Thanks, @reminisce. We're prepping a blog post for release after upstreaming detailing the inference performance improvements that come from nGraph. In fact, the ideas are similar to https://mxnet.incubator.apache.org/tutorials/tensorrt/inference_with_trt.html, would adding that blog to the module tutorials make sense?
[ Full content available at: https://github.com/apache/incubator-mxnet/pull/12502 ] This message was relayed via gitbox.apache.org for [email protected]
