Troed Sångberg

Yet another itch scratched: Opencode plugin for use with llama-server to show both when and how fast prefill/prompt processing and token generation happens.

source: https://codeberg.org/troed/oc-ls-stats

installation: opencode plugin @troed/oc-ls-stats@latest --global

#OpenCode #llamacpp

oc-ls-stats

Opencode plugin to display the tokens per seconds currently generated by llama-server, as well as whether it's doing prompt processing or token generation.

Codeberg.org
Jun 14 at 1:59pmWeb