MArk: Exploiting Cloud Services for Cost-Effective, SLO-Aware Machine Learning Inference Serving
By Chengliang Zhang, Minchen Yu, Wei Wang, Feng Yan. USENIX Annual Technical Conference, 2019
359 citations recorded by the source corpus.
View Paper: https://www.semanticscholar.org/paper/5772d98f4b336d650cb9b9de6e27095002fb218f
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Hong Zhang
- Yupeng Tang
- Anurag Khandelwal
- P. Patel
- Ion Stoica
- Arpan Gujarati
- Esha Choukse
- Reza Karimi
Citations in the corpus
- Splitwise: Efficient Generative LLM Inference Using Phase Splitting (2023, background): “Prior work has studied heterogeneous scheduling for a variety of interactive services [65], [68], [83].”
- SHEPHERD: Serving DNNs in the Wild (2023, background): “rival patterns within each one-minute interval: (1) a Poisson process to model stable workloads, similar to [10] (“MAFstable”), and (2) a more bursty Markov-modulated Poisson process (MMPP) similar to [9] (“MAF-bursty”).”
- Serving DNNs like Clockwork: Performance Predictability from the Bottom Up (2020, background): “Several other projects investigate model serving in virtualized cloud environments and on serverless platforms, where predictability is in the hands of the cloud provider [10, 44, 77].”