Prediction Serving System
A Prediction Serving System is a online system that can support online prediction requests.
- Context:
- It can be developed using a Prediction Serving Framework, such as TensorFlow Serving, or Clipper.
- Example(s):
- Counter-Example(s):
- See: Controlled Experiment System, Clipper.
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. ...
- 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
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: ... Machine learning is being deployed in a growing number of applications which demand real-time, accurate, and robust predictions under heavy query load. However, most machine learning frameworks and systems only address model training and not deployment. ...