Parallel inference in DGL

Hello! I’m developing software that measures the performance of inferences on different frameworks. And actually I have a question: are there any tools for parallelism specifically inference, not for training?

For example, in PyTorch it is possible to run multiple threads on the GPU in image inference.

Perhaps there are some other parallelism tools in DGL? Only interested in inference, not training

Which PyTorch tool are you using for inference? You may be able to use it with DGL too.

This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.