{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T20:06:50Z","timestamp":1778962010155,"version":"3.51.4"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T00:00:00Z","timestamp":1778889600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T00:00:00Z","timestamp":1778889600000},"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":["Int J Parallel Prog"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1007\/s10766-026-00812-y","type":"journal-article","created":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T19:14:33Z","timestamp":1778958873000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SymTensor: Symbolic and Adaptive Tensor Partitioning by Unified Parallelism for Deep Learning"],"prefix":"10.1007","volume":"54","author":[{"given":"Hongxing","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengdao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Serge","family":"Petiton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,16]]},"reference":[{"key":"812_CR1","unstructured":"Abadi, M., Barham, P., Chen, J., et\u00a0al.: TensorFlow: a system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), pp. 265\u2013283 (2016)"},{"key":"812_CR2","unstructured":"Brown, TB., Mann, B., Ryder, N., et\u00a0al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, pp. 1877\u20131901 (2020)"},{"key":"812_CR3","doi-asserted-by":"crossref","unstructured":"Chen, L.: Deep learning and practice with mindspore. Springer Nature (2021)","DOI":"10.1007\/978-981-16-2233-5"},{"key":"812_CR4","doi-asserted-by":"crossref","unstructured":"Dao, T., Fu, D., Ermon, S., et\u00a0al.: FlashAttention: fast and memory-efficient exact attention with IO-awareness. In: Advances in Neural Information Processing Systems, pp. 16094\u201316107 (2022)","DOI":"10.52202\/068431-1189"},{"key":"812_CR5","unstructured":"Dean, J., Corrado, GS., Monga, R., et\u00a0al.: Large scale distributed deep networks. In: Proceedings of the 26th International Conference on Neural Information Processing Systems\u2014Volume 1. Curran Associates Inc., Red Hook, NY, USA, NIPS\u201912, pp. 1223\u20131231 (2012)"},{"key":"812_CR6","unstructured":"Foster, I.: Designing and Building Parallel Programs: Concepts and Tools for Parallel Software Engineering. Addison-Wesley Longman Publishing Co., Inc, New York (1995)"},{"key":"812_CR7","unstructured":"Hockney, R.W., Jesshope, C.R.: Parallel Computers Two: Architecture, Programming and Algorithms, 2nd edn. IOP Publishing Ltd., GBR (1988)"},{"key":"812_CR8","unstructured":"Hu, EJ., Shen, Y., Wallis, P., et\u00a0al.: LoRA: Low-rank adaptation of large language models. In: International Conference on Learning Representations (2022)"},{"key":"812_CR9","unstructured":"Huang, Y., Cheng, Y., Bapna, A., et\u00a0al.: GPipe: efficient training of giant neural networks using pipeline parallelism. In: Advances in Neural Information Processing Systems, pp. 103\u2013112 (2019)"},{"key":"812_CR10","unstructured":"Jiang, A.Q., Sablayrolles, A., Roux, A., et\u00a0al.: Mixtral of experts. arXiv:2401.04088 (2024)"},{"key":"812_CR11","unstructured":"Lepikhin, D., Lee, H., Xu, Y., et\u00a0al.: GShard: scaling giant models with conditional computation and automatic sharding. In: Proceedings of the International Conference on Learning Representations (ICLR) (2021)"},{"key":"812_CR12","doi-asserted-by":"crossref","unstructured":"Narayanan, D., Shoeybi, M., Casper, J., et\u00a0al.: Efficient large-scale language model training on GPU clusters using megatron-LM. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. Association for Computing Machinery, New York, NY, USA, SC \u201921 (2021)","DOI":"10.1145\/3458817.3476209"},{"key":"812_CR13","unstructured":"NVIDIA NVIDIA Collective Communications Library (NCCL). NVIDIA Developer Documentation (2021)"},{"key":"812_CR14","unstructured":"Paszke, A., Gross, S., Massa, F., et\u00a0al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8024\u20138035 (2019)"},{"key":"812_CR15","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S., Ruwase, O., Rasley, J, et\u00a0al.: 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. Association for Computing Machinery, New York, NY, USA, SC \u201921 (2021)","DOI":"10.1145\/3458817.3476205"},{"key":"812_CR16","unstructured":"Shoeybi, M., Patwary, M., Puri, R., et\u00a0al.: Megatron-LM: Training multi-billion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053 (2019)"},{"key":"812_CR17","unstructured":"Touvron, H., Martin, L., Stone, K., et\u00a0al.: LLaMA 2: Open foundation and fine-tuned chat models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics, New York, pp. 123\u2013133 (2023)"},{"key":"812_CR18","doi-asserted-by":"crossref","unstructured":"Wang, H., Li, C., Tachon, T., et\u00a0al.: Efficient and systematic partitioning of large and deep neural networks for parallelization. In: Euro-Par 2021: Parallel Processing, Lecture Notes in Computer Science, vol. 12820. Springer, Berlin, pp. 201\u2013216 (2021)","DOI":"10.1007\/978-3-030-85665-6_13"},{"key":"812_CR19","unstructured":"Xu, Y., Lee, H., Chen, D., et\u00a0al.: GSPMD: general and scalable parallelization for ML computation graphs. In: NeurIPS (2021)"},{"key":"812_CR20","unstructured":"Yang, A., Yang, B., Hui, B., et\u00a0al.: Qwen2 technical report. arXiv preprint arXiv:2407.10671 (2024)"},{"key":"812_CR21","unstructured":"Zheng, L., Wang, S., Lin, Z., et\u00a0al.: Alpa: Automating inter- and intra-operator parallelism for distributed deep learning. In: Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX Association, New York, pp. 559\u2013578 (2024)"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-026-00812-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10766-026-00812-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-026-00812-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T19:14:39Z","timestamp":1778958879000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10766-026-00812-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,16]]},"references-count":21,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["812"],"URL":"https:\/\/doi.org\/10.1007\/s10766-026-00812-y","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"value":"0885-7458","type":"print"},{"value":"1573-7640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,16]]},"assertion":[{"value":"29 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"12"}}