Skip to content

Comments

CUDA 12 support for the Conda Runtime#680

Merged
LostRuins merged 2 commits intoLostRuins:concedo_experimentalfrom
henk717:concedo_experimental
Feb 16, 2024
Merged

CUDA 12 support for the Conda Runtime#680
LostRuins merged 2 commits intoLostRuins:concedo_experimentalfrom
henk717:concedo_experimental

Conversation

@henk717
Copy link
Collaborator

@henk717 henk717 commented Feb 14, 2024

This PR removes unneeded version definitions and an unneeded dependency. See my comments on the individual commits for more detailed explanations.

This dependency is something that is used to build libcudart which we are also already targeting. The individual file is no longer being distributed with the CUDA12 conda devkit, so we can no longer target it directly. But because all its functionality is inside libcudart we also don't need it.

This commit removes the inclusion so that Koboldcpp can be compiled with CUDA12 as distributed by conda. I have tested this on the 1.57 release on CUDA11.5 and CUDA12.1.
The package versions are already controlled by the label, we don't need to define it multiple times for it to work correctly. Removing the separate definitions allows people to easily change which version of CUDA they wish for their system.
@LostRuins
Copy link
Owner

looks good, any performance or compatibility impacts?

@LostRuins
Copy link
Owner

nvm lets just merge

@LostRuins LostRuins merged commit 01b7daf into LostRuins:concedo_experimental Feb 16, 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