Skip to content

server: coherent log output for KV cache full #6637

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

Merged
merged 1 commit into from
Apr 12, 2024

Conversation

phymbert
Copy link
Collaborator

Motivation

Some logs are using llama log method instead of the server one.

Changes

  • Use server logs dedicated method when KV Cache is full.

Still some to update during slots context shifting, but it can be done later on.

Concerns

One would want to log also server logs in llama.log but it can be done later.

References

@ggerganov ggerganov merged commit 24ee66e into master Apr 12, 2024
@phymbert phymbert deleted the hp/server/coherent-logs branch April 12, 2024 11:55
tybalex pushed a commit to rubra-ai/tools.cpp that referenced this pull request Apr 17, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants