How does model serving scale after post-training?
One participant says they see value in managing all the machine-learning infrastructure for users—and that their team is working toward it.
TLDR
A user asked what happens after post-training and whether model serving can scale to “infinite users.” In reply, another participant said the original thinking was that many providers already offer production inference. They said their team is working toward managing all the machine-learning infrastructure for users, rather than leaving them “on your own” at some point.
Combined views
805
3 Sources, first seen ago
