Skip to content

Conversation

sachaarbonel
Copy link
Contributor

Summary

  • Added bench.js k6 script to examples/server/ for load testing the Whisper HTTP server with concurrent multipart requests.
  • Updated examples/server/README.md with a new section detailing how to run the benchmark, including example commands and environment variable explanations.
  • Ensured the script is configurable and works with standard k6 installations.

Motivation

This addition enables easy benchmarking and stress testing of the Whisper server’s /inference endpoint, helping users and developers validate performance under concurrent load.

@sachaarbonel
Copy link
Contributor Author

@danbev done

@danbev danbev merged commit 78b31ca into ggml-org:master May 22, 2025
53 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants