Skip to content

scale.bythebay.io: Stepan Pushkarev, Multi Runtime Serving Pipelines

FunctionalTV10.9K subscribers

233 views

About this video

Advanced · Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video

Stepan Pushkarev explains how to serve multiple machine learning models across different runtimes in production environments. The talk covers deployment strategies and runtime abstraction techniques.

Video by FunctionalTV, played through YouTube's embedded player.