Open arjunsuresh opened 1 year ago
I believe many of our CM automation recipes can plug in models and data sets locally, right?
yes Grigori. But this issue is for running MLPerf inference on systems without internet and there even pip install will fail. So, we probably need to do the preparation on a host machine and then do the final run on the target. Nvidia does this for their Jetson Orin submission and not having internet improves the power efficiency :)
Some edge systems may not be connected to internet and we need a way to run mlperf inference benchmarks on them using CM.