| Ray: A distributed framework for emerging {AI} applications P Moritz, R Nishihara, S Wang, A Tumanov, R Liaw, E Liang, M Elibol, ... 13th USENIX symposium on operating systems design and implementation (OSDI …, 2018 | 1625 | 2018 |
| Heterogeneity and dynamicity of clouds at scale: Google trace analysis C Reiss, A Tumanov, GR Ganger, RH Katz, MA Kozuch Proceedings of the third ACM symposium on cloud computing, 1-13, 2012 | 1392 | 2012 |
| Serverless computing: One step forward, two steps back JM Hellerstein, J Faleiro, JE Gonzalez, J Schleier-Smith, V Sreekanti, ... arXiv preprint arXiv:1812.03651, 2018 | 553 | 2018 |
| Cloudburst: Stateful functions-as-a-service V Sreekanti, C Wu, XC Lin, J Schleier-Smith, JM Faleiro, JE Gonzalez, ... arXiv preprint arXiv:2001.04592, 2020 | 351 | 2020 |
| Morpheus: Towards automated {SLOs} for enterprise clusters SA Jyothi, C Curino, I Menache, SM Narayanamurthy, A Tumanov, ... 12th USENIX symposium on operating systems design and implementation (OSDI …, 2016 | 341 | 2016 |
| Towards understanding heterogeneous clouds at scale: Google trace analysis C Reiss, AT CMU, GRG CMU, RH Katz, MA Kozuch | 266 | 2012 |
| Cirrus: A serverless framework for end-to-end ml workflows J Carreira, P Fonseca, A Tumanov, A Zhang, R Katz Proceedings of the ACM Symposium on Cloud Computing, 13-24, 2019 | 263 | 2019 |
| TetriSched: global rescheduling with adaptive plan-ahead in dynamic heterogeneous clusters A Tumanov, T Zhu, JW Park, MA Kozuch, M Harchol-Balter, GR Ganger Proceedings of the Eleventh European Conference on Computer Systems, 1-16, 2016 | 252 | 2016 |
| InferLine: latency-aware provisioning and scaling for prediction serving pipelines D Crankshaw, GE Sela, X Mo, C Zumar, I Stoica, J Gonzalez, A Tumanov Proceedings of the 11th ACM Symposium on Cloud Computing, 477-491, 2020 | 149 | 2020 |
| Idk cascades: Fast deep learning by learning not to overthink X Wang, Y Luo, D Crankshaw, A Tumanov, F Yu, JE Gonzalez arXiv preprint arXiv:1706.00885, 2017 | 142 | 2017 |
| Prioritymeister: Tail latency qos for shared networked storage T Zhu, A Tumanov, MA Kozuch, M Harchol-Balter, GR Ganger Proceedings of the ACM Symposium on Cloud Computing, 1-14, 2014 | 135 | 2014 |
| Taming {Throughput-Latency} tradeoff in {LLM} inference with {Sarathi-Serve} A Agrawal, N Kedia, A Panwar, J Mohan, N Kwatra, B Gulavani, ... 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI …, 2024 | 128 | 2024 |
| Proteus: agile ml elasticity through tiered reliability in dynamic resource markets A Harlap, A Tumanov, A Chung, GR Ganger, PB Gibbons Proceedings of the Twelfth European Conference on Computer Systems, 589-604, 2017 | 121 | 2017 |
| Holmes: health online model ensemble serving for deep learning models in intensive care units S Hong, Y Xu, A Khare, S Priambada, K Maher, A Aljiffry, J Sun, ... Proceedings of the 26th ACM SIGKDD International Conference on Knowledge …, 2020 | 110 | 2020 |
| 3sigma: distribution-based cluster scheduling for runtime uncertainty JW Park, A Tumanov, A Jiang, MA Kozuch, GR Ganger Proceedings of the Thirteenth EuroSys Conference, 1-17, 2018 | 98 | 2018 |
| Dynamic space-time scheduling for gpu inference P Jain, X Mo, A Jain, H Subbaraj, RS Durrani, A Tumanov, J Gonzalez, ... arXiv preprint arXiv:1901.00041, 2018 | 95 | 2018 |
| A case for serverless machine learning J Carreira, P Fonseca, A Tumanov, A Zhang, R Katz Workshop on Systems for ML and Open Source Software at NeurIPS 2018, 2018 | 95 | 2018 |
| Real-time machine learning: The missing pieces R Nishihara, P Moritz, S Wang, A Tumanov, W Paul, J Schleier-Smith, ... Proceedings of the 16th workshop on hot topics in operating systems, 106-110, 2017 | 88 | 2017 |
| Kaleidoscope: cloud micro-elasticity via vm state coloring R Bryant, A Tumanov, O Irzak, A Scannell, K Joshi, M Hiltunen, ... Proceedings of the sixth conference on Computer systems, 273-286, 2011 | 79 | 2011 |
| Tributary: spot-dancing for elastic services with latency {SLOs} A Harlap, A Chung, A Tumanov, GR Ganger, PB Gibbons 2018 USENIX Annual Technical Conference (USENIX ATC 18), 1-14, 2018 | 73 | 2018 |
Greg GangerJatras Professor, Carnegie Mellon UniversityVerified email at ece.cmu.edu
