Skip to content

Conversation

@jiqing-feng
Copy link
Collaborator

IPEX don't need to install cuda lib, will cache it in the dynamic cuda qlinear.
Also fixed too much logs, I suppose we only need to log once because all qlinears in a model should have the same backend.

@jiqing-feng jiqing-feng marked this pull request as draft December 6, 2024 03:06
@Qubitium Qubitium marked this pull request as ready for review December 6, 2024 03:12
@Qubitium Qubitium merged commit e604d07 into ModelCloud:main Dec 6, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants