{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:44:57Z","timestamp":1782798297131,"version":"3.54.5"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,18]]},"DOI":"10.1109\/infocom59046.2026.11571238","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:38:15Z","timestamp":1782761895000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["AdaptPipe: Mitigating Runtime Bubbles via Granularity-Adaptive Scheduling under Memory Constraints"],"prefix":"10.1109","author":[{"given":"Yumeng","family":"Cui","sequence":"first","affiliation":[{"name":"Tsinghua University,INSC, BNRist,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jessie Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,INSC, BNRist,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Najila","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University,INSC, BNRist,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Deng","sequence":"additional","affiliation":[{"name":"China Unicom,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Du","sequence":"additional","affiliation":[{"name":"China Unicom,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuxuan","family":"Zeng","sequence":"additional","affiliation":[{"name":"China Unicom,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jilong","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,INSC, BNRist,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref4","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref5","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref6","first-page":"463","article-title":"A unified architecture for accelerating distributed DNN training in heterogeneous GPU\/CPU clusters","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2020)","author":"Jiang"},{"key":"ref7","article-title":"Scaling distributed machine learning with the parameter server","volume-title":"Proceedings of the Operating Systems Design and Implementation (OSDI 2014)","author":"Andersen"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378499"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ipdpsw63119.2024.00208"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.134"},{"key":"ref11","first-page":"1","article-title":"Beyond data and model parallelism for deep neural networks","volume-title":"Proceedings of Machine Learning and Systems","volume":"1","author":"Jia"},{"key":"ref12","article-title":"One weird trick for parallelizing convolutional neural networks","author":"Krizhevsky","year":"2014"},{"key":"ref13","article-title":"Mesh-tensorflow: Deep learning for supercomputers","volume":"31","author":"Shazeer","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441593"},{"key":"ref15","first-page":"1","article-title":"Efficient large-scale language model training on gpu clusters using megatron-lm","volume-title":"Proceedings of the international conference for high performance computing, networking, storage and analysis","author":"Narayanan"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1476"},{"key":"ref17","first-page":"1","article-title":"Hanayo: Harnessing wave-like pipeline parallelism for enhanced large model training efficiency","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Liu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476145"},{"key":"ref19","first-page":"48","article-title":"Breadth-first pipeline parallelism","volume-title":"Proceedings of Machine Learning and Systems","volume":"5","author":"Lamy-Poirier"},{"key":"ref20","article-title":"Zero bubble (almost) pipeline parallelism","volume-title":"The Twelfth International Conference on Learning Representations","author":"Qi"},{"key":"ref21","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024"},{"key":"ref22","first-page":"526","article-title":"On optimizing the communication of model parallelism","volume-title":"Proceedings of Machine Learning and Systems","volume":"5","author":"Zhuang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3717469"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3710848.3710869"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519563"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1811.06965"},{"key":"ref27","article-title":"Pipedream: Fast and efficient pipeline parallel dnn training","author":"Harlap","year":"2018"},{"key":"ref28","first-page":"269","article-title":"Pipemare: Asynchronous pipeline parallel dnn training","volume-title":"Proceedings of Machine Learning and Systems","volume":"3","author":"Yang"},{"key":"ref29","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.890"},{"key":"ref31","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019"},{"key":"ref32","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"}],"event":{"name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","location":"Tokyo, Japan","start":{"date-parts":[[2026,5,18]]},"end":{"date-parts":[[2026,5,21]]}},"container-title":["IEEE INFOCOM 2026 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11571071\/11571169\/11571238.pdf?arnumber=11571238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:17:08Z","timestamp":1782796628000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11571238\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/infocom59046.2026.11571238","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}