Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

CUDA: use min compute capability of GPUs actually used #2506

Merged
merged 1 commit into from
Aug 4, 2023

Conversation

cebtenzzre
Copy link
Collaborator

These are my currently installed GPUs:

ggml_init_cublas: found 2 CUDA devices:
  Device 0: Tesla P40, compute capability 6.1
  Device 1: NVIDIA GeForce GTX 970, compute capability 5.2

I found that if I disabled my GTX 970 using --tensor-split 1,0, I still couldn't use the full compute capability of my Telsa P40. With this change, I am able to benefit from the --mul-mat-q option without physically removing the GTX 970 from my PC, which my displays are connected to.

Copy link
Collaborator

@JohannesGaessler JohannesGaessler left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Alternatively you could have used the environmental variable CUDA_VISIBLE_DEVICES to hide the 970.

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