Replies: 1 comment
-
I see it's been already discussed. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I keep seeing posts about powerinfer https://github.com/SJTU-IPADS/PowerInfer giving an 11x speedup.
From what I understand it keeps often used terms in GPU memory and less often used terms in CPU memory.
It looks like it needs to rework models in order to accomplish this.
Any thoughts?
11x speedup!!!
Beta Was this translation helpful? Give feedback.
All reactions