30 releases 30 tags

RSS feed

• v0.2.27 ed02cf4b93

  Compare

  0.2.27 Stable

  marella released this 2023-09-10 11:13:26 -04:00 | 0 commits to main since this release

  Changes

  • Skip evaluating tokens that are evaluated in the past. This can significantly speed up prompt processing in chat applications that prepend previous messages to prompt.
  • Deprecate LLM.reset() method. Use high-level API instead.
  • Add support for batching and beam search to 🤗 model.
  • Remove universal binary option when building for AVX2, AVX on macOS.