Open ma7dev opened 2 years ago
TorchServe seems to be a way to handle serving multiple models and having an access point to them. I thought it had a way to quantize the model like TensorFlowLite in order to reduce the model size and increase the speed of computation.
!anime
: AnimeGANv2!arcane
: ArcaneGAN!art
: BlendGAN!pixel
: Pyxelate!paint
: GLIDE!en
: English!ar
: Arabic!wolf
: Arabic Poetry!chat
: English!klaam
: Klaam!tts
: English Female Voice TTSTorchServe to reduce computation time and usage