Skip to content

Speed up inference time. #5208

Answered by glenn-jocher
danielsoy asked this question in Q&A
Discussion options

You must be logged in to vote

@danielsoy I think almost any usable GPU will run faster than CPU, i.e. an NVIDIA 1080 Ti would be an easy place to start if you are on a budget.

Even the K80, which is Colab's slowest GPU from several years ago runs default inference in about 30 ms:

Replies: 1 comment 1 reply

Comment options

You must be logged in to vote
1 reply
@danielsoy
Comment options

Answer selected by danielsoy
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants