Skip to content

CTranslate2 1.0.1

Compare
Choose a tag to compare
@guillaumekln guillaumekln released this 08 Oct 11:46
· 1574 commits to master since this release

CTranslate2 1.0.1

Fixes and improvements

  • Fix loading of newer OpenNMT-py models
  • Promote FP16 to FP32 in model converter scripts
  • Improve INT8 performance on CPU and GPU
  • Improve performance on GPU by fusing the layer normalization operation x * gamma + beta
  • Enable INT8 and INT16 computation on all platforms with Intel MKL 2019.5 and above