Skip to content

Make prompt cache saving and restoring MLA aware #497

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 6 commits into from
Jun 6, 2025

Conversation

saood06
Copy link
Collaborator

@saood06 saood06 commented Jun 6, 2025

Tested working with both a long (3.5K tokens) and a short prompt with both matching up in size with what is expected. The long prompt was also tested on a fresh launch of the server to ensure it gave output consistent with what would be expected given the information in the prompt.

Closes #436

@saood06 saood06 requested a review from ikawrakow June 6, 2025 08:33
@ikawrakow ikawrakow merged commit ffd87f2 into main Jun 6, 2025
Thireus added a commit to Thireus/ik_llama.cpp that referenced this pull request Jun 6, 2025
Make prompt cache saving and restoring MLA aware (ikawrakow#497)
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.

Bug: Saving the prompt cache causes Segfault
3 participants