Replies: 1 comment
-
Relay is computational graph level IR so you don't need it if you just want to write an operator. |
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.
-
TVM seems to introduce several IRs: Relay, Tensor Expression and Tensor IR. If I need to implement a custom op in my model, which IR should I use?
Beta Was this translation helpful? Give feedback.
All reactions