Replies: 1 comment 1 reply
-
I think the biggest barrier here is that Coral TPUs only support TensorFlow Lite models, whereas our inference is currently built on llama.cpp which has its own format. |
Beta Was this translation helpful? Give feedback.
1 reply
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.
Uh oh!
There was an error while loading. Please reload this page.
-
can a coral tpu be used to help accelerate processing?
something like this:
https://coral.ai/products/m2-accelerator-dual-edgetpu/
Beta Was this translation helpful? Give feedback.
All reactions