Go to OctoML
All Collections
Frequently Asked Questions
Frequently Asked Questions
Where is the Developer Documentation?
What hardware targets are supported for packaging and acceleration?
Which ML frameworks, libraries, and versions are supported?
What model architectures are supported?
How do input names, shapes, and dimensions work in the OctoML Platform?
What are the differences between the TVM Techniques Auto-scheduling and AutoTVM?
Using OctoML Platform with ONNX-RT TVM Execution Provider
How can I use TVM to further improve model performance?
How do I use a Dockerfile to access the Platform from an isolated environment?