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

metal : add abort callback #905

Merged
merged 1 commit into from
Aug 7, 2024
Merged

Conversation

conradev
Copy link
Contributor

This allows aborting metal execution midway through a compute graph.

If an abort callback is set, only two command buffers are enqueued at a time and ggml calls the abort callback after every command buffer executions. I am not able to measure a performance difference with an abort callback configured

@conradev
Copy link
Contributor Author

@ggerganov did I put this PR up in the right repo?

I also have a follow-up change to llama.cpp so that llama_decode can be aborted (and return an error code when that happens)

@ggerganov ggerganov merged commit 1f2b80a into ggerganov:master Aug 7, 2024
4 checks passed
@conradev conradev deleted the ck/metal-abort branch August 29, 2024 20:31
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