Skip to content

Conversation

@IMbackK
Copy link
Collaborator

@IMbackK IMbackK commented Feb 19, 2025

this adds a workaround for #11949. Once ROCm/clr#138 is fixed this will add a memory leak, i promise to restrict the workaround to versions with the bug as soon as a release fixing the underlying issue is released.

@github-actions github-actions bot added Nvidia GPU Issues specific to Nvidia GPUs ggml changes relating to the ggml tensor library for machine learning labels Feb 19, 2025
@IMbackK
Copy link
Collaborator Author

IMbackK commented Feb 19, 2025

after some additional discussion in ROCm/clr#138 it seams to me like the lamacpp code and the cuda runtime is also broken and its a bit unclear how this is supposed to work in the first place as the ownership of the memory is quite unclear given the available documentation.

@IMbackK IMbackK closed this Mar 2, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants