Does triton inference server do model loading optimization #5984
Unanswered
sfc-gh-zhwang
asked this question in
Q&A
Replies: 0 comments
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.
-
When loading onnx/pytorch/fastertransformer model, does triton load the model from disk to cpu/memory and to gpu or triton directly load the model to gpu memory?
Beta Was this translation helpful? Give feedback.
All reactions