Zero-Offload + Pytorch Compile 2.0 + ONNXRT #3004
Unanswered
agemagician
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
-
Hello,
Are there any plans to support CPU offload + pytorch compile using onnxrt backend ?
I need to accelerate bloom 176B model using only 2 GPUs but it seems a bit slow.
Beta Was this translation helpful? Give feedback.
All reactions