{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T15:09:14Z","timestamp":1784905754905,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":13,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T00:00:00Z","timestamp":1708387200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,2]]},"DOI":"10.1145\/3627535.3638480","type":"proceedings-article","created":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T14:22:41Z","timestamp":1708438961000},"page":"460-462","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["POSTER: LLM-PQ:Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3376-0607","authenticated-orcid":false,"given":"Juntao","family":"Zhao","sequence":"first","affiliation":[{"name":"The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5902-1611","authenticated-orcid":false,"given":"Borui","family":"Wan","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3144-4398","authenticated-orcid":false,"given":"Chuan","family":"Wu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3989-4358","authenticated-orcid":false,"given":"Yanghua","family":"Peng","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Seattle, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4879-5335","authenticated-orcid":false,"given":"Haibin","family":"Lin","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Seattle, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,2,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00051"},{"key":"e_1_3_2_1_2_1","volume-title":"SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression. ArXiv abs\/2306.03078","author":"Dettmers Tim","year":"2023","unstructured":"Tim Dettmers, Ruslan Svirschevski, Vage Egiazarian, Denis Kuznedelev, Elias Frantar, Saleh Ashkboos, Alexander Borzunov, Torsten Hoefler, and Dan Alistarh. 2023. SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression. ArXiv abs\/2306.03078 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"e_1_3_2_1_4_1","volume-title":"n.d.. Text Generation Inference. https:\/\/github.com\/huggingface\/text-generation-inference. Accessed on","author":"Face Hugging","year":"2023","unstructured":"Hugging Face. n.d.. Text Generation Inference. https:\/\/github.com\/huggingface\/text-generation-inference. Accessed on: July 24, 2023."},{"key":"e_1_3_2_1_5_1","volume-title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers. ArXiv abs\/2210.17323","author":"Frantar Elias","year":"2022","unstructured":"Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. 2022. GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers. ArXiv abs\/2210.17323 (2022)."},{"key":"e_1_3_2_1_6_1","volume-title":"Pipeline Parallelism for Inference on Heterogeneous Edge Computing. ArXiv abs\/2110.14895","author":"Hu Yang","year":"2021","unstructured":"Yang Hu, Connor Imes, Xuanang Zhao, Souvik Kundu, Peter A. Beerel, Stephen P. Crago, and John Paul Walters. 2021. Pipeline Parallelism for Inference on Heterogeneous Edge Computing. ArXiv abs\/2110.14895 (2021)."},{"key":"e_1_3_2_1_7_1","volume-title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration. ArXiv abs\/2306.00978","author":"Lin Ji","year":"2023","unstructured":"Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Xingyu Dang, and Song Han. 2023. AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration. ArXiv abs\/2306.00978 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6pf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Neural Information Processing Systems."},{"key":"e_1_3_2_1_9_1","volume-title":"Fran\u00e7ois Yvon, Matthias Gall\u00e9, et al.","author":"Scao Teven Le","year":"2022","unstructured":"Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ili\u0107, Daniel Hesslow, Roman Castagn\u00e9, Alexandra Sasha Luccioni, Fran\u00e7ois Yvon, Matthias Gall\u00e9, et al. 2022. Bloom: A 176b-parameter open-access multilingual language model. ArXiv abs\/2211.05100 (2022)."},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning.","author":"Sheng Ying","year":"2023","unstructured":"Ying Sheng, Lianmin Zheng, Binhang Yuan, Zhuohan Li, Max Ryabinin, Beidi Chen, Percy Liang, Christopher R\u00e9, Ion Stoica, and Ce Zhang. 2023. FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU. In Proceedings of the 40th International Conference on Machine Learning."},{"key":"e_1_3_2_1_11_1","volume-title":"LLaMA: Open and Efficient Foundation Language Models. ArXiv abs\/2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, Aur'elien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. ArXiv abs\/2302.13971 (2023)."},{"key":"e_1_3_2_1_12_1","volume-title":"Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN Training. ArXiv abs\/2306.01381","author":"Wan Borui","year":"2023","unstructured":"Borui Wan, Jun Zhao, and Chuan Wu. 2023. Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN Training. ArXiv abs\/2306.01381 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer.","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. 2022. OPT: Open Pre-trained Transformer Language Models. ArXiv abs\/2205.01068 (2022)."}],"event":{"name":"PPoPP '24: 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","location":"Edinburgh United Kingdom","acronym":"PPoPP '24","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGPLAN ACM Special Interest Group on Programming Languages"]},"container-title":["Proceedings of the 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627535.3638480","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627535.3638480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:27Z","timestamp":1750182567000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627535.3638480"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,20]]},"references-count":13,"alternative-id":["10.1145\/3627535.3638480","10.1145\/3627535"],"URL":"https:\/\/doi.org\/10.1145\/3627535.3638480","relation":{},"subject":[],"published":{"date-parts":[[2024,2,20]]},"assertion":[{"value":"2024-02-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}