Skip to content

0.12.6

Compare
Choose a tag to compare
@b4rtaz b4rtaz released this 17 Feb 19:55
· 8 commits to main since this release
415946f
  • Fixed a bug in launch.py that caused the model to be redownloaded even when the user opted not to download it again.
  • The model name is now returned by the API.
  • The quantizeF32toQ80 function now includes an implementation that uses AVX2 instructions.