|
Is there a way to disable llama.vim by default so that it doesn't make any API calls until I execute I use it with llama-swap in front of llama-server, and every time I edit a file it causes llama-swap to load the model I have configured to use with llama.vim, but often I just want to quickly edit a file (without any need for llama.vim completion) and not change the model I currently have loaded in my GPU. |
Answered by
ggerganov
Sep 15, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Set
enable_at_startupto false: #80