Caenorst commented on issue #14040: Reformat of TensorRT to use subgraph API URL: https://github.com/apache/incubator-mxnet/pull/14040#issuecomment-461536280 @reminisce Yes, what I mean is that if weights for TensorRT node are on CPU while the rest of the graph is on GPU, it would be less of a problem. Also an argument for onnx-tensorrt is that there is more Ops supported with plugins implemented (slice, some activation, resize with nearest interpolation...)
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
