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 : bump max layers from 512 to 1024 #9910

Open
wants to merge 1 commit into
base: master
Choose a base branch
from

Conversation

nicoboss
Copy link
Contributor

This fixes #9909

This increases LLAMA_MAX_LAYERS from 512 to 1024 making it possible for llama.cpp to load models with more than 512 layers.
I further incremented LLAMA_SESSION_VERSION as it was done back when LLAMA_MAX_LAYERS got increased to 512 in #8530

Thanks to this change I was able to run FatLlama-1.7T-Instruct which prior to this change caused llama.cpp to crash.

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: LLAMA_MAX_LAYERS must be increased to run FatLlama 1.7T
1 participant