{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:58:30Z","timestamp":1782835110795,"version":"3.54.5"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Major Program of Guangdong Basic and Applied Research","award":["2019B030302002"],"award-info":[{"award-number":["2019B030302002"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62461146204"],"award-info":[{"award-number":["62461146204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62332021"],"award-info":[{"award-number":["62332021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402534"],"award-info":[{"award-number":["62402534"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515110117"],"award-info":[{"award-number":["2023A1515110117"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Pazhou Lab","award":["PZL2023KF0001"],"award-info":[{"award-number":["PZL2023KF0001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tpds.2024.3521582","type":"journal-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:39:04Z","timestamp":1735155544000},"page":"717-730","source":"Crossref","is-referenced-by-count":3,"title":["Co-Designing Transformer Architectures for Distributed Inference With Low Communication"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4707-9492","authenticated-orcid":false,"given":"Jiangsu","family":"Du","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6551-9274","authenticated-orcid":false,"given":"Yuanxin","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8867-0655","authenticated-orcid":false,"given":"Shengyuan","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1417-3012","authenticated-orcid":false,"given":"Jiazhi","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9943-6020","authenticated-orcid":false,"given":"Xu","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5582-1031","authenticated-orcid":false,"given":"Dan","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5315-3375","authenticated-orcid":false,"given":"Yutong","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"issue":"8","key":"ref3","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref4","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1176"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT56998.2023.10307046"},{"key":"ref7","article-title":"Transformer-based deep learning models for the sentiment analysis of social media data","volume":"14","author":"Kokab","year":"2022","journal-title":"Array"},{"key":"ref8","first-page":"19","article-title":"Communication efficient distributed machine learning with the parameter server","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1811.06965"},{"key":"ref10","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.134"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3041474"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621342"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.71"},{"key":"ref20","first-page":"117","article-title":"Taming $\\lbrace${Throughput-Latency $\\rbrace$} tradeoff in $\\lbrace${ LLM$\\rbrace$} inference with $\\lbrace${Sarathi-Serve$\\rbrace$}","volume-title":"Proc. 18th USENIX Symp. Operating Syst. Des. Implementation","author":"Agrawal"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ipdpsw63119.2024.00208"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref23","article-title":"Sglang: Efficient execution of structured language model programs","author":"Zheng","year":"2023"},{"key":"ref25","first-page":"606","article-title":"Efficiently scaling transformer inference","volume-title":"Proc. Mach. Learn. Syst.","volume":"5","author":"Pope","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2858384"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3581791.3596870"},{"key":"ref28","article-title":"ZeRO++: Extremely efficient collective communication for giant model training","author":"Wang","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483278"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507778"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638466"},{"key":"ref32","first-page":"526","article-title":"On optimizing the communication of model parallelism","volume-title":"Proc. Mach. Learn. Syst.","volume":"5","author":"Zhuang","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695964"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10279202"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430898"},{"key":"ref36","first-page":"162","article-title":"HeteGen: Efficient heterogeneous parallel inference for large language models on resource-constrained devices","volume-title":"Proc. Mach. Learn. Syst.","volume":"6","author":"Xuanlei","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00051"},{"key":"ref38","first-page":"193","article-title":"$\\lbrace${DistServe$\\rbrace$}: Disaggregating prefill and decoding for goodput-optimized large language model serving","volume-title":"Proc. 18th USENIX Symp. Operating Syst. Des. Implementation","author":"Zhong"},{"key":"ref39","first-page":"521","article-title":"ORCA: A distributed serving system for $\\lbrace${Transformer-Based$\\rbrace$} generative models","volume-title":"Proc. 16th USENIX Symp. Operating Syst. Des. Implementation","author":"Yu"},{"key":"ref40","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with IO-awareness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dao"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532372"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441578"},{"key":"ref43","article-title":"FP8 versus int8 for efficient deep learning inference","author":"van Baalen","year":"2023"},{"key":"ref44","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022"},{"key":"ref45","first-page":"22137","article-title":"Deja vu: Contextual sparsity for efficient LLMs at inference time","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/10908515\/10812976.pdf?arnumber=10812976","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T18:52:34Z","timestamp":1741114354000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10812976\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":42,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2024.3521582","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}