Triton Inference Server Feature Requests

Triton Inference Server Feature Requests

Add support for dynamic PyTorch models (no torchscript needed)

Want to be able to run PyTorch models without having to convert to Torchscript.

May be useful for certain customers who have a mix of production models and models not in production and in PyTorch. Would be useful to have both run in the same TRTIS environment.

  • Guest
  • Nov 21 2019
  • Attach files