PRETZEL: Opening the Black Box of Machine Learning Prediction Serving Systems
Machine Learning models are often composed of pipelines of transformations. While this design allows to efficiently execute single model components at training time, prediction serving has different requirements such as low latency, high throughput and graceful performance degradation under heavy lo...
Saved in:
Main Authors | , , , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
14.10.2018
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Machine Learning models are often composed of pipelines of transformations.
While this design allows to efficiently execute single model components at
training time, prediction serving has different requirements such as low
latency, high throughput and graceful performance degradation under heavy load.
Current prediction serving systems consider models as black boxes, whereby
prediction-time-specific optimizations are ignored in favor of ease of
deployment. In this paper, we present PRETZEL, a prediction serving system
introducing a novel white box architecture enabling both end-to-end and
multi-model optimizations. Using production-like model pipelines, our
experiments show that PRETZEL is able to introduce performance improvements
over different dimensions; compared to state-of-the-art approaches PRETZEL is
on average able to reduce 99th percentile latency by 5.5x while reducing memory
footprint by 25x, and increasing throughput by 4.7x. |
---|---|
DOI: | 10.48550/arxiv.1810.06115 |