tabby/python/tabby-loadtest
Meng Zhang edd33a326d
feat(loadtest): add loadtest tools (#906)
* add loadtest tools

* update

* [autofix.ci] apply automated fixes

* add readme

* cleanup legacy loadtest

---------

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2023-11-28 14:34:00 +08:00
..
loadtest.js feat(loadtest): add loadtest tools (#906) 2023-11-28 14:34:00 +08:00
README.md feat(loadtest): add loadtest tools (#906) 2023-11-28 14:34:00 +08:00
record.csv feat(loadtest): add loadtest tools (#906) 2023-11-28 14:34:00 +08:00
run.sh feat(loadtest): add loadtest tools (#906) 2023-11-28 14:34:00 +08:00
server.py feat(loadtest): add loadtest tools (#906) 2023-11-28 14:34:00 +08:00

Run loadtest with tabby on modal GPUs

Steps:

  1. Adjust TABBY_API_HOST in run.sh to match your modal deployment url.
  2. Add models you're interested in to benchmark at end of run.sh
  3. Run run.sh, output will be appended to record.csv