{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:11:49Z","timestamp":1784139109223,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809755","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"2139-2149","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SilverTorch: A Unified Model-based System to Democratize Large-Scale Recommendation on GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0043-9802","authenticated-orcid":false,"given":"Bi","family":"Xue","sequence":"first","affiliation":[{"name":"Meta Platforms, Inc, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3966-0136","authenticated-orcid":false,"given":"Hong","family":"Wu","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9472-8767","authenticated-orcid":false,"given":"Lei","family":"Chen","sequence":"additional","affiliation":[{"name":"Meta RecSys, Meta Platforms, Inc, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3758-8899","authenticated-orcid":false,"given":"Chao","family":"Yang","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2911-8315","authenticated-orcid":false,"given":"Yiming","family":"Ma","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9109-4273","authenticated-orcid":false,"given":"Fei","family":"Ding","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3595-216X","authenticated-orcid":false,"given":"Zhen","family":"Wang","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8165-2543","authenticated-orcid":false,"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7136-4182","authenticated-orcid":false,"given":"Xiaoheng","family":"Mao","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2795-8421","authenticated-orcid":false,"given":"Ke","family":"Huang","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2404-5571","authenticated-orcid":false,"given":"Xialu","family":"Li","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9540-4043","authenticated-orcid":false,"given":"Peng","family":"Xia","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9379-4442","authenticated-orcid":false,"given":"Rui","family":"Jian","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5225-3605","authenticated-orcid":false,"given":"Yanli","family":"Zhao","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1238-0454","authenticated-orcid":false,"given":"Yanzun","family":"Huang","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2725-7458","authenticated-orcid":false,"given":"Yijie","family":"Deng","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0067-0683","authenticated-orcid":false,"given":"Harry","family":"Tran","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3071-2730","authenticated-orcid":false,"given":"Ryan","family":"Chang","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0713-2629","authenticated-orcid":false,"given":"Min","family":"Yu","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6976-8682","authenticated-orcid":false,"given":"Eric","family":"Dong","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2784-2626","authenticated-orcid":false,"given":"Jiazhou","family":"Wang","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4793-6129","authenticated-orcid":false,"given":"Qianqian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5240-8011","authenticated-orcid":false,"given":"Keke","family":"Zhai","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9903-3197","authenticated-orcid":false,"given":"Hongzhang","family":"Yin","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3528-3812","authenticated-orcid":false,"given":"Pawel","family":"Garbacki","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0698-5731","authenticated-orcid":false,"given":"Zheng","family":"Fang","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9118-7933","authenticated-orcid":false,"given":"Yiyi","family":"Pan","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1848-1626","authenticated-orcid":false,"given":"Min","family":"Ni","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7490-8597","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"265","volume-title":"12th USENIX symposium on operating systems design and implementation (OSDI 16)","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. 2016. {TensorFlow}: a system for {Large-Scale} machine learning. In 12th USENIX symposium on operating systems design and implementation (OSDI 16). 265-283."},{"key":"e_1_3_2_1_2_1","volume-title":"Understanding scaling laws for recommendation models. arXiv preprint arXiv:2208.08489","author":"Ardalani Newsha","year":"2022","unstructured":"Newsha Ardalani, Carole-Jean Wu, Zeliang Chen, Bhargav Bhushanam, and Adnan Aziz. 2022. Understanding scaling laws for recommendation models. arXiv preprint arXiv:2208.08489 (2022)."},{"key":"e_1_3_2_1_3_1","unstructured":"David Arthur and Sergei Vassilvitskii. 2006. k-means: The advantages of careful seeding. Technical Report. Stanford."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539170"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3680091"},{"key":"e_1_3_2_1_6_1","volume-title":"The anatomy of a large-scale hypertextual web search engine. Computer networks and ISDN systems 30, 1-7","author":"Brin Sergey","year":"1998","unstructured":"Sergey Brin and Lawrence Page. 1998. The anatomy of a large-scale hypertextual web search engine. Computer networks and ISDN systems 30, 1-7 (1998), 107-117."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2914808"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714822"},{"key":"e_1_3_2_1_10_1","unstructured":"Matthijs Douze Alexandr Guzhva Chengqi Deng Jeff Johnson Gergely Szilvasy Pierre-Emmanuel Mazar\u00e9 Maria Lomeli Lucas Hosseini and Herv\u00e9 J\u00e9gou. 2024. The Faiss library. (2024). arXiv:2401.08281 [cs.LG]"},{"key":"e_1_3_2_1_11_1","volume-title":"SysML conference","author":"Frostig Roy","year":"2019","unstructured":"Roy Frostig, Matthew James Johnson, and Chris Leary. 2019. Compiling machine learning programs via high-level tracing. In SysML conference 2018."