{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T00:07:08Z","timestamp":1755994028582,"version":"3.44.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032024053","type":"print"},{"value":"9783032024060","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T00:00:00Z","timestamp":1755993600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T00:00:00Z","timestamp":1755993600000},"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\/978-3-032-02406-0_13","type":"book-chapter","created":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T09:26:20Z","timestamp":1755941180000},"page":"179-193","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Integrated Approach for\u00a0Prototyping and\u00a0Deploying Large Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0246-0819","authenticated-orcid":false,"given":"Jan","family":"Majkutewicz","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5029-6768","authenticated-orcid":false,"given":"Julian","family":"Szyma\u0144ski","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,24]]},"reference":[{"key":"13_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"13_CR2","unstructured":"Askell, A., et\u00a0al.: A general language assistant as a laboratory for alignment. arXiv preprint arXiv:2112.00861 (2021)"},{"key":"13_CR3","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol.\u00a033, pp. 1877\u20131901. Curran Associates, Inc. (2020)"},{"key":"13_CR4","first-page":"1","volume":"6","author":"L Chen","year":"2024","unstructured":"Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., Krishnamurthy, A.: Punica: multi-tenant lora serving. Proc. Mach. Learn. Syst. 6, 1\u201313 (2024)","journal-title":"Proc. Mach. Learn. Syst."},{"key":"13_CR5","unstructured":"Crankshaw, D., Wang, X., Zhou, G., Franklin, M.J., Gonzalez, J.E., Stoica, I.: Clipper: a low-latency online prediction serving system. In: 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17), pp. 613\u2013627 (2017)"},{"key":"13_CR6","unstructured":"Cui, W., et al.: DVABatch: diversity-aware multi-entry multi-exit batching for efficient processing of DNN services on GPUs. In: 2022 USENIX Annual Technical Conference (USENIX ATC 22), pp. 183\u2013198 (2022)"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Ding, N., et al.: Enhancing chat language models by scaling high-quality instructional conversations (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.183"},{"key":"13_CR8","unstructured":"Dubey, A., et\u00a0al.: The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"13_CR9","unstructured":"Gudibande, A., et al.: The false promise of imitating proprietary llms. arXiv preprint arXiv:2305.15717 (2023)"},{"key":"13_CR10","unstructured":"Gujarati, A., et al.: Serving DNNs like clockwork: Performance predictability from the bottom up. In: 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20), pp. 443\u2013462 (2020)"},{"key":"13_CR11","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022)"},{"key":"13_CR12","unstructured":"Huang, Q., et al.: Lawyer llama technical report. arXiv preprint arXiv:2305.15062 (2023)"},{"key":"13_CR13","unstructured":"Jiang, A.Q., et\u00a0al.: Mistral 7bb. arXiv preprint arXiv:2310.06825 (2023)"},{"key":"13_CR14","unstructured":"Lewandowska-Tomaszczyk, B., Przepi\u00f3rkowski, A., Ba\u0144ko, M., G\u00f3rski, R.: Narodowy korpus j\u0119zyka polskiego. Biuletyn Polskiego Towarzystwa J\u0119z\u0119koznawczego, p.\u00a047 (2012)"},{"key":"13_CR15","unstructured":"Miao, X., Oliaro, G., Cheng, X., Wu, M., Unger, C., Jia, Z.: Flexllm: a system for co-serving large language model inference and parameter-efficient finetuning. arXiv preprint arXiv:2402.18789 (2024)"},{"key":"13_CR16","unstructured":"Ociepa, K., \u0141ukasz Flis, Wr\u00f3bel, K., Gwo\u017adziej, A., Kinas, R.: Bielik 7b v0.1: a polish language model \u2013 development, insights, and evaluation (2024)"},{"key":"13_CR17","unstructured":"Ociepa, K., \u0141ukasz Flis, Wr\u00f3bel, K., Gwo\u017adziej, A., Kinas, R., SpeakLeash Team, Cyfronet team: Bielik-11b-v2.2-instruct model card (2024), https:\/\/huggingface.co\/speakleash\/Bielik-11B-v2.2-Instruct, Accessed: 22 Jan 2025"},{"key":"13_CR18","unstructured":"Ogrodniczuk, M., Kope\u0107, M.: The polish summaries corpus. In: Calzolari, N., et al. (eds.) Proceedings of the Ninth International Conference on Language Resources and Evaluation, LREC\u00a02014. pp, 3712\u20133715. European Language Resources Association (ELRA), Reykjav\u00edk, Iceland (2014), http:\/\/www.lrec-conf.org\/proceedings\/lrec2014\/index.html"},{"key":"13_CR19","unstructured":"Olston, C., et al.: Tensorflow-serving: flexible, high-performance ml serving. arXiv preprint arXiv:1712.06139 (2017)"},{"key":"13_CR20","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI (2019)"},{"key":"13_CR21","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: your language model is secretly a reward model. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"13_CR22","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":"13_CR23","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 2020, pp. 3505\u20133506. ACM, New York, NY, USA (2020). https:\/\/doi.org\/10.1145\/3394486.3406703","DOI":"10.1145\/3394486.3406703"},{"key":"13_CR24","unstructured":"Sheng, Y., et\u00a0al.: S-lora: serving thousands of concurrent lora adapters. arXiv preprint arXiv:2311.03285 (2023)"},{"key":"13_CR25","first-page":"3008","volume":"33","author":"N Stiennon","year":"2020","unstructured":"Stiennon, N., et al.: Learning to summarize from human feedback. Adv. Neural. Inf. Process. Syst. 33, 3008\u20133021 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR26","unstructured":"Wang, H., et al.: Huatuo: tuning llama model with chinese medical knowledge. arXiv preprint arXiv:2304.06975 (2023)"},{"key":"13_CR27","unstructured":"Wei, J., et al.: Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652 (2021)"},{"key":"13_CR28","unstructured":"Wei, J., et al.: Emergent abilities of large language models. Trans. Mach. Learn. Res. (2022)"},{"key":"13_CR29","unstructured":"Wolf, T.: Huggingface\u2019s transformers: state-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019)"},{"key":"13_CR30","unstructured":"Wu, S., et al.: Bloomberggpt: a large language model for finance. arXiv preprint arXiv:2303.17564 (2023)"},{"issue":"4","key":"13_CR31","first-page":"39","volume":"41","author":"M Zaharia","year":"2018","unstructured":"Zaharia, M., et al.: Accelerating the machine learning lifecycle with mlflow. IEEE Data Eng. Bull. 41(4), 39\u201345 (2018)","journal-title":"IEEE Data Eng. Bull."}],"container-title":["Lecture Notes in Computer Science","Computer Information Systems and Industrial Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-02406-0_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T09:26:24Z","timestamp":1755941184000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02406-0_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,24]]},"ISBN":["9783032024053","9783032024060"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02406-0_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,24]]},"assertion":[{"value":"24 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare relevant to this article\u2019s content.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"CISIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Information Systems and Industrial Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Fukuoka","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"11 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cisim2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pb.edu.pl\/cisim\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}