@pi-plugins/speed0.1.9
Inference speed extension for pi-agent: tokens/sec and time to first token.
Untested on omp
This is a pi package. No one has reported whether it works on omp yet. If you try it, add your result below.
Reports 0
No reports yet.
Readme
@pi-plugins/speed
See estimated generation speed and time to first token in pi, above the editor.
Install
pi install npm:@pi-plugins/speed
To try it for one session without changing your settings:
pi -e npm:@pi-plugins/speed
Usage
Send a prompt. The status line updates automatically as measurements become available:
~48 tok/s · TTFT 920ms
~48 tok/smeans approximately 48 tokens per second, based on recent responses from the selected model.TTFTmeans time to first token: how long the model takes to start responding.
There are no commands or settings. Use elapsed to track the full
agent run, including tool calls.