},{"key":"e_1_3_2_1_12_1","unstructured":"github 2023. Faiss on the GPU Limitations. https:\/\/github.com\/facebookresearch\/faiss\/wiki\/Faiss-on-the-GPU#limitations."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080789"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403305"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3547387"},{"key":"e_1_3_2_1_16_1","volume-title":"Ravishankar Krishnawamy, and Rohan Kadekodi.","author":"Subramanya Suhas Jayaram","year":"2019","unstructured":"Suhas Jayaram Subramanya, Fnu Devvrit, Harsha Vardhan Simhadri, Ravishankar Krishnawamy, and Rohan Kadekodi. 2019. Diskann: Fast accurate billion-point nearest neighbor search on a single node. Advances in neural information processing Systems 32 (2019)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_18_1","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems 33 (2020) 9459-9474."},{"key":"e_1_3_2_1_19_1","unstructured":"Milvus 2023. Milvus GPU Limitations. https:\/\/milvus.io\/docs\/gpu_index.md."},{"key":"e_1_3_2_1_20_1","first-page":"561","volume-title":"13th USENIX symposium on operating systems design and implementation (OSDI 18)","author":"Moritz Philipp","year":"2018","unstructured":"Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael I Jordan, et al. 2018. Ray: A distributed framework for emerging {AI} applications. In 13th USENIX symposium on operating systems design and implementation (OSDI 18). 561-577."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3533727"},{"key":"e_1_3_2_1_22_1","volume-title":"Jianyu Huang, Narayanan Sundaraman, Jongsoo Park, Xiaodong Wang, Udit Gupta, Carole-Jean Wu, Alisson G Azzolini, et al.","author":"Naumov Maxim","year":"2019","unstructured":"Maxim Naumov, Dheevatsa Mudigere, Hao-Jun Michael Shi, Jianyu Huang, Narayanan Sundaraman, Jongsoo Park, Xiaodong Wang, Udit Gupta, Carole-Jean Wu, Alisson G Azzolini, et al. 2019. Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:1906.00091 (2019)."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of IRS.","author":"Oldridge Even","year":"2020","unstructured":"Even Oldridge, Julio Perez, Ben Frederickson, Nicolas Koumchatzky, Minseok Lee, Zehuan Wang, Lei Wu, Fan Yu, Rick Zamora, Onur Yilmaz, et al. 2020. Merlin: a gpu accelerated recommendation framework. In Proceedings of IRS."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00323"},{"key":"e_1_3_2_1_25_1","volume-title":"Lance: Efficient Random Access in Columnar Storage through Adaptive Structural Encodings. arXiv preprint arXiv:2504.15247","author":"Pace Weston","year":"2025","unstructured":"Weston Pace, Chang She, Lei Xu, Will Jones, Albert Lockett, Jun Wang, and Raunak Shah. 2025. Lance: Efficient Random Access in Columnar Storage through Adaptive Structural Encodings. arXiv preprint arXiv:2504.15247 (2025)."},{"key":"e_1_3_2_1_26_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703","author":"Paszke A","year":"2019","unstructured":"A Paszke. 2019. Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703 (2019)."},{"key":"e_1_3_2_1_27_1","unstructured":"Pinterest. 2023. Manas HNSW Realtime: Powering Realtime Embedding-Based Retrieval. https:\/\/medium.com\/pinterest-engineering\/manas-hnsw-realtime-powering-realtime-embedding-based-retrieval-dc71dfd6afdd."},{"key":"e_1_3_2_1_28_1","volume-title":"Retrieved","year":"2022","unstructured":"Rapidsai. 2022. Rapidsai\/raft: RAFT contains fundamental widely-used algorithms and primitives for data science, Graph and machine learning. Retrieved Oct 21, 2025 from https:\/\/github.com\/rapidsai\/raft"},{"key":"e_1_3_2_1_29_1","first-page":"4d","volume-title":"AWS","unstructured":"vantage. 2025. AWS p4d.24xlarge Instance Cost. https:\/\/instances.vantage.sh\/aws\/ec2\/p4d.24xlarge?region=us-west-2."},{"key":"e_1_3_2_1_30_1","unstructured":"vantage. 2025. AWS r6i.8xlarge Instance Cost. https:\/\/instances.vantage.sh\/aws\/ec2\/r6i.8xlarge?region=us-west-1."},{"key":"e_1_3_2_1_31_1","unstructured":"vantage. 2025. AWS x2idn.24xlarge Instance Cost. https:\/\/instances.vantage.sh\/aws\/ec2\/x2idn.24xlarge?region=us-west-1."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219869"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457550"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346996"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330739"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599897"},{"key":"e_1_3_2_1_37_1","unstructured":"Jiaqi Zhai Lucy Liao Xing Liu Yueming Wang Rui Li Xuan Cao Leon Gao Zhaojie Gong Fangda Gu Michael He et al. 2024. Actions speak louder than words: Trillion-parameter sequential transducers for generative recommendations. arXiv preprint arXiv:2402.17152 (2024)."},{"key":"e_1_3_2_1_38_1","volume-title":"Wukong: Towards a scaling law for large-scale recommendation. arXiv preprint arXiv:2403.02545","author":"Zhang Buyun","year":"2024","unstructured":"Buyun Zhang, Liang Luo, Yuxin Chen, Jade Nie, Xi Liu, Daifeng Guo, Yanli Zhao, Shen Li, Yuchen Hao, Yantao Yao, et al. 2024. Wukong: Towards a scaling law for large-scale recommendation. arXiv preprint arXiv:2403.02545 (2024)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737255"},{"key":"e_1_3_2_1_40_1","volume-title":"Embedding in recommender systems: A survey. arXiv preprint arXiv:2310.18608","author":"Zhao Xiangyu","year":"2023","unstructured":"Xiangyu Zhao, Maolin Wang, Xinjian Zhao, Jiansheng Li, Shucheng Zhou, Dawei Yin, Qing Li, Jiliang Tang, and Ruocheng Guo. 2023. Embedding in recommender systems: A survey. arXiv preprint arXiv:2310.18608 (2023)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:32:46Z","timestamp":1784136766000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809755"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":41,"alternative-id":["10.1145\/3805712.3809755","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809755","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}