Support Inference on the third-party engines, TensorRT for example. Use subgraph to support all the Fluid models.
We will fully support any model on TensorRT with subgraph engine design and enable its full features.
With Anakin, we will support the full graph, and subgraph feature if their C++ parser is valid.
List view
0 issues of 0 selected
There are no open issues in this milestone
Add issues to milestones to help organize your work for a particular release or project. Find and add issues with no milestones in this repo.