AWS Inferentia Support? #2789
MoonKraken
started this conversation in
Ideas
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Are there any plans for AWS Inferentia support? They seem to provide a much better GPU memory / cost ratio, allowing larger models to be run more affordably.
I'm not aware of what adding this would entail or whether it's even feasible, just wondering whether it's been considered.
Beta Was this translation helpful? Give feedback.
All reactions