{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T15:02:41Z","timestamp":1781190161783,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819596935","type":"print"},{"value":"9789819596942","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\/978-981-95-9694-2_3","type":"book-chapter","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T14:28:08Z","timestamp":1781188088000},"page":"27-44","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PerfMamba: Performance Analysis and\u00a0Pruning of\u00a0Selective State Space Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0389-931X","authenticated-orcid":false,"given":"Abdullah Al","family":"Asif","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4332-8442","authenticated-orcid":false,"given":"Mobina","family":"Kashaniyan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2415-566X","authenticated-orcid":false,"given":"Sixing","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan Pablo","family":"Mu\u00f1oz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8672-5317","authenticated-orcid":false,"given":"Ali","family":"Jannesari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"key":"3_CR1","unstructured":"Pytorch profiler. https:\/\/pytorch.org\/tutorials\/recipes\/recipes\/profiler_recipe.html"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Adhianto, L., et al.: HPCTOOLKIT: tools for performance analysis of optimized parallel programs. Concurrency Compututation: Pract. Experience, 22(6), pp. 685\u2013701 (2010). http:\/\/hpctoolkit.org","DOI":"10.1002\/cpe.1553"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Ali, A.A., Zimerman, I., Wolf, L.: The hidden attention of mamba models. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, vol. 1, pp. 1516\u20131534 (2025)","DOI":"10.18653\/v1\/2025.acl-long.76"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Bisk, Y., et\u00a0al.: PIQA: reasoning about physical commonsense in natural language. In: Proceedings of the AAAI conference on artificial intelligence, pp. 7432\u20137439 (2020)","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"3_CR5","doi-asserted-by":"publisher","unstructured":"Cheng, H., Zhang, M., Shi, J.Q.: A survey on deep neural network pruning: taxonomy, comparison, analysis, and recommendations. IEEE Trans. Pattern Anal. Mach. Intell. pp. 10558\u201310578 (2024). https:\/\/doi.org\/10.1109\/TPAMI.2024.3447085","DOI":"10.1109\/TPAMI.2024.3447085"},{"key":"3_CR6","unstructured":"Clark, P., et al.: Think you have solved question answering? Try arc, the AI2 reasoning challenge (2018). https:\/\/arxiv.org\/abs\/1803.05457"},{"key":"3_CR7","unstructured":"Dao, T., Gu, A.: Transformers are SSMS: generalized models and efficient algorithms through structured state space duality. In: Proceedings of the 41st International Conference on Machine Learning (2024)"},{"key":"3_CR8","unstructured":"Dehghani, M., Arnab, A., Beyer, L., Vaswani, A., Tay, Y.: The efficiency misnomer. In: International Conference on Learning Representations (2022). https:\/\/arxiv.org\/abs\/2110.12894"},{"key":"3_CR9","unstructured":"Dery, L., Kolawole, S., Kagy, J.F., Smith, V., Neubig, G., Talwalkar, A.: Everybody prune now: structured pruning of LLMs with only forward passes. arXiv preprint arXiv:2402.05406 (2024)"},{"key":"3_CR10","unstructured":"Gao, Y., Glowacka, D.: Deep gate recurrent neural network. In: Proceedings of the 8th Asian Conference on Machine Learning, pp. 350\u2013365 (Nov, 2016)"},{"key":"3_CR11","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. In: First Conference on Language Modeling (2024). https:\/\/openreview.net\/forum?id=tEYskw1VY2"},{"key":"3_CR12","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces. In: International Conference on Learning Representations (2022). https:\/\/arxiv.org\/abs\/2111.00396"},{"key":"3_CR13","unstructured":"Gu, A., et al.: Combining recurrent, convolutional, and continuous-time models with linear state space layers. Adv. Neural Inf. Process. Syst. pp. 572\u2013585 (2021)"},{"key":"3_CR14","unstructured":"Le\u00a0Cun, Y., Denker, J.S., Solla, S.A.: Optimal brain damage. In: Proceedings of the 3rd International Conference on Neural Information Processing Systems, pp. 598\u2013605 (1989)"},{"key":"3_CR15","unstructured":"Lenz, B., et al.: Jamba: Hybrid transformer-mamba language models. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=JFPaD7lpBD"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Marca: Mamba accelerator with reconfigurable architecture. In: 2024 ACM\/IEEE International Conference On Computer Aided Design (ICCAD) pp.