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

llama : only use default buffer types for the KV cache #10358

Merged
merged 1 commit into from
Nov 17, 2024
Merged

Conversation

slaren
Copy link
Collaborator

@slaren slaren commented Nov 17, 2024

It's not easy to test a single op to determine KV buffer compatibility, so instead we use only the device default buffer type for the KV.

Fixes #10351

@github-actions github-actions bot added the ggml changes relating to the ggml tensor library for machine learning label Nov 17, 2024
@slaren slaren merged commit be5cacc into master Nov 17, 2024
54 checks passed
@slaren slaren deleted the sl/fix-kv-buft branch November 17, 2024 11:25
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Nov 18, 2024
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
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Bug: rwkv and mamba models cannot be used with -ngl 0 after CPU backend refactor
2 participants