CoRR arxiv:2305.16121 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2305.16121","DOI":"10.48550\/ARXIV.2305.16121"},{"key":"7_CR13","doi-asserted-by":"publisher","unstructured":"Liu, W., Lai, Z., Li, S., Duan, Y., Ge, K., Li, D.: Autopipe: a fast pipeline parallelism approach with balanced partitioning and micro-batch slicing. In: 2022 IEEE International Conference on Cluster Computing (CLUSTER), pp. 301\u2013312 (2022). https:\/\/doi.org\/10.1109\/CLUSTER51413.2022.00042","DOI":"10.1109\/CLUSTER51413.2022.00042"},{"key":"7_CR14","doi-asserted-by":"publisher","unstructured":"Narayanan, D., et al.: Pipedream: generalized pipeline parallelism for dnn training. In: Proceedings of the 27th ACM Symposium on Operating Systems Principles. SOSP \u201919, pp. 1\u201315. Association for Computing Machinery, New York (2019). https:\/\/doi.org\/10.1145\/3341301.3359646","DOI":"10.1145\/3341301.3359646"},{"key":"7_CR15","unstructured":"Narayanan, D., Phanishayee, A., Shi, K., Chen, X., Zaharia, M.: Memory-efficient pipeline-parallel dnn training. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 7937\u20137947. PMLR (2021)"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Narayanan, D., et al.: Efficient large-scale language model training on gpu clusters using megatron-lm. In: SC21: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201314 (2021)","DOI":"10.1145\/3458817.3476209"},{"key":"7_CR17","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021)"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S., Rasley, J., Ruwase, O., He, Y.: Zero: memory optimizations toward training trillion parameter models. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. SC \u201920. IEEE Press (2020)","DOI":"10.1109\/SC41405.2020.00024"},{"key":"7_CR19","doi-asserted-by":"publisher","unstructured":"Rajbhandari, S., Ruwase, O., Rasley, J., Smith, S., He, Y.: Zero-infinity: breaking the gpu memory wall for extreme scale deep learning. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. SC \u201921. Association for Computing Machinery, New York (2021). https:\/\/doi.org\/10.1145\/3458817.3476205","DOI":"10.1145\/3458817.3476205"},{"key":"7_CR20","doi-asserted-by":"publisher","unstructured":"Rasley, J., Rajbhandari, S., Ruwase, O., He, Y.: Deepspeed: system optimizations enable training deep learning models with over 100 billion parameters. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. KDD \u201920, pp. 3505\u20133506. Association for Computing Machinery, New York (2020). https:\/\/doi.org\/10.1145\/3394486.3406703","DOI":"10.1145\/3394486.3406703"},{"key":"7_CR21","unstructured":"Ren, J., et al.: ZeRO-offload: democratizing billion-scale model training. In: 2021 USENIX Annual Technical Conference (USENIX ATC 21), pp. 551\u2013564. USENIX Association (2021)"},{"key":"7_CR22","unstructured":"Shoeybi, M., Patwary, M., Puri, R., LeGresley, P., Casper, J., Catanzaro, B.: Megatron-lm: training multi-billion parameter language models using model parallelism. CoRR arxiv:1909.08053 (2019)"},{"key":"7_CR23","unstructured":"Tarnawski, J.M., Narayanan, D., Phanishayee, A.: Piper: multidimensional planner for dnn parallelization. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol.\u00a034, pp. 24829\u201324840. Curran Associates, Inc. (2021)"},{"key":"7_CR24","unstructured":"Team, M.N.: Introducing mpt-7b: a new standard for open-source, commercially usable llms (2023). Accessed 05 May 2023"},{"key":"7_CR25","unstructured":"Wang, B., Komatsuzaki, A.: GPT-J-6B: a 6 billion parameter autoregressive language model (2021)"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-8402-4_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T07:18:30Z","timestamp":1775632710000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-8402-4_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819584017","9789819584024"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-8402-4_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ieee-cybermatics.org\/2025\/ica3pp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}