v6.0.1
Summary
This update extends OpenAI-compatible endpoints and enhances server reliability.
Summary of Contributions
- Significantly improve server reliability by avoiding race conditions (@danielholanda)
- Curate list of Hybrid models shared in /models server endpoint (@danielholanda)
- Increase the server's max new tokens default value to 1500 (@jeremyfowers)
- Avoid sudden closure on server startup (@danielholanda )
- Extend OpenAI-compatible endpoints:
stop
parameter and/completions
endpoint (@danielholanda ) - Fix server test name collision, add no-op test, and update black (@jeremyfowers)
Full Changelog: v6.0.0...v6.0.1