Clipper Prediction Serving Framework

A Clipper Prediction Serving Framework is a prediction serving framework.

• See: TensorFlow Serving, Prediction Serving System.

---

---

References

2018

• https://github.com/ucbrise/clipper
  • QUOTE: Clipper is a prediction serving system that sits between user-facing applications and a wide range of commonly used machine learning models and frameworks. Learn more about Clipper and view documentation at our website http://clipper.ai. …

2017

• (Crankshaw et al., 2017) ⇒ Daniel Crankshaw, Xin Wang, Giulio Zhou, Michael J. Franklin, Joseph E. Gonzalez, and Ion Stoica. (2017). “Clipper: A Low-latency Online Prediction Serving System.” In: Proceedings of the 14th USENIX Conference on Networked Systems Design and Implementation. ISBN:978-1-931971-37-9
  • QUOTE: ... In this paper, we introduce Clipper, a general-purpose low-latency prediction serving system. Interposing between end-user applications and a wide range of machine learning frameworks, Clipper introduces a modular architecture to simplify model deployment across frameworks and applications. Furthermore, by introducing caching, batching, and adaptive model selection techniques, Clipper reduces prediction latency and improves prediction throughput, accuracy, and robustness without modifying the underlying machine learning frameworks. We evaluate Clipper on four common machine learning benchmark datasets and demonstrate its ability to meet the latency, accuracy, and throughput demands of online serving applications. Finally, we compare Clipper to the Tensorflow Serving system and demonstrate that we are able to achieve comparable throughput and latency while enabling model composition and online learning to improve accuracy and render more robust predictions.

---