We've just released new improvements!

Nvidia G5 (A10G) instances on AWS available

  • Kick off a model package request to see how these instances perform on your model!

New tutorial available on using a BERT model for Natural Language Processing tasks

  • We released a new tutorial on how to accelerate a BERT model for a Natural Language Processing task using OctoML’s optimized ONNX engine.

  • Our full list of tutorials is available here.

  • Please contact us via chat or email if you’d like to request tutorials on other topics!

Did this answer your question?