\u00a01\u20139 (2024). https:\/\/api.semanticscholar.org\/CorpusID:272704058","DOI":"10.1145\/3676536.3676798"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Munoz, J.P., Yuan, J., Jain, N.: Mamba-shedder: post-transformer compression for efficient selective structured state space models. In: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 3851\u20133863 (2025)","DOI":"10.18653\/v1\/2025.naacl-long.195"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Qin, J., Liu, F.: Mamba-spike: enhancing the mamba architecture with a spiking front-end for efficient temporal data processing. Comput. Graph. Int. Conf. pp. 323\u2013334 (2024)","DOI":"10.1007\/978-3-031-82021-2_23"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Shen, M., Molchanov, P., Yin, H., Alvarez, J.M.: When to prune? A policy towards early structural pruning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12247\u201312256 (2022)","DOI":"10.1109\/CVPR52688.2022.01193"},{"key":"3_CR20","unstructured":"Shleifer, S., Weston, J., Ott, M.: NormFormer: improved transformer pretraining with extra normalization. CoRR (2021). https:\/\/arxiv.org\/abs\/2110.09456"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Sun, K., Yu, D., Yu, D., Cardie, C.: Improving machine reading comprehension with general reading strategies. In: North American Chapter of the Association for Computational Linguistics (2018). https:\/\/api.semanticscholar.org\/CorpusID:53109787","DOI":"10.18653\/v1\/N19-1270"},{"key":"3_CR22","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. (2017)"},{"key":"3_CR23","unstructured":"Waleffe, R., et al.: An empirical study of mamba-based language models (2024). https:\/\/arxiv.org\/abs\/2406.07887"},{"key":"3_CR24","unstructured":"Wolf, T., et\u00a0al.: Transformers: state-of-the-art natural language processing (2020). https:\/\/github.com\/huggingface\/transformers"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Xia, M., Zhong, Z., Chen, D.: Structured pruning learns compact and accurate models. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, pp. 1513\u20131528 (2022)","DOI":"10.18653\/v1\/2022.acl-long.107"},{"key":"3_CR26","unstructured":"Xiao, Y., et al.: Mambatree: tree topology is all you need in state space model. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024)"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zhang, H.: Comparative analysis of structured pruning and unstructured pruning. Front. Comput. pp. 882\u2013889 (2022)","DOI":"10.1007\/978-981-16-8052-6_112"},{"key":"3_CR28","doi-asserted-by":"publisher","unstructured":"Yousefzadeh-Asl-Miandoab, E., Robroek, T., Tozun, P.: Profiling and monitoring deep learning training tasks. In: Proceedings of the 3rd Workshop on Machine Learning and Systems, pp. 18\u201325 (2023). https:\/\/doi.org\/10.1145\/3578356.3592589","DOI":"10.1145\/3578356.3592589"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Zellers, R., Holtzman, A., Bisk, Y., Farhadi, A., Choi, Y.: Hellaswag: Can a machine really finish your sentence? In: Annual Meeting of the Association for Computational Linguistics (2019). https:\/\/api.semanticscholar.org\/CorpusID:159041722","DOI":"10.18653\/v1\/P19-1472"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Zhan, Z., et al.: Rethinking token reduction for state space models. In: Conference on Empirical Methods in Natural Language Processing (2024). https:\/\/api.semanticscholar.org\/CorpusID:273501765","DOI":"10.18653\/v1\/2024.emnlp-main.100"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: A survey on visual mamba. Appl. Sci. (2024)","DOI":"10.3390\/app14135683"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Zhao, P., et al.: Pruning foundation models for high accuracy without retraining. In: Conference on Empirical Methods in Natural Language Processing (2024). https:\/\/api.semanticscholar.org\/CorpusID:273501976","DOI":"10.18653\/v1\/2024.findings-emnlp.566"},{"key":"3_CR33","doi-asserted-by":"publisher","unstructured":"Zhou, K., Krentel, M.W., Mellor-Crummey, J.: Tools for top-down performance analysis of GPU-accelerated applications. In: Proceedings of the 34th ACM International Conference on Supercomputing (2020). https:\/\/doi.org\/10.1145\/3392717.3392752","DOI":"10.1145\/3392717.3392752"}],"container-title":["Lecture Notes in Computer Science","Evaluation Science and Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-9694-2_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T14:28:18Z","timestamp":1781188098000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-9694-2_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819596935","9789819596942"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-9694-2_3","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":"1 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Bench","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Benchmarking, Measuring and Optimization","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chengdu","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":"3 December 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bench2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.benchcouncil.org\/bench2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}