)
Barista: Enabling Greater Flexibility in Machine Learning Model Deployment
Dec 06, 2023
Room 1A12
Practitioners Stage
- Machine learning (ML) model deployment is one of the most common topics of discussion in the industry. That’s because deployment represents a meeting of two related but dramatically different domains, ML practice and software development.
- The process of deploying ML models can frequently be slow and awkward, and the interfaces through which we turn models into deployed software are something we devote a lot of attention to, looking for ways to save time and reduce risk.
- Barista, the ML Model Serving team’s flagship product, manages lifecycles for all types of models - from Recommendations and Vision to Ads and Search. The Barista interface has evolved dramatically alongside the significant evolution in the scope and range of our ML practice.
- In this talk we’ll walk you through the story of where we started with this interface, where we ended up, and where we intend to keep going.
){kind=logo}
)
){kind=logo}
){kind=logo}
.svg){kind=logo}
){kind=logo}
){kind=logo}
)
.jpg/fit-in/500x500/filters:no_upscale()){kind=logo}
){kind=logo}
){kind=logo}
)
)
){kind=logo}
)
)
-(1).png/fit-in/500x500/filters:no_upscale()){kind=logo}
){kind=logo}
.png/fit-in/500x500/filters:no_upscale()){kind=logo}
){kind=logo}
){kind=logo}
.jpg/fit-in/500x500/filters:no_upscale())
){kind=logo}
.png/fit-in/500x500/filters:no_upscale()){kind=logo}
.png/fit-in/500x500/filters:no_upscale()){kind=logo}
.jpg/fit-in/500x500/filters:no_upscale())
){kind=logo}
.svg)
)
.png/fit-in/500x500/filters:no_upscale()){kind=logo}
){kind=logo}
){kind=logo}
-31-.jpg/fit-in/500x500/filters:no_upscale()){kind=logo}
){kind=logo}
){kind=logo}
-(1).png/fit-in/500x500/filters:no_upscale())
.svg){kind=logo}
.png/fit-in/500x500/filters:no_upscale())
)
)
.png/fit-in/500x500/filters:no_upscale()){kind=logo}
)
.png/fit-in/500x500/filters:no_upscale())
)
){kind=logo}
){kind=logo}
)
){kind=logo}
.png/fit-in/500x500/filters:no_upscale())
){kind=logo}
.jpg/fit-in/500x500/filters:no_upscale())