Skip to content

v0.5.1

Compare
Choose a tag to compare
@matteo-grella matteo-grella released this 07 Mar 18:41
· 883 commits to main since this release

Added

Changed

  • Improve nlp.transformer.generation algorithms:
    • optimize Generator.getTopKScoredTokens().
    • optimize Generator.updateTokensScores().
  • Simplify mat32.Dense.Mul when doing Matrix-Vector multiplication.
  • Refactor math32 functions using chewxy/math32 functions.
  • Improve ag.Graph efficiency:
    • Use pre-computed cache doing ag.Graph.groupNodesByHeight().
    • Use sync.pool to reduce allocations of graph's operators.

Fixed

  • Fix past key-values usage on self-attention and cross-attention