GPU and JIT talk
#2286
-
@rusty1s and @lgray I just watched your talk here: https://www.youtube.com/watch?v=4swsvOLzL_A, thanks a lot it was really interesting. Sorry I have a basic question: It is mentioned that the JIT allows you to not depend on CUDA libraries. Can you explain why this is? |
Beta Was this translation helpful? Give feedback.
Answered by
rusty1s
Mar 22, 2021
Replies: 1 comment 1 reply
-
The JIT allows us to be independent of a Python environment, while CUDA is still required in case you want to execute your GNN on a GPU. |
Beta Was this translation helpful? Give feedback.
1 reply
Answer selected by
Padarn
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
The JIT allows us to be independent of a Python environment, while CUDA is still required in case you want to execute your GNN on a GPU.