-
Hi @ggerganov @danbev, |
Beta Was this translation helpful? Give feedback.
Answered by
danbev
Oct 30, 2024
Replies: 1 comment 2 replies
-
If you are using ./llama-cli -m models/llama-2-7b.Q4_K_M.gguf --no-warmup --prompt '"Some prompt"' -n 10 --log-disable |
Beta Was this translation helpful? Give feedback.
2 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
The logging of performance timing data is done using
info
log level which is also used in other places, and I'm not aware of any ability to have more fine grained logging. So just logging the perf data and nothing else is not possible at the moment as far as I know. But you can access this information as it is exposed in llama.h and adapt it to your use case.